From c39de951282df9a60ef70664e4378d88006b2670 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:04:53 +0300
Subject: [PATCH 001/637] fs/ntfs3: Improve alternative boot processing
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/super.c | 35 +++++++++++++++++------------------
1 file changed, 17 insertions(+), 18 deletions(-)
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 9153dffde950..09d61c6c90aa 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -866,6 +866,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
u16 fn, ao;
u8 cluster_bits;
u32 boot_off = 0;
+ sector_t boot_block = 0;
const char *hint = "Primary boot";
/* Save original dev_size. Used with alternative boot. */
@@ -873,11 +874,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
sbi->volume.blocks = dev_size >> PAGE_SHIFT;
- bh = ntfs_bread(sb, 0);
+read_boot:
+ bh = ntfs_bread(sb, boot_block);
if (!bh)
- return -EIO;
+ return boot_block ? -EINVAL : -EIO;
-check_boot:
err = -EINVAL;
/* Corrupted image; do not read OOB */
@@ -1108,26 +1109,24 @@ check_boot:
}
out:
- if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
+ brelse(bh);
+
+ if (err == -EINVAL && !boot_block && dev_size0 > PAGE_SHIFT) {
u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
u64 lbo = dev_size0 - sizeof(*boot);
- /*
- * Try alternative boot (last sector)
- */
- brelse(bh);
-
- sb_set_blocksize(sb, block_size);
- bh = ntfs_bread(sb, lbo >> blksize_bits(block_size));
- if (!bh)
- return -EINVAL;
-
+ boot_block = lbo >> blksize_bits(block_size);
boot_off = lbo & (block_size - 1);
- hint = "Alternative boot";
- dev_size = dev_size0; /* restore original size. */
- goto check_boot;
+ if (boot_block && block_size >= boot_off + sizeof(*boot)) {
+ /*
+ * Try alternative boot (last sector)
+ */
+ sb_set_blocksize(sb, block_size);
+ hint = "Alternative boot";
+ dev_size = dev_size0; /* restore original size. */
+ goto read_boot;
+ }
}
- brelse(bh);
return err;
}
From 22457c047ed971f2f2e33be593ddfabd9639a409 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:17:07 +0300
Subject: [PATCH 002/637] fs/ntfs3: Modified fix directory element type
detection
Unfortunately reparse attribute is used for many purposes (several dozens).
It is not possible here to know is this name symlink or not.
To get exactly the type of name we should to open inode (read mft).
getattr for opened file (fstat) correctly returns symlink.
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/dir.c | 30 +++++++++++++++++++++++++-----
1 file changed, 25 insertions(+), 5 deletions(-)
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index ec0566b322d5..22ede4da0450 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
return 0;
}
- /* NTFS: symlinks are "dir + reparse" or "file + reparse" */
- if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
- dt_type = DT_LNK;
- else
- dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+ /*
+ * NTFS: symlinks are "dir + reparse" or "file + reparse"
+ * Unfortunately reparse attribute is used for many purposes (several dozens).
+ * It is not possible here to know is this name symlink or not.
+ * To get exactly the type of name we should to open inode (read mft).
+ * getattr for opened file (fstat) correctly returns symlink.
+ */
+ dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+
+ /*
+ * It is not reliable to detect the type of name using duplicated information
+ * stored in parent directory.
+ * The only correct way to get the type of name - read MFT record and find ATTR_STD.
+ * The code below is not good idea.
+ * It does additional locks/reads just to get the type of name.
+ * Should we use additional mount option to enable branch below?
+ */
+ if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) &&
+ ino != ni->mi.rno) {
+ struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL);
+ if (!IS_ERR_OR_NULL(inode)) {
+ dt_type = fs_umode_to_dtype(inode->i_mode);
+ iput(inode);
+ }
+ }
return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
}
From 6a799c928b78b14999b7705c4cca0f88e297fe96 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:24:33 +0300
Subject: [PATCH 003/637] fs/ntfs3: Improve ntfs_dir_count
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/dir.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 22ede4da0450..726122ecd39b 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -515,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
struct INDEX_HDR *hdr;
const struct ATTR_FILE_NAME *fname;
u32 e_size, off, end;
- u64 vbo = 0;
size_t drs = 0, fles = 0, bit = 0;
- loff_t i_size = ni->vfs_inode.i_size;
struct indx_node *node = NULL;
- u8 index_bits = ni->dir.index_bits;
+ size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits;
if (is_empty)
*is_empty = true;
@@ -563,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
fles += 1;
}
- if (vbo >= i_size)
+ if (bit >= max_indx)
goto out;
err = indx_used_bit(&ni->dir, ni, &bit);
@@ -573,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
if (bit == MINUS_ONE_T)
goto out;
- vbo = (u64)bit << index_bits;
- if (vbo >= i_size)
+ if (bit >= max_indx)
goto out;
err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits,
@@ -584,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
hdr = &node->index->ihdr;
bit += 1;
- vbo = (u64)bit << ni->dir.idx2vbn_bits;
}
out:
From 1918c10e137eae266b8eb0ab1cc14421dcb0e3e2 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:26:31 +0300
Subject: [PATCH 004/637] fs/ntfs3: Correct hard links updating when dealing
with DOS names
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/record.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 53629b1f65e9..7b6423584eae 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -535,8 +535,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi,
return false;
if (ni && is_attr_indexed(attr)) {
- le16_add_cpu(&ni->mi.mrec->hard_links, -1);
- ni->mi.dirty = true;
+ u16 links = le16_to_cpu(ni->mi.mrec->hard_links);
+ struct ATTR_FILE_NAME *fname =
+ attr->type != ATTR_NAME ?
+ NULL :
+ resident_data_ex(attr,
+ SIZEOF_ATTRIBUTE_FILENAME);
+ if (fname && fname->type == FILE_NAME_DOS) {
+ /* Do not decrease links count deleting DOS name. */
+ } else if (!links) {
+ /* minor error. Not critical. */
+ } else {
+ ni->mi.mrec->hard_links = cpu_to_le16(links - 1);
+ ni->mi.dirty = true;
+ }
}
used -= asize;
From 85ba2a75faee759809a7e43b4c103ac59bac1026 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:34:24 +0300
Subject: [PATCH 005/637] fs/ntfs3: Print warning while fixing hard links count
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/inode.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 5e3d71374918..fa6c7965473c 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -412,7 +412,6 @@ end_enum:
goto out;
if (!is_match && name) {
- /* Reuse rec as buffer for ascii name. */
err = -ENOENT;
goto out;
}
@@ -427,6 +426,7 @@ end_enum:
if (names != le16_to_cpu(rec->hard_links)) {
/* Correct minor error on the fly. Do not mark inode as dirty. */
+ ntfs_inode_warn(inode, "Correct links count -> %u.", names);
rec->hard_links = cpu_to_le16(names);
ni->mi.dirty = true;
}
From 865e7a7700d930d34895a70f8af2eb4e778a5b0e Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:42:04 +0300
Subject: [PATCH 006/637] fs/ntfs3: Reduce stack usage
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/fslog.c | 214 +++++++++++++++++++++--------------------------
1 file changed, 96 insertions(+), 118 deletions(-)
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 98ccb6650858..7dbb000fc691 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -974,6 +974,16 @@ skip_looking:
return e;
}
+struct restart_info {
+ u64 last_lsn;
+ struct RESTART_HDR *r_page;
+ u32 vbo;
+ bool chkdsk_was_run;
+ bool valid_page;
+ bool initialized;
+ bool restart;
+};
+
#define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001)
#define NTFSLOG_WRAPPED 0x00000001
@@ -987,6 +997,7 @@ struct ntfs_log {
struct ntfs_inode *ni;
u32 l_size;
+ u32 orig_file_size;
u32 sys_page_size;
u32 sys_page_mask;
u32 page_size;
@@ -1040,6 +1051,8 @@ struct ntfs_log {
struct CLIENT_ID client_id;
u32 client_undo_commit;
+
+ struct restart_info rst_info, rst_info2;
};
static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn)
@@ -1105,16 +1118,6 @@ static inline bool verify_client_lsn(struct ntfs_log *log,
lsn <= le64_to_cpu(log->ra->current_lsn) && lsn;
}
-struct restart_info {
- u64 last_lsn;
- struct RESTART_HDR *r_page;
- u32 vbo;
- bool chkdsk_was_run;
- bool valid_page;
- bool initialized;
- bool restart;
-};
-
static int read_log_page(struct ntfs_log *log, u32 vbo,
struct RECORD_PAGE_HDR **buffer, bool *usa_error)
{
@@ -1176,7 +1179,7 @@ out:
* restart page header. It will stop the first time we find a
* valid page header.
*/
-static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
+static int log_read_rst(struct ntfs_log *log, bool first,
struct restart_info *info)
{
u32 skip, vbo;
@@ -1192,7 +1195,7 @@ static int log_read_rst(struct ntfs_log *log, u32 l_size, bool first,
}
/* Loop continuously until we succeed. */
- for (; vbo < l_size; vbo = 2 * vbo + skip, skip = 0) {
+ for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) {
bool usa_error;
bool brst, bchk;
struct RESTART_AREA *ra;
@@ -1285,22 +1288,17 @@ check_result:
/*
* Ilog_init_pg_hdr - Init @log from restart page header.
*/
-static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
- u32 page_size, u16 major_ver, u16 minor_ver)
+static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver)
{
- log->sys_page_size = sys_page_size;
- log->sys_page_mask = sys_page_size - 1;
- log->page_size = page_size;
- log->page_mask = page_size - 1;
- log->page_bits = blksize_bits(page_size);
+ log->sys_page_size = log->page_size;
+ log->sys_page_mask = log->page_mask;
log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits;
if (!log->clst_per_page)
log->clst_per_page = 1;
- log->first_page = major_ver >= 2 ?
- 0x22 * page_size :
- ((sys_page_size << 1) + (page_size << 1));
+ log->first_page = major_ver >= 2 ? 0x22 * log->page_size :
+ 4 * log->page_size;
log->major_ver = major_ver;
log->minor_ver = minor_ver;
}
@@ -1308,12 +1306,11 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size,
/*
* log_create - Init @log in cases when we don't have a restart area to use.
*/
-static void log_create(struct ntfs_log *log, u32 l_size, const u64 last_lsn,
+static void log_create(struct ntfs_log *log, const u64 last_lsn,
u32 open_log_count, bool wrapped, bool use_multi_page)
{
- log->l_size = l_size;
/* All file offsets must be quadword aligned. */
- log->file_data_bits = blksize_bits(l_size) - 3;
+ log->file_data_bits = blksize_bits(log->l_size) - 3;
log->seq_num_mask = (8 << log->file_data_bits) - 1;
log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits;
log->seq_num = (last_lsn >> log->file_data_bits) + 2;
@@ -3720,10 +3717,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
struct ntfs_sb_info *sbi = ni->mi.sbi;
struct ntfs_log *log;
- struct restart_info rst_info, rst_info2;
- u64 rec_lsn, ra_lsn, checkpt_lsn = 0, rlsn = 0;
+ u64 rec_lsn, checkpt_lsn = 0, rlsn = 0;
struct ATTR_NAME_ENTRY *attr_names = NULL;
- struct ATTR_NAME_ENTRY *ane;
struct RESTART_TABLE *dptbl = NULL;
struct RESTART_TABLE *trtbl = NULL;
const struct RESTART_TABLE *rt;
@@ -3741,9 +3736,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
struct TRANSACTION_ENTRY *tr;
struct DIR_PAGE_ENTRY *dp;
u32 i, bytes_per_attr_entry;
- u32 l_size = ni->vfs_inode.i_size;
- u32 orig_file_size = l_size;
- u32 page_size, vbo, tail, off, dlen;
+ u32 vbo, tail, off, dlen;
u32 saved_len, rec_len, transact_id;
bool use_second_page;
struct RESTART_AREA *ra2, *ra = NULL;
@@ -3758,52 +3751,50 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
u16 t16;
u32 t32;
- /* Get the size of page. NOTE: To replay we can use default page. */
-#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
- page_size = norm_file_page(PAGE_SIZE, &l_size, true);
-#else
- page_size = norm_file_page(PAGE_SIZE, &l_size, false);
-#endif
- if (!page_size)
- return -EINVAL;
-
log = kzalloc(sizeof(struct ntfs_log), GFP_NOFS);
if (!log)
return -ENOMEM;
log->ni = ni;
- log->l_size = l_size;
- log->one_page_buf = kmalloc(page_size, GFP_NOFS);
+ log->l_size = log->orig_file_size = ni->vfs_inode.i_size;
+ /* Get the size of page. NOTE: To replay we can use default page. */
+#if PAGE_SIZE >= DefaultLogPageSize && PAGE_SIZE <= DefaultLogPageSize * 2
+ log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true);
+#else
+ log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, false);
+#endif
+ if (!log->page_size) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ log->one_page_buf = kmalloc(log->page_size, GFP_NOFS);
if (!log->one_page_buf) {
err = -ENOMEM;
goto out;
}
- log->page_size = page_size;
- log->page_mask = page_size - 1;
- log->page_bits = blksize_bits(page_size);
+ log->page_mask = log->page_size - 1;
+ log->page_bits = blksize_bits(log->page_size);
/* Look for a restart area on the disk. */
- memset(&rst_info, 0, sizeof(struct restart_info));
- err = log_read_rst(log, l_size, true, &rst_info);
+ err = log_read_rst(log, true, &log->rst_info);
if (err)
goto out;
/* remember 'initialized' */
- *initialized = rst_info.initialized;
+ *initialized = log->rst_info.initialized;
- if (!rst_info.restart) {
- if (rst_info.initialized) {
+ if (!log->rst_info.restart) {
+ if (log->rst_info.initialized) {
/* No restart area but the file is not initialized. */
err = -EINVAL;
goto out;
}
- log_init_pg_hdr(log, page_size, page_size, 1, 1);
- log_create(log, l_size, 0, get_random_u32(), false, false);
-
- log->ra = ra;
+ log_init_pg_hdr(log, 1, 1);
+ log_create(log, 0, get_random_u32(), false, false);
ra = log_create_ra(log);
if (!ra) {
@@ -3820,25 +3811,26 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
* If the restart offset above wasn't zero then we won't
* look for a second restart.
*/
- if (rst_info.vbo)
+ if (log->rst_info.vbo)
goto check_restart_area;
- memset(&rst_info2, 0, sizeof(struct restart_info));
- err = log_read_rst(log, l_size, false, &rst_info2);
+ err = log_read_rst(log, false, &log->rst_info2);
if (err)
goto out;
/* Determine which restart area to use. */
- if (!rst_info2.restart || rst_info2.last_lsn <= rst_info.last_lsn)
+ if (!log->rst_info2.restart ||
+ log->rst_info2.last_lsn <= log->rst_info.last_lsn)
goto use_first_page;
use_second_page = true;
- if (rst_info.chkdsk_was_run && page_size != rst_info.vbo) {
+ if (log->rst_info.chkdsk_was_run &&
+ log->page_size != log->rst_info.vbo) {
struct RECORD_PAGE_HDR *sp = NULL;
bool usa_error;
- if (!read_log_page(log, page_size, &sp, &usa_error) &&
+ if (!read_log_page(log, log->page_size, &sp, &usa_error) &&
sp->rhdr.sign == NTFS_CHKD_SIGNATURE) {
use_second_page = false;
}
@@ -3846,52 +3838,43 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
}
if (use_second_page) {
- kfree(rst_info.r_page);
- memcpy(&rst_info, &rst_info2, sizeof(struct restart_info));
- rst_info2.r_page = NULL;
+ kfree(log->rst_info.r_page);
+ memcpy(&log->rst_info, &log->rst_info2,
+ sizeof(struct restart_info));
+ log->rst_info2.r_page = NULL;
}
use_first_page:
- kfree(rst_info2.r_page);
+ kfree(log->rst_info2.r_page);
check_restart_area:
/*
* If the restart area is at offset 0, we want
* to write the second restart area first.
*/
- log->init_ra = !!rst_info.vbo;
+ log->init_ra = !!log->rst_info.vbo;
/* If we have a valid page then grab a pointer to the restart area. */
- ra2 = rst_info.valid_page ?
- Add2Ptr(rst_info.r_page,
- le16_to_cpu(rst_info.r_page->ra_off)) :
+ ra2 = log->rst_info.valid_page ?
+ Add2Ptr(log->rst_info.r_page,
+ le16_to_cpu(log->rst_info.r_page->ra_off)) :
NULL;
- if (rst_info.chkdsk_was_run ||
+ if (log->rst_info.chkdsk_was_run ||
(ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) {
bool wrapped = false;
bool use_multi_page = false;
u32 open_log_count;
/* Do some checks based on whether we have a valid log page. */
- if (!rst_info.valid_page) {
- open_log_count = get_random_u32();
- goto init_log_instance;
- }
- open_log_count = le32_to_cpu(ra2->open_log_count);
+ open_log_count = log->rst_info.valid_page ?
+ le32_to_cpu(ra2->open_log_count) :
+ get_random_u32();
- /*
- * If the restart page size isn't changing then we want to
- * check how much work we need to do.
- */
- if (page_size != le32_to_cpu(rst_info.r_page->sys_page_size))
- goto init_log_instance;
+ log_init_pg_hdr(log, 1, 1);
-init_log_instance:
- log_init_pg_hdr(log, page_size, page_size, 1, 1);
-
- log_create(log, l_size, rst_info.last_lsn, open_log_count,
- wrapped, use_multi_page);
+ log_create(log, log->rst_info.last_lsn, open_log_count, wrapped,
+ use_multi_page);
ra = log_create_ra(log);
if (!ra) {
@@ -3916,28 +3899,27 @@ init_log_instance:
* use the log file. We must use the system page size instead of the
* default size if there is not a clean shutdown.
*/
- t32 = le32_to_cpu(rst_info.r_page->sys_page_size);
- if (page_size != t32) {
- l_size = orig_file_size;
- page_size =
- norm_file_page(t32, &l_size, t32 == DefaultLogPageSize);
+ t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size);
+ if (log->page_size != t32) {
+ log->l_size = log->orig_file_size;
+ log->page_size = norm_file_page(t32, &log->l_size,
+ t32 == DefaultLogPageSize);
}
- if (page_size != t32 ||
- page_size != le32_to_cpu(rst_info.r_page->page_size)) {
+ if (log->page_size != t32 ||
+ log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) {
err = -EINVAL;
goto out;
}
/* If the file size has shrunk then we won't mount it. */
- if (l_size < le64_to_cpu(ra2->l_size)) {
+ if (log->l_size < le64_to_cpu(ra2->l_size)) {
err = -EINVAL;
goto out;
}
- log_init_pg_hdr(log, page_size, page_size,
- le16_to_cpu(rst_info.r_page->major_ver),
- le16_to_cpu(rst_info.r_page->minor_ver));
+ log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver),
+ le16_to_cpu(log->rst_info.r_page->minor_ver));
log->l_size = le64_to_cpu(ra2->l_size);
log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits);
@@ -3945,7 +3927,7 @@ init_log_instance:
log->seq_num_mask = (8 << log->file_data_bits) - 1;
log->last_lsn = le64_to_cpu(ra2->current_lsn);
log->seq_num = log->last_lsn >> log->file_data_bits;
- log->ra_off = le16_to_cpu(rst_info.r_page->ra_off);
+ log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off);
log->restart_size = log->sys_page_size - log->ra_off;
log->record_header_len = le16_to_cpu(ra2->rec_hdr_len);
log->ra_size = le16_to_cpu(ra2->ra_len);
@@ -4045,7 +4027,7 @@ find_oldest:
log->current_avail = current_log_avail(log);
/* Remember which restart area to write first. */
- log->init_ra = rst_info.vbo;
+ log->init_ra = log->rst_info.vbo;
process_log:
/* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */
@@ -4105,7 +4087,7 @@ process_log:
log->client_id.seq_num = cr->seq_num;
log->client_id.client_idx = client;
- err = read_rst_area(log, &rst, &ra_lsn);
+ err = read_rst_area(log, &rst, &checkpt_lsn);
if (err)
goto out;
@@ -4114,9 +4096,8 @@ process_log:
bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28;
- checkpt_lsn = le64_to_cpu(rst->check_point_start);
- if (!checkpt_lsn)
- checkpt_lsn = ra_lsn;
+ if (rst->check_point_start)
+ checkpt_lsn = le64_to_cpu(rst->check_point_start);
/* Allocate and Read the Transaction Table. */
if (!rst->transact_table_len)
@@ -4330,23 +4311,20 @@ check_attr_table:
lcb = NULL;
check_attribute_names2:
- if (!rst->attr_names_len)
- goto trace_attribute_table;
-
- ane = attr_names;
- if (!oatbl)
- goto trace_attribute_table;
- while (ane->off) {
- /* TODO: Clear table on exit! */
- oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
- t16 = le16_to_cpu(ane->name_bytes);
- oe->name_len = t16 / sizeof(short);
- oe->ptr = ane->name;
- oe->is_attr_name = 2;
- ane = Add2Ptr(ane, sizeof(struct ATTR_NAME_ENTRY) + t16);
+ if (rst->attr_names_len && oatbl) {
+ struct ATTR_NAME_ENTRY *ane = attr_names;
+ while (ane->off) {
+ /* TODO: Clear table on exit! */
+ oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
+ t16 = le16_to_cpu(ane->name_bytes);
+ oe->name_len = t16 / sizeof(short);
+ oe->ptr = ane->name;
+ oe->is_attr_name = 2;
+ ane = Add2Ptr(ane,
+ sizeof(struct ATTR_NAME_ENTRY) + t16);
+ }
}
-trace_attribute_table:
/*
* If the checkpt_lsn is zero, then this is a freshly
* formatted disk and we have no work to do.
@@ -5189,7 +5167,7 @@ out:
kfree(oatbl);
kfree(dptbl);
kfree(attr_names);
- kfree(rst_info.r_page);
+ kfree(log->rst_info.r_page);
kfree(ra);
kfree(log->one_page_buf);
From a8b0c9fc3a2dba07f697ef7825e04363ff12f071 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:46:16 +0300
Subject: [PATCH 007/637] fs/ntfs3: Fix multithreaded stress test
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/attrib.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 63f70259edc0..4b78b669a3bd 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -886,7 +886,7 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
struct runs_tree *run = &ni->file.run;
struct ntfs_sb_info *sbi;
u8 cluster_bits;
- struct ATTRIB *attr = NULL, *attr_b;
+ struct ATTRIB *attr, *attr_b;
struct ATTR_LIST_ENTRY *le, *le_b;
struct mft_inode *mi, *mi_b;
CLST hint, svcn, to_alloc, evcn1, next_svcn, asize, end, vcn0, alen;
@@ -904,12 +904,8 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
*len = 0;
up_read(&ni->file.run_lock);
- if (*len) {
- if (*lcn != SPARSE_LCN || !new)
- return 0; /* Fast normal way without allocation. */
- else if (clen > *len)
- clen = *len;
- }
+ if (*len && (*lcn != SPARSE_LCN || !new))
+ return 0; /* Fast normal way without allocation. */
/* No cluster in cache or we need to allocate cluster in hole. */
sbi = ni->mi.sbi;
@@ -918,6 +914,17 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
ni_lock(ni);
down_write(&ni->file.run_lock);
+ /* Repeat the code above (under write lock). */
+ if (!run_lookup_entry(run, vcn, lcn, len, NULL))
+ *len = 0;
+
+ if (*len) {
+ if (*lcn != SPARSE_LCN || !new)
+ goto out; /* normal way without allocation. */
+ if (clen > *len)
+ clen = *len;
+ }
+
le_b = NULL;
attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b);
if (!attr_b) {
From d155617006ebc172a80d3eb013c4b867f9a8ada4 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 11:47:30 +0300
Subject: [PATCH 008/637] fs/ntfs3: Fix detected field-spanning write (size 8)
of single field "le->name"
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/ntfs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 86aecbb01a92..13e96fc63dae 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY {
__le64 vcn; // 0x08: Starting VCN of this attribute.
struct MFT_REF ref; // 0x10: MFT record number with attribute.
__le16 id; // 0x18: struct ATTRIB ID.
- __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset.
+ __le16 name[]; // 0x1A: Just to align. To get real name can use name_off.
}; // sizeof(0x20)
From a40b73f608e7de2120fdb9ddc8970421b3c50bc9 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:08:36 +0300
Subject: [PATCH 009/637] fs/ntfs3: Correct use bh_read
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/file.c | 19 +++++++++----------
fs/ntfs3/inode.c | 7 +++----
2 files changed, 12 insertions(+), 14 deletions(-)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index a5a30a24ce5d..5691f04e6751 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -188,6 +188,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
u32 bh_next, bh_off, to;
sector_t iblock;
struct folio *folio;
+ bool dirty = false;
for (; idx < idx_end; idx += 1, from = 0) {
page_off = (loff_t)idx << PAGE_SHIFT;
@@ -223,29 +224,27 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
/* Ok, it's mapped. Make sure it's up-to-date. */
if (folio_test_uptodate(folio))
set_buffer_uptodate(bh);
-
- if (!buffer_uptodate(bh)) {
- err = bh_read(bh, 0);
- if (err < 0) {
- folio_unlock(folio);
- folio_put(folio);
- goto out;
- }
+ else if (bh_read(bh, 0) < 0) {
+ err = -EIO;
+ folio_unlock(folio);
+ folio_put(folio);
+ goto out;
}
mark_buffer_dirty(bh);
-
} while (bh_off = bh_next, iblock += 1,
head != (bh = bh->b_this_page));
folio_zero_segment(folio, from, to);
+ dirty = true;
folio_unlock(folio);
folio_put(folio);
cond_resched();
}
out:
- mark_inode_dirty(inode);
+ if (dirty)
+ mark_inode_dirty(inode);
return err;
}
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index fa6c7965473c..bba0208c4afd 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -345,9 +345,7 @@ next_attr:
inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer
.PrintNameLength) /
sizeof(u16);
-
ni->i_valid = inode->i_size;
-
/* Clear directory bit. */
if (ni->ni_flags & NI_FLAG_DIR) {
indx_clear(&ni->dir);
@@ -653,9 +651,10 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo,
off = vbo & (PAGE_SIZE - 1);
folio_set_bh(bh, folio, off);
- err = bh_read(bh, 0);
- if (err < 0)
+ if (bh_read(bh, 0) < 0) {
+ err = -EIO;
goto out;
+ }
folio_zero_segment(folio, off + voff, off + block_size);
}
}
From 4dea9cd522424d3002894c20b729c6fbfb6fc22b Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:16:49 +0300
Subject: [PATCH 010/637] fs/ntfs3: Add file_modified
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/file.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 5691f04e6751..bb80ce2eec2f 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -632,11 +632,17 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
&ni->file.run, i_size, &ni->i_valid,
true, NULL);
ni_unlock(ni);
+ if (err)
+ goto out;
} else if (new_size > i_size) {
inode->i_size = new_size;
}
}
+ err = file_modified(file);
+ if (err)
+ goto out;
+
out:
if (map_locked)
filemap_invalidate_unlock(mapping);
@@ -1040,6 +1046,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;
+ int err;
struct ntfs_inode *ni = ntfs_i(inode);
if (is_encrypted(ni)) {
@@ -1067,6 +1074,12 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret <= 0)
goto out;
+ err = file_modified(iocb->ki_filp);
+ if (err) {
+ ret = err;
+ goto out;
+ }
+
if (WARN_ON(ni->ni_flags & NI_FLAG_COMPRESSED_MASK)) {
/* Should never be here, see ntfs_file_open(). */
ret = -EOPNOTSUPP;
From e50f9560b8168a625703a3e7fe1fde9fa53f0837 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:17:46 +0300
Subject: [PATCH 011/637] fs/ntfs3: Drop suid and sgid bits as a part of fpunch
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/file.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index bb80ce2eec2f..0ff5d3af2889 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -498,10 +498,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
ni_lock(ni);
err = attr_punch_hole(ni, vbo, len, &frame_size);
ni_unlock(ni);
+ if (!err)
+ goto ok;
+
if (err != E_NTFS_NOTALIGNED)
goto out;
/* Process not aligned punch. */
+ err = 0;
mask = frame_size - 1;
vbo_a = (vbo + mask) & ~mask;
end_a = end & ~mask;
@@ -524,6 +528,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
ni_lock(ni);
err = attr_punch_hole(ni, vbo_a, end_a - vbo_a, NULL);
ni_unlock(ni);
+ if (err)
+ goto out;
}
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
/*
@@ -563,6 +569,8 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
ni_lock(ni);
err = attr_insert_range(ni, vbo, len);
ni_unlock(ni);
+ if (err)
+ goto out;
} else {
/* Check new size. */
u8 cluster_bits = sbi->cluster_bits;
@@ -639,6 +647,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
}
}
+ok:
err = file_modified(file);
if (err)
goto out;
From 6c3684e703837d2116b5cf4beb37aa7145a66b60 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:19:37 +0300
Subject: [PATCH 012/637] fs/ntfs3: Implement super_operations::shutdown
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/file.c | 18 ++++++++++++++++++
fs/ntfs3/frecord.c | 3 +++
fs/ntfs3/inode.c | 21 +++++++++++++++++++--
fs/ntfs3/namei.c | 12 ++++++++++++
fs/ntfs3/ntfs_fs.h | 9 ++++++++-
fs/ntfs3/super.c | 12 ++++++++++++
fs/ntfs3/xattr.c | 3 +++
7 files changed, 75 insertions(+), 3 deletions(-)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 0ff5d3af2889..07ed3d946e7c 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -260,6 +260,9 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
bool rw = vma->vm_flags & VM_WRITE;
int err;
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
if (is_encrypted(ni)) {
ntfs_inode_warn(inode, "mmap encrypted not supported");
return -EOPNOTSUPP;
@@ -677,6 +680,9 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
umode_t mode = inode->i_mode;
int err;
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
err = setattr_prepare(idmap, dentry, attr);
if (err)
goto out;
@@ -732,6 +738,9 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
struct inode *inode = file->f_mapping->host;
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
if (is_encrypted(ni)) {
ntfs_inode_warn(inode, "encrypted i/o not supported");
return -EOPNOTSUPP;
@@ -766,6 +775,9 @@ static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
struct inode *inode = in->f_mapping->host;
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
if (is_encrypted(ni)) {
ntfs_inode_warn(inode, "encrypted i/o not supported");
return -EOPNOTSUPP;
@@ -1058,6 +1070,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
int err;
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
if (is_encrypted(ni)) {
ntfs_inode_warn(inode, "encrypted i/o not supported");
return -EOPNOTSUPP;
@@ -1118,6 +1133,9 @@ int ntfs_file_open(struct inode *inode, struct file *file)
{
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
if (unlikely((is_compressed(ni) || is_encrypted(ni)) &&
(file->f_flags & O_DIRECT))) {
return -EOPNOTSUPP;
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 3df2d9e34b91..8744ba36d422 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -3259,6 +3259,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
if (is_bad_inode(inode) || sb_rdonly(sb))
return 0;
+ if (unlikely(ntfs3_forced_shutdown(sb)))
+ return -EIO;
+
if (!ni_trylock(ni)) {
/* 'ni' is under modification, skip for now. */
mark_inode_dirty_sync(inode);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index bba0208c4afd..85452a6b1d40 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -852,9 +852,13 @@ static int ntfs_resident_writepage(struct folio *folio,
struct writeback_control *wbc, void *data)
{
struct address_space *mapping = data;
- struct ntfs_inode *ni = ntfs_i(mapping->host);
+ struct inode *inode = mapping->host;
+ struct ntfs_inode *ni = ntfs_i(inode);
int ret;
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
ni_lock(ni);
ret = attr_data_write_resident(ni, &folio->page);
ni_unlock(ni);
@@ -868,7 +872,12 @@ static int ntfs_resident_writepage(struct folio *folio,
static int ntfs_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- if (is_resident(ntfs_i(mapping->host)))
+ struct inode *inode = mapping->host;
+
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
+ if (is_resident(ntfs_i(inode)))
return write_cache_pages(mapping, wbc, ntfs_resident_writepage,
mapping);
return mpage_writepages(mapping, wbc, ntfs_get_block);
@@ -888,6 +897,9 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping,
struct inode *inode = mapping->host;
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
*pagep = NULL;
if (is_resident(ni)) {
struct page *page =
@@ -1305,6 +1317,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
goto out1;
}
+ if (unlikely(ntfs3_forced_shutdown(sb))) {
+ err = -EIO;
+ goto out2;
+ }
+
/* Mark rw ntfs as dirty. it will be cleared at umount. */
ntfs_set_state(sbi, NTFS_DIRTY_DIRTY);
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ee3093be5170..cae41db0aaa7 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -181,6 +181,9 @@ static int ntfs_unlink(struct inode *dir, struct dentry *dentry)
struct ntfs_inode *ni = ntfs_i(dir);
int err;
+ if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+ return -EIO;
+
ni_lock_dir(ni);
err = ntfs_unlink_inode(dir, dentry);
@@ -199,6 +202,9 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
u32 size = strlen(symname);
struct inode *inode;
+ if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+ return -EIO;
+
inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0,
symname, size, NULL);
@@ -227,6 +233,9 @@ static int ntfs_rmdir(struct inode *dir, struct dentry *dentry)
struct ntfs_inode *ni = ntfs_i(dir);
int err;
+ if (unlikely(ntfs3_forced_shutdown(dir->i_sb)))
+ return -EIO;
+
ni_lock_dir(ni);
err = ntfs_unlink_inode(dir, dentry);
@@ -264,6 +273,9 @@ static int ntfs_rename(struct mnt_idmap *idmap, struct inode *dir,
1024);
static_assert(PATH_MAX >= 4 * 1024);
+ if (unlikely(ntfs3_forced_shutdown(sb)))
+ return -EIO;
+
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index f6706143d14b..d40bc7669ae5 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -61,6 +61,8 @@ enum utf16_endian;
/* sbi->flags */
#define NTFS_FLAGS_NODISCARD 0x00000001
+/* ntfs in shutdown state. */
+#define NTFS_FLAGS_SHUTDOWN 0x00000002
/* Set when LogFile is replaying. */
#define NTFS_FLAGS_LOG_REPLAYING 0x00000008
/* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -226,7 +228,7 @@ struct ntfs_sb_info {
u64 maxbytes; // Maximum size for normal files.
u64 maxbytes_sparse; // Maximum size for sparse file.
- u32 flags; // See NTFS_FLAGS_XXX.
+ unsigned long flags; // See NTFS_FLAGS_
CLST zone_max; // Maximum MFT zone length in clusters
CLST bad_clusters; // The count of marked bad clusters.
@@ -999,6 +1001,11 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
return sb->s_fs_info;
}
+static inline bool ntfs3_forced_shutdown(struct super_block *sb)
+{
+ return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+}
+
/*
* ntfs_up_cluster - Align up on cluster boundary.
*/
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 09d61c6c90aa..af8521a6ed95 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -714,6 +714,14 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
return 0;
}
+/*
+ * ntfs_shutdown - super_operations::shutdown
+ */
+static void ntfs_shutdown(struct super_block *sb)
+{
+ set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+}
+
/*
* ntfs_sync_fs - super_operations::sync_fs
*/
@@ -724,6 +732,9 @@ static int ntfs_sync_fs(struct super_block *sb, int wait)
struct ntfs_inode *ni;
struct inode *inode;
+ if (unlikely(ntfs3_forced_shutdown(sb)))
+ return -EIO;
+
ni = sbi->security.ni;
if (ni) {
inode = &ni->vfs_inode;
@@ -763,6 +774,7 @@ static const struct super_operations ntfs_sops = {
.put_super = ntfs_put_super,
.statfs = ntfs_statfs,
.show_options = ntfs_show_options,
+ .shutdown = ntfs_shutdown,
.sync_fs = ntfs_sync_fs,
.write_inode = ntfs3_write_inode,
};
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 4274b6f31cfa..071356d096d8 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -744,6 +744,9 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de,
int err;
struct ntfs_inode *ni = ntfs_i(inode);
+ if (unlikely(ntfs3_forced_shutdown(inode->i_sb)))
+ return -EIO;
+
/* Dispatch request. */
if (!strcmp(name, SYSTEM_DOS_ATTRIB)) {
/* system.dos_attrib */
From 97ec56d390a3a0077b36cb38627f671c72dddce6 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 24 Nov 2023 12:21:12 +0300
Subject: [PATCH 013/637] fs/ntfs3: ntfs3_forced_shutdown use int instead of
bool
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/fsntfs.c | 3 ++-
fs/ntfs3/ntfs_fs.h | 6 +++---
fs/ntfs3/super.c | 2 +-
3 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index fbfe21dbb425..350461d8cece 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -853,7 +853,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait)
/*
* sb can be NULL here. In this case sbi->flags should be 0 too.
*/
- if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR))
+ if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR) ||
+ unlikely(ntfs3_forced_shutdown(sb)))
return;
blocksize = sb->s_blocksize;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index d40bc7669ae5..7510875efef6 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -62,7 +62,7 @@ enum utf16_endian;
/* sbi->flags */
#define NTFS_FLAGS_NODISCARD 0x00000001
/* ntfs in shutdown state. */
-#define NTFS_FLAGS_SHUTDOWN 0x00000002
+#define NTFS_FLAGS_SHUTDOWN_BIT 0x00000002 /* == 4*/
/* Set when LogFile is replaying. */
#define NTFS_FLAGS_LOG_REPLAYING 0x00000008
/* Set when we changed first MFT's which copy must be updated in $MftMirr. */
@@ -1001,9 +1001,9 @@ static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb)
return sb->s_fs_info;
}
-static inline bool ntfs3_forced_shutdown(struct super_block *sb)
+static inline int ntfs3_forced_shutdown(struct super_block *sb)
{
- return test_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+ return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
}
/*
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index af8521a6ed95..65ef4b57411f 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -719,7 +719,7 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root)
*/
static void ntfs_shutdown(struct super_block *sb)
{
- set_bit(NTFS_FLAGS_SHUTDOWN, &ntfs_sb(sb)->flags);
+ set_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags);
}
/*
From d6ca2d253900b9b0a3a1ad77541d606010f5e5eb Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:08:00 +0300
Subject: [PATCH 014/637] fs/ntfs3: Add and fix comments
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/dir.c | 4 +++-
fs/ntfs3/fsntfs.c | 2 +-
fs/ntfs3/ntfs.h | 2 +-
fs/ntfs3/ntfs_fs.h | 2 +-
4 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 726122ecd39b..9f6dd445eb04 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -536,8 +536,10 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
e = Add2Ptr(hdr, off);
e_size = le16_to_cpu(e->size);
if (e_size < sizeof(struct NTFS_DE) ||
- off + e_size > end)
+ off + e_size > end) {
+ /* Looks like corruption. */
break;
+ }
if (de_is_last(e))
break;
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 350461d8cece..321978019407 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -2129,8 +2129,8 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi,
if (le32_to_cpu(d_security->size) == new_sec_size &&
d_security->key.hash == hash_key.hash &&
!memcmp(d_security + 1, sd, size_sd)) {
- *security_id = d_security->key.sec_id;
/* Such security already exists. */
+ *security_id = d_security->key.sec_id;
err = 0;
goto out;
}
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 13e96fc63dae..c8981429c721 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -523,7 +523,7 @@ struct ATTR_LIST_ENTRY {
__le64 vcn; // 0x08: Starting VCN of this attribute.
struct MFT_REF ref; // 0x10: MFT record number with attribute.
__le16 id; // 0x18: struct ATTRIB ID.
- __le16 name[]; // 0x1A: Just to align. To get real name can use name_off.
+ __le16 name[]; // 0x1A: To get real name use name_off.
}; // sizeof(0x20)
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 7510875efef6..abbc7182554a 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -874,7 +874,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode,
int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry);
ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-extern const struct xattr_handler * const ntfs_xattr_handlers[];
+extern const struct xattr_handler *const ntfs_xattr_handlers[];
int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size);
void ntfs_get_wsl_perm(struct inode *inode);
From aaab47f204aaf47838241d57bf8662c8840de60a Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:09:34 +0300
Subject: [PATCH 015/637] fs/ntfs3: Add NULL ptr dereference checking at the
end of attr_allocate_frame()
It is preferable to exit through the out: label because
internal debugging functions are located there.
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/attrib.c | 20 ++++++++++++--------
1 file changed, 12 insertions(+), 8 deletions(-)
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 4b78b669a3bd..646e2dad1b75 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -1743,8 +1743,10 @@ repack:
le_b = NULL;
attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
0, NULL, &mi_b);
- if (!attr_b)
- return -ENOENT;
+ if (!attr_b) {
+ err = -ENOENT;
+ goto out;
+ }
attr = attr_b;
le = le_b;
@@ -1825,13 +1827,15 @@ ins_ext:
ok:
run_truncate_around(run, vcn);
out:
- if (new_valid > data_size)
- new_valid = data_size;
+ if (attr_b) {
+ if (new_valid > data_size)
+ new_valid = data_size;
- valid_size = le64_to_cpu(attr_b->nres.valid_size);
- if (new_valid != valid_size) {
- attr_b->nres.valid_size = cpu_to_le64(valid_size);
- mi_b->dirty = true;
+ valid_size = le64_to_cpu(attr_b->nres.valid_size);
+ if (new_valid != valid_size) {
+ attr_b->nres.valid_size = cpu_to_le64(valid_size);
+ mi_b->dirty = true;
+ }
}
return err;
From 652483bfbc45137e8dce556c9ddbd4458dad4452 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 28 Nov 2023 11:17:20 +0300
Subject: [PATCH 016/637] fs/ntfs3: Fix c/mtime typo
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/frecord.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 8744ba36d422..6ff4f70ba077 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -3291,7 +3291,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
modified = true;
}
- ts = inode_get_mtime(inode);
+ ts = inode_get_ctime(inode);
dup.c_time = kernel2nt(&ts);
if (std->c_time != dup.c_time) {
std->c_time = dup.c_time;
From fe752331d4b361d43cfd0b89534b4b2176057c32 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@linux.ibm.com>
Date: Wed, 20 Dec 2023 13:53:17 +0100
Subject: [PATCH 017/637] KVM: s390: vsie: fix race during shadow creation
Right now it is possible to see gmap->private being zero in
kvm_s390_vsie_gmap_notifier resulting in a crash. This is due to the
fact that we add gmap->private == kvm after creation:
static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
struct vsie_page *vsie_page)
{
[...]
gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
if (IS_ERR(gmap))
return PTR_ERR(gmap);
gmap->private = vcpu->kvm;
Let children inherit the private field of the parent.
Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Fixes: a3508fbe9dc6 ("KVM: s390: vsie: initial support for nested virtualization")
Cc: <stable@vger.kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Link: https://lore.kernel.org/r/20231220125317.4258-1-borntraeger@linux.ibm.com
---
arch/s390/kvm/vsie.c | 1 -
arch/s390/mm/gmap.c | 1 +
2 files changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 8207a892bbe2..db9a180de65f 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1220,7 +1220,6 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu,
gmap = gmap_shadow(vcpu->arch.gmap, asce, edat);
if (IS_ERR(gmap))
return PTR_ERR(gmap);
- gmap->private = vcpu->kvm;
vcpu->kvm->stat.gmap_shadow_create++;
WRITE_ONCE(vsie_page->gmap, gmap);
return 0;
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 6f96b5a71c63..8da39deb56ca 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -1691,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
return ERR_PTR(-ENOMEM);
new->mm = parent->mm;
new->parent = gmap_get(parent);
+ new->private = parent->private;
new->orig_asce = asce;
new->edat_level = edat_level;
new->initialized = false;
From 4cdfb6e7bc9c80142d33bf1d4653a73fa678ba56 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Thu, 21 Dec 2023 13:59:43 +0300
Subject: [PATCH 018/637] fs/ntfs3: Disable ATTR_LIST_ENTRY size check
The use of sizeof(struct ATTR_LIST_ENTRY) has been replaced with le_size(0)
due to alignment peculiarities on different platforms.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312071005.g6YrbaIe-lkp@intel.com/
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/attrlist.c | 8 ++++----
fs/ntfs3/ntfs.h | 2 --
2 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 7c01735d1219..48e7da47c6b7 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
{
size_t off;
u16 sz;
+ const unsigned le_min_size = le_size(0);
if (!le) {
le = ni->attr_list.le;
} else {
sz = le16_to_cpu(le->size);
- if (sz < sizeof(struct ATTR_LIST_ENTRY)) {
+ if (sz < le_min_size) {
/* Impossible 'cause we should not return such le. */
return NULL;
}
@@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
/* Check boundary. */
off = PtrOffset(ni->attr_list.le, le);
- if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) {
+ if (off + le_min_size > ni->attr_list.size) {
/* The regular end of list. */
return NULL;
}
@@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni,
sz = le16_to_cpu(le->size);
/* Check le for errors. */
- if (sz < sizeof(struct ATTR_LIST_ENTRY) ||
- off + sz > ni->attr_list.size ||
+ if (sz < le_min_size || off + sz > ni->attr_list.size ||
sz < le->name_off + le->name_len * sizeof(short)) {
return NULL;
}
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index c8981429c721..9c7478150a03 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -527,8 +527,6 @@ struct ATTR_LIST_ENTRY {
}; // sizeof(0x20)
-static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20);
-
static inline u32 le_size(u8 name_len)
{
return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) +
From 83303a4c776ce1032d88df59e811183479acea77 Mon Sep 17 00:00:00 2001
From: Eric Farman <farman@linux.ibm.com>
Date: Fri, 1 Dec 2023 19:16:57 +0100
Subject: [PATCH 019/637] KVM: s390: fix cc for successful PQAP
The various errors that are possible when processing a PQAP
instruction (the absence of a driver hook, an error FROM that
hook), all correctly set the PSW condition code to 3. But if
that processing works successfully, CC0 needs to be set to
convey that everything was fine.
Fix the check so that the guest can examine the condition code
to determine whether GPR1 has meaningful data.
Fixes: e5282de93105 ("s390: ap: kvm: add PQAP interception for AQIC")
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Link: https://lore.kernel.org/r/20231201181657.1614645-1-farman@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-Id: <20231201181657.1614645-1-farman@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
---
arch/s390/kvm/priv.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 621a17fd1a1b..f875a404a0a0 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -676,8 +676,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
if (vcpu->kvm->arch.crypto.pqap_hook) {
pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook;
ret = pqap_hook(vcpu);
- if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000)
- kvm_s390_set_psw_cc(vcpu, 3);
+ if (!ret) {
+ if (vcpu->run->s.regs.gprs[1] & 0x00ff0000)
+ kvm_s390_set_psw_cc(vcpu, 3);
+ else
+ kvm_s390_set_psw_cc(vcpu, 0);
+ }
up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem);
return ret;
}
From 85e985a4f46e462a37f1875cb74ed380e7c0c2e0 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 10 Jan 2024 15:16:26 +0200
Subject: [PATCH 020/637] interconnect: qcom: sc8180x: Mark CO0 BCM keepalive
The CO0 BCM needs to be up at all times, otherwise some hardware (like
the UFS controller) loses its connection to the rest of the SoC,
resulting in a hang of the platform, accompanied by a spectacular
logspam.
Mark it as keepalive to prevent such cases.
Fixes: 9c8c6bac1ae8 ("interconnect: qcom: Add SC8180x providers")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/20231214-topic-sc8180_fixes-v1-1-421904863006@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/sc8180x.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/interconnect/qcom/sc8180x.c b/drivers/interconnect/qcom/sc8180x.c
index 20331e119beb..03d626776ba1 100644
--- a/drivers/interconnect/qcom/sc8180x.c
+++ b/drivers/interconnect/qcom/sc8180x.c
@@ -1372,6 +1372,7 @@ static struct qcom_icc_bcm bcm_mm0 = {
static struct qcom_icc_bcm bcm_co0 = {
.name = "CO0",
+ .keepalive = true,
.num_nodes = 1,
.nodes = { &slv_qns_cdsp_mem_noc }
};
From 24406f6794aa631516241deb9e19de333d6a0600 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 10 Jan 2024 15:16:46 +0200
Subject: [PATCH 021/637] interconnect: qcom: sm8550: Enable sync_state
To ensure the interconnect votes are actually meaningful and in order to
prevent holding all buses at FMAX, introduce the sync state callback.
Fixes: e6f0d6a30f73 ("interconnect: qcom: Add SM8550 interconnect provider driver")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20231218-topic-8550_fixes-v1-2-ce1272d77540@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/sm8550.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/interconnect/qcom/sm8550.c b/drivers/interconnect/qcom/sm8550.c
index 629faa4c9aae..fc22cecf650f 100644
--- a/drivers/interconnect/qcom/sm8550.c
+++ b/drivers/interconnect/qcom/sm8550.c
@@ -2223,6 +2223,7 @@ static struct platform_driver qnoc_driver = {
.driver = {
.name = "qnoc-sm8550",
.of_match_table = qnoc_of_match,
+ .sync_state = icc_sync_state,
},
};
From ddb17dc880eeaac37b5a6e984de07b882de7d78d Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Tue, 16 Jan 2024 10:32:20 +0300
Subject: [PATCH 022/637] fs/ntfs3: Use kvfree to free memory allocated by
kvmalloc
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/attrlist.c | 4 ++--
fs/ntfs3/bitmap.c | 4 ++--
fs/ntfs3/frecord.c | 4 ++--
fs/ntfs3/super.c | 2 +-
4 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 48e7da47c6b7..9f4bd8d26090 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -29,7 +29,7 @@ static inline bool al_is_valid_le(const struct ntfs_inode *ni,
void al_destroy(struct ntfs_inode *ni)
{
run_close(&ni->attr_list.run);
- kfree(ni->attr_list.le);
+ kvfree(ni->attr_list.le);
ni->attr_list.le = NULL;
ni->attr_list.size = 0;
ni->attr_list.dirty = false;
@@ -318,7 +318,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name,
memcpy(ptr, al->le, off);
memcpy(Add2Ptr(ptr, off + sz), le, old_size - off);
le = Add2Ptr(ptr, off);
- kfree(al->le);
+ kvfree(al->le);
al->le = ptr;
} else {
memmove(Add2Ptr(le, sz), le, old_size - off);
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 63f14a0232f6..845f9b22deef 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -124,7 +124,7 @@ void wnd_close(struct wnd_bitmap *wnd)
{
struct rb_node *node, *next;
- kfree(wnd->free_bits);
+ kvfree(wnd->free_bits);
wnd->free_bits = NULL;
run_close(&wnd->run);
@@ -1360,7 +1360,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
memcpy(new_free, wnd->free_bits, wnd->nwnd * sizeof(short));
memset(new_free + wnd->nwnd, 0,
(new_wnd - wnd->nwnd) * sizeof(short));
- kfree(wnd->free_bits);
+ kvfree(wnd->free_bits);
wnd->free_bits = new_free;
}
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 6ff4f70ba077..2636ab7640ac 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -778,7 +778,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
run_deallocate(sbi, &ni->attr_list.run, true);
run_close(&ni->attr_list.run);
ni->attr_list.size = 0;
- kfree(ni->attr_list.le);
+ kvfree(ni->attr_list.le);
ni->attr_list.le = NULL;
ni->attr_list.dirty = false;
@@ -927,7 +927,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
return 0;
out:
- kfree(ni->attr_list.le);
+ kvfree(ni->attr_list.le);
ni->attr_list.le = NULL;
ni->attr_list.size = 0;
return err;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 65ef4b57411f..c55a29793a8d 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -625,7 +625,7 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
{
kfree(sbi->new_rec);
kvfree(ntfs_put_shared(sbi->upcase));
- kfree(sbi->def_table);
+ kvfree(sbi->def_table);
kfree(sbi->compress.lznt);
#ifdef CONFIG_NTFS3_LZX_XPRESS
xpress_free_decompressor(sbi->compress.xpress);
From 935024212dafebe065ccb5c4d399f19e4b8dbb82 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Tue, 16 Jan 2024 06:27:31 +0000
Subject: [PATCH 023/637] dt-bindings: don't anchor DT_SCHEMA_FILES to bindings
directory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit 5e3ef4546819 ("dt-bindings: ignore paths outside kernel for
DT_SCHEMA_FILES") anchored all searches to the bindings directory
(since bindings only exist below that), but it turns out this is not
always desired.
Just anchor to the base kernel source directory and while at it, break
the overly long line for legibility.
Reported-by: Michal Simek <michal.simek@amd.com>
Fixes: 5e3ef4546819 ("dt-bindings: ignore paths outside kernel for DT_SCHEMA_FILES")
Closes: https://lore.kernel.org/all/827695c3-bb33-4a86-8586-2c7323530398@amd.com/
Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Tested-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/20240116062731.2810067-1-git@andred.net
Signed-off-by: Rob Herring <robh@kernel.org>
---
Documentation/devicetree/bindings/Makefile | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index 2323fd5b7cda..129cf698fa8a 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -28,7 +28,10 @@ $(obj)/%.example.dts: $(src)/%.yaml check_dtschema_version FORCE
find_all_cmd = find $(srctree)/$(src) \( -name '*.yaml' ! \
-name 'processed-schema*' \)
-find_cmd = $(find_all_cmd) | sed 's|^$(srctree)/$(src)/||' | grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | sed 's|^|$(srctree)/$(src)/|'
+find_cmd = $(find_all_cmd) | \
+ sed 's|^$(srctree)/||' | \
+ grep -F -e "$(subst :," -e ",$(DT_SCHEMA_FILES))" | \
+ sed 's|^|$(srctree)/|'
CHK_DT_DOCS := $(shell $(find_cmd))
quiet_cmd_yamllint = LINT $(src)
From 367188297254e7f81e3c3c94e6d6a623f757c4cb Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 16:11:09 +0530
Subject: [PATCH 024/637] RISC-V: KVM: Allow Zbc extension for Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zbc extension for Guest/VM.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 1 +
arch/riscv/kvm/vcpu_onereg.c | 2 ++
2 files changed, 3 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index d6b7a5b95874..bbff9c7e8f3f 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -139,6 +139,7 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZIHPM,
KVM_RISCV_ISA_EXT_SMSTATEEN,
KVM_RISCV_ISA_EXT_ZICOND,
+ KVM_RISCV_ISA_EXT_ZBC,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index fc34557f5356..4522fdfec94e 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -42,6 +42,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(SVPBMT),
KVM_ISA_EXT_ARR(ZBA),
KVM_ISA_EXT_ARR(ZBB),
+ KVM_ISA_EXT_ARR(ZBC),
KVM_ISA_EXT_ARR(ZBS),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
@@ -92,6 +93,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_SVNAPOT:
case KVM_RISCV_ISA_EXT_ZBA:
case KVM_RISCV_ISA_EXT_ZBB:
+ case KVM_RISCV_ISA_EXT_ZBC:
case KVM_RISCV_ISA_EXT_ZBS:
case KVM_RISCV_ISA_EXT_ZICNTR:
case KVM_RISCV_ISA_EXT_ZICOND:
From ac396141308d07a9534c5a7f1f7c80cb95e35b20 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 18:47:23 +0530
Subject: [PATCH 025/637] KVM: riscv: selftests: Add Zbc extension to
get-reg-list test
The KVM RISC-V allows Zbc extension for Guest/VM so let us add
this extension to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6652108816db..2e8e1c52b9ef 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -49,6 +49,7 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
@@ -394,6 +395,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(SVPBMT),
KVM_ISA_EXT_ARR(ZBA),
KVM_ISA_EXT_ARR(ZBB),
+ KVM_ISA_EXT_ARR(ZBC),
KVM_ISA_EXT_ARR(ZBS),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
@@ -888,6 +890,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
@@ -914,6 +917,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_svpbmt,
&config_zba,
&config_zbb,
+ &config_zbc,
&config_zbs,
&config_zicbom,
&config_zicboz,
From f370b4e668f017f523968f7490163fa922dcd92e Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 20:36:36 +0530
Subject: [PATCH 026/637] RISC-V: KVM: Allow scalar crypto extensions for
Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable scalar crypto extensions for
Guest/VM. This includes extensions Zbkb, Zbkc, Zbkx, Zknd, Zkne,
Zknh, Zkr, Zksed, Zksh, and Zkt.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 10 ++++++++++
arch/riscv/kvm/vcpu_onereg.c | 20 ++++++++++++++++++++
2 files changed, 30 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index bbff9c7e8f3f..453edf620b87 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -140,6 +140,16 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_SMSTATEEN,
KVM_RISCV_ISA_EXT_ZICOND,
KVM_RISCV_ISA_EXT_ZBC,
+ KVM_RISCV_ISA_EXT_ZBKB,
+ KVM_RISCV_ISA_EXT_ZBKC,
+ KVM_RISCV_ISA_EXT_ZBKX,
+ KVM_RISCV_ISA_EXT_ZKND,
+ KVM_RISCV_ISA_EXT_ZKNE,
+ KVM_RISCV_ISA_EXT_ZKNH,
+ KVM_RISCV_ISA_EXT_ZKR,
+ KVM_RISCV_ISA_EXT_ZKSED,
+ KVM_RISCV_ISA_EXT_ZKSH,
+ KVM_RISCV_ISA_EXT_ZKT,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 4522fdfec94e..680da2a55da2 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -43,6 +43,9 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZBA),
KVM_ISA_EXT_ARR(ZBB),
KVM_ISA_EXT_ARR(ZBC),
+ KVM_ISA_EXT_ARR(ZBKB),
+ KVM_ISA_EXT_ARR(ZBKC),
+ KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
@@ -52,6 +55,13 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZIFENCEI),
KVM_ISA_EXT_ARR(ZIHINTPAUSE),
KVM_ISA_EXT_ARR(ZIHPM),
+ KVM_ISA_EXT_ARR(ZKND),
+ KVM_ISA_EXT_ARR(ZKNE),
+ KVM_ISA_EXT_ARR(ZKNH),
+ KVM_ISA_EXT_ARR(ZKR),
+ KVM_ISA_EXT_ARR(ZKSED),
+ KVM_ISA_EXT_ARR(ZKSH),
+ KVM_ISA_EXT_ARR(ZKT),
};
static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -94,6 +104,9 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZBA:
case KVM_RISCV_ISA_EXT_ZBB:
case KVM_RISCV_ISA_EXT_ZBC:
+ case KVM_RISCV_ISA_EXT_ZBKB:
+ case KVM_RISCV_ISA_EXT_ZBKC:
+ case KVM_RISCV_ISA_EXT_ZBKX:
case KVM_RISCV_ISA_EXT_ZBS:
case KVM_RISCV_ISA_EXT_ZICNTR:
case KVM_RISCV_ISA_EXT_ZICOND:
@@ -101,6 +114,13 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZIFENCEI:
case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
case KVM_RISCV_ISA_EXT_ZIHPM:
+ case KVM_RISCV_ISA_EXT_ZKND:
+ case KVM_RISCV_ISA_EXT_ZKNE:
+ case KVM_RISCV_ISA_EXT_ZKNH:
+ case KVM_RISCV_ISA_EXT_ZKR:
+ case KVM_RISCV_ISA_EXT_ZKSED:
+ case KVM_RISCV_ISA_EXT_ZKSH:
+ case KVM_RISCV_ISA_EXT_ZKT:
return false;
/* Extensions which can be disabled using Smstateen */
case KVM_RISCV_ISA_EXT_SSAIA:
From 14d70de562dfd78be638fc59b0a323235acc67be Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 20:47:58 +0530
Subject: [PATCH 027/637] KVM: riscv: selftests: Add scaler crypto extensions
to get-reg-list test
The KVM RISC-V allows scaler crypto extensions for Guest/VM so let us
add these extensions to get-reg-list test. This includes extensions
Zbkb, Zbkc, Zbkx, Zknd, Zkne, Zknh, Zkr, Zksed, Zksh, and Zkt.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
.../selftests/kvm/riscv/get-reg-list.c | 40 +++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 2e8e1c52b9ef..3f5674fbd680 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -50,6 +50,9 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKB:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
@@ -59,6 +62,13 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNE:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKNH:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKR:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
/*
* Like ISA_EXT registers, SBI_EXT registers are only visible when the
* host supports them and disabling them does not affect the visibility
@@ -396,6 +406,9 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZBA),
KVM_ISA_EXT_ARR(ZBB),
KVM_ISA_EXT_ARR(ZBC),
+ KVM_ISA_EXT_ARR(ZBKB),
+ KVM_ISA_EXT_ARR(ZBKC),
+ KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
@@ -405,6 +418,13 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZIFENCEI),
KVM_ISA_EXT_ARR(ZIHINTPAUSE),
KVM_ISA_EXT_ARR(ZIHPM),
+ KVM_ISA_EXT_ARR(ZKND),
+ KVM_ISA_EXT_ARR(ZKNE),
+ KVM_ISA_EXT_ARR(ZKNH),
+ KVM_ISA_EXT_ARR(ZKR),
+ KVM_ISA_EXT_ARR(ZKSED),
+ KVM_ISA_EXT_ARR(ZKSH),
+ KVM_ISA_EXT_ARR(ZKT),
};
if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
@@ -891,6 +911,9 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
@@ -900,6 +923,13 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkne, ZKNE);
+KVM_ISA_EXT_SIMPLE_CONFIG(zknh, ZKNH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
struct vcpu_reg_list *vcpu_configs[] = {
&config_sbi_base,
@@ -918,6 +948,9 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zba,
&config_zbb,
&config_zbc,
+ &config_zbkb,
+ &config_zbkc,
+ &config_zbkx,
&config_zbs,
&config_zicbom,
&config_zicboz,
@@ -927,5 +960,12 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zifencei,
&config_zihintpause,
&config_zihpm,
+ &config_zknd,
+ &config_zkne,
+ &config_zknh,
+ &config_zkr,
+ &config_zksed,
+ &config_zksh,
+ &config_zkt,
};
int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
From afd1ef3adfbc36e35fcf4f742fd90aea6480a276 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 21:38:43 +0530
Subject: [PATCH 028/637] RISC-V: KVM: Allow vector crypto extensions for
Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable vector crypto extensions for
Guest/VM. This includes extensions Zvbb, Zvbc, Zvkb, Zvkg,
Zvkned, Zvknha, Zvknhb, Zvksed, Zvksh, and Zvkt.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 10 ++++++++++
arch/riscv/kvm/vcpu_onereg.c | 20 ++++++++++++++++++++
2 files changed, 30 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 453edf620b87..e68ba0819ef7 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -150,6 +150,16 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZKSED,
KVM_RISCV_ISA_EXT_ZKSH,
KVM_RISCV_ISA_EXT_ZKT,
+ KVM_RISCV_ISA_EXT_ZVBB,
+ KVM_RISCV_ISA_EXT_ZVBC,
+ KVM_RISCV_ISA_EXT_ZVKB,
+ KVM_RISCV_ISA_EXT_ZVKG,
+ KVM_RISCV_ISA_EXT_ZVKNED,
+ KVM_RISCV_ISA_EXT_ZVKNHA,
+ KVM_RISCV_ISA_EXT_ZVKNHB,
+ KVM_RISCV_ISA_EXT_ZVKSED,
+ KVM_RISCV_ISA_EXT_ZVKSH,
+ KVM_RISCV_ISA_EXT_ZVKT,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 680da2a55da2..297acdcfed77 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -62,6 +62,16 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZKSED),
KVM_ISA_EXT_ARR(ZKSH),
KVM_ISA_EXT_ARR(ZKT),
+ KVM_ISA_EXT_ARR(ZVBB),
+ KVM_ISA_EXT_ARR(ZVBC),
+ KVM_ISA_EXT_ARR(ZVKB),
+ KVM_ISA_EXT_ARR(ZVKG),
+ KVM_ISA_EXT_ARR(ZVKNED),
+ KVM_ISA_EXT_ARR(ZVKNHA),
+ KVM_ISA_EXT_ARR(ZVKNHB),
+ KVM_ISA_EXT_ARR(ZVKSED),
+ KVM_ISA_EXT_ARR(ZVKSH),
+ KVM_ISA_EXT_ARR(ZVKT),
};
static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
@@ -121,6 +131,16 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZKSED:
case KVM_RISCV_ISA_EXT_ZKSH:
case KVM_RISCV_ISA_EXT_ZKT:
+ case KVM_RISCV_ISA_EXT_ZVBB:
+ case KVM_RISCV_ISA_EXT_ZVBC:
+ case KVM_RISCV_ISA_EXT_ZVKB:
+ case KVM_RISCV_ISA_EXT_ZVKG:
+ case KVM_RISCV_ISA_EXT_ZVKNED:
+ case KVM_RISCV_ISA_EXT_ZVKNHA:
+ case KVM_RISCV_ISA_EXT_ZVKNHB:
+ case KVM_RISCV_ISA_EXT_ZVKSED:
+ case KVM_RISCV_ISA_EXT_ZVKSH:
+ case KVM_RISCV_ISA_EXT_ZVKT:
return false;
/* Extensions which can be disabled using Smstateen */
case KVM_RISCV_ISA_EXT_SSAIA:
From 2ddf79070f7edada19fecec57d8591d6b718fa53 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 21:54:33 +0530
Subject: [PATCH 029/637] KVM: riscv: selftests: Add vector crypto extensions
to get-reg-list test
The KVM RISC-V allows vector crypto extensions for Guest/VM so let us
add these extensions to get-reg-list test. This includes extensions
Zvbb, Zvbc, Zvkb, Zvkg, Zvkned, Zvknha, Zvknhb, Zvksed, Zvksh, and Zvkt.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
.../selftests/kvm/riscv/get-reg-list.c | 40 +++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 3f5674fbd680..6b4ba06e26e5 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -69,6 +69,16 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHA:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNHB:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSED:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKSH:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKT:
/*
* Like ISA_EXT registers, SBI_EXT registers are only visible when the
* host supports them and disabling them does not affect the visibility
@@ -425,6 +435,16 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZKSED),
KVM_ISA_EXT_ARR(ZKSH),
KVM_ISA_EXT_ARR(ZKT),
+ KVM_ISA_EXT_ARR(ZVBB),
+ KVM_ISA_EXT_ARR(ZVBC),
+ KVM_ISA_EXT_ARR(ZVKB),
+ KVM_ISA_EXT_ARR(ZVKG),
+ KVM_ISA_EXT_ARR(ZVKNED),
+ KVM_ISA_EXT_ARR(ZVKNHA),
+ KVM_ISA_EXT_ARR(ZVKNHB),
+ KVM_ISA_EXT_ARR(ZVKSED),
+ KVM_ISA_EXT_ARR(ZVKSH),
+ KVM_ISA_EXT_ARR(ZVKT),
};
if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name))
@@ -930,6 +950,16 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknha, ZVKNHA);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvknhb, ZVKNHB);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksed, ZVKSED);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvksh, ZVKSH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvkt, ZVKT);
struct vcpu_reg_list *vcpu_configs[] = {
&config_sbi_base,
@@ -967,5 +997,15 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zksed,
&config_zksh,
&config_zkt,
+ &config_zvbb,
+ &config_zvbc,
+ &config_zvkb,
+ &config_zvkg,
+ &config_zvkned,
+ &config_zvknha,
+ &config_zvknhb,
+ &config_zvksed,
+ &config_zvksh,
+ &config_zvkt,
};
int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
From f3901ece5b3894177d1816208d0fb06b295617e0 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:01:55 +0530
Subject: [PATCH 030/637] RISC-V: KVM: Allow Zfh[min] extensions for Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zfh[min] extensions for Guest/VM.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 2 ++
arch/riscv/kvm/vcpu_onereg.c | 4 ++++
2 files changed, 6 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index e68ba0819ef7..a8411ae5cc85 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -160,6 +160,8 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZVKSED,
KVM_RISCV_ISA_EXT_ZVKSH,
KVM_RISCV_ISA_EXT_ZVKT,
+ KVM_RISCV_ISA_EXT_ZFH,
+ KVM_RISCV_ISA_EXT_ZFHMIN,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 297acdcfed77..e00745bf0590 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,6 +47,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZBKC),
KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
+ KVM_ISA_EXT_ARR(ZFH),
+ KVM_ISA_EXT_ARR(ZFHMIN),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
KVM_ISA_EXT_ARR(ZICNTR),
@@ -118,6 +120,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZBKC:
case KVM_RISCV_ISA_EXT_ZBKX:
case KVM_RISCV_ISA_EXT_ZBS:
+ case KVM_RISCV_ISA_EXT_ZFH:
+ case KVM_RISCV_ISA_EXT_ZFHMIN:
case KVM_RISCV_ISA_EXT_ZICNTR:
case KVM_RISCV_ISA_EXT_ZICOND:
case KVM_RISCV_ISA_EXT_ZICSR:
From 496ee21a17ce45e92483fdf1827ba91f4867f160 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:11:02 +0530
Subject: [PATCH 031/637] KVM: riscv: selftests: Add Zfh[min] extensions to
get-reg-list test
The KVM RISC-V allows Zfh[min] extensions for Guest/VM so let us
add these extensions to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6b4ba06e26e5..eeb9857feede 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -54,6 +54,8 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR:
@@ -420,6 +422,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZBKC),
KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
+ KVM_ISA_EXT_ARR(ZFH),
+ KVM_ISA_EXT_ARR(ZFHMIN),
KVM_ISA_EXT_ARR(ZICBOM),
KVM_ISA_EXT_ARR(ZICBOZ),
KVM_ISA_EXT_ARR(ZICNTR),
@@ -935,6 +939,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ);
KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
@@ -982,6 +988,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zbkc,
&config_zbkx,
&config_zbs,
+ &config_zfh,
+ &config_zfhmin,
&config_zicbom,
&config_zicboz,
&config_zicntr,
From ab6da9cdc3f3d1d091d657219fb6e98f710ee098 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:15:10 +0530
Subject: [PATCH 032/637] RISC-V: KVM: Allow Zihintntl extension for Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zihintntl extension for Guest/VM.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 1 +
arch/riscv/kvm/vcpu_onereg.c | 2 ++
2 files changed, 3 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index a8411ae5cc85..95e4d5a1793e 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -162,6 +162,7 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZVKT,
KVM_RISCV_ISA_EXT_ZFH,
KVM_RISCV_ISA_EXT_ZFHMIN,
+ KVM_RISCV_ISA_EXT_ZIHINTNTL,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index e00745bf0590..deceaa6f9cfa 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -55,6 +55,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZICOND),
KVM_ISA_EXT_ARR(ZICSR),
KVM_ISA_EXT_ARR(ZIFENCEI),
+ KVM_ISA_EXT_ARR(ZIHINTNTL),
KVM_ISA_EXT_ARR(ZIHINTPAUSE),
KVM_ISA_EXT_ARR(ZIHPM),
KVM_ISA_EXT_ARR(ZKND),
@@ -126,6 +127,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZICOND:
case KVM_RISCV_ISA_EXT_ZICSR:
case KVM_RISCV_ISA_EXT_ZIFENCEI:
+ case KVM_RISCV_ISA_EXT_ZIHINTNTL:
case KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
case KVM_RISCV_ISA_EXT_ZIHPM:
case KVM_RISCV_ISA_EXT_ZKND:
From 1a3bc507821d24a80a6af8beb08af8032c33ebd7 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:22:06 +0530
Subject: [PATCH 033/637] KVM: riscv: selftests: Add Zihintntl extension to
get-reg-list test
The KVM RISC-V allows Zihintntl extension for Guest/VM so let us
add this extension to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index eeb9857feede..c9a45e17267b 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -62,6 +62,7 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTNTL:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKND:
@@ -430,6 +431,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZICOND),
KVM_ISA_EXT_ARR(ZICSR),
KVM_ISA_EXT_ARR(ZIFENCEI),
+ KVM_ISA_EXT_ARR(ZIHINTNTL),
KVM_ISA_EXT_ARR(ZIHINTPAUSE),
KVM_ISA_EXT_ARR(ZIHPM),
KVM_ISA_EXT_ARR(ZKND),
@@ -947,6 +949,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR);
KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND);
KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR);
KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI);
+KVM_ISA_EXT_SIMPLE_CONFIG(zihintntl, ZIHINTNTL);
KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE);
KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM);
KVM_ISA_EXT_SIMPLE_CONFIG(zknd, ZKND);
@@ -996,6 +999,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zicond,
&config_zicsr,
&config_zifencei,
+ &config_zihintntl,
&config_zihintpause,
&config_zihpm,
&config_zknd,
From f46300285926c2b0d0c79bf40c87d45e169cecb6 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:26:05 +0530
Subject: [PATCH 034/637] RISC-V: KVM: Allow Zvfh[min] extensions for Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zvfh[min] extensions for Guest/VM.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 2 ++
arch/riscv/kvm/vcpu_onereg.c | 4 ++++
2 files changed, 6 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 95e4d5a1793e..7d07722aa1aa 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -163,6 +163,8 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZFH,
KVM_RISCV_ISA_EXT_ZFHMIN,
KVM_RISCV_ISA_EXT_ZIHINTNTL,
+ KVM_RISCV_ISA_EXT_ZVFH,
+ KVM_RISCV_ISA_EXT_ZVFHMIN,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index deceaa6f9cfa..707d9d9883c8 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -67,6 +67,8 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZKT),
KVM_ISA_EXT_ARR(ZVBB),
KVM_ISA_EXT_ARR(ZVBC),
+ KVM_ISA_EXT_ARR(ZVFH),
+ KVM_ISA_EXT_ARR(ZVFHMIN),
KVM_ISA_EXT_ARR(ZVKB),
KVM_ISA_EXT_ARR(ZVKG),
KVM_ISA_EXT_ARR(ZVKNED),
@@ -139,6 +141,8 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZKT:
case KVM_RISCV_ISA_EXT_ZVBB:
case KVM_RISCV_ISA_EXT_ZVBC:
+ case KVM_RISCV_ISA_EXT_ZVFH:
+ case KVM_RISCV_ISA_EXT_ZVFHMIN:
case KVM_RISCV_ISA_EXT_ZVKB:
case KVM_RISCV_ISA_EXT_ZVKG:
case KVM_RISCV_ISA_EXT_ZVKNED:
From 1216fdd99be113fa75ccdd0497802bd0fe4369aa Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:35:06 +0530
Subject: [PATCH 035/637] KVM: riscv: selftests: Add Zvfh[min] extensions to
get-reg-list test
The KVM RISC-V allows Zvfh[min] extensions for Guest/VM so let us
add these extensions to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index c9a45e17267b..02ec1a44624a 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -74,6 +74,8 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFHMIN:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKB:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKG:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVKNED:
@@ -443,6 +445,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZKT),
KVM_ISA_EXT_ARR(ZVBB),
KVM_ISA_EXT_ARR(ZVBC),
+ KVM_ISA_EXT_ARR(ZVFH),
+ KVM_ISA_EXT_ARR(ZVFHMIN),
KVM_ISA_EXT_ARR(ZVKB),
KVM_ISA_EXT_ARR(ZVKG),
KVM_ISA_EXT_ARR(ZVKNED),
@@ -961,6 +965,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH);
+KVM_ISA_EXT_SIMPLE_CONFIG(zvfhmin, ZVFHMIN);
KVM_ISA_EXT_SIMPLE_CONFIG(zvkb, ZVKB);
KVM_ISA_EXT_SIMPLE_CONFIG(zvkg, ZVKG);
KVM_ISA_EXT_SIMPLE_CONFIG(zvkned, ZVKNED);
@@ -1011,6 +1017,8 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zkt,
&config_zvbb,
&config_zvbc,
+ &config_zvfh,
+ &config_zvfhmin,
&config_zvkb,
&config_zvkg,
&config_zvkned,
From 41182cc6f507011a2e6c82657779e451ed9942bb Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:43:12 +0530
Subject: [PATCH 036/637] RISC-V: KVM: Allow Zfa extension for Guest/VM
We extend the KVM ISA extension ONE_REG interface to allow KVM
user space to detect and enable Zfa extension for Guest/VM.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/include/uapi/asm/kvm.h | 1 +
arch/riscv/kvm/vcpu_onereg.c | 2 ++
2 files changed, 3 insertions(+)
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7d07722aa1aa..7499e88a947c 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -165,6 +165,7 @@ enum KVM_RISCV_ISA_EXT_ID {
KVM_RISCV_ISA_EXT_ZIHINTNTL,
KVM_RISCV_ISA_EXT_ZVFH,
KVM_RISCV_ISA_EXT_ZVFHMIN,
+ KVM_RISCV_ISA_EXT_ZFA,
KVM_RISCV_ISA_EXT_MAX,
};
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 707d9d9883c8..5f7355e96008 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,6 +47,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
KVM_ISA_EXT_ARR(ZBKC),
KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
+ KVM_ISA_EXT_ARR(ZFA),
KVM_ISA_EXT_ARR(ZFH),
KVM_ISA_EXT_ARR(ZFHMIN),
KVM_ISA_EXT_ARR(ZICBOM),
@@ -123,6 +124,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
case KVM_RISCV_ISA_EXT_ZBKC:
case KVM_RISCV_ISA_EXT_ZBKX:
case KVM_RISCV_ISA_EXT_ZBS:
+ case KVM_RISCV_ISA_EXT_ZFA:
case KVM_RISCV_ISA_EXT_ZFH:
case KVM_RISCV_ISA_EXT_ZFHMIN:
case KVM_RISCV_ISA_EXT_ZICNTR:
From 4d0e8f9a361b3a1f7b67418c536b258323de734f Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 27 Nov 2023 22:45:35 +0530
Subject: [PATCH 037/637] KVM: riscv: selftests: Add Zfa extension to
get-reg-list test
The KVM RISC-V allows Zfa extension for Guest/VM so let us
add this extension to get-reg-list test.
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 02ec1a44624a..4fd0f8951574 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -54,6 +54,7 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKC:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBKX:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFA:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFH:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM:
@@ -425,6 +426,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(ZBKC),
KVM_ISA_EXT_ARR(ZBKX),
KVM_ISA_EXT_ARR(ZBS),
+ KVM_ISA_EXT_ARR(ZFA),
KVM_ISA_EXT_ARR(ZFH),
KVM_ISA_EXT_ARR(ZFHMIN),
KVM_ISA_EXT_ARR(ZICBOM),
@@ -945,6 +947,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB);
KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC);
KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX);
KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA);
KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH);
KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN);
KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM);
@@ -997,6 +1000,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_zbkc,
&config_zbkx,
&config_zbs,
+ &config_zfa,
&config_zfh,
&config_zfhmin,
&config_zicbom,
From 741ba0134fa7822fcf4e4a0a537a5c4cfd706b20 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 27 Dec 2023 16:21:24 +0100
Subject: [PATCH 038/637] pmdomain: core: Move the unused cleanup to a _sync
initcall
The unused clock cleanup uses the _sync initcall to give all users at
earlier initcalls time to probe. Do the same to avoid leaving some PDs
dangling at "on" (which actually happened on qcom!).
Fixes: 2fe71dcdfd10 ("PM / domains: Add late_initcall to disable unused PM domains")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231227-topic-pmdomain_sync_cleanup-v1-1-5f36769d538b@linaro.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/pmdomain/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index a1f6cba3ae6c..18e232b5ed53 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -1109,7 +1109,7 @@ static int __init genpd_power_off_unused(void)
return 0;
}
-late_initcall(genpd_power_off_unused);
+late_initcall_sync(genpd_power_off_unused);
#ifdef CONFIG_PM_SLEEP
From f0e4a1356466ec1858ae8e5c70bea2ce5e55008b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 12 Jan 2024 17:33:55 +0100
Subject: [PATCH 039/637] pmdomain: renesas: r8a77980-sysc: CR7 must be always
on
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The power domain containing the Cortex-R7 CPU core on the R-Car V3H SoC
must always be in power-on state, unlike on other SoCs in the R-Car Gen3
family. See Table 9.4 "Power domains" in the R-Car Series, 3rd
Generation Hardware User’s Manual Rev.1.00 and later.
Fix this by marking the domain as a CPU domain without control
registers, so the driver will not touch it.
Fixes: 41d6d8bd8ae9 ("soc: renesas: rcar-sysc: add R8A77980 support")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/fdad9a86132d53ecddf72b734dac406915c4edc0.1705076735.git.geert+renesas@glider.be
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/pmdomain/renesas/r8a77980-sysc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/pmdomain/renesas/r8a77980-sysc.c b/drivers/pmdomain/renesas/r8a77980-sysc.c
index 39ca84a67daa..621e411fc999 100644
--- a/drivers/pmdomain/renesas/r8a77980-sysc.c
+++ b/drivers/pmdomain/renesas/r8a77980-sysc.c
@@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = {
PD_CPU_NOCR },
{ "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU,
PD_CPU_NOCR },
- { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON },
+ { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON,
+ PD_CPU_NOCR },
{ "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON },
{ "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR },
{ "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR },
From 6154fb9c2134f8d9534b2de10491aa3a22f3c9ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?N=C3=ADcolas=20F=2E=20R=2E=20A=2E=20Prado?=
<nfraprado@collabora.com>
Date: Mon, 22 Jan 2024 11:29:18 -0300
Subject: [PATCH 040/637] kselftest: dt: Stop relying on dirname to improve
performance
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When walking directory trees, instead of looking for specific files and
running dirname to get the parent folder, traverse all folders and
ignore the ones not containing the desired files. This avoids the need
to call dirname inside the loop, which drastically decreases run time:
Running locally on a mt8192-asurada-spherion, which reports 160 test
cases, has gone from 5.5s to 2.9s, while running remotely with an
nfsroot has gone from 13.5s to 5.5s.
This change has a side-effect, which is that the root DT node now
also shows in the output, even though it isn't expected to bind to a
driver. However there shouldn't be a matching driver for the board
compatible, so the end result will be just an extra skipped test:
ok 1 / # SKIP
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/310391e8-fdf2-4c2f-a680-7744eb685177@sirena.org.uk
Fixes: 14571ab1ad21 ("kselftest: Add new test for detecting unprobed Devicetree devices")
Tested-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Nícolas F. R. A. Prado <nfraprado@collabora.com>
Link: https://lore.kernel.org/r/20240122-dt-kselftest-dirname-perf-fix-v2-1-f1630532fd38@collabora.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
tools/testing/selftests/dt/test_unprobed_devices.sh | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh
index b07af2a4c4de..7fae90293a9d 100755
--- a/tools/testing/selftests/dt/test_unprobed_devices.sh
+++ b/tools/testing/selftests/dt/test_unprobed_devices.sh
@@ -33,8 +33,8 @@ if [[ ! -d "${PDT}" ]]; then
fi
nodes_compatible=$(
- for node_compat in $(find ${PDT} -name compatible); do
- node=$(dirname "${node_compat}")
+ for node in $(find ${PDT} -type d); do
+ [ ! -f "${node}"/compatible ] && continue
# Check if node is available
if [[ -e "${node}"/status ]]; then
status=$(tr -d '\000' < "${node}"/status)
@@ -46,10 +46,11 @@ nodes_compatible=$(
nodes_dev_bound=$(
IFS=$'\n'
- for uevent in $(find /sys/devices -name uevent); do
- if [[ -d "$(dirname "${uevent}")"/driver ]]; then
- grep '^OF_FULLNAME=' "${uevent}" | sed -e 's|OF_FULLNAME=||'
- fi
+ for dev_dir in $(find /sys/devices -type d); do
+ [ ! -f "${dev_dir}"/uevent ] && continue
+ [ ! -d "${dev_dir}"/driver ] && continue
+
+ grep '^OF_FULLNAME=' "${dev_dir}"/uevent | sed -e 's|OF_FULLNAME=||'
done
)
From 95a0d596bbd0552a78e13ced43f2be1038883c81 Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Fri, 8 Dec 2023 15:31:19 +0800
Subject: [PATCH 041/637] iio: core: fix memleak in iio_device_register_sysfs
When iio_device_register_sysfs_group() fails, we should
free iio_dev_opaque->chan_attr_group.attrs to prevent
potential memleak.
Fixes: 32f171724e5c ("iio: core: rework iio device group creation")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Link: https://lore.kernel.org/r/20231208073119.29283-1-dinghao.liu@zju.edu.cn
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/industrialio-core.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 9a85752124dd..173dc00762a1 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1584,10 +1584,13 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev)
ret = iio_device_register_sysfs_group(indio_dev,
&iio_dev_opaque->chan_attr_group);
if (ret)
- goto error_clear_attrs;
+ goto error_free_chan_attrs;
return 0;
+error_free_chan_attrs:
+ kfree(iio_dev_opaque->chan_attr_group.attrs);
+ iio_dev_opaque->chan_attr_group.attrs = NULL;
error_clear_attrs:
iio_free_chan_devattr_list(&iio_dev_opaque->channel_attr_list);
From b67f3e653e305abf1471934d7b9fdb9ad2df3eef Mon Sep 17 00:00:00 2001
From: Sam Protsenko <semen.protsenko@linaro.org>
Date: Wed, 20 Dec 2023 12:47:53 -0600
Subject: [PATCH 042/637] iio: pressure: bmp280: Add missing bmp085 to SPI id
table
"bmp085" is missing in bmp280_spi_id[] table, which leads to the next
warning in dmesg:
SPI driver bmp280 has no spi_device_id for bosch,bmp085
Add "bmp085" to bmp280_spi_id[] by mimicking its existing description in
bmp280_of_spi_match[] table to fix the above warning.
Signed-off-by: Sam Protsenko <semen.protsenko@linaro.org>
Fixes: b26b4e91700f ("iio: pressure: bmp280: add SPI interface driver")
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/pressure/bmp280-spi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index 433d6fac83c4..e8a5fed07e88 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -87,6 +87,7 @@ static const struct of_device_id bmp280_of_spi_match[] = {
MODULE_DEVICE_TABLE(of, bmp280_of_spi_match);
static const struct spi_device_id bmp280_spi_id[] = {
+ { "bmp085", (kernel_ulong_t)&bmp180_chip_info },
{ "bmp180", (kernel_ulong_t)&bmp180_chip_info },
{ "bmp181", (kernel_ulong_t)&bmp180_chip_info },
{ "bmp280", (kernel_ulong_t)&bmp280_chip_info },
From 792595bab4925aa06532a14dd256db523eb4fa5e Mon Sep 17 00:00:00 2001
From: "zhili.liu" <zhili.liu@ucas.com.cn>
Date: Tue, 2 Jan 2024 09:07:11 +0800
Subject: [PATCH 043/637] iio: magnetometer: rm3100: add boundary check for the
value read from RM3100_REG_TMRC
Recently, we encounter kernel crash in function rm3100_common_probe
caused by out of bound access of array rm3100_samp_rates (because of
underlying hardware failures). Add boundary check to prevent out of
bound access.
Fixes: 121354b2eceb ("iio: magnetometer: Add driver support for PNI RM3100")
Suggested-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Signed-off-by: zhili.liu <zhili.liu@ucas.com.cn>
Link: https://lore.kernel.org/r/1704157631-3814-1-git-send-email-zhouzhouyi@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/magnetometer/rm3100-core.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c
index 69938204456f..42b70cd42b39 100644
--- a/drivers/iio/magnetometer/rm3100-core.c
+++ b/drivers/iio/magnetometer/rm3100-core.c
@@ -530,6 +530,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
struct rm3100_data *data;
unsigned int tmp;
int ret;
+ int samp_rate_index;
indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
if (!indio_dev)
@@ -586,9 +587,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq)
ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp);
if (ret < 0)
return ret;
+
+ samp_rate_index = tmp - RM3100_TMRC_OFFSET;
+ if (samp_rate_index < 0 || samp_rate_index >= RM3100_SAMP_NUM) {
+ dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n");
+ return -EINVAL;
+ }
/* Initializing max wait time, which is double conversion time. */
- data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2]
- * 2;
+ data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2;
/* Cycle count values may not be what we want. */
if ((tmp - RM3100_TMRC_OFFSET) == 0)
From 35ec2d03b282a939949090bd8c39eb37a5856721 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 10 Jan 2024 10:56:11 -0800
Subject: [PATCH 044/637] iio: imu: bno055: serdev requires REGMAP
There are a ton of build errors when REGMAP is not set, so select
REGMAP to fix all of them.
Examples (not all of them):
../drivers/iio/imu/bno055/bno055_ser_core.c:495:15: error: variable 'bno055_ser_regmap_bus' has initializer but incomplete type
495 | static struct regmap_bus bno055_ser_regmap_bus = {
../drivers/iio/imu/bno055/bno055_ser_core.c:496:10: error: 'struct regmap_bus' has no member named 'write'
496 | .write = bno055_ser_write_reg,
../drivers/iio/imu/bno055/bno055_ser_core.c:497:10: error: 'struct regmap_bus' has no member named 'read'
497 | .read = bno055_ser_read_reg,
../drivers/iio/imu/bno055/bno055_ser_core.c: In function 'bno055_ser_probe':
../drivers/iio/imu/bno055/bno055_ser_core.c:532:18: error: implicit declaration of function 'devm_regmap_init'; did you mean 'vmem_map_init'? [-Werror=implicit-function-declaration]
532 | regmap = devm_regmap_init(&serdev->dev, &bno055_ser_regmap_bus,
../drivers/iio/imu/bno055/bno055_ser_core.c:532:16: warning: assignment to 'struct regmap *' from 'int' makes pointer from integer without a cast [-Wint-conversion]
532 | regmap = devm_regmap_init(&serdev->dev, &bno055_ser_regmap_bus,
../drivers/iio/imu/bno055/bno055_ser_core.c: At top level:
../drivers/iio/imu/bno055/bno055_ser_core.c:495:26: error: storage size of 'bno055_ser_regmap_bus' isn't known
495 | static struct regmap_bus bno055_ser_regmap_bus = {
Fixes: 2eef5a9cc643 ("iio: imu: add BNO055 serdev driver")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Andrea Merello <andrea.merello@iit.it>
Cc: Jonathan Cameron <jic23@kernel.org>
Cc: Lars-Peter Clausen <lars@metafoo.de>
Cc: linux-iio@vger.kernel.org
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240110185611.19723-1-rdunlap@infradead.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/imu/bno055/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig
index 83e53acfbe88..c7f5866a177d 100644
--- a/drivers/iio/imu/bno055/Kconfig
+++ b/drivers/iio/imu/bno055/Kconfig
@@ -8,6 +8,7 @@ config BOSCH_BNO055
config BOSCH_BNO055_SERIAL
tristate "Bosch BNO055 attached via UART"
depends on SERIAL_DEV_BUS
+ select REGMAP
select BOSCH_BNO055
help
Enable this to support Bosch BNO055 IMUs attached via UART.
From f1dfcbaa7b9d131859b0167c428480ae6e7e817d Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sun, 21 Jan 2024 13:46:16 +0000
Subject: [PATCH 045/637] iio: humidity: hdc3020: Add Makefile, Kconfig and
MAINTAINERS entry
Something when wrong when applying the original patch and only the
c file made it in. Here the rest of the changes are applied.
Fixes: c9180b8e39be ("iio: humidity: Add driver for ti HDC302x humidity sensors")
Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Cc: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Cc: Li peiyu <579lpy@gmail.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
---
MAINTAINERS | 8 ++++++++
drivers/iio/humidity/Kconfig | 12 ++++++++++++
drivers/iio/humidity/Makefile | 1 +
3 files changed, 21 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a69..1b590e6f6bdd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22005,6 +22005,14 @@ F: Documentation/devicetree/bindings/media/i2c/ti,ds90*
F: drivers/media/i2c/ds90*
F: include/media/i2c/ds90*
+TI HDC302X HUMIDITY DRIVER
+M: Javier Carrasco <javier.carrasco.cruz@gmail.com>
+M: Li peiyu <579lpy@gmail.com>
+L: linux-iio@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/iio/humidity/ti,hdc3020.yaml
+F: drivers/iio/humidity/hdc3020.c
+
TI ICSSG ETHERNET DRIVER (ICSSG)
R: MD Danish Anwar <danishanwar@ti.com>
R: Roger Quadros <rogerq@kernel.org>
diff --git a/drivers/iio/humidity/Kconfig b/drivers/iio/humidity/Kconfig
index 2de5494e7c22..b15b7a3b66d5 100644
--- a/drivers/iio/humidity/Kconfig
+++ b/drivers/iio/humidity/Kconfig
@@ -48,6 +48,18 @@ config HDC2010
To compile this driver as a module, choose M here: the module
will be called hdc2010.
+config HDC3020
+ tristate "TI HDC3020 relative humidity and temperature sensor"
+ depends on I2C
+ select CRC8
+ help
+ Say yes here to build support for the Texas Instruments
+ HDC3020, HDC3021 and HDC3022 relative humidity and temperature
+ sensors.
+
+ To compile this driver as a module, choose M here: the module
+ will be called hdc3020.
+
config HID_SENSOR_HUMIDITY
tristate "HID Environmental humidity sensor"
depends on HID_SENSOR_HUB
diff --git a/drivers/iio/humidity/Makefile b/drivers/iio/humidity/Makefile
index f19ff3de97c5..5fbeef299f61 100644
--- a/drivers/iio/humidity/Makefile
+++ b/drivers/iio/humidity/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_AM2315) += am2315.o
obj-$(CONFIG_DHT11) += dht11.o
obj-$(CONFIG_HDC100X) += hdc100x.o
obj-$(CONFIG_HDC2010) += hdc2010.o
+obj-$(CONFIG_HDC3020) += hdc3020.o
obj-$(CONFIG_HID_SENSOR_HUMIDITY) += hid-sensor-humidity.o
hts221-y := hts221_core.o \
From 8e98b87f515d8c4bae521048a037b2cc431c3fd5 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Wed, 17 Jan 2024 14:10:49 +0100
Subject: [PATCH 046/637] iio: imu: adis: ensure proper DMA alignment
Aligning the buffer to the L1 cache is not sufficient in some platforms
as they might have larger cacheline sizes for caches after L1 and thus,
we can't guarantee DMA safety.
That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same
for the sigma_delta ADCs.
[1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/
Fixes: ccd2b52f4ac6 ("staging:iio: Add common ADIS library")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20240117-adis-improv-v1-1-7f90e9fad200@analog.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
include/linux/iio/imu/adis.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index dc9ea299e088..8898966bc0f0 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -11,6 +11,7 @@
#include <linux/spi/spi.h>
#include <linux/interrupt.h>
+#include <linux/iio/iio.h>
#include <linux/iio/types.h>
#define ADIS_WRITE_REG(reg) ((0x80 | (reg)))
@@ -131,7 +132,7 @@ struct adis {
unsigned long irq_flag;
void *buffer;
- u8 tx[10] ____cacheline_aligned;
+ u8 tx[10] __aligned(IIO_DMA_MINALIGN);
u8 rx[4];
};
From 59598510be1d49e1cff7fd7593293bb8e1b2398b Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Wed, 17 Jan 2024 13:41:03 +0100
Subject: [PATCH 047/637] iio: adc: ad_sigma_delta: ensure proper DMA alignment
Aligning the buffer to the L1 cache is not sufficient in some platforms
as they might have larger cacheline sizes for caches after L1 and thus,
we can't guarantee DMA safety.
That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same
for the sigma_delta ADCs.
[1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/
Fixes: 0fb6ee8d0b5e ("iio: ad_sigma_delta: Don't put SPI transfer buffer on the stack")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20240117-dev_sigma_delta_no_irq_flags-v1-1-db39261592cf@analog.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
include/linux/iio/adc/ad_sigma_delta.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 7852f6c9a714..719cf9cc6e1a 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -8,6 +8,8 @@
#ifndef __AD_SIGMA_DELTA_H__
#define __AD_SIGMA_DELTA_H__
+#include <linux/iio/iio.h>
+
enum ad_sigma_delta_mode {
AD_SD_MODE_CONTINUOUS = 0,
AD_SD_MODE_SINGLE = 1,
@@ -99,7 +101,7 @@ struct ad_sigma_delta {
* 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
* rounded to 16 bytes to take into account padding.
*/
- uint8_t tx_buf[4] ____cacheline_aligned;
+ uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN);
uint8_t rx_buf[16] __aligned(8);
};
From 9c46e3a5232d855a65f440b298a2a66497f799d2 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 8 Jan 2024 12:07:02 +0300
Subject: [PATCH 048/637] iio: adc: ad7091r8: Fix error code in
ad7091r8_gpio_setup()
There is a copy and paste error so it accidentally returns ->convst_gpio
instead of ->reset_gpio. Fix it.
Fixes: 0b76ff46c463 ("iio: adc: Add support for AD7091R-8")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Marcelo Schmitt <marcelo.schmitt1@gmail.com>
Link: https://lore.kernel.org/r/fd905ad0-6413-489c-9a3b-90c0cdb35ec9@moroto.mountain
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/adc/ad7091r8.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iio/adc/ad7091r8.c b/drivers/iio/adc/ad7091r8.c
index 57700f124803..700564305057 100644
--- a/drivers/iio/adc/ad7091r8.c
+++ b/drivers/iio/adc/ad7091r8.c
@@ -195,7 +195,7 @@ static int ad7091r8_gpio_setup(struct ad7091r_state *st)
st->reset_gpio = devm_gpiod_get_optional(st->dev, "reset",
GPIOD_OUT_HIGH);
if (IS_ERR(st->reset_gpio))
- return dev_err_probe(st->dev, PTR_ERR(st->convst_gpio),
+ return dev_err_probe(st->dev, PTR_ERR(st->reset_gpio),
"Error on requesting reset GPIO\n");
if (st->reset_gpio) {
From c41336f4d69057cbf88fed47951379b384540df5 Mon Sep 17 00:00:00 2001
From: Eugen Hristev <eugen.hristev@collabora.com>
Date: Mon, 25 Dec 2023 15:36:15 +0200
Subject: [PATCH 049/637] pmdomain: mediatek: fix race conditions with genpd
If the power domains are registered first with genpd and *after that*
the driver attempts to power them on in the probe sequence, then it is
possible that a race condition occurs if genpd tries to power them on
in the same time.
The same is valid for powering them off before unregistering them
from genpd.
Attempt to fix race conditions by first removing the domains from genpd
and *after that* powering down domains.
Also first power up the domains and *after that* register them
to genpd.
Fixes: 59b644b01cf4 ("soc: mediatek: Add MediaTek SCPSYS power domains")
Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20231225133615.78993-1-eugen.hristev@collabora.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/pmdomain/mediatek/mtk-pm-domains.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c
index e26dc17d07ad..e274e3315fe7 100644
--- a/drivers/pmdomain/mediatek/mtk-pm-domains.c
+++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c
@@ -561,6 +561,11 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
goto err_put_node;
}
+ /* recursive call to add all subdomains */
+ ret = scpsys_add_subdomain(scpsys, child);
+ if (ret)
+ goto err_put_node;
+
ret = pm_genpd_add_subdomain(parent_pd, child_pd);
if (ret) {
dev_err(scpsys->dev, "failed to add %s subdomain to parent %s\n",
@@ -570,11 +575,6 @@ static int scpsys_add_subdomain(struct scpsys *scpsys, struct device_node *paren
dev_dbg(scpsys->dev, "%s add subdomain: %s\n", parent_pd->name,
child_pd->name);
}
-
- /* recursive call to add all subdomains */
- ret = scpsys_add_subdomain(scpsys, child);
- if (ret)
- goto err_put_node;
}
return 0;
@@ -588,9 +588,6 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
{
int ret;
- if (scpsys_domain_is_on(pd))
- scpsys_power_off(&pd->genpd);
-
/*
* We're in the error cleanup already, so we only complain,
* but won't emit another error on top of the original one.
@@ -600,6 +597,8 @@ static void scpsys_remove_one_domain(struct scpsys_domain *pd)
dev_err(pd->scpsys->dev,
"failed to remove domain '%s' : %d - state may be inconsistent\n",
pd->genpd.name, ret);
+ if (scpsys_domain_is_on(pd))
+ scpsys_power_off(&pd->genpd);
clk_bulk_put(pd->num_clks, pd->clks);
clk_bulk_put(pd->num_subsys_clks, pd->subsys_clks);
From afb2a4fb84555ef9e61061f6ea63ed7087b295d5 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 12 Jan 2024 19:37:29 +0100
Subject: [PATCH 050/637] riscv/efistub: Ensure GP-relative addressing is not
used
The cflags for the RISC-V efistub were missing -mno-relax, thus were
under the risk that the compiler could use GP-relative addressing. That
happened for _edata with binutils-2.41 and kernel 6.1, causing the
relocation to fail due to an invalid kernel_size in handle_kernel_image.
It was not yet observed with newer versions, but that may just be luck.
Cc: <stable@vger.kernel.org>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/libstub/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 06964a3c130f..d561d7de46a9 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -28,7 +28,7 @@ cflags-$(CONFIG_ARM) += -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
-DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
-DEFI_HAVE_STRCMP -fno-builtin -fpic \
$(call cc-option,-mno-single-pic-base)
-cflags-$(CONFIG_RISCV) += -fpic -DNO_ALTERNATIVE
+cflags-$(CONFIG_RISCV) += -fpic -DNO_ALTERNATIVE -mno-relax
cflags-$(CONFIG_LOONGARCH) += -fpie
cflags-$(CONFIG_EFI_PARAMS_FROM_FDT) += -I$(srctree)/scripts/dtc/libfdt
From d2baf8cc82c17459fca019a12348efcf86bfec29 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 16 Jan 2024 14:52:27 +0100
Subject: [PATCH 051/637] riscv/efistub: Tighten ELF relocation check
The EFI stub makefile contains logic to ensure that the objects that
make up the stub do not contain relocations that require runtime fixups
(typically to account for the runtime load address of the executable)
On RISC-V, we also avoid GP based relocations, as they require that GP
is assigned the correct base in the startup code, which is not
implemented in the EFI stub.
So add these relocation types to the grep expression that is used to
carry out this check.
Link: https://lkml.kernel.org/r/42c63cb9-87d0-49db-9af8-95771b186684%40siemens.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/libstub/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d561d7de46a9..73f4810f6db3 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -143,7 +143,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS
# exist.
STUBCOPY_FLAGS-$(CONFIG_RISCV) += --prefix-alloc-sections=.init \
--prefix-symbols=__efistub_
-STUBCOPY_RELOC-$(CONFIG_RISCV) := R_RISCV_HI20
+STUBCOPY_RELOC-$(CONFIG_RISCV) := -E R_RISCV_HI20\|R_RISCV_$(BITS)\|R_RISCV_RELAX
# For LoongArch, keep all the symbols in .init section and make sure that no
# absolute symbols references exist.
From 1793ce9f205efe07ca2992ef129b86dab2c329f5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 30 Dec 2023 22:08:23 -0800
Subject: [PATCH 052/637] drm/msm/dpu: fix kernel-doc warnings
Correct all kernel-doc warnings in dpu_encoder.c and dpu_rm.c:
dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb' description in 'dpu_encoder_virt'
dpu_encoder.c:212: warning: Excess struct member 'crtc_kickoff_cb_data' description in 'dpu_encoder_virt'
dpu_encoder.c:212: warning: Excess struct member 'debugfs_root' description in 'dpu_encoder_virt'
dpu_rm.c:35: warning: Excess struct member 'hw_res' description in 'dpu_rm_requirements'
dpu_rm.c:208: warning: No description found for return value of '_dpu_rm_get_lm_peer'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Sean Paul <sean@poorly.run>
Cc: Marijn Suijten <marijn.suijten@somainline.org>
Cc: linux-arm-msm@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: freedreno@lists.freedesktop.org
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Paloma Arellano <quic_parellan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312170641.5exlvQQx-lkp@intel.com/
Fixes: 62d35629da80 ("drm/msm/dpu: move encoder status to standard encoder debugfs dir")
Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support")
Patchwork: https://patchwork.freedesktop.org/patch/572962/
Link: https://lore.kernel.org/r/20231231060823.1934-1-rdunlap@infradead.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ----
drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 3 ++-
2 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 83380bc92a00..f2b82ca5efb3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -144,10 +144,6 @@ enum dpu_enc_rc_states {
* to track crtc in the disable() hook which is called
* _after_ encoder_mask is cleared.
* @connector: If a mode is set, cached pointer to the active connector
- * @crtc_kickoff_cb: Callback into CRTC that will flush & start
- * all CTL paths
- * @crtc_kickoff_cb_data: Opaque user data given to crtc_kickoff_cb
- * @debugfs_root: Debug file system root file node
* @enc_lock: Lock around physical encoder
* create/destroy/enable/disable
* @frame_busy_mask: Bitmask tracking which phys_enc we are still
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index b58a9c2ae326..724537ab776d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -29,7 +29,6 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
/**
* struct dpu_rm_requirements - Reservation requirements parameter bundle
* @topology: selected topology for the display
- * @hw_res: Hardware resources required as reported by the encoders
*/
struct dpu_rm_requirements {
struct msm_display_topology topology;
@@ -204,6 +203,8 @@ static bool _dpu_rm_needs_split_display(const struct msm_display_topology *top)
* _dpu_rm_get_lm_peer - get the id of a mixer which is a peer of the primary
* @rm: dpu resource manager handle
* @primary_idx: index of primary mixer in rm->mixer_blks[]
+ *
+ * Returns: lm peer mixed id on success or %-EINVAL on error
*/
static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx)
{
From 77e8aad5519e04f6c1e132aaec1c5f8faf41844f Mon Sep 17 00:00:00 2001
From: Kuogee Hsieh <quic_khsieh@quicinc.com>
Date: Wed, 10 Jan 2024 12:18:51 -0800
Subject: [PATCH 053/637] drm/msms/dp: fixed link clock divider bits be over
written in BPC unknown case
Since the value of DP_TEST_BIT_DEPTH_8 is already left shifted, in the
BPC unknown case, the additional shift causes spill over to the other
bits of the [DP_CONFIGURATION_CTRL] register.
Fix this by changing the return value of dp_link_get_test_bits_depth()
in the BPC unknown case to (DP_TEST_BIT_DEPTH_8 >> DP_TEST_BIT_DEPTH_SHIFT).
Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: Kuogee Hsieh <quic_khsieh@quicinc.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/573989/
Link: https://lore.kernel.org/r/1704917931-30133-1-git-send-email-quic_khsieh@quicinc.com
[quic_abhinavk@quicinc.com: fix minor checkpatch warning to align with opening braces]
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/dp/dp_ctrl.c | 5 -----
drivers/gpu/drm/msm/dp/dp_link.c | 10 +++++++---
2 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 77a8d9366ed7..fb588fde298a 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -135,11 +135,6 @@ static void dp_ctrl_config_ctrl(struct dp_ctrl_private *ctrl)
tbd = dp_link_get_test_bits_depth(ctrl->link,
ctrl->panel->dp_mode.bpp);
- if (tbd == DP_TEST_BIT_DEPTH_UNKNOWN) {
- pr_debug("BIT_DEPTH not set. Configure default\n");
- tbd = DP_TEST_BIT_DEPTH_8;
- }
-
config |= tbd << DP_CONFIGURATION_CTRL_BPC_SHIFT;
/* Num of Lanes */
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index 98427d45e9a7..a0015b9e79eb 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -1179,6 +1179,9 @@ void dp_link_reset_phy_params_vx_px(struct dp_link *dp_link)
u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
{
u32 tbd;
+ struct dp_link_private *link;
+
+ link = container_of(dp_link, struct dp_link_private, dp_link);
/*
* Few simplistic rules and assumptions made here:
@@ -1196,12 +1199,13 @@ u32 dp_link_get_test_bits_depth(struct dp_link *dp_link, u32 bpp)
tbd = DP_TEST_BIT_DEPTH_10;
break;
default:
- tbd = DP_TEST_BIT_DEPTH_UNKNOWN;
+ drm_dbg_dp(link->drm_dev, "bpp=%d not supported, use bpc=8\n",
+ bpp);
+ tbd = DP_TEST_BIT_DEPTH_8;
break;
}
- if (tbd != DP_TEST_BIT_DEPTH_UNKNOWN)
- tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
+ tbd = (tbd >> DP_TEST_BIT_DEPTH_SHIFT);
return tbd;
}
From fcccdafd91f8bdde568b86ff70848cf83f029add Mon Sep 17 00:00:00 2001
From: Kuogee Hsieh <quic_khsieh@quicinc.com>
Date: Wed, 17 Jan 2024 13:13:30 -0800
Subject: [PATCH 054/637] drm/msm/dp: return correct Colorimetry for
DP_TEST_DYNAMIC_RANGE_CEA case
MSA MISC0 bit 1 to 7 contains Colorimetry Indicator Field.
dp_link_get_colorimetry_config() returns wrong colorimetry value
in the DP_TEST_DYNAMIC_RANGE_CEA case in the current implementation.
Hence fix this problem by having dp_link_get_colorimetry_config()
return defined CEA RGB colorimetry value in the case of
DP_TEST_DYNAMIC_RANGE_CEA.
Changes in V2:
-- drop retrieving colorimetry from colorspace
-- drop dr = link->dp_link.test_video.test_dyn_range assignment
Changes in V3:
-- move defined MISCr0a Colorimetry vale to dp_reg.h
-- rewording commit title
-- rewording commit text to more precise describe this patch
Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: Kuogee Hsieh <quic_khsieh@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/574888/
Link: https://lore.kernel.org/r/1705526010-597-1-git-send-email-quic_khsieh@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/dp/dp_link.c | 12 +++++++-----
drivers/gpu/drm/msm/dp/dp_reg.h | 3 +++
2 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c
index a0015b9e79eb..49dfac1fd1ef 100644
--- a/drivers/gpu/drm/msm/dp/dp_link.c
+++ b/drivers/gpu/drm/msm/dp/dp_link.c
@@ -7,6 +7,7 @@
#include <drm/drm_print.h>
+#include "dp_reg.h"
#include "dp_link.h"
#include "dp_panel.h"
@@ -1082,7 +1083,7 @@ int dp_link_process_request(struct dp_link *dp_link)
int dp_link_get_colorimetry_config(struct dp_link *dp_link)
{
- u32 cc;
+ u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB;
struct dp_link_private *link;
if (!dp_link) {
@@ -1096,10 +1097,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link)
* Unless a video pattern CTS test is ongoing, use RGB_VESA
* Only RGB_VESA and RGB_CEA supported for now
*/
- if (dp_link_is_video_pattern_requested(link))
- cc = link->dp_link.test_video.test_dyn_range;
- else
- cc = DP_TEST_DYNAMIC_RANGE_VESA;
+ if (dp_link_is_video_pattern_requested(link)) {
+ if (link->dp_link.test_video.test_dyn_range &
+ DP_TEST_DYNAMIC_RANGE_CEA)
+ cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB;
+ }
return cc;
}
diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h
index ea85a691e72b..78785ed4b40c 100644
--- a/drivers/gpu/drm/msm/dp/dp_reg.h
+++ b/drivers/gpu/drm/msm/dp/dp_reg.h
@@ -143,6 +143,9 @@
#define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001)
#define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005)
+#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0)
+#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04)
+
#define REG_DP_VALID_BOUNDARY (0x00000030)
#define REG_DP_VALID_BOUNDARY_2 (0x00000034)
From 7f3d03c48b1eb6bc45ab20ca98b8b11be25f9f52 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Wed, 17 Jan 2024 11:41:09 -0800
Subject: [PATCH 055/637] drm/msm/dpu: check for valid hw_pp in
dpu_encoder_helper_phys_cleanup
The commit 8b45a26f2ba9 ("drm/msm/dpu: reserve cdm blocks for writeback
in case of YUV output") introduced a smatch warning about another
conditional block in dpu_encoder_helper_phys_cleanup() which had assumed
hw_pp will always be valid which may not necessarily be true.
Lets fix the other conditional block by making sure hw_pp is valid
before dereferencing it.
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: ae4d721ce100 ("drm/msm/dpu: add an API to reset the encoder related hw blocks")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/574878/
Link: https://lore.kernel.org/r/20240117194109.21609-1-quic_abhinavk@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index f2b82ca5efb3..6a4b489d44e5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2068,7 +2068,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
}
/* reset the merge 3D HW block */
- if (phys_enc->hw_pp->merge_3d) {
+ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
BLEND_3D_NONE);
if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d)
@@ -2099,7 +2099,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
if (phys_enc->hw_wb)
intf_cfg.wb = phys_enc->hw_wb->idx;
- if (phys_enc->hw_pp->merge_3d)
+ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d)
intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
if (ctl->ops.reset_intf_cfg)
From 116099ed345c932a8ae4a0d884a8f6cc54fd5fed Mon Sep 17 00:00:00 2001
From: Hu Yadi <hu.yadi@h3c.com>
Date: Tue, 23 Jan 2024 14:26:21 +0800
Subject: [PATCH 056/637] selftests/landlock: Fix net_test build with old libc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
One issue comes up while building selftest/landlock/net_test on my side
(gcc 7.3/glibc-2.28/kernel-4.19).
net_test.c: In function ‘set_service’:
net_test.c:91:45: warning: implicit declaration of function ‘gettid’; [-Wimplicit-function-declaration]
"_selftests-landlock-net-tid%d-index%d", gettid(),
^~~~~~
getgid
net_test.c:(.text+0x4e0): undefined reference to `gettid'
Signed-off-by: Hu Yadi <hu.yadi@h3c.com>
Suggested-by: Jiao <jiaoxupo@h3c.com>
Reviewed-by: Berlin <berlin@h3c.com>
Fixes: a549d055a22e ("selftests/landlock: Add network tests")
Link: https://lore.kernel.org/r/20240123062621.25082-1-hu.yadi@h3c.com
[mic: Cosmetic fixes]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
tools/testing/selftests/landlock/net_test.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index ea5f727dd257..efcde123af1f 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -17,6 +17,7 @@
#include <string.h>
#include <sys/prctl.h>
#include <sys/socket.h>
+#include <sys/syscall.h>
#include <sys/un.h>
#include "common.h"
@@ -54,6 +55,11 @@ struct service_fixture {
};
};
+static pid_t sys_gettid(void)
+{
+ return syscall(__NR_gettid);
+}
+
static int set_service(struct service_fixture *const srv,
const struct protocol_variant prot,
const unsigned short index)
@@ -88,7 +94,7 @@ static int set_service(struct service_fixture *const srv,
case AF_UNIX:
srv->unix_addr.sun_family = prot.domain;
sprintf(srv->unix_addr.sun_path,
- "_selftests-landlock-net-tid%d-index%d", gettid(),
+ "_selftests-landlock-net-tid%d-index%d", sys_gettid(),
index);
srv->unix_addr_len = SUN_LEN(&srv->unix_addr);
srv->unix_addr.sun_path[0] = '\0';
From 40b7835e74e0383be308d528c5e0e41b3bf72ade Mon Sep 17 00:00:00 2001
From: Hu Yadi <hu.yadi@h3c.com>
Date: Wed, 24 Jan 2024 10:29:08 +0800
Subject: [PATCH 057/637] selftests/landlock: Fix fs_test build with old libc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
One issue comes up while building selftest/landlock/fs_test on my side
(gcc 7.3/glibc-2.28/kernel-4.19).
gcc -Wall -O2 -isystem fs_test.c -lcap -o selftests/landlock/fs_test
fs_test.c:4575:9: error: initializer element is not constant
.mnt = mnt_tmp,
^~~~~~~
Signed-off-by: Hu Yadi <hu.yadi@h3c.com>
Suggested-by: Jiao <jiaoxupo@h3c.com>
Reviewed-by: Berlin <berlin@h3c.com>
Link: https://lore.kernel.org/r/20240124022908.42100-1-hu.yadi@h3c.com
Fixes: 04f9070e99a4 ("selftests/landlock: Add tests for pseudo filesystems")
[mic: Factor out mount's data string and make mnt_tmp static]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
tools/testing/selftests/landlock/fs_test.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 50818904397c..2d6d9b43d958 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -241,9 +241,11 @@ struct mnt_opt {
const char *const data;
};
-const struct mnt_opt mnt_tmp = {
+#define MNT_TMP_DATA "size=4m,mode=700"
+
+static const struct mnt_opt mnt_tmp = {
.type = "tmpfs",
- .data = "size=4m,mode=700",
+ .data = MNT_TMP_DATA,
};
static int mount_opt(const struct mnt_opt *const mnt, const char *const target)
@@ -4632,7 +4634,10 @@ FIXTURE_VARIANT(layout3_fs)
/* clang-format off */
FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) {
/* clang-format on */
- .mnt = mnt_tmp,
+ .mnt = {
+ .type = "tmpfs",
+ .data = MNT_TMP_DATA,
+ },
.file_path = file1_s1d1,
};
From 8d35217149daa33358c284aca6a56d5ab92cfc6c Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 15 Dec 2023 03:32:22 +0200
Subject: [PATCH 058/637] drm/msm/mdss: specify cfg bandwidth for SDM670
Lower the requested CFG bus bandwidth for the SDM670 platform. The
default value is 153600 kBps, which is twice as big as required by the
platform according to the vendor kernel.
Fixes: a55c8ff252d3 ("drm/msm/mdss: Handle the reg bus ICC path")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Tested-by: Richard Acayan <mailingradian@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/572182/
Link: https://lore.kernel.org/r/20231215013222.827975-1-dmitry.baryshkov@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/msm_mdss.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 455b2e3a0cdd..35423d10aafa 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -562,6 +562,7 @@ static const struct msm_mdss_data sdm670_data = {
.ubwc_enc_version = UBWC_2_0,
.ubwc_dec_version = UBWC_2_0,
.highest_bank_bit = 1,
+ .reg_bus_bw = 76800,
};
static const struct msm_mdss_data sdm845_data = {
From 9b3058d1f456464a02e202cc7fc660508709097c Mon Sep 17 00:00:00 2001
From: Gregory Greenman <gregory.greenman@intel.com>
Date: Tue, 2 Jan 2024 14:20:19 +0200
Subject: [PATCH 059/637] MAINTAINERS: remove myself as iwlwifi driver
maintainer
As I'm resigning from Intel, it's time to remove myself as a maintainer
of iwlwifi. Good luck to Miri!
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://msgid.link/20240102122019.1689602-1-gregory.greenman@intel.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 92152ac346c8..d8ca0e10c8d1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11128,7 +11128,6 @@ S: Supported
F: drivers/net/wireless/intel/iwlegacy/
INTEL WIRELESS WIFI LINK (iwlwifi)
-M: Gregory Greenman <gregory.greenman@intel.com>
M: Miri Korenblit <miriam.rachel.korenblit@intel.com>
L: linux-wireless@vger.kernel.org
S: Supported
From 353d321f63f7dbfc9ef58498cc732c9fe886a596 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Jan 2024 20:08:11 +0200
Subject: [PATCH 060/637] wifi: iwlwifi: fix double-free bug
The storage for the TLV PC register data wasn't done like all
the other storage in the drv->fw area, which is cleared at the
end of deallocation. Therefore, the freeing must also be done
differently, explicitly NULL'ing it out after the free, since
otherwise there's a nasty double-free bug here if a file fails
to load after this has been parsed, and we get another free
later (e.g. because no other file exists.) Fix that by adding
the missing NULL assignment.
Cc: stable@vger.kernel.org
Fixes: 5e31b3df86ec ("wifi: iwlwifi: dbg: print pc register data once fw dump occurred")
Reported-by: Guy Kaplan <guy.kaplan@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240123200528.675f3c24ec0d.I6ab4015cd78d82dd95471f840629972ef0331de3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index ffe2670720c9..abf8001bdac1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -128,6 +128,7 @@ static void iwl_dealloc_ucode(struct iwl_drv *drv)
kfree(drv->fw.ucode_capa.cmd_versions);
kfree(drv->fw.phy_integration_ver);
kfree(drv->trans->dbg.pc_data);
+ drv->trans->dbg.pc_data = NULL;
for (i = 0; i < IWL_UCODE_TYPE_MAX; i++)
iwl_free_fw_img(drv, drv->fw.img + i);
From b743287d7a0007493f5cada34ed2085d475050b4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 25 Jan 2024 09:51:09 +0100
Subject: [PATCH 061/637] wifi: cfg80211: fix wiphy delayed work queueing
When a wiphy work is queued with timer, and then again
without a delay, it's started immediately but *also*
started again after the timer expires. This can lead,
for example, to warnings in mac80211's offchannel code
as reported by Jouni. Running the same work twice isn't
expected, of course. Fix this by deleting the timer at
this point, when queuing immediately due to delay=0.
Cc: stable@vger.kernel.org
Reported-by: Jouni Malinen <j@w1.fi>
Fixes: a3ee4dc84c4e ("wifi: cfg80211: add a work abstraction with special semantics")
Link: https://msgid.link/20240125095108.2feb0eaaa446.I4617f3210ed0e7f252290d5970dac6a876aa595b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/wireless/core.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 409d74c57ca0..3fb1b637352a 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1661,6 +1661,7 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy,
unsigned long delay)
{
if (!delay) {
+ del_timer(&dwork->timer);
wiphy_work_queue(wiphy, &dwork->work);
return;
}
From 3a3ef3940798e85121066a859127e72a528dc32a Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Tue, 23 Jan 2024 20:08:19 +0200
Subject: [PATCH 062/637] wifi: iwlwifi: mvm: skip adding debugfs symlink for
reconfig
The function to add an interface may be called without a previous
removal if the HW is being reconfigured. As such, only add the symlink
if the hardware is not being reconfigured due to a HW_RESTART.
Fixes: c36235acb34f ("wifi: iwlwifi: mvm: rework debugfs handling")
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240123200528.314395eacda4.I5823e962c3c3674b942383733debd10b3fe903e2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 6 ++++--
drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 3 ++-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 7f13dff04b26..3447d67a8b31 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1600,7 +1600,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
*/
if (vif->type == NL80211_IFTYPE_AP ||
vif->type == NL80211_IFTYPE_ADHOC) {
- iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+ if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+ iwl_mvm_vif_dbgfs_add_link(mvm, vif);
ret = 0;
goto out;
}
@@ -1640,7 +1641,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
iwl_mvm_chandef_get_primary_80(&vif->bss_conf.chandef);
}
- iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+ if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+ iwl_mvm_vif_dbgfs_add_link(mvm, vif);
if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 61170173f917..1f36e934ef69 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -81,7 +81,8 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw,
ieee80211_hw_set(mvm->hw, RX_INCLUDES_FCS);
}
- iwl_mvm_vif_dbgfs_add_link(mvm, vif);
+ if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+ iwl_mvm_vif_dbgfs_add_link(mvm, vif);
if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
From 1b023d475ae928f3036cefee9ea0a499af1d8900 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 16 Jan 2024 21:05:25 -0600
Subject: [PATCH 063/637] wifi: mac80211: Drop WBRF debugging statements
Due to the way that debugging is used in the mac80211 subsystem
this message ends up being noisier than it needs to be.
As the statement is only useful at a first stage of triage for
BIOS bugs, just drop it.
Cc: Jun Ma <Jun.Ma2@amd.com>
Suggested-by: Kalle Valo <kvalo@kernel.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240117030525.539-1-mario.limonciello@amd.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/wbrf.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
index a05c5b971789..3a8612309137 100644
--- a/net/mac80211/wbrf.c
+++ b/net/mac80211/wbrf.c
@@ -23,8 +23,6 @@ void ieee80211_check_wbrf_support(struct ieee80211_local *local)
return;
local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev);
- dev_dbg(dev, "WBRF is %s supported\n",
- local->wbrf_supported ? "" : "not");
}
static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end)
From a7a6a01f88e87dec4bf2365571dd2dc7403d52d0 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 26 Jan 2024 12:14:30 +0100
Subject: [PATCH 064/637] x86/efistub: Give up if memory attribute protocol
returns an error
The recently introduced EFI memory attributes protocol should be used
if it exists to ensure that the memory allocation created for the kernel
permits execution. This is needed for compatibility with tightened
requirements related to Windows logo certification for x86 PCs.
Currently, we simply strip the execute protect (XP) attribute from the
entire range, but this might be rejected under some firmware security
policies, and so in a subsequent patch, this will be changed to only
strip XP from the executable region that runs early, and make it
read-only (RO) as well.
In order to catch any issues early, ensure that the memory attribute
protocol works as intended, and give up if it produces spurious errors.
Note that the DXE services based fallback was always based on best
effort, so don't propagate any errors returned by that API.
Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/libstub/x86-stub.c | 24 ++++++++++++++----------
drivers/firmware/efi/libstub/x86-stub.h | 4 ++--
2 files changed, 16 insertions(+), 12 deletions(-)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 0d510c9a06a4..cb0be88c8131 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
}
}
-void efi_adjust_memory_range_protection(unsigned long start,
- unsigned long size)
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+ unsigned long size)
{
efi_status_t status;
efi_gcd_memory_space_desc_t desc;
@@ -236,13 +236,17 @@ void efi_adjust_memory_range_protection(unsigned long start,
rounded_end = roundup(start + size, EFI_PAGE_SIZE);
if (memattr != NULL) {
- efi_call_proto(memattr, clear_memory_attributes, rounded_start,
- rounded_end - rounded_start, EFI_MEMORY_XP);
- return;
+ status = efi_call_proto(memattr, clear_memory_attributes,
+ rounded_start,
+ rounded_end - rounded_start,
+ EFI_MEMORY_XP);
+ if (status != EFI_SUCCESS)
+ efi_warn("Failed to clear EFI_MEMORY_XP attribute\n");
+ return status;
}
if (efi_dxe_table == NULL)
- return;
+ return EFI_SUCCESS;
/*
* Don't modify memory region attributes, they are
@@ -255,7 +259,7 @@ void efi_adjust_memory_range_protection(unsigned long start,
status = efi_dxe_call(get_memory_space_descriptor, start, &desc);
if (status != EFI_SUCCESS)
- return;
+ break;
next = desc.base_address + desc.length;
@@ -280,8 +284,10 @@ void efi_adjust_memory_range_protection(unsigned long start,
unprotect_start,
unprotect_start + unprotect_size,
status);
+ break;
}
}
+ return EFI_SUCCESS;
}
static void setup_unaccepted_memory(void)
@@ -805,9 +811,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
*kernel_entry = addr + entry;
- efi_adjust_memory_range_protection(addr, kernel_total_size);
-
- return EFI_SUCCESS;
+ return efi_adjust_memory_range_protection(addr, kernel_total_size);
}
static void __noreturn enter_kernel(unsigned long kernel_addr,
diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h
index 37c5a36b9d8c..1c20e99a6494 100644
--- a/drivers/firmware/efi/libstub/x86-stub.h
+++ b/drivers/firmware/efi/libstub/x86-stub.h
@@ -5,8 +5,8 @@
extern void trampoline_32bit_src(void *, bool);
extern const u16 trampoline_ljmp_imm_offset;
-void efi_adjust_memory_range_protection(unsigned long start,
- unsigned long size);
+efi_status_t efi_adjust_memory_range_protection(unsigned long start,
+ unsigned long size);
#ifdef CONFIG_X86_64
efi_status_t efi_setup_5level_paging(void);
From a69eeaad093dd2c8fd0b216c8143b380b73d672d Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dima.fedrau@gmail.com>
Date: Fri, 26 Jan 2024 14:52:26 +0100
Subject: [PATCH 065/637] iio: humidity: hdc3020: fix temperature offset
The temperature offset should be negative according to the datasheet.
Adding a minus to the existing offset results in correct temperature
calculations.
Fixes: c9180b8e39be ("iio: humidity: Add driver for ti HDC302x humidity sensors")
Reviewed-by: Nuno Sa <nuno.sa@analog.com>
Signed-off-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Link: https://lore.kernel.org/r/20240126135226.3977904-1-dima.fedrau@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/humidity/hdc3020.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iio/humidity/hdc3020.c b/drivers/iio/humidity/hdc3020.c
index 4e3311170725..ed70415512f6 100644
--- a/drivers/iio/humidity/hdc3020.c
+++ b/drivers/iio/humidity/hdc3020.c
@@ -322,7 +322,7 @@ static int hdc3020_read_raw(struct iio_dev *indio_dev,
if (chan->type != IIO_TEMP)
return -EINVAL;
- *val = 16852;
+ *val = -16852;
return IIO_VAL_INT;
default:
From 6db053cd949fcd6254cea9f2cd5d39f7bd64379c Mon Sep 17 00:00:00 2001
From: David Schiller <david.schiller@jku.at>
Date: Mon, 22 Jan 2024 14:49:17 +0100
Subject: [PATCH 066/637] staging: iio: ad5933: fix type mismatch regression
Commit 4c3577db3e4f ("Staging: iio: impedance-analyzer: Fix sparse
warning") fixed a compiler warning, but introduced a bug that resulted
in one of the two 16 bit IIO channels always being zero (when both are
enabled).
This is because int is 32 bits wide on most architectures and in the
case of a little-endian machine the two most significant bytes would
occupy the buffer for the second channel as 'val' is being passed as a
void pointer to 'iio_push_to_buffers()'.
Fix by defining 'val' as u16. Tested working on ARM64.
Fixes: 4c3577db3e4f ("Staging: iio: impedance-analyzer: Fix sparse warning")
Signed-off-by: David Schiller <david.schiller@jku.at>
Link: https://lore.kernel.org/r/20240122134916.2137957-1-david.schiller@jku.at
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/staging/iio/impedance-analyzer/ad5933.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index e748a5d04e97..9149d41fe65b 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -608,7 +608,7 @@ static void ad5933_work(struct work_struct *work)
struct ad5933_state, work.work);
struct iio_dev *indio_dev = i2c_get_clientdata(st->client);
__be16 buf[2];
- int val[2];
+ u16 val[2];
unsigned char status;
int ret;
From 6f6c72acddf4357fcc83593c20ef9064fb42db92 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sat, 27 Jan 2024 21:02:08 +0100
Subject: [PATCH 067/637] iio: move LIGHT_UVA and LIGHT_UVB to the end of
iio_modifier
The new modifiers should have added to the end of the enum, so they do
not affect the existing entries.
No modifiers were added since then, so they can be moved safely to the
end of the list.
Move IIO_MOD_LIGHT_UVA and IIO_MOD_LIGHT_UVB to the end of iio_modifier.
Fixes: b89710bd215e ("iio: add modifiers for A and B ultraviolet light")
Suggested-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20240127200208.185815-1-javier.carrasco.cruz@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
include/uapi/linux/iio/types.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index 5060963707b1..f2e0b2d50e6b 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -91,8 +91,6 @@ enum iio_modifier {
IIO_MOD_CO2,
IIO_MOD_VOC,
IIO_MOD_LIGHT_UV,
- IIO_MOD_LIGHT_UVA,
- IIO_MOD_LIGHT_UVB,
IIO_MOD_LIGHT_DUV,
IIO_MOD_PM1,
IIO_MOD_PM2P5,
@@ -107,6 +105,8 @@ enum iio_modifier {
IIO_MOD_PITCH,
IIO_MOD_YAW,
IIO_MOD_ROLL,
+ IIO_MOD_LIGHT_UVA,
+ IIO_MOD_LIGHT_UVB,
};
enum iio_event_type {
From eba38cc7578bef94865341c73608bdf49193a51d Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@kernel.org>
Date: Sun, 28 Jan 2024 09:53:55 +0100
Subject: [PATCH 068/637] bcachefs: Fix build on parisc by avoiding __multi3()
The gcc compiler on paric does support the __int128 type, although the
architecture does not have native 128-bit support.
The effect is, that the bcachefs u128_square() function will pull in the
libgcc __multi3() helper, which breaks the kernel build when bcachefs is
built as module since this function isn't currently exported in
arch/parisc/kernel/parisc_ksyms.c.
The build failure can be seen in the latest debian kernel build at:
https://buildd.debian.org/status/fetch.php?pkg=linux&arch=hppa&ver=6.7.1-1%7Eexp1&stamp=1706132569&raw=0
We prefer to not export that symbol, so fall back to the optional 64-bit
implementation provided by bcachefs and thus avoid usage of __multi3().
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/mean_and_variance.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h
index b2be565bb8f2..64df11ab422b 100644
--- a/fs/bcachefs/mean_and_variance.h
+++ b/fs/bcachefs/mean_and_variance.h
@@ -17,7 +17,7 @@
* Rust and rustc has issues with u128.
*/
-#if defined(__SIZEOF_INT128__) && defined(__KERNEL__)
+#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC)
typedef struct {
unsigned __int128 v;
From 6bb3f7f4c3f4da8e09de188f2f63e8f741bba3bd Mon Sep 17 00:00:00 2001
From: Guoyu Ou <benogy@gmail.com>
Date: Sun, 28 Jan 2024 16:46:17 +0800
Subject: [PATCH 069/637] bcachefs: unlock parent dir if entry is not found in
subvolume deletion
Parent dir is locked by user_path_locked_at() before validating the
required dentry. It should be unlocked if we can not perform the
deletion.
This fixes the problem:
$ bcachefs subvolume delete not-exist-entry
BCH_IOCTL_SUBVOLUME_DESTROY ioctl error: No such file or directory
$ bcachefs subvolume delete not-exist-entry
the second will stuck because the parent dir is locked in the previous
deletion.
Signed-off-by: Guoyu Ou <benogy@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/fs-ioctl.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 3a4c24c28e7f..3dc8630ff9fe 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -455,6 +455,7 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
if (IS_ERR(victim))
return PTR_ERR(victim);
+ dir = d_inode(path.dentry);
if (victim->d_sb->s_fs_info != c) {
ret = -EXDEV;
goto err;
@@ -463,14 +464,13 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
ret = -ENOENT;
goto err;
}
- dir = d_inode(path.dentry);
ret = __bch2_unlink(dir, victim, true);
if (!ret) {
fsnotify_rmdir(dir, victim);
d_delete(victim);
}
- inode_unlock(dir);
err:
+ inode_unlock(dir);
dput(victim);
path_put(&path);
return ret;
From d6d33f03baa43d763fe094ca926eeae7d3421d07 Mon Sep 17 00:00:00 2001
From: Ism Hong <ism.hong@gmail.com>
Date: Tue, 26 Dec 2023 16:51:41 +0800
Subject: [PATCH 070/637] fs/ntfs3: use non-movable memory for ntfs3 MFT buffer
cache
Since the buffer cache for ntfs3 metadata is not released until the file
system is unmounted, allocating from the movable zone may result in cma
allocation failures. This is due to the page still being used by ntfs3,
leading to migration failures.
To address this, this commit use sb_bread_umovable() instead of
sb_bread(). This change prevents allocation from the movable zone,
ensuring compatibility with scenarios where the buffer head is not
released until unmount. This patch is inspired by commit
a8ac900b8163("ext4: use non-movable memory for the ext4 superblock").
The issue is found when playing video files stored in NTFS on the
Android TV platform. During this process, the media parser reads the
video file, causing ntfs3 to allocate buffer cache from the CMA area.
Subsequently, the hardware decoder attempts to allocate memory from the
same CMA area. However, the page is still in use by ntfs3, resulting in
a migrate failure in alloc_contig_range().
The pinned page and allocating stacktrace reported by page owner shows
below:
page:ffffffff00b68880 refcount:3 mapcount:0 mapping:ffffff80046aa828
index:0xc0040 pfn:0x20fa4
aops:def_blk_aops ino:0
flags: 0x2020(active|private)
page dumped because: migration failure
page last allocated via order 0, migratetype Movable,
gfp_mask 0x108c48
(GFP_NOFS|__GFP_NOFAIL|__GFP_HARDWALL|__GFP_MOVABLE),
page_owner tracks the page as allocated
prep_new_page
get_page_from_freelist
__alloc_pages_nodemask
pagecache_get_page
__getblk_gfp
__bread_gfp
ntfs_read_run_nb
ntfs_read_bh
mi_read
ntfs_iget5
dir_search_u
ntfs_lookup
__lookup_slow
lookup_slow
walk_component
path_lookupat
Signed-off-by: Ism Hong <ism.hong@gmail.com>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/ntfs_fs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index abbc7182554a..2b54ae94440f 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -1035,7 +1035,7 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
static inline struct buffer_head *ntfs_bread(struct super_block *sb,
sector_t block)
{
- struct buffer_head *bh = sb_bread(sb, block);
+ struct buffer_head *bh = sb_bread_unmovable(sb, block);
if (bh)
return bh;
From 5ca87d01eba7bdfe9536a157ca33c1455bb8d16c Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:03:21 +0300
Subject: [PATCH 071/637] fs/ntfs3: Prevent generic message "attempt to access
beyond end of device"
It used in test environment.
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/fsntfs.c | 24 ++++++++++++++++++++++++
fs/ntfs3/ntfs_fs.h | 14 +-------------
2 files changed, 25 insertions(+), 13 deletions(-)
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 321978019407..ae2ef5c11868 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -1007,6 +1007,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes)
return cpu_to_le32(hash);
}
+/*
+ * simple wrapper for sb_bread_unmovable.
+ */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block)
+{
+ struct ntfs_sb_info *sbi = sb->s_fs_info;
+ struct buffer_head *bh;
+
+ if (unlikely(block >= sbi->volume.blocks)) {
+ /* prevent generic message "attempt to access beyond end of device" */
+ ntfs_err(sb, "try to read out of volume at offset 0x%llx",
+ (u64)block << sb->s_blocksize_bits);
+ return NULL;
+ }
+
+ bh = sb_bread_unmovable(sb, block);
+ if (bh)
+ return bh;
+
+ ntfs_err(sb, "failed to read volume at offset 0x%llx",
+ (u64)block << sb->s_blocksize_bits);
+ return NULL;
+}
+
int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer)
{
struct block_device *bdev = sb->s_bdev;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 2b54ae94440f..81f7563428ee 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -586,6 +586,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes);
int log_replay(struct ntfs_inode *ni, bool *initialized);
/* Globals from fsntfs.c */
+struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block);
bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes);
int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes,
bool simple);
@@ -1032,19 +1033,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size)
return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
}
-static inline struct buffer_head *ntfs_bread(struct super_block *sb,
- sector_t block)
-{
- struct buffer_head *bh = sb_bread_unmovable(sb, block);
-
- if (bh)
- return bh;
-
- ntfs_err(sb, "failed to read volume at offset 0x%llx",
- (u64)block << sb->s_blocksize_bits);
- return NULL;
-}
-
static inline struct ntfs_inode *ntfs_i(struct inode *inode)
{
return container_of(inode, struct ntfs_inode, vfs_inode);
From 4fd6c08a16d7f1ba10212c9ef7bc73218144b463 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:12:38 +0300
Subject: [PATCH 072/637] fs/ntfs3: Use i_size_read and i_size_write
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/attrib.c | 4 ++--
fs/ntfs3/dir.c | 2 +-
fs/ntfs3/file.c | 11 ++++++-----
fs/ntfs3/frecord.c | 10 +++++-----
fs/ntfs3/index.c | 8 ++++----
fs/ntfs3/inode.c | 2 +-
6 files changed, 19 insertions(+), 18 deletions(-)
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 646e2dad1b75..7aadf5010999 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -2084,7 +2084,7 @@ next_attr:
/* Update inode size. */
ni->i_valid = valid_size;
- ni->vfs_inode.i_size = data_size;
+ i_size_write(&ni->vfs_inode, data_size);
inode_set_bytes(&ni->vfs_inode, total_size);
ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
mark_inode_dirty(&ni->vfs_inode);
@@ -2499,7 +2499,7 @@ int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
mi_b->dirty = true;
done:
- ni->vfs_inode.i_size += bytes;
+ i_size_write(&ni->vfs_inode, ni->vfs_inode.i_size + bytes);
ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
mark_inode_dirty(&ni->vfs_inode);
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 9f6dd445eb04..effa6accf8a8 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -517,7 +517,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs,
u32 e_size, off, end;
size_t drs = 0, fles = 0, bit = 0;
struct indx_node *node = NULL;
- size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits;
+ size_t max_indx = i_size_read(&ni->vfs_inode) >> ni->dir.index_bits;
if (is_empty)
*is_empty = true;
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 07ed3d946e7c..b702543a8795 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -646,7 +646,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len)
if (err)
goto out;
} else if (new_size > i_size) {
- inode->i_size = new_size;
+ i_size_write(inode, new_size);
}
}
@@ -696,7 +696,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
goto out;
}
inode_dio_wait(inode);
- oldsize = inode->i_size;
+ oldsize = i_size_read(inode);
newsize = attr->ia_size;
if (newsize <= oldsize)
@@ -708,7 +708,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
goto out;
ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
- inode->i_size = newsize;
+ i_size_write(inode, newsize);
}
setattr_copy(idmap, inode, attr);
@@ -847,7 +847,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from)
size_t count = iov_iter_count(from);
loff_t pos = iocb->ki_pos;
struct inode *inode = file_inode(file);
- loff_t i_size = inode->i_size;
+ loff_t i_size = i_size_read(inode);
struct address_space *mapping = inode->i_mapping;
struct ntfs_inode *ni = ntfs_i(inode);
u64 valid = ni->i_valid;
@@ -1177,7 +1177,8 @@ static int ntfs_file_release(struct inode *inode, struct file *file)
down_write(&ni->file.run_lock);
err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run,
- inode->i_size, &ni->i_valid, false, NULL);
+ i_size_read(inode), &ni->i_valid, false,
+ NULL);
up_write(&ni->file.run_lock);
ni_unlock(ni);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 2636ab7640ac..3b42938a9d3b 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -2099,7 +2099,7 @@ int ni_readpage_cmpr(struct ntfs_inode *ni, struct page *page)
gfp_t gfp_mask;
struct page *pg;
- if (vbo >= ni->vfs_inode.i_size) {
+ if (vbo >= i_size_read(&ni->vfs_inode)) {
SetPageUptodate(page);
err = 0;
goto out;
@@ -2173,7 +2173,7 @@ int ni_decompress_file(struct ntfs_inode *ni)
{
struct ntfs_sb_info *sbi = ni->mi.sbi;
struct inode *inode = &ni->vfs_inode;
- loff_t i_size = inode->i_size;
+ loff_t i_size = i_size_read(inode);
struct address_space *mapping = inode->i_mapping;
gfp_t gfp_mask = mapping_gfp_mask(mapping);
struct page **pages = NULL;
@@ -2457,6 +2457,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
struct ATTR_LIST_ENTRY *le = NULL;
struct runs_tree *run = &ni->file.run;
u64 valid_size = ni->i_valid;
+ loff_t i_size = i_size_read(&ni->vfs_inode);
u64 vbo_disk;
size_t unc_size;
u32 frame_size, i, npages_disk, ondisk_size;
@@ -2548,7 +2549,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
}
}
- frames = (ni->vfs_inode.i_size - 1) >> frame_bits;
+ frames = (i_size - 1) >> frame_bits;
err = attr_wof_frame_info(ni, attr, run, frame64, frames,
frame_bits, &ondisk_size, &vbo_data);
@@ -2556,8 +2557,7 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages,
goto out2;
if (frame64 == frames) {
- unc_size = 1 + ((ni->vfs_inode.i_size - 1) &
- (frame_size - 1));
+ unc_size = 1 + ((i_size - 1) & (frame_size - 1));
ondisk_size = attr_size(attr) - vbo_data;
} else {
unc_size = frame_size;
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index cf92b2433f7a..daabaad63aaf 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1462,7 +1462,7 @@ static int indx_create_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
goto out2;
if (in->name == I30_NAME) {
- ni->vfs_inode.i_size = data_size;
+ i_size_write(&ni->vfs_inode, data_size);
inode_set_bytes(&ni->vfs_inode, alloc_size);
}
@@ -1544,7 +1544,7 @@ static int indx_add_allocate(struct ntfs_index *indx, struct ntfs_inode *ni,
}
if (in->name == I30_NAME)
- ni->vfs_inode.i_size = data_size;
+ i_size_write(&ni->vfs_inode, data_size);
*vbn = bit << indx->idx2vbn_bits;
@@ -2090,7 +2090,7 @@ static int indx_shrink(struct ntfs_index *indx, struct ntfs_inode *ni,
return err;
if (in->name == I30_NAME)
- ni->vfs_inode.i_size = new_data;
+ i_size_write(&ni->vfs_inode, new_data);
bpb = bitmap_size(bit);
if (bpb * 8 == nbits)
@@ -2576,7 +2576,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni,
err = attr_set_size(ni, ATTR_ALLOC, in->name, in->name_len,
&indx->alloc_run, 0, NULL, false, NULL);
if (in->name == I30_NAME)
- ni->vfs_inode.i_size = 0;
+ i_size_write(&ni->vfs_inode, 0);
err = ni_remove_attr(ni, ATTR_ALLOC, in->name, in->name_len,
false, NULL);
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 85452a6b1d40..eb7a8c9fba01 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -985,7 +985,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
}
if (pos + err > inode->i_size) {
- inode->i_size = pos + err;
+ i_size_write(inode, pos + err);
dirty = true;
}
From 1b7dd28e14c4728ae1a815605ca33ffb4ce1b309 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:13:59 +0300
Subject: [PATCH 073/637] fs/ntfs3: Correct function is_rst_area_valid
Reported-by: Robert Morris <rtm@csail.mit.edu>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/fslog.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 7dbb000fc691..855519713bf7 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
{
const struct RESTART_AREA *ra;
u16 cl, fl, ul;
- u32 off, l_size, file_dat_bits, file_size_round;
+ u32 off, l_size, seq_bits;
u16 ro = le16_to_cpu(rhdr->ra_off);
u32 sys_page = le32_to_cpu(rhdr->sys_page_size);
@@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr)
/* Make sure the sequence number bits match the log file size. */
l_size = le64_to_cpu(ra->l_size);
- file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits);
- file_size_round = 1u << (file_dat_bits + 3);
- if (file_size_round != l_size &&
- (file_size_round < l_size || (file_size_round / 2) > l_size)) {
- return false;
+ seq_bits = sizeof(u64) * 8 + 3;
+ while (l_size) {
+ l_size >>= 1;
+ seq_bits -= 1;
}
+ if (seq_bits != ra->seq_num_bits)
+ return false;
+
/* The log page data offset and record header length must be quad-aligned. */
if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) ||
!IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8))
From 652cfeb43d6b9aba5c7c4902bed7a7340df131fb Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Fri, 26 Jan 2024 11:14:31 +0300
Subject: [PATCH 074/637] fs/ntfs3: Fixed overflow check in mi_enum_attr()
Reported-by: Robert Morris <rtm@csail.mit.edu>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/record.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 7b6423584eae..6aa3a9d44df1 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -279,7 +279,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
if (t16 > asize)
return NULL;
- if (t16 + le32_to_cpu(attr->res.data_size) > asize)
+ if (le32_to_cpu(attr->res.data_size) > asize - t16)
return NULL;
t32 = sizeof(short) * attr->name_len;
From d68968440b1a75dee05cfac7f368f1aa139e1911 Mon Sep 17 00:00:00 2001
From: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
Date: Mon, 29 Jan 2024 10:30:09 +0300
Subject: [PATCH 075/637] fs/ntfs3: Update inode->i_size after success write
into compressed file
Reported-by: Giovanni Santini <giovannisantini93@yahoo.it>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/file.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index b702543a8795..691b0c9b95ae 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -1054,6 +1054,8 @@ out:
iocb->ki_pos += written;
if (iocb->ki_pos > ni->i_valid)
ni->i_valid = iocb->ki_pos;
+ if (iocb->ki_pos > i_size)
+ i_size_write(inode, iocb->ki_pos);
return written;
}
From ec4d82f855ce332de26fe080892483de98cc1a19 Mon Sep 17 00:00:00 2001
From: Mohammad Rahimi <rahimi.mhmmd@gmail.com>
Date: Sat, 27 Jan 2024 11:26:28 +0800
Subject: [PATCH 076/637] thunderbolt: Fix setting the CNS bit in ROUTER_CS_5
The bit 23, CM TBT3 Not Supported (CNS), in ROUTER_CS_5 indicates
whether a USB4 Connection Manager is TBT3-Compatible and should be:
0b for TBT3-Compatible
1b for Not TBT3-Compatible
Fixes: b04079837b20 ("thunderbolt: Add initial support for USB4")
Cc: stable@vger.kernel.org
Signed-off-by: Mohammad Rahimi <rahimi.mhmmd@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/thunderbolt/tb_regs.h | 2 +-
drivers/thunderbolt/usb4.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h
index 87e4795275fe..6f798f6a2b84 100644
--- a/drivers/thunderbolt/tb_regs.h
+++ b/drivers/thunderbolt/tb_regs.h
@@ -203,7 +203,7 @@ struct tb_regs_switch_header {
#define ROUTER_CS_5_WOP BIT(1)
#define ROUTER_CS_5_WOU BIT(2)
#define ROUTER_CS_5_WOD BIT(3)
-#define ROUTER_CS_5_C3S BIT(23)
+#define ROUTER_CS_5_CNS BIT(23)
#define ROUTER_CS_5_PTO BIT(24)
#define ROUTER_CS_5_UTO BIT(25)
#define ROUTER_CS_5_HCO BIT(26)
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index f8f0d24ff6e4..1515eff8cc3e 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -290,7 +290,7 @@ int usb4_switch_setup(struct tb_switch *sw)
}
/* TBT3 supported by the CM */
- val |= ROUTER_CS_5_C3S;
+ val &= ~ROUTER_CS_5_CNS;
return tb_sw_write(sw, &val, TB_CFG_SWITCH, ROUTER_CS_5, 1);
}
From ebd4acc0cbeae9efea15993b11b05bd32942f3f0 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 23 Jan 2024 14:27:30 +0100
Subject: [PATCH 077/637] riscv: Fix wrong size passed to
local_flush_tlb_range_asid()
local_flush_tlb_range_asid() takes the size as argument, not the end of
the range to flush, so fix this by computing the size from the end and
the start of the range.
Fixes: 7a92fc8b4d20 ("mm: Introduce flush_cache_vmap_early()")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
arch/riscv/mm/tlbflush.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8d12b26f5ac3..9619965f6501 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -68,7 +68,7 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+ local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
}
static void __ipi_flush_tlb_all(void *info)
From b2dd7b953c25ffd5912dda17e980e7168bebcf6c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 17 Oct 2023 17:04:39 +0300
Subject: [PATCH 078/637] fs/ntfs3: Fix an NULL dereference bug
The issue here is when this is called from ntfs_load_attr_list(). The
"size" comes from le32_to_cpu(attr->res.data_size) so it can't overflow
on a 64bit systems but on 32bit systems the "+ 1023" can overflow and
the result is zero. This means that the kmalloc will succeed by
returning the ZERO_SIZE_PTR and then the memcpy() will crash with an
Oops on the next line.
Fixes: be71b5cba2e6 ("fs/ntfs3: Add attrib operations")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/ntfs_fs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 81f7563428ee..627419bd6f77 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -475,7 +475,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn,
int al_update(struct ntfs_inode *ni, int sync);
static inline size_t al_aligned(size_t size)
{
- return (size + 1023) & ~(size_t)1023;
+ return size_add(size, 1023) & ~(size_t)1023;
}
/* Globals from bitfunc.c */
From 731ab1f9828800df871c5a7ab9ffe965317d3f15 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Sat, 30 Dec 2023 17:00:03 +0800
Subject: [PATCH 079/637] fs/ntfs3: Fix oob in ntfs_listxattr
The length of name cannot exceed the space occupied by ea.
Reported-and-tested-by: syzbot+65e940cfb8f99a97aca7@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/xattr.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 071356d096d8..53e7d1fa036a 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -219,6 +219,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
if (!ea->name_len)
break;
+ if (ea->name_len > ea_size)
+ break;
+
if (buffer) {
/* Check if we can use field ea->name */
if (off + ea_size > size)
From 1f5fa4b3b85ceb43f1053290f0ade037b50e6297 Mon Sep 17 00:00:00 2001
From: Nekun <nekokun@firemail.cc>
Date: Mon, 30 Oct 2023 08:33:54 +0000
Subject: [PATCH 080/637] fs/ntfs3: Add ioctl operation for directories
(FITRIM)
While ntfs3 supports discards, FITRIM ioctl() command has defined
only for regular files. This may confuse users trying to invoke
`fstrim` utility with the directory argument (for example, call
`fstrim <mountpoint>` which is the common practice). In this case,
ioctl() returns -ENOTTY without any error messages in kernel ring
buffer, this may be easily interpreted as no support for discards
in ntfs3 driver.
Currently only FITRIM command implemented in ntfs_ioctl() and
passed inode used only for dereferencing NTFS superblock, so
no need for separate ioctl() handler for directories, just add
existing ntfs_ioctl() handler to ntfs_dir_operations.
Signed-off-by: Nekun <nekokun@firemail.cc>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/dir.c | 4 ++++
fs/ntfs3/file.c | 4 ++--
fs/ntfs3/ntfs_fs.h | 2 ++
3 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index effa6accf8a8..5cf3d9decf64 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -611,5 +611,9 @@ const struct file_operations ntfs_dir_operations = {
.iterate_shared = ntfs_readdir,
.fsync = generic_file_fsync,
.open = ntfs_file_open,
+ .unlocked_ioctl = ntfs_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ntfs_compat_ioctl,
+#endif
};
// clang-format on
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 691b0c9b95ae..5418662c80d8 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -48,7 +48,7 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg)
return 0;
}
-static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info;
@@ -61,7 +61,7 @@ static long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg)
}
#ifdef CONFIG_COMPAT
-static long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg)
{
return ntfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 627419bd6f77..79356fd29a14 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -502,6 +502,8 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
int ntfs_file_open(struct inode *inode, struct file *file);
int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
+long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg);
+long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg);
extern const struct inode_operations ntfs_special_inode_operations;
extern const struct inode_operations ntfs_file_inode_operations;
extern const struct file_operations ntfs_file_operations;
From 622cd3daa8eae37359a6fd3c07c36d19f66606b5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 10 Nov 2023 20:59:22 +0100
Subject: [PATCH 081/637] fs/ntfs3: Slightly simplify ntfs_inode_printk()
The size passed to snprintf() includes the space for the trailing space.
So there is no reason here not to use all the available space.
So remove the -1 when computing 'name_len'.
While at it, use the size of the array directly instead of the intermediate
'name_len' variable.
snprintf() also guaranties that the buffer if NULL terminated, so there is
no need to write an additional trailing NULL "To be sure".
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Konstantin Komarov <almaz.alexandrovich@paragon-software.com>
---
fs/ntfs3/super.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index c55a29793a8d..cef5467fd928 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -122,13 +122,12 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...)
if (name) {
struct dentry *de = d_find_alias(inode);
- const u32 name_len = ARRAY_SIZE(s_name_buf) - 1;
if (de) {
spin_lock(&de->d_lock);
- snprintf(name, name_len, " \"%s\"", de->d_name.name);
+ snprintf(name, sizeof(s_name_buf), " \"%s\"",
+ de->d_name.name);
spin_unlock(&de->d_lock);
- name[name_len] = 0; /* To be sure. */
} else {
name[0] = 0;
}
From 8eed4e00a370b37b4e5985ed983dccedd555ea9d Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Mon, 29 Jan 2024 14:38:42 +0800
Subject: [PATCH 082/637] x86/lib: Revert to _ASM_EXTABLE_UA() for
{get,put}_user() fixups
During memory error injection test on kernels >= v6.4, the kernel panics
like below. However, this issue couldn't be reproduced on kernels <= v6.3.
mce: [Hardware Error]: CPU 296: Machine Check Exception: f Bank 1: bd80000000100134
mce: [Hardware Error]: RIP 10:<ffffffff821b9776> {__get_user_nocheck_4+0x6/0x20}
mce: [Hardware Error]: TSC 411a93533ed ADDR 346a8730040 MISC 86
mce: [Hardware Error]: PROCESSOR 0:a06d0 TIME 1706000767 SOCKET 1 APIC 211 microcode 80001490
mce: [Hardware Error]: Run the above through 'mcelog --ascii'
mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel
Kernel panic - not syncing: Fatal local machine check
The MCA code can recover from an in-kernel #MC if the fixup type is
EX_TYPE_UACCESS, explicitly indicating that the kernel is attempting to
access userspace memory. However, if the fixup type is EX_TYPE_DEFAULT
the only thing that is raised for an in-kernel #MC is a panic.
ex_handler_uaccess() would warn if users gave a non-canonical addresses
(with bit 63 clear) to {get, put}_user(), which was unexpected.
Therefore, commit
b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()")
replaced _ASM_EXTABLE_UA() with _ASM_EXTABLE() for {get, put}_user()
fixups. However, the new fixup type EX_TYPE_DEFAULT results in a panic.
Commit
6014bc27561f ("x86-64: make access_ok() independent of LAM")
added the check gp_fault_address_ok() right before the WARN_ONCE() in
ex_handler_uaccess() to not warn about non-canonical user addresses due
to LAM.
With that in place, revert back to _ASM_EXTABLE_UA() for {get,put}_user()
exception fixups in order to be able to handle in-kernel MCEs correctly
again.
[ bp: Massage commit message. ]
Fixes: b19b74bc99b1 ("x86/mm: Rework address range check in get_user() and put_user()")
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20240129063842.61584-1-qiuxu.zhuo@intel.com
---
arch/x86/lib/getuser.S | 24 ++++++++++++------------
arch/x86/lib/putuser.S | 20 ++++++++++----------
2 files changed, 22 insertions(+), 22 deletions(-)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 20ef350a60fb..10d5ed8b5990 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
#endif
/* get_user */
- _ASM_EXTABLE(1b, __get_user_handle_exception)
- _ASM_EXTABLE(2b, __get_user_handle_exception)
- _ASM_EXTABLE(3b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(3b, __get_user_handle_exception)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(4b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(4b, __get_user_handle_exception)
#else
- _ASM_EXTABLE(4b, __get_user_8_handle_exception)
- _ASM_EXTABLE(5b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
#endif
/* __get_user */
- _ASM_EXTABLE(6b, __get_user_handle_exception)
- _ASM_EXTABLE(7b, __get_user_handle_exception)
- _ASM_EXTABLE(8b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(8b, __get_user_handle_exception)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(9b, __get_user_handle_exception)
+ _ASM_EXTABLE_UA(9b, __get_user_handle_exception)
#else
- _ASM_EXTABLE(9b, __get_user_8_handle_exception)
- _ASM_EXTABLE(10b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+ _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
#endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 2877f5934177..975c9c18263d 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -133,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
RET
SYM_CODE_END(__put_user_handle_exception)
- _ASM_EXTABLE(1b, __put_user_handle_exception)
- _ASM_EXTABLE(2b, __put_user_handle_exception)
- _ASM_EXTABLE(3b, __put_user_handle_exception)
- _ASM_EXTABLE(4b, __put_user_handle_exception)
- _ASM_EXTABLE(5b, __put_user_handle_exception)
- _ASM_EXTABLE(6b, __put_user_handle_exception)
- _ASM_EXTABLE(7b, __put_user_handle_exception)
- _ASM_EXTABLE(9b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(9b, __put_user_handle_exception)
#ifdef CONFIG_X86_32
- _ASM_EXTABLE(8b, __put_user_handle_exception)
- _ASM_EXTABLE(10b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+ _ASM_EXTABLE_UA(10b, __put_user_handle_exception)
#endif
From e4ad71e2367f3f7b7409c30df9cdbb34da15e012 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Fri, 26 Jan 2024 11:57:24 +0100
Subject: [PATCH 083/637] MAINTAINERS: wifi: brcm80211: cleanup entry
There has been some discussion about what is expected from
a maintainer and so a cleanup seems to be in order. A dedicated
mailing list has been created to discuss brcm80211 specific
development issues. Keeping the status as Supported although
help in maintaining this driver is welcomed.
Cc: brcm80211@lists.linux.dev
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240126105724.384063-1-arend.vanspriel@broadcom.com
---
MAINTAINERS | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index d8ca0e10c8d1..25d530ab90d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4169,14 +4169,14 @@ F: drivers/firmware/broadcom/tee_bnxt_fw.c
F: drivers/net/ethernet/broadcom/bnxt/
F: include/linux/firmware/broadcom/tee_bnxt_fw.h
-BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M: Arend van Spriel <aspriel@gmail.com>
-M: Franky Lin <franky.lin@broadcom.com>
-M: Hante Meuleman <hante.meuleman@broadcom.com>
+BROADCOM BRCM80211 IEEE802.11 WIRELESS DRIVERS
+M: Arend van Spriel <arend.vanspriel@broadcom.com>
L: linux-wireless@vger.kernel.org
+L: brcm80211@lists.linux.dev
L: brcm80211-dev-list.pdl@broadcom.com
S: Supported
F: drivers/net/wireless/broadcom/brcm80211/
+F: include/linux/platform_data/brcmfmac.h
BROADCOM BRCMSTB GPIO DRIVER
M: Doug Berger <opendmb@gmail.com>
From 02add85a9eefb5c969b9bb6916f14607ca2faae0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 14:40:41 -0800
Subject: [PATCH 084/637] KVM: selftests: Reword the NX hugepage test's skip
message to be more helpful
Rework the NX hugepage test's skip message regarding the magic token to
provide all of the necessary magic, and to very explicitly recommended
using the wrapper shell script.
Opportunistically remove an overzealous newline; splitting the
recommendation message across two lines of ~45 characters makes it much
harder to read than running out a single line to 98 characters.
Link: https://lore.kernel.org/r/20231129224042.530798-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 83e25bccc139..17bbb96fc4df 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -257,9 +257,9 @@ int main(int argc, char **argv)
TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES));
__TEST_REQUIRE(token == MAGIC_TOKEN,
- "This test must be run with the magic token %d.\n"
- "This is done by nx_huge_pages_test.sh, which\n"
- "also handles environment setup for the test.", MAGIC_TOKEN);
+ "This test must be run with the magic token via '-t %d'.\n"
+ "Running via nx_huge_pages_test.sh, which also handles "
+ "environment setup, is strongly recommended.", MAGIC_TOKEN);
run_test(reclaim_period_ms, false, reboot_permissions);
run_test(reclaim_period_ms, true, reboot_permissions);
From 250e138d876838774bca3140d544438898df0489 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 18:02:43 +0100
Subject: [PATCH 085/637] KVM: selftests: Remove redundant newlines
TEST_* functions append their own newline. Remove newlines from
TEST_* callsites to avoid extra newlines in output.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231206170241.82801-8-ajones@ventanamicro.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/demand_paging_test.c | 4 ++--
.../testing/selftests/kvm/dirty_log_perf_test.c | 4 ++--
tools/testing/selftests/kvm/dirty_log_test.c | 4 ++--
tools/testing/selftests/kvm/get-reg-list.c | 2 +-
tools/testing/selftests/kvm/guest_print_test.c | 8 ++++----
.../selftests/kvm/hardware_disable_test.c | 6 +++---
.../testing/selftests/kvm/kvm_create_max_vcpus.c | 2 +-
.../testing/selftests/kvm/kvm_page_table_test.c | 4 ++--
tools/testing/selftests/kvm/lib/elf.c | 2 +-
tools/testing/selftests/kvm/lib/kvm_util.c | 16 ++++++++--------
tools/testing/selftests/kvm/lib/memstress.c | 2 +-
.../testing/selftests/kvm/lib/userfaultfd_util.c | 2 +-
.../kvm/memslot_modification_stress_test.c | 2 +-
tools/testing/selftests/kvm/memslot_perf_test.c | 6 +++---
tools/testing/selftests/kvm/rseq_test.c | 4 ++--
.../selftests/kvm/set_memory_region_test.c | 6 +++---
.../selftests/kvm/system_counter_offset_test.c | 2 +-
17 files changed, 38 insertions(+), 38 deletions(-)
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 09c116a82a84..bf3609f71854 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -45,10 +45,10 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
/* Let the guest access its memory */
ret = _vcpu_run(vcpu);
- TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
if (get_ucall(vcpu, NULL) != UCALL_SYNC) {
TEST_ASSERT(false,
- "Invalid guest sync status: exit_reason=%s\n",
+ "Invalid guest sync status: exit_reason=%s",
exit_reason_str(run->exit_reason));
}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index d374dbcf9a53..504f6fe980e8 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -88,9 +88,9 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
ret = _vcpu_run(vcpu);
ts_diff = timespec_elapsed(start);
- TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
- "Invalid guest sync status: exit_reason=%s\n",
+ "Invalid guest sync status: exit_reason=%s",
exit_reason_str(run->exit_reason));
pr_debug("Got sync event from vCPU %d\n", vcpu_idx);
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 6cbecf499767..babea97b31a4 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -262,7 +262,7 @@ static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
"vcpu run failed: errno=%d", err);
TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
- "Invalid guest sync status: exit_reason=%s\n",
+ "Invalid guest sync status: exit_reason=%s",
exit_reason_str(run->exit_reason));
vcpu_handle_sync_stop();
@@ -410,7 +410,7 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
pr_info("vcpu continues now.\n");
} else {
TEST_ASSERT(false, "Invalid guest sync status: "
- "exit_reason=%s\n",
+ "exit_reason=%s",
exit_reason_str(run->exit_reason));
}
}
diff --git a/tools/testing/selftests/kvm/get-reg-list.c b/tools/testing/selftests/kvm/get-reg-list.c
index 8274ef04301f..91f05f78e824 100644
--- a/tools/testing/selftests/kvm/get-reg-list.c
+++ b/tools/testing/selftests/kvm/get-reg-list.c
@@ -152,7 +152,7 @@ static void check_supported(struct vcpu_reg_list *c)
continue;
__TEST_REQUIRE(kvm_has_cap(s->capability),
- "%s: %s not available, skipping tests\n",
+ "%s: %s not available, skipping tests",
config_name(c), s->name);
}
}
diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c
index 41230b746190..3502caa3590c 100644
--- a/tools/testing/selftests/kvm/guest_print_test.c
+++ b/tools/testing/selftests/kvm/guest_print_test.c
@@ -98,7 +98,7 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg)
int offset = len_str - len_substr;
TEST_ASSERT(len_substr <= len_str,
- "Expected '%s' to be a substring of '%s'\n",
+ "Expected '%s' to be a substring of '%s'",
assert_msg, expected_assert_msg);
TEST_ASSERT(strcmp(&assert_msg[offset], expected_assert_msg) == 0,
@@ -116,7 +116,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf,
vcpu_run(vcpu);
TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
- "Unexpected exit reason: %u (%s),\n",
+ "Unexpected exit reason: %u (%s),",
run->exit_reason, exit_reason_str(run->exit_reason));
switch (get_ucall(vcpu, &uc)) {
@@ -161,11 +161,11 @@ static void test_limits(void)
vcpu_run(vcpu);
TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON,
- "Unexpected exit reason: %u (%s),\n",
+ "Unexpected exit reason: %u (%s),",
run->exit_reason, exit_reason_str(run->exit_reason));
TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_ABORT,
- "Unexpected ucall command: %lu, Expected: %u (UCALL_ABORT)\n",
+ "Unexpected ucall command: %lu, Expected: %u (UCALL_ABORT)",
uc.cmd, UCALL_ABORT);
kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
index f5d59b9934f1..decc521fc760 100644
--- a/tools/testing/selftests/kvm/hardware_disable_test.c
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -41,7 +41,7 @@ static void *run_vcpu(void *arg)
vcpu_run(vcpu);
- TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+ TEST_ASSERT(false, "%s: exited with reason %d: %s",
__func__, run->exit_reason,
exit_reason_str(run->exit_reason));
pthread_exit(NULL);
@@ -55,7 +55,7 @@ static void *sleeping_thread(void *arg)
fd = open("/dev/null", O_RDWR);
close(fd);
}
- TEST_ASSERT(false, "%s: exited\n", __func__);
+ TEST_ASSERT(false, "%s: exited", __func__);
pthread_exit(NULL);
}
@@ -118,7 +118,7 @@ static void run_test(uint32_t run)
for (i = 0; i < VCPU_NUM; ++i)
check_join(threads[i], &b);
/* Should not be reached */
- TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+ TEST_ASSERT(false, "%s: [%d] child escaped the ninja", __func__, run);
}
void wait_for_child_setup(pid_t pid)
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index 31b3cb24b9a7..b9e23265e4b3 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -65,7 +65,7 @@ int main(int argc, char *argv[])
int r = setrlimit(RLIMIT_NOFILE, &rl);
__TEST_REQUIRE(r >= 0,
- "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+ "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)",
old_rlim_max, nr_fds_wanted);
} else {
TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index e37dc9c21888..e0ba97ac1c56 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -204,9 +204,9 @@ static void *vcpu_worker(void *data)
ret = _vcpu_run(vcpu);
ts_diff = timespec_elapsed(start);
- TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
- "Invalid guest sync status: exit_reason=%s\n",
+ "Invalid guest sync status: exit_reason=%s",
exit_reason_str(vcpu->run->exit_reason));
pr_debug("Got sync event from vCPU %d\n", vcpu->id);
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index 266f3876e10a..f34d926d9735 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -184,7 +184,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
"Seek to program segment offset failed,\n"
" program header idx: %u errno: %i\n"
" offset_rv: 0x%jx\n"
- " expected: 0x%jx\n",
+ " expected: 0x%jx",
n1, errno, (intmax_t) offset_rv,
(intmax_t) phdr.p_offset);
test_read(fd, addr_gva2hva(vm, phdr.p_vaddr),
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index e066d584c656..8754abaff5e9 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -320,7 +320,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
uint64_t nr_pages;
TEST_ASSERT(nr_runnable_vcpus,
- "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");
+ "Use vm_create_barebones() for VMs that _never_ have vCPUs");
TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
"nr_vcpus = %d too large for host, max-vcpus = %d",
@@ -491,7 +491,7 @@ void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
CPU_ZERO(&mask);
CPU_SET(pcpu, &mask);
r = sched_setaffinity(0, sizeof(mask), &mask);
- TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
+ TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu);
}
static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
@@ -499,7 +499,7 @@ static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
uint32_t pcpu = atoi_non_negative("CPU number", cpu_str);
TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask),
- "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu);
+ "Not allowed to run on pCPU '%d', check cgroups?", pcpu);
return pcpu;
}
@@ -529,7 +529,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
int i, r;
cpu_list = strdup(pcpus_string);
- TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");
+ TEST_ASSERT(cpu_list, "strdup() allocation failed.");
r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
TEST_ASSERT(!r, "sched_getaffinity() failed");
@@ -538,7 +538,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
/* 1. Get all pcpus for vcpus. */
for (i = 0; i < nr_vcpus; i++) {
- TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
+ TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'", i);
vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
cpu = strtok(NULL, delim);
}
@@ -1057,7 +1057,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
" rc: %i errno: %i\n"
" slot: %u flags: 0x%x\n"
- " guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d\n",
+ " guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
ret, errno, slot, flags,
guest_paddr, (uint64_t) region->region.memory_size,
region->region.guest_memfd);
@@ -1222,7 +1222,7 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
len = min_t(uint64_t, end - gpa, region->region.memory_size - offset);
ret = fallocate(region->region.guest_memfd, mode, fd_offset, len);
- TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx\n",
+ TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx",
punch_hole ? "punch hole" : "allocate", gpa, len,
region->region.guest_memfd, mode, fd_offset);
}
@@ -1265,7 +1265,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
struct kvm_vcpu *vcpu;
/* Confirm a vcpu with the specified id doesn't already exist. */
- TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id);
+ TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists", vcpu_id);
/* Allocate and initialize new vcpu structure. */
vcpu = calloc(1, sizeof(*vcpu));
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index d05487e5a371..cf2c73971308 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -192,7 +192,7 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
TEST_ASSERT(guest_num_pages < region_end_gfn,
"Requested more guest memory than address space allows.\n"
" guest pages: %" PRIx64 " max gfn: %" PRIx64
- " nr_vcpus: %d wss: %" PRIx64 "]\n",
+ " nr_vcpus: %d wss: %" PRIx64 "]",
guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes);
args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size;
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index 271f63891581..f4eef6eb2dc2 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -69,7 +69,7 @@ static void *uffd_handler_thread_fn(void *arg)
if (pollfd[1].revents & POLLIN) {
r = read(pollfd[1].fd, &tmp_chr, 1);
TEST_ASSERT(r == 1,
- "Error reading pipefd in UFFD thread\n");
+ "Error reading pipefd in UFFD thread");
break;
}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 9855c41ca811..156361966612 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -45,7 +45,7 @@ static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
/* Let the guest access its memory until a stop signal is received */
while (!READ_ONCE(memstress_args.stop_vcpus)) {
ret = _vcpu_run(vcpu);
- TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d", ret);
if (get_ucall(vcpu, NULL) == UCALL_SYNC)
continue;
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 8698d1ab60d0..579a64f97333 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -175,11 +175,11 @@ static void wait_for_vcpu(void)
struct timespec ts;
TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
- "clock_gettime() failed: %d\n", errno);
+ "clock_gettime() failed: %d", errno);
ts.tv_sec += 2;
TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
- "sem_timedwait() failed: %d\n", errno);
+ "sem_timedwait() failed: %d", errno);
}
static void *vm_gpa2hva(struct vm_data *data, uint64_t gpa, uint64_t *rempages)
@@ -336,7 +336,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
gpa = vm_phy_pages_alloc(data->vm, npages, guest_addr, slot);
TEST_ASSERT(gpa == guest_addr,
- "vm_phy_pages_alloc() failed\n");
+ "vm_phy_pages_alloc() failed");
data->hva_slots[slot - 1] = addr_gpa2hva(data->vm, guest_addr);
memset(data->hva_slots[slot - 1], 0, npages * guest_page_size);
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index f74e76d03b7e..28f97fb52044 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -245,7 +245,7 @@ int main(int argc, char *argv[])
} while (snapshot != atomic_read(&seq_cnt));
TEST_ASSERT(rseq_cpu == cpu,
- "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu);
+ "rseq CPU = %d, sched CPU = %d", rseq_cpu, cpu);
}
/*
@@ -256,7 +256,7 @@ int main(int argc, char *argv[])
* migrations given the 1us+ delay in the migration task.
*/
TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
- "Only performed %d KVM_RUNs, task stalled too much?\n", i);
+ "Only performed %d KVM_RUNs, task stalled too much?", i);
pthread_join(migration_thread, NULL);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 075b80dbe237..40337f566eeb 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -98,11 +98,11 @@ static void wait_for_vcpu(void)
struct timespec ts;
TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
- "clock_gettime() failed: %d\n", errno);
+ "clock_gettime() failed: %d", errno);
ts.tv_sec += 2;
TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
- "sem_timedwait() failed: %d\n", errno);
+ "sem_timedwait() failed: %d", errno);
/* Wait for the vCPU thread to reenter the guest. */
usleep(100000);
@@ -302,7 +302,7 @@ static void test_delete_memory_region(void)
if (run->exit_reason == KVM_EXIT_INTERNAL_ERROR)
TEST_ASSERT(regs.rip >= final_rip_start &&
regs.rip < final_rip_end,
- "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx\n",
+ "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx",
final_rip_start, final_rip_end, regs.rip);
kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
index 7f5b330b6a1b..513d421a9bff 100644
--- a/tools/testing/selftests/kvm/system_counter_offset_test.c
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -108,7 +108,7 @@ static void enter_guest(struct kvm_vcpu *vcpu)
handle_abort(&uc);
return;
default:
- TEST_ASSERT(0, "unhandled ucall %ld\n",
+ TEST_ASSERT(0, "unhandled ucall %ld",
get_ucall(vcpu, &uc));
}
}
From 95be17e4008b592342ec6cfb9264f4b54c21b790 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 18:02:44 +0100
Subject: [PATCH 086/637] KVM: selftests: aarch64: Remove redundant newlines
TEST_* functions append their own newline. Remove newlines from
TEST_* callsites to avoid extra newlines in output.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20231206170241.82801-9-ajones@ventanamicro.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/aarch64/arch_timer.c | 12 ++++++------
tools/testing/selftests/kvm/aarch64/hypercalls.c | 16 ++++++++--------
.../selftests/kvm/aarch64/page_fault_test.c | 6 +++---
.../testing/selftests/kvm/aarch64/smccc_filter.c | 2 +-
.../selftests/kvm/aarch64/vpmu_counter_access.c | 12 ++++++------
.../selftests/kvm/lib/aarch64/processor.c | 2 +-
tools/testing/selftests/kvm/lib/aarch64/vgic.c | 4 ++--
7 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 274b8465b42a..2cb8dd1f8275 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -248,7 +248,7 @@ static void *test_vcpu_run(void *arg)
REPORT_GUEST_ASSERT(uc);
break;
default:
- TEST_FAIL("Unexpected guest exit\n");
+ TEST_FAIL("Unexpected guest exit");
}
return NULL;
@@ -287,7 +287,7 @@ static int test_migrate_vcpu(unsigned int vcpu_idx)
/* Allow the error where the vCPU thread is already finished */
TEST_ASSERT(ret == 0 || ret == ESRCH,
- "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n",
+ "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d",
vcpu_idx, new_pcpu, ret);
return ret;
@@ -326,12 +326,12 @@ static void test_run(struct kvm_vm *vm)
pthread_mutex_init(&vcpu_done_map_lock, NULL);
vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
- TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap\n");
+ TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap");
for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) {
ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run,
(void *)(unsigned long)i);
- TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread\n", i);
+ TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i);
}
/* Spawn a thread to control the vCPU migrations */
@@ -340,7 +340,7 @@ static void test_run(struct kvm_vm *vm)
ret = pthread_create(&pt_vcpu_migration, NULL,
test_vcpu_migration, NULL);
- TEST_ASSERT(!ret, "Failed to create the migration pthread\n");
+ TEST_ASSERT(!ret, "Failed to create the migration pthread");
}
@@ -384,7 +384,7 @@ static struct kvm_vm *test_vm_create(void)
if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET))
vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset);
else
- TEST_FAIL("no support for global offset\n");
+ TEST_FAIL("no support for global offset");
}
for (i = 0; i < nr_vcpus; i++)
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index 31f66ba97228..27c10e7a7e01 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -175,18 +175,18 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
/* First 'read' should be an upper limit of the features supported */
vcpu_get_reg(vcpu, reg_info->reg, &val);
TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit),
- "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n",
+ "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx",
reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val);
/* Test a 'write' by disabling all the features of the register map */
ret = __vcpu_set_reg(vcpu, reg_info->reg, 0);
TEST_ASSERT(ret == 0,
- "Failed to clear all the features of reg: 0x%lx; ret: %d\n",
+ "Failed to clear all the features of reg: 0x%lx; ret: %d",
reg_info->reg, errno);
vcpu_get_reg(vcpu, reg_info->reg, &val);
TEST_ASSERT(val == 0,
- "Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg);
+ "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg);
/*
* Test enabling a feature that's not supported.
@@ -195,7 +195,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
if (reg_info->max_feat_bit < 63) {
ret = __vcpu_set_reg(vcpu, reg_info->reg, BIT(reg_info->max_feat_bit + 1));
TEST_ASSERT(ret != 0 && errno == EINVAL,
- "Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n",
+ "Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx",
errno, reg_info->reg);
}
}
@@ -216,7 +216,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
*/
vcpu_get_reg(vcpu, reg_info->reg, &val);
TEST_ASSERT(val == 0,
- "Expected all the features to be cleared for reg: 0x%lx\n",
+ "Expected all the features to be cleared for reg: 0x%lx",
reg_info->reg);
/*
@@ -226,7 +226,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
*/
ret = __vcpu_set_reg(vcpu, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit));
TEST_ASSERT(ret != 0 && errno == EBUSY,
- "Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n",
+ "Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx",
errno, reg_info->reg);
}
}
@@ -265,7 +265,7 @@ static void test_guest_stage(struct kvm_vm **vm, struct kvm_vcpu **vcpu)
case TEST_STAGE_HVC_IFACE_FALSE_INFO:
break;
default:
- TEST_FAIL("Unknown test stage: %d\n", prev_stage);
+ TEST_FAIL("Unknown test stage: %d", prev_stage);
}
}
@@ -294,7 +294,7 @@ static void test_run(void)
REPORT_GUEST_ASSERT(uc);
break;
default:
- TEST_FAIL("Unexpected guest exit\n");
+ TEST_FAIL("Unexpected guest exit");
}
}
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 08a5ca5bed56..53fddad57cbb 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -414,10 +414,10 @@ static bool punch_hole_in_backing_store(struct kvm_vm *vm,
if (fd != -1) {
ret = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
0, paging_size);
- TEST_ASSERT(ret == 0, "fallocate failed\n");
+ TEST_ASSERT(ret == 0, "fallocate failed");
} else {
ret = madvise(hva, paging_size, MADV_DONTNEED);
- TEST_ASSERT(ret == 0, "madvise failed\n");
+ TEST_ASSERT(ret == 0, "madvise failed");
}
return true;
@@ -501,7 +501,7 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
void fail_vcpu_run_no_handler(int ret)
{
- TEST_FAIL("Unexpected vcpu run failure\n");
+ TEST_FAIL("Unexpected vcpu run failure");
}
void fail_vcpu_run_mmio_no_syndrome_handler(int ret)
diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
index f4ceae9c8925..2d189f3da228 100644
--- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c
+++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c
@@ -178,7 +178,7 @@ static void expect_call_denied(struct kvm_vcpu *vcpu)
struct ucall uc;
if (get_ucall(vcpu, &uc) != UCALL_SYNC)
- TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd);
+ TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
TEST_ASSERT(uc.args[1] == SMCCC_RET_NOT_SUPPORTED,
"Unexpected SMCCC return code: %lu", uc.args[1]);
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index 9d51b5691349..5f9713364693 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -517,11 +517,11 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
if (expect_fail)
TEST_ASSERT(pmcr_orig == pmcr,
- "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx\n",
+ "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx",
pmcr, pmcr_n);
else
TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr),
- "Failed to update PMCR.N to %lu (received: %lu)\n",
+ "Failed to update PMCR.N to %lu (received: %lu)",
pmcr_n, get_pmcr_n(pmcr));
}
@@ -594,12 +594,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
*/
vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val);
TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
- "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+ "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
KVM_ARM64_SYS_REG(set_reg_id), reg_val);
vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val);
TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
- "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+ "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
/*
@@ -611,12 +611,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val);
TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
- "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+ "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
KVM_ARM64_SYS_REG(set_reg_id), reg_val);
vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val);
TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
- "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+ "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 41c776b642c0..43b9a7283360 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -398,7 +398,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
int i;
TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
- " num: %u\n", num);
+ " num: %u", num);
va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b5f28d21a947..184378d593e9 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -38,7 +38,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
struct list_head *iter;
unsigned int nr_gic_pages, nr_vcpus_created = 0;
- TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty\n");
+ TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty");
/*
* Make sure that the caller is infact calling this
@@ -47,7 +47,7 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
list_for_each(iter, &vm->vcpus)
nr_vcpus_created++;
TEST_ASSERT(nr_vcpus == nr_vcpus_created,
- "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)\n",
+ "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)",
nr_vcpus, nr_vcpus_created);
/* Distributor setup */
From 93e43e50b80b4f342251fb48f8ebced4d3c34983 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 18:02:45 +0100
Subject: [PATCH 087/637] KVM: selftests: riscv: Remove redundant newlines
TEST_* functions append their own newline. Remove newlines from
TEST_* callsites to avoid extra newlines in output.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20231206170241.82801-10-ajones@ventanamicro.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/lib/riscv/processor.c | 2 +-
tools/testing/selftests/kvm/riscv/get-reg-list.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 7ca736fb4194..2bb33a8ac03c 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -327,7 +327,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
int i;
TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
- " num: %u\n", num);
+ " num: %u", num);
va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6652108816db..50bb9bb73a7b 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -150,7 +150,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
/* Double check whether the desired extension was enabled */
__TEST_REQUIRE(vcpu_has_ext(vcpu, feature),
- "%s not available, skipping tests\n", s->name);
+ "%s not available, skipping tests", s->name);
}
}
From a38125f188c141cd1297d14af84c28b5276ab287 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 18:02:46 +0100
Subject: [PATCH 088/637] KVM: selftests: s390x: Remove redundant newlines
TEST_* functions append their own newline. Remove newlines from
TEST_* callsites to avoid extra newlines in output.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Acked-by: Janosch Frank <frankja@linux.ibm.com>
Acked-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Link: https://lore.kernel.org/r/20231206170241.82801-11-ajones@ventanamicro.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/lib/s390x/processor.c | 2 +-
tools/testing/selftests/kvm/s390x/resets.c | 4 ++--
.../selftests/kvm/s390x/sync_regs_test.c | 20 +++++++++----------
3 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 15945121daf1..f6d227892cbc 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -198,7 +198,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
int i;
TEST_ASSERT(num >= 1 && num <= 5, "Unsupported number of args,\n"
- " num: %u\n",
+ " num: %u",
num);
va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index e41e2cb8ffa9..357943f2bea8 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -78,7 +78,7 @@ static void assert_noirq(struct kvm_vcpu *vcpu)
* (notably, the emergency call interrupt we have injected) should
* be cleared by the resets, so this should be 0.
*/
- TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d\n", errno);
+ TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d", errno);
TEST_ASSERT(!irqs, "IRQ pending");
}
@@ -199,7 +199,7 @@ static void inject_irq(struct kvm_vcpu *vcpu)
irq->type = KVM_S390_INT_EMERGENCY;
irq->u.emerg.code = vcpu->id;
irqs = __vcpu_ioctl(vcpu, KVM_S390_SET_IRQ_STATE, &irq_state);
- TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno);
+ TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d", errno);
}
static struct kvm_vm *create_vm(struct kvm_vcpu **vcpu)
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index 636a70ddac1e..43fb25ddc3ec 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -39,13 +39,13 @@ static void guest_code(void)
#define REG_COMPARE(reg) \
TEST_ASSERT(left->reg == right->reg, \
"Register " #reg \
- " values did not match: 0x%llx, 0x%llx\n", \
+ " values did not match: 0x%llx, 0x%llx", \
left->reg, right->reg)
#define REG_COMPARE32(reg) \
TEST_ASSERT(left->reg == right->reg, \
"Register " #reg \
- " values did not match: 0x%x, 0x%x\n", \
+ " values did not match: 0x%x, 0x%x", \
left->reg, right->reg)
@@ -82,14 +82,14 @@ void test_read_invalid(struct kvm_vcpu *vcpu)
run->kvm_valid_regs = INVALID_SYNC_FIELD;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_valid_regs = 0;
run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_valid_regs = 0;
}
@@ -103,14 +103,14 @@ void test_set_invalid(struct kvm_vcpu *vcpu)
run->kvm_dirty_regs = INVALID_SYNC_FIELD;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_dirty_regs = 0;
run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_dirty_regs = 0;
}
@@ -125,12 +125,12 @@ void test_req_and_verify_all_valid_regs(struct kvm_vcpu *vcpu)
/* Request and verify all valid register sets. */
run->kvm_valid_regs = TEST_SYNC_FIELDS;
rv = _vcpu_run(vcpu);
- TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
TEST_ASSERT(run->s390_sieic.icptcode == 4 &&
(run->s390_sieic.ipa >> 8) == 0x83 &&
(run->s390_sieic.ipb >> 16) == 0x501,
- "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x\n",
+ "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x",
run->s390_sieic.icptcode, run->s390_sieic.ipa,
run->s390_sieic.ipb);
@@ -161,7 +161,7 @@ void test_set_and_verify_various_reg_values(struct kvm_vcpu *vcpu)
}
rv = _vcpu_run(vcpu);
- TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1,
"r11 sync regs value incorrect 0x%llx.",
@@ -193,7 +193,7 @@ void test_clear_kvm_dirty_regs_bits(struct kvm_vcpu *vcpu)
run->s.regs.gprs[11] = 0xDEADBEEF;
run->s.regs.diag318 = 0x4B1D;
rv = _vcpu_run(vcpu);
- TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
+ TEST_ASSERT(rv == 0, "vcpu_run failed: %d", rv);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF,
"r11 sync regs value incorrect 0x%llx.",
From d877550eaf2dc9090d782864c96939397a3c6835 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@google.com>
Date: Mon, 29 Jan 2024 22:36:03 -0800
Subject: [PATCH 089/637] x86/fpu: Stop relying on userspace for info to fault
in xsave buffer
Before this change, the expected size of the user space buffer was
taken from fx_sw->xstate_size. fx_sw->xstate_size can be changed
from user-space, so it is possible construct a sigreturn frame where:
* fx_sw->xstate_size is smaller than the size required by valid bits in
fx_sw->xfeatures.
* user-space unmaps parts of the sigrame fpu buffer so that not all of
the buffer required by xrstor is accessible.
In this case, xrstor tries to restore and accesses the unmapped area
which results in a fault. But fault_in_readable succeeds because buf +
fx_sw->xstate_size is within the still mapped area, so it goes back and
tries xrstor again. It will spin in this loop forever.
Instead, fault in the maximum size which can be touched by XRSTOR (taken
from fpstate->user_size).
[ dhansen: tweak subject / changelog ]
Fixes: fcb3635f5018 ("x86/fpu/signal: Handle #PF in the direct restore path")
Reported-by: Konstantin Bogomolov <bogomolov@google.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrei Vagin <avagin@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20240130063603.3392627-1-avagin%40google.com
---
arch/x86/kernel/fpu/signal.c | 13 +++++--------
1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 558076dbde5b..247f2225aa9f 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
* Attempt to restore the FPU registers directly from user memory.
* Pagefaults are handled and any errors returned are fatal.
*/
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
- bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
{
struct fpu *fpu = ¤t->thread.fpu;
int ret;
+ /* Restore enabled features only. */
+ xrestore &= fpu->fpstate->user_xfeatures;
retry:
fpregs_lock();
/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
if (ret != X86_TRAP_PF)
return false;
- if (!fault_in_readable(buf, size))
+ if (!fault_in_readable(buf, fpu->fpstate->user_size))
goto retry;
return false;
}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
struct user_i387_ia32_struct env;
bool success, fx_only = false;
union fpregs_state *fpregs;
- unsigned int state_size;
u64 user_xfeatures = 0;
if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
return false;
fx_only = !fx_sw_user.magic1;
- state_size = fx_sw_user.xstate_size;
user_xfeatures = fx_sw_user.xfeatures;
} else {
user_xfeatures = XFEATURE_MASK_FPSSE;
- state_size = fpu->fpstate->user_size;
}
if (likely(!ia32_fxstate)) {
/* Restore the FPU registers directly from user memory. */
- return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
- state_size);
+ return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
}
/*
From 65612e993493014cb95be81ca4f98e08732c46d0 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 6 Dec 2023 18:02:47 +0100
Subject: [PATCH 090/637] KVM: selftests: x86_64: Remove redundant newlines
TEST_* functions append their own newline. Remove newlines from
TEST_* callsites to avoid extra newlines in output.
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20231206170241.82801-12-ajones@ventanamicro.com
[sean: keep the newline in the "tsc\n" strncmp()]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/lib/x86_64/processor.c | 10 +++----
tools/testing/selftests/kvm/lib/x86_64/vmx.c | 6 ++--
tools/testing/selftests/kvm/x86_64/amx_test.c | 2 +-
.../testing/selftests/kvm/x86_64/cpuid_test.c | 4 +--
.../selftests/kvm/x86_64/flds_emulation.h | 2 +-
.../selftests/kvm/x86_64/hyperv_clock.c | 4 +--
.../testing/selftests/kvm/x86_64/hyperv_ipi.c | 2 +-
.../selftests/kvm/x86_64/hyperv_tlb_flush.c | 2 +-
.../selftests/kvm/x86_64/kvm_clock_test.c | 6 ++--
.../selftests/kvm/x86_64/platform_info_test.c | 2 +-
.../kvm/x86_64/pmu_event_filter_test.c | 2 +-
.../selftests/kvm/x86_64/sev_migrate_tests.c | 28 +++++++++----------
.../smaller_maxphyaddr_emulation_test.c | 4 +--
.../selftests/kvm/x86_64/sync_regs_test.c | 10 +++----
.../kvm/x86_64/ucna_injection_test.c | 8 +++---
.../selftests/kvm/x86_64/userspace_io_test.c | 2 +-
.../kvm/x86_64/vmx_apic_access_test.c | 2 +-
.../selftests/kvm/x86_64/vmx_dirty_log_test.c | 16 +++++------
.../vmx_exception_with_invalid_guest_state.c | 2 +-
.../selftests/kvm/x86_64/xapic_ipi_test.c | 8 +++---
.../selftests/kvm/x86_64/xcr0_cpuid_test.c | 2 +-
.../selftests/kvm/x86_64/xss_msr_test.c | 2 +-
22 files changed, 63 insertions(+), 63 deletions(-)
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d8288374078e..4bc52948447d 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -170,10 +170,10 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
* this level.
*/
TEST_ASSERT(current_level != target_level,
- "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
+ "Cannot create hugepage at level: %u, vaddr: 0x%lx",
current_level, vaddr);
TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
- "Cannot create page table at level: %u, vaddr: 0x%lx\n",
+ "Cannot create page table at level: %u, vaddr: 0x%lx",
current_level, vaddr);
}
return pte;
@@ -220,7 +220,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
/* Fill in page table entry. */
pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
- "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
+ "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
}
@@ -253,7 +253,7 @@ static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
if (*pte & PTE_LARGE_MASK) {
TEST_ASSERT(*level == PG_LEVEL_NONE ||
*level == current_level,
- "Unexpected hugepage at level %d\n", current_level);
+ "Unexpected hugepage at level %d", current_level);
*level = current_level;
}
@@ -825,7 +825,7 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
struct kvm_regs regs;
TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
- " num: %u\n",
+ " num: %u",
num);
va_start(ap, num);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 59d97531c9b1..089b8925b6b2 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -54,7 +54,7 @@ int vcpu_enable_evmcs(struct kvm_vcpu *vcpu)
/* KVM should return supported EVMCS version range */
TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
(evmcs_ver & 0xff) > 0,
- "Incorrect EVMCS version range: %x:%x\n",
+ "Incorrect EVMCS version range: %x:%x",
evmcs_ver & 0xff, evmcs_ver >> 8);
return evmcs_ver;
@@ -387,10 +387,10 @@ static void nested_create_pte(struct kvm_vm *vm,
* this level.
*/
TEST_ASSERT(current_level != target_level,
- "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+ "Cannot create hugepage at level: %u, nested_paddr: 0x%lx",
current_level, nested_paddr);
TEST_ASSERT(!pte->page_size,
- "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+ "Cannot create page table at level: %u, nested_paddr: 0x%lx",
current_level, nested_paddr);
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 11329e5ff945..f7da543570ad 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -296,7 +296,7 @@ int main(int argc, char *argv[])
void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
/* Only check TMM0 register, 1 tile */
ret = memcmp(amx_start, tiles_data, TILE_SIZE);
- TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
+ TEST_ASSERT(ret == 0, "memcmp failed, ret=%d", ret);
kvm_x86_state_cleanup(state);
break;
case 9:
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index 3b34d8156d1c..8c579ce714e9 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -84,7 +84,7 @@ static void compare_cpuids(const struct kvm_cpuid2 *cpuid1,
TEST_ASSERT(e1->function == e2->function &&
e1->index == e2->index && e1->flags == e2->flags,
- "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x\n",
+ "CPUID entries[%d] mismtach: 0x%x.%d.%x vs. 0x%x.%d.%x",
i, e1->function, e1->index, e1->flags,
e2->function, e2->index, e2->flags);
@@ -170,7 +170,7 @@ static void test_get_cpuid2(struct kvm_vcpu *vcpu)
vcpu_ioctl(vcpu, KVM_GET_CPUID2, cpuid);
TEST_ASSERT(cpuid->nent == vcpu->cpuid->nent,
- "KVM didn't update nent on success, wanted %u, got %u\n",
+ "KVM didn't update nent on success, wanted %u, got %u",
vcpu->cpuid->nent, cpuid->nent);
for (i = 0; i < vcpu->cpuid->nent; i++) {
diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
index 0a1573d52882..37b1a9f52864 100644
--- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h
+++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
@@ -41,7 +41,7 @@ static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu)
insn_bytes = run->emulation_failure.insn_bytes;
TEST_ASSERT(insn_bytes[0] == 0xd9 && insn_bytes[1] == 0,
- "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x\n",
+ "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x",
insn_bytes[0], insn_bytes[1]);
vcpu_regs_get(vcpu, ®s);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index f5e1e98f04f9..65690d916db7 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -220,7 +220,7 @@ int main(void)
tsc_page_gva = vm_vaddr_alloc_page(vm);
memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize());
TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
- "TSC page has to be page aligned\n");
+ "TSC page has to be page aligned");
vcpu_args_set(vcpu, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
host_check_tsc_msr_rdtsc(vcpu);
@@ -237,7 +237,7 @@ int main(void)
break;
case UCALL_DONE:
/* Keep in sync with guest_main() */
- TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+ TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d",
stage);
goto out;
default:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 65e5f4c05068..f1617762c22f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -289,7 +289,7 @@ int main(int argc, char *argv[])
switch (get_ucall(vcpu[0], &uc)) {
case UCALL_SYNC:
TEST_ASSERT(uc.args[1] == stage,
- "Unexpected stage: %ld (%d expected)\n",
+ "Unexpected stage: %ld (%d expected)",
uc.args[1], stage);
break;
case UCALL_DONE:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
index c4443f71f8dd..05b56095cf76 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
@@ -658,7 +658,7 @@ int main(int argc, char *argv[])
switch (get_ucall(vcpu[0], &uc)) {
case UCALL_SYNC:
TEST_ASSERT(uc.args[1] == stage,
- "Unexpected stage: %ld (%d expected)\n",
+ "Unexpected stage: %ld (%d expected)",
uc.args[1], stage);
break;
case UCALL_ABORT:
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
index 1778704360a6..3e0b7d51abda 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
@@ -92,7 +92,7 @@ static void setup_clock(struct kvm_vm *vm, struct test_case *test_case)
break;
} while (errno == EINTR);
- TEST_ASSERT(!r, "clock_gettime() failed: %d\n", r);
+ TEST_ASSERT(!r, "clock_gettime() failed: %d", r);
data.realtime = ts.tv_sec * NSEC_PER_SEC;
data.realtime += ts.tv_nsec;
@@ -127,7 +127,7 @@ static void enter_guest(struct kvm_vcpu *vcpu)
handle_abort(&uc);
return;
default:
- TEST_ASSERT(0, "unhandled ucall: %ld\n", uc.cmd);
+ TEST_ASSERT(0, "unhandled ucall: %ld", uc.cmd);
}
}
}
@@ -154,7 +154,7 @@ static void check_clocksource(void)
}
clk_name = malloc(st.st_size);
- TEST_ASSERT(clk_name, "failed to allocate buffer to read file\n");
+ TEST_ASSERT(clk_name, "failed to allocate buffer to read file");
if (!fgets(clk_name, st.st_size, fp)) {
pr_info("failed to read clocksource file: %d; assuming TSC.\n",
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index c9a07963d68a..87011965dc41 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -44,7 +44,7 @@ static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu)
get_ucall(vcpu, &uc);
TEST_ASSERT(uc.cmd == UCALL_SYNC,
- "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd);
+ "Received ucall other than UCALL_SYNC: %lu", uc.cmd);
TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 283cc55597a4..a3bd54b925ab 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -866,7 +866,7 @@ static void __test_fixed_counter_bitmap(struct kvm_vcpu *vcpu, uint8_t idx,
* userspace doesn't set any pmu filter.
*/
count = run_vcpu_to_sync(vcpu);
- TEST_ASSERT(count, "Unexpected count value: %ld\n", count);
+ TEST_ASSERT(count, "Unexpected count value: %ld", count);
for (i = 0; i < BIT(nr_fixed_counters); i++) {
bitmap = BIT(i);
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index c7ef97561038..a49828adf294 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -91,7 +91,7 @@ static void sev_migrate_from(struct kvm_vm *dst, struct kvm_vm *src)
int ret;
ret = __sev_migrate_from(dst, src);
- TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno);
+ TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d", ret, errno);
}
static void test_sev_migrate_from(bool es)
@@ -113,7 +113,7 @@ static void test_sev_migrate_from(bool es)
/* Migrate the guest back to the original VM. */
ret = __sev_migrate_from(src_vm, dst_vms[NR_MIGRATE_TEST_VMS - 1]);
TEST_ASSERT(ret == -1 && errno == EIO,
- "VM that was migrated from should be dead. ret %d, errno: %d\n", ret,
+ "VM that was migrated from should be dead. ret %d, errno: %d", ret,
errno);
kvm_vm_free(src_vm);
@@ -172,7 +172,7 @@ static void test_sev_migrate_parameters(void)
vm_no_sev = aux_vm_create(true);
ret = __sev_migrate_from(vm_no_vcpu, vm_no_sev);
TEST_ASSERT(ret == -1 && errno == EINVAL,
- "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
+ "Migrations require SEV enabled. ret %d, errno: %d", ret,
errno);
if (!have_sev_es)
@@ -187,25 +187,25 @@ static void test_sev_migrate_parameters(void)
ret = __sev_migrate_from(sev_vm, sev_es_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n",
+ "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d",
ret, errno);
ret = __sev_migrate_from(sev_es_vm, sev_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n",
+ "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d",
ret, errno);
ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n",
+ "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d",
ret, errno);
ret = __sev_migrate_from(vm_no_vcpu, sev_es_vm_no_vmsa);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n",
+ "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d",
ret, errno);
kvm_vm_free(sev_vm);
@@ -227,7 +227,7 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src)
int ret;
ret = __sev_mirror_create(dst, src);
- TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
+ TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno);
}
static void verify_mirror_allowed_cmds(int vm_fd)
@@ -259,7 +259,7 @@ static void verify_mirror_allowed_cmds(int vm_fd)
ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able call command: %d. ret: %d, errno: %d\n",
+ "Should not be able call command: %d. ret: %d, errno: %d",
cmd_id, ret, errno);
}
@@ -301,18 +301,18 @@ static void test_sev_mirror_parameters(void)
ret = __sev_mirror_create(sev_vm, sev_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able copy context to self. ret: %d, errno: %d\n",
+ "Should not be able copy context to self. ret: %d, errno: %d",
ret, errno);
ret = __sev_mirror_create(vm_no_vcpu, vm_with_vcpu);
TEST_ASSERT(ret == -1 && errno == EINVAL,
- "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+ "Copy context requires SEV enabled. ret %d, errno: %d", ret,
errno);
ret = __sev_mirror_create(vm_with_vcpu, sev_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+ "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d",
ret, errno);
if (!have_sev_es)
@@ -322,13 +322,13 @@ static void test_sev_mirror_parameters(void)
ret = __sev_mirror_create(sev_vm, sev_es_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n",
+ "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d",
ret, errno);
ret = __sev_mirror_create(sev_es_vm, sev_vm);
TEST_ASSERT(
ret == -1 && errno == EINVAL,
- "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
+ "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d",
ret, errno);
kvm_vm_free(sev_es_vm);
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
index 06edf00a97d6..1a46dd7bb391 100644
--- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
@@ -74,7 +74,7 @@ int main(int argc, char *argv[])
MEM_REGION_SIZE / PAGE_SIZE, 0);
gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
MEM_REGION_GPA, MEM_REGION_SLOT);
- TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+ TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc");
virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
hva = addr_gpa2hva(vm, MEM_REGION_GPA);
memset(hva, 0, PAGE_SIZE);
@@ -102,7 +102,7 @@ int main(int argc, char *argv[])
case UCALL_DONE:
break;
default:
- TEST_FAIL("Unrecognized ucall: %lu\n", uc.cmd);
+ TEST_FAIL("Unrecognized ucall: %lu", uc.cmd);
}
kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 00965ba33f73..a91b5b145fa3 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -46,7 +46,7 @@ static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
#define REG_COMPARE(reg) \
TEST_ASSERT(left->reg == right->reg, \
"Register " #reg \
- " values did not match: 0x%llx, 0x%llx\n", \
+ " values did not match: 0x%llx, 0x%llx", \
left->reg, right->reg)
REG_COMPARE(rax);
REG_COMPARE(rbx);
@@ -230,14 +230,14 @@ int main(int argc, char *argv[])
run->kvm_valid_regs = INVALID_SYNC_FIELD;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_valid_regs = 0;
run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_valid_regs = 0;
@@ -245,14 +245,14 @@ int main(int argc, char *argv[])
run->kvm_dirty_regs = INVALID_SYNC_FIELD;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_dirty_regs = 0;
run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
rv = _vcpu_run(vcpu);
TEST_ASSERT(rv < 0 && errno == EINVAL,
- "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
rv);
run->kvm_dirty_regs = 0;
diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
index 0ed32ec903d0..dcbb3c29fb8e 100644
--- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
+++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
@@ -143,7 +143,7 @@ static void run_vcpu_expect_gp(struct kvm_vcpu *vcpu)
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_SYNC,
- "Expect UCALL_SYNC\n");
+ "Expect UCALL_SYNC");
TEST_ASSERT(uc.args[1] == SYNC_GP, "#GP is expected.");
printf("vCPU received GP in guest.\n");
}
@@ -188,7 +188,7 @@ static void *run_ucna_injection(void *arg)
TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
- "Expect UCALL_SYNC\n");
+ "Expect UCALL_SYNC");
TEST_ASSERT(uc.args[1] == SYNC_FIRST_UCNA, "Injecting first UCNA.");
printf("Injecting first UCNA at %#x.\n", FIRST_UCNA_ADDR);
@@ -198,7 +198,7 @@ static void *run_ucna_injection(void *arg)
TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
TEST_ASSERT(get_ucall(params->vcpu, &uc) == UCALL_SYNC,
- "Expect UCALL_SYNC\n");
+ "Expect UCALL_SYNC");
TEST_ASSERT(uc.args[1] == SYNC_SECOND_UCNA, "Injecting second UCNA.");
printf("Injecting second UCNA at %#x.\n", SECOND_UCNA_ADDR);
@@ -208,7 +208,7 @@ static void *run_ucna_injection(void *arg)
TEST_ASSERT_KVM_EXIT_REASON(params->vcpu, KVM_EXIT_IO);
if (get_ucall(params->vcpu, &uc) == UCALL_ABORT) {
- TEST_ASSERT(false, "vCPU assertion failure: %s.\n",
+ TEST_ASSERT(false, "vCPU assertion failure: %s.",
(const char *)uc.args[0]);
}
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 255c50b0dc32..9481cbcf284f 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -71,7 +71,7 @@ int main(int argc, char *argv[])
break;
TEST_ASSERT(run->io.port == 0x80,
- "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+ "Expected I/O at port 0x80, got port 0x%x", run->io.port);
/*
* Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
index 2bed5fb3a0d6..a81a24761aac 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -99,7 +99,7 @@ int main(int argc, char *argv[])
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
TEST_ASSERT(run->internal.suberror ==
KVM_INTERNAL_ERROR_EMULATION,
- "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+ "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u",
run->internal.suberror);
break;
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index e4ad5fef52ff..7f6f5f23fb9b 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -128,17 +128,17 @@ int main(int argc, char *argv[])
*/
kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
if (uc.args[1]) {
- TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n");
- TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n");
+ TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean");
+ TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest");
} else {
- TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n");
- TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n");
+ TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty");
+ TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest");
}
- TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n");
- TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n");
- TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n");
- TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n");
+ TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty");
+ TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest");
+ TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty");
+ TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest");
break;
case UCALL_DONE:
done = true;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
index a9b827c69f32..fad3634fd9eb 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -28,7 +28,7 @@ static void __run_vcpu_with_invalid_state(struct kvm_vcpu *vcpu)
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);
TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
- "Expected emulation failure, got %d\n",
+ "Expected emulation failure, got %d",
run->emulation_failure.suberror);
}
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
index 67ac2a3292ef..725c206ba0b9 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
@@ -216,7 +216,7 @@ static void *vcpu_thread(void *arg)
"Halting vCPU halted %lu times, woke %lu times, received %lu IPIs.\n"
"Halter TPR=%#x PPR=%#x LVR=%#x\n"
"Migrations attempted: %lu\n"
- "Migrations completed: %lu\n",
+ "Migrations completed: %lu",
vcpu->id, (const char *)uc.args[0],
params->data->ipis_sent, params->data->hlt_count,
params->data->wake_count,
@@ -288,7 +288,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
}
TEST_ASSERT(nodes > 1,
- "Did not find at least 2 numa nodes. Can't do migration\n");
+ "Did not find at least 2 numa nodes. Can't do migration");
fprintf(stderr, "Migrating amongst %d nodes found\n", nodes);
@@ -347,7 +347,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
wake_count != data->wake_count,
"IPI, HLT and wake count have not increased "
"in the last %lu seconds. "
- "HLTer is likely hung.\n", interval_secs);
+ "HLTer is likely hung.", interval_secs);
ipis_sent = data->ipis_sent;
hlt_count = data->hlt_count;
@@ -381,7 +381,7 @@ void get_cmdline_args(int argc, char *argv[], int *run_secs,
"-m adds calls to migrate_pages while vCPUs are running."
" Default is no migrations.\n"
"-d <delay microseconds> - delay between migrate_pages() calls."
- " Default is %d microseconds.\n",
+ " Default is %d microseconds.",
DEFAULT_RUN_SECS, DEFAULT_DELAY_USECS);
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
index dc6217440db3..25a0b0db5c3c 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
@@ -116,7 +116,7 @@ int main(int argc, char *argv[])
vcpu_run(vcpu);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Unexpected exit reason: %u (%s),\n",
+ "Unexpected exit reason: %u (%s),",
run->exit_reason,
exit_reason_str(run->exit_reason));
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
index e0ddf47362e7..167c97abff1b 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
@@ -29,7 +29,7 @@ int main(int argc, char *argv[])
xss_val = vcpu_get_msr(vcpu, MSR_IA32_XSS);
TEST_ASSERT(xss_val == 0,
- "MSR_IA32_XSS should be initialized to zero\n");
+ "MSR_IA32_XSS should be initialized to zero");
vcpu_set_msr(vcpu, MSR_IA32_XSS, xss_val);
From 46fee9e38995af9ae16a8cc7d05031486d44cf35 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Jan 2024 14:03:02 -0800
Subject: [PATCH 091/637] KVM: selftests: Delete superfluous, unused "stage"
variable in AMX test
Delete the AMX's tests "stage" counter, as the counter is no longer used,
which makes clang unhappy:
x86_64/amx_test.c:224:6: error: variable 'stage' set but not used
int stage, ret;
^
1 error generated.
Note, "stage" was never really used, it just happened to be dumped out by
a (failed) assertion on run->exit_reason, i.e. the AMX test has no concept
of stages, the code was likely copy+pasted from a different test.
Fixes: c96f57b08012 ("KVM: selftests: Make vCPU exit reason test assertion common")
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20240109220302.399296-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/x86_64/amx_test.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index f7da543570ad..eae521f050e0 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -221,7 +221,7 @@ int main(int argc, char *argv[])
vm_vaddr_t amx_cfg, tiledata, xstate;
struct ucall uc;
u32 amx_offset;
- int stage, ret;
+ int ret;
/*
* Note, all off-by-default features must be enabled before anything
@@ -263,7 +263,7 @@ int main(int argc, char *argv[])
memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE));
vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate);
- for (stage = 1; ; stage++) {
+ for (;;) {
vcpu_run(vcpu);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
From 8ad4855273488c9bd5320b3fee80f66f0023f326 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 29 Jan 2024 09:58:46 +0100
Subject: [PATCH 092/637] KVM: selftests: Avoid infinite loop in
hyperv_features when invtsc is missing
When X86_FEATURE_INVTSC is missing, guest_test_msrs_access() was supposed
to skip testing dependent Hyper-V invariant TSC feature. Unfortunately,
'continue' does not lead to that as stage is not incremented. Moreover,
'vm' allocated with vm_create_with_one_vcpu() is not freed and the test
runs out of available file descriptors very quickly.
Fixes: bd827bd77537 ("KVM: selftests: Test Hyper-V invariant TSC control")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240129085847.2674082-1-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/x86_64/hyperv_features.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 4f4193fc74ff..b923a285e96f 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -454,7 +454,7 @@ static void guest_test_msrs_access(void)
case 44:
/* MSR is not available when CPUID feature bit is unset */
if (!has_invtsc)
- continue;
+ goto next_stage;
msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
msr->write = false;
msr->fault_expected = true;
@@ -462,7 +462,7 @@ static void guest_test_msrs_access(void)
case 45:
/* MSR is vailable when CPUID feature bit is set */
if (!has_invtsc)
- continue;
+ goto next_stage;
vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT);
msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
msr->write = false;
@@ -471,7 +471,7 @@ static void guest_test_msrs_access(void)
case 46:
/* Writing bits other than 0 is forbidden */
if (!has_invtsc)
- continue;
+ goto next_stage;
msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
msr->write = true;
msr->write_val = 0xdeadbeef;
@@ -480,7 +480,7 @@ static void guest_test_msrs_access(void)
case 47:
/* Setting bit 0 enables the feature */
if (!has_invtsc)
- continue;
+ goto next_stage;
msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL;
msr->write = true;
msr->write_val = 1;
@@ -513,6 +513,7 @@ static void guest_test_msrs_access(void)
return;
}
+next_stage:
stage++;
kvm_vm_free(vm);
}
From c2a449a30fa2b5ddc1dd058e92e047157c9eeb9e Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 29 Jan 2024 09:58:47 +0100
Subject: [PATCH 093/637] KVM: selftests: Fail tests when open() fails with
!ENOENT
open_path_or_exit() is used for '/dev/kvm', '/dev/sev', and
'/sys/module/%s/parameters/%s' and skipping test when the entry is missing
is completely reasonable. Other errors, however, may indicate a real issue
which is easy to miss. E.g. when 'hyperv_features' test was entering an
infinite loop the output was:
./hyperv_features
Testing access to Hyper-V specific MSRs
1..0 # SKIP - /dev/kvm not available (errno: 24)
and this can easily get overlooked.
Keep ENOENT case 'special' for skipping tests and fail when open() results
in any other errno.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240129085847.2674082-2-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/lib/kvm_util.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 8754abaff5e9..1b197426f29f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -27,7 +27,8 @@ int open_path_or_exit(const char *path, int flags)
int fd;
fd = open(path, flags);
- __TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno);
+ __TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno));
+ TEST_ASSERT(fd >= 0, "Failed to open '%s'", path);
return fd;
}
From 2f77465b05b1270c832b5e2ee27037672ad2a10a Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 30 Jan 2024 19:01:35 +0100
Subject: [PATCH 094/637] x86/efistub: Avoid placing the kernel below
LOAD_PHYSICAL_ADDR
The EFI stub's kernel placement logic randomizes the physical placement
of the kernel by taking all available memory into account, and picking a
region at random, based on a random seed.
When KASLR is disabled, this seed is set to 0x0, and this results in the
lowest available region of memory to be selected for loading the kernel,
even if this is below LOAD_PHYSICAL_ADDR. Some of this memory is
typically reserved for the GFP_DMA region, to accommodate masters that
can only access the first 16 MiB of system memory.
Even if such devices are rare these days, we may still end up with a
warning in the kernel log, as reported by Tom:
swapper/0: page allocation failure: order:10, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0
Fix this by tweaking the random allocation logic to accept a low bound
on the placement, and set it to LOAD_PHYSICAL_ADDR.
Fixes: a1b87d54f4e4 ("x86/efistub: Avoid legacy decompressor when doing EFI boot")
Reported-by: Tom Englund <tomenglund26@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218404
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/libstub/efistub.h | 3 ++-
drivers/firmware/efi/libstub/kaslr.c | 2 +-
drivers/firmware/efi/libstub/randomalloc.c | 12 +++++++-----
drivers/firmware/efi/libstub/x86-stub.c | 1 +
drivers/firmware/efi/libstub/zboot.c | 2 +-
5 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 212687c30d79..c04b82ea40f2 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -956,7 +956,8 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
unsigned long *addr, unsigned long random_seed,
- int memory_type, unsigned long alloc_limit);
+ int memory_type, unsigned long alloc_min,
+ unsigned long alloc_max);
efi_status_t efi_random_get_seed(void);
diff --git a/drivers/firmware/efi/libstub/kaslr.c b/drivers/firmware/efi/libstub/kaslr.c
index 62d63f7a2645..1a9808012abd 100644
--- a/drivers/firmware/efi/libstub/kaslr.c
+++ b/drivers/firmware/efi/libstub/kaslr.c
@@ -119,7 +119,7 @@ efi_status_t efi_kaslr_relocate_kernel(unsigned long *image_addr,
*/
status = efi_random_alloc(*reserve_size, min_kimg_align,
reserve_addr, phys_seed,
- EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+ EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
if (status != EFI_SUCCESS)
efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
} else {
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 674a064b8f7a..4e96a855fdf4 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -17,7 +17,7 @@
static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
unsigned long size,
unsigned long align_shift,
- u64 alloc_limit)
+ u64 alloc_min, u64 alloc_max)
{
unsigned long align = 1UL << align_shift;
u64 first_slot, last_slot, region_end;
@@ -30,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
return 0;
region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1,
- alloc_limit);
+ alloc_max);
if (region_end < size)
return 0;
- first_slot = round_up(md->phys_addr, align);
+ first_slot = round_up(max(md->phys_addr, alloc_min), align);
last_slot = round_down(region_end - size + 1, align);
if (first_slot > last_slot)
@@ -56,7 +56,8 @@ efi_status_t efi_random_alloc(unsigned long size,
unsigned long *addr,
unsigned long random_seed,
int memory_type,
- unsigned long alloc_limit)
+ unsigned long alloc_min,
+ unsigned long alloc_max)
{
unsigned long total_slots = 0, target_slot;
unsigned long total_mirrored_slots = 0;
@@ -78,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size,
efi_memory_desc_t *md = (void *)map->map + map_offset;
unsigned long slots;
- slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit);
+ slots = get_entry_num_slots(md, size, ilog2(align), alloc_min,
+ alloc_max);
MD_NUM_SLOTS(md) = slots;
total_slots += slots;
if (md->attribute & EFI_MEMORY_MORE_RELIABLE)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index cb0be88c8131..99429bc4b0c7 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -799,6 +799,7 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
seed[0], EFI_LOADER_CODE,
+ LOAD_PHYSICAL_ADDR,
EFI_X86_KERNEL_ALLOC_LIMIT);
if (status != EFI_SUCCESS)
return status;
diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c
index bdb17eac0cb4..1ceace956758 100644
--- a/drivers/firmware/efi/libstub/zboot.c
+++ b/drivers/firmware/efi/libstub/zboot.c
@@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab)
}
status = efi_random_alloc(alloc_size, min_kimg_align, &image_base,
- seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
+ seed, EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT);
if (status != EFI_SUCCESS) {
efi_err("Failed to allocate memory\n");
goto free_cmdline;
From aa0e784dea7c1a026aabff9db1cb5d2bd92b3e92 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 19 Jan 2024 18:06:35 +0800
Subject: [PATCH 095/637] efi/libstub: Add one kernel-doc comment
Add the description of @memory_type to silence the warning:
drivers/firmware/efi/libstub/alignedmem.c:27: warning: Function parameter or struct member 'memory_type' not described in 'efi_allocate_pages_aligned'
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
[ardb: tweak comment]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/libstub/alignedmem.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
index 6b83c492c3b8..31928bd87e0f 100644
--- a/drivers/firmware/efi/libstub/alignedmem.c
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -14,6 +14,7 @@
* @max: the address that the last allocated memory page shall not
* exceed
* @align: minimum alignment of the base of the allocation
+ * @memory_type: the type of memory to allocate
*
* Allocate pages as EFI_LOADER_DATA. The allocated pages are aligned according
* to @align, which should be >= EFI_ALLOC_ALIGN. The last allocated page will
From 10c02aad111df02088d1a81792a709f6a7eca6cc Mon Sep 17 00:00:00 2001
From: Sebastian Ene <sebastianene@google.com>
Date: Wed, 24 Jan 2024 09:10:28 +0000
Subject: [PATCH 096/637] KVM: arm64: Fix circular locking dependency
The rule inside kvm enforces that the vcpu->mutex is taken *inside*
kvm->lock. The rule is violated by the pkvm_create_hyp_vm() which acquires
the kvm->lock while already holding the vcpu->mutex lock from
kvm_vcpu_ioctl(). Avoid the circular locking dependency altogether by
protecting the hyp vm handle with the config_lock, much like we already
do for other forms of VM-scoped data.
Signed-off-by: Sebastian Ene <sebastianene@google.com>
Cc: stable@vger.kernel.org
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240124091027.1477174-2-sebastianene@google.com
---
arch/arm64/kvm/pkvm.c | 27 +++++++++++++++++----------
1 file changed, 17 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 8350fb8fee0b..b7be96a53597 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void)
hyp_mem_base);
}
+static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
+{
+ if (host_kvm->arch.pkvm.handle) {
+ WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
+ host_kvm->arch.pkvm.handle));
+ }
+
+ host_kvm->arch.pkvm.handle = 0;
+ free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+}
+
/*
* Allocates and donates memory for hypervisor VM structs at EL2.
*
@@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
return 0;
destroy_vm:
- pkvm_destroy_hyp_vm(host_kvm);
+ __pkvm_destroy_hyp_vm(host_kvm);
return ret;
free_vm:
free_pages_exact(hyp_vm, hyp_vm_sz);
@@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm)
{
int ret = 0;
- mutex_lock(&host_kvm->lock);
+ mutex_lock(&host_kvm->arch.config_lock);
if (!host_kvm->arch.pkvm.handle)
ret = __pkvm_create_hyp_vm(host_kvm);
- mutex_unlock(&host_kvm->lock);
+ mutex_unlock(&host_kvm->arch.config_lock);
return ret;
}
void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
{
- if (host_kvm->arch.pkvm.handle) {
- WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
- host_kvm->arch.pkvm.handle));
- }
-
- host_kvm->arch.pkvm.handle = 0;
- free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+ mutex_lock(&host_kvm->arch.config_lock);
+ __pkvm_destroy_hyp_vm(host_kvm);
+ mutex_unlock(&host_kvm->arch.config_lock);
}
int pkvm_init_host_vm(struct kvm *host_kvm)
From 98323e9d70172f1b46d1cadb20d6c54abf62870d Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Wed, 17 Jan 2024 20:05:45 +0100
Subject: [PATCH 097/637] topology: Set capacity_freq_ref in all cases
If "capacity-dmips-mhz" is not set, raw_capacity is null and we skip the
normalization step which includes setting per_cpu capacity_freq_ref.
Always register the notifier but skip the capacity normalization if
raw_capacity is null.
Fixes: 9942cb22ea45 ("sched/topology: Add a new arch_scale_freq_ref() method")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Tested-by: Pierre Gondois <pierre.gondois@arm.com>
Tested-by: Mark Brown <broonie@kernel.org>
Tested-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20240117190545.596057-1-vincent.guittot@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/arch_topology.c | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 018ac202de34..024b78a0cfc1 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -431,9 +431,6 @@ init_cpu_capacity_callback(struct notifier_block *nb,
struct cpufreq_policy *policy = data;
int cpu;
- if (!raw_capacity)
- return 0;
-
if (val != CPUFREQ_CREATE_POLICY)
return 0;
@@ -450,9 +447,11 @@ init_cpu_capacity_callback(struct notifier_block *nb,
}
if (cpumask_empty(cpus_to_visit)) {
- topology_normalize_cpu_scale();
- schedule_work(&update_topology_flags_work);
- free_raw_capacity();
+ if (raw_capacity) {
+ topology_normalize_cpu_scale();
+ schedule_work(&update_topology_flags_work);
+ free_raw_capacity();
+ }
pr_debug("cpu_capacity: parsing done\n");
schedule_work(&parsing_done_work);
}
@@ -472,7 +471,7 @@ static int __init register_cpufreq_notifier(void)
* On ACPI-based systems skip registering cpufreq notifier as cpufreq
* information is not needed for cpu capacity initialization.
*/
- if (!acpi_disabled || !raw_capacity)
+ if (!acpi_disabled)
return -EINVAL;
if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL))
From f884a9f9e59206a2d41f265e7e403f080d10b493 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 10 Jan 2024 17:48:44 +0100
Subject: [PATCH 098/637] btrfs: send: return EOPNOTSUPP on unknown flags
When some ioctl flags are checked we return EOPNOTSUPP, like for
BTRFS_SCRUB_SUPPORTED_FLAGS, BTRFS_SUBVOL_CREATE_ARGS_MASK or fallocate
modes. The EINVAL is supposed to be for a supported but invalid
values or combination of options. Fix that when checking send flags so
it's consistent with the rest.
CC: stable@vger.kernel.org # 4.14+
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5rryOLzp3EKq8RTbjMHMHeaJubfpsVLF6H4qJnKCUR1w@mail.gmail.com/
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/send.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 2d7519a6ce72..7902298c1f25 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -8111,7 +8111,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
}
if (arg->flags & ~BTRFS_SEND_FLAG_MASK) {
- ret = -EINVAL;
+ ret = -EOPNOTSUPP;
goto out;
}
From 0c309d66dacddf8ce939b891d9ead4a8e21ad6f0 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 10 Jan 2024 17:51:26 -0800
Subject: [PATCH 099/637] btrfs: forbid creating subvol qgroups
Creating a qgroup 0/subvolid leads to various races and it isn't
helpful, because you can't specify a subvol id when creating a subvol,
so you can't be sure it will be the right one. Any requirements on the
automatic subvol can be gratified by using a higher level qgroup and the
inheritance parameters of subvol creation.
Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs")
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/ioctl.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5d42319b43f2..fb2323b323bf 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3806,6 +3806,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
goto out;
}
+ if (sa->create && is_fstree(sa->qgroupid)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
From a8df35619948bd8363d330c20a90c9a7fbff28c0 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 10 Jan 2024 17:30:00 -0800
Subject: [PATCH 100/637] btrfs: forbid deleting live subvol qgroup
If a subvolume still exists, forbid deleting its qgroup 0/subvolid.
This behavior generally leads to incorrect behavior in squotas and
doesn't have a legitimate purpose.
Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/qgroup.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 63b426cc7798..5470e1cdf10c 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1736,6 +1736,15 @@ out:
return ret;
}
+static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
+{
+ return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
+ qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
+ qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
+ qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
+ qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
+}
+
int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -1755,6 +1764,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
goto out;
}
+ if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
/* Check if there are no children of this qgroup */
if (!list_empty(&qgroup->members)) {
ret = -EBUSY;
From e03ee2fe873eb68c1f9ba5112fee70303ebf9dfb Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Sat, 20 Jan 2024 19:41:28 +1030
Subject: [PATCH 101/637] btrfs: do not ASSERT() if the newly created subvolume
already got read
[BUG]
There is a syzbot crash, triggered by the ASSERT() during subvolume
creation:
assertion failed: !anon_dev, in fs/btrfs/disk-io.c:1319
------------[ cut here ]------------
kernel BUG at fs/btrfs/disk-io.c:1319!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
RIP: 0010:btrfs_get_root_ref.part.0+0x9aa/0xa60
<TASK>
btrfs_get_new_fs_root+0xd3/0xf0
create_subvol+0xd02/0x1650
btrfs_mksubvol+0xe95/0x12b0
__btrfs_ioctl_snap_create+0x2f9/0x4f0
btrfs_ioctl_snap_create+0x16b/0x200
btrfs_ioctl+0x35f0/0x5cf0
__x64_sys_ioctl+0x19d/0x210
do_syscall_64+0x3f/0xe0
entry_SYSCALL_64_after_hwframe+0x63/0x6b
---[ end trace 0000000000000000 ]---
[CAUSE]
During create_subvol(), after inserting root item for the newly created
subvolume, we would trigger btrfs_get_new_fs_root() to get the
btrfs_root of that subvolume.
The idea here is, we have preallocated an anonymous device number for
the subvolume, thus we can assign it to the new subvolume.
But there is really nothing preventing things like backref walk to read
the new subvolume.
If that happens before we call btrfs_get_new_fs_root(), the subvolume
would be read out, with a new anonymous device number assigned already.
In that case, we would trigger ASSERT(), as we really expect no one to
read out that subvolume (which is not yet accessible from the fs).
But things like backref walk is still possible to trigger the read on
the subvolume.
Thus our assumption on the ASSERT() is not correct in the first place.
[FIX]
Fix it by removing the ASSERT(), and just free the @anon_dev, reset it
to 0, and continue.
If the subvolume tree is read out by something else, it should have
already get a new anon_dev assigned thus we only need to free the
preallocated one.
Reported-by: Chenyuan Yang <chenyuan0y@gmail.com>
Fixes: 2dfb1e43f57d ("btrfs: preallocate anon block device at first phase of snapshot creation")
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/disk-io.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c6907d533fe8..e71ef97d0a7c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1336,8 +1336,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
- /* Shouldn't get preallocated anon_dev for cached roots */
- ASSERT(!anon_dev);
+ /*
+ * Some other caller may have read out the newly inserted
+ * subvolume already (for things like backref walk etc). Not
+ * that common but still possible. In that case, we just need
+ * to free the anon_dev.
+ */
+ if (unlikely(anon_dev)) {
+ free_anon_bdev(anon_dev);
+ anon_dev = 0;
+ }
+
if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
btrfs_put_root(root);
return ERR_PTR(-ENOENT);
From 4451e8e8415e4ef48cdc763d66855f8c25fda94c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 23 Jan 2024 12:08:18 -0600
Subject: [PATCH 102/637] pinctrl: amd: Add IRQF_ONESHOT to the interrupt
request
On some systems the interrupt is shared between GPIO controller
and ACPI SCI. When the interrupt is shared with the ACPI SCI the
flags need to be identical.
This should fix the GPIO controller failing to work after commit
7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI").
```
[ 0.417335] genirq: Flags mismatch irq 9. 00000088 (pinctrl_amd) vs. 00002080 (acpi)
[ 0.420073] amd_gpio: probe of AMDI0030:00 failed with error -16
```
Cc: Rafael J. Wysocki <rafael@kernel.org>
Reported-by: Christian Heusel <christian@heusel.eu>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218407
Fixes: 7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI")
Link: https://lore.kernel.org/linux-acpi/CAJZ5v0iRqUXeuKmC_+dAJtDBLWQ3x15n4gRH48y7MEaLoXF+UA@mail.gmail.com/T/#mc5506014141b61e472b24e095889535a04458083
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Tested-by: Christian Heusel <christian@heusel.eu>
Link: https://lore.kernel.org/r/20240123180818.3994-1-mario.limonciello@amd.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/pinctrl/pinctrl-amd.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 03ecb3d1aaf6..49f89b70dcec 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
}
ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler,
- IRQF_SHARED, KBUILD_MODNAME, gpio_dev);
+ IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev);
if (ret)
goto out2;
From 2d3b3ab8d0d54e6c20260c8c1a73901a7a58a9cd Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Date: Fri, 19 Jan 2024 17:06:21 +0530
Subject: [PATCH 103/637] dt-bindings: xilinx: replace Piyush Mehta
maintainership
As Piyush is leaving AMD, he handed over ahci-ceva, ZynqMP Mode Pin GPIO
controller, Zynq UltraScale+ MPSoC and Versal reset, Xilinx SuperSpeed
DWC3 USB SoC controller, Microchip USB5744 4-port Hub Controller and
Xilinx udc controller maintainership duties to Mubin and Radhey.
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Acked-by: Mubin Sayyed <mubin.sayyed@amd.com>
Acked-by: Michal Simek <michal.simek@amd.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Piyush Mehta <piyush.mehta@amd.com>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/1705664181-722937-1-git-send-email-radhey.shyam.pandey@amd.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml | 3 ++-
.../devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml | 3 ++-
Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml | 3 ++-
Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml | 3 ++-
Documentation/devicetree/bindings/usb/microchip,usb5744.yaml | 3 ++-
Documentation/devicetree/bindings/usb/xlnx,usb2.yaml | 3 ++-
6 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
index b29ce598f9aa..9952e0ef7767 100644
--- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
+++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Ceva AHCI SATA Controller
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
description: |
The Ceva SATA controller mostly conforms to the AHCI interface with some
diff --git a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
index 56143f1fe84a..501771c672a6 100644
--- a/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
+++ b/Documentation/devicetree/bindings/gpio/xlnx,zynqmp-gpio-modepin.yaml
@@ -12,7 +12,8 @@ description:
PS_MODE). Every pin can be configured as input/output.
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
index 49db66801429..1f1b42dde94d 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Zynq UltraScale+ MPSoC and Versal reset
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
description: |
The Zynq UltraScale+ MPSoC and Versal has several different resets.
diff --git a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
index bb373eb025a5..00f87a558c7d 100644
--- a/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc3-xilinx.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Xilinx SuperSpeed DWC3 USB SoC controller
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
index ff3a1707ef57..dfaf3ddde105 100644
--- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
+++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml
@@ -16,8 +16,9 @@ description:
USB 2.0 traffic.
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
- Michal Simek <michal.simek@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
index 868dffe314bc..a7f75fe36665 100644
--- a/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
+++ b/Documentation/devicetree/bindings/usb/xlnx,usb2.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Xilinx udc controller
maintainers:
- - Piyush Mehta <piyush.mehta@amd.com>
+ - Mubin Sayyed <mubin.sayyed@amd.com>
+ - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
properties:
compatible:
From 4c654ec0ba0f9a04905ebad538689524a8779154 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 22 Jan 2024 14:49:58 -0600
Subject: [PATCH 104/637] dt-bindings: display: nxp,tda998x: Fix 'audio-ports'
constraints
The constraints for 'audio-ports' don't match the description. There can
be 1 or 2 DAI entries and each entry is exactly 2 values. Also, the
values' sizes are 32-bits, not 8-bits. Move the size constraints to the
outer dimension (number of DAIs) and add constraints on inner array
values.
Link: https://lore.kernel.org/r/20240122204959.1665970-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
.../devicetree/bindings/display/bridge/nxp,tda998x.yaml | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
index 21d995f29a1e..b8e9cf6ce4e6 100644
--- a/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/nxp,tda998x.yaml
@@ -29,19 +29,22 @@ properties:
audio-ports:
description:
- Array of 8-bit values, 2 values per DAI (Documentation/sound/soc/dai.rst).
+ Array of 2 values per DAI (Documentation/sound/soc/dai.rst).
The implementation allows one or two DAIs.
If two DAIs are defined, they must be of different type.
$ref: /schemas/types.yaml#/definitions/uint32-matrix
+ minItems: 1
+ maxItems: 2
items:
- minItems: 1
items:
- description: |
The first value defines the DAI type: TDA998x_SPDIF or TDA998x_I2S
(see include/dt-bindings/display/tda998x.h).
+ enum: [ 1, 2 ]
- description:
The second value defines the tda998x AP_ENA reg content when the
DAI in question is used.
+ maximum: 0xff
'#sound-dai-cells':
enum: [ 0, 1 ]
From adf0c363ad2c7ceccb2831a295cd8fc50378269e Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 24 Jan 2024 13:07:14 -0600
Subject: [PATCH 105/637] dt-bindings: tpm: Drop type from "resets"
"resets" is a standard property which already has a type. Users only need
to define how many clocks and what each clock is if more than 1 clock.
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/20240124190714.1553772-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
Documentation/devicetree/bindings/tpm/tpm-common.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/tpm/tpm-common.yaml b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
index 90390624a8be..3c1241b2a43f 100644
--- a/Documentation/devicetree/bindings/tpm/tpm-common.yaml
+++ b/Documentation/devicetree/bindings/tpm/tpm-common.yaml
@@ -42,7 +42,7 @@ properties:
resets:
description: Reset controller to reset the TPM
- $ref: /schemas/types.yaml#/definitions/phandle
+ maxItems: 1
reset-gpios:
description: Output GPIO pin to reset the TPM
From 8f7e917907385e112a845d668ae2832f41e64bf5 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Tue, 23 Jan 2024 16:14:22 +0100
Subject: [PATCH 106/637] of: property: fix typo in io-channels
The property is io-channels and not io-channel. This was effectively
preventing the devlink creation.
Fixes: 8e12257dead7 ("of: property: Add device link support for iommus, mboxes and io-channels")
Cc: stable@vger.kernel.org
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Reviewed-by: Saravana Kannan <saravanak@google.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20240123-iio-backend-v7-1-1bff236b8693@analog.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/property.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 641a40cf5cf3..bbf0dee2fb9c 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1244,7 +1244,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells")
DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells")
DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells")
DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells")
-DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells")
+DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells")
DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL)
DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells")
DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells")
From 6231c9e1a9f35b535c66709aa8a6eda40dbc4132 Mon Sep 17 00:00:00 2001
From: Prasad Pandit <pjp@fedoraproject.org>
Date: Wed, 3 Jan 2024 13:23:43 +0530
Subject: [PATCH 107/637] KVM: x86: make KVM_REQ_NMI request iff NMI pending
for vcpu
kvm_vcpu_ioctl_x86_set_vcpu_events() routine makes 'KVM_REQ_NMI'
request for a vcpu even when its 'events->nmi.pending' is zero.
Ex:
qemu_thread_start
kvm_vcpu_thread_fn
qemu_wait_io_event
qemu_wait_io_event_common
process_queued_cpu_work
do_kvm_cpu_synchronize_post_init/_reset
kvm_arch_put_registers
kvm_put_vcpu_events (cpu, level=[2|3])
This leads vCPU threads in QEMU to constantly acquire & release the
global mutex lock, delaying the guest boot due to lock contention.
Add check to make KVM_REQ_NMI request only if vcpu has NMI pending.
Fixes: bdedff263132 ("KVM: x86: Route pending NMIs from userspace through process_nmi()")
Cc: stable@vger.kernel.org
Signed-off-by: Prasad Pandit <pjp@fedoraproject.org>
Link: https://lore.kernel.org/r/20240103075343.549293-1-ppandit@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/x86.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c080205..25bc52cdf8f4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5454,7 +5454,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
vcpu->arch.nmi_pending = 0;
atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
- kvm_make_request(KVM_REQ_NMI, vcpu);
+ if (events->nmi.pending)
+ kvm_make_request(KVM_REQ_NMI, vcpu);
}
static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);
From 5b778e1c2e9760ffe99482de26e70cd74683ba5c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:35 -0800
Subject: [PATCH 108/637] wifi: fill in MODULE_DESCRIPTION()s for wlcore
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI WLAN wlcore drivers.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-2-leitao@debian.org
---
drivers/net/wireless/ti/wlcore/main.c | 1 +
drivers/net/wireless/ti/wlcore/sdio.c | 1 +
drivers/net/wireless/ti/wlcore/spi.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index fb9ed97774c7..5736acb4d206 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6793,6 +6793,7 @@ MODULE_PARM_DESC(bug_on_recovery, "BUG() on fw recovery");
module_param(no_recovery, int, 0600);
MODULE_PARM_DESC(no_recovery, "Prevent HW recovery. FW will remain stuck.");
+MODULE_DESCRIPTION("TI WLAN core driver");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index f0686635db46..eb5482ed76ae 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -447,6 +447,7 @@ module_sdio_driver(wl1271_sdio_driver);
module_param(dump, bool, 0600);
MODULE_PARM_DESC(dump, "Enable sdio read/write dumps.");
+MODULE_DESCRIPTION("TI WLAN SDIO helpers");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index 7d9a139db59e..0aa2b2f3c5c9 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -562,6 +562,7 @@ static struct spi_driver wl1271_spi_driver = {
};
module_spi_driver(wl1271_spi_driver);
+MODULE_DESCRIPTION("TI WLAN SPI helpers");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
MODULE_AUTHOR("Juuso Oikarinen <juuso.oikarinen@nokia.com>");
From 2f2b503ea770cf817044851a583e8880d1de4ae2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:36 -0800
Subject: [PATCH 109/637] wifi: fill in MODULE_DESCRIPTION()s for wl1251 and
wl12xx
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI wireless drivers wl12xx and wl1251.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-3-leitao@debian.org
---
drivers/net/wireless/ti/wl1251/sdio.c | 1 +
drivers/net/wireless/ti/wl1251/spi.c | 1 +
drivers/net/wireless/ti/wl12xx/main.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index 301bd0043a43..4e5b351f80f0 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -343,5 +343,6 @@ static void __exit wl1251_sdio_exit(void)
module_init(wl1251_sdio_init);
module_exit(wl1251_sdio_exit);
+MODULE_DESCRIPTION("TI WL1251 SDIO helpers");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 29292f06bd3d..1936bb3af54a 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -342,6 +342,7 @@ static struct spi_driver wl1251_spi_driver = {
module_spi_driver(wl1251_spi_driver);
+MODULE_DESCRIPTION("TI WL1251 SPI helpers");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Kalle Valo <kvalo@adurom.com>");
MODULE_ALIAS("spi:wl1251");
diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c
index de045fe4ca1e..b26d42b4e3cc 100644
--- a/drivers/net/wireless/ti/wl12xx/main.c
+++ b/drivers/net/wireless/ti/wl12xx/main.c
@@ -1955,6 +1955,7 @@ module_param_named(tcxo, tcxo_param, charp, 0);
MODULE_PARM_DESC(tcxo,
"TCXO clock: 19.2, 26, 38.4, 52, 16.368, 32.736, 16.8, 33.6");
+MODULE_DESCRIPTION("TI WL12xx wireless driver");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
MODULE_FIRMWARE(WL127X_FW_NAME_SINGLE);
From 257ca10c7317d4a424e48bb95d14ca53a1f1dd6f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:37 -0800
Subject: [PATCH 110/637] wifi: fill in MODULE_DESCRIPTION()s for Broadcom WLAN
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Broadcom FullMac WLAN drivers.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-4-leitao@debian.org
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c | 1 +
drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c | 1 +
drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
index d55f3271d619..4f0c1e1a8e60 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bca/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_bca_exit(void)
brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_BCA, THIS_MODULE);
}
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom AP chipsets");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_IMPORT_NS(BRCMFMAC);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
index f82fbbe3ecef..90d06cda03a2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cyw/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_cyw_exit(void)
brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_CYW, THIS_MODULE);
}
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Cypress/Infineon chipsets");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_IMPORT_NS(BRCMFMAC);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
index 02918d434556..b66135e3cff4 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/wcc/module.c
@@ -20,6 +20,7 @@ static void __exit brcmf_wcc_exit(void)
brcmf_fwvid_unregister_vendor(BRCMF_FWVENDOR_WCC, THIS_MODULE);
}
+MODULE_DESCRIPTION("Broadcom FullMAC WLAN driver plugin for Broadcom mobility chipsets");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_IMPORT_NS(BRCMFMAC);
From f8782ea450ad83df5f3dfdb1fca093f46238febe Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:38 -0800
Subject: [PATCH 111/637] wifi: fill in MODULE_DESCRIPTION()s for ar5523
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Atheros AR5523 wireless driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-5-leitao@debian.org
---
drivers/net/wireless/ath/ar5523/ar5523.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 43e0db78d42b..a742cec44e3d 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1803,5 +1803,6 @@ static struct usb_driver ar5523_driver = {
module_usb_driver(ar5523_driver);
+MODULE_DESCRIPTION("Atheros AR5523 wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_FIRMWARE(AR5523_FIRMWARE_FILE);
From e063d2a05d713d396044124867704b08e5c30860 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:39 -0800
Subject: [PATCH 112/637] wifi: fill in MODULE_DESCRIPTION()s for wcn36xx
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Qualcomm Atheros WCN3660/3680 wireless driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-6-leitao@debian.org
---
drivers/net/wireless/ath/wcn36xx/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 41119fb177e3..4e6b4df8562f 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1685,6 +1685,7 @@ static struct platform_driver wcn36xx_driver = {
module_platform_driver(wcn36xx_driver);
+MODULE_DESCRIPTION("Qualcomm Atheros WCN3660/3680 wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Eugene Krasnikov k.eugene.e@gmail.com");
MODULE_FIRMWARE(WLAN_NV_FILE);
From 714ea2f109d9d561789078fd8a1beeffa9af36d6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:40 -0800
Subject: [PATCH 113/637] wifi: fill in MODULE_DESCRIPTION()s for p54spi
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Prism54 SPI wireless driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-7-leitao@debian.org
---
drivers/net/wireless/intersil/p54/p54spi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/intersil/p54/p54spi.c b/drivers/net/wireless/intersil/p54/p54spi.c
index ce0179b8ab36..0073b5e0f9c9 100644
--- a/drivers/net/wireless/intersil/p54/p54spi.c
+++ b/drivers/net/wireless/intersil/p54/p54spi.c
@@ -700,6 +700,7 @@ static struct spi_driver p54spi_driver = {
module_spi_driver(p54spi_driver);
+MODULE_DESCRIPTION("Prism54 SPI wireless driver");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Christian Lamparter <chunkeey@web.de>");
MODULE_ALIAS("spi:cx3110x");
From 35337ac472605da9db051827fa2d39e6c02c6d81 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:41 -0800
Subject: [PATCH 114/637] wifi: fill in MODULE_DESCRIPTION()s for wl18xx
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the TI WiLink 8 wireless driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-8-leitao@debian.org
---
drivers/net/wireless/ti/wl18xx/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/ti/wl18xx/main.c b/drivers/net/wireless/ti/wl18xx/main.c
index 20d9181b3410..2ccac1cdec01 100644
--- a/drivers/net/wireless/ti/wl18xx/main.c
+++ b/drivers/net/wireless/ti/wl18xx/main.c
@@ -2086,6 +2086,7 @@ module_param_named(num_rx_desc, num_rx_desc_param, int, 0400);
MODULE_PARM_DESC(num_rx_desc_param,
"Number of Rx descriptors: u8 (default is 32)");
+MODULE_DESCRIPTION("TI WiLink 8 wireless driver");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Luciano Coelho <coelho@ti.com>");
MODULE_FIRMWARE(WL18XX_FW_NAME);
From c9013880284d78bac6498d9c0b0b7043cf0f5639 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:42 -0800
Subject: [PATCH 115/637] wifi: fill in MODULE_DESCRIPTION()s for wilc1000
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Atmel WILC1000 SPI driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-9-leitao@debian.org
---
drivers/net/wireless/microchip/wilc1000/netdev.c | 1 +
drivers/net/wireless/microchip/wilc1000/sdio.c | 1 +
drivers/net/wireless/microchip/wilc1000/spi.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c
index 91d71e0f7ef2..81e8f25863f5 100644
--- a/drivers/net/wireless/microchip/wilc1000/netdev.c
+++ b/drivers/net/wireless/microchip/wilc1000/netdev.c
@@ -1018,5 +1018,6 @@ unregister_netdev:
return ERR_PTR(ret);
}
+MODULE_DESCRIPTION("Atmel WILC1000 core wireless driver");
MODULE_LICENSE("GPL");
MODULE_FIRMWARE(WILC1000_FW(WILC1000_API_VER));
diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 0d13e3e46e98..d6d394693090 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -984,4 +984,5 @@ static struct sdio_driver wilc_sdio_driver = {
module_driver(wilc_sdio_driver,
sdio_register_driver,
sdio_unregister_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SDIO wireless driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 77b4cdff73c3..1d8b241ce43c 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -273,6 +273,7 @@ static struct spi_driver wilc_spi_driver = {
.remove = wilc_bus_remove,
};
module_spi_driver(wilc_spi_driver);
+MODULE_DESCRIPTION("Atmel WILC1000 SPI wireless driver");
MODULE_LICENSE("GPL");
static int wilc_spi_tx(struct wilc *wilc, u8 *b, u32 len)
From f3f8f050316893fe2da523458ff7f5f6d61fb1a6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 30 Jan 2024 02:42:43 -0800
Subject: [PATCH 116/637] wifi: fill in MODULE_DESCRIPTION()s for mt76 drivers
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the MediaTek mt76 drivers.
Here is a sorted list of descriptions. It might make the reviewing
process easier.
MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
MODULE_DESCRIPTION("MediaTek MT76x helpers");
MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
MODULE_DESCRIPTION("MediaTek MT7921 core driver");
MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
MODULE_DESCRIPTION("MediaTek MT7925 core driver");
MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
MODULE_DESCRIPTION("MediaTek MT792x core driver");
MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240130104243.3025393-10-leitao@debian.org
---
drivers/net/wireless/mediatek/mt76/mt7603/main.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7615/main.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7615/mmio.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7615/sdio.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7615/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x0/pci.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x0/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x2/pci.c | 1 +
drivers/net/wireless/mediatek/mt76/mt76x2/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7915/mmio.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7921/main.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7921/pci.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7921/sdio.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7921/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7925/main.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7925/pci.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7925/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt792x_core.c | 1 +
drivers/net/wireless/mediatek/mt76/mt792x_usb.c | 1 +
drivers/net/wireless/mediatek/mt76/mt7996/mmio.c | 1 +
drivers/net/wireless/mediatek/mt76/sdio.c | 1 +
drivers/net/wireless/mediatek/mt76/usb.c | 1 +
drivers/net/wireless/mediatek/mt76/util.c | 1 +
29 files changed, 29 insertions(+)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 89d738deea62..e2146d30e553 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -728,6 +728,7 @@ const struct ieee80211_ops mt7603_ops = {
.set_sar_specs = mt7603_set_sar_specs,
};
+MODULE_DESCRIPTION("MediaTek MT7603E and MT76x8 wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
static int __init mt7603_init(void)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index dab16b5fc386..0971c164b57e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -1375,4 +1375,5 @@ const struct ieee80211_ops mt7615_ops = {
};
EXPORT_SYMBOL_GPL(mt7615_ops);
+MODULE_DESCRIPTION("MediaTek MT7615E and MT7663E wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index ac036a072439..87a956ea3ad7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -270,4 +270,5 @@ static void __exit mt7615_exit(void)
module_init(mt7615_init);
module_exit(mt7615_exit);
+MODULE_DESCRIPTION("MediaTek MT7615E MMIO helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index 67cedd2555f9..9692890ba51b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -253,4 +253,5 @@ module_sdio_driver(mt7663s_driver);
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663S (SDIO) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 04963b9f7498..df737e1ff27b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -281,4 +281,5 @@ module_usb_driver(mt7663u_driver);
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7663U (USB) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index 0052d103e276..820b39590027 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -349,4 +349,5 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_register_device);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7663 SDIO/USB helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 96494ba2fdf7..3a20ba0d2492 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -3160,4 +3160,5 @@ exit:
EXPORT_SYMBOL_GPL(mt76_connac2_mcu_fill_message);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x connac layer helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index c3a392a1a659..bcd24c9072ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -342,4 +342,5 @@ int mt76x0_eeprom_init(struct mt76x02_dev *dev)
return 0;
}
+MODULE_DESCRIPTION("MediaTek MT76x EEPROM helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 9277ff38b7a2..293e66fa83d5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -302,6 +302,7 @@ static const struct pci_device_id mt76x0e_device_table[] = {
MODULE_DEVICE_TABLE(pci, mt76x0e_device_table);
MODULE_FIRMWARE(MT7610E_FIRMWARE);
MODULE_FIRMWARE(MT7650E_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0E (PCIe) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
static struct pci_driver mt76x0e_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 0422c332354a..dd042949cf82 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -336,6 +336,7 @@ err:
MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
MODULE_FIRMWARE(MT7610E_FIRMWARE);
MODULE_FIRMWARE(MT7610U_FIRMWARE);
+MODULE_DESCRIPTION("MediaTek MT76x0U (USB) wireless driver");
MODULE_LICENSE("GPL");
static struct usb_driver mt76x0_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
index 02da543dfc5c..b2cc44914294 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_mcu.c
@@ -293,4 +293,5 @@ void mt76x02u_init_mcu(struct mt76_dev *dev)
EXPORT_SYMBOL_GPL(mt76x02u_init_mcu);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x02 MCU helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index 8a0e8124b894..8020446be37b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -696,4 +696,5 @@ void mt76x02_config_mac_addr_list(struct mt76x02_dev *dev)
}
EXPORT_SYMBOL_GPL(mt76x02_config_mac_addr_list);
+MODULE_DESCRIPTION("MediaTek MT76x02 helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
index 8c01855885ce..1fe5f5a02f93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/eeprom.c
@@ -506,4 +506,5 @@ int mt76x2_eeprom_init(struct mt76x02_dev *dev)
}
EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
+MODULE_DESCRIPTION("MediaTek MT76x2 EEPROM helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index df85ebc6e1df..30959746e924 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -165,6 +165,7 @@ mt76x2e_resume(struct pci_dev *pdev)
MODULE_DEVICE_TABLE(pci, mt76x2e_device_table);
MODULE_FIRMWARE(MT7662_FIRMWARE);
MODULE_FIRMWARE(MT7662_ROM_PATCH);
+MODULE_DESCRIPTION("MediaTek MT76x2E (PCIe) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
static struct pci_driver mt76pci_driver = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 55068f3252ef..ca78e14251c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -147,4 +147,5 @@ static struct usb_driver mt76x2u_driver = {
module_usb_driver(mt76x2u_driver);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x2U (USB) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index aff4f21e843d..3039f53e2245 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -958,4 +958,5 @@ static void __exit mt7915_exit(void)
module_init(mt7915_init);
module_exit(mt7915_exit);
+MODULE_DESCRIPTION("MediaTek MT7915E MMIO helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 0645417e0582..0d5adc5ddae3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1418,5 +1418,6 @@ const struct ieee80211_ops mt7921_ops = {
};
EXPORT_SYMBOL_GPL(mt7921_ops);
+MODULE_DESCRIPTION("MediaTek MT7921 core driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index 57903c6e4f11..dde26f327478 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -544,4 +544,5 @@ MODULE_FIRMWARE(MT7922_FIRMWARE_WM);
MODULE_FIRMWARE(MT7922_ROM_PATCH);
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7921E (PCIe) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 7591e54d2897..a9ce1e746b95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -323,5 +323,6 @@ static struct sdio_driver mt7921s_driver = {
.drv.pm = pm_sleep_ptr(&mt7921s_pm_ops),
};
module_sdio_driver(mt7921s_driver);
+MODULE_DESCRIPTION("MediaTek MT7921S (SDIO) wireless driver");
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index e5258c74fc07..8b7c03c47598 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -336,5 +336,6 @@ static struct usb_driver mt7921u_driver = {
};
module_usb_driver(mt7921u_driver);
+MODULE_DESCRIPTION("MediaTek MT7921U (USB) wireless driver");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 8f1075da4903..125a1be3cb64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1450,4 +1450,5 @@ const struct ieee80211_ops mt7925_ops = {
EXPORT_SYMBOL_GPL(mt7925_ops);
MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek MT7925 core driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 734f31ee40d3..1fd99a856541 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -583,4 +583,5 @@ MODULE_FIRMWARE(MT7925_FIRMWARE_WM);
MODULE_FIRMWARE(MT7925_ROM_PATCH);
MODULE_AUTHOR("Deren Wu <deren.wu@mediatek.com>");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925E (PCIe) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
index 9b885c5b3ed5..1e0f094fc905 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
@@ -329,4 +329,5 @@ static struct usb_driver mt7925u_driver = {
module_usb_driver(mt7925u_driver);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT7925U (USB) wireless driver");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 502be22dbe36..c42101aa9e45 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -862,5 +862,6 @@ int mt792x_load_firmware(struct mt792x_dev *dev)
}
EXPORT_SYMBOL_GPL(mt792x_load_firmware);
+MODULE_DESCRIPTION("MediaTek MT792x core driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
index 2dd283caed36..589a3efb9f8c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c
@@ -314,5 +314,6 @@ void mt792xu_disconnect(struct usb_interface *usb_intf)
}
EXPORT_SYMBOL_GPL(mt792xu_disconnect);
+MODULE_DESCRIPTION("MediaTek MT792x USB helpers");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index c50d89a445e9..9f2abfa273c9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -650,4 +650,5 @@ static void __exit mt7996_exit(void)
module_init(mt7996_init);
module_exit(mt7996_exit);
+MODULE_DESCRIPTION("MediaTek MT7996 MMIO helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index c52d550f0c32..3e88798df017 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -672,4 +672,5 @@ EXPORT_SYMBOL_GPL(mt76s_init);
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("MediaTek MT76x SDIO helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index 1584665fe3cb..5a0bcb5071bd 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -1128,4 +1128,5 @@ int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf)
EXPORT_SYMBOL_GPL(mt76u_init);
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_DESCRIPTION("MediaTek MT76x USB helpers");
MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index fc76c66ff1a5..d6c01a2dd198 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -138,4 +138,5 @@ int __mt76_worker_fn(void *ptr)
}
EXPORT_SYMBOL_GPL(__mt76_worker_fn);
+MODULE_DESCRIPTION("MediaTek MT76x helpers");
MODULE_LICENSE("Dual BSD/GPL");
From d9807d60c145836043ffa602328ea1d66dc458b1 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Wed, 17 Jan 2024 22:03:33 +0800
Subject: [PATCH 117/637] riscv: mm: execute local TLB flush after populating
vmemmap
The spare_init() calls memmap_populate() many times to create VA to PA
mapping for the VMEMMAP area, where all "struct page" are located once
CONFIG_SPARSEMEM_VMEMMAP is defined. These "struct page" are later
initialized in the zone_sizes_init() function. However, during this
process, no sfence.vma instruction is executed for this VMEMMAP area.
This omission may cause the hart to fail to perform page table walk
because some data related to the address translation is invisible to the
hart. To solve this issue, the local_flush_tlb_kernel_range() is called
right after the sparse_init() to execute a sfence.vma instruction for this
VMEMMAP area, ensuring that all data related to the address translation
is visible to the hart.
Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem")
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117140333.2479667-1-vincent.chen@sifive.com
Fixes: 7a92fc8b4d20 ("mm: Introduce flush_cache_vmap_early()")
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/tlbflush.h | 1 +
arch/riscv/mm/init.c | 4 ++++
arch/riscv/mm/tlbflush.c | 3 ++-
3 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 928f096dca21..4112cc8d1d69 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -75,6 +75,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
#define flush_tlb_mm(mm) flush_tlb_all()
#define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
#endif /* !CONFIG_SMP || !CONFIG_MMU */
#endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 32cad6a65ccd..fa34cf55037b 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1385,6 +1385,10 @@ void __init misc_mem_init(void)
early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
arch_numa_init();
sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+ /* The entire VMEMMAP region has been populated. Flush TLB for this region */
+ local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
zone_sizes_init();
arch_reserve_crashkernel();
memblock_dump_all();
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 8d12b26f5ac3..dffb0e5bd942 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,9 +66,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
local_flush_tlb_range_threshold_asid(start, size, stride, asid);
}
+/* Flush a range of kernel pages without broadcasting */
void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+ local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
}
static void __ipi_flush_tlb_all(void *info)
From 9e05d9b06757732477cca428e87f3d72163d01cf Mon Sep 17 00:00:00 2001
From: Tengfei Yu <moehanabichan@gmail.com>
Date: Thu, 25 Jan 2024 13:08:23 +0800
Subject: [PATCH 118/637] KVM: x86: Check irqchip mode before create PIT
As the kvm api(https://docs.kernel.org/virt/kvm/api.html) reads,
KVM_CREATE_PIT2 call is only valid after enabling in-kernel irqchip
support via KVM_CREATE_IRQCHIP.
Without this check, I can create PIT first and enable irqchip-split
then, which may cause the PIT invalid because of lacking of in-kernel
PIC to inject the interrupt.
Signed-off-by: Tengfei Yu <moehanabichan@gmail.com>
Message-Id: <20240125050823.4893-1-moehanabichan@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/x86.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c080205..9a89471a613c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7016,6 +7016,9 @@ set_identity_unlock:
r = -EEXIST;
if (kvm->arch.vpit)
goto create_pit_unlock;
+ r = -ENOENT;
+ if (!pic_in_kernel(kvm))
+ goto create_pit_unlock;
r = -ENOMEM;
kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
if (kvm->arch.vpit)
From d52734d00b8e86604a66b4cdfa9e8bb541daca2d Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Date: Wed, 24 Jan 2024 21:18:21 +0100
Subject: [PATCH 119/637] KVM: x86: Give a hint when Win2016 might fail to boot
due to XSAVES erratum
Since commit b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17")
kernel unconditionally clears the XSAVES CPU feature bit on Zen1/2 CPUs.
Because KVM CPU caps are initialized from the kernel boot CPU features this
makes the XSAVES feature also unavailable for KVM guests in this case.
At the same time the XSAVEC feature is left enabled.
Unfortunately, having XSAVEC but no XSAVES in CPUID breaks Hyper-V enabled
Windows Server 2016 VMs that have more than one vCPU.
Let's at least give users hint in the kernel log what could be wrong since
these VMs currently simply hang at boot with a black screen - giving no
clue what suddenly broke them and how to make them work again.
Trigger the kernel message hint based on the particular guest ID written to
the Guest OS Identity Hyper-V MSR implemented by KVM.
Defer this check to when the L1 Hyper-V hypervisor enables SVM in EFER
since we want to limit this message to Hyper-V enabled Windows guests only
(Windows session running nested as L2) but the actual Guest OS Identity MSR
write is done by L1 and happens before it enables SVM.
Fixes: b0563468eeac ("x86/CPU/AMD: Disable XSAVES on AMD family 0x17")
Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-Id: <b83ab45c5e239e5d148b0ae7750133a67ac9575c.1706127425.git.maciej.szmigiero@oracle.com>
[Move some checks before mutex_lock(), rename function. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/kvm/hyperv.c | 50 +++++++++++++++++++++++++++++++++
arch/x86/kvm/hyperv.h | 3 ++
arch/x86/kvm/x86.c | 4 +++
4 files changed, 59 insertions(+)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b5b2d0fde579..d271ba20a0b2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1145,6 +1145,8 @@ struct kvm_hv {
unsigned int synic_auto_eoi_used;
struct kvm_hv_syndbg hv_syndbg;
+
+ bool xsaves_xsavec_checked;
};
#endif
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4943f6b2bbee..8a47f8541eab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr)
return false;
}
+#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839
+#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */
+
+/*
+ * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC
+ * configuration.
+ * Such configuration can result from, for example, AMD Erratum 1386 workaround.
+ *
+ * Print a notice so users aren't left wondering what's suddenly gone wrong.
+ */
+static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+
+ /* Check again under the hv_lock. */
+ if (hv->xsaves_xsavec_checked)
+ return;
+
+ if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) !=
+ KVM_HV_WIN2016_GUEST_ID)
+ return;
+
+ hv->xsaves_xsavec_checked = true;
+
+ /* UP configurations aren't affected */
+ if (atomic_read(&kvm->online_vcpus) < 2)
+ return;
+
+ if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) ||
+ !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC))
+ return;
+
+ pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. "
+ "If it fails to boot try disabling XSAVEC in the VM config.\n");
+}
+
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
+
+ if (!vcpu->arch.hyperv_enabled ||
+ hv->xsaves_xsavec_checked)
+ return;
+
+ mutex_lock(&hv->hv_lock);
+ __kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+ mutex_unlock(&hv->hv_lock);
+}
+
static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
bool host)
{
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 1dc0b6604526..923e64903da9 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -182,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock);
void kvm_hv_request_tsc_page_update(struct kvm *kvm);
+void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu);
+
void kvm_hv_init_vm(struct kvm *kvm);
void kvm_hv_destroy_vm(struct kvm *kvm);
int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
@@ -267,6 +269,7 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
static inline void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock) {}
static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {}
+static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {}
static inline void kvm_hv_init_vm(struct kvm *kvm) {}
static inline void kvm_hv_destroy_vm(struct kvm *kvm) {}
static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a89471a613c..bf10a9073a09 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1782,6 +1782,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS)
kvm_mmu_reset_context(vcpu);
+ if (!static_cpu_has(X86_FEATURE_XSAVES) &&
+ (efer & EFER_SVME))
+ kvm_hv_xsaves_xsavec_maybe_warn(vcpu);
+
return 0;
}
From a9ef277488cfc1b7da88235dc11c338a14f34835 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 24 Jan 2024 15:03:17 +0200
Subject: [PATCH 120/637] x86/kvm: Fix SEV check in sev_map_percpu_data()
The function sev_map_percpu_data() checks if it is running on an SEV
platform by checking the CC_ATTR_GUEST_MEM_ENCRYPT attribute. However,
this attribute is also defined for TDX.
To avoid false positives, add a cc_vendor check.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: 4d96f9109109 ("x86/sev: Replace occurrences of sev_active() with cc_platform_has()")
Suggested-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: David Rientjes <rientjes@google.com>
Message-Id: <20240124130317.495519-1-kirill.shutemov@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kernel/kvm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index dfe9945b9bec..428ee74002e1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void)
{
int cpu;
- if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ if (cc_vendor != CC_VENDOR_AMD ||
+ !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
for_each_possible_cpu(cpu) {
From 607aad1e4356c210dbef9022955a3089377909b2 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Mon, 29 Jan 2024 20:25:56 +0100
Subject: [PATCH 121/637] of: unittest: Fix compile in the non-dynamic case
If CONFIG_OF_KOBJ is not set, a device_node does not contain a
kobj and attempts to access the embedded kobj via kref_read break
the compile.
Replace affected kref_read calls with a macro that reads the
refcount if it exists and returns 1 if there is no embedded kobj.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401291740.VP219WIz-lkp@intel.com/
Fixes: 4dde83569832 ("of: Fix double free in of_parse_phandle_with_args_map")
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Link: https://lore.kernel.org/r/20240129192556.403271-1-lk@c--e.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/unittest.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index cfd60e35a899..d7593bde2d02 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -50,6 +50,12 @@ static struct unittest_results {
failed; \
})
+#ifdef CONFIG_OF_KOBJ
+#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref)
+#else
+#define OF_KREF_READ(NODE) 1
+#endif
+
/*
* Expected message may have a message level other than KERN_INFO.
* Print the expected message only if the current loglevel will allow
@@ -570,7 +576,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
pr_err("missing testcase data\n");
return;
}
- prefs[i] = kref_read(&p[i]->kobj.kref);
+ prefs[i] = OF_KREF_READ(p[i]);
}
rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells");
@@ -693,9 +699,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void)
unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
for (i = 0; i < ARRAY_SIZE(p); ++i) {
- unittest(prefs[i] == kref_read(&p[i]->kobj.kref),
+ unittest(prefs[i] == OF_KREF_READ(p[i]),
"provider%d: expected:%d got:%d\n",
- i, prefs[i], kref_read(&p[i]->kobj.kref));
+ i, prefs[i], OF_KREF_READ(p[i]));
of_node_put(p[i]);
}
}
From a107d643b2a3382e0a2d2c4ef08bf8c6bff4561d Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Mon, 18 Dec 2023 08:54:00 +0100
Subject: [PATCH 122/637] media: Revert "media: rkisp1: Drop IRQF_SHARED"
This reverts commit 85d2a31fe4d9be1555f621ead7a520d8791e0f74.
The rkisp1 does share interrupt lines on some platforms, after all. Thus
we need to revert this, and implement a fix for the rkisp1 shared irq
handling in a follow-up patch.
Closes: https://lore.kernel.org/all/87o7eo8vym.fsf@gmail.com/
Link: https://lore.kernel.org/r/20231218-rkisp-shirq-fix-v1-1-173007628248@ideasonboard.com
Reported-by: Mikhail Rudenko <mike.rudenko@gmail.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
index f96f821a7b50..acc559652d6e 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
@@ -559,7 +559,7 @@ static int rkisp1_probe(struct platform_device *pdev)
rkisp1->irqs[il] = irq;
}
- ret = devm_request_irq(dev, irq, info->isrs[i].isr, 0,
+ ret = devm_request_irq(dev, irq, info->isrs[i].isr, IRQF_SHARED,
dev_driver_string(dev), dev);
if (ret) {
dev_err(dev, "request irq failed: %d\n", ret);
From ffb635bb398fc07cb38f8a7b4a82cbe5f412f08e Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Mon, 18 Dec 2023 08:54:01 +0100
Subject: [PATCH 123/637] media: rkisp1: Fix IRQ handling due to shared
interrupts
The driver requests the interrupts as IRQF_SHARED, so the interrupt
handlers can be called at any time. If such a call happens while the ISP
is powered down, the SoC will hang as the driver tries to access the
ISP registers.
This can be reproduced even without the platform sharing the IRQ line:
Enable CONFIG_DEBUG_SHIRQ and unload the driver, and the board will
hang.
Fix this by adding a new field, 'irqs_enabled', which is used to bail
out from the interrupt handler when the ISP is not operational.
Link: https://lore.kernel.org/r/20231218-rkisp-shirq-fix-v1-2-173007628248@ideasonboard.com
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
.../platform/rockchip/rkisp1/rkisp1-capture.c | 3 +++
.../platform/rockchip/rkisp1/rkisp1-common.h | 2 ++
.../platform/rockchip/rkisp1/rkisp1-csi.c | 3 +++
.../platform/rockchip/rkisp1/rkisp1-dev.c | 22 +++++++++++++++++++
.../platform/rockchip/rkisp1/rkisp1-isp.c | 3 +++
5 files changed, 33 insertions(+)
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
index aebd3c12020b..c381c22135a2 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
@@ -725,6 +725,9 @@ irqreturn_t rkisp1_capture_isr(int irq, void *ctx)
unsigned int i;
u32 status;
+ if (!rkisp1->irqs_enabled)
+ return IRQ_NONE;
+
status = rkisp1_read(rkisp1, RKISP1_CIF_MI_MIS);
if (!status)
return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
index 4b6b28c05b89..b757f75edecf 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-common.h
@@ -450,6 +450,7 @@ struct rkisp1_debug {
* @debug: debug params to be exposed on debugfs
* @info: version-specific ISP information
* @irqs: IRQ line numbers
+ * @irqs_enabled: the hardware is enabled and can cause interrupts
*/
struct rkisp1_device {
void __iomem *base_addr;
@@ -471,6 +472,7 @@ struct rkisp1_device {
struct rkisp1_debug debug;
const struct rkisp1_info *info;
int irqs[RKISP1_NUM_IRQS];
+ bool irqs_enabled;
};
/*
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
index b6e47e2f1b94..4202642e0523 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
@@ -196,6 +196,9 @@ irqreturn_t rkisp1_csi_isr(int irq, void *ctx)
struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
u32 val, status;
+ if (!rkisp1->irqs_enabled)
+ return IRQ_NONE;
+
status = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_MIS);
if (!status)
return IRQ_NONE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
index acc559652d6e..73cf08a74011 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-dev.c
@@ -305,6 +305,24 @@ static int __maybe_unused rkisp1_runtime_suspend(struct device *dev)
{
struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
+ rkisp1->irqs_enabled = false;
+ /* Make sure the IRQ handler will see the above */
+ mb();
+
+ /*
+ * Wait until any running IRQ handler has returned. The IRQ handler
+ * may get called even after this (as it's a shared interrupt line)
+ * but the 'irqs_enabled' flag will make the handler return immediately.
+ */
+ for (unsigned int il = 0; il < ARRAY_SIZE(rkisp1->irqs); ++il) {
+ if (rkisp1->irqs[il] == -1)
+ continue;
+
+ /* Skip if the irq line is the same as previous */
+ if (il == 0 || rkisp1->irqs[il - 1] != rkisp1->irqs[il])
+ synchronize_irq(rkisp1->irqs[il]);
+ }
+
clk_bulk_disable_unprepare(rkisp1->clk_size, rkisp1->clks);
return pinctrl_pm_select_sleep_state(dev);
}
@@ -321,6 +339,10 @@ static int __maybe_unused rkisp1_runtime_resume(struct device *dev)
if (ret)
return ret;
+ rkisp1->irqs_enabled = true;
+ /* Make sure the IRQ handler will see the above */
+ mb();
+
return 0;
}
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
index f00873d31c42..78a1f7a1499b 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
@@ -976,6 +976,9 @@ irqreturn_t rkisp1_isp_isr(int irq, void *ctx)
struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
u32 status, isp_err;
+ if (!rkisp1->irqs_enabled)
+ return IRQ_NONE;
+
status = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS);
if (!status)
return IRQ_NONE;
From aa125f229076a8230a171d519dbdb2a862145d33 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 28 Jan 2024 10:23:09 +0200
Subject: [PATCH 124/637] wifi: iwlwifi: remove extra kernel-doc
This no longer exists, remove the kernel-doc.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240128102209.d2192d79bc09.Id9551728d618248dd471382a5283503a8976237a@changeid
---
drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index e27774e7ed74..80fda056e46a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2015-2017 Intel Deutschland GmbH
*/
@@ -19,7 +19,6 @@
* @fwrt_ptr: pointer to the buffer coming from fwrt
* @trans_ptr: pointer to struct %iwl_trans_dump_data which contains the
* transport's data.
- * @trans_len: length of the valid data in trans_ptr
* @fwrt_len: length of the valid data in fwrt_ptr
*/
struct iwl_fw_dump_ptrs {
From f66556c1333b3bd4806fc98ee07c419ab545e6ee Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Dec 2023 22:43:25 +0100
Subject: [PATCH 125/637] media: atomisp: Adjust for v4l2_subdev_state handling
changes in 6.8
The atomisp driver emulates a standard v4l2 device, which also works
for non media-controller aware applications.
Part of this requires making try_fmt calls on the sensor when
a normal v4l2 app is making try_fmt calls on the /dev/video# mode.
With the recent v4l2_subdev_state handling changes in 6.8 this no longer
works, fixing this requires 2 changes:
1. The atomisp code was using its own internal v4l2_subdev_pad_config
for this. Replace the internal v4l2_subdev_pad_config with allocating
a full v4l2_subdev_state for storing the full try_fmt state.
2. The paths actually setting the fmt or crop selection now need to be
passed the v4l2_subdev's active state, so that sensor drivers which
are using the v4l2_subdev's active state to store their state keep
working.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
.../staging/media/atomisp/pci/atomisp_cmd.c | 58 ++++++++++--------
.../media/atomisp/pci/atomisp_internal.h | 4 +-
.../staging/media/atomisp/pci/atomisp_ioctl.c | 52 +++++++++-------
.../staging/media/atomisp/pci/atomisp_v4l2.c | 59 ++++++++++++++-----
4 files changed, 111 insertions(+), 62 deletions(-)
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index f44e6412f4e3..d0db2efe0045 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -3723,12 +3723,10 @@ apply_min_padding:
static int atomisp_set_crop(struct atomisp_device *isp,
const struct v4l2_mbus_framefmt *format,
+ struct v4l2_subdev_state *sd_state,
int which)
{
struct atomisp_input_subdev *input = &isp->inputs[isp->asd.input_curr];
- struct v4l2_subdev_state pad_state = {
- .pads = &input->pad_cfg,
- };
struct v4l2_subdev_selection sel = {
.which = which,
.target = V4L2_SEL_TGT_CROP,
@@ -3754,7 +3752,7 @@ static int atomisp_set_crop(struct atomisp_device *isp,
sel.r.left = ((input->native_rect.width - sel.r.width) / 2) & ~1;
sel.r.top = ((input->native_rect.height - sel.r.height) / 2) & ~1;
- ret = v4l2_subdev_call(input->camera, pad, set_selection, &pad_state, &sel);
+ ret = v4l2_subdev_call(input->camera, pad, set_selection, sd_state, &sel);
if (ret)
dev_err(isp->dev, "Error setting crop to %ux%u @%ux%u: %d\n",
sel.r.width, sel.r.height, sel.r.left, sel.r.top, ret);
@@ -3770,9 +3768,6 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
const struct atomisp_format_bridge *fmt, *snr_fmt;
struct atomisp_sub_device *asd = &isp->asd;
struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
- struct v4l2_subdev_state pad_state = {
- .pads = &input->pad_cfg,
- };
struct v4l2_subdev_format format = {
.which = V4L2_SUBDEV_FORMAT_TRY,
};
@@ -3809,11 +3804,16 @@ int atomisp_try_fmt(struct atomisp_device *isp, struct v4l2_pix_format *f,
dev_dbg(isp->dev, "try_mbus_fmt: asking for %ux%u\n",
format.format.width, format.format.height);
- ret = atomisp_set_crop(isp, &format.format, V4L2_SUBDEV_FORMAT_TRY);
- if (ret)
- return ret;
+ v4l2_subdev_lock_state(input->try_sd_state);
+
+ ret = atomisp_set_crop(isp, &format.format, input->try_sd_state,
+ V4L2_SUBDEV_FORMAT_TRY);
+ if (ret == 0)
+ ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+ input->try_sd_state, &format);
+
+ v4l2_subdev_unlock_state(input->try_sd_state);
- ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &format);
if (ret)
return ret;
@@ -4238,9 +4238,7 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
struct atomisp_device *isp = asd->isp;
struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
const struct atomisp_format_bridge *format;
- struct v4l2_subdev_state pad_state = {
- .pads = &input->pad_cfg,
- };
+ struct v4l2_subdev_state *act_sd_state;
struct v4l2_subdev_format vformat = {
.which = V4L2_SUBDEV_FORMAT_TRY,
};
@@ -4268,12 +4266,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
/* Disable dvs if resolution can't be supported by sensor */
if (asd->params.video_dis_en && asd->run_mode->val == ATOMISP_RUN_MODE_VIDEO) {
- ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_TRY);
- if (ret)
- return ret;
+ v4l2_subdev_lock_state(input->try_sd_state);
+
+ ret = atomisp_set_crop(isp, &vformat.format, input->try_sd_state,
+ V4L2_SUBDEV_FORMAT_TRY);
+ if (ret == 0) {
+ vformat.which = V4L2_SUBDEV_FORMAT_TRY;
+ ret = v4l2_subdev_call(input->camera, pad, set_fmt,
+ input->try_sd_state, &vformat);
+ }
+
+ v4l2_subdev_unlock_state(input->try_sd_state);
- vformat.which = V4L2_SUBDEV_FORMAT_TRY;
- ret = v4l2_subdev_call(input->camera, pad, set_fmt, &pad_state, &vformat);
if (ret)
return ret;
@@ -4291,12 +4295,18 @@ static int atomisp_set_fmt_to_snr(struct video_device *vdev, const struct v4l2_p
}
}
- ret = atomisp_set_crop(isp, &vformat.format, V4L2_SUBDEV_FORMAT_ACTIVE);
- if (ret)
- return ret;
+ act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
+ ret = atomisp_set_crop(isp, &vformat.format, act_sd_state,
+ V4L2_SUBDEV_FORMAT_ACTIVE);
+ if (ret == 0) {
+ vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+ ret = v4l2_subdev_call(input->camera, pad, set_fmt, act_sd_state, &vformat);
+ }
+
+ if (act_sd_state)
+ v4l2_subdev_unlock_state(act_sd_state);
- vformat.which = V4L2_SUBDEV_FORMAT_ACTIVE;
- ret = v4l2_subdev_call(input->camera, pad, set_fmt, NULL, &vformat);
if (ret)
return ret;
diff --git a/drivers/staging/media/atomisp/pci/atomisp_internal.h b/drivers/staging/media/atomisp/pci/atomisp_internal.h
index f7b4bee9574b..d5b077e602ca 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_internal.h
+++ b/drivers/staging/media/atomisp/pci/atomisp_internal.h
@@ -132,8 +132,8 @@ struct atomisp_input_subdev {
/* Sensor rects for sensors which support crop */
struct v4l2_rect native_rect;
struct v4l2_rect active_rect;
- /* Sensor pad_cfg for which == V4L2_SUBDEV_FORMAT_TRY calls */
- struct v4l2_subdev_pad_config pad_cfg;
+ /* Sensor state for which == V4L2_SUBDEV_FORMAT_TRY calls */
+ struct v4l2_subdev_state *try_sd_state;
struct v4l2_subdev *motor;
diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
index 01b7fa9b56a2..5b2d88c02d36 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
@@ -781,12 +781,20 @@ static int atomisp_enum_framesizes(struct file *file, void *priv,
.which = V4L2_SUBDEV_FORMAT_ACTIVE,
.code = input->code,
};
+ struct v4l2_subdev_state *act_sd_state;
int ret;
+ if (!input->camera)
+ return -EINVAL;
+
if (input->crop_support)
return atomisp_enum_framesizes_crop(isp, fsize);
- ret = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+ act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+ ret = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+ act_sd_state, &fse);
+ if (act_sd_state)
+ v4l2_subdev_unlock_state(act_sd_state);
if (ret)
return ret;
@@ -803,18 +811,25 @@ static int atomisp_enum_frameintervals(struct file *file, void *priv,
struct video_device *vdev = video_devdata(file);
struct atomisp_device *isp = video_get_drvdata(vdev);
struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+ struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
struct v4l2_subdev_frame_interval_enum fie = {
- .code = atomisp_in_fmt_conv[0].code,
+ .code = atomisp_in_fmt_conv[0].code,
.index = fival->index,
.width = fival->width,
.height = fival->height,
.which = V4L2_SUBDEV_FORMAT_ACTIVE,
};
+ struct v4l2_subdev_state *act_sd_state;
int ret;
- ret = v4l2_subdev_call(isp->inputs[asd->input_curr].camera,
- pad, enum_frame_interval, NULL,
- &fie);
+ if (!input->camera)
+ return -EINVAL;
+
+ act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+ ret = v4l2_subdev_call(input->camera, pad, enum_frame_interval,
+ act_sd_state, &fie);
+ if (act_sd_state)
+ v4l2_subdev_unlock_state(act_sd_state);
if (ret)
return ret;
@@ -830,30 +845,25 @@ static int atomisp_enum_fmt_cap(struct file *file, void *fh,
struct video_device *vdev = video_devdata(file);
struct atomisp_device *isp = video_get_drvdata(vdev);
struct atomisp_sub_device *asd = atomisp_to_video_pipe(vdev)->asd;
+ struct atomisp_input_subdev *input = &isp->inputs[asd->input_curr];
struct v4l2_subdev_mbus_code_enum code = {
.which = V4L2_SUBDEV_FORMAT_ACTIVE,
};
const struct atomisp_format_bridge *format;
- struct v4l2_subdev *camera;
+ struct v4l2_subdev_state *act_sd_state;
unsigned int i, fi = 0;
- int rval;
+ int ret;
- camera = isp->inputs[asd->input_curr].camera;
- if(!camera) {
- dev_err(isp->dev, "%s(): camera is NULL, device is %s\n",
- __func__, vdev->name);
+ if (!input->camera)
return -EINVAL;
- }
- rval = v4l2_subdev_call(camera, pad, enum_mbus_code, NULL, &code);
- if (rval == -ENOIOCTLCMD) {
- dev_warn(isp->dev,
- "enum_mbus_code pad op not supported by %s. Please fix your sensor driver!\n",
- camera->name);
- }
-
- if (rval)
- return rval;
+ act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+ ret = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+ act_sd_state, &code);
+ if (act_sd_state)
+ v4l2_subdev_unlock_state(act_sd_state);
+ if (ret)
+ return ret;
for (i = 0; i < ARRAY_SIZE(atomisp_output_fmts); i++) {
format = &atomisp_output_fmts[i];
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index c1c8501ec61f..547e1444ad97 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -862,6 +862,9 @@ static void atomisp_unregister_entities(struct atomisp_device *isp)
v4l2_device_unregister(&isp->v4l2_dev);
media_device_unregister(&isp->media_dev);
media_device_cleanup(&isp->media_dev);
+
+ for (i = 0; i < isp->input_cnt; i++)
+ __v4l2_subdev_state_free(isp->inputs[i].try_sd_state);
}
static int atomisp_register_entities(struct atomisp_device *isp)
@@ -933,32 +936,49 @@ v4l2_device_failed:
static void atomisp_init_sensor(struct atomisp_input_subdev *input)
{
+ static struct lock_class_key try_sd_state_key;
struct v4l2_subdev_mbus_code_enum mbus_code_enum = { };
struct v4l2_subdev_frame_size_enum fse = { };
- struct v4l2_subdev_state sd_state = {
- .pads = &input->pad_cfg,
- };
struct v4l2_subdev_selection sel = { };
+ struct v4l2_subdev_state *try_sd_state, *act_sd_state;
int i, err;
+ /*
+ * FIXME: Drivers are not supposed to use __v4l2_subdev_state_alloc()
+ * but atomisp needs this for try_fmt on its /dev/video# node since
+ * it emulates a normal v4l2 device there, passing through try_fmt /
+ * set_fmt to the sensor.
+ */
+ try_sd_state = __v4l2_subdev_state_alloc(input->camera,
+ "atomisp:try_sd_state->lock", &try_sd_state_key);
+ if (IS_ERR(try_sd_state))
+ return;
+
+ input->try_sd_state = try_sd_state;
+
+ act_sd_state = v4l2_subdev_lock_and_get_active_state(input->camera);
+
mbus_code_enum.which = V4L2_SUBDEV_FORMAT_ACTIVE;
- err = v4l2_subdev_call(input->camera, pad, enum_mbus_code, NULL, &mbus_code_enum);
+ err = v4l2_subdev_call(input->camera, pad, enum_mbus_code,
+ act_sd_state, &mbus_code_enum);
if (!err)
input->code = mbus_code_enum.code;
sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
sel.target = V4L2_SEL_TGT_NATIVE_SIZE;
- err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+ err = v4l2_subdev_call(input->camera, pad, get_selection,
+ act_sd_state, &sel);
if (err)
- return;
+ goto unlock_act_sd_state;
input->native_rect = sel.r;
sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
sel.target = V4L2_SEL_TGT_CROP_DEFAULT;
- err = v4l2_subdev_call(input->camera, pad, get_selection, NULL, &sel);
+ err = v4l2_subdev_call(input->camera, pad, get_selection,
+ act_sd_state, &sel);
if (err)
- return;
+ goto unlock_act_sd_state;
input->active_rect = sel.r;
@@ -973,7 +993,8 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
fse.code = input->code;
fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
- err = v4l2_subdev_call(input->camera, pad, enum_frame_size, NULL, &fse);
+ err = v4l2_subdev_call(input->camera, pad, enum_frame_size,
+ act_sd_state, &fse);
if (err)
break;
@@ -989,22 +1010,26 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
* for padding, set the crop rect to cover the entire sensor instead
* of only the default active area.
*
- * Do this for both try and active formats since the try_crop rect in
- * pad_cfg may influence (clamp) future try_fmt calls with which == try.
+ * Do this for both try and active formats since the crop rect in
+ * try_sd_state may influence (clamp size) in calls with which == try.
*/
sel.which = V4L2_SUBDEV_FORMAT_TRY;
sel.target = V4L2_SEL_TGT_CROP;
sel.r = input->native_rect;
- err = v4l2_subdev_call(input->camera, pad, set_selection, &sd_state, &sel);
+ v4l2_subdev_lock_state(input->try_sd_state);
+ err = v4l2_subdev_call(input->camera, pad, set_selection,
+ input->try_sd_state, &sel);
+ v4l2_subdev_unlock_state(input->try_sd_state);
if (err)
- return;
+ goto unlock_act_sd_state;
sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
sel.target = V4L2_SEL_TGT_CROP;
sel.r = input->native_rect;
- err = v4l2_subdev_call(input->camera, pad, set_selection, NULL, &sel);
+ err = v4l2_subdev_call(input->camera, pad, set_selection,
+ act_sd_state, &sel);
if (err)
- return;
+ goto unlock_act_sd_state;
dev_info(input->camera->dev, "Supports crop native %dx%d active %dx%d binning %d\n",
input->native_rect.width, input->native_rect.height,
@@ -1012,6 +1037,10 @@ static void atomisp_init_sensor(struct atomisp_input_subdev *input)
input->binning_support);
input->crop_support = true;
+
+unlock_act_sd_state:
+ if (act_sd_state)
+ v4l2_subdev_unlock_state(act_sd_state);
}
int atomisp_register_device_nodes(struct atomisp_device *isp)
From 6a9d552483d50953320b9d3b57abdee8d436f23f Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Thu, 13 Apr 2023 10:50:32 +0200
Subject: [PATCH 126/637] media: rc: bpf attach/detach requires write
permission
Note that bpf attach/detach also requires CAP_NET_ADMIN.
Cc: stable@vger.kernel.org
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
drivers/media/rc/bpf-lirc.c | 6 +++---
drivers/media/rc/lirc_dev.c | 5 ++++-
drivers/media/rc/rc-core-priv.h | 2 +-
3 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fe17c7f98e81..52d82cbe7685 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -253,7 +253,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
if (attr->attach_flags)
return -EINVAL;
- rcdev = rc_dev_get_from_fd(attr->target_fd);
+ rcdev = rc_dev_get_from_fd(attr->target_fd, true);
if (IS_ERR(rcdev))
return PTR_ERR(rcdev);
@@ -278,7 +278,7 @@ int lirc_prog_detach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
- rcdev = rc_dev_get_from_fd(attr->target_fd);
+ rcdev = rc_dev_get_from_fd(attr->target_fd, true);
if (IS_ERR(rcdev)) {
bpf_prog_put(prog);
return PTR_ERR(rcdev);
@@ -303,7 +303,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
if (attr->query.query_flags)
return -EINVAL;
- rcdev = rc_dev_get_from_fd(attr->query.target_fd);
+ rcdev = rc_dev_get_from_fd(attr->query.target_fd, false);
if (IS_ERR(rcdev))
return PTR_ERR(rcdev);
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index a537734832c5..caad59f76793 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -814,7 +814,7 @@ void __exit lirc_dev_exit(void)
unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX);
}
-struct rc_dev *rc_dev_get_from_fd(int fd)
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write)
{
struct fd f = fdget(fd);
struct lirc_fh *fh;
@@ -828,6 +828,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd)
return ERR_PTR(-EINVAL);
}
+ if (write && !(f.file->f_mode & FMODE_WRITE))
+ return ERR_PTR(-EPERM);
+
fh = f.file->private_data;
dev = fh->rc;
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index ef1e95e1af7f..7df949fc65e2 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev);
void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc);
int lirc_register(struct rc_dev *dev);
void lirc_unregister(struct rc_dev *dev);
-struct rc_dev *rc_dev_get_from_fd(int fd);
+struct rc_dev *rc_dev_get_from_fd(int fd, bool write);
#else
static inline int lirc_dev_init(void) { return 0; }
static inline void lirc_dev_exit(void) {}
From dc9ceb90c4b42c6e5c6757df1d6257110433788e Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Wed, 17 Jan 2024 09:14:19 +0100
Subject: [PATCH 127/637] media: ir_toy: fix a memleak in irtoy_tx
When irtoy_command fails, buf should be freed since it is allocated by
irtoy_tx, or there is a memleak.
Fixes: 4114978dcd24 ("media: ir_toy: prevent device from hanging during transmit")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
drivers/media/rc/ir_toy.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c
index 196806709259..69e630d85262 100644
--- a/drivers/media/rc/ir_toy.c
+++ b/drivers/media/rc/ir_toy.c
@@ -332,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
sizeof(COMMAND_SMODE_EXIT), STATE_COMMAND_NO_RESP);
if (err) {
dev_err(irtoy->dev, "exit sample mode: %d\n", err);
+ kfree(buf);
return err;
}
@@ -339,6 +340,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND);
if (err) {
dev_err(irtoy->dev, "enter sample mode: %d\n", err);
+ kfree(buf);
return err;
}
From 346c84e281a963437b9fe9dfcd92c531630289de Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 30 Jan 2024 09:55:25 +0100
Subject: [PATCH 128/637] media: pwm-ir-tx: Depend on CONFIG_HIGH_RES_TIMERS
Since commit 363d0e56285e ("media: pwm-ir-tx: Trigger edges from
hrtimer interrupt context"), pwm-ir-tx uses high resolution timers
for IR signal generation when the pwm can be used from atomic context.
Ensure they are available.
Fixes: 363d0e56285e ("media: pwm-ir-tx: Trigger edges from hrtimer interrupt context")
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
drivers/media/rc/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index 2afe67ffa285..74d69ce22a33 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -319,6 +319,7 @@ config IR_PWM_TX
tristate "PWM IR transmitter"
depends on LIRC
depends on PWM
+ depends on HIGH_RES_TIMERS
depends on OF
help
Say Y if you want to use a PWM based IR transmitter. This is
From e440c5f2e3e6893aeb39bbba6dd181207840a795 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 9 Jan 2024 15:11:17 +0100
Subject: [PATCH 129/637] KVM: selftests: Generalize check_clocksource() from
kvm_clock_test
Several existing x86 selftests need to check that the underlying system
clocksource is TSC or based on TSC but every test implements its own
check. As a first step towards unification, extract check_clocksource()
from kvm_clock_test and split it into two functions: arch-neutral
'sys_get_cur_clocksource()' and x86-specific 'sys_clocksource_is_tsc()'.
Fix a couple of pre-existing issues in kvm_clock_test: memory leakage in
check_clocksource() and using TEST_ASSERT() instead of TEST_REQUIRE().
The change also makes the test fail when system clocksource can't be read
from sysfs.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-2-vkuznets@redhat.com
[sean: eliminate if-elif pattern just to set a bool true]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../testing/selftests/kvm/include/test_util.h | 2 +
.../selftests/kvm/include/x86_64/processor.h | 2 +
tools/testing/selftests/kvm/lib/test_util.c | 25 ++++++++++++
.../selftests/kvm/lib/x86_64/processor.c | 10 +++++
.../selftests/kvm/x86_64/kvm_clock_test.c | 38 +------------------
5 files changed, 40 insertions(+), 37 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 71a41fa924b7..50a5e31ba8da 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -195,4 +195,6 @@ __printf(3, 4) int guest_snprintf(char *buf, int n, const char *fmt, ...);
char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1)));
+char *sys_get_cur_clocksource(void);
+
#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index a84863503fcb..01eec72e0d3e 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1271,4 +1271,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+bool sys_clocksource_is_tsc(void);
+
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 5d7f28b02d73..5a8f8becb129 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -392,3 +392,28 @@ char *strdup_printf(const char *fmt, ...)
return str;
}
+
+#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
+
+char *sys_get_cur_clocksource(void)
+{
+ char *clk_name;
+ struct stat st;
+ FILE *fp;
+
+ fp = fopen(CLOCKSOURCE_PATH, "r");
+ TEST_ASSERT(fp, "failed to open clocksource file, errno: %d", errno);
+
+ TEST_ASSERT(!fstat(fileno(fp), &st), "failed to stat clocksource file, errno: %d",
+ errno);
+
+ clk_name = malloc(st.st_size);
+ TEST_ASSERT(clk_name, "failed to allocate buffer to read file");
+
+ TEST_ASSERT(fgets(clk_name, st.st_size, fp), "failed to read clocksource file: %d",
+ ferror(fp));
+
+ fclose(fp);
+
+ return clk_name;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 4bc52948447d..e6964ff2a37d 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1299,3 +1299,13 @@ void kvm_selftest_arch_init(void)
host_cpu_is_intel = this_cpu_is_intel();
host_cpu_is_amd = this_cpu_is_amd();
}
+
+bool sys_clocksource_is_tsc(void)
+{
+ char *clk_name = sys_get_cur_clocksource();
+ bool ret = !strcmp(clk_name, "tsc\n");
+
+ free(clk_name);
+
+ return ret;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
index 3e0b7d51abda..6fcc1a433587 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
@@ -132,42 +132,6 @@ static void enter_guest(struct kvm_vcpu *vcpu)
}
}
-#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource"
-
-static void check_clocksource(void)
-{
- char *clk_name;
- struct stat st;
- FILE *fp;
-
- fp = fopen(CLOCKSOURCE_PATH, "r");
- if (!fp) {
- pr_info("failed to open clocksource file: %d; assuming TSC.\n",
- errno);
- return;
- }
-
- if (fstat(fileno(fp), &st)) {
- pr_info("failed to stat clocksource file: %d; assuming TSC.\n",
- errno);
- goto out;
- }
-
- clk_name = malloc(st.st_size);
- TEST_ASSERT(clk_name, "failed to allocate buffer to read file");
-
- if (!fgets(clk_name, st.st_size, fp)) {
- pr_info("failed to read clocksource file: %d; assuming TSC.\n",
- ferror(fp));
- goto out;
- }
-
- TEST_ASSERT(!strncmp(clk_name, "tsc\n", st.st_size),
- "clocksource not supported: %s", clk_name);
-out:
- fclose(fp);
-}
-
int main(void)
{
struct kvm_vcpu *vcpu;
@@ -179,7 +143,7 @@ int main(void)
flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK);
TEST_REQUIRE(flags & KVM_CLOCK_REALTIME);
- check_clocksource();
+ TEST_REQUIRE(sys_clocksource_is_tsc());
vm = vm_create_with_one_vcpu(&vcpu, guest_main);
From 410cb01ead5bcec500c0654f361d620553f930aa Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 9 Jan 2024 15:11:18 +0100
Subject: [PATCH 130/637] KVM: selftests: Use generic sys_clocksource_is_tsc()
in vmx_nested_tsc_scaling_test
Despite its name, system_has_stable_tsc() just checks that system
clocksource is 'tsc'; this can now be done with generic
sys_clocksource_is_tsc().
No functional change intended.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-3-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../kvm/x86_64/vmx_nested_tsc_scaling_test.c | 19 +------------------
1 file changed, 1 insertion(+), 18 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
index e710b6e7fb38..93b0a850a240 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
@@ -116,23 +116,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_DONE();
}
-static bool system_has_stable_tsc(void)
-{
- bool tsc_is_stable;
- FILE *fp;
- char buf[4];
-
- fp = fopen("/sys/devices/system/clocksource/clocksource0/current_clocksource", "r");
- if (fp == NULL)
- return false;
-
- tsc_is_stable = fgets(buf, sizeof(buf), fp) &&
- !strncmp(buf, "tsc", sizeof(buf));
-
- fclose(fp);
- return tsc_is_stable;
-}
-
int main(int argc, char *argv[])
{
struct kvm_vcpu *vcpu;
@@ -148,7 +131,7 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
- TEST_REQUIRE(system_has_stable_tsc());
+ TEST_REQUIRE(sys_clocksource_is_tsc());
/*
* We set L1's scale factor to be a random number from 2 to 10.
From 09951bf2cbb3a7893f76d1364b0ae6e3007ff1de Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 9 Jan 2024 15:11:19 +0100
Subject: [PATCH 131/637] KVM: selftests: Run clocksource dependent tests with
hyperv_clocksource_tsc_page too
KVM's 'gtod_is_based_on_tsc()' recognizes two clocksources: 'tsc' and
'hyperv_clocksource_tsc_page' and enables kvmclock in 'masterclock'
mode when either is in use. Transform 'sys_clocksource_is_tsc()' into
'sys_clocksource_is_based_on_tsc()' to support the later. This affects
two tests: kvm_clock_test and vmx_nested_tsc_scaling_test, both seem
to work well when system clocksource is 'hyperv_clocksource_tsc_page'.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-4-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/include/x86_64/processor.h | 2 +-
tools/testing/selftests/kvm/lib/x86_64/processor.c | 5 +++--
tools/testing/selftests/kvm/x86_64/kvm_clock_test.c | 2 +-
.../selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c | 2 +-
4 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 01eec72e0d3e..5bca8c947c82 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1271,6 +1271,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
-bool sys_clocksource_is_tsc(void);
+bool sys_clocksource_is_based_on_tsc(void);
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index e6964ff2a37d..f639b3e062e3 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1300,10 +1300,11 @@ void kvm_selftest_arch_init(void)
host_cpu_is_amd = this_cpu_is_amd();
}
-bool sys_clocksource_is_tsc(void)
+bool sys_clocksource_is_based_on_tsc(void)
{
char *clk_name = sys_get_cur_clocksource();
- bool ret = !strcmp(clk_name, "tsc\n");
+ bool ret = !strcmp(clk_name, "tsc\n") ||
+ !strcmp(clk_name, "hyperv_clocksource_tsc_page\n");
free(clk_name);
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
index 6fcc1a433587..5bc12222d87a 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
@@ -143,7 +143,7 @@ int main(void)
flags = kvm_check_cap(KVM_CAP_ADJUST_CLOCK);
TEST_REQUIRE(flags & KVM_CLOCK_REALTIME);
- TEST_REQUIRE(sys_clocksource_is_tsc());
+ TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
vm = vm_create_with_one_vcpu(&vcpu, guest_main);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
index 93b0a850a240..1759fa5cb3f2 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
@@ -131,7 +131,7 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
- TEST_REQUIRE(sys_clocksource_is_tsc());
+ TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
/*
* We set L1's scale factor to be a random number from 2 to 10.
From b6831a108be1206cd9f0e7905b48677b4147d5f9 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 9 Jan 2024 15:11:20 +0100
Subject: [PATCH 132/637] KVM: selftests: Make hyperv_clock require TSC based
system clocksource
KVM sets up Hyper-V TSC page clocksource for its guests when system
clocksource is 'based on TSC' (see gtod_is_based_on_tsc()), running
hyperv_clock with any other clocksource leads to imminent failure.
Add the missing requirement to make the test skip gracefully.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-5-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/x86_64/hyperv_clock.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index 65690d916db7..e058bc676cd6 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -212,6 +212,7 @@ int main(void)
int stage;
TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME));
+ TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
vm = vm_create_with_one_vcpu(&vcpu, guest_main);
From 9e62797fd7e8eef9c8a3f7b54b57fbc9caf6a20a Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 9 Jan 2024 15:11:21 +0100
Subject: [PATCH 133/637] KVM: x86: Make gtod_is_based_on_tsc() return 'bool'
gtod_is_based_on_tsc() is boolean in nature, i.e. it returns '1' for good
clocksources and '0' otherwise. Moreover, its result is used raw by
kvm_get_time_and_clockread()/kvm_get_walltime_and_clockread() which are
'bool'.
No functional change intended.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20240109141121.1619463-6-vkuznets@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/x86.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 363b1c080205..aa27aec10860 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2507,7 +2507,7 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
}
#ifdef CONFIG_X86_64
-static inline int gtod_is_based_on_tsc(int mode)
+static inline bool gtod_is_based_on_tsc(int mode)
{
return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
}
From f0377ff97509f5a4921993d5d61da000361bd884 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Thu, 18 Jan 2024 12:48:54 +0100
Subject: [PATCH 134/637] nvme-host: fix the updating of the firmware version
The original code didn't update the firmware version if the
"next slot" of the AFI register isn't zero or if the
"current slot" field is zero; in those cases it assumed
that a reset was needed.
However, the NVMe specification doesn't exclude the possibility that
the "next slot" value is equal to the "current slot" value,
meaning that the same firmware slot will be activated after performing
a controller level reset; in this case a reset is clearly not
necessary and we can safely update the firmware version.
Modify the code so the kernel will report that a Controller Level Reset
is needed only in the following cases:
1) If the "current slot" field is zero. This is invalid and means that
something is wrong, a reset is needed.
or
2) if the "next slot" field isn't zero AND it's not equal to the
"current slot" value. This means that at the next reset a different
firmware slot will be activated.
Fixes: 983a338b96c8 ("nvme: update firmware version after commit")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/core.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0d124a8ca9c3..975245527c1f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4191,6 +4191,7 @@ static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl)
static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
{
struct nvme_fw_slot_info_log *log;
+ u8 next_fw_slot, cur_fw_slot;
log = kmalloc(sizeof(*log), GFP_KERNEL);
if (!log)
@@ -4202,13 +4203,15 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
goto out_free_log;
}
- if (log->afi & 0x70 || !(log->afi & 0x7)) {
+ cur_fw_slot = log->afi & 0x7;
+ next_fw_slot = (log->afi & 0x70) >> 4;
+ if (!cur_fw_slot || (next_fw_slot && (cur_fw_slot != next_fw_slot))) {
dev_info(ctrl->device,
"Firmware is activated after next Controller Level Reset\n");
goto out_free_log;
}
- memcpy(ctrl->subsys->firmware_rev, &log->frs[(log->afi & 0x7) - 1],
+ memcpy(ctrl->subsys->firmware_rev, &log->frs[cur_fw_slot - 1],
sizeof(ctrl->subsys->firmware_rev));
out_free_log:
From 1458eb2c9d88ad4b35eb6d6a4aa1d43d8fbf7f62 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 17 Jan 2024 20:57:40 +0100
Subject: [PATCH 135/637] riscv: Fix set_huge_pte_at() for NAPOT mapping
As stated by the privileged specification, we must clear a NAPOT
mapping and emit a sfence.vma before setting a new translation.
Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117195741.1926459-2-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/mm/hugetlbpage.c | 42 +++++++++++++++++++++++++++++++++++--
1 file changed, 40 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 431596c0e20e..865ac5c7d159 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -177,13 +177,36 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
return entry;
}
+static void clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ ptep_get_and_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
void set_huge_pte_at(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
pte_t pte,
unsigned long sz)
{
- unsigned long hugepage_shift;
+ unsigned long hugepage_shift, pgsize;
int i, pte_num;
if (sz >= PGDIR_SIZE)
@@ -198,7 +221,22 @@ void set_huge_pte_at(struct mm_struct *mm,
hugepage_shift = PAGE_SHIFT;
pte_num = sz >> hugepage_shift;
- for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
+ pgsize = 1 << hugepage_shift;
+
+ if (!pte_present(pte)) {
+ for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+ set_ptes(mm, addr, ptep, pte, 1);
+ return;
+ }
+
+ if (!pte_napot(pte)) {
+ set_ptes(mm, addr, ptep, pte, 1);
+ return;
+ }
+
+ clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+ for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
set_pte_at(mm, addr, ptep, pte);
}
From a179a4bfb694f80f2709a1d0398469e787acb974 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 17 Jan 2024 20:57:41 +0100
Subject: [PATCH 136/637] riscv: Fix hugetlb_mask_last_page() when NAPOT is
enabled
When NAPOT is enabled, a new hugepage size is available and then we need
to make hugetlb_mask_last_page() aware of that.
Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117195741.1926459-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/mm/hugetlbpage.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 865ac5c7d159..87406b26c3da 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -125,6 +125,26 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return pte;
}
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+ unsigned long hp_size = huge_page_size(h);
+
+ switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SIZE:
+ return P4D_SIZE - PUD_SIZE;
+#endif
+ case PMD_SIZE:
+ return PUD_SIZE - PMD_SIZE;
+ case napot_cont_size(NAPOT_CONT64KB_ORDER):
+ return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+ default:
+ break;
+ }
+
+ return 0UL;
+}
+
static pte_t get_clear_contig(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
From 03facb39d6c6433a78d0f79c7a146b1e6a61943e Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Wed, 31 Jan 2024 07:08:54 -0800
Subject: [PATCH 137/637] drm/msm/gem: Fix double resv lock aquire
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Since commit 79e2cf2e7a19 ("drm/gem: Take reservation lock for vmap/vunmap
operations"), the resv lock is already held in the prime vmap path, so
don't try to grab it again.
v2: This applies to vunmap path as well
v3: Fix fixes commit
Fixes: 79e2cf2e7a19 ("drm/gem: Take reservation lock for vmap/vunmap operations")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Christian König <christian.koenig@amd.com>
Patchwork: https://patchwork.freedesktop.org/patch/576642/
---
drivers/gpu/drm/msm/msm_gem_prime.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 5f68e31a3e4e..0915f3b68752 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -26,7 +26,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
{
void *vaddr;
- vaddr = msm_gem_get_vaddr(obj);
+ vaddr = msm_gem_get_vaddr_locked(obj);
if (IS_ERR(vaddr))
return PTR_ERR(vaddr);
iosys_map_set_vaddr(map, vaddr);
@@ -36,7 +36,7 @@ int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
{
- msm_gem_put_vaddr(obj);
+ msm_gem_put_vaddr_locked(obj);
}
struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
From 6a0dbcd20ef252ebf98af94186a2e53da7167bed Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Tue, 9 Jan 2024 22:41:08 +0200
Subject: [PATCH 138/637] drm/msm/a6xx: set highest_bank_bit to 13 for a610
During the testing of Gnome on Qualcomm Robotics platform screen
corruption has been observed. Lowering GPU's highest_bank_bit from 14 to
13 seems to fix the screen corruption.
Note, the MDSS and DPU drivers use HBB=1 (which maps to the
highest_bank_bit = 14). So this change merely works around the UBWC
swizzling issue on this platform until the real cause is found.
Fixes: e7fc9398e608 ("drm/msm/a6xx: Add A610 support")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/573838/
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index c0bc924cd302..c9c55e2ea584 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1287,7 +1287,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
gpu->ubwc_config.highest_bank_bit = 15;
if (adreno_is_a610(gpu)) {
- gpu->ubwc_config.highest_bank_bit = 14;
+ gpu->ubwc_config.highest_bank_bit = 13;
gpu->ubwc_config.min_acc_len = 1;
gpu->ubwc_config.ubwc_mode = 1;
}
From 917e9b7c2350e3e53162fcf5035e5f2d68e2cbed Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Tue, 9 Jan 2024 10:22:17 -0800
Subject: [PATCH 139/637] Revert "drm/msm/gpu: Push gpu lock down past runpm"
This reverts commit abe2023b4cea192ab266b351fd38dc9dbd846df0.
Changing the locking order means that scheduler/msm_job_run() can race
with the recovery kthread worker, with the result that the GPU gets an
extra runpm get when we are trying to power it off. Leaving the GPU in
an unrecovered state.
I'll need to come up with a different scheme for appeasing lockdep.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/573835/
---
drivers/gpu/drm/msm/msm_gpu.c | 11 +++++------
drivers/gpu/drm/msm/msm_ringbuffer.c | 7 +++++--
2 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 095390774f22..655002b21b0d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -751,12 +751,14 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned long flags;
+ WARN_ON(!mutex_is_locked(&gpu->lock));
+
pm_runtime_get_sync(&gpu->pdev->dev);
- mutex_lock(&gpu->lock);
-
msm_gpu_hw_init(gpu);
+ submit->seqno = submit->hw_fence->seqno;
+
update_sw_cntrs(gpu);
/*
@@ -781,11 +783,8 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
gpu->funcs->submit(gpu, submit);
gpu->cur_ctx_seqno = submit->queue->ctx->seqno;
- hangcheck_timer_reset(gpu);
-
- mutex_unlock(&gpu->lock);
-
pm_runtime_put(&gpu->pdev->dev);
+ hangcheck_timer_reset(gpu);
}
/*
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 4bc13f7d005a..9d6655f96f0c 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -21,8 +21,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
msm_fence_init(submit->hw_fence, fctx);
- submit->seqno = submit->hw_fence->seqno;
-
mutex_lock(&priv->lru.lock);
for (i = 0; i < submit->nr_bos; i++) {
@@ -35,8 +33,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
mutex_unlock(&priv->lru.lock);
+ /* TODO move submit path over to using a per-ring lock.. */
+ mutex_lock(&gpu->lock);
+
msm_gpu_submit(gpu, submit);
+ mutex_unlock(&gpu->lock);
+
return dma_fence_get(submit->hw_fence);
}
From bb6f4dbe2639d5b8a9fde4bfb6fefecfd3f18df3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Thu, 25 Jan 2024 16:32:29 +0100
Subject: [PATCH 140/637] selftests/landlock: Fix capability for net_test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
CAP_NET_ADMIN allows to configure network interfaces, not CAP_SYS_ADMIN
which only allows to call unshare(2). Without this change, running
network tests as a non-root user but with all capabilities would fail at
the setup_loopback() step with "RTNETLINK answers: Operation not
permitted".
The issue is only visible when running tests with non-root users (i.e.
only relying on ambient capabilities). Indeed, when configuring the
network interface, the "ip" command is called, which may lead to the
special handling of capabilities for the root user by execve(2). If
root is the caller, then the inherited, permitted and effective
capabilities are all reset, which then includes CAP_NET_ADMIN. However,
if a non-root user is the caller, then ambient capabilities are masked
by the inherited ones, which were explicitly dropped.
To make execution deterministic whatever users are running the tests,
set the noroot secure bit for each test, and set the inheritable and
ambient capabilities to CAP_NET_ADMIN, the only capability that may be
required after an execve(2).
Factor out _effective_cap() into _change_cap(), and use it to manage
ambient capabilities with the new set_ambient_cap() and
clear_ambient_cap() helpers.
This makes it possible to run all Landlock tests with check-linux.sh
from https://github.com/landlock-lsm/landlock-test-tools
Cc: Konstantin Meskhidze <konstantin.meskhidze@huawei.com>
Fixes: a549d055a22e ("selftests/landlock: Add network tests")
Link: https://lore.kernel.org/r/20240125153230.3817165-2-mic@digikod.net
[mic: Make sure SECBIT_NOROOT_LOCKED is set]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
tools/testing/selftests/landlock/common.h | 48 +++++++++++++++++----
tools/testing/selftests/landlock/net_test.c | 5 ++-
2 files changed, 44 insertions(+), 9 deletions(-)
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 5b79758cae62..e64bbdf0e86e 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -9,6 +9,7 @@
#include <errno.h>
#include <linux/landlock.h>
+#include <linux/securebits.h>
#include <sys/capability.h>
#include <sys/socket.h>
#include <sys/syscall.h>
@@ -115,11 +116,16 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
/* clang-format off */
CAP_DAC_OVERRIDE,
CAP_MKNOD,
+ CAP_NET_ADMIN,
+ CAP_NET_BIND_SERVICE,
CAP_SYS_ADMIN,
CAP_SYS_CHROOT,
- CAP_NET_BIND_SERVICE,
/* clang-format on */
};
+ const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED;
+
+ if ((cap_get_secbits() & noroot) != noroot)
+ EXPECT_EQ(0, cap_set_secbits(noroot));
cap_p = cap_get_proc();
EXPECT_NE(NULL, cap_p)
@@ -137,6 +143,8 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
}
}
+
+ /* Automatically resets ambient capabilities. */
EXPECT_NE(-1, cap_set_proc(cap_p))
{
TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
@@ -145,6 +153,9 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
{
TH_LOG("Failed to cap_free: %s", strerror(errno));
}
+
+ /* Quickly checks that ambient capabilities are cleared. */
+ EXPECT_NE(-1, cap_get_ambient(caps[0]));
}
/* We cannot put such helpers in a library because of kselftest_harness.h . */
@@ -158,8 +169,9 @@ static void __maybe_unused drop_caps(struct __test_metadata *const _metadata)
_init_caps(_metadata, true);
}
-static void _effective_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps, const cap_flag_value_t value)
+static void _change_cap(struct __test_metadata *const _metadata,
+ const cap_flag_t flag, const cap_value_t cap,
+ const cap_flag_value_t value)
{
cap_t cap_p;
@@ -168,7 +180,7 @@ static void _effective_cap(struct __test_metadata *const _metadata,
{
TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value))
+ EXPECT_NE(-1, cap_set_flag(cap_p, flag, 1, &cap, value))
{
TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
}
@@ -183,15 +195,35 @@ static void _effective_cap(struct __test_metadata *const _metadata,
}
static void __maybe_unused set_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps)
+ const cap_value_t cap)
{
- _effective_cap(_metadata, caps, CAP_SET);
+ _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_SET);
}
static void __maybe_unused clear_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps)
+ const cap_value_t cap)
{
- _effective_cap(_metadata, caps, CAP_CLEAR);
+ _change_cap(_metadata, CAP_EFFECTIVE, cap, CAP_CLEAR);
+}
+
+static void __maybe_unused
+set_ambient_cap(struct __test_metadata *const _metadata, const cap_value_t cap)
+{
+ _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_SET);
+
+ EXPECT_NE(-1, cap_set_ambient(cap, CAP_SET))
+ {
+ TH_LOG("Failed to set ambient capability %d: %s", cap,
+ strerror(errno));
+ }
+}
+
+static void __maybe_unused clear_ambient_cap(
+ struct __test_metadata *const _metadata, const cap_value_t cap)
+{
+ EXPECT_EQ(1, cap_get_ambient(cap));
+ _change_cap(_metadata, CAP_INHERITABLE, cap, CAP_CLEAR);
+ EXPECT_EQ(0, cap_get_ambient(cap));
}
/* Receives an FD from a UNIX socket. Returns the received FD, or -errno. */
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index efcde123af1f..936cfc879f1d 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -107,8 +107,11 @@ static void setup_loopback(struct __test_metadata *const _metadata)
{
set_cap(_metadata, CAP_SYS_ADMIN);
ASSERT_EQ(0, unshare(CLONE_NEWNET));
- ASSERT_EQ(0, system("ip link set dev lo up"));
clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ set_ambient_cap(_metadata, CAP_NET_ADMIN);
+ ASSERT_EQ(0, system("ip link set dev lo up"));
+ clear_ambient_cap(_metadata, CAP_NET_ADMIN);
}
static bool is_restricted(const struct protocol_variant *const prot,
From 46eba193d04f8bd717e525eb4110f3c46c12aec3 Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Wed, 31 Jan 2024 10:08:28 +0800
Subject: [PATCH 141/637] net: stmmac: xgmac: fix handling of DPP safety error
for DMA channels
Commit 56e58d6c8a56 ("net: stmmac: Implement Safety Features in
XGMAC core") checks and reports safety errors, but leaves the
Data Path Parity Errors for each channel in DMA unhandled at all, lead to
a storm of interrupt.
Fix it by checking and clearing the DMA_DPP_Interrupt_Status register.
Fixes: 56e58d6c8a56 ("net: stmmac: Implement Safety Features in XGMAC core")
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 1 +
.../net/ethernet/stmicro/stmmac/dwxgmac2.h | 3 +
.../ethernet/stmicro/stmmac/dwxgmac2_core.c | 57 ++++++++++++++++++-
3 files changed, 60 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 721c1f8e892f..b4f60ab078d6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -216,6 +216,7 @@ struct stmmac_safety_stats {
unsigned long mac_errors[32];
unsigned long mtl_errors[32];
unsigned long dma_errors[32];
+ unsigned long dma_dpp_errors[32];
};
/* Number of fields in Safety Stats */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 207ff1799f2c..5c67a3f89f08 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -303,6 +303,8 @@
#define XGMAC_RXCEIE BIT(4)
#define XGMAC_TXCEIE BIT(0)
#define XGMAC_MTL_ECC_INT_STATUS 0x000010cc
+#define XGMAC_MTL_DPP_CONTROL 0x000010e0
+#define XGMAC_DDPP_DISABLE BIT(0)
#define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x)))
#define XGMAC_TQS GENMASK(25, 16)
#define XGMAC_TQS_SHIFT 16
@@ -385,6 +387,7 @@
#define XGMAC_DCEIE BIT(1)
#define XGMAC_TCEIE BIT(0)
#define XGMAC_DMA_ECC_INT_STATUS 0x0000306c
+#define XGMAC_DMA_DPP_INT_STATUS 0x00003074
#define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x)))
#define XGMAC_SPH BIT(24)
#define XGMAC_PBLx8 BIT(16)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index eb48211d9b0e..04d7c4dc2e35 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -830,6 +830,43 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
};
+static const char * const dpp_rx_err = "Read Rx Descriptor Parity checker Error";
+static const char * const dpp_tx_err = "Read Tx Descriptor Parity checker Error";
+static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
+ { true, "TDPES0", dpp_tx_err },
+ { true, "TDPES1", dpp_tx_err },
+ { true, "TDPES2", dpp_tx_err },
+ { true, "TDPES3", dpp_tx_err },
+ { true, "TDPES4", dpp_tx_err },
+ { true, "TDPES5", dpp_tx_err },
+ { true, "TDPES6", dpp_tx_err },
+ { true, "TDPES7", dpp_tx_err },
+ { true, "TDPES8", dpp_tx_err },
+ { true, "TDPES9", dpp_tx_err },
+ { true, "TDPES10", dpp_tx_err },
+ { true, "TDPES11", dpp_tx_err },
+ { true, "TDPES12", dpp_tx_err },
+ { true, "TDPES13", dpp_tx_err },
+ { true, "TDPES14", dpp_tx_err },
+ { true, "TDPES15", dpp_tx_err },
+ { true, "RDPES0", dpp_rx_err },
+ { true, "RDPES1", dpp_rx_err },
+ { true, "RDPES2", dpp_rx_err },
+ { true, "RDPES3", dpp_rx_err },
+ { true, "RDPES4", dpp_rx_err },
+ { true, "RDPES5", dpp_rx_err },
+ { true, "RDPES6", dpp_rx_err },
+ { true, "RDPES7", dpp_rx_err },
+ { true, "RDPES8", dpp_rx_err },
+ { true, "RDPES9", dpp_rx_err },
+ { true, "RDPES10", dpp_rx_err },
+ { true, "RDPES11", dpp_rx_err },
+ { true, "RDPES12", dpp_rx_err },
+ { true, "RDPES13", dpp_rx_err },
+ { true, "RDPES14", dpp_rx_err },
+ { true, "RDPES15", dpp_rx_err },
+};
+
static void dwxgmac3_handle_dma_err(struct net_device *ndev,
void __iomem *ioaddr, bool correctable,
struct stmmac_safety_stats *stats)
@@ -841,6 +878,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev,
dwxgmac3_log_error(ndev, value, correctable, "DMA",
dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats);
+
+ value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+ writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS);
+
+ dwxgmac3_log_error(ndev, value, false, "DMA_DPP",
+ dwxgmac3_dma_dpp_errors,
+ STAT_OFF(dma_dpp_errors), stats);
}
static int
@@ -881,6 +925,12 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */
writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL);
+ /* 5. Enable Data Path Parity Protection */
+ value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
+ /* already enabled by default, explicit enable it again */
+ value &= ~XGMAC_DDPP_DISABLE;
+ writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
+
return 0;
}
@@ -914,7 +964,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev,
ret |= !corr;
}
- err = dma & (XGMAC_DEUIS | XGMAC_DECIS);
+ /* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in
+ * DMA_Safety_Interrupt_Status, so we handle DMA Data Path
+ * Parity Errors here
+ */
+ err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS);
corr = dma & XGMAC_DECIS;
if (err) {
dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats);
@@ -930,6 +984,7 @@ static const struct dwxgmac3_error {
{ dwxgmac3_mac_errors },
{ dwxgmac3_mtl_errors },
{ dwxgmac3_dma_errors },
+ { dwxgmac3_dma_dpp_errors },
};
static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats,
From ccb88e9549e7cfd8bcd511c538f437e20026e983 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@amd.com>
Date: Thu, 25 Jan 2024 17:12:53 -0600
Subject: [PATCH 142/637] crypto: ccp - Fix null pointer dereference in
__sev_platform_shutdown_locked
The SEV platform device can be shutdown with a null psp_master,
e.g., using DEBUG_TEST_DRIVER_REMOVE. Found using KASAN:
[ 137.148210] ccp 0000:23:00.1: enabling device (0000 -> 0002)
[ 137.162647] ccp 0000:23:00.1: no command queues available
[ 137.170598] ccp 0000:23:00.1: sev enabled
[ 137.174645] ccp 0000:23:00.1: psp enabled
[ 137.178890] general protection fault, probably for non-canonical address 0xdffffc000000001e: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN NOPTI
[ 137.182693] KASAN: null-ptr-deref in range [0x00000000000000f0-0x00000000000000f7]
[ 137.182693] CPU: 93 PID: 1 Comm: swapper/0 Not tainted 6.8.0-rc1+ #311
[ 137.182693] RIP: 0010:__sev_platform_shutdown_locked+0x51/0x180
[ 137.182693] Code: 08 80 3c 08 00 0f 85 0e 01 00 00 48 8b 1d 67 b6 01 08 48 b8 00 00 00 00 00 fc ff df 48 8d bb f0 00 00 00 48 89 f9 48 c1 e9 03 <80> 3c 01 00 0f 85 fe 00 00 00 48 8b 9b f0 00 00 00 48 85 db 74 2c
[ 137.182693] RSP: 0018:ffffc900000cf9b0 EFLAGS: 00010216
[ 137.182693] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 000000000000001e
[ 137.182693] RDX: 0000000000000000 RSI: 0000000000000008 RDI: 00000000000000f0
[ 137.182693] RBP: ffffc900000cf9c8 R08: 0000000000000000 R09: fffffbfff58f5a66
[ 137.182693] R10: ffffc900000cf9c8 R11: ffffffffac7ad32f R12: ffff8881e5052c28
[ 137.182693] R13: ffff8881e5052c28 R14: ffff8881758e43e8 R15: ffffffffac64abf8
[ 137.182693] FS: 0000000000000000(0000) GS:ffff889de7000000(0000) knlGS:0000000000000000
[ 137.182693] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 137.182693] CR2: 0000000000000000 CR3: 0000001cf7c7e000 CR4: 0000000000350ef0
[ 137.182693] Call Trace:
[ 137.182693] <TASK>
[ 137.182693] ? show_regs+0x6c/0x80
[ 137.182693] ? __die_body+0x24/0x70
[ 137.182693] ? die_addr+0x4b/0x80
[ 137.182693] ? exc_general_protection+0x126/0x230
[ 137.182693] ? asm_exc_general_protection+0x2b/0x30
[ 137.182693] ? __sev_platform_shutdown_locked+0x51/0x180
[ 137.182693] sev_firmware_shutdown.isra.0+0x1e/0x80
[ 137.182693] sev_dev_destroy+0x49/0x100
[ 137.182693] psp_dev_destroy+0x47/0xb0
[ 137.182693] sp_destroy+0xbb/0x240
[ 137.182693] sp_pci_remove+0x45/0x60
[ 137.182693] pci_device_remove+0xaa/0x1d0
[ 137.182693] device_remove+0xc7/0x170
[ 137.182693] really_probe+0x374/0xbe0
[ 137.182693] ? srso_return_thunk+0x5/0x5f
[ 137.182693] __driver_probe_device+0x199/0x460
[ 137.182693] driver_probe_device+0x4e/0xd0
[ 137.182693] __driver_attach+0x191/0x3d0
[ 137.182693] ? __pfx___driver_attach+0x10/0x10
[ 137.182693] bus_for_each_dev+0x100/0x190
[ 137.182693] ? __pfx_bus_for_each_dev+0x10/0x10
[ 137.182693] ? __kasan_check_read+0x15/0x20
[ 137.182693] ? srso_return_thunk+0x5/0x5f
[ 137.182693] ? _raw_spin_unlock+0x27/0x50
[ 137.182693] driver_attach+0x41/0x60
[ 137.182693] bus_add_driver+0x2a8/0x580
[ 137.182693] driver_register+0x141/0x480
[ 137.182693] __pci_register_driver+0x1d6/0x2a0
[ 137.182693] ? srso_return_thunk+0x5/0x5f
[ 137.182693] ? esrt_sysfs_init+0x1cd/0x5d0
[ 137.182693] ? __pfx_sp_mod_init+0x10/0x10
[ 137.182693] sp_pci_init+0x22/0x30
[ 137.182693] sp_mod_init+0x14/0x30
[ 137.182693] ? __pfx_sp_mod_init+0x10/0x10
[ 137.182693] do_one_initcall+0xd1/0x470
[ 137.182693] ? __pfx_do_one_initcall+0x10/0x10
[ 137.182693] ? parameq+0x80/0xf0
[ 137.182693] ? srso_return_thunk+0x5/0x5f
[ 137.182693] ? __kmalloc+0x3b0/0x4e0
[ 137.182693] ? kernel_init_freeable+0x92d/0x1050
[ 137.182693] ? kasan_populate_vmalloc_pte+0x171/0x190
[ 137.182693] ? srso_return_thunk+0x5/0x5f
[ 137.182693] kernel_init_freeable+0xa64/0x1050
[ 137.182693] ? __pfx_kernel_init+0x10/0x10
[ 137.182693] kernel_init+0x24/0x160
[ 137.182693] ? __switch_to_asm+0x3e/0x70
[ 137.182693] ret_from_fork+0x40/0x80
[ 137.182693] ? __pfx_kernel_init+0x10/0x10
[ 137.182693] ret_from_fork_asm+0x1b/0x30
[ 137.182693] </TASK>
[ 137.182693] Modules linked in:
[ 137.538483] ---[ end trace 0000000000000000 ]---
Fixes: 1b05ece0c931 ("crypto: ccp - During shutdown, check SEV data pointer before using")
Cc: stable@vger.kernel.org
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Acked-by: John Allen <john.allen@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
drivers/crypto/ccp/sev-dev.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e4d3f45242f6..b04bc1d3d627 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -534,10 +534,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init);
static int __sev_platform_shutdown_locked(int *error)
{
- struct sev_device *sev = psp_master->sev_data;
+ struct psp_device *psp = psp_master;
+ struct sev_device *sev;
int ret;
- if (!sev || sev->state == SEV_STATE_UNINIT)
+ if (!psp || !psp->sev_data)
+ return 0;
+
+ sev = psp->sev_data;
+
+ if (sev->state == SEV_STATE_UNINIT)
return 0;
ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
From 69fba378edcaffba7bc7d299fdee02e377069d30 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 29 Jan 2024 22:17:11 +0800
Subject: [PATCH 143/637] crypto: cbc - Ensure statesize is zero
The cbc template should not be applied on stream ciphers, especially
ones that have internal state. Enforce this by checking the state
size when the instance is created.
Reported-by: syzbot+050eeedd6c285d8c42f2@syzkaller.appspotmail.com
Fixes: 47309ea13591 ("crypto: arc4 - Add internal state")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
crypto/cbc.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/crypto/cbc.c b/crypto/cbc.c
index eedddef9ce40..e81918ca68b7 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -148,6 +148,9 @@ static int crypto_cbc_create(struct crypto_template *tmpl, struct rtattr **tb)
if (!is_power_of_2(inst->alg.co.base.cra_blocksize))
goto out_free_inst;
+ if (inst->alg.co.statesize)
+ goto out_free_inst;
+
inst->alg.encrypt = crypto_cbc_encrypt;
inst->alg.decrypt = crypto_cbc_decrypt;
From 24c890dd712f6345e382256cae8c97abb0406b70 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 1 Feb 2024 13:49:09 +0800
Subject: [PATCH 144/637] crypto: algif_hash - Remove bogus SGL free on
zero-length error path
When a zero-length message is hashed by algif_hash, and an error
is triggered, it tries to free an SG list that was never allocated
in the first place. Fix this by not freeing the SG list on the
zero-length error path.
Reported-by: Shigeru Yoshida <syoshida@redhat.com>
Reported-by: xingwei lee <xrivendell7@gmail.com>
Fixes: b6d972f68983 ("crypto: af_alg/hash: Fix recvmsg() after sendmsg(MSG_MORE)")
Cc: <stable@vger.kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Reported-by: syzbot+3266db0c26d1fbbe3abb@syzkaller.appspotmail.com
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
crypto/algif_hash.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 82c44d4899b9..e24c829d7a01 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg,
if (!(msg->msg_flags & MSG_MORE)) {
err = hash_alloc_result(sk, ctx);
if (err)
- goto unlock_free;
+ goto unlock_free_result;
ahash_request_set_crypt(&ctx->req, NULL,
ctx->result, 0);
err = crypto_wait_req(crypto_ahash_final(&ctx->req),
&ctx->wait);
if (err)
- goto unlock_free;
+ goto unlock_free_result;
}
goto done_more;
}
@@ -170,6 +170,7 @@ unlock:
unlock_free:
af_alg_free_sg(&ctx->sgl);
+unlock_free_result:
hash_free_result(sk, ctx);
ctx->more = false;
goto unlock;
From 177fbbcb4ed6b306c1626a277fac3fb1c495a4c7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 13:14:13 +0100
Subject: [PATCH 145/637] wifi: cfg80211: detect stuck ECSA element in probe
resp
We recently added some validation that we don't try to
connect to an AP that is currently in a channel switch
process, since that might want the channel to be quiet
or we might not be able to connect in time to hear the
switching in a beacon. This was in commit c09c4f31998b
("wifi: mac80211: don't connect to an AP while it's in
a CSA process").
However, we promptly got a report that this caused new
connection failures, and it turns out that the AP that
we now cannot connect to is permanently advertising an
extended channel switch announcement, even with quiet.
The AP in question was an Asus RT-AC53, with firmware
3.0.0.4.380_10760-g21a5898.
As a first step, attempt to detect that we're dealing
with such a situation, so mac80211 can use this later.
Reported-by: coldolt <andypalmadi@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/CAJvGw+DQhBk_mHXeu6RTOds5iramMW2FbMB01VbKRA4YbHHDTA@mail.gmail.com/
Fixes: c09c4f31998b ("wifi: mac80211: don't connect to an AP while it's in a CSA process")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240129131413.246972c8775e.Ibf834d7f52f9951a353b6872383da710a7358338@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
include/net/cfg80211.h | 4 +++
net/wireless/scan.c | 59 +++++++++++++++++++++++++++++++++++++++++-
2 files changed, 62 insertions(+), 1 deletion(-)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cf79656ce09c..2b54fdd8ca15 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2910,6 +2910,8 @@ struct cfg80211_bss_ies {
* own the beacon_ies, but they're just pointers to the ones from the
* @hidden_beacon_bss struct)
* @proberesp_ies: the information elements from the last Probe Response frame
+ * @proberesp_ecsa_stuck: ECSA element is stuck in the Probe Response frame,
+ * cannot rely on it having valid data
* @hidden_beacon_bss: in case this BSS struct represents a probe response from
* a BSS that hides the SSID in its beacon, this points to the BSS struct
* that holds the beacon data. @beacon_ies is still valid, of course, and
@@ -2950,6 +2952,8 @@ struct cfg80211_bss {
u8 chains;
s8 chain_signal[IEEE80211_MAX_CHAINS];
+ u8 proberesp_ecsa_stuck:1;
+
u8 bssid_index;
u8 max_bssid_indicator;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2249b1a89d1c..389a52c29bfc 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1731,6 +1731,61 @@ static void cfg80211_update_hidden_bsses(struct cfg80211_internal_bss *known,
}
}
+static void cfg80211_check_stuck_ecsa(struct cfg80211_registered_device *rdev,
+ struct cfg80211_internal_bss *known,
+ const struct cfg80211_bss_ies *old)
+{
+ const struct ieee80211_ext_chansw_ie *ecsa;
+ const struct element *elem_new, *elem_old;
+ const struct cfg80211_bss_ies *new, *bcn;
+
+ if (known->pub.proberesp_ecsa_stuck)
+ return;
+
+ new = rcu_dereference_protected(known->pub.proberesp_ies,
+ lockdep_is_held(&rdev->bss_lock));
+ if (WARN_ON(!new))
+ return;
+
+ if (new->tsf - old->tsf < USEC_PER_SEC)
+ return;
+
+ elem_old = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+ old->data, old->len);
+ if (!elem_old)
+ return;
+
+ elem_new = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+ new->data, new->len);
+ if (!elem_new)
+ return;
+
+ bcn = rcu_dereference_protected(known->pub.beacon_ies,
+ lockdep_is_held(&rdev->bss_lock));
+ if (bcn &&
+ cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+ bcn->data, bcn->len))
+ return;
+
+ if (elem_new->datalen != elem_old->datalen)
+ return;
+ if (elem_new->datalen < sizeof(struct ieee80211_ext_chansw_ie))
+ return;
+ if (memcmp(elem_new->data, elem_old->data, elem_new->datalen))
+ return;
+
+ ecsa = (void *)elem_new->data;
+
+ if (!ecsa->mode)
+ return;
+
+ if (ecsa->new_ch_num !=
+ ieee80211_frequency_to_channel(known->pub.channel->center_freq))
+ return;
+
+ known->pub.proberesp_ecsa_stuck = 1;
+}
+
static bool
cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
struct cfg80211_internal_bss *known,
@@ -1750,8 +1805,10 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
/* Override possible earlier Beacon frame IEs */
rcu_assign_pointer(known->pub.ies,
new->pub.proberesp_ies);
- if (old)
+ if (old) {
+ cfg80211_check_stuck_ecsa(rdev, known, old);
kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head);
+ }
}
if (rcu_access_pointer(new->pub.beacon_ies)) {
From 35e2385dbe787936c793d70755a5177d267a40aa Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 13:14:14 +0100
Subject: [PATCH 146/637] wifi: mac80211: improve CSA/ECSA connection refusal
As mentioned in the previous commit, we pretty quickly found
that some APs have ECSA elements stuck in their probe response,
so using that to not attempt to connect while CSA is happening
we never connect to such an AP.
Improve this situation by checking more carefully and ignoring
the ECSA if cfg80211 has previously detected the ECSA element
being stuck in the probe response.
Additionally, allow connecting to an AP that's switching to a
channel it's already using, unless it's using quiet mode. In
this case, we may just have to adjust bandwidth later. If it's
actually switching channels, it's better not to try to connect
in the middle of that.
Reported-by: coldolt <andypalmadi@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/CAJvGw+DQhBk_mHXeu6RTOds5iramMW2FbMB01VbKRA4YbHHDTA@mail.gmail.com/
Fixes: c09c4f31998b ("wifi: mac80211: don't connect to an AP while it's in a CSA process")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240129131413.cc2d0a26226e.I682c016af76e35b6c47007db50e8554c5a426910@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/mlme.c | 103 ++++++++++++++++++++++++++++++++------------
1 file changed, 76 insertions(+), 27 deletions(-)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 073105deb424..c62c7c6ce91f 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7309,6 +7309,75 @@ out_err:
return err;
}
+static bool ieee80211_mgd_csa_present(struct ieee80211_sub_if_data *sdata,
+ const struct cfg80211_bss_ies *ies,
+ u8 cur_channel, bool ignore_ecsa)
+{
+ const struct element *csa_elem, *ecsa_elem;
+ struct ieee80211_channel_sw_ie *csa = NULL;
+ struct ieee80211_ext_chansw_ie *ecsa = NULL;
+
+ if (!ies)
+ return false;
+
+ csa_elem = cfg80211_find_elem(WLAN_EID_CHANNEL_SWITCH,
+ ies->data, ies->len);
+ if (csa_elem && csa_elem->datalen == sizeof(*csa))
+ csa = (void *)csa_elem->data;
+
+ ecsa_elem = cfg80211_find_elem(WLAN_EID_EXT_CHANSWITCH_ANN,
+ ies->data, ies->len);
+ if (ecsa_elem && ecsa_elem->datalen == sizeof(*ecsa))
+ ecsa = (void *)ecsa_elem->data;
+
+ if (csa && csa->count == 0)
+ csa = NULL;
+ if (csa && !csa->mode && csa->new_ch_num == cur_channel)
+ csa = NULL;
+
+ if (ecsa && ecsa->count == 0)
+ ecsa = NULL;
+ if (ecsa && !ecsa->mode && ecsa->new_ch_num == cur_channel)
+ ecsa = NULL;
+
+ if (ignore_ecsa && ecsa) {
+ sdata_info(sdata,
+ "Ignoring ECSA in probe response - was considered stuck!\n");
+ return csa;
+ }
+
+ return csa || ecsa;
+}
+
+static bool ieee80211_mgd_csa_in_process(struct ieee80211_sub_if_data *sdata,
+ struct cfg80211_bss *bss)
+{
+ u8 cur_channel;
+ bool ret;
+
+ cur_channel = ieee80211_frequency_to_channel(bss->channel->center_freq);
+
+ rcu_read_lock();
+ if (ieee80211_mgd_csa_present(sdata,
+ rcu_dereference(bss->beacon_ies),
+ cur_channel, false)) {
+ ret = true;
+ goto out;
+ }
+
+ if (ieee80211_mgd_csa_present(sdata,
+ rcu_dereference(bss->proberesp_ies),
+ cur_channel, bss->proberesp_ecsa_stuck)) {
+ ret = true;
+ goto out;
+ }
+
+ ret = false;
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
/* config hooks */
int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
struct cfg80211_auth_request *req)
@@ -7317,7 +7386,6 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_mgd_auth_data *auth_data;
struct ieee80211_link_data *link;
- const struct element *csa_elem, *ecsa_elem;
u16 auth_alg;
int err;
bool cont_auth;
@@ -7360,21 +7428,10 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
if (ifmgd->assoc_data)
return -EBUSY;
- rcu_read_lock();
- csa_elem = ieee80211_bss_get_elem(req->bss, WLAN_EID_CHANNEL_SWITCH);
- ecsa_elem = ieee80211_bss_get_elem(req->bss,
- WLAN_EID_EXT_CHANSWITCH_ANN);
- if ((csa_elem &&
- csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
- ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
- (ecsa_elem &&
- ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
- ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
- rcu_read_unlock();
+ if (ieee80211_mgd_csa_in_process(sdata, req->bss)) {
sdata_info(sdata, "AP is in CSA process, reject auth\n");
return -EINVAL;
}
- rcu_read_unlock();
auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len +
req->ie_len, GFP_KERNEL);
@@ -7684,7 +7741,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_mgd_assoc_data *assoc_data;
- const struct element *ssid_elem, *csa_elem, *ecsa_elem;
+ const struct element *ssid_elem;
struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
ieee80211_conn_flags_t conn_flags = 0;
struct ieee80211_link_data *link;
@@ -7707,23 +7764,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
cbss = req->link_id < 0 ? req->bss : req->links[req->link_id].bss;
- rcu_read_lock();
- ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
- if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
- rcu_read_unlock();
+ if (ieee80211_mgd_csa_in_process(sdata, cbss)) {
+ sdata_info(sdata, "AP is in CSA process, reject assoc\n");
kfree(assoc_data);
return -EINVAL;
}
- csa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_CHANNEL_SWITCH);
- ecsa_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_EXT_CHANSWITCH_ANN);
- if ((csa_elem &&
- csa_elem->datalen == sizeof(struct ieee80211_channel_sw_ie) &&
- ((struct ieee80211_channel_sw_ie *)csa_elem->data)->count != 0) ||
- (ecsa_elem &&
- ecsa_elem->datalen == sizeof(struct ieee80211_ext_chansw_ie) &&
- ((struct ieee80211_ext_chansw_ie *)ecsa_elem->data)->count != 0)) {
- sdata_info(sdata, "AP is in CSA process, reject assoc\n");
+ rcu_read_lock();
+ ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID);
+ if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) {
rcu_read_unlock();
kfree(assoc_data);
return -EINVAL;
From 9480adfe4e0f0319b9da04b44e4eebd5ad07e0cd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:53:48 +0100
Subject: [PATCH 147/637] wifi: mac80211: fix RCU use in TDLS fast-xmit
This looks up the link under RCU protection, but isn't
guaranteed to actually have protection. Fix that.
Fixes: 8cc07265b691 ("wifi: mac80211: handle TDLS data frames with MLO")
Link: https://msgid.link/20240129155348.8a9c0b1e1d89.I553f96ce953bb41b0b877d592056164dec20d01c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/tx.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 68a48abc7287..e448ab338448 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3100,10 +3100,11 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
/* DA SA BSSID */
build.da_offs = offsetof(struct ieee80211_hdr, addr1);
build.sa_offs = offsetof(struct ieee80211_hdr, addr2);
+ rcu_read_lock();
link = rcu_dereference(sdata->link[tdls_link_id]);
- if (WARN_ON_ONCE(!link))
- break;
- memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+ if (!WARN_ON_ONCE(!link))
+ memcpy(hdr->addr3, link->u.mgd.bssid, ETH_ALEN);
+ rcu_read_unlock();
build.hdr_len = 24;
break;
}
From dd6c064cfc3fc18d871107c6f5db8837e88572e4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:53:55 +0100
Subject: [PATCH 148/637] wifi: mac80211: set station RX-NSS on reconfig
When a station is added/reconfigured by userspace, e.g. a TDLS
peer or a SoftAP client STA, rx_nss is currently not always set,
so that it might be left zero. Set it up properly.
Link: https://msgid.link/20240129155354.98f148a3d654.I193a02155f557ea54dc9d0232da66cf96734119a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/cfg.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 489dd97f5172..321698012e12 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1869,6 +1869,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
sband->band);
}
+ ieee80211_sta_set_rx_nss(link_sta);
+
return ret;
}
From 733c498a80853acbafe284a40468b91f4d41f0b4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 15:54:02 +0100
Subject: [PATCH 149/637] wifi: mac80211: fix driver debugfs for vif type
change
If a driver implements the change_interface() method, we switch
interface type without taking the interface down, but still will
recreate the debugfs for it since it's a new type. As such, we
should use the ieee80211_debugfs_recreate_netdev() function here
to also recreate the driver's files, if it is indeed from a type
change while up.
Link: https://msgid.link/20240129155402.7311a36ffeeb.I18df02bbeb685d4250911de5ffbaf090f60c3803@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/debugfs_netdev.c | 4 ++--
net/mac80211/debugfs_netdev.h | 5 -----
net/mac80211/iface.c | 2 +-
3 files changed, 3 insertions(+), 8 deletions(-)
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index dce5606ed66d..68596ef78b15 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -997,8 +997,8 @@ static void add_link_files(struct ieee80211_link_data *link,
}
}
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
- bool mld_vif)
+static void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
+ bool mld_vif)
{
char buf[10+IFNAMSIZ];
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index b226b1aae88a..a02ec0a413f6 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -11,8 +11,6 @@
#include "ieee80211_i.h"
#ifdef CONFIG_MAC80211_DEBUGFS
-void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata,
- bool mld_vif);
void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata);
void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
@@ -24,9 +22,6 @@ void ieee80211_link_debugfs_remove(struct ieee80211_link_data *link);
void ieee80211_link_debugfs_drv_add(struct ieee80211_link_data *link);
void ieee80211_link_debugfs_drv_remove(struct ieee80211_link_data *link);
#else
-static inline void ieee80211_debugfs_add_netdev(
- struct ieee80211_sub_if_data *sdata, bool mld_vif)
-{}
static inline void ieee80211_debugfs_remove_netdev(
struct ieee80211_sub_if_data *sdata)
{}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e4e7c0b38cb6..11c4caa4748e 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1783,7 +1783,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
/* need to do this after the switch so vif.type is correct */
ieee80211_link_setup(&sdata->deflink);
- ieee80211_debugfs_add_netdev(sdata, false);
+ ieee80211_debugfs_recreate_netdev(sdata, false);
}
static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
From 86b2dac224f963be92634a878888222e1e938f48 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 19:54:05 +0100
Subject: [PATCH 150/637] wifi: mac80211: initialize SMPS mode correctly
The SMPS mode is currently re-initialized too late, since
ieee80211_prep_channel() can be called again after we've
already done ieee80211_setup_assoc_link(), in case there's
some override of the channel configuration. Fix this.
Link: https://msgid.link/20240129195405.d6d74508be18.I0a7303b1ce4d8e5436011951ab624372a445c069@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/mlme.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index c62c7c6ce91f..f1cdd2df323e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2023 Intel Corporation
+ * Copyright (C) 2018 - 2024 Intel Corporation
*/
#include <linux/delay.h>
@@ -2918,6 +2918,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
/* other links will be destroyed */
sdata->deflink.u.mgd.bss = NULL;
+ sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
netif_carrier_off(sdata->dev);
@@ -5045,9 +5046,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
if (!link)
return 0;
- /* will change later if needed */
- link->smps_mode = IEEE80211_SMPS_OFF;
-
/*
* If this fails (possibly due to channel context sharing
* on incompatible channels, e.g. 80+80 and 160 sharing the
@@ -7096,6 +7094,7 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link)
link->u.mgd.p2p_noa_index = -1;
link->u.mgd.conn_flags = 0;
link->conf->bssid = link->u.mgd.bssid;
+ link->smps_mode = IEEE80211_SMPS_OFF;
wiphy_work_init(&link->u.mgd.request_smps_work,
ieee80211_request_smps_mgd_work);
From 178e9d6adc4356c2f1659f575ecea626e7fbd05a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 19:57:30 +0100
Subject: [PATCH 151/637] wifi: mac80211: fix unsolicited broadcast probe
config
There's a bug in ieee80211_set_unsol_bcast_probe_resp(), it tries
to return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP (which has the value
1<<31) in an int, which makes it negative and considered an error.
Fix this by passing the changed flags to set separately.
Fixes: 3b1c256eb4ae ("wifi: mac80211: fixes in FILS discovery updates")
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://msgid.link/20240129195729.965b0740bf80.I6bc6f5236863f686c17d689be541b1dd2633c417@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/cfg.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 321698012e12..327682995c92 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5,7 +5,7 @@
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*/
#include <linux/ieee80211.h>
@@ -987,7 +987,8 @@ static int
ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
struct cfg80211_unsol_bcast_probe_resp *params,
struct ieee80211_link_data *link,
- struct ieee80211_bss_conf *link_conf)
+ struct ieee80211_bss_conf *link_conf,
+ u64 *changed)
{
struct unsol_bcast_probe_resp_data *new, *old = NULL;
@@ -1011,7 +1012,8 @@ ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL);
}
- return BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+ *changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+ return 0;
}
static int ieee80211_set_ftm_responder_params(
@@ -1450,10 +1452,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
err = ieee80211_set_unsol_bcast_probe_resp(sdata,
¶ms->unsol_bcast_probe_resp,
- link, link_conf);
+ link, link_conf, &changed);
if (err < 0)
goto error;
- changed |= err;
err = drv_start_ap(sdata->local, sdata, link_conf);
if (err) {
@@ -1525,10 +1526,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
err = ieee80211_set_unsol_bcast_probe_resp(sdata,
¶ms->unsol_bcast_probe_resp,
- link, link_conf);
+ link, link_conf, &changed);
if (err < 0)
return err;
- changed |= err;
if (beacon->he_bss_color_valid &&
beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) {
From a0b4f2291319c5d47ecb196b90400814fdcfd126 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 31 Jan 2024 16:48:56 +0100
Subject: [PATCH 152/637] wifi: mac80211: fix waiting for beacons logic
This should be waiting if we don't have a beacon yet,
but somehow I managed to invert the logic. Fix that.
Fixes: 74e1309acedc ("wifi: mac80211: mlme: look up beacon elems only if needed")
Link: https://msgid.link/20240131164856.922701229546.I239b379e7cee04608e73c016b737a5245e5b23dd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/mlme.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f1cdd2df323e..12f67871af69 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8046,8 +8046,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
rcu_read_lock();
beacon_ies = rcu_dereference(req->bss->beacon_ies);
-
- if (beacon_ies) {
+ if (!beacon_ies) {
/*
* Wait up to one beacon interval ...
* should this be more if we miss one?
From c042600c17d8c490279f0ae2baee29475fe8047d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 31 Jan 2024 16:48:23 +0100
Subject: [PATCH 153/637] wifi: mac80211: adding missing drv_mgd_complete_tx()
call
There's a call to drv_mgd_prepare_tx() and so there should
be one to drv_mgd_complete_tx(), but on this path it's not.
Add it.
Link: https://msgid.link/20240131164824.2f0922a514e1.I5aac89b93bcead88c374187d70cad0599d29d2c8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/mlme.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 12f67871af69..2022a26eb881 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8127,6 +8127,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
ieee80211_report_disconnect(sdata, frame_buf,
sizeof(frame_buf), true,
req->reason_code, false);
+ drv_mgd_complete_tx(sdata->local, sdata, &info);
return 0;
}
From 62a6183c13319e4d2227473a04abd104c4f56dcf Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jan 2024 20:09:07 +0100
Subject: [PATCH 154/637] wifi: mac80211: accept broadcast probe responses on 6
GHz
On the 6 GHz band, probe responses are sent as broadcast to
optimise medium usage. However, without OCE configuration
we weren't accepting them, which is wrong, even if wpa_s is
by default enabling OCE. Accept them without the OCE config
as well.
Link: https://msgid.link/20240129200907.5a89c2821897.I92e9dfa0f9b350bc7f37dd4bb38031d156d78d8a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/scan.c | 30 ++++++++++++++++++------------
1 file changed, 18 insertions(+), 12 deletions(-)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 645355e5f1bc..f9d5842601fa 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2013-2015 Intel Mobile Communications GmbH
* Copyright 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*/
#include <linux/if_arp.h>
@@ -237,14 +237,18 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
}
static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_channel *channel,
u32 scan_flags, const u8 *da)
{
if (!sdata)
return false;
- /* accept broadcast for OCE */
- if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP &&
- is_broadcast_ether_addr(da))
+
+ /* accept broadcast on 6 GHz and for OCE */
+ if (is_broadcast_ether_addr(da) &&
+ (channel->band == NL80211_BAND_6GHZ ||
+ scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP))
return true;
+
if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR)
return true;
return ether_addr_equal(da, sdata->vif.addr);
@@ -293,6 +297,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0);
}
+ channel = ieee80211_get_channel_khz(local->hw.wiphy,
+ ieee80211_rx_status_to_khz(rx_status));
+
+ if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
+ return;
+
if (ieee80211_is_probe_resp(mgmt->frame_control)) {
struct cfg80211_scan_request *scan_req;
struct cfg80211_sched_scan_request *sched_scan_req;
@@ -310,19 +320,15 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
/* ignore ProbeResp to foreign address or non-bcast (OCE)
* unless scanning with randomised address
*/
- if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags,
+ if (!ieee80211_scan_accept_presp(sdata1, channel,
+ scan_req_flags,
mgmt->da) &&
- !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags,
+ !ieee80211_scan_accept_presp(sdata2, channel,
+ sched_scan_req_flags,
mgmt->da))
return;
}
- channel = ieee80211_get_channel_khz(local->hw.wiphy,
- ieee80211_rx_status_to_khz(rx_status));
-
- if (!channel || channel->flags & IEEE80211_CHAN_DISABLED)
- return;
-
bss = ieee80211_bss_info_update(local, rx_status,
mgmt, skb->len,
channel);
From fe92f874f09145a6951deacaa4961390238bbe0d Mon Sep 17 00:00:00 2001
From: Michael Lass <bevan@bi-co.net>
Date: Wed, 31 Jan 2024 16:52:20 +0100
Subject: [PATCH 155/637] net: Fix from address in memcpy_to_iter_csum()
While inlining csum_and_memcpy() into memcpy_to_iter_csum(), the from
address passed to csum_partial_copy_nocheck() was accidentally changed.
This causes a regression in applications using UDP, as for example
OpenAFS, causing loss of datagrams.
Fixes: dc32bff195b4 ("iov_iter, net: Fold in csum_and_memcpy()")
Cc: David Howells <dhowells@redhat.com>
Cc: stable@vger.kernel.org
Cc: regressions@lists.linux.dev
Signed-off-by: Michael Lass <bevan@bi-co.net>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/datagram.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 103d46fa0eeb..a8b625abe242 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
__wsum *csum = priv2;
- __wsum next = csum_partial_copy_nocheck(from, iter_to, len);
+ __wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
*csum = csum_block_add(*csum, next, progress);
return 0;
From 1fa942f31665ea5dc5d4d95893dd13723eaa97cc Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 28 Jan 2024 08:53:57 +0200
Subject: [PATCH 156/637] wifi: iwlwifi: mvm: fix a battery life regression
Fix the DBG_CONFIG_TOKEN to not enable debug components that would
prevent the device to save power.
Fixes: fc2fe0a5e856 ("wifi: iwlwifi: fw: disable firmware debug asserts")
Cc: stable@vger.kernel.org
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Eilon Rinat <eilon.rinat@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240128084842.90d2600edc27.Id657ea2f0ddb131f5f9d0ac39aeb8c88754fe54b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/fw/api/debug.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index 798731ecbefd..b740c65a7dca 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -537,7 +537,7 @@ enum iwl_fw_dbg_config_cmd_type {
}; /* LDBG_CFG_CMD_TYPE_API_E_VER_1 */
/* this token disables debug asserts in the firmware */
-#define IWL_FW_DBG_CONFIG_TOKEN 0x00011301
+#define IWL_FW_DBG_CONFIG_TOKEN 0x00010001
/**
* struct iwl_fw_dbg_config_cmd - configure FW debug
From 16867c38bcd3be2eb9016a3198a096f93959086e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 1 Feb 2024 16:17:39 +0200
Subject: [PATCH 157/637] wifi: iwlwifi: exit eSR only after the FW does
Currently the driver exits eSR by calling
iwl_mvm_esr_mode_inactive() before updating the FW
(by deactivating one of the links), and therefore before
sending the EML frame notifying that we are no longer in eSR.
This is wrong for several reasons:
1. The driver sends SMPS activation frames when we are still in eSR
and SMPS should be disabled when in eSR
2. The driver restores RLC configuration as it was before eSR
entering, and RLC command shouldn't be sent in eSR
Fix this by calling iwl_mvm_esr_mode_inactive() after FW update
Fixes: 12bacfc2c065 ("wifi: iwlwifi: handle eSR transitions")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://msgid.link/20240201155157.d8d9dc277d4e.Ib5aee0fd05e35b1da7f18753eb3c8fa0a3f872f3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 1f36e934ef69..893b69fc841b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -438,6 +438,9 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
mvmvif->ap_ibss_active = false;
}
+ iwl_mvm_link_changed(mvm, vif, link_conf,
+ LINK_CONTEXT_MODIFY_ACTIVE, false);
+
if (iwl_mvm_is_esr_supported(mvm->fwrt.trans) && n_active > 1) {
int ret = iwl_mvm_esr_mode_inactive(mvm, vif);
@@ -449,9 +452,6 @@ __iwl_mvm_mld_unassign_vif_chanctx(struct iwl_mvm *mvm,
if (vif->type == NL80211_IFTYPE_MONITOR)
iwl_mvm_mld_rm_snif_sta(mvm, vif);
- iwl_mvm_link_changed(mvm, vif, link_conf,
- LINK_CONTEXT_MODIFY_ACTIVE, false);
-
if (switching_chanctx)
return;
mvmvif->link[link_id]->phy_ctxt = NULL;
From a23c0af103e184bb1252dddddda040f6641bea7b Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Thu, 1 Feb 2024 16:17:30 +0200
Subject: [PATCH 158/637] wifi: iwlwifi: do not announce EPCS support
mac80211 does not have proper support for EPCS currently as that would
require changing the ECDA parameters if EPCS (Emergency Preparedness
Communications Service) is in use. As such, do not announce support for
it in the capabilities.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240201155157.59d71656addc.Idde91b3018239c49fc6ed231b411d05354fb9fb1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 402896988686..2f6774ec37b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -668,7 +668,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
.has_eht = true,
.eht_cap_elem = {
.mac_cap_info[0] =
- IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 |
@@ -793,7 +792,6 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
.has_eht = true,
.eht_cap_elem = {
.mac_cap_info[0] =
- IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2,
@@ -1020,8 +1018,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
if (CSR_HW_REV_TYPE(trans->hw_rev) == IWL_CFG_MAC_TYPE_GL &&
iftype_data->eht_cap.has_eht) {
iftype_data->eht_cap.eht_cap_elem.mac_cap_info[0] &=
- ~(IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
- IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
+ ~(IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2);
iftype_data->eht_cap.eht_cap_elem.phy_cap_info[3] &=
~(IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO |
From 7fddac12c38237252431d5b8af7b6d5771b6d125 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 2 Feb 2024 01:56:33 -0800
Subject: [PATCH 159/637] driver core: Fix
device_link_flag_is_sync_state_only()
device_link_flag_is_sync_state_only() correctly returns true on the flags
of an existing device link that only implements sync_state() functionality.
However, it incorrectly and confusingly returns false if it's called with
DL_FLAG_SYNC_STATE_ONLY.
This bug doesn't manifest in any of the existing calls to this function,
but fix this confusing behavior to avoid future bugs.
Fixes: 67cad5c67019 ("driver core: fw_devlink: Add DL_FLAG_CYCLE support to device links")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240202095636.868578-2-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/core.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 14d46af40f9a..52215c4c7209 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -284,10 +284,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target)
return false;
}
+#define DL_MARKER_FLAGS (DL_FLAG_INFERRED | \
+ DL_FLAG_CYCLE | \
+ DL_FLAG_MANAGED)
static inline bool device_link_flag_is_sync_state_only(u32 flags)
{
- return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) ==
- (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED);
+ return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY;
}
/**
From 6442d79d880cf7a2fff18779265d657fef0cce4c Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 2 Feb 2024 01:56:34 -0800
Subject: [PATCH 160/637] driver core: fw_devlink: Improve detection of
overlapping cycles
fw_devlink can detect most overlapping/intersecting cycles. However it was
missing a few corner cases because of an incorrect optimization logic that
tries to avoid repeating cycle detection for devices that are already
marked as part of a cycle.
Here's an example provided by Xu Yang (edited for clarity):
usb
+-----+
tcpc | |
+-----+ | +--|
| |----------->|EP|
|--+ | | +--|
|EP|<-----------| |
|--+ | | B |
| | +-----+
| A | |
+-----+ |
^ +-----+ |
| | | |
+-----| C |<--+
| |
+-----+
usb-phy
Node A (tcpc) will be populated as device 1-0050.
Node B (usb) will be populated as device 38100000.usb.
Node C (usb-phy) will be populated as device 381f0040.usb-phy.
The description below uses the notation:
consumer --> supplier
child ==> parent
1. Node C is populated as device C. No cycles detected because cycle
detection is only run when a fwnode link is converted to a device link.
2. Node B is populated as device B. As we convert B --> C into a device
link we run cycle detection and find and mark the device link/fwnode
link cycle:
C--> A --> B.EP ==> B --> C
3. Node A is populated as device A. As we convert C --> A into a device
link, we see it's already part of a cycle (from step 2) and don't run
cycle detection. Thus we miss detecting the cycle:
A --> B.EP ==> B --> A.EP ==> A
Looking at it another way, A depends on B in one way:
A --> B.EP ==> B
But B depends on A in two ways and we only detect the first:
B --> C --> A
B --> A.EP ==> A
To detect both of these, we remove the incorrect optimization attempt in
step 3 and run cycle detection even if the fwnode link from which the
device link is being created has already been marked as part of a cycle.
Reported-by: Xu Yang <xu.yang_2@nxp.com>
Closes: https://lore.kernel.org/lkml/DU2PR04MB8822693748725F85DC0CB86C8C792@DU2PR04MB8822.eurprd04.prod.outlook.com/
Fixes: 3fb16866b51d ("driver core: fw_devlink: Make cycle detection more robust")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240202095636.868578-3-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/core.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 52215c4c7209..e3d666461835 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2060,9 +2060,14 @@ static int fw_devlink_create_devlink(struct device *con,
/*
* SYNC_STATE_ONLY device links don't block probing and supports cycles.
- * So cycle detection isn't necessary and shouldn't be done.
+ * So, one might expect that cycle detection isn't necessary for them.
+ * However, if the device link was marked as SYNC_STATE_ONLY because
+ * it's part of a cycle, then we still need to do cycle detection. This
+ * is because the consumer and supplier might be part of multiple cycles
+ * and we need to detect all those cycles.
*/
- if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) {
+ if (!device_link_flag_is_sync_state_only(flags) ||
+ flags & DL_FLAG_CYCLE) {
device_links_write_lock();
if (__fw_devlink_relax_cycles(con, sup_handle)) {
__fwnode_link_cycle(link);
From 6e7ad1aebb4fc9fed0217dd50ef6e58a53f17d81 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Fri, 2 Feb 2024 01:56:35 -0800
Subject: [PATCH 161/637] driver core: fw_devlink: Improve logs for cycle
detection
The links in a cycle are not all logged in a consistent manner or not
logged at all. Make them consistent by adding a "cycle:" string and log all
the link in the cycles (even the child ==> parent dependency) so that it's
easier to debug cycle detection code. Also, mark the start and end of a
cycle so it's easy to tell when multiple cycles are logged back to back.
Signed-off-by: Saravana Kannan <saravanak@google.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20240202095636.868578-4-saravanak@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/core.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index e3d666461835..9828da9b933c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -125,7 +125,7 @@ static void __fwnode_link_del(struct fwnode_link *link)
*/
static void __fwnode_link_cycle(struct fwnode_link *link)
{
- pr_debug("%pfwf: Relaxing link with %pfwf\n",
+ pr_debug("%pfwf: cycle: depends on %pfwf\n",
link->consumer, link->supplier);
link->flags |= FWLINK_FLAG_CYCLE;
}
@@ -1945,6 +1945,7 @@ static bool __fw_devlink_relax_cycles(struct device *con,
/* Termination condition. */
if (sup_dev == con) {
+ pr_debug("----- cycle: start -----\n");
ret = true;
goto out;
}
@@ -1976,8 +1977,11 @@ static bool __fw_devlink_relax_cycles(struct device *con,
else
par_dev = fwnode_get_next_parent_dev(sup_handle);
- if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode))
+ if (par_dev && __fw_devlink_relax_cycles(con, par_dev->fwnode)) {
+ pr_debug("%pfwf: cycle: child of %pfwf\n", sup_handle,
+ par_dev->fwnode);
ret = true;
+ }
if (!sup_dev)
goto out;
@@ -1993,6 +1997,8 @@ static bool __fw_devlink_relax_cycles(struct device *con,
if (__fw_devlink_relax_cycles(con,
dev_link->supplier->fwnode)) {
+ pr_debug("%pfwf: cycle: depends on %pfwf\n", sup_handle,
+ dev_link->supplier->fwnode);
fw_devlink_relax_link(dev_link);
dev_link->flags |= DL_FLAG_CYCLE;
ret = true;
@@ -2072,6 +2078,7 @@ static int fw_devlink_create_devlink(struct device *con,
if (__fw_devlink_relax_cycles(con, sup_handle)) {
__fwnode_link_cycle(link);
flags = fw_devlink_get_flags(link->flags);
+ pr_debug("----- cycle: end -----\n");
dev_info(con, "Fixed dependency cycle(s) with %pfwf\n",
sup_handle);
}
From 5bdda0048c8d1bbe2019513b2d6200cc0d09c7bd Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 26 Jan 2024 14:31:53 -0800
Subject: [PATCH 162/637] wifi: brcmfmac: Adjust n_channels usage for
__counted_by
After commit e3eac9f32ec0 ("wifi: cfg80211: Annotate struct
cfg80211_scan_request with __counted_by"), the compiler may enforce
dynamic array indexing of req->channels to stay below n_channels. As a
result, n_channels needs to be increased _before_ accessing the newly
added array index. Increment it first, then use "i" for the prior index.
Solves this warning in the coming GCC that has __counted_by support:
../drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c: In function 'brcmf_internal_escan_add_info':
../drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c:3783:46: warning: operation on 'req->
n_channels' may be undefined [-Wsequence-point]
3783 | req->channels[req->n_channels++] = chan;
| ~~~~~~~~~~~~~~~^~
Fixes: e3eac9f32ec0 ("wifi: cfg80211: Annotate struct cfg80211_scan_request with __counted_by")
Cc: Arend van Spriel <aspriel@gmail.com>
Cc: Franky Lin <franky.lin@broadcom.com>
Cc: Hante Meuleman <hante.meuleman@broadcom.com>
Cc: Kalle Valo <kvalo@kernel.org>
Cc: Chi-hsien Lin <chi-hsien.lin@infineon.com>
Cc: Ian Lin <ian.lin@infineon.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Wright Feng <wright.feng@cypress.com>
Cc: Hector Martin <marcan@marcan.st>
Cc: linux-wireless@vger.kernel.org
Cc: brcm80211-dev-list.pdl@broadcom.com
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240126223150.work.548-kees@kernel.org
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 133c5ea6429c..28d6a30cc010 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -3779,8 +3779,10 @@ static int brcmf_internal_escan_add_info(struct cfg80211_scan_request *req,
if (req->channels[i] == chan)
break;
}
- if (i == req->n_channels)
- req->channels[req->n_channels++] = chan;
+ if (i == req->n_channels) {
+ req->n_channels++;
+ req->channels[i] = chan;
+ }
for (i = 0; i < req->n_ssids; i++) {
if (req->ssids[i].ssid_len == ssid_len &&
From de1034b38a346ef6be25fe8792f5d1e0684d5ff4 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@rivosinc.com>
Date: Fri, 2 Feb 2024 10:07:03 -0800
Subject: [PATCH 163/637] efi: runtime: Fix potential overflow of soft-reserved
region size
md_size will have been narrowed if we have >= 4GB worth of pages in a
soft-reserved region.
Signed-off-by: Andrew Bresticker <abrestic@rivosinc.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/arm-runtime.c | 2 +-
drivers/firmware/efi/riscv-runtime.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 83f5bb57fa4c..83092d93f36a 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void)
efi_memory_desc_t *md;
for_each_efi_memory_desc(md) {
- int md_size = md->num_pages << EFI_PAGE_SHIFT;
+ u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
struct resource *res;
if (!(md->attribute & EFI_MEMORY_SP))
diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c
index 09525fb5c240..01f0f90ea418 100644
--- a/drivers/firmware/efi/riscv-runtime.c
+++ b/drivers/firmware/efi/riscv-runtime.c
@@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void)
efi_memory_desc_t *md;
for_each_efi_memory_desc(md) {
- int md_size = md->num_pages << EFI_PAGE_SHIFT;
+ u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
struct resource *res;
if (!(md->attribute & EFI_MEMORY_SP))
From 0bcff59ef7a652fcdc6d535554b63278c2406c8f Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@rivosinc.com>
Date: Fri, 2 Feb 2024 10:07:04 -0800
Subject: [PATCH 164/637] efi: Don't add memblocks for soft-reserved memory
Adding memblocks for soft-reserved regions prevents them from later being
hotplugged in by dax_kmem.
Signed-off-by: Andrew Bresticker <abrestic@rivosinc.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/efi-init.c | 19 ++++++++++---------
1 file changed, 10 insertions(+), 9 deletions(-)
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index d4987d013080..a00e07b853f2 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -143,15 +143,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
case EFI_BOOT_SERVICES_DATA:
case EFI_CONVENTIONAL_MEMORY:
case EFI_PERSISTENT_MEMORY:
- /*
- * Special purpose memory is 'soft reserved', which means it
- * is set aside initially, but can be hotplugged back in or
- * be assigned to the dax driver after boot.
- */
- if (efi_soft_reserve_enabled() &&
- (md->attribute & EFI_MEMORY_SP))
- return false;
-
/*
* According to the spec, these regions are no longer reserved
* after calling ExitBootServices(). However, we can only use
@@ -196,6 +187,16 @@ static __init void reserve_regions(void)
size = npages << PAGE_SHIFT;
if (is_memory(md)) {
+ /*
+ * Special purpose memory is 'soft reserved', which
+ * means it is set aside initially. Don't add a memblock
+ * for it now so that it can be hotplugged back in or
+ * be assigned to the dax driver after boot.
+ */
+ if (efi_soft_reserve_enabled() &&
+ (md->attribute & EFI_MEMORY_SP))
+ continue;
+
early_init_dt_add_memory_arch(paddr, size);
if (!is_usable_memory(md))
From ba5e1272142d051dcc57ca1d3225ad8a089f9858 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 1 Feb 2024 17:53:24 +0000
Subject: [PATCH 165/637] netdevsim: avoid potential loop in
nsim_dev_trap_report_work()
Many syzbot reports include the following trace [1]
If nsim_dev_trap_report_work() can not grab the mutex,
it should rearm itself at least one jiffie later.
[1]
Sending NMI from CPU 1 to CPUs 0:
NMI backtrace for cpu 0
CPU: 0 PID: 32383 Comm: kworker/0:2 Not tainted 6.8.0-rc2-syzkaller-00031-g861c0981648f #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Workqueue: events nsim_dev_trap_report_work
RIP: 0010:bytes_is_nonzero mm/kasan/generic.c:89 [inline]
RIP: 0010:memory_is_nonzero mm/kasan/generic.c:104 [inline]
RIP: 0010:memory_is_poisoned_n mm/kasan/generic.c:129 [inline]
RIP: 0010:memory_is_poisoned mm/kasan/generic.c:161 [inline]
RIP: 0010:check_region_inline mm/kasan/generic.c:180 [inline]
RIP: 0010:kasan_check_range+0x101/0x190 mm/kasan/generic.c:189
Code: 07 49 39 d1 75 0a 45 3a 11 b8 01 00 00 00 7c 0b 44 89 c2 e8 21 ed ff ff 83 f0 01 5b 5d 41 5c c3 48 85 d2 74 4f 48 01 ea eb 09 <48> 83 c0 01 48 39 d0 74 41 80 38 00 74 f2 eb b6 41 bc 08 00 00 00
RSP: 0018:ffffc90012dcf998 EFLAGS: 00000046
RAX: fffffbfff258af1e RBX: fffffbfff258af1f RCX: ffffffff8168eda3
RDX: fffffbfff258af1f RSI: 0000000000000004 RDI: ffffffff92c578f0
RBP: fffffbfff258af1e R08: 0000000000000000 R09: fffffbfff258af1e
R10: ffffffff92c578f3 R11: ffffffff8acbcbc0 R12: 0000000000000002
R13: ffff88806db38400 R14: 1ffff920025b9f42 R15: ffffffff92c578e8
FS: 0000000000000000(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000c00994e078 CR3: 000000002c250000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<NMI>
</NMI>
<TASK>
instrument_atomic_read include/linux/instrumented.h:68 [inline]
atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
queued_spin_is_locked include/asm-generic/qspinlock.h:57 [inline]
debug_spin_unlock kernel/locking/spinlock_debug.c:101 [inline]
do_raw_spin_unlock+0x53/0x230 kernel/locking/spinlock_debug.c:141
__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:150 [inline]
_raw_spin_unlock_irqrestore+0x22/0x70 kernel/locking/spinlock.c:194
debug_object_activate+0x349/0x540 lib/debugobjects.c:726
debug_work_activate kernel/workqueue.c:578 [inline]
insert_work+0x30/0x230 kernel/workqueue.c:1650
__queue_work+0x62e/0x11d0 kernel/workqueue.c:1802
__queue_delayed_work+0x1bf/0x270 kernel/workqueue.c:1953
queue_delayed_work_on+0x106/0x130 kernel/workqueue.c:1989
queue_delayed_work include/linux/workqueue.h:563 [inline]
schedule_delayed_work include/linux/workqueue.h:677 [inline]
nsim_dev_trap_report_work+0x9c0/0xc80 drivers/net/netdevsim/dev.c:842
process_one_work+0x886/0x15d0 kernel/workqueue.c:2633
process_scheduled_works kernel/workqueue.c:2706 [inline]
worker_thread+0x8b9/0x1290 kernel/workqueue.c:2787
kthread+0x2c6/0x3a0 kernel/kthread.c:388
ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:242
</TASK>
Fixes: 012ec02ae441 ("netdevsim: convert driver to use unlocked devlink API during init/fini")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240201175324.3752746-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/netdevsim/dev.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b4d3b9cde8bd..92a7a36b93ac 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -835,14 +835,14 @@ static void nsim_dev_trap_report_work(struct work_struct *work)
trap_report_dw.work);
nsim_dev = nsim_trap_data->nsim_dev;
- /* For each running port and enabled packet trap, generate a UDP
- * packet with a random 5-tuple and report it.
- */
if (!devl_trylock(priv_to_devlink(nsim_dev))) {
- schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 0);
+ schedule_delayed_work(&nsim_dev->trap_data->trap_report_dw, 1);
return;
}
+ /* For each running port and enabled packet trap, generate a UDP
+ * packet with a random 5-tuple and report it.
+ */
list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) {
if (!netif_running(nsim_dev_port->ns->netdev))
continue;
From 05519c86d6997cfb9bb6c82ce1595d1015b718dc Mon Sep 17 00:00:00 2001
From: Mingwei Zhang <mizhang@google.com>
Date: Tue, 23 Jan 2024 22:12:20 +0000
Subject: [PATCH 166/637] KVM: x86/pmu: Fix type length error when reading
pmu->fixed_ctr_ctrl
Use a u64 instead of a u8 when taking a snapshot of pmu->fixed_ctr_ctrl
when reprogramming fixed counters, as truncating the value results in KVM
thinking fixed counter 2 is already disabled (the bug also affects fixed
counters 3+, but KVM doesn't yet support those). As a result, if the
guest disables fixed counter 2, KVM will get a false negative and fail to
reprogram/disable emulation of the counter, which can leads to incorrect
counts and spurious PMIs in the guest.
Fixes: 76d287b2342e ("KVM: x86/pmu: Drop "u8 ctrl, int idx" for reprogram_fixed_counter()")
Cc: stable@vger.kernel.org
Signed-off-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20240123221220.3911317-1-mizhang@google.com
[sean: rewrite changelog to call out the effects of the bug]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/vmx/pmu_intel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a6216c874729..315c7c2ba89b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
{
struct kvm_pmc *pmc;
- u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+ u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
int i;
pmu->fixed_ctr_ctrl = data;
From 2e7d3b67630dfd8f178c41fa2217aa00e79a5887 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 1 Feb 2024 10:47:51 +0100
Subject: [PATCH 167/637] net: atlantic: Fix DMA mapping for PTP hwts ring
Function aq_ring_hwts_rx_alloc() maps extra AQ_CFG_RXDS_DEF bytes
for PTP HWTS ring but then generic aq_ring_free() does not take this
into account.
Create and use a specific function to free HWTS ring to fix this
issue.
Trace:
[ 215.351607] ------------[ cut here ]------------
[ 215.351612] DMA-API: atlantic 0000:4b:00.0: device driver frees DMA memory with different size [device address=0x00000000fbdd0000] [map size=34816 bytes] [unmap size=32768 bytes]
[ 215.351635] WARNING: CPU: 33 PID: 10759 at kernel/dma/debug.c:988 check_unmap+0xa6f/0x2360
...
[ 215.581176] Call Trace:
[ 215.583632] <TASK>
[ 215.585745] ? show_trace_log_lvl+0x1c4/0x2df
[ 215.590114] ? show_trace_log_lvl+0x1c4/0x2df
[ 215.594497] ? debug_dma_free_coherent+0x196/0x210
[ 215.599305] ? check_unmap+0xa6f/0x2360
[ 215.603147] ? __warn+0xca/0x1d0
[ 215.606391] ? check_unmap+0xa6f/0x2360
[ 215.610237] ? report_bug+0x1ef/0x370
[ 215.613921] ? handle_bug+0x3c/0x70
[ 215.617423] ? exc_invalid_op+0x14/0x50
[ 215.621269] ? asm_exc_invalid_op+0x16/0x20
[ 215.625480] ? check_unmap+0xa6f/0x2360
[ 215.629331] ? mark_lock.part.0+0xca/0xa40
[ 215.633445] debug_dma_free_coherent+0x196/0x210
[ 215.638079] ? __pfx_debug_dma_free_coherent+0x10/0x10
[ 215.643242] ? slab_free_freelist_hook+0x11d/0x1d0
[ 215.648060] dma_free_attrs+0x6d/0x130
[ 215.651834] aq_ring_free+0x193/0x290 [atlantic]
[ 215.656487] aq_ptp_ring_free+0x67/0x110 [atlantic]
...
[ 216.127540] ---[ end trace 6467e5964dd2640b ]---
[ 216.132160] DMA-API: Mapped at:
[ 216.132162] debug_dma_alloc_coherent+0x66/0x2f0
[ 216.132165] dma_alloc_attrs+0xf5/0x1b0
[ 216.132168] aq_ring_hwts_rx_alloc+0x150/0x1f0 [atlantic]
[ 216.132193] aq_ptp_ring_alloc+0x1bb/0x540 [atlantic]
[ 216.132213] aq_nic_init+0x4a1/0x760 [atlantic]
Fixes: 94ad94558b0f ("net: aquantia: add PTP rings infrastructure")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240201094752.883026-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/aquantia/atlantic/aq_ptp.c | 4 ++--
drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 13 +++++++++++++
drivers/net/ethernet/aquantia/atlantic/aq_ring.h | 1 +
3 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
index abd4832e4ed2..5acb3e16b567 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
@@ -993,7 +993,7 @@ int aq_ptp_ring_alloc(struct aq_nic_s *aq_nic)
return 0;
err_exit_hwts_rx:
- aq_ring_free(&aq_ptp->hwts_rx);
+ aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
err_exit_ptp_rx:
aq_ring_free(&aq_ptp->ptp_rx);
err_exit_ptp_tx:
@@ -1011,7 +1011,7 @@ void aq_ptp_ring_free(struct aq_nic_s *aq_nic)
aq_ring_free(&aq_ptp->ptp_tx);
aq_ring_free(&aq_ptp->ptp_rx);
- aq_ring_free(&aq_ptp->hwts_rx);
+ aq_ring_hwts_rx_free(&aq_ptp->hwts_rx);
aq_ptp_skb_ring_release(&aq_ptp->skb_ring);
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index cda8597b4e14..f7433abd6591 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -919,6 +919,19 @@ void aq_ring_free(struct aq_ring_s *self)
}
}
+void aq_ring_hwts_rx_free(struct aq_ring_s *self)
+{
+ if (!self)
+ return;
+
+ if (self->dx_ring) {
+ dma_free_coherent(aq_nic_get_dev(self->aq_nic),
+ self->size * self->dx_size + AQ_CFG_RXDS_DEF,
+ self->dx_ring, self->dx_ring_pa);
+ self->dx_ring = NULL;
+ }
+}
+
unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
{
unsigned int count;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index 52847310740a..d627ace850ff 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -210,6 +210,7 @@ int aq_ring_rx_fill(struct aq_ring_s *self);
int aq_ring_hwts_rx_alloc(struct aq_ring_s *self,
struct aq_nic_s *aq_nic, unsigned int idx,
unsigned int size, unsigned int dx_size);
+void aq_ring_hwts_rx_free(struct aq_ring_s *self);
void aq_ring_hwts_rx_clean(struct aq_ring_s *self, struct aq_nic_s *aq_nic);
unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data);
From cb9f4a30fb85e1f4f149ada595a67899adb3db19 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:38 +0100
Subject: [PATCH 168/637] selftests: net: cut more slack for gro fwd tests.
The udpgro_fwd.sh self-tests are somewhat unstable. There are
a few timing constraints the we struggle to meet on very slow
environments.
Instead of skipping the whole tests in such envs, increase the
test resilience WRT very slow hosts: increase the inter-packets
timeouts, avoid resetting the counters every second and finally
disable reduce the background traffic noise.
Tested with:
for I in $(seq 1 100); do
./tools/testing/selftests/kselftest_install/run_kselftest.sh \
-t net:udpgro_fwd.sh || exit -1
done
in a slow environment.
Fixes: a062260a9d5f ("selftests: net: add UDP GRO forwarding self-tests")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/f4b6b11064a0d39182a9ae6a853abae3e9b4426a.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/udpgro_fwd.sh | 14 ++++++++++++--
tools/testing/selftests/net/udpgso_bench_rx.c | 2 +-
2 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index d6b9c759043c..9cd5e885e91f 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -39,6 +39,10 @@ create_ns() {
for ns in $NS_SRC $NS_DST; do
ip netns add $ns
ip -n $ns link set dev lo up
+
+ # disable route solicitations to decrease 'noise' traffic
+ ip netns exec $ns sysctl -qw net.ipv6.conf.default.router_solicitations=0
+ ip netns exec $ns sysctl -qw net.ipv6.conf.all.router_solicitations=0
done
ip link add name veth$SRC type veth peer name veth$DST
@@ -80,6 +84,12 @@ create_vxlan_pair() {
create_vxlan_endpoint $BASE$ns veth$ns $BM_NET_V6$((3 - $ns)) vxlan6$ns 6
ip -n $BASE$ns addr add dev vxlan6$ns $OL_NET_V6$ns/24 nodad
done
+
+ # preload neighbur cache, do avoid some noisy traffic
+ local addr_dst=$(ip -j -n $BASE$DST link show dev vxlan6$DST |jq -r '.[]["address"]')
+ local addr_src=$(ip -j -n $BASE$SRC link show dev vxlan6$SRC |jq -r '.[]["address"]')
+ ip -n $BASE$DST neigh add dev vxlan6$DST lladdr $addr_src $OL_NET_V6$SRC
+ ip -n $BASE$SRC neigh add dev vxlan6$SRC lladdr $addr_dst $OL_NET_V6$DST
}
is_ipv6() {
@@ -119,7 +129,7 @@ run_test() {
# not enable GRO
ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 4789
ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
- ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
+ ip netns exec $NS_DST ./udpgso_bench_rx -C 2000 -R 100 -n 10 -l 1300 $rx_args &
local spid=$!
wait_local_port_listen "$NS_DST" 8000 udp
ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
@@ -168,7 +178,7 @@ run_bench() {
# bind the sender and the receiver to different CPUs to try
# get reproducible results
ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
- ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10 &
+ ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 2000 -R 100 &
local spid=$!
wait_local_port_listen "$NS_DST" 8000 udp
ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index f35a924d4a30..1cbadd267c96 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -375,7 +375,7 @@ static void do_recv(void)
do_flush_udp(fd);
tnow = gettimeofday_ms();
- if (tnow > treport) {
+ if (!cfg_expected_pkt_nr && tnow > treport) {
if (packets)
fprintf(stderr,
"%s rx: %6lu MB/s %8lu calls/s\n",
From d75df752647728c6d65e594e5e4493448bea6cda Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:39 +0100
Subject: [PATCH 169/637] selftests: net: fix setup_ns usage in rtnetlink.sh
The setup_ns helper marks the testns global variable as
readonly. Later attempts to set such variable are unsuccessful,
causing a couple test failures.
Avoid completely the variable re-initialization and let the
function access the global value.
Fixes: e9ce7ededf14 ("selftests: rtnetlink: use setup_ns in bonding test")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/6e7c937c8ff73ca52a21a4a536a13a76ec0173a8.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/rtnetlink.sh | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 4667d74579d1..874a2952aa8e 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -440,7 +440,6 @@ kci_test_encap_vxlan()
local ret=0
vxlan="test-vxlan0"
vlan="test-vlan0"
- testns="$1"
run_cmd ip -netns "$testns" link add "$vxlan" type vxlan id 42 group 239.1.1.1 \
dev "$devdummy" dstport 4789
if [ $? -ne 0 ]; then
@@ -485,7 +484,6 @@ kci_test_encap_fou()
{
local ret=0
name="test-fou"
- testns="$1"
run_cmd_grep 'Usage: ip fou' ip fou help
if [ $? -ne 0 ];then
end_test "SKIP: fou: iproute2 too old"
@@ -526,8 +524,8 @@ kci_test_encap()
run_cmd ip -netns "$testns" link set lo up
run_cmd ip -netns "$testns" link add name "$devdummy" type dummy
run_cmd ip -netns "$testns" link set "$devdummy" up
- run_cmd kci_test_encap_vxlan "$testns"
- run_cmd kci_test_encap_fou "$testns"
+ run_cmd kci_test_encap_vxlan
+ run_cmd kci_test_encap_fou
ip netns del "$testns"
return $ret
From e71e016ad0f6e641a7898b8cda5f62f8e2beb2f1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:40 +0100
Subject: [PATCH 170/637] selftests: net: fix tcp listener handling in pmtu.sh
The pmtu.sh test uses a few TCP listener in a problematic way:
It hard-codes a constant timeout to wait for the listener starting-up
in background. That introduces unneeded latency and on very slow and
busy host it can fail.
Additionally the test starts again the same listener in the same
namespace on the same port, just after the previous connection
completed. Fast host can attempt starting the new server before the
old one really closed the socket.
Address the issues using the wait_local_port_listen helper and
explicitly waiting for the background listener process exit.
Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/f8e8f6d44427d8c45e9f6a71ee1a321047452087.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/pmtu.sh | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 3f118e3f1c66..f0febc19baae 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -199,6 +199,7 @@
# Same as above but with IPv6
source lib.sh
+source net_helper.sh
PAUSE_ON_FAIL=no
VERBOSE=0
@@ -1336,13 +1337,15 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
TCPDST="TCP:[${dst}]:50000"
fi
${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile &
+ local socat_pid=$!
- sleep 1
+ wait_local_port_listen ${NS_B} 50000 tcp
dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
size=$(du -sb $tmpoutfile)
size=${size%%/tmp/*}
+ wait ${socat_pid}
[ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1
done
From 691bb4e49c98a47bc643dd808453136ce78b15b4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 1 Feb 2024 19:42:41 +0100
Subject: [PATCH 171/637] selftests: net: avoid just another constant wait
Using hard-coded constant timeout to wait for some expected
event is deemed to fail sooner or later, especially in slow
env.
Our CI has spotted another of such race:
# TEST: ipv6: cleanup of cached exceptions - nexthop objects [FAIL]
# can't delete veth device in a timely manner, PMTU dst likely leaked
Replace the crude sleep with a loop looking for the expected condition
at low interval for a much longer range.
Fixes: b3cc4f8a8a41 ("selftests: pmtu: add explicit tests for PMTU exceptions cleanup")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/fd5c745e9bb665b724473af6a9373a8c2a62b247.1706812005.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/pmtu.sh | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f0febc19baae..d65fdd407d73 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1957,6 +1957,13 @@ check_command() {
return 0
}
+check_running() {
+ pid=${1}
+ cmd=${2}
+
+ [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ]
+}
+
test_cleanup_vxlanX_exception() {
outer="${1}"
encap="vxlan"
@@ -1987,11 +1994,12 @@ test_cleanup_vxlanX_exception() {
${ns_a} ip link del dev veth_A-R1 &
iplink_pid=$!
- sleep 1
- if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then
- err " can't delete veth device in a timely manner, PMTU dst likely leaked"
- return 1
- fi
+ for i in $(seq 1 20); do
+ check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0
+ sleep 0.1
+ done
+ err " can't delete veth device in a timely manner, PMTU dst likely leaked"
+ return 1
}
test_cleanup_ipv6_exception() {
From d7f5fb33cf77247b7bf9a871aaeea72ca4f51ad7 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 31 Jan 2024 21:14:13 +0100
Subject: [PATCH 172/637] tsnep: Fix mapping for zero copy XDP_TX action
For XDP_TX action xdp_buff is converted to xdp_frame. The conversion is
done by xdp_convert_buff_to_frame(). The memory type of the resulting
xdp_frame depends on the memory type of the xdp_buff. For page pool
based xdp_buff it produces xdp_frame with memory type
MEM_TYPE_PAGE_POOL. For zero copy XSK pool based xdp_buff it produces
xdp_frame with memory type MEM_TYPE_PAGE_ORDER0.
tsnep_xdp_xmit_back() is not prepared for that and uses always the page
pool buffer type TSNEP_TX_TYPE_XDP_TX. This leads to invalid mappings
and the transmission of undefined data.
Improve tsnep_xdp_xmit_back() to use the generic buffer type
TSNEP_TX_TYPE_XDP_NDO for zero copy XDP_TX.
Fixes: 3fc2333933fd ("tsnep: Add XDP socket zero-copy RX support")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/engleder/tsnep_main.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 9aeff2b37a61..64eadd320798 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -719,17 +719,25 @@ static void tsnep_xdp_xmit_flush(struct tsnep_tx *tx)
static bool tsnep_xdp_xmit_back(struct tsnep_adapter *adapter,
struct xdp_buff *xdp,
- struct netdev_queue *tx_nq, struct tsnep_tx *tx)
+ struct netdev_queue *tx_nq, struct tsnep_tx *tx,
+ bool zc)
{
struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp);
bool xmit;
+ u32 type;
if (unlikely(!xdpf))
return false;
+ /* no page pool for zero copy */
+ if (zc)
+ type = TSNEP_TX_TYPE_XDP_NDO;
+ else
+ type = TSNEP_TX_TYPE_XDP_TX;
+
__netif_tx_lock(tx_nq, smp_processor_id());
- xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, TSNEP_TX_TYPE_XDP_TX);
+ xmit = tsnep_xdp_xmit_frame_ring(xdpf, tx, type);
/* Avoid transmit queue timeout since we share it with the slow path */
if (xmit)
@@ -1273,7 +1281,7 @@ static bool tsnep_xdp_run_prog(struct tsnep_rx *rx, struct bpf_prog *prog,
case XDP_PASS:
return false;
case XDP_TX:
- if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+ if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, false))
goto out_failure;
*status |= TSNEP_XDP_TX;
return true;
@@ -1323,7 +1331,7 @@ static bool tsnep_xdp_run_prog_zc(struct tsnep_rx *rx, struct bpf_prog *prog,
case XDP_PASS:
return false;
case XDP_TX:
- if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx))
+ if (!tsnep_xdp_xmit_back(rx->adapter, xdp, tx_nq, tx, true))
goto out_failure;
*status |= TSNEP_XDP_TX;
return true;
From d75abeec401f8c86b470e7028a13fcdc87e5dd06 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Thu, 1 Feb 2024 09:38:15 +0100
Subject: [PATCH 173/637] tunnels: fix out of bounds access when building IPv6
PMTU error
If the ICMPv6 error is built from a non-linear skb we get the following
splat,
BUG: KASAN: slab-out-of-bounds in do_csum+0x220/0x240
Read of size 4 at addr ffff88811d402c80 by task netperf/820
CPU: 0 PID: 820 Comm: netperf Not tainted 6.8.0-rc1+ #543
...
kasan_report+0xd8/0x110
do_csum+0x220/0x240
csum_partial+0xc/0x20
skb_tunnel_check_pmtu+0xeb9/0x3280
vxlan_xmit_one+0x14c2/0x4080
vxlan_xmit+0xf61/0x5c00
dev_hard_start_xmit+0xfb/0x510
__dev_queue_xmit+0x7cd/0x32a0
br_dev_queue_push_xmit+0x39d/0x6a0
Use skb_checksum instead of csum_partial who cannot deal with non-linear
SKBs.
Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/ip_tunnel_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 586b1b3e35b8..80ccd6661aa3 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
};
skb_reset_network_header(skb);
- csum = csum_partial(icmp6h, len, 0);
+ csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
IPPROTO_ICMPV6, csum);
From f3616173bf9be9bf39d131b120d6eea4e6324cb5 Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Thu, 1 Feb 2024 20:41:05 +0800
Subject: [PATCH 174/637] atm: idt77252: fix a memleak in open_card_ubr0
When alloc_scq fails, card->vcs[0] (i.e. vc) should be freed. Otherwise,
in the following call chain:
idt77252_init_one
|-> idt77252_dev_open
|-> open_card_ubr0
|-> alloc_scq [failed]
|-> deinit_card
|-> vfree(card->vcs);
card->vcs is freed and card->vcs[0] is leaked.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/atm/idt77252.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index e327a0229dc1..e7f713cd70d3 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2930,6 +2930,8 @@ open_card_ubr0(struct idt77252_dev *card)
vc->scq = alloc_scq(card, vc->class);
if (!vc->scq) {
printk("%s: can't get SCQ.\n", card->name);
+ kfree(card->vcs[0]);
+ card->vcs[0] = NULL;
return -ENOMEM;
}
From b09b58e31b0f43d76f79b9943da3fb7c2843dcbb Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Thu, 1 Feb 2024 20:47:13 +0800
Subject: [PATCH 175/637] octeontx2-pf: Fix a memleak otx2_sq_init
When qmem_alloc and pfvf->hw_ops->sq_aq_init fails, sq->sg should be
freed to prevent memleak.
Fixes: c9c12d339d93 ("octeontx2-pf: Add support for PTP clock")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../ethernet/marvell/octeontx2/nic/otx2_common.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7ca6941ea0b9..02d0b707aea5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -951,8 +951,11 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
if (pfvf->ptp && qidx < pfvf->hw.tx_queues) {
err = qmem_alloc(pfvf->dev, &sq->timestamps, qset->sqe_cnt,
sizeof(*sq->timestamps));
- if (err)
+ if (err) {
+ kfree(sq->sg);
+ sq->sg = NULL;
return err;
+ }
}
sq->head = 0;
@@ -968,7 +971,14 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
sq->stats.bytes = 0;
sq->stats.pkts = 0;
- return pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+ err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura);
+ if (err) {
+ kfree(sq->sg);
+ sq->sg = NULL;
+ return err;
+ }
+
+ return 0;
}
From 54ce1927eb787f7bbb7ee664841c8f5932703f39 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 31 Jan 2024 15:55:38 -0800
Subject: [PATCH 176/637] cxl/cper: Fix errant CPER prints for CXL events
Jonathan reports that CXL CPER events dump an extra generic error
message.
{1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 1
{1}[Hardware Error]: event severity: recoverable
{1}[Hardware Error]: Error 0, type: recoverable
{1}[Hardware Error]: section type: unknown, fbcd0a77-c260-417f-85a9-088b1621eba6
{1}[Hardware Error]: section length: 0x90
{1}[Hardware Error]: 00000000: 00000090 00000007 00000000 0d938086 ................
{1}[Hardware Error]: 00000010: 00100000 00000000 00040000 00000000 ................
...
CXL events were rerouted though the CXL subsystem for additional
processing. However, when that work was done it was missed that
cper_estatus_print_section() continued with a generic error message
which is confusing.
Teach CPER print code to ignore printing details of some section types.
Assign the CXL event GUIDs to this set to prevent confusing unknown
prints.
Reported-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Suggested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/acpi/apei/ghes.c | 26 --------------------------
drivers/firmware/efi/cper.c | 19 +++++++++++++++++++
include/linux/cper.h | 23 +++++++++++++++++++++++
3 files changed, 42 insertions(+), 26 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7b7c605166e0..fe825a432c5b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -680,32 +680,6 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
static DECLARE_RWSEM(cxl_cper_rw_sem);
static cxl_cper_callback cper_callback;
-/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
-
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CPER_SEC_CXL_GEN_MEDIA_GUID \
- GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \
- 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
-
-/*
- * DRAM Event Record
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
- */
-#define CPER_SEC_CXL_DRAM_GUID \
- GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \
- 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-#define CPER_SEC_CXL_MEM_MODULE_GUID \
- GUID_INIT(0xfe927475, 0xdd59, 0x4339, \
- 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
-
static void cxl_cper_post_event(enum cxl_event_type event_type,
struct cxl_cper_event_rec *rec)
{
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 35c37f667781..9b3884ff81e6 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx,
}
}
+struct ignore_section {
+ guid_t guid;
+ const char *name;
+};
+
+static const struct ignore_section ignore_sections[] = {
+ { .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" },
+ { .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" },
+ { .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" },
+};
+
static void
cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata,
int sec_no)
@@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
+
+ for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) {
+ if (guid_equal(sec_type, &ignore_sections[i].guid)) {
+ printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name);
+ return;
+ }
+ }
+
if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c1a7dc325121..265b0f8fc0b3 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -90,6 +90,29 @@ enum {
GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \
0x72, 0x2D, 0xEB, 0x41)
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID \
+ GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \
+ 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID \
+ GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \
+ 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID \
+ GUID_INIT(0xfe927475, 0xdd59, 0x4339, \
+ 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
/*
* Flags bits definitions for flags in struct cper_record_header
* If set, the error has been recovered
From dbea519d6878c298dd0f48e6ec2dbacebe4bbb2a Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 31 Jan 2024 15:55:39 -0800
Subject: [PATCH 177/637] cxl/trace: Remove unnecessary memcpy's
CPER events don't have UUIDs. Therefore UUIDs were removed from the
records passed to trace events and replaced with hard coded values.
As pointed out by Jonathan, the new defines for the UUIDs present a more
efficient way to assign UUID in trace records.[1]
Replace memcpy's with the use of static data.
[1] https://lore.kernel.org/all/20240108132325.00000e9c@Huawei.com/
Suggested-by: Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/cxl/core/trace.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 89445435303a..bdf117a33744 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -338,7 +338,7 @@ TRACE_EVENT(cxl_general_media,
TP_fast_assign(
CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
- memcpy(&__entry->hdr_uuid, &CXL_EVENT_GEN_MEDIA_UUID, sizeof(uuid_t));
+ __entry->hdr_uuid = CXL_EVENT_GEN_MEDIA_UUID;
/* General Media */
__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -425,7 +425,7 @@ TRACE_EVENT(cxl_dram,
TP_fast_assign(
CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
- memcpy(&__entry->hdr_uuid, &CXL_EVENT_DRAM_UUID, sizeof(uuid_t));
+ __entry->hdr_uuid = CXL_EVENT_DRAM_UUID;
/* DRAM */
__entry->dpa = le64_to_cpu(rec->phys_addr);
@@ -573,7 +573,7 @@ TRACE_EVENT(cxl_memory_module,
TP_fast_assign(
CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
- memcpy(&__entry->hdr_uuid, &CXL_EVENT_MEM_MODULE_UUID, sizeof(uuid_t));
+ __entry->hdr_uuid = CXL_EVENT_MEM_MODULE_UUID;
/* Memory Module Event */
__entry->event_type = rec->event_type;
From 42dfa94d802a48c871e2017cbf86153270c86632 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 4 Feb 2024 16:43:05 +0900
Subject: [PATCH 178/637] KVM: arm64: Do not source virt/lib/Kconfig twice
For ARCH=arm64, virt/lib/Kconfig is sourced twice,
from arch/arm64/kvm/Kconfig and from drivers/vfio/Kconfig.
There is no good reason to parse virt/lib/Kconfig twice.
Commit 2412405b3141 ("KVM: arm/arm64: register irq bypass consumer
on ARM/ARM64") should not have added this 'source' directive.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240204074305.31492-1-masahiroy@kernel.org
---
arch/arm64/kvm/Kconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 6c3c8ca73e7f..27ca89b628a0 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -3,7 +3,6 @@
# KVM configuration
#
-source "virt/lib/Kconfig"
source "virt/kvm/Kconfig"
menuconfig VIRTUALIZATION
From 9cae43da9867412f8bd09aee5c8a8dc5e8dc3dc2 Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Thu, 1 Feb 2024 20:40:38 -0800
Subject: [PATCH 179/637] hv_netvsc: Register VF in netvsc_probe if
NET_DEVICE_REGISTER missed
If hv_netvsc driver is unloaded and reloaded, the NET_DEVICE_REGISTER
handler cannot perform VF register successfully as the register call
is received before netvsc_probe is finished. This is because we
register register_netdevice_notifier() very early( even before
vmbus_driver_register()).
To fix this, we try to register each such matching VF( if it is visible
as a netdevice) at the end of netvsc_probe.
Cc: stable@vger.kernel.org
Fixes: 85520856466e ("hv_netvsc: Fix race of register_netdevice_notifier and VF register")
Suggested-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/hyperv/netvsc_drv.c | 82 +++++++++++++++++++++++++--------
1 file changed, 62 insertions(+), 20 deletions(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 273bd8a20122..11831a1c9762 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -42,6 +42,10 @@
#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE 1
+#define VF_REG_IN_NOTIFIER 2
+
static unsigned int ring_size __ro_after_init = 128;
module_param(ring_size, uint, 0444);
MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
@@ -2185,7 +2189,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
}
static int netvsc_vf_join(struct net_device *vf_netdev,
- struct net_device *ndev)
+ struct net_device *ndev, int context)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
int ret;
@@ -2208,7 +2212,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
goto upper_link_failed;
}
- schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+ /* If this registration is called from probe context vf_takeover
+ * is taken care of later in probe itself.
+ */
+ if (context == VF_REG_IN_NOTIFIER)
+ schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
@@ -2346,7 +2354,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
return NOTIFY_DONE;
}
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
{
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
@@ -2386,7 +2394,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
- if (netvsc_vf_join(vf_netdev, ndev) != 0)
+ if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
return NOTIFY_DONE;
dev_hold(vf_netdev);
@@ -2484,10 +2492,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
return NOTIFY_OK;
}
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+ /* Skip NetVSC interfaces */
+ if (event_ndev->netdev_ops == &device_ops)
+ return -ENODEV;
+
+ /* Avoid non-Ethernet type devices */
+ if (event_ndev->type != ARPHRD_ETHER)
+ return -ENODEV;
+
+ /* Avoid Vlan dev with same MAC registering as VF */
+ if (is_vlan_dev(event_ndev))
+ return -ENODEV;
+
+ /* Avoid Bonding master dev with same MAC registering as VF */
+ if (netif_is_bond_master(event_ndev))
+ return -ENODEV;
+
+ return 0;
+}
+
static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id)
{
- struct net_device *net = NULL;
+ struct net_device *net = NULL, *vf_netdev;
struct net_device_context *net_device_ctx;
struct netvsc_device_info *device_info = NULL;
struct netvsc_device *nvdev;
@@ -2599,6 +2628,30 @@ static int netvsc_probe(struct hv_device *dev,
}
list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+ /* When the hv_netvsc driver is unloaded and reloaded, the
+ * NET_DEVICE_REGISTER for the vf device is replayed before probe
+ * is complete. This is because register_netdevice_notifier() gets
+ * registered before vmbus_driver_register() so that callback func
+ * is set before probe and we don't miss events like NETDEV_POST_INIT
+ * So, in this section we try to register the matching vf device that
+ * is present as a netdevice, knowing that its register call is not
+ * processed in the netvsc_netdev_notifier(as probing is progress and
+ * get_netvsc_byslot fails).
+ */
+ for_each_netdev(dev_net(net), vf_netdev) {
+ ret = check_dev_is_matching_vf(vf_netdev);
+ if (ret != 0)
+ continue;
+
+ if (net != get_netvsc_byslot(vf_netdev))
+ continue;
+
+ netvsc_prepare_bonding(vf_netdev);
+ netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+ __netvsc_vf_setup(net, vf_netdev);
+ break;
+ }
rtnl_unlock();
netvsc_devinfo_put(device_info);
@@ -2754,28 +2807,17 @@ static int netvsc_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+ int ret = 0;
- /* Skip our own events */
- if (event_dev->netdev_ops == &device_ops)
- return NOTIFY_DONE;
-
- /* Avoid non-Ethernet type devices */
- if (event_dev->type != ARPHRD_ETHER)
- return NOTIFY_DONE;
-
- /* Avoid Vlan dev with same MAC registering as VF */
- if (is_vlan_dev(event_dev))
- return NOTIFY_DONE;
-
- /* Avoid Bonding master dev with same MAC registering as VF */
- if (netif_is_bond_master(event_dev))
+ ret = check_dev_is_matching_vf(event_dev);
+ if (ret != 0)
return NOTIFY_DONE;
switch (event) {
case NETDEV_POST_INIT:
return netvsc_prepare_bonding(event_dev);
case NETDEV_REGISTER:
- return netvsc_register_vf(event_dev);
+ return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
case NETDEV_UNREGISTER:
return netvsc_unregister_vf(event_dev);
case NETDEV_UP:
From 621c6257128149e45b36ffb973a01c3f3461b893 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Sun, 4 Feb 2024 04:56:17 -0800
Subject: [PATCH 180/637] iio: hid-sensor-als: Return 0 for
HID_USAGE_SENSOR_TIME_TIMESTAMP
When als_capture_sample() is called with usage ID
HID_USAGE_SENSOR_TIME_TIMESTAMP, return 0. The HID sensor core ignores
the return value for capture_sample() callback, so return value doesn't
make difference. But correct the return value to return success instead
of -EINVAL.
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20240204125617.2635574-1-srinivas.pandruvada@linux.intel.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/light/hid-sensor-als.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index 5cd27f04b45e..b6c4bef2a7bb 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -226,6 +226,7 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
case HID_USAGE_SENSOR_TIME_TIMESTAMP:
als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
*(s64 *)raw_data);
+ ret = 0;
break;
default:
break;
From 1168491e7f53581ba7b6014a39a49cfbbb722feb Mon Sep 17 00:00:00 2001
From: Loic Prylli <lprylli@netflix.com>
Date: Fri, 3 Nov 2023 11:30:55 +0100
Subject: [PATCH 181/637] hwmon: (aspeed-pwm-tacho) mutex for tach reading
the ASPEED_PTCR_RESULT Register can only hold the result for a
single fan input. Adding a mutex to protect the register until the
reading is done.
Signed-off-by: Loic Prylli <lprylli@netflix.com>
Signed-off-by: Alexander Hansen <alexander.hansen@9elements.com>
Fixes: 2d7a548a3eff ("drivers: hwmon: Support for ASPEED PWM/Fan tach")
Link: https://lore.kernel.org/r/121d888762a1232ef403cf35230ccf7b3887083a.1699007401.git.alexander.hansen@9elements.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
drivers/hwmon/aspeed-pwm-tacho.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c
index f6e1e55e8292..4acc1858d8ac 100644
--- a/drivers/hwmon/aspeed-pwm-tacho.c
+++ b/drivers/hwmon/aspeed-pwm-tacho.c
@@ -195,6 +195,8 @@ struct aspeed_pwm_tacho_data {
u8 fan_tach_ch_source[MAX_ASPEED_FAN_TACH_CHANNELS];
struct aspeed_cooling_device *cdev[8];
const struct attribute_group *groups[3];
+ /* protects access to shared ASPEED_PTCR_RESULT */
+ struct mutex tach_lock;
};
enum type { TYPEM, TYPEN, TYPEO };
@@ -529,6 +531,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
u8 fan_tach_ch_source, type, mode, both;
int ret;
+ mutex_lock(&priv->tach_lock);
+
regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
@@ -546,6 +550,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
ASPEED_RPM_STATUS_SLEEP_USEC,
usec);
+ mutex_unlock(&priv->tach_lock);
+
/* return -ETIMEDOUT if we didn't get an answer. */
if (ret)
return ret;
@@ -915,6 +921,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
+ mutex_init(&priv->tach_lock);
priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
&aspeed_pwm_tacho_regmap_config);
if (IS_ERR(priv->regmap))
From 4e440abc894585a34c2904a32cd54af1742311b3 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:34 +0800
Subject: [PATCH 182/637] hwmon: (coretemp) Fix out-of-bounds memory access
Fix a bug that pdata->cpu_map[] is set before out-of-bounds check.
The problem might be triggered on systems with more than 128 cores per
package.
Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240202092144.71180-2-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
drivers/hwmon/coretemp.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ba82d1e79c13..e78c76919111 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -509,18 +509,14 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
if (pkg_flag) {
attr_no = PKG_SYSFS_ATTR_NO;
} else {
- index = ida_alloc(&pdata->ida, GFP_KERNEL);
+ index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
if (index < 0)
return index;
+
pdata->cpu_map[index] = topology_core_id(cpu);
attr_no = index + BASE_SYSFS_ATTR_NO;
}
- if (attr_no > MAX_CORE_DATA - 1) {
- err = -ERANGE;
- goto ida_free;
- }
-
tdata = init_temp_data(cpu, pkg_flag);
if (!tdata) {
err = -ENOMEM;
From fdaf0c8629d4524a168cb9e4ad4231875749b28c Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:35 +0800
Subject: [PATCH 183/637] hwmon: (coretemp) Fix bogus core_id to attr name
mapping
Before commit 7108b80a542b ("hwmon/coretemp: Handle large core ID
value"), there is a fixed mapping between
1. cpu_core_id
2. the index in pdata->core_data[] array
3. the sysfs attr name, aka "tempX_"
The later two always equal cpu_core_id + 2.
After the commit, pdata->core_data[] index is got from ida so that it
can handle sparse core ids and support more cores within a package.
However, the commit erroneously maps the sysfs attr name to
pdata->core_data[] index instead of cpu_core_id + 2.
As a result, the code is not aligned with the comments, and brings user
visible changes in hwmon sysfs on systems with sparse core id.
For example, before commit 7108b80a542b ("hwmon/coretemp: Handle large
core ID value"),
/sys/class/hwmon/hwmon2/temp2_label:Core 0
/sys/class/hwmon/hwmon2/temp3_label:Core 1
/sys/class/hwmon/hwmon2/temp4_label:Core 2
/sys/class/hwmon/hwmon2/temp5_label:Core 3
/sys/class/hwmon/hwmon2/temp6_label:Core 4
/sys/class/hwmon/hwmon3/temp10_label:Core 8
/sys/class/hwmon/hwmon3/temp11_label:Core 9
after commit,
/sys/class/hwmon/hwmon2/temp2_label:Core 0
/sys/class/hwmon/hwmon2/temp3_label:Core 1
/sys/class/hwmon/hwmon2/temp4_label:Core 2
/sys/class/hwmon/hwmon2/temp5_label:Core 3
/sys/class/hwmon/hwmon2/temp6_label:Core 4
/sys/class/hwmon/hwmon2/temp7_label:Core 8
/sys/class/hwmon/hwmon2/temp8_label:Core 9
Restore the previous behavior and rework the code, comments and variable
names to avoid future confusions.
Fixes: 7108b80a542b ("hwmon/coretemp: Handle large core ID value")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20240202092144.71180-3-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
drivers/hwmon/coretemp.c | 32 +++++++++++++++++++-------------
1 file changed, 19 insertions(+), 13 deletions(-)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index e78c76919111..95f4c0b00b2d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -419,7 +419,7 @@ static ssize_t show_temp(struct device *dev,
}
static int create_core_attrs(struct temp_data *tdata, struct device *dev,
- int attr_no)
+ int index)
{
int i;
static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
@@ -431,13 +431,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
};
for (i = 0; i < tdata->attr_size; i++) {
+ /*
+ * We map the attr number to core id of the CPU
+ * The attr number is always core id + 2
+ * The Pkgtemp will always show up as temp1_*, if available
+ */
+ int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2;
+
snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH,
"temp%d_%s", attr_no, suffixes[i]);
sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
tdata->sd_attrs[i].dev_attr.attr.mode = 0444;
tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
- tdata->sd_attrs[i].index = attr_no;
+ tdata->sd_attrs[i].index = index;
tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr;
}
tdata->attr_group.attrs = tdata->attrs;
@@ -495,26 +502,25 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
struct platform_data *pdata = platform_get_drvdata(pdev);
struct cpuinfo_x86 *c = &cpu_data(cpu);
u32 eax, edx;
- int err, index, attr_no;
+ int err, index;
if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
return 0;
/*
- * Find attr number for sysfs:
- * We map the attr number to core id of the CPU
- * The attr number is always core id + 2
- * The Pkgtemp will always show up as temp1_*, if available
+ * Get the index of tdata in pdata->core_data[]
+ * tdata for package: pdata->core_data[1]
+ * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1]
*/
if (pkg_flag) {
- attr_no = PKG_SYSFS_ATTR_NO;
+ index = PKG_SYSFS_ATTR_NO;
} else {
index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL);
if (index < 0)
return index;
pdata->cpu_map[index] = topology_core_id(cpu);
- attr_no = index + BASE_SYSFS_ATTR_NO;
+ index += BASE_SYSFS_ATTR_NO;
}
tdata = init_temp_data(cpu, pkg_flag);
@@ -540,20 +546,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
if (get_ttarget(tdata, &pdev->dev) >= 0)
tdata->attr_size++;
- pdata->core_data[attr_no] = tdata;
+ pdata->core_data[index] = tdata;
/* Create sysfs interfaces */
- err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no);
+ err = create_core_attrs(tdata, pdata->hwmon_dev, index);
if (err)
goto exit_free;
return 0;
exit_free:
- pdata->core_data[attr_no] = NULL;
+ pdata->core_data[index] = NULL;
kfree(tdata);
ida_free:
if (!pkg_flag)
- ida_free(&pdata->ida, index);
+ ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO);
return err;
}
From 34cf8c657cf0365791cdc658ddbca9cc907726ce Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Fri, 2 Feb 2024 17:21:36 +0800
Subject: [PATCH 184/637] hwmon: (coretemp) Enlarge per package core count
limit
Currently, coretemp driver supports only 128 cores per package.
This loses some core temperature information on systems that have more
than 128 cores per package.
[ 58.685033] coretemp coretemp.0: Adding Core 128 failed
[ 58.692009] coretemp coretemp.0: Adding Core 129 failed
...
Enlarge the limitation to 512 because there are platforms with more than
256 cores per package.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20240202092144.71180-4-rui.zhang@intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
drivers/hwmon/coretemp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 95f4c0b00b2d..b8fc8d1ef20d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -41,7 +41,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
#define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */
#define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */
-#define NUM_REAL_CORES 128 /* Number of Real cores per cpu */
+#define NUM_REAL_CORES 512 /* Number of Real cores per cpu */
#define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */
#define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */
#define TOTAL_ATTRS (MAX_CORE_ATTRS + 1)
From 862cf85fef85becc55a173387527adb4f076fab0 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Wed, 31 Jan 2024 10:16:47 +0100
Subject: [PATCH 185/637] iio: commom: st_sensors: ensure proper DMA alignment
Aligning the buffer to the L1 cache is not sufficient in some platforms
as they might have larger cacheline sizes for caches after L1 and thus,
we can't guarantee DMA safety.
That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same
for st_sensors common buffer.
While at it, moved the odr_lock before buffer_data as we definitely
don't want any other data to share a cacheline with the buffer.
[1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/
Fixes: e031d5f558f1 ("iio:st_sensors: remove buffer allocation at each buffer enable")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Cc: <Stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240131-dev_dma_safety_stm-v2-1-580c07fae51b@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
include/linux/iio/common/st_sensors.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 607c3a89a647..f9ae5cdd884f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -258,9 +258,9 @@ struct st_sensor_data {
bool hw_irq_trigger;
s64 hw_timestamp;
- char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
-
struct mutex odr_lock;
+
+ char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN);
};
#ifdef CONFIG_IIO_BUFFER
From 4cb81840d8f29b66d9d05c6d7f360c9560f7e2f4 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 31 Jan 2024 16:52:46 -0600
Subject: [PATCH 186/637] iio: accel: bma400: Fix a compilation problem
The kernel fails when compiling without `CONFIG_REGMAP_I2C` but with
`CONFIG_BMA400`.
```
ld: drivers/iio/accel/bma400_i2c.o: in function `bma400_i2c_probe':
bma400_i2c.c:(.text+0x23): undefined reference to `__devm_regmap_init_i2c'
```
Link: https://download.01.org/0day-ci/archive/20240131/202401311634.FE5CBVwe-lkp@intel.com/config
Fixes: 465c811f1f20 ("iio: accel: Add driver for the BMA400")
Fixes: 9bea10642396 ("iio: accel: bma400: add support for bma400 spi")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20240131225246.14169-1-mario.limonciello@amd.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/accel/Kconfig | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig
index 91adcac875a4..c9d7afe489e8 100644
--- a/drivers/iio/accel/Kconfig
+++ b/drivers/iio/accel/Kconfig
@@ -219,10 +219,12 @@ config BMA400
config BMA400_I2C
tristate
+ select REGMAP_I2C
depends on BMA400
config BMA400_SPI
tristate
+ select REGMAP_SPI
depends on BMA400
config BMC150_ACCEL
From eef00a82c568944f113f2de738156ac591bbd5cd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Feb 2024 09:54:04 +0000
Subject: [PATCH 187/637] inet: read sk->sk_family once in inet_recv_error()
inet_recv_error() is called without holding the socket lock.
IPv6 socket could mutate to IPv4 with IPV6_ADDRFORM
socket option and trigger a KCSAN warning.
Fixes: f4713a3dfad0 ("net-timestamp: make tcp_recvmsg call ipv6_recv_error for AF_INET6 socks")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/af_inet.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4e635dd3d3c8..a5a820ee2026 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1628,10 +1628,12 @@ EXPORT_SYMBOL(inet_current_timestamp);
int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
- if (sk->sk_family == AF_INET)
+ unsigned int family = READ_ONCE(sk->sk_family);
+
+ if (family == AF_INET)
return ip_recv_error(sk, msg, len, addr_len);
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == AF_INET6)
+ if (family == AF_INET6)
return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len);
#endif
return -EINVAL;
From a40f93e9286968863c661f2b9e314d97adc2f84e Mon Sep 17 00:00:00 2001
From: Mike Tipton <quic_mdtipton@quicinc.com>
Date: Thu, 1 Feb 2024 17:48:05 -0800
Subject: [PATCH 188/637] interconnect: qcom: sm8650: Use correct ACV
enable_mask
The ACV enable_mask is historically BIT(3), but it's BIT(0) on this
target. Fix it.
Fixes: c062bcab5924 ("interconnect: qcom: introduce RPMh Network-On-Chip Interconnect on SM8650 SoC")
Signed-off-by: Mike Tipton <quic_mdtipton@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20240202014806.7876-2-quic_mdtipton@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/sm8650.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/interconnect/qcom/sm8650.c b/drivers/interconnect/qcom/sm8650.c
index b83de54577b6..b962e6c233ef 100644
--- a/drivers/interconnect/qcom/sm8650.c
+++ b/drivers/interconnect/qcom/sm8650.c
@@ -1160,7 +1160,7 @@ static struct qcom_icc_node qns_gemnoc_sf = {
static struct qcom_icc_bcm bcm_acv = {
.name = "ACV",
- .enable_mask = BIT(3),
+ .enable_mask = BIT(0),
.num_nodes = 1,
.nodes = { &ebi },
};
From 5464e7acea4a6c56b3c5c2d7aeef2eda92227b33 Mon Sep 17 00:00:00 2001
From: Mike Tipton <quic_mdtipton@quicinc.com>
Date: Thu, 1 Feb 2024 17:48:06 -0800
Subject: [PATCH 189/637] interconnect: qcom: x1e80100: Add missing ACV
enable_mask
The ACV BCM is voted using bitmasks. Add the proper mask for this
target.
Fixes: 9f196772841e ("interconnect: qcom: Add X1E80100 interconnect provider driver")
Signed-off-by: Mike Tipton <quic_mdtipton@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Tested-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20240202014806.7876-3-quic_mdtipton@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/x1e80100.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c
index d19501d913b3..cbaf4f9c41be 100644
--- a/drivers/interconnect/qcom/x1e80100.c
+++ b/drivers/interconnect/qcom/x1e80100.c
@@ -1586,6 +1586,7 @@ static struct qcom_icc_node qns_pcie_south_gem_noc_pcie = {
static struct qcom_icc_bcm bcm_acv = {
.name = "ACV",
+ .enable_mask = BIT(3),
.num_nodes = 1,
.nodes = { &ebi },
};
From 1a00897e5e96c29b21580dfcfec168dc16c67469 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Fri, 4 Aug 2023 12:05:44 +0800
Subject: [PATCH 190/637] drm/i915: Replace dead 01.org link
01.org is dead so replace old gvt link with current wiki page.
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Zhi Wang <zhi.wang.linux@gmail.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20230804040544.1972958-1-zhenyuw@linux.intel.com
---
MAINTAINERS | 2 +-
drivers/gpu/drm/i915/Kconfig | 2 +-
drivers/gpu/drm/i915/intel_gvt.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a69..03fbe24bf40d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10804,7 +10804,7 @@ M: Zhi Wang <zhi.a.wang@intel.com>
L: intel-gvt-dev@lists.freedesktop.org
L: intel-gfx@lists.freedesktop.org
S: Supported
-W: https://01.org/igvt-g
+W: https://github.com/intel/gvt-linux/wiki
T: git https://github.com/intel/gvt-linux.git
F: drivers/gpu/drm/i915/gvt/
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index b5d6e3352071..3089029abba4 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -140,7 +140,7 @@ config DRM_I915_GVT_KVMGT
Note that this driver only supports newer device from Broadwell on.
For further information and setup guide, you can visit:
- http://01.org/igvt-g.
+ https://github.com/intel/gvt-linux/wiki.
If in doubt, say "N".
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index e98b6d69a91a..9b6d87c8b583 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -41,7 +41,7 @@
* To virtualize GPU resources GVT-g driver depends on hypervisor technology
* e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
* and be virtualized within GVT-g device module. More architectural design
- * doc is available on https://01.org/group/2230/documentation-list.
+ * doc is available on https://github.com/intel/gvt-linux/wiki.
*/
static LIST_HEAD(intel_gvt_devices);
From 47caa96478b99d6d1199b89467cc3e5a6cc754ee Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:41:47 +0300
Subject: [PATCH 191/637] drm/i915/gvt: Fix uninitialized variable in
handle_mmio()
This code prints the wrong variable in the warning message. It should
print "i" instead of "info->offset". On the first iteration "info" is
uninitialized leading to a crash and on subsequent iterations it prints
the previous offset instead of the current one.
Fixes: e0f74ed4634d ("i915/gvt: Separate the MMIO tracking table from GVT-g")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/11957c20-b178-4027-9b0a-e32e9591dd7c@moroto.mountain
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
drivers/gpu/drm/i915/gvt/handlers.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90f6c1ece57d..efcb00472be2 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2849,8 +2849,7 @@ static int handle_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
for (i = start; i < end; i += 4) {
p = intel_gvt_find_mmio_info(gvt, i);
if (p) {
- WARN(1, "dup mmio definition offset %x\n",
- info->offset);
+ WARN(1, "dup mmio definition offset %x\n", i);
/* We return -EEXIST here to make GVT-g load fail.
* So duplicated MMIO can be found as soon as
From 44e4192f88978e32e4ac08b27141f3767366f79b Mon Sep 17 00:00:00 2001
From: Zhi Wang <zhi.wang.linux@gmail.com>
Date: Tue, 30 Jan 2024 21:27:43 +0000
Subject: [PATCH 192/637] MAINTAINERS: Update Zhi Wang's email address
Update my email address to zhi.wang.linux@gmail.com.
CC: Zhenyu Wang <zhenyuw@linux.intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhi Wang <zhi.wang.linux@gmail.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20240130212743.7727-1-zhi.wang.linux@gmail.com
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 03fbe24bf40d..052149d304ba 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10800,7 +10800,7 @@ F: drivers/gpio/gpio-tangier.h
INTEL GVT-g DRIVERS (Intel GPU Virtualization)
M: Zhenyu Wang <zhenyuw@linux.intel.com>
-M: Zhi Wang <zhi.a.wang@intel.com>
+M: Zhi Wang <zhi.wang.linux@gmail.com>
L: intel-gvt-dev@lists.freedesktop.org
L: intel-gfx@lists.freedesktop.org
S: Supported
From 8ded03ae48b3657e0fbca99d8a9d8fa1bfb8c9be Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Fri, 2 Feb 2024 18:26:46 -0600
Subject: [PATCH 193/637] powerpc/pseries/papr-sysparm: use u8 arrays for
payloads
Some PAPR system parameter values are formatted by firmware as
nul-terminated strings (e.g. LPAR name, shared processor attributes).
But the values returned for other parameters, such as processor module
info and TLB block invalidate characteristics, are binary data with
parameter-specific layouts. So char[] isn't the appropriate type for
the general case. Use u8/__u8.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Fixes: 905b9e48786e ("powerpc/pseries/papr-sysparm: Expose character device to user space")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240202-papr-sysparm-ioblock-data-use-u8-v1-1-f5c6c89f65ec@linux.ibm.com
---
arch/powerpc/include/asm/papr-sysparm.h | 2 +-
arch/powerpc/include/uapi/asm/papr-sysparm.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index 0dbbff59101d..c3cd5b131033 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -32,7 +32,7 @@ typedef struct {
*/
struct papr_sysparm_buf {
__be16 len;
- char val[PAPR_SYSPARM_MAX_OUTPUT];
+ u8 val[PAPR_SYSPARM_MAX_OUTPUT];
};
struct papr_sysparm_buf *papr_sysparm_buf_alloc(void);
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
index 9f9a0f267ea5..f733467b1534 100644
--- a/arch/powerpc/include/uapi/asm/papr-sysparm.h
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -14,7 +14,7 @@ enum {
struct papr_sysparm_io_block {
__u32 parameter;
__u16 length;
- char data[PAPR_SYSPARM_MAX_OUTPUT];
+ __u8 data[PAPR_SYSPARM_MAX_OUTPUT];
};
/**
From dd839f31d7cd5e04f4111a219024268c6f6973f0 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Sun, 4 Feb 2024 08:51:52 +0100
Subject: [PATCH 194/637] bcachefs: install fd later to avoid race with close
Calling fd_install() makes a file reachable for userland, including the
possibility to close the file descriptor, which leads to calling its
'release' hook. If that happens before the code had a chance to bump the
reference of the newly created task struct, the release callback will
call put_task_struct() too early, leading to the premature destruction
of the kernel thread.
Avoid that race by calling fd_install() later, after all the setup is
done.
Fixes: 1c6fdbd8f246 ("bcachefs: Initial commit")
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/thread_with_file.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index b1c867aa2b58..9220d7de10db 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -53,9 +53,9 @@ int bch2_run_thread_with_file(struct thread_with_file *thr,
if (ret)
goto err;
- fd_install(fd, file);
get_task_struct(thr->task);
wake_up_process(thr->task);
+ fd_install(fd, file);
return fd;
err:
if (fd >= 0)
From 7b508b323b2ec45be59769bd4e4aeba729c52cf6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 1 Feb 2024 21:01:02 -0500
Subject: [PATCH 195/637] bcachefs: time_stats: Check for last_event == 0 when
updating freq stats
This fixes spurious outliers in the frequency stats.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/util.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 56b815fd9fc6..231003b405ef 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -418,14 +418,15 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats,
bch2_quantiles_update(&stats->quantiles, duration);
}
- if (time_after64(end, stats->last_event)) {
+ if (stats->last_event && time_after64(end, stats->last_event)) {
freq = end - stats->last_event;
mean_and_variance_update(&stats->freq_stats, freq);
mean_and_variance_weighted_update(&stats->freq_stats_weighted, freq);
stats->max_freq = max(stats->max_freq, freq);
stats->min_freq = min(stats->min_freq, freq);
- stats->last_event = end;
}
+
+ stats->last_event = end;
}
static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats,
From 4639c5021029d49fd2f97fa8d74731f167f98919 Mon Sep 17 00:00:00 2001
From: bo liu <bo.liu@senarytech.com>
Date: Mon, 5 Feb 2024 09:38:02 +0800
Subject: [PATCH 196/637] ALSA: hda/conexant: Add quirk for SWS JS201D
The SWS JS201D need a different pinconfig from windows driver.
Add a quirk to use a specific pinconfig to SWS JS201D.
Signed-off-by: bo liu <bo.liu@senarytech.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240205013802.51907-1-bo.liu@senarytech.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_conexant.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e8819e8a9876..e8209178d87b 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -344,6 +344,7 @@ enum {
CXT_FIXUP_HP_ZBOOK_MUTE_LED,
CXT_FIXUP_HEADSET_MIC,
CXT_FIXUP_HP_MIC_NO_PRESENCE,
+ CXT_PINCFG_SWS_JS201D,
};
/* for hda_fixup_thinkpad_acpi() */
@@ -841,6 +842,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = {
{}
};
+/* SuoWoSi/South-holding JS201D with sn6140 */
+static const struct hda_pintbl cxt_pincfg_sws_js201d[] = {
+ { 0x16, 0x03211040 }, /* hp out */
+ { 0x17, 0x91170110 }, /* SPK/Class_D */
+ { 0x18, 0x95a70130 }, /* Internal mic */
+ { 0x19, 0x03a11020 }, /* Headset Mic */
+ { 0x1a, 0x40f001f0 }, /* Not used */
+ { 0x21, 0x40f001f0 }, /* Not used */
+ {}
+};
+
static const struct hda_fixup cxt_fixups[] = {
[CXT_PINCFG_LENOVO_X200] = {
.type = HDA_FIXUP_PINS,
@@ -996,6 +1008,10 @@ static const struct hda_fixup cxt_fixups[] = {
.chained = true,
.chain_id = CXT_FIXUP_HEADSET_MIC,
},
+ [CXT_PINCFG_SWS_JS201D] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = cxt_pincfg_sws_js201d,
+ },
};
static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -1069,6 +1085,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
+ SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D),
SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
@@ -1109,6 +1126,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
{ .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" },
{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
{ .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" },
+ { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" },
{}
};
From fddab35fd064414c677e9488c4fb3a1f67725d37 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Mon, 5 Feb 2024 15:22:52 +0800
Subject: [PATCH 197/637] ALSA: hda/realtek: add IDs for Dell dual spk platform
This patch adds another two IDs for the Dell dual speaker platform.
Signed-off-by: Shuming Fan <shumingf@realtek.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240205072252.3791500-1-shumingf@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 6994c4c5073c..e045d3e76a45 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9737,7 +9737,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0c0b, "Dell Oasis 14 RPL-P", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x0c0d, "Dell Oasis", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
+ SND_PCI_QUIRK(0x1028, 0x0c0e, "Dell Oasis 16", ALC289_FIXUP_RTK_AMP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
From 1ad55cecf22f05f1c884adf63cc09d3c3e609ebf Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 5 Feb 2024 09:11:07 +0100
Subject: [PATCH 198/637] x86/efistub: Use 1:1 file:memory mapping for PE/COFF
.compat section
The .compat section is a dummy PE section that contains the address of
the 32-bit entrypoint of the 64-bit kernel image if it is bootable from
32-bit firmware (i.e., CONFIG_EFI_MIXED=y)
This section is only 8 bytes in size and is only referenced from the
loader, and so it is placed at the end of the memory view of the image,
to avoid the need for padding it to 4k, which is required for sections
appearing in the middle of the image.
Unfortunately, this violates the PE/COFF spec, and even if most EFI
loaders will work correctly (including the Tianocore reference
implementation), PE loaders do exist that reject such images, on the
basis that both the file and memory views of the file contents should be
described by the section headers in a monotonically increasing manner
without leaving any gaps.
So reorganize the sections to avoid this issue. This results in a slight
padding overhead (< 4k) which can be avoided if desired by disabling
CONFIG_EFI_MIXED (which is only needed in rare cases these days)
Fixes: 3e3eabe26dc8 ("x86/boot: Increase section and file alignment to 4k/512")
Reported-by: Mike Beaton <mjsbeaton@gmail.com>
Link: https://lkml.kernel.org/r/CAHzAAWQ6srV6LVNdmfbJhOwhBw5ZzxxZZ07aHt9oKkfYAdvuQQ%40mail.gmail.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
arch/x86/boot/header.S | 14 ++++++--------
arch/x86/boot/setup.ld | 6 +++---
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b2771710ed98..a1bbedd989e4 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -106,8 +106,7 @@ extra_header_fields:
.word 0 # MinorSubsystemVersion
.long 0 # Win32VersionValue
- .long setup_size + ZO__end + pecompat_vsize
- # SizeOfImage
+ .long setup_size + ZO__end # SizeOfImage
.long salign # SizeOfHeaders
.long 0 # CheckSum
@@ -143,7 +142,7 @@ section_table:
.ascii ".setup"
.byte 0
.byte 0
- .long setup_size - salign # VirtualSize
+ .long pecompat_fstart - salign # VirtualSize
.long salign # VirtualAddress
.long pecompat_fstart - salign # SizeOfRawData
.long salign # PointerToRawData
@@ -156,8 +155,8 @@ section_table:
#ifdef CONFIG_EFI_MIXED
.asciz ".compat"
- .long 8 # VirtualSize
- .long setup_size + ZO__end # VirtualAddress
+ .long pecompat_fsize # VirtualSize
+ .long pecompat_fstart # VirtualAddress
.long pecompat_fsize # SizeOfRawData
.long pecompat_fstart # PointerToRawData
@@ -172,17 +171,16 @@ section_table:
* modes this image supports.
*/
.pushsection ".pecompat", "a", @progbits
- .balign falign
- .set pecompat_vsize, salign
+ .balign salign
.globl pecompat_fstart
pecompat_fstart:
.byte 0x1 # Version
.byte 8 # Size
.word IMAGE_FILE_MACHINE_I386 # PE machine type
.long setup_size + ZO_efi32_pe_entry # Entrypoint
+ .byte 0x0 # Sentinel
.popsection
#else
- .set pecompat_vsize, 0
.set pecompat_fstart, setup_size
#endif
.ascii ".text"
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 83bb7efad8ae..3a2d1360abb0 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -24,6 +24,9 @@ SECTIONS
.text : { *(.text .text.*) }
.text32 : { *(.text32) }
+ .pecompat : { *(.pecompat) }
+ PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
. = ALIGN(16);
.rodata : { *(.rodata*) }
@@ -36,9 +39,6 @@ SECTIONS
. = ALIGN(16);
.data : { *(.data*) }
- .pecompat : { *(.pecompat) }
- PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
-
.signature : {
setup_sig = .;
LONG(0x5a5aaa55)
From b3d4f7f2288901ed2392695919b3c0e24c1b4084 Mon Sep 17 00:00:00 2001
From: Daniel Basilio <daniel.basilio@corigine.com>
Date: Fri, 2 Feb 2024 13:37:17 +0200
Subject: [PATCH 199/637] nfp: use correct macro for LengthSelect in BAR config
The 1st and 2nd expansion BAR configuration registers are configured,
when the driver starts up, in variables 'barcfg_msix_general' and
'barcfg_msix_xpb', respectively. The 'LengthSelect' field is ORed in
from bit 0, which is incorrect. The 'LengthSelect' field should
start from bit 27.
This has largely gone un-noticed because
NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT happens to be 0.
Fixes: 4cb584e0ee7d ("nfp: add CPP access core")
Cc: stable@vger.kernel.org # 4.11+
Signed-off-by: Daniel Basilio <daniel.basilio@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 33b4c2856316..3f10c5365c80 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -537,11 +537,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface)
const u32 barcfg_msix_general =
NFP_PCIE_BAR_PCIE2CPP_MapType(
NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) |
- NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT;
+ NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+ NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT);
const u32 barcfg_msix_xpb =
NFP_PCIE_BAR_PCIE2CPP_MapType(
NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) |
- NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT |
+ NFP_PCIE_BAR_PCIE2CPP_LengthSelect(
+ NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) |
NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress(
NFP_CPP_TARGET_ISLAND_XPB);
const u32 barcfg_explicit[4] = {
From 1a1c13303ff6d64e6f718dc8aa614e580ca8d9b4 Mon Sep 17 00:00:00 2001
From: Daniel de Villiers <daniel.devilliers@corigine.com>
Date: Fri, 2 Feb 2024 13:37:18 +0200
Subject: [PATCH 200/637] nfp: flower: prevent re-adding mac index for bonded
port
When physical ports are reset (either through link failure or manually
toggled down and up again) that are slaved to a Linux bond with a tunnel
endpoint IP address on the bond device, not all tunnel packets arriving
on the bond port are decapped as expected.
The bond dev assigns the same MAC address to itself and each of its
slaves. When toggling a slave device, the same MAC address is therefore
offloaded to the NFP multiple times with different indexes.
The issue only occurs when re-adding the shared mac. The
nfp_tunnel_add_shared_mac() function has a conditional check early on
that checks if a mac entry already exists and if that mac entry is
global: (entry && nfp_tunnel_is_mac_idx_global(entry->index)). In the
case of a bonded device (For example br-ex), the mac index is obtained,
and no new index is assigned.
We therefore modify the conditional in nfp_tunnel_add_shared_mac() to
check if the port belongs to the LAG along with the existing checks to
prevent a new global mac index from being re-assigned to the slave port.
Fixes: 20cce8865098 ("nfp: flower: enable MAC address sharing for offloadable devs")
CC: stable@vger.kernel.org # 5.1+
Signed-off-by: Daniel de Villiers <daniel.devilliers@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index e522845c7c21..0d7d138d6e0d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -1084,7 +1084,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
u16 nfp_mac_idx = 0;
entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
- if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+ if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) {
if (entry->bridge_count ||
!nfp_flower_is_supported_bridge(netdev)) {
nfp_tunnel_offloaded_macs_inc_ref_and_link(entry,
From 0f4d6f011bca0df2051532b41b596366aa272019 Mon Sep 17 00:00:00 2001
From: James Hershaw <james.hershaw@corigine.com>
Date: Fri, 2 Feb 2024 13:37:19 +0200
Subject: [PATCH 201/637] nfp: enable NETDEV_XDP_ACT_REDIRECT feature flag
Enable previously excluded xdp feature flag for NFD3 devices. This
feature flag is required in order to bind nfp interfaces to an xdp
socket and the nfp driver does in fact support the feature.
Fixes: 66c0e13ad236 ("drivers: net: turn on XDP features")
Cc: stable@vger.kernel.org # 6.3+
Signed-off-by: James Hershaw <james.hershaw@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 3b3210d823e8..f28e769e6fda 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2776,6 +2776,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
case NFP_NFD_VER_NFD3:
netdev->netdev_ops = &nfp_nfd3_netdev_ops;
netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
+ netdev->xdp_features |= NETDEV_XDP_ACT_REDIRECT;
break;
case NFP_NFD_VER_NFDK:
netdev->netdev_ops = &nfp_nfdk_netdev_ops;
From ed8b94f6e0acd652ce69bd69d678a0c769172df8 Mon Sep 17 00:00:00 2001
From: Gaurav Batra <gbatra@linux.ibm.com>
Date: Mon, 22 Jan 2024 16:24:07 -0600
Subject: [PATCH 202/637] powerpc/pseries/iommu: Fix iommu initialisation
during DLPAR add
When a PCI device is dynamically added, the kernel oopses with a NULL
pointer dereference:
BUG: Kernel NULL pointer dereference on read at 0x00000030
Faulting instruction address: 0xc0000000006bbe5c
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: rpadlpar_io rpaphp rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs xsk_diag bonding nft_compat nf_tables nfnetlink rfkill binfmt_misc dm_multipath rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi ib_ipoib rdma_cm iw_cm ib_cm mlx5_ib ib_uverbs ib_core pseries_rng drm drm_panel_orientation_quirks xfs libcrc32c mlx5_core mlxfw sd_mod t10_pi sg tls ibmvscsi ibmveth scsi_transport_srp vmx_crypto pseries_wdt psample dm_mirror dm_region_hash dm_log dm_mod fuse
CPU: 17 PID: 2685 Comm: drmgr Not tainted 6.7.0-203405+ #66
Hardware name: IBM,9080-HEX POWER10 (raw) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_008) hv:phyp pSeries
NIP: c0000000006bbe5c LR: c000000000a13e68 CTR: c0000000000579f8
REGS: c00000009924f240 TRAP: 0300 Not tainted (6.7.0-203405+)
MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24002220 XER: 20040006
CFAR: c000000000a13e64 DAR: 0000000000000030 DSISR: 40000000 IRQMASK: 0
...
NIP sysfs_add_link_to_group+0x34/0x94
LR iommu_device_link+0x5c/0x118
Call Trace:
iommu_init_device+0x26c/0x318 (unreliable)
iommu_device_link+0x5c/0x118
iommu_init_device+0xa8/0x318
iommu_probe_device+0xc0/0x134
iommu_bus_notifier+0x44/0x104
notifier_call_chain+0xb8/0x19c
blocking_notifier_call_chain+0x64/0x98
bus_notify+0x50/0x7c
device_add+0x640/0x918
pci_device_add+0x23c/0x298
of_create_pci_dev+0x400/0x884
of_scan_pci_dev+0x124/0x1b0
__of_scan_bus+0x78/0x18c
pcibios_scan_phb+0x2a4/0x3b0
init_phb_dynamic+0xb8/0x110
dlpar_add_slot+0x170/0x3b8 [rpadlpar_io]
add_slot_store.part.0+0xb4/0x130 [rpadlpar_io]
kobj_attr_store+0x2c/0x48
sysfs_kf_write+0x64/0x78
kernfs_fop_write_iter+0x1b0/0x290
vfs_write+0x350/0x4a0
ksys_write+0x84/0x140
system_call_exception+0x124/0x330
system_call_vectored_common+0x15c/0x2ec
Commit a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities
and allow blocking domains") broke DLPAR add of PCI devices.
The above added iommu_device structure to pci_controller. During
system boot, PCI devices are discovered and this newly added iommu_device
structure is initialized by a call to iommu_device_register().
During DLPAR add of a PCI device, a new pci_controller structure is
allocated but there are no calls made to iommu_device_register()
interface.
Fix is to register the iommu device during DLPAR add as well.
Fixes: a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains")
Signed-off-by: Gaurav Batra <gbatra@linux.ibm.com>
[mpe: Trim oops and tweak some change log wording]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240122222407.39603-1-gbatra@linux.ibm.com
---
arch/powerpc/include/asm/ppc-pci.h | 3 +++
arch/powerpc/kernel/iommu.c | 21 ++++++++++++++++-----
arch/powerpc/platforms/pseries/pci_dlpar.c | 4 ++++
3 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index ce2b1b5eebdd..c3a3f3df36d1 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -29,6 +29,9 @@ void *pci_traverse_device_nodes(struct device_node *start,
void *(*fn)(struct device_node *, void *),
void *data);
extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
+extern void ppc_iommu_register_device(struct pci_controller *phb);
+extern void ppc_iommu_unregister_device(struct pci_controller *phb);
+
/* From rtas_pci.h */
extern void init_pci_config_tokens (void);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ebe259bdd462..c6f62e130d55 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1388,6 +1388,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
NULL,
};
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+ iommu_device_sysfs_add(&phb->iommu, phb->parent,
+ spapr_tce_iommu_groups, "iommu-phb%04x",
+ phb->global_number);
+ iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+ phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+ iommu_device_unregister(&phb->iommu);
+ iommu_device_sysfs_remove(&phb->iommu);
+}
+
/*
* This registers IOMMU devices of PHBs. This needs to happen
* after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1398,11 +1413,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
struct pci_controller *hose;
list_for_each_entry(hose, &hose_list, list_node) {
- iommu_device_sysfs_add(&hose->iommu, hose->parent,
- spapr_tce_iommu_groups, "iommu-phb%04x",
- hose->global_number);
- iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
- hose->parent);
+ ppc_iommu_register_device(hose);
}
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4ba824568119..4448386268d9 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
pseries_msi_allocate_domains(phb);
+ ppc_iommu_register_device(phb);
+
/* Create EEH devices for the PHB */
eeh_phb_pe_create(phb);
@@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
}
}
+ ppc_iommu_unregister_device(phb);
+
pseries_msi_free_domains(phb);
/* Keep a reference so phb isn't freed yet */
From aad98efd0b121f63a2e1c221dcb4d4850128c697 Mon Sep 17 00:00:00 2001
From: Naveen N Rao <naveen@kernel.org>
Date: Fri, 2 Feb 2024 21:13:16 +0530
Subject: [PATCH 203/637] powerpc/64: Set task pt_regs->link to the LR value on
scv entry
Nysal reported that userspace backtraces are missing in offcputime bcc
tool. As an example:
$ sudo ./bcc/tools/offcputime.py -uU
Tracing off-CPU time (us) of user threads by user stack... Hit Ctrl-C to end.
^C
write
- python (9107)
8
write
- sudo (9105)
9
mmap
- python (9107)
16
clock_nanosleep
- multipathd (697)
3001604
The offcputime bcc tool attaches a bpf program to a kprobe on
finish_task_switch(), which is usually hit on a syscall from userspace.
With the switch to system call vectored, we started setting
pt_regs->link to zero. This is because system call vectored behaves like
a function call with LR pointing to the system call return address, and
with no modification to SRR0/SRR1. The LR value does indicate our next
instruction, so it is being saved as pt_regs->nip, and pt_regs->link is
being set to zero. This is not a problem by itself, but BPF uses perf
callchain infrastructure for capturing stack traces, and that stores LR
as the second entry in the stack trace. perf has code to cope with the
second entry being zero, and skips over it. However, generic userspace
unwinders assume that a zero entry indicates end of the stack trace,
resulting in a truncated userspace stack trace.
Rather than fixing all userspace unwinders to ignore/skip past the
second entry, store the real LR value in pt_regs->link so that there
continues to be a valid, though duplicate entry in the stack trace.
With this change:
$ sudo ./bcc/tools/offcputime.py -uU
Tracing off-CPU time (us) of user threads by user stack... Hit Ctrl-C to end.
^C
write
write
[unknown]
[unknown]
[unknown]
[unknown]
[unknown]
PyObject_VectorcallMethod
[unknown]
[unknown]
PyObject_CallOneArg
PyFile_WriteObject
PyFile_WriteString
[unknown]
[unknown]
PyObject_Vectorcall
_PyEval_EvalFrameDefault
PyEval_EvalCode
[unknown]
[unknown]
[unknown]
_PyRun_SimpleFileObject
_PyRun_AnyFileObject
Py_RunMain
[unknown]
Py_BytesMain
[unknown]
__libc_start_main
- python (1293)
7
write
write
[unknown]
sudo_ev_loop_v1
sudo_ev_dispatch_v1
[unknown]
[unknown]
[unknown]
[unknown]
__libc_start_main
- sudo (1291)
7
syscall
syscall
bpf_open_perf_buffer_opts
[unknown]
[unknown]
[unknown]
[unknown]
_PyObject_MakeTpCall
PyObject_Vectorcall
_PyEval_EvalFrameDefault
PyEval_EvalCode
[unknown]
[unknown]
[unknown]
_PyRun_SimpleFileObject
_PyRun_AnyFileObject
Py_RunMain
[unknown]
Py_BytesMain
[unknown]
__libc_start_main
- python (1293)
11
clock_nanosleep
clock_nanosleep
nanosleep
sleep
[unknown]
[unknown]
__clone
- multipathd (698)
3001661
Fixes: 7fa95f9adaee ("powerpc/64s: system call support for scv/rfscv instructions")
Cc: stable@vger.kernel.org
Reported-by: "Nysal Jan K.A" <nysal@linux.ibm.com>
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240202154316.395276-1-naveen@kernel.org
---
arch/powerpc/kernel/interrupt_64.S | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bd863702d812..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
mr r10,r1
ld r1,PACAKSAVE(r13)
std r10,0(r1)
- std r11,_NIP(r1)
+ std r11,_LINK(r1)
+ std r11,_NIP(r1) /* Saved LR is also the next instruction */
std r12,_MSR(r1)
std r0,GPR0(r1)
std r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
std r9,GPR13(r1)
SAVE_NVGPRS(r1)
std r11,_XER(r1)
- std r11,_LINK(r1)
std r11,_CTR(r1)
li r11,\trapnr
From f09696279b5dd1770a3de2e062f1c5d1449213ff Mon Sep 17 00:00:00 2001
From: R Nageswara Sastry <rnsastry@linux.ibm.com>
Date: Wed, 31 Jan 2024 18:38:59 +0530
Subject: [PATCH 204/637] selftests/powerpc/papr_vpd: Check devfd before
get_system_loc_code()
Calling get_system_loc_code before checking devfd and errno fails the test
when the device is not available, the expected behaviour is a SKIP.
Change the order of 'SKIP_IF_MSG' to correctly SKIP when the /dev/
papr-vpd device is not available.
Test output before:
Test FAILED on line 271
Test output after:
[SKIP] Test skipped on line 266: /dev/papr-vpd not present
Signed-off-by: R Nageswara Sastry <rnsastry@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240131130859.14968-1-rnsastry@linux.ibm.com
---
tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
index 98cbb9109ee6..505294da1b9f 100644
--- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -263,10 +263,10 @@ static int papr_vpd_system_loc_code(void)
off_t size;
int fd;
- SKIP_IF_MSG(get_system_loc_code(&lc),
- "Cannot determine system location code");
SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
DEVPATH " not present");
+ SKIP_IF_MSG(get_system_loc_code(&lc),
+ "Cannot determine system location code");
FAIL_IF(devfd < 0);
From a038a3ff8c6582404834852c043dadc73a5b68b4 Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Date: Wed, 24 Jan 2024 11:38:38 +0100
Subject: [PATCH 205/637] powerpc/6xx: set High BAT Enable flag on G2_LE cores
MMU_FTR_USE_HIGH_BATS is set for G2_LE cores and derivatives like e300cX,
but the high BATs need to be enabled in HID2 to work. Add register
definitions and add the needed setup to __setup_cpu_603.
This fixes boot on CPUs like the MPC5200B with STRICT_KERNEL_RWX enabled
on systems where the flag has not been set by the bootloader already.
Fixes: e4d6654ebe6e ("powerpc/mm/32s: rework mmu_mapin_ram()")
Signed-off-by: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240124103838.43675-1-matthias.schiffer@ew.tq-group.com
---
arch/powerpc/include/asm/reg.h | 2 ++
arch/powerpc/kernel/cpu_setup_6xx.S | 20 +++++++++++++++++++-
2 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7fd09f25452d..bb47af9054a9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -617,6 +617,8 @@
#endif
#define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */
#define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */
+#define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */
#define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */
#define SPRN_IABR2 0x3FA /* 83xx */
#define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f29ce3dd6140..bfd3f442e5eb 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
bl __init_fpu_registers
END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
bl setup_common_caches
+
+ /*
+ * This assumes that all cores using __setup_cpu_603 with
+ * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+ */
+BEGIN_MMU_FTR_SECTION
+ bl setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
mtlr r5
blr
_GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
blr
SYM_FUNC_END(setup_604_hid0)
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+ mfspr r11,SPRN_HID2_G2_LE
+ oris r11,r11,HID2_G2_LE_HBE@h
+ mtspr SPRN_HID2_G2_LE,r11
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
/* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
* erratas we work around here.
* Moto MPC710CE.pdf describes them, those are errata
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
mtcr r7
blr
_ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
From 4a7aee96200ad281a5cc4cf5c7a2e2a49d2b97b0 Mon Sep 17 00:00:00 2001
From: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Date: Tue, 23 Jan 2024 09:45:59 +0800
Subject: [PATCH 206/637] powerpc/kasan: Fix addr error caused by page
alignment
In kasan_init_region, when k_start is not page aligned, at the begin of
for loop, k_cur = k_start & PAGE_MASK is less than k_start, and then
`va = block + k_cur - k_start` is less than block, the addr va is invalid,
because the memory address space from va to block is not alloced by
memblock_alloc, which will not be reserved by memblock_reserve later, it
will be used by other places.
As a result, memory overwriting occurs.
for example:
int __init __weak kasan_init_region(void *start, size_t size)
{
[...]
/* if say block(dcd97000) k_start(feef7400) k_end(feeff3fe) */
block = memblock_alloc(k_end - k_start, PAGE_SIZE);
[...]
for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
/* at the begin of for loop
* block(dcd97000) va(dcd96c00) k_cur(feef7000) k_start(feef7400)
* va(dcd96c00) is less than block(dcd97000), va is invalid
*/
void *va = block + k_cur - k_start;
[...]
}
[...]
}
Therefore, page alignment is performed on k_start before
memblock_alloc() to ensure the validity of the VA address.
Fixes: 663c0c9496a6 ("powerpc/kasan: Fix shadow area set up for modules.")
Signed-off-by: Jiangfeng Xiao <xiaojiangfeng@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/1705974359-43790-1-git-send-email-xiaojiangfeng@huawei.com
---
arch/powerpc/mm/kasan/init_32.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..aa9aa11927b2 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
if (ret)
return ret;
+ k_start = k_start & PAGE_MASK;
block = memblock_alloc(k_end - k_start, PAGE_SIZE);
if (!block)
return -ENOMEM;
From f31041417bf7f4a4df8b3bfb52cb31bbe805b934 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:13 +0000
Subject: [PATCH 207/637] rxrpc: Fix generation of serial numbers to skip zero
In the Rx protocol, every packet generated is marked with a per-connection
monotonically increasing serial number. This number can be referenced in
an ACK packet generated in response to an incoming packet - thereby
allowing the sender to use this for RTT determination, amongst other
things.
However, if the reference field in the ACK is zero, it doesn't refer to any
incoming packet (it could be a ping to find out if a packet got lost, for
example) - so we shouldn't generate zero serial numbers.
Fix the generation of serial numbers to retry if it comes up with a zero.
Furthermore, since the serial numbers are only ever allocated within the
I/O thread this connection is bound to, there's no need for atomics so
remove that too.
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/rxrpc/ar-internal.h | 16 +++++++++++++++-
net/rxrpc/conn_event.c | 2 +-
net/rxrpc/output.c | 8 ++++----
net/rxrpc/proc.c | 2 +-
net/rxrpc/rxkad.c | 4 ++--
5 files changed, 23 insertions(+), 9 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index dbeb75c29857..31b0dd8c9b2d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -510,7 +510,7 @@ struct rxrpc_connection {
enum rxrpc_call_completion completion; /* Completion condition */
s32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
- atomic_t serial; /* packet serial number counter */
+ rxrpc_serial_t tx_serial; /* Outgoing packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
u32 service_id; /* Service ID, possibly upgraded */
u32 security_level; /* Security level selected */
@@ -822,6 +822,20 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb)
#include <trace/events/rxrpc.h>
+/*
+ * Allocate the next serial number on a connection. 0 must be skipped.
+ */
+static inline rxrpc_serial_t rxrpc_get_next_serial(struct rxrpc_connection *conn)
+{
+ rxrpc_serial_t serial;
+
+ serial = conn->tx_serial;
+ if (serial == 0)
+ serial = 1;
+ conn->tx_serial = serial + 1;
+ return serial;
+}
+
/*
* af_rxrpc.c
*/
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 95f4bc206b3d..ec5eae60ab0c 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -117,7 +117,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
iov[2].iov_base = &ack_info;
iov[2].iov_len = sizeof(ack_info);
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(conn->proto.cid | channel);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index a0906145e829..4a292f860ae3 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -216,7 +216,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n;
len = iov[0].iov_len;
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
txb->wire.serial = htonl(serial);
trace_rxrpc_tx_ack(call->debug_id, serial,
ntohl(txb->ack.firstPacket),
@@ -302,7 +302,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
iov[0].iov_base = &pkt;
iov[0].iov_len = sizeof(pkt);
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
pkt.whdr.serial = htonl(serial);
iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt));
@@ -334,7 +334,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
_enter("%x,{%d}", txb->seq, txb->len);
/* Each transmission of a Tx packet needs a new serial number */
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
txb->wire.serial = htonl(serial);
if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) &&
@@ -558,7 +558,7 @@ void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
len = iov[0].iov_len + iov[1].iov_len;
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
whdr.serial = htonl(serial);
iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 6c86cbb98d1d..26dc2f26d92d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -181,7 +181,7 @@ print:
atomic_read(&conn->active),
state,
key_serial(conn->key),
- atomic_read(&conn->serial),
+ conn->tx_serial,
conn->hi_serial,
conn->channels[0].call_id,
conn->channels[1].call_id,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index b52dedcebce0..6b32d61d4cdc 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -664,7 +664,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
len = iov[0].iov_len + iov[1].iov_len;
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
whdr.serial = htonl(serial);
ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
@@ -721,7 +721,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
len = iov[0].iov_len + iov[1].iov_len + iov[2].iov_len;
- serial = atomic_inc_return(&conn->serial);
+ serial = rxrpc_get_next_serial(conn);
whdr.serial = htonl(serial);
rxrpc_local_dont_fragment(conn->local, false);
From e7870cf13d20f56bfc19f9c3e89707c69cf104ef Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:14 +0000
Subject: [PATCH 208/637] rxrpc: Fix delayed ACKs to not set the reference
serial number
Fix the construction of delayed ACKs to not set the reference serial number
as they can't be used as an RTT reference.
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/rxrpc/ar-internal.h | 1 -
net/rxrpc/call_event.c | 6 +-----
2 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 31b0dd8c9b2d..b4ab26c3718a 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -696,7 +696,6 @@ struct rxrpc_call {
/* Receive-phase ACK management (ACKs we send). */
u8 ackr_reason; /* reason to ACK */
u16 ackr_sack_base; /* Starting slot in SACK table ring */
- rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */
rxrpc_seq_t ackr_window; /* Base of SACK window */
rxrpc_seq_t ackr_wtop; /* Base of SACK window */
unsigned int ackr_nr_unacked; /* Number of unacked packets */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index e363f21a2014..c61efe08695d 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -43,8 +43,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial,
unsigned long expiry = rxrpc_soft_ack_delay;
unsigned long now = jiffies, ack_at;
- call->ackr_serial = serial;
-
if (rxrpc_soft_ack_delay < expiry)
expiry = rxrpc_soft_ack_delay;
if (call->peer->srtt_us != 0)
@@ -373,7 +371,6 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
{
unsigned long now, next, t;
- rxrpc_serial_t ackr_serial;
bool resend = false, expired = false;
s32 abort_code;
@@ -423,8 +420,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET);
- ackr_serial = xchg(&call->ackr_serial, 0);
- rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial,
+ rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0,
rxrpc_propose_ack_ping_for_lost_ack);
}
From 6f769f22822aa4124b556339781b04d810f0e038 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:15 +0000
Subject: [PATCH 209/637] rxrpc: Fix response to PING RESPONSE ACKs to a dead
call
Stop rxrpc from sending a DUP ACK in response to a PING RESPONSE ACK on a
dead call. We may have initiated the ping but the call may have beaten the
response to completion.
Fixes: 18bfeba50dfd ("rxrpc: Perform terminal call ACK/ABORT retransmission from conn processor")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/rxrpc/conn_event.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index ec5eae60ab0c..1f251d758cb9 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -95,6 +95,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
_enter("%d", conn->debug_id);
+ if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) {
+ if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+ &pkt.ack, sizeof(pkt.ack)) < 0)
+ return;
+ if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE)
+ return;
+ }
+
chan = &conn->channels[channel];
/* If the last call got moved on whilst we were waiting to run, just
From 41b7fa157ea1c8c3a575ca7f5f32034de9bee3ae Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Feb 2024 15:19:16 +0000
Subject: [PATCH 210/637] rxrpc: Fix counting of new acks and nacks
Fix the counting of new acks and nacks when parsing a packet - something
that is used in congestion control.
As the code stands, it merely notes if there are any nacks whereas what we
really should do is compare the previous SACK table to the new one,
assuming we get two successive ACK packets with nacks in them. However, we
really don't want to do that if we can avoid it as the tables might not
correspond directly as one may be shifted from the other - something that
will only get harder to deal with once extended ACK tables come into full
use (with a capacity of up to 8192).
Instead, count the number of nacks shifted out of the old SACK, the number
of nacks retained in the portion still active and the number of new acks
and nacks in the new table then calculate what we need.
Note this ends up a bit of an estimate as the Rx protocol allows acks to be
withdrawn by the receiver and packets requested to be retransmitted.
Fixes: d57a3a151660 ("rxrpc: Save last ACK's SACK table rather than marking txbufs")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/trace/events/rxrpc.h | 8 ++-
net/rxrpc/ar-internal.h | 20 ++++--
net/rxrpc/call_event.c | 6 +-
net/rxrpc/call_object.c | 1 +
net/rxrpc/input.c | 115 +++++++++++++++++++++++++++++------
5 files changed, 122 insertions(+), 28 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4c1ef7b3705c..87b8de9b6c1c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -128,6 +128,7 @@
EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \
EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \
EM(rxrpc_skb_get_conn_work, "GET conn-work") \
+ EM(rxrpc_skb_get_last_nack, "GET last-nack") \
EM(rxrpc_skb_get_local_work, "GET locl-work") \
EM(rxrpc_skb_get_reject_work, "GET rej-work ") \
EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \
@@ -141,6 +142,7 @@
EM(rxrpc_skb_put_error_report, "PUT error-rep") \
EM(rxrpc_skb_put_input, "PUT input ") \
EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \
+ EM(rxrpc_skb_put_last_nack, "PUT last-nack") \
EM(rxrpc_skb_put_purge, "PUT purge ") \
EM(rxrpc_skb_put_rotate, "PUT rotate ") \
EM(rxrpc_skb_put_unknown, "PUT unknown ") \
@@ -1552,7 +1554,7 @@ TRACE_EVENT(rxrpc_congest,
memcpy(&__entry->sum, summary, sizeof(__entry->sum));
),
- TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+ TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s",
__entry->call,
__entry->ack_serial,
__print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1560,9 +1562,9 @@ TRACE_EVENT(rxrpc_congest,
__print_symbolic(__entry->sum.mode, rxrpc_congest_modes),
__entry->sum.cwnd,
__entry->sum.ssthresh,
- __entry->sum.nr_acks, __entry->sum.saw_nacks,
+ __entry->sum.nr_acks, __entry->sum.nr_retained_nacks,
__entry->sum.nr_new_acks,
- __entry->sum.nr_rot_new_acks,
+ __entry->sum.nr_new_nacks,
__entry->top - __entry->hard_ack,
__entry->sum.cumulative_acks,
__entry->sum.dup_acks,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index b4ab26c3718a..7818aae1be8e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -199,11 +199,19 @@ struct rxrpc_host_header {
*/
struct rxrpc_skb_priv {
struct rxrpc_connection *conn; /* Connection referred to (poke packet) */
- u16 offset; /* Offset of data */
- u16 len; /* Length of data */
- u8 flags;
+ union {
+ struct {
+ u16 offset; /* Offset of data */
+ u16 len; /* Length of data */
+ u8 flags;
#define RXRPC_RX_VERIFIED 0x01
-
+ };
+ struct {
+ rxrpc_seq_t first_ack; /* First packet in acks table */
+ u8 nr_acks; /* Number of acks+nacks */
+ u8 nr_nacks; /* Number of nacks */
+ };
+ };
struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */
};
@@ -692,6 +700,7 @@ struct rxrpc_call {
u8 cong_dup_acks; /* Count of ACKs showing missing packets */
u8 cong_cumul_acks; /* Cumulative ACK count */
ktime_t cong_tstamp; /* Last time cwnd was changed */
+ struct sk_buff *cong_last_nack; /* Last ACK with nacks received */
/* Receive-phase ACK management (ACKs we send). */
u8 ackr_reason; /* reason to ACK */
@@ -729,7 +738,8 @@ struct rxrpc_call {
struct rxrpc_ack_summary {
u16 nr_acks; /* Number of ACKs in packet */
u16 nr_new_acks; /* Number of new ACKs in packet */
- u16 nr_rot_new_acks; /* Number of rotated new ACKs */
+ u16 nr_new_nacks; /* Number of new nacks in packet */
+ u16 nr_retained_nacks; /* Number of nacks retained between ACKs */
u8 ack_reason;
bool saw_nacks; /* Saw NACKs in packet */
bool new_low_nack; /* T if new low NACK found */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index c61efe08695d..0f78544d043b 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -112,6 +112,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
{
struct rxrpc_ackpacket *ack = NULL;
+ struct rxrpc_skb_priv *sp;
struct rxrpc_txbuf *txb;
unsigned long resend_at;
rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted);
@@ -139,14 +140,15 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
* explicitly NAK'd packets.
*/
if (ack_skb) {
+ sp = rxrpc_skb(ack_skb);
ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header);
- for (i = 0; i < ack->nAcks; i++) {
+ for (i = 0; i < sp->nr_acks; i++) {
rxrpc_seq_t seq;
if (ack->acks[i] & 1)
continue;
- seq = ntohl(ack->firstPacket) + i;
+ seq = sp->first_ack + i;
if (after(txb->seq, transmitted))
break;
if (after(txb->seq, seq))
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0943e54370ba..9fc9a6c3f685 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -686,6 +686,7 @@ static void rxrpc_destroy_call(struct work_struct *work)
del_timer_sync(&call->timer);
+ rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
rxrpc_cleanup_ring(call);
while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
struct rxrpc_txbuf, call_link))) {
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 92495e73b869..9691de00ade7 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -45,11 +45,9 @@ static void rxrpc_congestion_management(struct rxrpc_call *call,
}
cumulative_acks += summary->nr_new_acks;
- cumulative_acks += summary->nr_rot_new_acks;
if (cumulative_acks > 255)
cumulative_acks = 255;
- summary->mode = call->cong_mode;
summary->cwnd = call->cong_cwnd;
summary->ssthresh = call->cong_ssthresh;
summary->cumulative_acks = cumulative_acks;
@@ -151,6 +149,7 @@ out_no_clear_ca:
cwnd = RXRPC_TX_MAX_WINDOW;
call->cong_cwnd = cwnd;
call->cong_cumul_acks = cumulative_acks;
+ summary->mode = call->cong_mode;
trace_rxrpc_congest(call, summary, acked_serial, change);
if (resend)
rxrpc_resend(call, skb);
@@ -213,7 +212,6 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) {
if (before_eq(txb->seq, call->acks_hard_ack))
continue;
- summary->nr_rot_new_acks++;
if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) {
set_bit(RXRPC_CALL_TX_LAST, &call->flags);
rot_last = true;
@@ -254,6 +252,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
{
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
+ if (unlikely(call->cong_last_nack)) {
+ rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+ call->cong_last_nack = NULL;
+ }
+
switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
@@ -702,6 +705,43 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
wake_up(&call->waitq);
}
+/*
+ * Determine how many nacks from the previous ACK have now been satisfied.
+ */
+static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call,
+ struct rxrpc_ack_summary *summary,
+ rxrpc_seq_t seq)
+{
+ struct sk_buff *skb = call->cong_last_nack;
+ struct rxrpc_ackpacket ack;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ unsigned int i, new_acks = 0, retained_nacks = 0;
+ rxrpc_seq_t old_seq = sp->first_ack;
+ u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack);
+
+ if (after_eq(seq, old_seq + sp->nr_acks)) {
+ summary->nr_new_acks += sp->nr_nacks;
+ summary->nr_new_acks += seq - (old_seq + sp->nr_acks);
+ summary->nr_retained_nacks = 0;
+ } else if (seq == old_seq) {
+ summary->nr_retained_nacks = sp->nr_nacks;
+ } else {
+ for (i = 0; i < sp->nr_acks; i++) {
+ if (acks[i] == RXRPC_ACK_TYPE_NACK) {
+ if (before(old_seq + i, seq))
+ new_acks++;
+ else
+ retained_nacks++;
+ }
+ }
+
+ summary->nr_new_acks += new_acks;
+ summary->nr_retained_nacks = retained_nacks;
+ }
+
+ return old_seq + sp->nr_acks;
+}
+
/*
* Process individual soft ACKs.
*
@@ -711,25 +751,51 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb,
* the timer on the basis that the peer might just not have processed them at
* the time the ACK was sent.
*/
-static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks,
- rxrpc_seq_t seq, int nr_acks,
- struct rxrpc_ack_summary *summary)
+static void rxrpc_input_soft_acks(struct rxrpc_call *call,
+ struct rxrpc_ack_summary *summary,
+ struct sk_buff *skb,
+ rxrpc_seq_t seq,
+ rxrpc_seq_t since)
{
- unsigned int i;
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+ unsigned int i, old_nacks = 0;
+ rxrpc_seq_t lowest_nak = seq + sp->nr_acks;
+ u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket);
- for (i = 0; i < nr_acks; i++) {
+ for (i = 0; i < sp->nr_acks; i++) {
if (acks[i] == RXRPC_ACK_TYPE_ACK) {
summary->nr_acks++;
- summary->nr_new_acks++;
+ if (after_eq(seq, since))
+ summary->nr_new_acks++;
} else {
- if (!summary->saw_nacks &&
- call->acks_lowest_nak != seq + i) {
- call->acks_lowest_nak = seq + i;
- summary->new_low_nack = true;
- }
summary->saw_nacks = true;
+ if (before(seq, since)) {
+ /* Overlap with previous ACK */
+ old_nacks++;
+ } else {
+ summary->nr_new_nacks++;
+ sp->nr_nacks++;
+ }
+
+ if (before(seq, lowest_nak))
+ lowest_nak = seq;
}
+ seq++;
}
+
+ if (lowest_nak != call->acks_lowest_nak) {
+ call->acks_lowest_nak = lowest_nak;
+ summary->new_low_nack = true;
+ }
+
+ /* We *can* have more nacks than we did - the peer is permitted to drop
+ * packets it has soft-acked and re-request them. Further, it is
+ * possible for the nack distribution to change whilst the number of
+ * nacks stays the same or goes down.
+ */
+ if (old_nacks < summary->nr_retained_nacks)
+ summary->nr_new_acks += summary->nr_retained_nacks - old_nacks;
+ summary->nr_retained_nacks = old_nacks;
}
/*
@@ -773,7 +839,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_ackinfo info;
rxrpc_serial_t ack_serial, acked_serial;
- rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
+ rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since;
int nr_acks, offset, ioffset;
_enter("");
@@ -789,6 +855,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
prev_pkt = ntohl(ack.previousPacket);
hard_ack = first_soft_ack - 1;
nr_acks = ack.nAcks;
+ sp->first_ack = first_soft_ack;
+ sp->nr_acks = nr_acks;
summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ?
ack.reason : RXRPC_ACK__INVALID);
@@ -858,6 +926,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
if (nr_acks > 0)
skb_condense(skb);
+ if (call->cong_last_nack) {
+ since = rxrpc_input_check_prev_ack(call, &summary, first_soft_ack);
+ rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack);
+ call->cong_last_nack = NULL;
+ } else {
+ summary.nr_new_acks = first_soft_ack - call->acks_first_seq;
+ call->acks_lowest_nak = first_soft_ack + nr_acks;
+ since = first_soft_ack;
+ }
+
call->acks_latest_ts = skb->tstamp;
call->acks_first_seq = first_soft_ack;
call->acks_prev_seq = prev_pkt;
@@ -866,7 +944,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
case RXRPC_ACK_PING:
break;
default:
- if (after(acked_serial, call->acks_highest_serial))
+ if (acked_serial && after(acked_serial, call->acks_highest_serial))
call->acks_highest_serial = acked_serial;
break;
}
@@ -905,8 +983,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
if (nr_acks > 0) {
if (offset > (int)skb->len - nr_acks)
return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
- rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
- nr_acks, &summary);
+ rxrpc_input_soft_acks(call, &summary, skb, first_soft_ack, since);
+ rxrpc_get_skb(skb, rxrpc_skb_get_last_nack);
+ call->cong_last_nack = skb;
}
if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) &&
From a19747c3b9bf6476cc36d0a3a5ef0ff92999169e Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 2 Feb 2024 17:06:59 +0100
Subject: [PATCH 211/637] selftests: net: let big_tcp test cope with slow env
In very slow environments, most big TCP cases including
segmentation and reassembly of big TCP packets have a good
chance to fail: by default the TCP client uses write size
well below 64K. If the host is low enough autocorking is
unable to build real big TCP packets.
Address the issue using much larger write operations.
Note that is hard to observe the issue without an extremely
slow and/or overloaded environment; reduce the TCP transfer
time to allow for much easier/faster reproducibility.
Fixes: 6bb382bcf742 ("selftests: add a selftest for big tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/big_tcp.sh | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index cde9a91c4797..2db9d15cd45f 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -122,7 +122,9 @@ do_netperf() {
local netns=$1
[ "$NF" = "6" ] && serip=$SERVER_IP6
- ip net exec $netns netperf -$NF -t TCP_STREAM -H $serip 2>&1 >/dev/null
+
+ # use large write to be sure to generate big tcp packets
+ ip net exec $netns netperf -$NF -t TCP_STREAM -l 1 -H $serip -- -m 262144 2>&1 >/dev/null
}
do_test() {
From 4703b014f28bf7a2e56d1da238ee95ef6c5ce76b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 5 Feb 2024 15:44:30 +0300
Subject: [PATCH 212/637] ASoC: cs35l56: fix reversed if statement in
cs35l56_dspwait_asp1tx_put()
It looks like the "!" character was added accidentally. The
regmap_update_bits_check() function is normally going to succeed. This
means the rest of the function is unreachable and we don't handle the
situation where "changed" is true correctly.
Fixes: 07f7d6e7a124 ("ASoC: cs35l56: Fix for initializing ASP1 mixer registers")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://lore.kernel.org/r/0c254c07-d1c0-4a5c-a22b-7e135cab032c@moroto.mountain
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs35l56.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index c23e29da4cfb..ebed5ab1245b 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -115,7 +115,7 @@ static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
ret = regmap_update_bits_check(cs35l56->base.regmap, addr,
CS35L56_ASP_TXn_SRC_MASK, val, &changed);
- if (!ret)
+ if (ret)
return ret;
if (changed)
From ac670505d825151ce47c1e75b9964485991954dd Mon Sep 17 00:00:00 2001
From: Jeffrey Hugo <quic_jhugo@quicinc.com>
Date: Fri, 2 Feb 2024 10:43:13 -0700
Subject: [PATCH 213/637] ASoC: dt-bindings: google,sc7280-herobrine: Drop
bouncing @codeaurora
The servers for the @codeaurora domain have long been retired and any
messages sent there bounce. Srinivasa Rao Mandadapu has left the
company and there does not appear to be an updated address to suggest,
so drop Srinivasa as maintainer of the binding. The binding still
appears to be maintined as Judy is listed.
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240202174313.4113670-1-quic_jhugo@quicinc.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../devicetree/bindings/sound/google,sc7280-herobrine.yaml | 1 -
1 file changed, 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
index ec4b6e547ca6..cdcd7c6f21eb 100644
--- a/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
+++ b/Documentation/devicetree/bindings/sound/google,sc7280-herobrine.yaml
@@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Google SC7280-Herobrine ASoC sound card driver
maintainers:
- - Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
- Judy Hsiao <judyhsiao@chromium.org>
description:
From b5fbde22684af5456d1de60758950944d69d69ad Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 2 Feb 2024 12:49:01 +0100
Subject: [PATCH 214/637] ASoC: Intel: avs: Fix pci_probe() error path
Recent changes modified operation-order in the probe() function without
updating its error path accordingly. If snd_hdac_i915_init() exists with
status EPROBE_DEFER the error path must cleanup allocated IRQs before
leaving the scope.
Fixes: 2dddc514b6e4 ("ASoC: Intel: avs: Move snd_hdac_i915_init to before probe_work.")
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://lore.kernel.org/r/20240202114901.1002127-1-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/avs/core.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c
index 59c3793f65df..db78eb2f0108 100644
--- a/sound/soc/intel/avs/core.c
+++ b/sound/soc/intel/avs/core.c
@@ -477,6 +477,9 @@ static int avs_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
return 0;
err_i915_init:
+ pci_free_irq(pci, 0, adev);
+ pci_free_irq(pci, 0, bus);
+ pci_free_irq_vectors(pci);
pci_clear_master(pci);
pci_set_drvdata(pci, NULL);
err_acquire_irq:
From 34a1066981a967eab619938e7b35a9be6b4c34e1 Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Sun, 4 Feb 2024 21:01:17 +0100
Subject: [PATCH 215/637] ASoC: tas2781: add module parameter to
tascodec_init()
The tascodec_init() of the snd-soc-tas2781-comlib module is called from
snd-soc-tas2781-i2c and snd-hda-scodec-tas2781-i2c modules. It calls
request_firmware_nowait() with parameter THIS_MODULE and a cont/callback
from the latter modules.
The latter modules can be removed while their callbacks are running,
resulting in a general protection failure.
Add module parameter to tascodec_init() so request_firmware_nowait() can
be called with the module of the callback.
Fixes: ef3bcde75d06 ("ASoC: tas2781: Add tas2781 driver")
CC: stable@vger.kernel.org
Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://lore.kernel.org/r/118dad922cef50525e5aab09badef2fa0eb796e5.1707076603.git.soyer@irl.hu
Signed-off-by: Mark Brown <broonie@kernel.org>
---
include/sound/tas2781.h | 1 +
sound/pci/hda/tas2781_hda_i2c.c | 2 +-
sound/soc/codecs/tas2781-comlib.c | 3 ++-
sound/soc/codecs/tas2781-i2c.c | 2 +-
4 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index b00d65417c31..9aff384941de 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -142,6 +142,7 @@ struct tasdevice_priv {
void tas2781_reset(struct tasdevice_priv *tas_dev);
int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+ struct module *module,
void (*cont)(const struct firmware *fw, void *context));
struct tasdevice_priv *tasdevice_kzalloc(struct i2c_client *i2c);
int tasdevice_init(struct tasdevice_priv *tas_priv);
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 2dd809de62e5..1bfb00102a77 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -710,7 +710,7 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
strscpy(comps->name, dev_name(dev), sizeof(comps->name));
- ret = tascodec_init(tas_hda->priv, codec, tasdev_fw_ready);
+ ret = tascodec_init(tas_hda->priv, codec, THIS_MODULE, tasdev_fw_ready);
if (!ret)
comps->playback_hook = tas2781_hda_playback_hook;
diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
index b7e56ceb1acf..5d0e5348b361 100644
--- a/sound/soc/codecs/tas2781-comlib.c
+++ b/sound/soc/codecs/tas2781-comlib.c
@@ -267,6 +267,7 @@ void tas2781_reset(struct tasdevice_priv *tas_dev)
EXPORT_SYMBOL_GPL(tas2781_reset);
int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
+ struct module *module,
void (*cont)(const struct firmware *fw, void *context))
{
int ret = 0;
@@ -280,7 +281,7 @@ int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
tas_priv->dev_name, tas_priv->ndev);
crc8_populate_msb(tas_priv->crc8_lkp_tbl, TASDEVICE_CRC8_POLYNOMIAL);
tas_priv->codec = codec;
- ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT,
+ ret = request_firmware_nowait(module, FW_ACTION_UEVENT,
tas_priv->rca_binaryname, tas_priv->dev, GFP_KERNEL, tas_priv,
cont);
if (ret)
diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 32913bd1a623..b5abff230e43 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -566,7 +566,7 @@ static int tasdevice_codec_probe(struct snd_soc_component *codec)
{
struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(codec);
- return tascodec_init(tas_priv, codec, tasdevice_fw_ready);
+ return tascodec_init(tas_priv, codec, THIS_MODULE, tasdevice_fw_ready);
}
static void tasdevice_deinit(void *context)
From c712c05e46c8ce550842951e9e2606e24dbf0475 Mon Sep 17 00:00:00 2001
From: Carlos Song <carlos.song@nxp.com>
Date: Sun, 4 Feb 2024 17:19:12 +0800
Subject: [PATCH 216/637] spi: imx: fix the burst length at DMA mode and CPU
mode
For DMA mode, the bus width of the DMA is equal to the size of data
word, so burst length should be configured as bits per word.
For CPU mode, because of the spi transfer len is in byte, so calculate
the total number of words according to spi transfer len and bits per
word, burst length should be configured as total data bits.
Signed-off-by: Carlos Song <carlos.song@nxp.com>
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Fixes: e9b220aeacf1 ("spi: spi-imx: correctly configure burst length when using dma")
Fixes: 5f66db08cbd3 ("spi: imx: Take in account bits per word instead of assuming 8-bits")
Link: https://lore.kernel.org/r/20240204091912.36488-1-carlos.song@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-imx.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 546cdce525fc..833a1bb7a914 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -2,6 +2,7 @@
// Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
// Copyright (C) 2008 Juergen Beisert
+#include <linux/bits.h>
#include <linux/clk.h>
#include <linux/completion.h>
#include <linux/delay.h>
@@ -660,15 +661,15 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
<< MX51_ECSPI_CTRL_BL_OFFSET;
else {
if (spi_imx->usedma) {
- ctrl |= (spi_imx->bits_per_word *
- spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1)
+ ctrl |= (spi_imx->bits_per_word - 1)
<< MX51_ECSPI_CTRL_BL_OFFSET;
} else {
if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST)
- ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1)
+ ctrl |= (MX51_ECSPI_CTRL_MAX_BURST * BITS_PER_BYTE - 1)
<< MX51_ECSPI_CTRL_BL_OFFSET;
else
- ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1)
+ ctrl |= spi_imx->count / DIV_ROUND_UP(spi_imx->bits_per_word,
+ BITS_PER_BYTE) * spi_imx->bits_per_word
<< MX51_ECSPI_CTRL_BL_OFFSET;
}
}
From 5ea9a7c5fe4149f165f0e3b624fe08df02b6c301 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 5 Feb 2024 13:22:39 +1100
Subject: [PATCH 217/637] nfsd: don't take fi_lock in nfsd_break_deleg_cb()
A recent change to check_for_locks() changed it to take ->flc_lock while
holding ->fi_lock. This creates a lock inversion (reported by lockdep)
because there is a case where ->fi_lock is taken while holding
->flc_lock.
->flc_lock is held across ->fl_lmops callbacks, and
nfsd_break_deleg_cb() is one of those and does take ->fi_lock. However
it doesn't need to.
Prior to v4.17-rc1~110^2~22 ("nfsd: create a separate lease for each
delegation") nfsd_break_deleg_cb() would walk the ->fi_delegations list
and so needed the lock. Since then it doesn't walk the list and doesn't
need the lock.
Two actions are performed under the lock. One is to call
nfsd_break_one_deleg which calls nfsd4_run_cb(). These doesn't act on
the nfs4_file at all, so don't need the lock.
The other is to set ->fi_had_conflict which is in the nfs4_file.
This field is only ever set here (except when initialised to false)
so there is no possible problem will multiple threads racing when
setting it.
The field is tested twice in nfs4_set_delegation(). The first test does
not hold a lock and is documented as an opportunistic optimisation, so
it doesn't impose any need to hold ->fi_lock while setting
->fi_had_conflict.
The second test in nfs4_set_delegation() *is* make under ->fi_lock, so
removing the locking when ->fi_had_conflict is set could make a change.
The change could only be interesting if ->fi_had_conflict tested as
false even though nfsd_break_one_deleg() ran before ->fi_lock was
unlocked. i.e. while hash_delegation_locked() was running.
As hash_delegation_lock() doesn't interact in any way with nfs4_run_cb()
there can be no importance to this interaction.
So this patch removes the locking from nfsd_break_one_deleg() and moves
the final test on ->fi_had_conflict out of the locked region to make it
clear that locking isn't important to the test. It is still tested
*after* vfs_setlease() has succeeded. This might be significant and as
vfs_setlease() takes ->flc_lock, and nfsd_break_one_deleg() is called
under ->flc_lock this "after" is a true ordering provided by a spinlock.
Fixes: edcf9725150e ("nfsd: fix RELEASE_LOCKOWNER")
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs4state.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6dc6340e2852..7d6c657e0409 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4945,10 +4945,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
*/
fl->fl_break_time = 0;
- spin_lock(&fp->fi_lock);
fp->fi_had_conflict = true;
nfsd_break_one_deleg(dp);
- spin_unlock(&fp->fi_lock);
return false;
}
@@ -5557,12 +5555,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
if (status)
goto out_unlock;
+ status = -EAGAIN;
+ if (fp->fi_had_conflict)
+ goto out_unlock;
+
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
- if (fp->fi_had_conflict)
- status = -EAGAIN;
- else
- status = hash_delegation_locked(dp, fp);
+ status = hash_delegation_locked(dp, fp);
spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
From 17adc3f329e922bd1dd5aee45f43d9dab351c1e9 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 22 Jan 2024 11:35:14 -0600
Subject: [PATCH 218/637] net: marvell,prestera: Fix example PCI bus addressing
The example for PCI devices has some addressing errors. 'reg' is written
as if the parent bus is PCI, but the default bus for examples is 1
address and size cell. 'ranges' is defining config space with a
size of 0. Generally, config space should not be defined in
'ranges', only PCI memory and I/O spaces. Fix these issues by updating
the values with made-up, but valid values.
This was uncovered with recent dtschema changes.
Link: https://lore.kernel.org/r/20240122173514.935742-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
Documentation/devicetree/bindings/net/marvell,prestera.yaml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/marvell,prestera.yaml b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
index 5ea8b73663a5..16ff892f7bbd 100644
--- a/Documentation/devicetree/bindings/net/marvell,prestera.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,prestera.yaml
@@ -78,8 +78,8 @@ examples:
pcie@0 {
#address-cells = <3>;
#size-cells = <2>;
- ranges = <0x0 0x0 0x0 0x0 0x0 0x0>;
- reg = <0x0 0x0 0x0 0x0 0x0 0x0>;
+ ranges = <0x02000000 0x0 0x100000 0x10000000 0x0 0x0>;
+ reg = <0x0 0x1000>;
device_type = "pci";
switch@0,0 {
From 61712c94782ce105253ee1939cda0c5c025b2c0c Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 30 Jan 2024 13:26:43 +1000
Subject: [PATCH 219/637] nouveau/gsp: use correct size for registry rpc.
Timur pointed this out before, and it just slipped my mind,
but this might help some things work better, around pcie power
management.
Cc: <stable@vger.kernel.org> # v6.7
Fixes: 8d55b0a940bb ("nouveau/gsp: add some basic registry entries.")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240130032643.2498315-1-airlied@gmail.com
---
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9ee58e2a0eb2..5e1fa176aac4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1078,7 +1078,6 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
if (IS_ERR(rpc))
return PTR_ERR(rpc);
- rpc->size = sizeof(*rpc);
rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
@@ -1094,6 +1093,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp)
strings += name_len;
str_offset += name_len;
}
+ rpc->size = str_offset;
return nvkm_gsp_rpc_wr(gsp, rpc, false);
}
From 042b5f83841fbf7ce39474412db3b5e4765a7ea7 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Fri, 2 Feb 2024 17:06:07 -0600
Subject: [PATCH 220/637] drm/nouveau: fix several DMA buffer leaks
Nouveau manages GSP-RM DMA buffers with nvkm_gsp_mem objects. Several of
these buffers are never dealloced. Some of them can be deallocated
right after GSP-RM is initialized, but the rest need to stay until the
driver unloads.
Also futher bullet-proof these objects by poisoning the buffer and
clearing the nvkm_gsp_mem object when it is deallocated. Poisoning
the buffer should trigger an error (or crash) from GSP-RM if it tries
to access the buffer after we've deallocated it, because we were wrong
about when it is safe to deallocate.
Finally, change the mem->size field to a size_t because that's the same
type that dma_alloc_coherent expects.
Cc: <stable@vger.kernel.org> # v6.7
Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-1-ttabi@nvidia.com
---
.../gpu/drm/nouveau/include/nvkm/subdev/gsp.h | 2 +-
.../gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 59 ++++++++++++-------
2 files changed, 39 insertions(+), 22 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index d1437c08645f..6f5d376d8fcc 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -9,7 +9,7 @@
#define GSP_PAGE_SIZE BIT(GSP_PAGE_SHIFT)
struct nvkm_gsp_mem {
- u32 size;
+ size_t size;
void *data;
dma_addr_t addr;
};
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 5e1fa176aac4..6208ddd92964 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -997,6 +997,32 @@ r535_gsp_rpc_get_gsp_static_info(struct nvkm_gsp *gsp)
return 0;
}
+static void
+nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
+{
+ if (mem->data) {
+ /*
+ * Poison the buffer to catch any unexpected access from
+ * GSP-RM if the buffer was prematurely freed.
+ */
+ memset(mem->data, 0xFF, mem->size);
+
+ dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
+ memset(mem, 0, sizeof(*mem));
+ }
+}
+
+static int
+nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, size_t size, struct nvkm_gsp_mem *mem)
+{
+ mem->size = size;
+ mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
+ if (WARN_ON(!mem->data))
+ return -ENOMEM;
+
+ return 0;
+}
+
static int
r535_gsp_postinit(struct nvkm_gsp *gsp)
{
@@ -1024,6 +1050,13 @@ r535_gsp_postinit(struct nvkm_gsp *gsp)
nvkm_inth_allow(&gsp->subdev.inth);
nvkm_wr32(device, 0x110004, 0x00000040);
+
+ /* Release the DMA buffers that were needed only for boot and init */
+ nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw);
+ nvkm_gsp_mem_dtor(gsp, &gsp->libos);
+ nvkm_gsp_mem_dtor(gsp, &gsp->rmargs);
+ nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta);
+
return ret;
}
@@ -1532,27 +1565,6 @@ r535_gsp_msg_run_cpu_sequencer(void *priv, u32 fn, void *repv, u32 repc)
return 0;
}
-static void
-nvkm_gsp_mem_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_mem *mem)
-{
- if (mem->data) {
- dma_free_coherent(gsp->subdev.device->dev, mem->size, mem->data, mem->addr);
- mem->data = NULL;
- }
-}
-
-static int
-nvkm_gsp_mem_ctor(struct nvkm_gsp *gsp, u32 size, struct nvkm_gsp_mem *mem)
-{
- mem->size = size;
- mem->data = dma_alloc_coherent(gsp->subdev.device->dev, size, &mem->addr, GFP_KERNEL);
- if (WARN_ON(!mem->data))
- return -ENOMEM;
-
- return 0;
-}
-
-
static int
r535_gsp_booter_unload(struct nvkm_gsp *gsp, u32 mbox0, u32 mbox1)
{
@@ -2150,6 +2162,11 @@ r535_gsp_dtor(struct nvkm_gsp *gsp)
mutex_destroy(&gsp->cmdq.mutex);
r535_gsp_dtor_fws(gsp);
+
+ nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem);
+ nvkm_gsp_mem_dtor(gsp, &gsp->loginit);
+ nvkm_gsp_mem_dtor(gsp, &gsp->logintr);
+ nvkm_gsp_mem_dtor(gsp, &gsp->logrm);
}
int
From 34e659f34a7559ecfd9c1f5b24d4c291f3f54711 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Fri, 2 Feb 2024 17:06:08 -0600
Subject: [PATCH 221/637] drm/nouveau: nvkm_gsp_radix3_sg() should use
nvkm_gsp_mem_ctor()
Function nvkm_gsp_radix3_sg() uses nvkm_gsp_mem objects to allocate the
radix3 tables, but it unnecessarily creates those objects manually
instead of using the standard nvkm_gsp_mem_ctor() function like the
rest of the code does.
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-2-ttabi@nvidia.com
---
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 6208ddd92964..a41735ab6068 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1950,20 +1950,20 @@ nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
* See kgspCreateRadix3_IMPL
*/
static int
-nvkm_gsp_radix3_sg(struct nvkm_device *device, struct sg_table *sgt, u64 size,
+nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
struct nvkm_gsp_radix3 *rx3)
{
u64 addr;
for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
u64 *ptes;
- int idx;
+ size_t bufsize;
+ int ret, idx;
- rx3->mem[i].size = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
- rx3->mem[i].data = dma_alloc_coherent(device->dev, rx3->mem[i].size,
- &rx3->mem[i].addr, GFP_KERNEL);
- if (WARN_ON(!rx3->mem[i].data))
- return -ENOMEM;
+ bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+ ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
+ if (ret)
+ return ret;
ptes = rx3->mem[i].data;
if (i == 2) {
@@ -2003,7 +2003,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
if (ret)
return ret;
- ret = nvkm_gsp_radix3_sg(gsp->subdev.device, &gsp->sr.sgt, len, &gsp->sr.radix3);
+ ret = nvkm_gsp_radix3_sg(gsp, &gsp->sr.sgt, len, &gsp->sr.radix3);
if (ret)
return ret;
@@ -2211,7 +2211,7 @@ r535_gsp_oneinit(struct nvkm_gsp *gsp)
memcpy(gsp->sig.data, data, size);
/* Build radix3 page table for ELF image. */
- ret = nvkm_gsp_radix3_sg(device, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
+ ret = nvkm_gsp_radix3_sg(gsp, &gsp->fw.mem.sgt, gsp->fw.len, &gsp->radix3);
if (ret)
return ret;
From 0647903efbc84b772325b4d24d9487e24d6d1e03 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sat, 3 Feb 2024 14:24:46 +0100
Subject: [PATCH 222/637] wifi: mt76: mt7996: fix fortify warning
Copy cck and ofdm separately in order to avoid __read_overflow2_field
warning.
Fixes: f75e4779d215 ("wifi: mt76: mt7996: add txpower setting support")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://msgid.link/20240203132446.54790-1-nbd@nbd.name
---
drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 3c729b563edc..699be57309c2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4477,7 +4477,8 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
skb_put_data(skb, &req, sizeof(req));
/* cck and ofdm */
- skb_put_data(skb, &la.cck, sizeof(la.cck) + sizeof(la.ofdm));
+ skb_put_data(skb, &la.cck, sizeof(la.cck));
+ skb_put_data(skb, &la.ofdm, sizeof(la.ofdm));
/* ht20 */
skb_put_data(skb, &la.mcs[0], 8);
/* ht40 */
From 3376ca3f1a2075eaa23c5576c47d04d7e8a4adda Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Sat, 3 Feb 2024 13:45:20 +0100
Subject: [PATCH 223/637] KVM: x86: Fix KVM_GET_MSRS stack info leak
Commit 6abe9c1386e5 ("KVM: X86: Move ignore_msrs handling upper the
stack") changed the 'ignore_msrs' handling, including sanitizing return
values to the caller. This was fine until commit 12bc2132b15e ("KVM:
X86: Do the same ignore_msrs check for feature msrs") which allowed
non-existing feature MSRs to be ignored, i.e. to not generate an error
on the ioctl() level. It even tried to preserve the sanitization of the
return value. However, the logic is flawed, as '*data' will be
overwritten again with the uninitialized stack value of msr.data.
Fix this by simplifying the logic and always initializing msr.data,
vanishing the need for an additional error exit path.
Fixes: 12bc2132b15e ("KVM: X86: Do the same ignore_msrs check for feature msrs")
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20240203124522.592778-2-minipli@grsecurity.net
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/x86.c | 15 +++++----------
1 file changed, 5 insertions(+), 10 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 25bc52cdf8f4..3f6e82fd37f3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1704,22 +1704,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
struct kvm_msr_entry msr;
int r;
+ /* Unconditionally clear the output for simplicity */
+ msr.data = 0;
msr.index = index;
r = kvm_get_msr_feature(&msr);
- if (r == KVM_MSR_RET_INVALID) {
- /* Unconditionally clear the output for simplicity */
- *data = 0;
- if (kvm_msr_ignored_check(index, 0, false))
- r = 0;
- }
-
- if (r)
- return r;
+ if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false))
+ r = 0;
*data = msr.data;
- return 0;
+ return r;
}
static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
From 4e6c9011990726f4d175e2cdfebe5b0b8cce4839 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 3 Feb 2024 10:45:21 +0800
Subject: [PATCH 224/637] scsi: core: Move scsi_host_busy() out of host lock if
it is for per-command
Commit 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock
for waking up EH handler") intended to fix a hard lockup issue triggered by
EH. The core idea was to move scsi_host_busy() out of the host lock when
processing individual commands for EH. However, a suggested style change
inadvertently caused scsi_host_busy() to remain under the host lock. Fix
this by calling scsi_host_busy() outside the lock.
Fixes: 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler")
Cc: Sathya Prakash Veerichetty <safhya.prakash@broadcom.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240203024521.2006455-1-ming.lei@redhat.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/scsi_error.c | 3 ++-
drivers/scsi/scsi_lib.c | 4 +++-
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 4f455884fdc4..612489afe8d2 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -282,11 +282,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head)
{
struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu);
struct Scsi_Host *shost = scmd->device->host;
+ unsigned int busy = scsi_host_busy(shost);
unsigned long flags;
spin_lock_irqsave(shost->host_lock, flags);
shost->host_failed++;
- scsi_eh_wakeup(shost, scsi_host_busy(shost));
+ scsi_eh_wakeup(shost, busy);
spin_unlock_irqrestore(shost->host_lock, flags);
}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1fb80eae9a63..df5ac03d5d6c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -278,9 +278,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
rcu_read_lock();
__clear_bit(SCMD_STATE_INFLIGHT, &cmd->state);
if (unlikely(scsi_host_in_recovery(shost))) {
+ unsigned int busy = scsi_host_busy(shost);
+
spin_lock_irqsave(shost->host_lock, flags);
if (shost->host_failed || shost->host_eh_scheduled)
- scsi_eh_wakeup(shost, scsi_host_busy(shost));
+ scsi_eh_wakeup(shost, busy);
spin_unlock_irqrestore(shost->host_lock, flags);
}
rcu_read_unlock();
From d6c1b19153f92e95e5e1801d540e98771053afae Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 20 Dec 2023 17:26:58 +0100
Subject: [PATCH 225/637] scsi: lpfc: Use unsigned type for num_sge
LUNs going into "failed ready running" state observed on >1T and on even
numbers of size (2T, 4T, 6T, 8T and 10T). The issue occurs when DIF is
enabled at the host.
The kernel logs:
Cannot setup S/G List for HBAIO segs 1/1 SGL 512 SCSI 256: 3 0
The host lpfc driver is failing to setup scatter/gather list (protection
data) for the I/Os.
The return type lpfc_bg_setup_sgl()/lpfc_bg_setup_sgl_prot() causes the
compiler to remove the most significant bit. Use an unsigned type instead.
Signed-off-by: Hannes Reinecke <hare@suse.de>
[dwagner: added commit message]
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Link: https://lore.kernel.org/r/20231220162658.12392-1-dwagner@suse.de
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/lpfc/lpfc_scsi.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index d26941b131fd..bf879d81846b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1918,7 +1918,7 @@ out:
*
* Returns the number of SGEs added to the SGL.
**/
-static int
+static uint32_t
lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
struct sli4_sge *sgl, int datasegcnt,
struct lpfc_io_buf *lpfc_cmd)
@@ -1926,8 +1926,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc,
struct scatterlist *sgde = NULL; /* s/g data entry */
struct sli4_sge_diseed *diseed = NULL;
dma_addr_t physaddr;
- int i = 0, num_sge = 0, status;
- uint32_t reftag;
+ int i = 0, status;
+ uint32_t reftag, num_sge = 0;
uint8_t txop, rxop;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
uint32_t rc;
@@ -2099,7 +2099,7 @@ out:
*
* Returns the number of SGEs added to the SGL.
**/
-static int
+static uint32_t
lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
struct sli4_sge *sgl, int datacnt, int protcnt,
struct lpfc_io_buf *lpfc_cmd)
@@ -2123,8 +2123,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc,
uint32_t rc;
#endif
uint32_t checking = 1;
- uint32_t dma_offset = 0;
- int num_sge = 0, j = 2;
+ uint32_t dma_offset = 0, num_sge = 0;
+ int j = 2;
struct sli4_hybrid_sgl *sgl_xtra = NULL;
sgpe = scsi_prot_sglist(sc);
From b513d30d59bb383a6a5d6b533afcab2cee99a8f8 Mon Sep 17 00:00:00 2001
From: Alice Chao <alice.chao@mediatek.com>
Date: Mon, 5 Feb 2024 18:49:04 +0800
Subject: [PATCH 226/637] scsi: ufs: core: Fix shift issue in
ufshcd_clear_cmd()
When task_tag >= 32 (in MCQ mode) and sizeof(unsigned int) == 4, 1U <<
task_tag will out of bounds for a u32 mask. Fix this up to prevent
SHIFT_ISSUE (bitwise shifts that are out of bounds for their data type).
[name:debug_monitors&]Unexpected kernel BRK exception at EL1
[name:traps&]Internal error: BRK handler: 00000000f2005514 [#1] PREEMPT SMP
[name:mediatek_cpufreq_hw&]cpufreq stop DVFS log done
[name:mrdump&]Kernel Offset: 0x1ba5800000 from 0xffffffc008000000
[name:mrdump&]PHYS_OFFSET: 0x80000000
[name:mrdump&]pstate: 22400005 (nzCv daif +PAN -UAO)
[name:mrdump&]pc : [0xffffffdbaf52bb2c] ufshcd_clear_cmd+0x280/0x288
[name:mrdump&]lr : [0xffffffdbaf52a774] ufshcd_wait_for_dev_cmd+0x3e4/0x82c
[name:mrdump&]sp : ffffffc0081471b0
<snip>
Workqueue: ufs_eh_wq_0 ufshcd_err_handler
Call trace:
dump_backtrace+0xf8/0x144
show_stack+0x18/0x24
dump_stack_lvl+0x78/0x9c
dump_stack+0x18/0x44
mrdump_common_die+0x254/0x480 [mrdump]
ipanic_die+0x20/0x30 [mrdump]
notify_die+0x15c/0x204
die+0x10c/0x5f8
arm64_notify_die+0x74/0x13c
do_debug_exception+0x164/0x26c
el1_dbg+0x64/0x80
el1h_64_sync_handler+0x3c/0x90
el1h_64_sync+0x68/0x6c
ufshcd_clear_cmd+0x280/0x288
ufshcd_wait_for_dev_cmd+0x3e4/0x82c
ufshcd_exec_dev_cmd+0x5bc/0x9ac
ufshcd_verify_dev_init+0x84/0x1c8
ufshcd_probe_hba+0x724/0x1ce0
ufshcd_host_reset_and_restore+0x260/0x574
ufshcd_reset_and_restore+0x138/0xbd0
ufshcd_err_handler+0x1218/0x2f28
process_one_work+0x5fc/0x1140
worker_thread+0x7d8/0xe20
kthread+0x25c/0x468
ret_from_fork+0x10/0x20
Signed-off-by: Alice Chao <alice.chao@mediatek.com>
Link: https://lore.kernel.org/r/20240205104905.24929-1-alice.chao@mediatek.com
Reviewed-by: Stanley Jhu <chu.stanley@gmail.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/ufs/core/ufshcd.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 029d017fc1b6..c6cff4aa440a 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3057,7 +3057,7 @@ bool ufshcd_cmd_inflight(struct scsi_cmnd *cmd)
*/
static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
{
- u32 mask = 1U << task_tag;
+ u32 mask;
unsigned long flags;
int err;
@@ -3075,6 +3075,8 @@ static int ufshcd_clear_cmd(struct ufs_hba *hba, u32 task_tag)
return 0;
}
+ mask = 1U << task_tag;
+
/* clear outstanding transaction before retry */
spin_lock_irqsave(hba->host->host_lock, flags);
ufshcd_utrl_clear(hba, mask);
From 17e94b2585417e04dabc2f13bc03b4665ae687f3 Mon Sep 17 00:00:00 2001
From: SEO HOYOUNG <hy50.seo@samsung.com>
Date: Mon, 22 Jan 2024 17:33:24 +0900
Subject: [PATCH 227/637] scsi: ufs: core: Remove the ufshcd_release() in
ufshcd_err_handling_prepare()
If ufshcd_err_handler() is called in a suspend/resume situation,
ufs_release() can be called twice and active_reqs end up going negative.
This is because ufshcd_err_handling_prepare() and
ufshcd_err_handling_unprepare() both call ufshcd_release().
Remove superfluous call to ufshcd_release().
Signed-off-by: SEO HOYOUNG <hy50.seo@samsung.com>
Link: https://lore.kernel.org/r/20240122083324.11797-1-hy50.seo@samsung.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/ufs/core/ufshcd.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index c6cff4aa440a..d77b25b79ae3 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6354,7 +6354,6 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
ufshcd_hold(hba);
if (!ufshcd_is_clkgating_allowed(hba))
ufshcd_setup_clocks(hba, true);
- ufshcd_release(hba);
pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM;
ufshcd_vops_resume(hba, pm_op);
} else {
From aac8a59537dfc704ff344f1aacfd143c089ee20f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 5 Feb 2024 15:43:41 -1000
Subject: [PATCH 228/637] Revert "workqueue: Override implicit ordered
attribute in workqueue_apply_unbound_cpumask()"
This reverts commit ca10d851b9ad0338c19e8e3089e24d565ebfffd7.
The commit allowed workqueue_apply_unbound_cpumask() to clear __WQ_ORDERED
on now removed implicitly ordered workqueues. This was incorrect in that
system-wide config change shouldn't break ordering properties of all
workqueues. The reason why apply_workqueue_attrs() path was allowed to do so
was because it was targeting the specific workqueue - either the workqueue
had WQ_SYSFS set or the workqueue user specifically tried to change
max_active, both of which indicate that the workqueue doesn't need to be
ordered.
The implicitly ordered workqueue promotion was removed by the previous
commit 3bc1e711c26b ("workqueue: Don't implicitly make UNBOUND workqueues w/
@max_active==1 ordered"). However, it didn't update this path and broke
build. Let's revert the commit which was incorrect in the first place which
also fixes build.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 3bc1e711c26b ("workqueue: Don't implicitly make UNBOUND workqueues w/ @max_active==1 ordered")
Fixes: ca10d851b9ad ("workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()")
Cc: stable@vger.kernel.org # v6.6+
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/workqueue.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 76e60faed892..7b482a26d741 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -5786,13 +5786,9 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
list_for_each_entry(wq, &workqueues, list) {
if (!(wq->flags & WQ_UNBOUND))
continue;
-
/* creating multiple pwqs breaks ordering guarantee */
- if (!list_empty(&wq->pwqs)) {
- if (wq->flags & __WQ_ORDERED_EXPLICIT)
- continue;
- wq->flags &= ~__WQ_ORDERED;
- }
+ if (wq->flags & __WQ_ORDERED)
+ continue;
ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask);
if (IS_ERR(ctx)) {
From d0399da9fb5f8e3d897b9776bffee2d3bfe20210 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 29 Jan 2024 19:04:13 -0800
Subject: [PATCH 229/637] drm/sched: Re-queue run job worker when
drm_sched_entity_pop_job() returns NULL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Rather then loop over entities until one with a ready job is found,
re-queue the run job worker when drm_sched_entity_pop_job() returns NULL.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Fixes: 66dbd9004a55 ("drm/sched: Drain all entities in DRM sched run job worker")
Reviewed-by: Luben Tuikov <ltuikov89@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240130030413.2031009-1-matthew.brost@intel.com
---
drivers/gpu/drm/scheduler/sched_main.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 85f082396d42..d442b893275b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1178,21 +1178,24 @@ static void drm_sched_run_job_work(struct work_struct *w)
struct drm_sched_entity *entity;
struct dma_fence *fence;
struct drm_sched_fence *s_fence;
- struct drm_sched_job *sched_job = NULL;
+ struct drm_sched_job *sched_job;
int r;
if (READ_ONCE(sched->pause_submit))
return;
/* Find entity with a ready job */
- while (!sched_job && (entity = drm_sched_select_entity(sched))) {
- sched_job = drm_sched_entity_pop_job(entity);
- if (!sched_job)
- complete_all(&entity->entity_idle);
- }
+ entity = drm_sched_select_entity(sched);
if (!entity)
return; /* No more work */
+ sched_job = drm_sched_entity_pop_job(entity);
+ if (!sched_job) {
+ complete_all(&entity->entity_idle);
+ drm_sched_run_job_queue(sched);
+ return;
+ }
+
s_fence = sched_job->s_fence;
atomic_add(sched_job->credits, &sched->credit_count);
From b3ff2d9c3a9c64cd0a011cdd407ffc38a6ea8788 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 230/637] LoongArch: Select ARCH_ENABLE_THP_MIGRATION instead
of redefining it
ARCH_ENABLE_THP_MIGRATION is supposed to be selected by arch Kconfig.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/Kconfig | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 10959e6c3583..64e9a01c7f36 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -12,6 +12,7 @@ config LOONGARCH
select ARCH_DISABLE_KASAN_INLINE
select ARCH_ENABLE_MEMORY_HOTPLUG
select ARCH_ENABLE_MEMORY_HOTREMOVE
+ select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_FORTIFY_SOURCE
@@ -667,10 +668,6 @@ config ARCH_SPARSEMEM_ENABLE
or have huge holes in the physical address space for other reasons.
See <file:Documentation/mm/numa.rst> for more.
-config ARCH_ENABLE_THP_MIGRATION
- def_bool y
- depends on TRANSPARENT_HUGEPAGE
-
config ARCH_MEMORY_PROBE
def_bool y
depends on MEMORY_HOTPLUG
From 6b79ecd084c99b31c8b4d0beda08893716d5558e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 231/637] LoongArch: Select HAVE_ARCH_SECCOMP to use the common
SECCOMP menu
LoongArch missed the refactoring made by commit 282a181b1a0d ("seccomp:
Move config option SECCOMP to arch/Kconfig") because LoongArch was not
mainlined at that time.
The 'depends on PROC_FS' statement is stale as described in that commit.
Select HAVE_ARCH_SECCOMP, and remove the duplicated config entry.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/Kconfig | 18 +-----------------
1 file changed, 1 insertion(+), 17 deletions(-)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 64e9a01c7f36..929f68926b34 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -100,6 +100,7 @@ config LOONGARCH
select HAVE_ARCH_KFENCE
select HAVE_ARCH_KGDB if PERF_EVENTS
select HAVE_ARCH_MMAP_RND_BITS if MMU
+ select HAVE_ARCH_SECCOMP
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
@@ -633,23 +634,6 @@ config RANDOMIZE_BASE_MAX_OFFSET
This is limited by the size of the lower address memory, 256MB.
-config SECCOMP
- bool "Enable seccomp to safely compute untrusted bytecode"
- depends on PROC_FS
- default y
- help
- This kernel feature is useful for number crunching applications
- that may need to compute untrusted bytecode during their
- execution. By using pipes or other transports made available to
- the process as file descriptors supporting the read/write
- syscalls, it's possible to isolate those applications in
- their own address space using seccomp. Once seccomp is
- enabled via /proc/<pid>/seccomp, it cannot be disabled
- and the task is only allowed to execute a few safe syscalls
- defined by each seccomp mode.
-
- If unsure, say Y. Only embedded should say N here.
-
endmenu
config ARCH_SELECT_MEMORY_MODEL
From 4551b30525cf3d2f026b92401ffe241eb04dfebe Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 232/637] LoongArch: Change acpi_core_pic[NR_CPUS] to
acpi_core_pic[MAX_CORE_PIC]
With default config, the value of NR_CPUS is 64. When HW platform has
more then 64 cpus, system will crash on these platforms. MAX_CORE_PIC
is the maximum cpu number in MADT table (max physical number) which can
exceed the supported maximum cpu number (NR_CPUS, max logical number),
but kernel should not crash. Kernel should boot cpus with NR_CPUS, let
the remainder cpus stay in BIOS.
The potential crash reason is that the array acpi_core_pic[NR_CPUS] can
be overflowed when parsing MADT table, and it is obvious that CORE_PIC
should be corresponding to physical core rather than logical core, so it
is better to define the array as acpi_core_pic[MAX_CORE_PIC].
With the patch, system can boot up 64 vcpus with qemu parameter -smp 128,
otherwise system will crash with the following message.
[ 0.000000] CPU 0 Unable to handle kernel paging request at virtual address 0000420000004259, era == 90000000037a5f0c, ra == 90000000037a46ec
[ 0.000000] Oops[#1]:
[ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 6.8.0-rc2+ #192
[ 0.000000] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
[ 0.000000] pc 90000000037a5f0c ra 90000000037a46ec tp 9000000003c90000 sp 9000000003c93d60
[ 0.000000] a0 0000000000000019 a1 9000000003d93bc0 a2 0000000000000000 a3 9000000003c93bd8
[ 0.000000] a4 9000000003c93a74 a5 9000000083c93a67 a6 9000000003c938f0 a7 0000000000000005
[ 0.000000] t0 0000420000004201 t1 0000000000000000 t2 0000000000000001 t3 0000000000000001
[ 0.000000] t4 0000000000000003 t5 0000000000000000 t6 0000000000000030 t7 0000000000000063
[ 0.000000] t8 0000000000000014 u0 ffffffffffffffff s9 0000000000000000 s0 9000000003caee98
[ 0.000000] s1 90000000041b0480 s2 9000000003c93da0 s3 9000000003c93d98 s4 9000000003c93d90
[ 0.000000] s5 9000000003caa000 s6 000000000a7fd000 s7 000000000f556b60 s8 000000000e0a4330
[ 0.000000] ra: 90000000037a46ec platform_init+0x214/0x250
[ 0.000000] ERA: 90000000037a5f0c efi_runtime_init+0x30/0x94
[ 0.000000] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
[ 0.000000] PRMD: 00000000 (PPLV0 -PIE -PWE)
[ 0.000000] EUEN: 00000000 (-FPE -SXE -ASXE -BTE)
[ 0.000000] ECFG: 00070800 (LIE=11 VS=7)
[ 0.000000] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0)
[ 0.000000] BADV: 0000420000004259
[ 0.000000] PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
[ 0.000000] Modules linked in:
[ 0.000000] Process swapper (pid: 0, threadinfo=(____ptrval____), task=(____ptrval____))
[ 0.000000] Stack : 9000000003c93a14 9000000003800898 90000000041844f8 90000000037a46ec
[ 0.000000] 000000000a7fd000 0000000008290000 0000000000000000 0000000000000000
[ 0.000000] 0000000000000000 0000000000000000 00000000019d8000 000000000f556b60
[ 0.000000] 000000000a7fd000 000000000f556b08 9000000003ca7700 9000000003800000
[ 0.000000] 9000000003c93e50 9000000003800898 9000000003800108 90000000037a484c
[ 0.000000] 000000000e0a4330 000000000f556b60 000000000a7fd000 000000000f556b08
[ 0.000000] 9000000003ca7700 9000000004184000 0000000000200000 000000000e02b018
[ 0.000000] 000000000a7fd000 90000000037a0790 9000000003800108 0000000000000000
[ 0.000000] 0000000000000000 000000000e0a4330 000000000f556b60 000000000a7fd000
[ 0.000000] 000000000f556b08 000000000eaae298 000000000eaa5040 0000000000200000
[ 0.000000] ...
[ 0.000000] Call Trace:
[ 0.000000] [<90000000037a5f0c>] efi_runtime_init+0x30/0x94
[ 0.000000] [<90000000037a46ec>] platform_init+0x214/0x250
[ 0.000000] [<90000000037a484c>] setup_arch+0x124/0x45c
[ 0.000000] [<90000000037a0790>] start_kernel+0x90/0x670
[ 0.000000] [<900000000378b0d8>] kernel_entry+0xd8/0xdc
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/acpi.h | 4 +++-
arch/loongarch/kernel/acpi.c | 4 +---
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index 8de6c4b83a61..49e29b29996f 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
return true;
}
+#define MAX_CORE_PIC 256
+
extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
extern int __init parse_acpi_topology(void);
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index b6b097bbf866..5cf59c617126 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -29,11 +29,9 @@ int disabled_cpus;
u64 acpi_saved_sp;
-#define MAX_CORE_PIC 256
-
#define PREFIX "ACPI: "
-struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
{
From 639420e9f6cd9ca074732b17ac450d2518d5937f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 233/637] LoongArch: Fix earlycon parameter if KASAN enabled
The earlycon parameter is based on fixmap, and fixmap addresses are not
supposed to be shadowed by KASAN. So return the kasan_early_shadow_page
in kasan_mem_to_shadow() if the input address is above FIXADDR_START.
Otherwise earlycon cannot work after kasan_init().
Cc: stable@vger.kernel.org
Fixes: 5aa4ac64e6add3e ("LoongArch: Add KASAN (Kernel Address Sanitizer) support")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/mm/kasan_init.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index cc3e81fe0186..c608adc99845 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr)
unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
unsigned long offset = 0;
+ if (maddr >= FIXADDR_START)
+ return (void *)(kasan_early_shadow_page);
+
maddr &= XRANGE_SHADOW_MASK;
switch (xrange) {
case XKPRANGE_CC_SEG:
From cca5efe77a6a2d02b3da4960f799fa233e460ab1 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 6 Feb 2024 12:32:05 +0800
Subject: [PATCH 234/637] LoongArch: vDSO: Disable UBSAN instrumentation
The vDSO executes in userspace, so the kernel's UBSAN should not
instrument it. Solves these kind of build errors:
loongarch64-linux-ld: arch/loongarch/vdso/vgettimeofday.o: in function `vdso_shift_ns':
lib/vdso/gettimeofday.c:23:(.text+0x3f8): undefined reference to `__ubsan_handle_shift_out_of_bounds'
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401310530.lZHCj1Zl-lkp@intel.com/
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Fangrui Song <maskray@google.com>
Cc: loongarch@lists.linux.dev
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/vdso/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index c74c9921304f..f597cd08a96b 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -2,6 +2,7 @@
# Objects to go into the VDSO.
KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
KCOV_INSTRUMENT := n
# Include the generic Makefile to check the built vdso.
From 3871aa01e1a779d866fa9dfdd5a836f342f4eb87 Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <syoshida@redhat.com>
Date: Thu, 1 Feb 2024 00:23:09 +0900
Subject: [PATCH 235/637] tipc: Check the bearer type before calling
tipc_udp_nl_bearer_add()
syzbot reported the following general protection fault [1]:
general protection fault, probably for non-canonical address 0xdffffc0000000010: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000080-0x0000000000000087]
...
RIP: 0010:tipc_udp_is_known_peer+0x9c/0x250 net/tipc/udp_media.c:291
...
Call Trace:
<TASK>
tipc_udp_nl_bearer_add+0x212/0x2f0 net/tipc/udp_media.c:646
tipc_nl_bearer_add+0x21e/0x360 net/tipc/bearer.c:1089
genl_family_rcv_msg_doit+0x1fc/0x2e0 net/netlink/genetlink.c:972
genl_family_rcv_msg net/netlink/genetlink.c:1052 [inline]
genl_rcv_msg+0x561/0x800 net/netlink/genetlink.c:1067
netlink_rcv_skb+0x16b/0x440 net/netlink/af_netlink.c:2544
genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076
netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
netlink_unicast+0x53b/0x810 net/netlink/af_netlink.c:1367
netlink_sendmsg+0x8b7/0xd70 net/netlink/af_netlink.c:1909
sock_sendmsg_nosec net/socket.c:730 [inline]
__sock_sendmsg+0xd5/0x180 net/socket.c:745
____sys_sendmsg+0x6ac/0x940 net/socket.c:2584
___sys_sendmsg+0x135/0x1d0 net/socket.c:2638
__sys_sendmsg+0x117/0x1e0 net/socket.c:2667
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x63/0x6b
The cause of this issue is that when tipc_nl_bearer_add() is called with
the TIPC_NLA_BEARER_UDP_OPTS attribute, tipc_udp_nl_bearer_add() is called
even if the bearer is not UDP.
tipc_udp_is_known_peer() called by tipc_udp_nl_bearer_add() assumes that
the media_ptr field of the tipc_bearer has an udp_bearer type object, so
the function goes crazy for non-UDP bearers.
This patch fixes the issue by checking the bearer type before calling
tipc_udp_nl_bearer_add() in tipc_nl_bearer_add().
Fixes: ef20cd4dd163 ("tipc: introduce UDP replicast")
Reported-and-tested-by: syzbot+5142b87a9abc510e14fa@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5142b87a9abc510e14fa [1]
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Reviewed-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Link: https://lore.kernel.org/r/20240131152310.4089541-1-syoshida@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/tipc/bearer.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2cde375477e3..878415c43527 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1086,6 +1086,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
#ifdef CONFIG_TIPC_MEDIA_UDP
if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) {
+ if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) {
+ rtnl_unlock();
+ NL_SET_ERR_MSG(info->extack, "UDP option is unsupported");
+ return -EINVAL;
+ }
+
err = tipc_udp_nl_bearer_add(b,
attrs[TIPC_NLA_BEARER_UDP_OPTS]);
if (err) {
From e459647710070684a48384d67742822379de8c1c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 2 Feb 2024 16:53:21 -0700
Subject: [PATCH 236/637] x86/coco: Define cc_vendor without
CONFIG_ARCH_HAS_CC_PLATFORM
After commit a9ef277488cf ("x86/kvm: Fix SEV check in
sev_map_percpu_data()"), there is a build error when building
x86_64_defconfig with GCOV using LLVM:
ld.lld: error: undefined symbol: cc_vendor
>>> referenced by kvm.c
>>> arch/x86/kernel/kvm.o:(kvm_smp_prepare_boot_cpu) in archive vmlinux.a
which corresponds to
if (cc_vendor != CC_VENDOR_AMD ||
!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
Without GCOV, clang is able to eliminate the use of cc_vendor because
cc_platform_has() evaluates to false when CONFIG_ARCH_HAS_CC_PLATFORM is
not set, meaning that if statement will be true no matter what value
cc_vendor has.
With GCOV, the instrumentation keeps the use of cc_vendor around for
code coverage purposes but cc_vendor is only declared, not defined,
without CONFIG_ARCH_HAS_CC_PLATFORM, leading to the build error above.
Provide a macro definition of cc_vendor when CONFIG_ARCH_HAS_CC_PLATFORM
is not set with a value of CC_VENDOR_NONE, so that the first condition
can always be evaluated/eliminated at compile time, avoiding the build
error altogether. This is very similar to the situation prior to
commit da86eb961184 ("x86/coco: Get rid of accessor functions").
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Message-Id: <20240202-provide-cc_vendor-without-arch_has_cc_platform-v1-1-09ad5f2a3099@kernel.org>
Fixes: a9ef277488cf ("x86/kvm: Fix SEV check in sev_map_percpu_data()", 2024-01-31)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/coco.h | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 6ae2d16a7613..76c310b19b11 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -10,13 +10,14 @@ enum cc_vendor {
CC_VENDOR_INTEL,
};
-extern enum cc_vendor cc_vendor;
-
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
void cc_set_mask(u64 mask);
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
#else
+#define cc_vendor (CC_VENDOR_NONE)
+
static inline u64 cc_mkenc(u64 val)
{
return val;
From b083d24fcf57580cc0b45dd7b0b4f84d8c4624f4 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Fri, 2 Feb 2024 02:24:59 +0000
Subject: [PATCH 237/637] selftests/net: Amend per-netns counter checks
Selftests here check not only that connect()/accept() for
TCP-AO/TCP-MD5/non-signed-TCP combinations do/don't establish
connections, but also counters: those are per-AO-key, per-socket and
per-netns.
The counters are checked on the server's side, as the server listener
has TCP-AO/TCP-MD5/no keys for different peers. All tests run in
the same namespaces with the same veth pair, created in test_init().
After close() in both client and server, the sides go through
the regular FIN/ACK + FIN/ACK sequence, which goes in the background.
If the selftest has already started a new testing scenario, read
per-netns counters - it may fail in the end iff it doesn't expect
the TCPAOGood per-netns counters go up during the test.
Let's just kill both TCP-AO sides - that will avoid any asynchronous
background TCP-AO segments going to either sides.
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/all/20240201132153.4d68f45e@kernel.org/T/#u
Fixes: 6f0c472a6815 ("selftests/net: Add TCP-AO + TCP-MD5 + no sign listen socket tests")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Link: https://lore.kernel.org/r/20240202-unsigned-md5-netns-counters-v1-1-8b90c37c0566@arista.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
tools/testing/selftests/net/tcp_ao/unsigned-md5.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index c5b568cd7d90..6b59a652159f 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -110,9 +110,9 @@ static void try_accept(const char *tst_name, unsigned int port,
test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
out:
- synchronize_threads(); /* close() */
+ synchronize_threads(); /* test_kill_sk() */
if (sk > 0)
- close(sk);
+ test_kill_sk(sk);
}
static void server_add_routes(void)
@@ -302,10 +302,10 @@ static void try_connect(const char *tst_name, unsigned int port,
test_ok("%s: connected", tst_name);
out:
- synchronize_threads(); /* close() */
+ synchronize_threads(); /* test_kill_sk() */
/* _test_connect_socket() cleans up on failure */
if (ret > 0)
- close(sk);
+ test_kill_sk(sk);
}
#define PREINSTALL_MD5_FIRST BIT(0)
@@ -486,10 +486,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
}
out:
- synchronize_threads(); /* close() */
+ synchronize_threads(); /* test_kill_sk() */
/* _test_connect_socket() cleans up on failure */
if (ret > 0)
- close(sk);
+ test_kill_sk(sk);
}
static void client_add_ip(union tcp_addr *client, const char *ip)
From 610010737f74482a61896596a0116876ecf9e65c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 5 Feb 2024 15:48:53 -0600
Subject: [PATCH 238/637] ASoC: amd: yc: Add DMI quirk for Lenovo Ideapad Pro 5
16ARP8
The laptop requires a quirk ID to enable its internal microphone. Add
it to the DMI quirk table.
Reported-by: Stanislav Petrov <stanislav.i.petrov@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=216925
Cc: stable@vger.kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20240205214853.2689-1-mario.limonciello@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 23d44a50d815..80ad60d485ea 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -248,6 +248,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "82YM"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "83AS"),
+ }
+ },
{
.driver_data = &acp6x_card,
.matches = {
From dad6a09f3148257ac1773cd90934d721d68ab595 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Mon, 29 Jan 2024 15:56:36 -0800
Subject: [PATCH 239/637] hrtimer: Report offline hrtimer enqueue
The hrtimers migration on CPU-down hotplug process has been moved
earlier, before the CPU actually goes to die. This leaves a small window
of opportunity to queue an hrtimer in a blind spot, leaving it ignored.
For example a practical case has been reported with RCU waking up a
SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that
way a sched/rt timer to the local offline CPU.
Make sure such situations never go unnoticed and warn when that happens.
Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240129235646.3171983-4-boqun.feng@gmail.com
---
include/linux/hrtimer.h | 4 +++-
kernel/time/hrtimer.c | 3 +++
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 87e3bedf8eb0..641c4567cfa7 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -157,6 +157,7 @@ enum hrtimer_base_type {
* @max_hang_time: Maximum time spent in hrtimer_interrupt
* @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
* expired
+ * @online: CPU is online from an hrtimers point of view
* @timer_waiters: A hrtimer_cancel() invocation waits for the timer
* callback to finish.
* @expires_next: absolute time of the next event, is required for remote
@@ -179,7 +180,8 @@ struct hrtimer_cpu_base {
unsigned int hres_active : 1,
in_hrtirq : 1,
hang_detected : 1,
- softirq_activated : 1;
+ softirq_activated : 1,
+ online : 1;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int nr_events;
unsigned short nr_retries;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 760793998cdd..edb0f821dcea 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
enum hrtimer_mode mode)
{
debug_activate(timer, mode);
+ WARN_ON_ONCE(!base->cpu_base->online);
base->cpu_base->active_bases |= 1 << base->index;
@@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
cpu_base->softirq_next_timer = NULL;
cpu_base->expires_next = KTIME_MAX;
cpu_base->softirq_expires_next = KTIME_MAX;
+ cpu_base->online = 1;
hrtimer_cpu_base_init_expiry_lock(cpu_base);
return 0;
}
@@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
raw_spin_unlock(&new_base->lock);
+ old_base->online = 0;
raw_spin_unlock(&old_base->lock);
return 0;
From 5c84bc8b617bf90e722cc57d447abd9a468d3a52 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Jan 2024 13:51:41 +0100
Subject: [PATCH 240/637] powerpc: udbg_memcons: mark functions static
ppc64_book3e_allmodconfig has one more driver that triggeres a
few missing-prototypes warnings:
arch/powerpc/sysdev/udbg_memcons.c:44:6: error: no previous prototype for 'memcons_putc' [-Werror=missing-prototypes]
arch/powerpc/sysdev/udbg_memcons.c:57:5: error: no previous prototype for 'memcons_getc_poll' [-Werror=missing-prototypes]
arch/powerpc/sysdev/udbg_memcons.c:80:5: error: no previous prototype for 'memcons_getc' [-Werror=missing-prototypes]
Mark all these function static as there are no other users.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240123125148.2004648-1-arnd@kernel.org
---
arch/powerpc/sysdev/udbg_memcons.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 5020044400dc..4de57ba52236 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -41,7 +41,7 @@ struct memcons memcons = {
.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
};
-void memcons_putc(char c)
+static void memcons_putc(char c)
{
char *new_output_pos;
@@ -54,7 +54,7 @@ void memcons_putc(char c)
memcons.output_pos = new_output_pos;
}
-int memcons_getc_poll(void)
+static int memcons_getc_poll(void)
{
char c;
char *new_input_pos;
@@ -77,7 +77,7 @@ int memcons_getc_poll(void)
return -1;
}
-int memcons_getc(void)
+static int memcons_getc(void)
{
int c;
From 1c57b9f63ab34f01b8c73731cc0efacb5a9a2f16 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 23 Jan 2024 13:51:42 +0100
Subject: [PATCH 241/637] powerpc: 85xx: mark local functions static
These functions are either used in only one file and can just be
made static or need an #include statement to avoid a warning:
arch/powerpc/platforms/85xx/mpc8536_ds.c:30:13: error: no previous prototype for 'mpc8536_ds_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1010rdb.c:27:13: error: no previous prototype for 'p1010_rdb_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_ds.c:373:6: error: no previous prototype for 'p1022ds_set_pixel_clock' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_ds.c:422:1: error: no previous prototype for 'p1022ds_valid_monitor_port' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_ds.c:435:13: error: no previous prototype for 'p1022_ds_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_rdk.c:43:6: error: no previous prototype for 'p1022rdk_set_pixel_clock' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_rdk.c:92:1: error: no previous prototype for 'p1022rdk_valid_monitor_port' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/p1022_rdk.c:99:13: error: no previous prototype for 'p1022_rdk_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/socrates_fpga_pic.c:273:13: error: no previous prototype for 'socrates_fpga_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/xes_mpc85xx.c:40:13: error: no previous prototype for 'xes_mpc85xx_pic_init' [-Werror=missing-prototypes]
arch/powerpc/platforms/85xx/mvme2500.c:24:13: error: no previous prototype for 'mvme2500_pic_init' [-Werror=missing-prototypes]
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240123125148.2004648-2-arnd@kernel.org
---
arch/powerpc/platforms/85xx/mpc8536_ds.c | 2 +-
arch/powerpc/platforms/85xx/mvme2500.c | 2 +-
arch/powerpc/platforms/85xx/p1010rdb.c | 2 +-
arch/powerpc/platforms/85xx/p1022_ds.c | 6 +++---
arch/powerpc/platforms/85xx/p1022_rdk.c | 6 +++---
arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 ++
arch/powerpc/platforms/85xx/xes_mpc85xx.c | 2 +-
7 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index e966b2ad8ecd..b3327a358eb4 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -27,7 +27,7 @@
#include "mpc85xx.h"
-void __init mpc8536_ds_pic_init(void)
+static void __init mpc8536_ds_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1b59e45a0c64..19122daadb55 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -21,7 +21,7 @@
#include "mpc85xx.h"
-void __init mvme2500_pic_init(void)
+static void __init mvme2500_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0,
MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 10d6f1fa3327..491895ac8bcf 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -24,7 +24,7 @@
#include "mpc85xx.h"
-void __init p1010_rdb_pic_init(void)
+static void __init p1010_rdb_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0dd786a061a6..adc3a2ee1415 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -370,7 +370,7 @@ exit:
*
* @pixclock: the wavelength, in picoseconds, of the clock
*/
-void p1022ds_set_pixel_clock(unsigned int pixclock)
+static void p1022ds_set_pixel_clock(unsigned int pixclock)
{
struct device_node *guts_np = NULL;
struct ccsr_guts __iomem *guts;
@@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
/**
* p1022ds_valid_monitor_port: set the monitor port for sysfs
*/
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
{
switch (port) {
@@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
#endif
-void __init p1022_ds_pic_init(void)
+static void __init p1022_ds_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 25ab6e9c1470..6198299d95b1 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -40,7 +40,7 @@
*
* @pixclock: the wavelength, in picoseconds, of the clock
*/
-void p1022rdk_set_pixel_clock(unsigned int pixclock)
+static void p1022rdk_set_pixel_clock(unsigned int pixclock)
{
struct device_node *guts_np = NULL;
struct ccsr_guts __iomem *guts;
@@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock)
/**
* p1022rdk_valid_monitor_port: set the monitor port for sysfs
*/
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
{
return FSL_DIU_PORT_DVI;
@@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
#endif
-void __init p1022_rdk_pic_init(void)
+static void __init p1022_rdk_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index baa12eff6d5d..60e0b8947ce6 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -8,6 +8,8 @@
#include <linux/of_irq.h>
#include <linux/io.h>
+#include "socrates_fpga_pic.h"
+
/*
* The FPGA supports 9 interrupt sources, which can be routed to 3
* interrupt request lines of the MPIC. The line to be used can be
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 45f257fc1ade..2582427d8d01 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -37,7 +37,7 @@
#define MPC85xx_L2CTL_L2I 0x40000000 /* L2 flash invalidate */
#define MPC85xx_L2CTL_L2SIZ_MASK 0x30000000 /* L2 SRAM size (R/O) */
-void __init xes_mpc85xx_pic_init(void)
+static void __init xes_mpc85xx_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
From 58aeb5623c2ebdadefe6352b14f8076a7073fea0 Mon Sep 17 00:00:00 2001
From: Fred Ai <fred.ai@bayhubtech.com>
Date: Sat, 3 Feb 2024 02:29:08 -0800
Subject: [PATCH 242/637] mmc: sdhci-pci-o2micro: Fix a warm reboot issue that
disk can't be detected by BIOS
Driver shall switch clock source from DLL clock to
OPE clock when power off card to ensure that card
can be identified with OPE clock by BIOS.
Signed-off-by: Fred Ai <fred.ai@bayhubtech.com>
Fixes:4be33cf18703 ("mmc: sdhci-pci-o2micro: Improve card input timing at SDR104/HS200 mode")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240203102908.4683-1-fredaibayhubtech@126.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/mmc/host/sdhci-pci-o2micro.c | 30 ++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index 7bfee28116af..d4a02184784a 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -693,6 +693,35 @@ static int sdhci_pci_o2_init_sd_express(struct mmc_host *mmc, struct mmc_ios *io
return 0;
}
+static void sdhci_pci_o2_set_power(struct sdhci_host *host, unsigned char mode, unsigned short vdd)
+{
+ struct sdhci_pci_chip *chip;
+ struct sdhci_pci_slot *slot = sdhci_priv(host);
+ u32 scratch_32 = 0;
+ u8 scratch_8 = 0;
+
+ chip = slot->chip;
+
+ if (mode == MMC_POWER_OFF) {
+ /* UnLock WP */
+ pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+ scratch_8 &= 0x7f;
+ pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+
+ /* Set PCR 0x354[16] to switch Clock Source back to OPE Clock */
+ pci_read_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, &scratch_32);
+ scratch_32 &= ~(O2_SD_SEL_DLL);
+ pci_write_config_dword(chip->pdev, O2_SD_OUTPUT_CLK_SOURCE_SWITCH, scratch_32);
+
+ /* Lock WP */
+ pci_read_config_byte(chip->pdev, O2_SD_LOCK_WP, &scratch_8);
+ scratch_8 |= 0x80;
+ pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch_8);
+ }
+
+ sdhci_set_power(host, mode, vdd);
+}
+
static int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
{
struct sdhci_pci_chip *chip;
@@ -1051,6 +1080,7 @@ static const struct sdhci_ops sdhci_pci_o2_ops = {
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_reset,
.set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_power = sdhci_pci_o2_set_power,
};
const struct sdhci_pci_fixes sdhci_o2 = {
From cc9432c4fb159a3913e0ce3173b8218cd5bad2e0 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Tue, 6 Feb 2024 09:39:12 +0100
Subject: [PATCH 243/637] mmc: slot-gpio: Allow non-sleeping GPIO ro
This change uses the appropriate _cansleep or non-sleeping API for
reading GPIO read-only state. This allows users with GPIOs that
never sleepbeing called in atomic context.
Implement the same mechanism as in commit 52af318c93e97 ("mmc: Allow
non-sleeping GPIO cd").
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240206083912.2543142-1-alexander.stein@ew.tq-group.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/mmc/core/slot-gpio.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 2a2d949a9344..39f45c2b6de8 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -75,11 +75,15 @@ EXPORT_SYMBOL(mmc_gpio_set_cd_irq);
int mmc_gpio_get_ro(struct mmc_host *host)
{
struct mmc_gpio *ctx = host->slot.handler_priv;
+ int cansleep;
if (!ctx || !ctx->ro_gpio)
return -ENOSYS;
- return gpiod_get_value_cansleep(ctx->ro_gpio);
+ cansleep = gpiod_cansleep(ctx->ro_gpio);
+ return cansleep ?
+ gpiod_get_value_cansleep(ctx->ro_gpio) :
+ gpiod_get_value(ctx->ro_gpio);
}
EXPORT_SYMBOL(mmc_gpio_get_ro);
From c9da9a1f17bf4fa96b115950fd389c917b583c1c Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Fri, 26 Jan 2024 13:27:58 +0100
Subject: [PATCH 244/637] accel/ivpu: Force snooping for MMU writes
Set AW_SNOOP_OVERRIDE bit in VPU_37/40XX_HOST_IF_TCU_PTW_OVERRIDES
to force snooping for MMU write accesses (setting event queue events).
MMU event queue buffer is the only buffer written by MMU and
mapped as write-back which break cache coherency. Force write
transactions to be snooped solving the problem.
Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-2-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_hw_37xx.c | 2 +-
drivers/accel/ivpu/ivpu_hw_40xx.c | 2 +-
drivers/accel/ivpu/ivpu_mmu.c | 3 ---
3 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index f15a93d83057..77accd029c4a 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -525,7 +525,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, NOSNOOP_OVERRIDE_EN, val);
- val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
+ val = REG_CLR_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AW_NOSNOOP_OVERRIDE, val);
val = REG_SET_FLD(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, AR_NOSNOOP_OVERRIDE, val);
REGV_WR32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES, val);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 704288084f37..86b89b94f9f3 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -530,7 +530,7 @@ static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
u32 val = REGV_RD32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES);
val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, SNOOP_OVERRIDE_EN, val);
- val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
+ val = REG_SET_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AW_SNOOP_OVERRIDE, val);
val = REG_CLR_FLD(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, AR_SNOOP_OVERRIDE, val);
REGV_WR32(VPU_40XX_HOST_IF_TCU_PTW_OVERRIDES, val);
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 9a3122ffce03..8df78adeee33 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -560,7 +560,6 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
mmu->cmdq.cons = 0;
memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
- clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
mmu->evtq.prod = 0;
mmu->evtq.cons = 0;
@@ -877,8 +876,6 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
return NULL;
- clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
-
evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
From b039f1c4d3727c3e44a7e89ff79e7e8533e1beec Mon Sep 17 00:00:00 2001
From: "Wachowski, Karol" <karol.wachowski@intel.com>
Date: Fri, 26 Jan 2024 13:27:59 +0100
Subject: [PATCH 245/637] accel/ivpu: Correct MMU queue size checking functions
Do not use kernel CIRC_SPACE and CIRC_CNT that
incorrectly return space of a queue when wrap bit was set.
Use correct implementation that compares producer, consumer and
wrap bit values.
Without this fix it was possible to lose events in case when event
queue was full.
Signed-off-by: Wachowski, Karol <karol.wachowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-3-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_mmu.c | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 8df78adeee33..91bd640655ab 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -72,10 +72,10 @@
#define IVPU_MMU_Q_COUNT_LOG2 4 /* 16 entries */
#define IVPU_MMU_Q_COUNT ((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
-#define IVPU_MMU_Q_WRAP_BIT (IVPU_MMU_Q_COUNT << 1)
-#define IVPU_MMU_Q_WRAP_MASK (IVPU_MMU_Q_WRAP_BIT - 1)
-#define IVPU_MMU_Q_IDX_MASK (IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_WRAP_MASK GENMASK(IVPU_MMU_Q_COUNT_LOG2, 0)
+#define IVPU_MMU_Q_IDX_MASK (IVPU_MMU_Q_COUNT - 1)
#define IVPU_MMU_Q_IDX(val) ((val) & IVPU_MMU_Q_IDX_MASK)
+#define IVPU_MMU_Q_WRP(val) ((val) & IVPU_MMU_Q_COUNT)
#define IVPU_MMU_CMDQ_CMD_SIZE 16
#define IVPU_MMU_CMDQ_SIZE (IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
@@ -475,20 +475,32 @@ static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
return 0;
}
+static bool ivpu_mmu_queue_is_full(struct ivpu_mmu_queue *q)
+{
+ return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+ (IVPU_MMU_Q_WRP(q->prod) != IVPU_MMU_Q_WRP(q->cons)));
+}
+
+static bool ivpu_mmu_queue_is_empty(struct ivpu_mmu_queue *q)
+{
+ return ((IVPU_MMU_Q_IDX(q->prod) == IVPU_MMU_Q_IDX(q->cons)) &&
+ (IVPU_MMU_Q_WRP(q->prod) == IVPU_MMU_Q_WRP(q->cons)));
+}
+
static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
{
- struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
- u64 *queue_buffer = q->base;
- int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+ struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+ u64 *queue_buffer = cmdq->base;
+ int idx = IVPU_MMU_Q_IDX(cmdq->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
- if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+ if (ivpu_mmu_queue_is_full(cmdq)) {
ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
return -EBUSY;
}
queue_buffer[idx] = data0;
queue_buffer[idx + 1] = data1;
- q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+ cmdq->prod = (cmdq->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
@@ -873,12 +885,10 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
evtq->prod = REGV_RD32(IVPU_MMU_REG_EVTQ_PROD_SEC);
- if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
+ if (ivpu_mmu_queue_is_empty(evtq))
return NULL;
evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
- REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, evtq->cons);
-
return evt;
}
@@ -899,6 +909,7 @@ void ivpu_mmu_irq_evtq_handler(struct ivpu_device *vdev)
}
ivpu_mmu_user_context_mark_invalid(vdev, ssid);
+ REGV_WR32(IVPU_MMU_REG_EVTQ_CONS_SEC, vdev->mmu->evtq.cons);
}
}
From a7f31091ddf457352e3dd7ac183fdbd26b4dcd04 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Fri, 26 Jan 2024 13:28:00 +0100
Subject: [PATCH 246/637] accel/ivpu: Disable d3hot_delay on all NPU
generations
NPU does not require this delay regardless of the generation.
All generations are integrated into the SOC.
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-4-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_drv.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 9418c73ee8ef..4b0640226986 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -480,9 +480,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
/* Clear any pending errors */
pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
- /* VPU 37XX does not require 10m D3hot delay */
- if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
- pdev->d3hot_delay = 0;
+ /* NPU does not require 10m D3hot delay */
+ pdev->d3hot_delay = 0;
ret = pcim_enable_device(pdev);
if (ret) {
From a939c03d37788e4a9a645c88d5e5b6a475ba0fd5 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@intel.com>
Date: Fri, 26 Jan 2024 13:28:02 +0100
Subject: [PATCH 247/637] accel/ivpu/40xx: Enable D0i3 message
All recent 40xx firmware already supports D0i3 entry message and this
WA is no longer needed.
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-6-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_fw.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6576232f3e67..5fa8bd4603d5 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -222,7 +222,6 @@ ivpu_fw_init_wa(struct ivpu_device *vdev)
const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
- (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
(ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
vdev->wa.disable_d0i3_msg = true;
From 553099da45397914a995dce6307d6c26523c2567 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@intel.com>
Date: Fri, 26 Jan 2024 13:28:03 +0100
Subject: [PATCH 248/637] accel/ivpu/40xx: Stop passing SKU boot parameters to
FW
This parameter was never used by the 40xx FW.
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-7-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_hw_40xx.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 86b89b94f9f3..1c995307c113 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -704,7 +704,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
{
struct ivpu_hw_info *hw = vdev->hw;
u32 tile_disable;
- u32 tile_enable;
u32 fuse;
fuse = REGB_RD32(VPU_40XX_BUTTRESS_TILE_FUSE);
@@ -725,10 +724,6 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev)
else
ivpu_dbg(vdev, MISC, "Fuse: All %d tiles enabled\n", TILE_MAX_NUM);
- tile_enable = (~tile_disable) & TILE_MAX_MASK;
-
- hw->sku = REG_SET_FLD_NUM(SKU, HW_ID, LNL_HW_ID, hw->sku);
- hw->sku = REG_SET_FLD_NUM(SKU, TILE, tile_enable, hw->sku);
hw->tile_fuse = tile_disable;
hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
From 5f8408aca66772d3aa9b4831577b2ac5ec41bcd9 Mon Sep 17 00:00:00 2001
From: Grzegorz Trzebiatowski <grzegorz.trzebiatowski@intel.com>
Date: Fri, 26 Jan 2024 13:28:04 +0100
Subject: [PATCH 249/637] accel/ivpu: Add job status for jobs aborted by the
driver
Add DRM_IVPU_JOB_STATUS_ABORTED to indicate that the job was aborted
by the driver due to e.g. TDR or user context MMU faults.
This will help UMD and tests distinguish if job was aborted by the FW
or the driver.
Signed-off-by: Grzegorz Trzebiatowski <grzegorz.trzebiatowski@intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-8-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_job.c | 4 ++--
include/uapi/drm/ivpu_accel.h | 1 +
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 0440bee3ecaf..e70cfb859339 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -294,7 +294,7 @@ static int ivpu_job_signal_and_destroy(struct ivpu_device *vdev, u32 job_id, u32
return -ENOENT;
if (job->file_priv->has_mmu_faults)
- job_status = VPU_JSM_STATUS_ABORTED;
+ job_status = DRM_IVPU_JOB_STATUS_ABORTED;
job->bos[CMD_BUF_IDX]->job_status = job_status;
dma_fence_signal(job->done_fence);
@@ -315,7 +315,7 @@ void ivpu_jobs_abort_all(struct ivpu_device *vdev)
unsigned long id;
xa_for_each(&vdev->submitted_jobs_xa, id, job)
- ivpu_job_signal_and_destroy(vdev, id, VPU_JSM_STATUS_ABORTED);
+ ivpu_job_signal_and_destroy(vdev, id, DRM_IVPU_JOB_STATUS_ABORTED);
}
static int ivpu_job_submit(struct ivpu_job *job)
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index 63c49318a863..19a13468eca5 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -305,6 +305,7 @@ struct drm_ivpu_submit {
/* drm_ivpu_bo_wait job status codes */
#define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
/**
* struct drm_ivpu_bo_wait - Wait for BO to become inactive
From 1ce2654d87e2fb91fea83b288bd9b2641045e42a Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Sat, 3 Feb 2024 13:31:33 +0800
Subject: [PATCH 250/637] net: stmmac: xgmac: fix a typo of register name in
DPP safety handling
DDPP is copied from Synopsys Data book:
DDPP: Disable Data path Parity Protection.
When it is 0x0, Data path Parity Protection is enabled.
When it is 0x1, Data path Parity Protection is disabled.
The macro name should be XGMAC_DPP_DISABLE.
Fixes: 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels")
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/20240203053133.1129236-1-0x1207@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 2 +-
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 5c67a3f89f08..6a2c7d22df1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -304,7 +304,7 @@
#define XGMAC_TXCEIE BIT(0)
#define XGMAC_MTL_ECC_INT_STATUS 0x000010cc
#define XGMAC_MTL_DPP_CONTROL 0x000010e0
-#define XGMAC_DDPP_DISABLE BIT(0)
+#define XGMAC_DPP_DISABLE BIT(0)
#define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x)))
#define XGMAC_TQS GENMASK(25, 16)
#define XGMAC_TQS_SHIFT 16
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 04d7c4dc2e35..323c57f03c93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -928,7 +928,7 @@ dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
/* 5. Enable Data Path Parity Protection */
value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL);
/* already enabled by default, explicit enable it again */
- value &= ~XGMAC_DDPP_DISABLE;
+ value &= ~XGMAC_DPP_DISABLE;
writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL);
return 0;
From 720e78d7fa0f1df905a42ae68e7e3b0f95e53946 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 31 Jan 2024 11:24:59 +0300
Subject: [PATCH 251/637] serial: 8250_pci1xxxx: partially revert off by one
patch
I was reviewing this code again and I realized I made a mistake here.
It should have been > instead of >=. The subtract ensures that we
don't go out of bounds. My patch meant that we don't read the last
chunk of the buffer.
Fixes: 86ee55e9bc7f ("serial: 8250_pci1xxxx: fix off by one in pci1xxxx_process_read_data()")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/bd6fb361-bbb9-427d-90e8-a5df4de76221@moroto.mountain
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/8250/8250_pci1xxxx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index cd258922bd78..2dda737b1660 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -302,7 +302,7 @@ static void pci1xxxx_process_read_data(struct uart_port *port,
* to read, the data is received one byte at a time.
*/
while (valid_burst_count--) {
- if (*buff_index >= (RX_BUF_SIZE - UART_BURST_SIZE))
+ if (*buff_index > (RX_BUF_SIZE - UART_BURST_SIZE))
break;
burst_buf = (u32 *)&rx_buff[*buff_index];
*burst_buf = readl(port->membase + UART_RX_BURST_FIFO);
From 3ee07964d407411fd578a3bc998de44fd64d266a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 1 Feb 2024 11:55:56 +0100
Subject: [PATCH 252/637] serial: core: introduce uart_port_tx_flags()
And an enum with a flag: UART_TX_NOSTOP. To NOT call
__port->ops->stop_tx() when the circular buffer is empty. mxs-uart needs
this (see the next patch).
Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: stable <stable@kernel.org>
Tested-by: Emil Kronborg <emil.kronborg@protonmail.com>
Link: https://lore.kernel.org/r/20240201105557.28043-1-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/linux/serial_core.h | 32 +++++++++++++++++++++++++++-----
1 file changed, 27 insertions(+), 5 deletions(-)
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 536b2581d3e2..55b1f3ba48ac 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -748,8 +748,17 @@ struct uart_driver {
void uart_write_wakeup(struct uart_port *port);
-#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test, \
- for_post) \
+/**
+ * enum UART_TX_FLAGS -- flags for uart_port_tx_flags()
+ *
+ * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer
+ */
+enum UART_TX_FLAGS {
+ UART_TX_NOSTOP = BIT(0),
+};
+
+#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \
+ for_test, for_post) \
({ \
struct uart_port *__port = (uport); \
struct circ_buf *xmit = &__port->state->xmit; \
@@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port);
if (pending < WAKEUP_CHARS) { \
uart_write_wakeup(__port); \
\
- if (pending == 0) \
+ if (!((flags) & UART_TX_NOSTOP) && pending == 0) \
__port->ops->stop_tx(__port); \
} \
\
@@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port);
*/
#define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \
unsigned int __count = (count); \
- __uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count, \
+ __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \
__count--); \
})
@@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port);
* See uart_port_tx_limited() for more details.
*/
#define uart_port_tx(port, ch, tx_ready, put_char) \
- __uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({}))
+ __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({}))
+
+/**
+ * uart_port_tx_flags -- transmit helper for uart_port with flags
+ * @port: uart port
+ * @ch: variable to store a character to be written to the HW
+ * @flags: %UART_TX_NOSTOP or similar
+ * @tx_ready: can HW accept more data function
+ * @put_char: function to write a character
+ *
+ * See uart_port_tx_limited() for more details.
+ */
+#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \
+ __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({}))
/*
* Baud rate helpers.
*/
From 7be50f2e8f20fc2299069b28dea59a28e3abe20a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 1 Feb 2024 11:55:57 +0100
Subject: [PATCH 253/637] serial: mxs-auart: fix tx
Emil reports:
After updating Linux on an i.MX28 board, serial communication over
AUART broke. When I TX from the board and measure on the TX pin, it
seems like the HW fifo is not emptied before the transmission is
stopped.
MXS performs weird things with stop_tx(). The driver makes it
conditional on uart_tx_stopped().
So the driver needs special handling. Pass the brand new UART_TX_NOSTOP
to uart_port_tx_flags() and handle the stop on its own.
Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Reported-by: Emil Kronborg <emil.kronborg@protonmail.com>
Cc: stable <stable@kernel.org>
Fixes: 2d141e683e9a ("tty: serial: use uart_port_tx() helper")
Closes: https://lore.kernel.org/all/miwgbnvy3hjpnricubg76ytpn7xoceehwahupy25bubbduu23s@om2lptpa26xw/
Tested-by: Stefan Wahren <wahrenst@gmx.net>
Tested-by: Emil Kronborg <emil.kronborg@protonmail.com>
Link: https://lore.kernel.org/r/20240201105557.28043-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/mxs-auart.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 3ec725555bcc..4749331fe618 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -605,13 +605,16 @@ static void mxs_auart_tx_chars(struct mxs_auart_port *s)
return;
}
- pending = uart_port_tx(&s->port, ch,
+ pending = uart_port_tx_flags(&s->port, ch, UART_TX_NOSTOP,
!(mxs_read(s, REG_STAT) & AUART_STAT_TXFF),
mxs_write(ch, s, REG_DATA));
if (pending)
mxs_set(AUART_INTR_TXIEN, s, REG_INTR);
else
mxs_clr(AUART_INTR_TXIEN, s, REG_INTR);
+
+ if (uart_tx_stopped(&s->port))
+ mxs_auart_stop_tx(&s->port);
}
static void mxs_auart_rx_char(struct mxs_auart_port *s)
From 411a20db905b44e18cc9129b745f1d5deba4eae5 Mon Sep 17 00:00:00 2001
From: Oleksandr Natalenko <oleksandr@natalenko.name>
Date: Mon, 29 Jan 2024 17:49:31 +0100
Subject: [PATCH 254/637] HID: logitech-hidpp: Do not flood kernel log
Since commit 680ee411a98e ("HID: logitech-hidpp: Fix connect event race")
the following messages appear in the kernel log from time to time:
logitech-hidpp-device 0003:046D:408A.0005: HID++ 4.5 device connected.
logitech-hidpp-device 0003:046D:408A.0005: HID++ 4.5 device connected.
logitech-hidpp-device 0003:046D:4051.0006: Disconnected
logitech-hidpp-device 0003:046D:408A.0005: Disconnected
As discussed, print the first per-device "device connected" message
at info level, demoting subsequent messages to debug level. Also,
demote the "Disconnected message" to debug level unconditionally.
Link: https://lore.kernel.org/lkml/3277085.44csPzL39Z@natalenko.name/
Signed-off-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
drivers/hid/hid-logitech-hidpp.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 6ef0c88e3e60..d2f3f234f29d 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -203,6 +203,8 @@ struct hidpp_device {
struct hidpp_scroll_counter vertical_wheel_counter;
u8 wireless_feature_index;
+
+ bool connected_once;
};
/* HID++ 1.0 error codes */
@@ -988,8 +990,13 @@ static int hidpp_root_get_protocol_version(struct hidpp_device *hidpp)
hidpp->protocol_minor = response.rap.params[1];
print_version:
- hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
- hidpp->protocol_major, hidpp->protocol_minor);
+ if (!hidpp->connected_once) {
+ hid_info(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+ hidpp->protocol_major, hidpp->protocol_minor);
+ hidpp->connected_once = true;
+ } else
+ hid_dbg(hidpp->hid_dev, "HID++ %u.%u device connected.\n",
+ hidpp->protocol_major, hidpp->protocol_minor);
return 0;
}
@@ -4184,7 +4191,7 @@ static void hidpp_connect_event(struct work_struct *work)
/* Get device version to check if it is connected */
ret = hidpp_root_get_protocol_version(hidpp);
if (ret) {
- hid_info(hidpp->hid_dev, "Disconnected\n");
+ hid_dbg(hidpp->hid_dev, "Disconnected\n");
if (hidpp->battery.ps) {
hidpp->battery.online = false;
hidpp->battery.status = POWER_SUPPLY_STATUS_UNKNOWN;
From c1d6708bf0d3dd976460d435373cf5abf21ce258 Mon Sep 17 00:00:00 2001
From: Jason Gerecke <killertofu@gmail.com>
Date: Mon, 29 Jan 2024 14:35:45 -0800
Subject: [PATCH 255/637] HID: wacom: Do not register input devices until after
hid_hw_start
If a input device is opened before hid_hw_start is called, events may
not be received from the hardware. In the case of USB-backed devices,
for example, the hid_hw_start function is responsible for filling in
the URB which is submitted when the input device is opened. If a device
is opened prematurely, polling will never start because the device will
not have been in the correct state to send the URB.
Because the wacom driver registers its input devices before calling
hid_hw_start, there is a window of time where a device can be opened
and end up in an inoperable state. Some ARM-based Chromebooks in particular
reliably trigger this bug.
This commit splits the wacom_register_inputs function into two pieces.
One which is responsible for setting up the allocated inputs (and runs
prior to hid_hw_start so that devices are ready for any input events
they may end up receiving) and another which only registers the devices
(and runs after hid_hw_start to ensure devices can be immediately opened
without issue). Note that the functions to initialize the LEDs and remotes
are also moved after hid_hw_start to maintain their own dependency chains.
Fixes: 7704ac937345 ("HID: wacom: implement generic HID handling for pen generic devices")
Cc: stable@vger.kernel.org # v3.18+
Suggested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jason Gerecke <jason.gerecke@wacom.com>
Tested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
drivers/hid/wacom_sys.c | 63 ++++++++++++++++++++++++++++-------------
1 file changed, 43 insertions(+), 20 deletions(-)
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index b613f11ed949..2bc45b24075c 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2087,7 +2087,7 @@ static int wacom_allocate_inputs(struct wacom *wacom)
return 0;
}
-static int wacom_register_inputs(struct wacom *wacom)
+static int wacom_setup_inputs(struct wacom *wacom)
{
struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
@@ -2106,10 +2106,6 @@ static int wacom_register_inputs(struct wacom *wacom)
input_free_device(pen_input_dev);
wacom_wac->pen_input = NULL;
pen_input_dev = NULL;
- } else {
- error = input_register_device(pen_input_dev);
- if (error)
- goto fail;
}
error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac);
@@ -2118,10 +2114,6 @@ static int wacom_register_inputs(struct wacom *wacom)
input_free_device(touch_input_dev);
wacom_wac->touch_input = NULL;
touch_input_dev = NULL;
- } else {
- error = input_register_device(touch_input_dev);
- if (error)
- goto fail;
}
error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
@@ -2130,7 +2122,34 @@ static int wacom_register_inputs(struct wacom *wacom)
input_free_device(pad_input_dev);
wacom_wac->pad_input = NULL;
pad_input_dev = NULL;
- } else {
+ }
+
+ return 0;
+}
+
+static int wacom_register_inputs(struct wacom *wacom)
+{
+ struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
+ struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
+ int error = 0;
+
+ pen_input_dev = wacom_wac->pen_input;
+ touch_input_dev = wacom_wac->touch_input;
+ pad_input_dev = wacom_wac->pad_input;
+
+ if (pen_input_dev) {
+ error = input_register_device(pen_input_dev);
+ if (error)
+ goto fail;
+ }
+
+ if (touch_input_dev) {
+ error = input_register_device(touch_input_dev);
+ if (error)
+ goto fail;
+ }
+
+ if (pad_input_dev) {
error = input_register_device(pad_input_dev);
if (error)
goto fail;
@@ -2383,6 +2402,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
if (error)
goto fail;
+ error = wacom_setup_inputs(wacom);
+ if (error)
+ goto fail;
+
+ if (features->type == HID_GENERIC)
+ connect_mask |= HID_CONNECT_DRIVER;
+
+ /* Regular HID work starts now */
+ error = hid_hw_start(hdev, connect_mask);
+ if (error) {
+ hid_err(hdev, "hw start failed\n");
+ goto fail;
+ }
+
error = wacom_register_inputs(wacom);
if (error)
goto fail;
@@ -2397,16 +2430,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
goto fail;
}
- if (features->type == HID_GENERIC)
- connect_mask |= HID_CONNECT_DRIVER;
-
- /* Regular HID work starts now */
- error = hid_hw_start(hdev, connect_mask);
- if (error) {
- hid_err(hdev, "hw start failed\n");
- goto fail;
- }
-
if (!wireless) {
/* Note that if query fails it is not a hard failure */
wacom_query_tablet_data(wacom);
From 853b8d7597eea4ccaaefbcf0942cd42fc86d542a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 2 Feb 2024 12:22:58 +0200
Subject: [PATCH 256/637] remap_range: merge do_clone_file_range() into
vfs_clone_file_range()
commit dfad37051ade ("remap_range: move permission hooks out of
do_clone_file_range()") moved the permission hooks from
do_clone_file_range() out to its caller vfs_clone_file_range(),
but left all the fast sanity checks in do_clone_file_range().
This makes the expensive security hooks be called in situations
that they would not have been called before (e.g. fs does not support
clone).
The only reason for the do_clone_file_range() helper was that overlayfs
did not use to be able to call vfs_clone_file_range() from copy up
context with sb_writers lock held. However, since commit c63e56a4a652
("ovl: do not open/llseek lower file with upper sb_writers held"),
overlayfs just uses an open coded version of vfs_clone_file_range().
Merge_clone_file_range() into vfs_clone_file_range(), restoring the
original order of checks as it was before the regressing commit and adapt
the overlayfs code to call vfs_clone_file_range() before the permission
hooks that were added by commit ca7ab482401c ("ovl: add permission hooks
outside of do_splice_direct()").
Note that in the merge of do_clone_file_range(), the file_start_write()
context was reduced to cover ->remap_file_range() without holding it
over the permission hooks, which was the reason for doing the regressing
commit in the first place.
Reported-and-tested-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401312229.eddeb9a6-oliver.sang@intel.com
Fixes: dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20240202102258.1582671-1-amir73il@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
fs/overlayfs/copy_up.c | 14 ++++++--------
fs/remap_range.c | 31 +++++++++----------------------
include/linux/fs.h | 3 ---
3 files changed, 15 insertions(+), 33 deletions(-)
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b8e25ca51016..8586e2f5d243 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -265,20 +265,18 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
if (IS_ERR(old_file))
return PTR_ERR(old_file);
+ /* Try to use clone_file_range to clone up within the same fs */
+ cloned = vfs_clone_file_range(old_file, 0, new_file, 0, len, 0);
+ if (cloned == len)
+ goto out_fput;
+
+ /* Couldn't clone, so now we try to copy the data */
error = rw_verify_area(READ, old_file, &old_pos, len);
if (!error)
error = rw_verify_area(WRITE, new_file, &new_pos, len);
if (error)
goto out_fput;
- /* Try to use clone_file_range to clone up within the same fs */
- ovl_start_write(dentry);
- cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
- ovl_end_write(dentry);
- if (cloned == len)
- goto out_fput;
- /* Couldn't clone, so now we try to copy the data */
-
/* Check if lower fs supports seek operation */
if (old_file->f_mode & FMODE_LSEEK)
skip_hole = true;
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f8c1120b8311..de07f978ce3e 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -373,9 +373,9 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
}
EXPORT_SYMBOL(generic_remap_file_range_prep);
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- loff_t len, unsigned int remap_flags)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags)
{
loff_t ret;
@@ -391,23 +391,6 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
if (!file_in->f_op->remap_file_range)
return -EOPNOTSUPP;
- ret = file_in->f_op->remap_file_range(file_in, pos_in,
- file_out, pos_out, len, remap_flags);
- if (ret < 0)
- return ret;
-
- fsnotify_access(file_in);
- fsnotify_modify(file_out);
- return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- loff_t len, unsigned int remap_flags)
-{
- loff_t ret;
-
ret = remap_verify_area(file_in, pos_in, len, false);
if (ret)
return ret;
@@ -417,10 +400,14 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
return ret;
file_start_write(file_out);
- ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
- remap_flags);
+ ret = file_in->f_op->remap_file_range(file_in, pos_in,
+ file_out, pos_out, len, remap_flags);
file_end_write(file_out);
+ if (ret < 0)
+ return ret;
+ fsnotify_access(file_in);
+ fsnotify_modify(file_out);
return ret;
}
EXPORT_SYMBOL(vfs_clone_file_range);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5966a70495..023f37c60709 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2101,9 +2101,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *count, unsigned int remap_flags);
-extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- loff_t len, unsigned int remap_flags);
extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
From f814bdda774c183b0cc15ec8f3b6e7c6f4527ba5 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 23 Jan 2024 18:58:26 +0100
Subject: [PATCH 257/637] blk-wbt: Fix detection of dirty-throttled tasks
The detection of dirty-throttled tasks in blk-wbt has been subtly broken
since its beginning in 2016. Namely if we are doing cgroup writeback and
the throttled task is not in the root cgroup, balance_dirty_pages() will
set dirty_sleep for the non-root bdi_writeback structure. However
blk-wbt checks dirty_sleep only in the root cgroup bdi_writeback
structure. Thus detection of recently throttled tasks is not working in
this case (we noticed this when we switched to cgroup v2 and suddently
writeback was slow).
Since blk-wbt has no easy way to get to proper bdi_writeback and
furthermore its intention has always been to work on the whole device
rather than on individual cgroups, just move the dirty_sleep timestamp
from bdi_writeback to backing_dev_info. That fixes the checking for
recently throttled task and saves memory for everybody as a bonus.
CC: stable@vger.kernel.org
Fixes: b57d74aff9ab ("writeback: track if we're sleeping on progress in balance_dirty_pages()")
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20240123175826.21452-1-jack@suse.cz
[axboe: fixup indentation errors]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-wbt.c | 4 ++--
include/linux/backing-dev-defs.h | 7 +++++--
mm/backing-dev.c | 2 +-
mm/page-writeback.c | 2 +-
4 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 5ba3cd574eac..0c0e270a8265 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -163,9 +163,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
*/
static bool wb_recent_wait(struct rq_wb *rwb)
{
- struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+ struct backing_dev_info *bdi = rwb->rqos.disk->bdi;
- return time_before(jiffies, wb->dirty_sleep + HZ);
+ return time_before(jiffies, bdi->last_bdp_sleep + HZ);
}
static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492..2ad261082bba 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -141,8 +141,6 @@ struct bdi_writeback {
struct delayed_work dwork; /* work item used for writeback */
struct delayed_work bw_dwork; /* work item used for bandwidth estimate */
- unsigned long dirty_sleep; /* last wait */
-
struct list_head bdi_node; /* anchored at bdi->wb_list */
#ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
* any dirty wbs, which is depended upon by bdi_has_dirty().
*/
atomic_long_t tot_write_bandwidth;
+ /*
+ * Jiffies when last process was dirty throttled on this bdi. Used by
+ * blk-wbt.
+ */
+ unsigned long last_bdp_sleep;
struct bdi_writeback wb; /* the root writeback info for this bdi */
struct list_head wb_list; /* list of all wbs */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1e3447bccdb1..e039d05304dd 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -436,7 +436,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
INIT_LIST_HEAD(&wb->work_list);
INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
- wb->dirty_sleep = jiffies;
err = fprop_local_init_percpu(&wb->completions, gfp);
if (err)
@@ -921,6 +920,7 @@ int bdi_init(struct backing_dev_info *bdi)
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->wb_list);
init_waitqueue_head(&bdi->wb_waitq);
+ bdi->last_bdp_sleep = jiffies;
return cgwb_bdi_init(bdi);
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index cd4e4ae77c40..cc37fa7f3364 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1921,7 +1921,7 @@ pause:
break;
}
__set_current_state(TASK_KILLABLE);
- wb->dirty_sleep = now;
+ bdi->last_bdp_sleep = jiffies;
io_schedule_timeout(pause);
current->dirty_paused_when = now + pause;
From ba58f873cdeec30b6da48e28dd5782c5a3e1371b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 2 Feb 2024 15:18:31 -0800
Subject: [PATCH 258/637] KVM: selftests: Fix a semaphore imbalance in the
dirty ring logging test
When finishing the final iteration of dirty_log_test testcase, set
host_quit _before_ the final "continue" so that the vCPU worker doesn't
run an extra iteration, and delete the hack-a-fix of an extra "continue"
from the dirty ring testcase. This fixes a bug where the extra post to
sem_vcpu_cont may not be consumed, which results in failures in subsequent
runs of the testcases. The bug likely was missed during development as
x86 supports only a single "guest mode", i.e. there aren't any subsequent
testcases after the dirty ring test, because for_each_guest_mode() only
runs a single iteration.
For the regular dirty log testcases, letting the vCPU run one extra
iteration is a non-issue as the vCPU worker waits on sem_vcpu_cont if and
only if the worker is explicitly told to stop (vcpu_sync_stop_requested).
But for the dirty ring test, which needs to periodically stop the vCPU to
reap the dirty ring, letting the vCPU resume the guest _after_ the last
iteration means the vCPU will get stuck without an extra "continue".
However, blindly firing off an post to sem_vcpu_cont isn't guaranteed to
be consumed, e.g. if the vCPU worker sees host_quit==true before resuming
the guest. This results in a dangling sem_vcpu_cont, which leads to
subsequent iterations getting out of sync, as the vCPU worker will
continue on before the main task is ready for it to resume the guest,
leading to a variety of asserts, e.g.
==== Test Assertion Failure ====
dirty_log_test.c:384: dirty_ring_vcpu_ring_full
pid=14854 tid=14854 errno=22 - Invalid argument
1 0x00000000004033eb: dirty_ring_collect_dirty_pages at dirty_log_test.c:384
2 0x0000000000402d27: log_mode_collect_dirty_pages at dirty_log_test.c:505
3 (inlined by) run_test at dirty_log_test.c:802
4 0x0000000000403dc7: for_each_guest_mode at guest_modes.c:100
5 0x0000000000401dff: main at dirty_log_test.c:941 (discriminator 3)
6 0x0000ffff9be173c7: ?? ??:0
7 0x0000ffff9be1749f: ?? ??:0
8 0x000000000040206f: _start at ??:?
Didn't continue vcpu even without ring full
Alternatively, the test could simply reset the semaphores before each
testcase, but papering over hacks with more hacks usually ends in tears.
Reported-by: Shaoqin Huang <shahuang@redhat.com>
Fixes: 84292e565951 ("KVM: selftests: Add dirty ring buffer test")
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Link: https://lore.kernel.org/r/20240202231831.354848-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
tools/testing/selftests/kvm/dirty_log_test.c | 50 +++++++++++---------
1 file changed, 27 insertions(+), 23 deletions(-)
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index babea97b31a4..eaad5b20854c 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -376,7 +376,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
cleared = kvm_vm_reset_dirty_ring(vcpu->vm);
- /* Cleared pages should be the same as collected */
+ /*
+ * Cleared pages should be the same as collected, as KVM is supposed to
+ * clear only the entries that have been harvested.
+ */
TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
"with collected (%u)", cleared, count);
@@ -415,12 +418,6 @@ static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
}
}
-static void dirty_ring_before_vcpu_join(void)
-{
- /* Kick another round of vcpu just to make sure it will quit */
- sem_post(&sem_vcpu_cont);
-}
-
struct log_mode {
const char *name;
/* Return true if this mode is supported, otherwise false */
@@ -433,7 +430,6 @@ struct log_mode {
uint32_t *ring_buf_idx);
/* Hook to call when after each vcpu run */
void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err);
- void (*before_vcpu_join) (void);
} log_modes[LOG_MODE_NUM] = {
{
.name = "dirty-log",
@@ -452,7 +448,6 @@ struct log_mode {
.supported = dirty_ring_supported,
.create_vm_done = dirty_ring_create_vm_done,
.collect_dirty_pages = dirty_ring_collect_dirty_pages,
- .before_vcpu_join = dirty_ring_before_vcpu_join,
.after_vcpu_run = dirty_ring_after_vcpu_run,
},
};
@@ -513,14 +508,6 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
mode->after_vcpu_run(vcpu, ret, err);
}
-static void log_mode_before_vcpu_join(void)
-{
- struct log_mode *mode = &log_modes[host_log_mode];
-
- if (mode->before_vcpu_join)
- mode->before_vcpu_join();
-}
-
static void generate_random_array(uint64_t *guest_array, uint64_t size)
{
uint64_t i;
@@ -719,6 +706,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct kvm_vm *vm;
unsigned long *bmap;
uint32_t ring_buf_idx = 0;
+ int sem_val;
if (!log_mode_supported()) {
print_skip("Log mode '%s' not supported",
@@ -788,12 +776,22 @@ static void run_test(enum vm_guest_mode mode, void *arg)
/* Start the iterations */
iteration = 1;
sync_global_to_guest(vm, iteration);
- host_quit = false;
+ WRITE_ONCE(host_quit, false);
host_dirty_count = 0;
host_clear_count = 0;
host_track_next_count = 0;
WRITE_ONCE(dirty_ring_vcpu_ring_full, false);
+ /*
+ * Ensure the previous iteration didn't leave a dangling semaphore, i.e.
+ * that the main task and vCPU worker were synchronized and completed
+ * verification of all iterations.
+ */
+ sem_getvalue(&sem_vcpu_stop, &sem_val);
+ TEST_ASSERT_EQ(sem_val, 0);
+ sem_getvalue(&sem_vcpu_cont, &sem_val);
+ TEST_ASSERT_EQ(sem_val, 0);
+
pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu);
while (iteration < p->iterations) {
@@ -819,15 +817,21 @@ static void run_test(enum vm_guest_mode mode, void *arg)
assert(host_log_mode == LOG_MODE_DIRTY_RING ||
atomic_read(&vcpu_sync_stop_requested) == false);
vm_dirty_log_verify(mode, bmap);
- sem_post(&sem_vcpu_cont);
- iteration++;
+ /*
+ * Set host_quit before sem_vcpu_cont in the final iteration to
+ * ensure that the vCPU worker doesn't resume the guest. As
+ * above, the dirty ring test may stop and wait even when not
+ * explicitly request to do so, i.e. would hang waiting for a
+ * "continue" if it's allowed to resume the guest.
+ */
+ if (++iteration == p->iterations)
+ WRITE_ONCE(host_quit, true);
+
+ sem_post(&sem_vcpu_cont);
sync_global_to_guest(vm, iteration);
}
- /* Tell the vcpu thread to quit */
- host_quit = true;
- log_mode_before_vcpu_join();
pthread_join(vcpu_thread, NULL);
pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
From 6fd78beed0213655c16ef728af0caec6d5ae4c73 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 31 Jan 2024 14:27:28 -0800
Subject: [PATCH 259/637] KVM: selftests: Don't assert on exact number of 4KiB
in dirty log split test
Drop dirty_log_page_splitting_test's assertion that the number of 4KiB
pages remains the same across dirty logging being enabled and disabled, as
the test doesn't guarantee that mappings outside of the memslots being
dirty logged are stable, e.g. KVM's mappings for code and pages in
memslot0 can be zapped by things like NUMA balancing.
To preserve the spirit of the check, assert that (a) the number of 4KiB
pages after splitting is _at least_ the number of 4KiB pages across all
memslots under test, and (b) the number of hugepages before splitting adds
up to the number of pages across all memslots under test. (b) is a little
tenuous as it relies on memslot0 being incompatible with transparent
hugepages, but that holds true for now as selftests explicitly madvise()
MADV_NOHUGEPAGE for memslot0 (__vm_create() unconditionally specifies the
backing type as VM_MEM_SRC_ANONYMOUS).
Reported-by: Yi Lai <yi1.lai@intel.com>
Reported-by: Tao Su <tao1.su@linux.intel.com>
Reviewed-by: Tao Su <tao1.su@linux.intel.com>
Link: https://lore.kernel.org/r/20240131222728.4100079-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../x86_64/dirty_log_page_splitting_test.c | 21 +++++++++++--------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
index 634c6bfcd572..ee3b384b991c 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
+++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
@@ -92,7 +92,6 @@ static void run_test(enum vm_guest_mode mode, void *unused)
uint64_t host_num_pages;
uint64_t pages_per_slot;
int i;
- uint64_t total_4k_pages;
struct kvm_page_stats stats_populated;
struct kvm_page_stats stats_dirty_logging_enabled;
struct kvm_page_stats stats_dirty_pass[ITERATIONS];
@@ -107,6 +106,9 @@ static void run_test(enum vm_guest_mode mode, void *unused)
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
pages_per_slot = host_num_pages / SLOTS;
+ TEST_ASSERT_EQ(host_num_pages, pages_per_slot * SLOTS);
+ TEST_ASSERT(!(host_num_pages % 512),
+ "Number of pages, '%lu' not a multiple of 2MiB", host_num_pages);
bitmaps = memstress_alloc_bitmaps(SLOTS, pages_per_slot);
@@ -165,10 +167,8 @@ static void run_test(enum vm_guest_mode mode, void *unused)
memstress_free_bitmaps(bitmaps, SLOTS);
memstress_destroy_vm(vm);
- /* Make assertions about the page counts. */
- total_4k_pages = stats_populated.pages_4k;
- total_4k_pages += stats_populated.pages_2m * 512;
- total_4k_pages += stats_populated.pages_1g * 512 * 512;
+ TEST_ASSERT_EQ((stats_populated.pages_2m * 512 +
+ stats_populated.pages_1g * 512 * 512), host_num_pages);
/*
* Check that all huge pages were split. Since large pages can only
@@ -180,19 +180,22 @@ static void run_test(enum vm_guest_mode mode, void *unused)
*/
if (dirty_log_manual_caps) {
TEST_ASSERT_EQ(stats_clear_pass[0].hugepages, 0);
- TEST_ASSERT_EQ(stats_clear_pass[0].pages_4k, total_4k_pages);
+ TEST_ASSERT(stats_clear_pass[0].pages_4k >= host_num_pages,
+ "Expected at least '%lu' 4KiB pages, found only '%lu'",
+ host_num_pages, stats_clear_pass[0].pages_4k);
TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, stats_populated.hugepages);
} else {
TEST_ASSERT_EQ(stats_dirty_logging_enabled.hugepages, 0);
- TEST_ASSERT_EQ(stats_dirty_logging_enabled.pages_4k, total_4k_pages);
+ TEST_ASSERT(stats_dirty_logging_enabled.pages_4k >= host_num_pages,
+ "Expected at least '%lu' 4KiB pages, found only '%lu'",
+ host_num_pages, stats_dirty_logging_enabled.pages_4k);
}
/*
* Once dirty logging is disabled and the vCPUs have touched all their
- * memory again, the page counts should be the same as they were
+ * memory again, the hugepage counts should be the same as they were
* right after initial population of memory.
*/
- TEST_ASSERT_EQ(stats_populated.pages_4k, stats_repopulated.pages_4k);
TEST_ASSERT_EQ(stats_populated.pages_2m, stats_repopulated.pages_2m);
TEST_ASSERT_EQ(stats_populated.pages_1g, stats_repopulated.pages_1g);
}
From 7ed4380009e96d9e9c605e12822e987b35b05648 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Wed, 7 Feb 2024 08:01:17 +0900
Subject: [PATCH 260/637] firewire: core: send bus reset promptly on gap count
error
If we are bus manager and the bus has inconsistent gap counts, send a
bus reset immediately instead of trying to read the root node's config
ROM first. Otherwise, we could spend a lot of time trying to read the
config ROM but never succeeding.
This eliminates a 50+ second delay before the FireWire bus is usable after
a newly connected device is powered on in certain circumstances.
The delay occurs if a gap count inconsistency occurs, we are not the root
node, and we become bus manager. One scenario that causes this is with a TI
XIO2213B OHCI, the first time a Sony DSR-25 is powered on after being
connected to the FireWire cable. In this configuration, the Linux box will
not receive the initial PHY configuration packet sent by the DSR-25 as IRM,
resulting in the DSR-25 having a gap count of 44 while the Linux box has a
gap count of 63.
FireWire devices have a gap count parameter, which is set to 63 on power-up
and can be changed with a PHY configuration packet. This determines the
duration of the subaction and arbitration gaps. For reliable communication,
all nodes on a FireWire bus must have the same gap count.
A node may have zero or more of the following roles: root node, bus manager
(BM), isochronous resource manager (IRM), and cycle master. Unless a root
node was forced with a PHY configuration packet, any node might become root
node after a bus reset. Only the root node can become cycle master. If the
root node is not cycle master capable, the BM or IRM should force a change
of root node.
After a bus reset, each node sends a self-ID packet, which contains its
current gap count. A single bus reset does not change the gap count, but
two bus resets in a row will set the gap count to 63. Because a consistent
gap count is required for reliable communication, IEEE 1394a-2000 requires
that the bus manager generate a bus reset if it detects that the gap count
is inconsistent.
When the gap count is inconsistent, build_tree() will notice this after the
self identification process. It will set card->gap_count to the invalid
value 0. If we become bus master, this will force bm_work() to send a bus
reset when it performs gap count optimization.
After a bus reset, there is no bus manager. We will almost always try to
become bus manager. Once we become bus manager, we will first determine
whether the root node is cycle master capable. Then, we will determine if
the gap count should be changed. If either the root node or the gap count
should be changed, we will generate a bus reset.
To determine if the root node is cycle master capable, we read its
configuration ROM. bm_work() will wait until we have finished trying to
read the configuration ROM.
However, an inconsistent gap count can make this take a long time.
read_config_rom() will read the first few quadlets from the config ROM. Due
to the gap count inconsistency, eventually one of the reads will time out.
When read_config_rom() fails, fw_device_init() calls it again until
MAX_RETRIES is reached. This takes 50+ seconds.
Once we give up trying to read the configuration ROM, bm_work() will wake
up, assume that the root node is not cycle master capable, and do a bus
reset. Hopefully, this will resolve the gap count inconsistency.
This change makes bm_work() check for an inconsistent gap count before
waiting for the root node's configuration ROM. If the gap count is
inconsistent, bm_work() will immediately do a bus reset. This eliminates
the 50+ second delay and rapidly brings the bus to a working state.
I considered that if the gap count is inconsistent, a PHY configuration
packet might not be successful, so it could be desirable to skip the PHY
configuration packet before the bus reset in this case. However, IEEE
1394a-2000 and IEEE 1394-2008 say that the bus manager may transmit a PHY
configuration packet before a bus reset when correcting a gap count error.
Since the standard endorses this, I decided it's safe to retain the PHY
configuration packet transmission.
Normally, after a topology change, we will reset the bus a maximum of 5
times to change the root node and perform gap count optimization. However,
if there is a gap count inconsistency, we must always generate a bus reset.
Otherwise the gap count inconsistency will persist and communication will
be unreliable. For that reason, if there is a gap count inconstency, we
generate a bus reset even if we already reached the 5 reset limit.
Signed-off-by: Adam Goldman <adamg@pobox.com>
Reference: https://sourceforge.net/p/linux1394/mailman/message/58727806/
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
drivers/firewire/core-card.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 6ac5ff20a2fe..8aaa7fcb2630 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work)
*/
card->bm_generation = generation;
- if (root_device == NULL) {
+ if (card->gap_count == 0) {
+ /*
+ * If self IDs have inconsistent gap counts, do a
+ * bus reset ASAP. The config rom read might never
+ * complete, so don't wait for it. However, still
+ * send a PHY configuration packet prior to the
+ * bus reset. The PHY configuration packet might
+ * fail, but 1394-2008 8.4.5.2 explicitly permits
+ * it in this case, so it should be safe to try.
+ */
+ new_root_id = local_id;
+ /*
+ * We must always send a bus reset if the gap count
+ * is inconsistent, so bypass the 5-reset limit.
+ */
+ card->bm_retries = 0;
+ } else if (root_device == NULL) {
/*
* Either link_on is false, or we failed to read the
* config rom. In either case, pick another root.
From 829388b725f8d266ccec32a2f446717d8693eaba Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Thu, 1 Feb 2024 14:04:36 +0800
Subject: [PATCH 261/637] kunit: device: Unregister the kunit_bus on shutdown
If KUnit is built as a module, and it's unloaded, the kunit_bus is not
unregistered. This causes an error if it's then re-loaded later, as we
try to re-register the bus.
Unregister the bus and root_device on shutdown, if it looks valid.
In addition, be more specific about the value of kunit_bus_device. It
is:
- a valid struct device* if the kunit_bus initialised correctly.
- an ERR_PTR if it failed to initialise.
- NULL before initialisation and after shutdown.
Fixes: d03c720e03bd ("kunit: Add APIs for managing devices")
Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
lib/kunit/device-impl.h | 2 ++
lib/kunit/device.c | 14 ++++++++++++++
lib/kunit/test.c | 3 +++
3 files changed, 19 insertions(+)
diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
index 54bd55836405..5fcd48ff0f36 100644
--- a/lib/kunit/device-impl.h
+++ b/lib/kunit/device-impl.h
@@ -13,5 +13,7 @@
// For internal use only -- registers the kunit_bus.
int kunit_bus_init(void);
+// For internal use only -- unregisters the kunit_bus.
+void kunit_bus_shutdown(void);
#endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
index 074c6dd2e36a..644a38a1f5b1 100644
--- a/lib/kunit/device.c
+++ b/lib/kunit/device.c
@@ -54,6 +54,20 @@ int kunit_bus_init(void)
return error;
}
+/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */
+void kunit_bus_shutdown(void)
+{
+ /* Make sure the bus exists before we unregister it. */
+ if (IS_ERR_OR_NULL(kunit_bus_device))
+ return;
+
+ bus_unregister(&kunit_bus_type);
+
+ root_device_unregister(kunit_bus_device);
+
+ kunit_bus_device = NULL;
+}
+
/* Release a 'fake' KUnit device. */
static void kunit_device_release(struct device *d)
{
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 31a5a992e646..1d1475578515 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -928,6 +928,9 @@ static void __exit kunit_exit(void)
#ifdef CONFIG_MODULES
unregister_module_notifier(&kunit_mod_nb);
#endif
+
+ kunit_bus_shutdown();
+
kunit_debugfs_cleanup();
}
module_exit(kunit_exit);
From 97cf301fa42e8ea6e0a24de97bc0abcdc87d9504 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 28 Jan 2024 13:04:05 +0100
Subject: [PATCH 262/637] riscv: Flush the tlb when a page directory is freed
The riscv privileged specification mandates to flush the TLB whenever a
page directory is modified, so add that to tlb_flush().
Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240128120405.25876-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/tlb.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1eb5682b2af6..50b63b5c15bd 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
static inline void tlb_flush(struct mmu_gather *tlb)
{
#ifdef CONFIG_MMU
- if (tlb->fullmm || tlb->need_flush_all)
+ if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
flush_tlb_mm(tlb->mm);
else
flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
From 1279f9d9dec2d7462823a18c29ad61359e0a007d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Sat, 3 Feb 2024 10:31:49 -0800
Subject: [PATCH 263/637] af_unix: Call kfree_skb() for dead unix_(sk)->oob_skb
in GC.
syzbot reported a warning [0] in __unix_gc() with a repro, which
creates a socketpair and sends one socket's fd to itself using the
peer.
socketpair(AF_UNIX, SOCK_STREAM, 0, [3, 4]) = 0
sendmsg(4, {msg_name=NULL, msg_namelen=0, msg_iov=[{iov_base="\360", iov_len=1}],
msg_iovlen=1, msg_control=[{cmsg_len=20, cmsg_level=SOL_SOCKET,
cmsg_type=SCM_RIGHTS, cmsg_data=[3]}],
msg_controllen=24, msg_flags=0}, MSG_OOB|MSG_PROBE|MSG_DONTWAIT|MSG_ZEROCOPY) = 1
This forms a self-cyclic reference that GC should finally untangle
but does not due to lack of MSG_OOB handling, resulting in memory
leak.
Recently, commit 11498715f266 ("af_unix: Remove io_uring code for
GC.") removed io_uring's dead code in GC and revealed the problem.
The code was executed at the final stage of GC and unconditionally
moved all GC candidates from gc_candidates to gc_inflight_list.
That papered over the reported problem by always making the following
WARN_ON_ONCE(!list_empty(&gc_candidates)) false.
The problem has been there since commit 2aab4b969002 ("af_unix: fix
struct pid leaks in OOB support") added full scm support for MSG_OOB
while fixing another bug.
To fix this problem, we must call kfree_skb() for unix_sk(sk)->oob_skb
if the socket still exists in gc_candidates after purging collected skb.
Then, we need to set NULL to oob_skb before calling kfree_skb() because
it calls last fput() and triggers unix_release_sock(), where we call
duplicate kfree_skb(u->oob_skb) if not NULL.
Note that the leaked socket remained being linked to a global list, so
kmemleak also could not detect it. We need to check /proc/net/protocol
to notice the unfreed socket.
[0]:
WARNING: CPU: 0 PID: 2863 at net/unix/garbage.c:345 __unix_gc+0xc74/0xe80 net/unix/garbage.c:345
Modules linked in:
CPU: 0 PID: 2863 Comm: kworker/u4:11 Not tainted 6.8.0-rc1-syzkaller-00583-g1701940b1a02 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Workqueue: events_unbound __unix_gc
RIP: 0010:__unix_gc+0xc74/0xe80 net/unix/garbage.c:345
Code: 8b 5c 24 50 e9 86 f8 ff ff e8 f8 e4 22 f8 31 d2 48 c7 c6 30 6a 69 89 4c 89 ef e8 97 ef ff ff e9 80 f9 ff ff e8 dd e4 22 f8 90 <0f> 0b 90 e9 7b fd ff ff 48 89 df e8 5c e7 7c f8 e9 d3 f8 ff ff e8
RSP: 0018:ffffc9000b03fba0 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffffc9000b03fc10 RCX: ffffffff816c493e
RDX: ffff88802c02d940 RSI: ffffffff896982f3 RDI: ffffc9000b03fb30
RBP: ffffc9000b03fce0 R08: 0000000000000001 R09: fffff52001607f66
R10: 0000000000000003 R11: 0000000000000002 R12: dffffc0000000000
R13: ffffc9000b03fc10 R14: ffffc9000b03fc10 R15: 0000000000000001
FS: 0000000000000000(0000) GS:ffff8880b9400000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005559c8677a60 CR3: 000000000d57a000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
process_one_work+0x889/0x15e0 kernel/workqueue.c:2633
process_scheduled_works kernel/workqueue.c:2706 [inline]
worker_thread+0x8b9/0x12a0 kernel/workqueue.c:2787
kthread+0x2c6/0x3b0 kernel/kthread.c:388
ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:242
</TASK>
Reported-by: syzbot+fa3ef895554bdbfd1183@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=fa3ef895554bdbfd1183
Fixes: 2aab4b969002 ("af_unix: fix struct pid leaks in OOB support")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240203183149.63573-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/unix/garbage.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 2405f0f9af31..8f63f0b4bf01 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -314,6 +314,17 @@ void unix_gc(void)
/* Here we are. Hitlist is filled. Die. */
__skb_queue_purge(&hitlist);
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+ list_for_each_entry_safe(u, next, &gc_candidates, link) {
+ struct sk_buff *skb = u->oob_skb;
+
+ if (skb) {
+ u->oob_skb = NULL;
+ kfree_skb(skb);
+ }
+ }
+#endif
+
spin_lock(&unix_gc_lock);
/* There could be io_uring registered files, just push them back to
From 58086721b7781c3e35b19c9b78c8f5a791070ba3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 5 Feb 2024 18:11:14 +0100
Subject: [PATCH 264/637] devlink: avoid potential loop in
devlink_rel_nested_in_notify_work()
In case devlink_rel_nested_in_notify_work() can not take the devlink
lock mutex. Convert the work to delayed work and in case of reschedule
do it jiffie later and avoid potential looping.
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Fixes: c137743bce02 ("devlink: introduce object and nested devlink relationship infra")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240205171114.338679-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/devlink/core.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/net/devlink/core.c b/net/devlink/core.c
index 4275a2bc6d8e..6a58342752b4 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -46,7 +46,7 @@ struct devlink_rel {
u32 obj_index;
devlink_rel_notify_cb_t *notify_cb;
devlink_rel_cleanup_cb_t *cleanup_cb;
- struct work_struct notify_work;
+ struct delayed_work notify_work;
} nested_in;
};
@@ -70,7 +70,7 @@ static void __devlink_rel_put(struct devlink_rel *rel)
static void devlink_rel_nested_in_notify_work(struct work_struct *work)
{
struct devlink_rel *rel = container_of(work, struct devlink_rel,
- nested_in.notify_work);
+ nested_in.notify_work.work);
struct devlink *devlink;
devlink = devlinks_xa_get(rel->nested_in.devlink_index);
@@ -96,13 +96,13 @@ rel_put:
return;
reschedule_work:
- schedule_work(&rel->nested_in.notify_work);
+ schedule_delayed_work(&rel->nested_in.notify_work, 1);
}
static void devlink_rel_nested_in_notify_work_schedule(struct devlink_rel *rel)
{
__devlink_rel_get(rel);
- schedule_work(&rel->nested_in.notify_work);
+ schedule_delayed_work(&rel->nested_in.notify_work, 0);
}
static struct devlink_rel *devlink_rel_alloc(void)
@@ -123,8 +123,8 @@ static struct devlink_rel *devlink_rel_alloc(void)
}
refcount_set(&rel->refcount, 1);
- INIT_WORK(&rel->nested_in.notify_work,
- &devlink_rel_nested_in_notify_work);
+ INIT_DELAYED_WORK(&rel->nested_in.notify_work,
+ &devlink_rel_nested_in_notify_work);
return rel;
}
From cb88cb53badb8aeb3955ad6ce80b07b598e310b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 5 Feb 2024 17:10:04 +0000
Subject: [PATCH 265/637] ppp_async: limit MRU to 64K
syzbot triggered a warning [1] in __alloc_pages():
WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp)
Willem fixed a similar issue in commit c0a2a1b0d631 ("ppp: limit MRU to 64K")
Adopt the same sanity check for ppp_async_ioctl(PPPIOCSMRU)
[1]:
WARNING: CPU: 1 PID: 11 at mm/page_alloc.c:4543 __alloc_pages+0x308/0x698 mm/page_alloc.c:4543
Modules linked in:
CPU: 1 PID: 11 Comm: kworker/u4:0 Not tainted 6.8.0-rc2-syzkaller-g41bccc98fb79 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Workqueue: events_unbound flush_to_ldisc
pstate: 204000c5 (nzCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __alloc_pages+0x308/0x698 mm/page_alloc.c:4543
lr : __alloc_pages+0xc8/0x698 mm/page_alloc.c:4537
sp : ffff800093967580
x29: ffff800093967660 x28: ffff8000939675a0 x27: dfff800000000000
x26: ffff70001272ceb4 x25: 0000000000000000 x24: ffff8000939675c0
x23: 0000000000000000 x22: 0000000000060820 x21: 1ffff0001272ceb8
x20: ffff8000939675e0 x19: 0000000000000010 x18: ffff800093967120
x17: ffff800083bded5c x16: ffff80008ac97500 x15: 0000000000000005
x14: 1ffff0001272cebc x13: 0000000000000000 x12: 0000000000000000
x11: ffff70001272cec1 x10: 1ffff0001272cec0 x9 : 0000000000000001
x8 : ffff800091c91000 x7 : 0000000000000000 x6 : 000000000000003f
x5 : 00000000ffffffff x4 : 0000000000000000 x3 : 0000000000000020
x2 : 0000000000000008 x1 : 0000000000000000 x0 : ffff8000939675e0
Call trace:
__alloc_pages+0x308/0x698 mm/page_alloc.c:4543
__alloc_pages_node include/linux/gfp.h:238 [inline]
alloc_pages_node include/linux/gfp.h:261 [inline]
__kmalloc_large_node+0xbc/0x1fc mm/slub.c:3926
__do_kmalloc_node mm/slub.c:3969 [inline]
__kmalloc_node_track_caller+0x418/0x620 mm/slub.c:4001
kmalloc_reserve+0x17c/0x23c net/core/skbuff.c:590
__alloc_skb+0x1c8/0x3d8 net/core/skbuff.c:651
__netdev_alloc_skb+0xb8/0x3e8 net/core/skbuff.c:715
netdev_alloc_skb include/linux/skbuff.h:3235 [inline]
dev_alloc_skb include/linux/skbuff.h:3248 [inline]
ppp_async_input drivers/net/ppp/ppp_async.c:863 [inline]
ppp_asynctty_receive+0x588/0x186c drivers/net/ppp/ppp_async.c:341
tty_ldisc_receive_buf+0x12c/0x15c drivers/tty/tty_buffer.c:390
tty_port_default_receive_buf+0x74/0xac drivers/tty/tty_port.c:37
receive_buf drivers/tty/tty_buffer.c:444 [inline]
flush_to_ldisc+0x284/0x6e4 drivers/tty/tty_buffer.c:494
process_one_work+0x694/0x1204 kernel/workqueue.c:2633
process_scheduled_works kernel/workqueue.c:2706 [inline]
worker_thread+0x938/0xef4 kernel/workqueue.c:2787
kthread+0x288/0x310 kernel/kthread.c:388
ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:860
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-and-tested-by: syzbot+c5da1f087c9e4ec6c933@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240205171004.1059724-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ppp/ppp_async.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 840da924708b..125793d8aefa 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -460,6 +460,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg)
case PPPIOCSMRU:
if (get_user(val, p))
break;
+ if (val > U16_MAX) {
+ err = -EINVAL;
+ break;
+ }
if (val < PPP_MRU)
val = PPP_MRU;
ap->mru = val;
From 38cc3c6dcc09dc3a1800b5ec22aef643ca11eab8 Mon Sep 17 00:00:00 2001
From: Petr Tesarik <petr@tesarici.cz>
Date: Sat, 3 Feb 2024 20:09:27 +0100
Subject: [PATCH 266/637] net: stmmac: protect updates of 64-bit statistics
counters
As explained by a comment in <linux/u64_stats_sync.h>, write side of struct
u64_stats_sync must ensure mutual exclusion, or one seqcount update could
be lost on 32-bit platforms, thus blocking readers forever. Such lockups
have been observed in real world after stmmac_xmit() on one CPU raced with
stmmac_napi_poll_tx() on another CPU.
To fix the issue without introducing a new lock, split the statics into
three parts:
1. fields updated only under the tx queue lock,
2. fields updated only during NAPI poll,
3. fields updated only from interrupt context,
Updates to fields in the first two groups are already serialized through
other locks. It is sufficient to split the existing struct u64_stats_sync
so that each group has its own.
Note that tx_set_ic_bit is updated from both contexts. Split this counter
so that each context gets its own, and calculate their sum to get the total
value in stmmac_get_ethtool_stats().
For the third group, multiple interrupts may be processed by different CPUs
at the same time, but interrupts on the same CPU will not nest. Move fields
from this group to a newly created per-cpu struct stmmac_pcpu_stats.
Fixes: 133466c3bbe1 ("net: stmmac: use per-queue 64 bit statistics where necessary")
Link: https://lore.kernel.org/netdev/Za173PhviYg-1qIn@torres.zugschlus.de/t/
Cc: stable@vger.kernel.org
Signed-off-by: Petr Tesarik <petr@tesarici.cz>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 56 +++++---
.../net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 15 +-
.../net/ethernet/stmicro/stmmac/dwmac4_lib.c | 15 +-
.../net/ethernet/stmicro/stmmac/dwmac_lib.c | 15 +-
.../ethernet/stmicro/stmmac/dwxgmac2_dma.c | 15 +-
.../ethernet/stmicro/stmmac/stmmac_ethtool.c | 125 ++++++++++------
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 133 +++++++++---------
7 files changed, 219 insertions(+), 155 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index b4f60ab078d6..5ba606a596e7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -59,28 +59,51 @@
#undef FRAME_FILTER_DEBUG
/* #define FRAME_FILTER_DEBUG */
+struct stmmac_q_tx_stats {
+ u64_stats_t tx_bytes;
+ u64_stats_t tx_set_ic_bit;
+ u64_stats_t tx_tso_frames;
+ u64_stats_t tx_tso_nfrags;
+};
+
+struct stmmac_napi_tx_stats {
+ u64_stats_t tx_packets;
+ u64_stats_t tx_pkt_n;
+ u64_stats_t poll;
+ u64_stats_t tx_clean;
+ u64_stats_t tx_set_ic_bit;
+};
+
struct stmmac_txq_stats {
- u64 tx_bytes;
- u64 tx_packets;
- u64 tx_pkt_n;
- u64 tx_normal_irq_n;
- u64 napi_poll;
- u64 tx_clean;
- u64 tx_set_ic_bit;
- u64 tx_tso_frames;
- u64 tx_tso_nfrags;
- struct u64_stats_sync syncp;
+ /* Updates protected by tx queue lock. */
+ struct u64_stats_sync q_syncp;
+ struct stmmac_q_tx_stats q;
+
+ /* Updates protected by NAPI poll logic. */
+ struct u64_stats_sync napi_syncp;
+ struct stmmac_napi_tx_stats napi;
} ____cacheline_aligned_in_smp;
+struct stmmac_napi_rx_stats {
+ u64_stats_t rx_bytes;
+ u64_stats_t rx_packets;
+ u64_stats_t rx_pkt_n;
+ u64_stats_t poll;
+};
+
struct stmmac_rxq_stats {
- u64 rx_bytes;
- u64 rx_packets;
- u64 rx_pkt_n;
- u64 rx_normal_irq_n;
- u64 napi_poll;
- struct u64_stats_sync syncp;
+ /* Updates protected by NAPI poll logic. */
+ struct u64_stats_sync napi_syncp;
+ struct stmmac_napi_rx_stats napi;
} ____cacheline_aligned_in_smp;
+/* Updates on each CPU protected by not allowing nested irqs. */
+struct stmmac_pcpu_stats {
+ struct u64_stats_sync syncp;
+ u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
+ u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+};
+
/* Extra statistic and debug information exposed by ethtool */
struct stmmac_extra_stats {
/* Transmit errors */
@@ -205,6 +228,7 @@ struct stmmac_extra_stats {
/* per queue statistics */
struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES];
struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES];
+ struct stmmac_pcpu_stats __percpu *pcpu_stats;
unsigned long rx_dropped;
unsigned long rx_errors;
unsigned long tx_dropped;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 137741b94122..b21d99faa2d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -441,8 +441,7 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
struct stmmac_extra_stats *x, u32 chan,
u32 dir)
{
- struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
- struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
int ret = 0;
u32 v;
@@ -455,9 +454,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
if (v & EMAC_TX_INT) {
ret |= handle_tx;
- u64_stats_update_begin(&txq_stats->syncp);
- txq_stats->tx_normal_irq_n++;
- u64_stats_update_end(&txq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
}
if (v & EMAC_TX_DMA_STOP_INT)
@@ -479,9 +478,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv,
if (v & EMAC_RX_INT) {
ret |= handle_rx;
- u64_stats_update_begin(&rxq_stats->syncp);
- rxq_stats->rx_normal_irq_n++;
- u64_stats_update_end(&rxq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
}
if (v & EMAC_RX_BUF_UA_INT)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 9470d3fd2ded..0d185e54eb7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -171,8 +171,7 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs;
u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan));
u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan));
- struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
- struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
int ret = 0;
if (dir == DMA_DIR_RX)
@@ -201,15 +200,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
}
/* TX/RX NORMAL interrupts */
if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
- u64_stats_update_begin(&rxq_stats->syncp);
- rxq_stats->rx_normal_irq_n++;
- u64_stats_update_end(&rxq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_rx;
}
if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
- u64_stats_update_begin(&txq_stats->syncp);
- txq_stats->tx_normal_irq_n++;
- u64_stats_update_end(&txq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_tx;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 7907d62d3437..85e18f9a22f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -162,8 +162,7 @@ static void show_rx_process_state(unsigned int status)
int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
struct stmmac_extra_stats *x, u32 chan, u32 dir)
{
- struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
- struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
int ret = 0;
/* read the status register (CSR5) */
u32 intr_status = readl(ioaddr + DMA_STATUS);
@@ -215,16 +214,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
u32 value = readl(ioaddr + DMA_INTR_ENA);
/* to schedule NAPI on real RIE event. */
if (likely(value & DMA_INTR_ENA_RIE)) {
- u64_stats_update_begin(&rxq_stats->syncp);
- rxq_stats->rx_normal_irq_n++;
- u64_stats_update_end(&rxq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_rx;
}
}
if (likely(intr_status & DMA_STATUS_TI)) {
- u64_stats_update_begin(&txq_stats->syncp);
- txq_stats->tx_normal_irq_n++;
- u64_stats_update_end(&txq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_tx;
}
if (unlikely(intr_status & DMA_STATUS_ERI))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 3cde695fec91..dd2ab6185c40 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -337,8 +337,7 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
struct stmmac_extra_stats *x, u32 chan,
u32 dir)
{
- struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan];
- struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan];
+ struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
int ret = 0;
@@ -367,15 +366,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
/* TX/RX NORMAL interrupts */
if (likely(intr_status & XGMAC_NIS)) {
if (likely(intr_status & XGMAC_RI)) {
- u64_stats_update_begin(&rxq_stats->syncp);
- rxq_stats->rx_normal_irq_n++;
- u64_stats_update_end(&rxq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_rx;
}
if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
- u64_stats_update_begin(&txq_stats->syncp);
- txq_stats->tx_normal_irq_n++;
- u64_stats_update_end(&txq_stats->syncp);
+ u64_stats_update_begin(&stats->syncp);
+ u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+ u64_stats_update_end(&stats->syncp);
ret |= handle_tx;
}
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 42d27b97dd1d..ec44becf0e2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -549,44 +549,79 @@ stmmac_set_pauseparam(struct net_device *netdev,
}
}
+static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+ u64 total;
+ int cpu;
+
+ total = 0;
+ for_each_possible_cpu(cpu) {
+ struct stmmac_pcpu_stats *pcpu;
+ unsigned int start;
+ u64 irq_n;
+
+ pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+ do {
+ start = u64_stats_fetch_begin(&pcpu->syncp);
+ irq_n = u64_stats_read(&pcpu->rx_normal_irq_n[q]);
+ } while (u64_stats_fetch_retry(&pcpu->syncp, start));
+ total += irq_n;
+ }
+ return total;
+}
+
+static u64 stmmac_get_tx_normal_irq_n(struct stmmac_priv *priv, int q)
+{
+ u64 total;
+ int cpu;
+
+ total = 0;
+ for_each_possible_cpu(cpu) {
+ struct stmmac_pcpu_stats *pcpu;
+ unsigned int start;
+ u64 irq_n;
+
+ pcpu = per_cpu_ptr(priv->xstats.pcpu_stats, cpu);
+ do {
+ start = u64_stats_fetch_begin(&pcpu->syncp);
+ irq_n = u64_stats_read(&pcpu->tx_normal_irq_n[q]);
+ } while (u64_stats_fetch_retry(&pcpu->syncp, start));
+ total += irq_n;
+ }
+ return total;
+}
+
static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
{
u32 tx_cnt = priv->plat->tx_queues_to_use;
u32 rx_cnt = priv->plat->rx_queues_to_use;
unsigned int start;
- int q, stat;
- char *p;
+ int q;
for (q = 0; q < tx_cnt; q++) {
struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q];
- struct stmmac_txq_stats snapshot;
+ u64 pkt_n;
do {
- start = u64_stats_fetch_begin(&txq_stats->syncp);
- snapshot = *txq_stats;
- } while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+ pkt_n = u64_stats_read(&txq_stats->napi.tx_pkt_n);
+ } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
- p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n);
- for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64);
- }
+ *data++ = pkt_n;
+ *data++ = stmmac_get_tx_normal_irq_n(priv, q);
}
for (q = 0; q < rx_cnt; q++) {
struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q];
- struct stmmac_rxq_stats snapshot;
+ u64 pkt_n;
do {
- start = u64_stats_fetch_begin(&rxq_stats->syncp);
- snapshot = *rxq_stats;
- } while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+ pkt_n = u64_stats_read(&rxq_stats->napi.rx_pkt_n);
+ } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
- p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n);
- for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64);
- }
+ *data++ = pkt_n;
+ *data++ = stmmac_get_rx_normal_irq_n(priv, q);
}
}
@@ -645,39 +680,49 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
pos = j;
for (i = 0; i < rx_queues_count; i++) {
struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i];
- struct stmmac_rxq_stats snapshot;
+ struct stmmac_napi_rx_stats snapshot;
+ u64 n_irq;
j = pos;
do {
- start = u64_stats_fetch_begin(&rxq_stats->syncp);
- snapshot = *rxq_stats;
- } while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+ snapshot = rxq_stats->napi;
+ } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
- data[j++] += snapshot.rx_pkt_n;
- data[j++] += snapshot.rx_normal_irq_n;
- normal_irq_n += snapshot.rx_normal_irq_n;
- napi_poll += snapshot.napi_poll;
+ data[j++] += u64_stats_read(&snapshot.rx_pkt_n);
+ n_irq = stmmac_get_rx_normal_irq_n(priv, i);
+ data[j++] += n_irq;
+ normal_irq_n += n_irq;
+ napi_poll += u64_stats_read(&snapshot.poll);
}
pos = j;
for (i = 0; i < tx_queues_count; i++) {
struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i];
- struct stmmac_txq_stats snapshot;
+ struct stmmac_napi_tx_stats napi_snapshot;
+ struct stmmac_q_tx_stats q_snapshot;
+ u64 n_irq;
j = pos;
do {
- start = u64_stats_fetch_begin(&txq_stats->syncp);
- snapshot = *txq_stats;
- } while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+ q_snapshot = txq_stats->q;
+ } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+ do {
+ start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+ napi_snapshot = txq_stats->napi;
+ } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
- data[j++] += snapshot.tx_pkt_n;
- data[j++] += snapshot.tx_normal_irq_n;
- normal_irq_n += snapshot.tx_normal_irq_n;
- data[j++] += snapshot.tx_clean;
- data[j++] += snapshot.tx_set_ic_bit;
- data[j++] += snapshot.tx_tso_frames;
- data[j++] += snapshot.tx_tso_nfrags;
- napi_poll += snapshot.napi_poll;
+ data[j++] += u64_stats_read(&napi_snapshot.tx_pkt_n);
+ n_irq = stmmac_get_tx_normal_irq_n(priv, i);
+ data[j++] += n_irq;
+ normal_irq_n += n_irq;
+ data[j++] += u64_stats_read(&napi_snapshot.tx_clean);
+ data[j++] += u64_stats_read(&q_snapshot.tx_set_ic_bit) +
+ u64_stats_read(&napi_snapshot.tx_set_ic_bit);
+ data[j++] += u64_stats_read(&q_snapshot.tx_tso_frames);
+ data[j++] += u64_stats_read(&q_snapshot.tx_tso_nfrags);
+ napi_poll += u64_stats_read(&napi_snapshot.poll);
}
normal_irq_n += priv->xstats.rx_early_irq;
data[j++] = normal_irq_n;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 25519952f754..75d029704503 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2482,7 +2482,6 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
struct xdp_desc xdp_desc;
bool work_done = true;
u32 tx_set_ic_bit = 0;
- unsigned long flags;
/* Avoids TX time-out as we are sharing with slow path */
txq_trans_cond_update(nq);
@@ -2566,9 +2565,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size);
entry = tx_q->cur_tx;
}
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->tx_set_ic_bit += tx_set_ic_bit;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_update_begin(&txq_stats->napi_syncp);
+ u64_stats_add(&txq_stats->napi.tx_set_ic_bit, tx_set_ic_bit);
+ u64_stats_update_end(&txq_stats->napi_syncp);
if (tx_desc) {
stmmac_flush_tx_descriptors(priv, queue);
@@ -2616,7 +2615,6 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
unsigned int bytes_compl = 0, pkts_compl = 0;
unsigned int entry, xmits = 0, count = 0;
u32 tx_packets = 0, tx_errors = 0;
- unsigned long flags;
__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
@@ -2782,11 +2780,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue,
if (tx_q->dirty_tx != tx_q->cur_tx)
*pending_packets = true;
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->tx_packets += tx_packets;
- txq_stats->tx_pkt_n += tx_packets;
- txq_stats->tx_clean++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_update_begin(&txq_stats->napi_syncp);
+ u64_stats_add(&txq_stats->napi.tx_packets, tx_packets);
+ u64_stats_add(&txq_stats->napi.tx_pkt_n, tx_packets);
+ u64_stats_inc(&txq_stats->napi.tx_clean);
+ u64_stats_update_end(&txq_stats->napi_syncp);
priv->xstats.tx_errors += tx_errors;
@@ -4213,7 +4211,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
struct stmmac_tx_queue *tx_q;
bool has_vlan, set_ic;
u8 proto_hdr_len, hdr;
- unsigned long flags;
u32 pay_len, mss;
dma_addr_t des;
int i;
@@ -4378,13 +4375,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->tx_bytes += skb->len;
- txq_stats->tx_tso_frames++;
- txq_stats->tx_tso_nfrags += nfrags;
+ u64_stats_update_begin(&txq_stats->q_syncp);
+ u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
+ u64_stats_inc(&txq_stats->q.tx_tso_frames);
+ u64_stats_add(&txq_stats->q.tx_tso_nfrags, nfrags);
if (set_ic)
- txq_stats->tx_set_ic_bit++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+ u64_stats_update_end(&txq_stats->q_syncp);
if (priv->sarc_type)
stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4483,7 +4480,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
struct stmmac_tx_queue *tx_q;
bool has_vlan, set_ic;
int entry, first_tx;
- unsigned long flags;
dma_addr_t des;
tx_q = &priv->dma_conf.tx_queue[queue];
@@ -4653,11 +4649,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
}
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->tx_bytes += skb->len;
+ u64_stats_update_begin(&txq_stats->q_syncp);
+ u64_stats_add(&txq_stats->q.tx_bytes, skb->len);
if (set_ic)
- txq_stats->tx_set_ic_bit++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+ u64_stats_update_end(&txq_stats->q_syncp);
if (priv->sarc_type)
stmmac_set_desc_sarc(priv, first, priv->sarc_type);
@@ -4921,12 +4917,11 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
set_ic = false;
if (set_ic) {
- unsigned long flags;
tx_q->tx_count_frames = 0;
stmmac_set_tx_ic(priv, tx_desc);
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->tx_set_ic_bit++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_update_begin(&txq_stats->q_syncp);
+ u64_stats_inc(&txq_stats->q.tx_set_ic_bit);
+ u64_stats_update_end(&txq_stats->q_syncp);
}
stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -5076,7 +5071,6 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
unsigned int len = xdp->data_end - xdp->data;
enum pkt_hash_types hash_type;
int coe = priv->hw->rx_csum;
- unsigned long flags;
struct sk_buff *skb;
u32 hash;
@@ -5106,10 +5100,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue,
skb_record_rx_queue(skb, queue);
napi_gro_receive(&ch->rxtx_napi, skb);
- flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
- rxq_stats->rx_pkt_n++;
- rxq_stats->rx_bytes += len;
- u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+ u64_stats_update_begin(&rxq_stats->napi_syncp);
+ u64_stats_inc(&rxq_stats->napi.rx_pkt_n);
+ u64_stats_add(&rxq_stats->napi.rx_bytes, len);
+ u64_stats_update_end(&rxq_stats->napi_syncp);
}
static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -5191,7 +5185,6 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
unsigned int desc_size;
struct bpf_prog *prog;
bool failure = false;
- unsigned long flags;
int xdp_status = 0;
int status = 0;
@@ -5346,9 +5339,9 @@ read_again:
stmmac_finalize_xdp_rx(priv, xdp_status);
- flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
- rxq_stats->rx_pkt_n += count;
- u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+ u64_stats_update_begin(&rxq_stats->napi_syncp);
+ u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+ u64_stats_update_end(&rxq_stats->napi_syncp);
priv->xstats.rx_dropped += rx_dropped;
priv->xstats.rx_errors += rx_errors;
@@ -5386,7 +5379,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
unsigned int desc_size;
struct sk_buff *skb = NULL;
struct stmmac_xdp_buff ctx;
- unsigned long flags;
int xdp_status = 0;
int buf_sz;
@@ -5646,11 +5638,11 @@ drain_data:
stmmac_rx_refill(priv, queue);
- flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
- rxq_stats->rx_packets += rx_packets;
- rxq_stats->rx_bytes += rx_bytes;
- rxq_stats->rx_pkt_n += count;
- u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+ u64_stats_update_begin(&rxq_stats->napi_syncp);
+ u64_stats_add(&rxq_stats->napi.rx_packets, rx_packets);
+ u64_stats_add(&rxq_stats->napi.rx_bytes, rx_bytes);
+ u64_stats_add(&rxq_stats->napi.rx_pkt_n, count);
+ u64_stats_update_end(&rxq_stats->napi_syncp);
priv->xstats.rx_dropped += rx_dropped;
priv->xstats.rx_errors += rx_errors;
@@ -5665,13 +5657,12 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
struct stmmac_priv *priv = ch->priv_data;
struct stmmac_rxq_stats *rxq_stats;
u32 chan = ch->index;
- unsigned long flags;
int work_done;
rxq_stats = &priv->xstats.rxq_stats[chan];
- flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
- rxq_stats->napi_poll++;
- u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+ u64_stats_update_begin(&rxq_stats->napi_syncp);
+ u64_stats_inc(&rxq_stats->napi.poll);
+ u64_stats_update_end(&rxq_stats->napi_syncp);
work_done = stmmac_rx(priv, budget, chan);
if (work_done < budget && napi_complete_done(napi, work_done)) {
@@ -5693,13 +5684,12 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
struct stmmac_txq_stats *txq_stats;
bool pending_packets = false;
u32 chan = ch->index;
- unsigned long flags;
int work_done;
txq_stats = &priv->xstats.txq_stats[chan];
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->napi_poll++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_update_begin(&txq_stats->napi_syncp);
+ u64_stats_inc(&txq_stats->napi.poll);
+ u64_stats_update_end(&txq_stats->napi_syncp);
work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets);
work_done = min(work_done, budget);
@@ -5729,17 +5719,16 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget)
struct stmmac_rxq_stats *rxq_stats;
struct stmmac_txq_stats *txq_stats;
u32 chan = ch->index;
- unsigned long flags;
rxq_stats = &priv->xstats.rxq_stats[chan];
- flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp);
- rxq_stats->napi_poll++;
- u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags);
+ u64_stats_update_begin(&rxq_stats->napi_syncp);
+ u64_stats_inc(&rxq_stats->napi.poll);
+ u64_stats_update_end(&rxq_stats->napi_syncp);
txq_stats = &priv->xstats.txq_stats[chan];
- flags = u64_stats_update_begin_irqsave(&txq_stats->syncp);
- txq_stats->napi_poll++;
- u64_stats_update_end_irqrestore(&txq_stats->syncp, flags);
+ u64_stats_update_begin(&txq_stats->napi_syncp);
+ u64_stats_inc(&txq_stats->napi.poll);
+ u64_stats_update_end(&txq_stats->napi_syncp);
tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets);
tx_done = min(tx_done, budget);
@@ -7065,10 +7054,13 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
u64 tx_bytes;
do {
- start = u64_stats_fetch_begin(&txq_stats->syncp);
- tx_packets = txq_stats->tx_packets;
- tx_bytes = txq_stats->tx_bytes;
- } while (u64_stats_fetch_retry(&txq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&txq_stats->q_syncp);
+ tx_bytes = u64_stats_read(&txq_stats->q.tx_bytes);
+ } while (u64_stats_fetch_retry(&txq_stats->q_syncp, start));
+ do {
+ start = u64_stats_fetch_begin(&txq_stats->napi_syncp);
+ tx_packets = u64_stats_read(&txq_stats->napi.tx_packets);
+ } while (u64_stats_fetch_retry(&txq_stats->napi_syncp, start));
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
@@ -7080,10 +7072,10 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64
u64 rx_bytes;
do {
- start = u64_stats_fetch_begin(&rxq_stats->syncp);
- rx_packets = rxq_stats->rx_packets;
- rx_bytes = rxq_stats->rx_bytes;
- } while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
+ start = u64_stats_fetch_begin(&rxq_stats->napi_syncp);
+ rx_packets = u64_stats_read(&rxq_stats->napi.rx_packets);
+ rx_bytes = u64_stats_read(&rxq_stats->napi.rx_bytes);
+ } while (u64_stats_fetch_retry(&rxq_stats->napi_syncp, start));
stats->rx_packets += rx_packets;
stats->rx_bytes += rx_bytes;
@@ -7477,9 +7469,16 @@ int stmmac_dvr_probe(struct device *device,
priv->dev = ndev;
for (i = 0; i < MTL_MAX_RX_QUEUES; i++)
- u64_stats_init(&priv->xstats.rxq_stats[i].syncp);
- for (i = 0; i < MTL_MAX_TX_QUEUES; i++)
- u64_stats_init(&priv->xstats.txq_stats[i].syncp);
+ u64_stats_init(&priv->xstats.rxq_stats[i].napi_syncp);
+ for (i = 0; i < MTL_MAX_TX_QUEUES; i++) {
+ u64_stats_init(&priv->xstats.txq_stats[i].q_syncp);
+ u64_stats_init(&priv->xstats.txq_stats[i].napi_syncp);
+ }
+
+ priv->xstats.pcpu_stats =
+ devm_netdev_alloc_pcpu_stats(device, struct stmmac_pcpu_stats);
+ if (!priv->xstats.pcpu_stats)
+ return -ENOMEM;
stmmac_set_ethtool_ops(ndev);
priv->pause = pause;
From d1722057477a3786b8c0d60c28fc281f6ecf1cc3 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 6 Feb 2024 11:38:49 +0000
Subject: [PATCH 267/637] ASoC: cs42l43: Handle error from
devm_pm_runtime_enable
As devm_pm_runtime_enable can fail due to memory allocations, it is
best to handle the error.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20240206113850.719888-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs42l43.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 6a64681767de..4d2a5584aa57 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2257,7 +2257,10 @@ static int cs42l43_codec_probe(struct platform_device *pdev)
pm_runtime_use_autosuspend(priv->dev);
pm_runtime_set_active(priv->dev);
pm_runtime_get_noresume(priv->dev);
- devm_pm_runtime_enable(priv->dev);
+
+ ret = devm_pm_runtime_enable(priv->dev);
+ if (ret)
+ goto err_pm;
for (i = 0; i < ARRAY_SIZE(cs42l43_irqs); i++) {
ret = cs42l43_request_irq(priv, dom, cs42l43_irqs[i].name,
From 64353af49fecbdec1de9aadf2369d54fc00f1899 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 6 Feb 2024 11:38:50 +0000
Subject: [PATCH 268/637] ASoC: cs42l43: Add system suspend ops to disable IRQ
The IRQ should be disabled whilst entering and exiting system suspend to
avoid the IRQ handler being called whilst the PM runtime is disabled.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20240206113850.719888-2-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs42l43.c | 43 ++++++++++++++++++++++++++++++++++++--
1 file changed, 41 insertions(+), 2 deletions(-)
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 4d2a5584aa57..a97ccb512deb 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2336,8 +2336,47 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
return 0;
}
-static DEFINE_RUNTIME_DEV_PM_OPS(cs42l43_codec_pm_ops, NULL,
- cs42l43_codec_runtime_resume, NULL);
+static int cs42l43_codec_suspend(struct device *dev)
+{
+ struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+ disable_irq(cs42l43->irq);
+
+ return 0;
+}
+
+static int cs42l43_codec_suspend_noirq(struct device *dev)
+{
+ struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+ enable_irq(cs42l43->irq);
+
+ return 0;
+}
+
+static int cs42l43_codec_resume(struct device *dev)
+{
+ struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+ enable_irq(cs42l43->irq);
+
+ return 0;
+}
+
+static int cs42l43_codec_resume_noirq(struct device *dev)
+{
+ struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+
+ disable_irq(cs42l43->irq);
+
+ return 0;
+}
+
+static const struct dev_pm_ops cs42l43_codec_pm_ops = {
+ SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend, cs42l43_codec_resume)
+ NOIRQ_SYSTEM_SLEEP_PM_OPS(cs42l43_codec_suspend_noirq, cs42l43_codec_resume_noirq)
+ RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL)
+};
static const struct platform_device_id cs42l43_codec_id_table[] = {
{ "cs42l43-codec", },
From 7011b51f13b391ee06708bb1f82653a2953f8cfc Mon Sep 17 00:00:00 2001
From: Ben Wolsieffer <ben.wolsieffer@hefring.com>
Date: Tue, 6 Feb 2024 10:10:05 -0500
Subject: [PATCH 269/637] regmap: kunit: fix raw noinc write test wrapping
The raw noinc write test places a known value in the register following
the noinc register to verify that it is not disturbed by the noinc
write. This test ensures this value is distinct by adding 100 to the
second element of the noinc write data.
The regmap registers are 16-bit, while the test value is stored in an
unsigned int. Therefore, adding 100 may cause the register to wrap while
the test value does not, causing the test to fail. This patch fixes this
by changing val_test and val_last from unsigned int to u16.
Signed-off-by: Ben Wolsieffer <ben.wolsieffer@hefring.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/linux-kernel/745d3a11-15bc-48b6-84c8-c8761c943bed@roeck-us.net/T/
Tested-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20240206151004.1636761-2-ben.wolsieffer@hefring.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/base/regmap/regmap-kunit.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
index 026bdcb45127..4eb18f5d3265 100644
--- a/drivers/base/regmap/regmap-kunit.c
+++ b/drivers/base/regmap/regmap-kunit.c
@@ -1202,7 +1202,8 @@ static void raw_noinc_write(struct kunit *test)
struct regmap *map;
struct regmap_config config;
struct regmap_ram_data *data;
- unsigned int val, val_test, val_last;
+ unsigned int val;
+ u16 val_test, val_last;
u16 val_array[BLOCK_TEST_SIZE];
config = raw_regmap_config;
From 4b00d0c513da58b68df015968721b11396fe4ab3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 4 Feb 2024 08:56:18 -0800
Subject: [PATCH 270/637] selftests: cmsg_ipv6: repeat the exact packet
cmsg_ipv6 test requests tcpdump to capture 4 packets,
and sends until tcpdump quits. Only the first packet
is "real", however, and the rest are basic UDP packets.
So if tcpdump doesn't start in time it will miss
the real packet and only capture the UDP ones.
This makes the test fail on slow machine (no KVM or with
debug enabled) 100% of the time, while it passes in fast
environments.
Repeat the "real" / expected packet.
Fixes: 9657ad09e1fa ("selftests: net: test IPV6_TCLASS")
Fixes: 05ae83d5a4a2 ("selftests: net: test IPV6_HOPLIMIT")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/cmsg_ipv6.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index f30bd57d5e38..8bc23fb4c82b 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -89,7 +89,7 @@ for ovr in setsock cmsg both diff; do
check_result $? 0 "TCLASS $prot $ovr - pass"
while [ -d /proc/$BG ]; do
- $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+ $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
done
tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
@@ -126,7 +126,7 @@ for ovr in setsock cmsg both diff; do
check_result $? 0 "HOPLIMIT $prot $ovr - pass"
while [ -d /proc/$BG ]; do
- $NSEXE ./cmsg_sender -6 -p u $TGT6 1234
+ $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
done
tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
From cd7d469c25704d414d71bf3644f163fb74e7996b Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Fri, 13 Oct 2023 13:55:44 +0800
Subject: [PATCH 271/637] libceph: fail sparse-read if the data length doesn't
match
Once this happens that means there have bugs.
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
include/linux/ceph/osd_client.h | 3 ++-
net/ceph/osd_client.c | 18 +++++++++++++++---
2 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fa018d5864e7..f66f6aac74f6 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -45,6 +45,7 @@ enum ceph_sparse_read_state {
CEPH_SPARSE_READ_HDR = 0,
CEPH_SPARSE_READ_EXTENTS,
CEPH_SPARSE_READ_DATA_LEN,
+ CEPH_SPARSE_READ_DATA_PRE,
CEPH_SPARSE_READ_DATA,
};
@@ -64,7 +65,7 @@ struct ceph_sparse_read {
u64 sr_req_len; /* orig request length */
u64 sr_pos; /* current pos in buffer */
int sr_index; /* current extent index */
- __le32 sr_datalen; /* length of actual data */
+ u32 sr_datalen; /* length of actual data */
u32 sr_count; /* extent count in reply */
int sr_ext_len; /* length of extent array */
struct ceph_sparse_extent *sr_extent; /* extent array */
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 625622016f57..2cea35e4ff8e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5857,8 +5857,8 @@ static int osd_sparse_read(struct ceph_connection *con,
struct ceph_osd *o = con->private;
struct ceph_sparse_read *sr = &o->o_sparse_read;
u32 count = sr->sr_count;
- u64 eoff, elen;
- int ret;
+ u64 eoff, elen, len = 0;
+ int i, ret;
switch (sr->sr_state) {
case CEPH_SPARSE_READ_HDR:
@@ -5903,8 +5903,20 @@ next_op:
convert_extent_map(sr);
ret = sizeof(sr->sr_datalen);
*pbuf = (char *)&sr->sr_datalen;
- sr->sr_state = CEPH_SPARSE_READ_DATA;
+ sr->sr_state = CEPH_SPARSE_READ_DATA_PRE;
break;
+ case CEPH_SPARSE_READ_DATA_PRE:
+ /* Convert sr_datalen to host-endian */
+ sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen);
+ for (i = 0; i < count; i++)
+ len += sr->sr_extent[i].len;
+ if (sr->sr_datalen != len) {
+ pr_warn_ratelimited("data len %u != extent len %llu\n",
+ sr->sr_datalen, len);
+ return -EREMOTEIO;
+ }
+ sr->sr_state = CEPH_SPARSE_READ_DATA;
+ fallthrough;
case CEPH_SPARSE_READ_DATA:
if (sr->sr_index >= count) {
sr->sr_state = CEPH_SPARSE_READ_HDR;
From ee97302fbc0c98a25732d736fc73aaf4d62c4128 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 14 Dec 2023 09:21:15 +0800
Subject: [PATCH 272/637] libceph: rename read_sparse_msg_*() to
read_partial_sparse_msg_*()
These functions are supposed to behave like other read_partial_*()
handlers: the contract with messenger v1 is that the handler bails if
the area of the message it's responsible for is already processed.
This comes up when handling short reads from the socket.
[ idryomov: changelog ]
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
net/ceph/messenger_v1.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index f9a50d7f0d20..4cb60bacf5f5 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -991,7 +991,7 @@ static inline int read_partial_message_section(struct ceph_connection *con,
return read_partial_message_chunk(con, section, sec_len, crc);
}
-static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
+static int read_partial_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
{
struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_bounce = ceph_test_opt(from_msgr(con->msgr), RXBOUNCE);
@@ -1026,7 +1026,7 @@ static int read_sparse_msg_extent(struct ceph_connection *con, u32 *crc)
return 1;
}
-static int read_sparse_msg_data(struct ceph_connection *con)
+static int read_partial_sparse_msg_data(struct ceph_connection *con)
{
struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
@@ -1043,7 +1043,7 @@ static int read_sparse_msg_data(struct ceph_connection *con)
con->v1.in_sr_len,
&crc);
else if (cursor->sr_resid > 0)
- ret = read_sparse_msg_extent(con, &crc);
+ ret = read_partial_sparse_msg_extent(con, &crc);
if (ret <= 0) {
if (do_datacrc)
@@ -1254,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con)
return -EIO;
if (m->sparse_read)
- ret = read_sparse_msg_data(con);
+ ret = read_partial_sparse_msg_data(con);
else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
ret = read_partial_msg_data_bounce(con);
else
From 8e46a2d068c92a905d01cbb018b00d66991585ab Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 14 Dec 2023 16:01:03 +0800
Subject: [PATCH 273/637] libceph: just wait for more data to be available on
the socket
A short read may occur while reading the message footer from the
socket. Later, when the socket is ready for another read, the
messenger invokes all read_partial_*() handlers, including
read_partial_sparse_msg_data(). The expectation is that
read_partial_sparse_msg_data() would bail, allowing the messenger to
invoke read_partial() for the footer and pick up where it left off.
However read_partial_sparse_msg_data() violates that and ends up
calling into the state machine in the OSD client. The sparse-read
state machine assumes that it's a new op and interprets some piece of
the footer as the sparse-read header and returns bogus extents/data
length, etc.
To determine whether read_partial_sparse_msg_data() should bail, let's
reuse cursor->total_resid. Because once it reaches to zero that means
all the extents and data have been successfully received in last read,
else it could break out when partially reading any of the extents and
data. And then osd_sparse_read() could continue where it left off.
[ idryomov: changelog ]
Link: https://tracker.ceph.com/issues/63586
Fixes: d396f89db39a ("libceph: add sparse read support to msgr1")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
include/linux/ceph/messenger.h | 2 +-
net/ceph/messenger_v1.c | 25 +++++++++++++------------
net/ceph/messenger_v2.c | 4 ++--
net/ceph/osd_client.c | 9 +++------
4 files changed, 19 insertions(+), 21 deletions(-)
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 2eaaabbe98cb..1717cc57cdac 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -283,7 +283,7 @@ struct ceph_msg {
struct kref kref;
bool more_to_follow;
bool needs_out_seq;
- bool sparse_read;
+ u64 sparse_read_total;
int front_alloc_len;
struct ceph_msgpool *pool;
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 4cb60bacf5f5..0cb61c76b9b8 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -160,8 +160,9 @@ static size_t sizeof_footer(struct ceph_connection *con)
static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
{
/* Initialize data cursor if it's not a sparse read */
- if (!msg->sparse_read)
- ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+ u64 len = msg->sparse_read_total ? : data_len;
+
+ ceph_msg_data_cursor_init(&msg->cursor, msg, len);
}
/*
@@ -1036,7 +1037,7 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con)
if (do_datacrc)
crc = con->in_data_crc;
- do {
+ while (cursor->total_resid) {
if (con->v1.in_sr_kvec.iov_base)
ret = read_partial_message_chunk(con,
&con->v1.in_sr_kvec,
@@ -1044,23 +1045,23 @@ static int read_partial_sparse_msg_data(struct ceph_connection *con)
&crc);
else if (cursor->sr_resid > 0)
ret = read_partial_sparse_msg_extent(con, &crc);
-
- if (ret <= 0) {
- if (do_datacrc)
- con->in_data_crc = crc;
- return ret;
- }
+ if (ret <= 0)
+ break;
memset(&con->v1.in_sr_kvec, 0, sizeof(con->v1.in_sr_kvec));
ret = con->ops->sparse_read(con, cursor,
(char **)&con->v1.in_sr_kvec.iov_base);
+ if (ret <= 0) {
+ ret = ret ? ret : 1; /* must return > 0 to indicate success */
+ break;
+ }
con->v1.in_sr_len = ret;
- } while (ret > 0);
+ }
if (do_datacrc)
con->in_data_crc = crc;
- return ret < 0 ? ret : 1; /* must return > 0 to indicate success */
+ return ret;
}
static int read_partial_msg_data(struct ceph_connection *con)
@@ -1253,7 +1254,7 @@ static int read_partial_message(struct ceph_connection *con)
if (!m->num_data_items)
return -EIO;
- if (m->sparse_read)
+ if (m->sparse_read_total)
ret = read_partial_sparse_msg_data(con);
else if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
ret = read_partial_msg_data_bounce(con);
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index f8ec60e1aba3..a0ca5414b333 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1128,7 +1128,7 @@ static int decrypt_tail(struct ceph_connection *con)
struct sg_table enc_sgt = {};
struct sg_table sgt = {};
struct page **pages = NULL;
- bool sparse = con->in_msg->sparse_read;
+ bool sparse = !!con->in_msg->sparse_read_total;
int dpos = 0;
int tail_len;
int ret;
@@ -2060,7 +2060,7 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
}
if (data_len(msg)) {
- if (msg->sparse_read)
+ if (msg->sparse_read_total)
con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
else
con->v2.in_state = IN_S_PREPARE_READ_DATA;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 2cea35e4ff8e..9d078b37fe0b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5510,7 +5510,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
}
m = ceph_msg_get(req->r_reply);
- m->sparse_read = (bool)srlen;
+ m->sparse_read_total = srlen;
dout("get_reply tid %lld %p\n", tid, m);
@@ -5777,11 +5777,8 @@ static int prep_next_sparse_read(struct ceph_connection *con,
}
if (o->o_sparse_op_idx < 0) {
- u64 srlen = sparse_data_requested(req);
-
- dout("%s: [%d] starting new sparse read req. srlen=0x%llx\n",
- __func__, o->o_osd, srlen);
- ceph_msg_data_cursor_init(cursor, con->in_msg, srlen);
+ dout("%s: [%d] starting new sparse read req\n",
+ __func__, o->o_osd);
} else {
u64 end;
From bbb20ea993f46743f7429092ddc52f1a5c5428ef Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 18 Jan 2024 14:24:41 +0800
Subject: [PATCH 274/637] ceph: always set initial i_blkbits to
CEPH_FSCRYPT_BLOCK_SHIFT
The fscrypt code will use i_blkbits to setup ci_data_unit_bits when
allocating the new inode, but ceph will initiate i_blkbits ater when
filling the inode, which is too late. Since ci_data_unit_bits will only
be used by the fscrypt framework so initiating i_blkbits with
CEPH_FSCRYPT_BLOCK_SHIFT is safe.
Link: https://tracker.ceph.com/issues/64035
Fixes: 5b1188847180 ("fscrypt: support crypto data unit size less than filesystem block size")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/inode.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0c25d326afc4..7b2e77517f23 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -78,6 +78,8 @@ struct inode *ceph_new_inode(struct inode *dir, struct dentry *dentry,
if (!inode)
return ERR_PTR(-ENOMEM);
+ inode->i_blkbits = CEPH_FSCRYPT_BLOCK_SHIFT;
+
if (!S_ISLNK(*mode)) {
err = ceph_pre_init_acls(dir, mode, as_ctx);
if (err < 0)
From cda4672da1c26835dcbd7aec2bfed954eda9b5ef Mon Sep 17 00:00:00 2001
From: Rishabh Dave <ridave@redhat.com>
Date: Thu, 1 Feb 2024 17:07:16 +0530
Subject: [PATCH 275/637] ceph: prevent use-after-free in encode_cap_msg()
In fs/ceph/caps.c, in encode_cap_msg(), "use after free" error was
caught by KASAN at this line - 'ceph_buffer_get(arg->xattr_buf);'. This
implies before the refcount could be increment here, it was freed.
In same file, in "handle_cap_grant()" refcount is decremented by this
line - 'ceph_buffer_put(ci->i_xattrs.blob);'. It appears that a race
occurred and resource was freed by the latter line before the former
line could increment it.
encode_cap_msg() is called by __send_cap() and __send_cap() is called by
ceph_check_caps() after calling __prep_cap(). __prep_cap() is where
arg->xattr_buf is assigned to ci->i_xattrs.blob. This is the spot where
the refcount must be increased to prevent "use after free" error.
Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/59259
Signed-off-by: Rishabh Dave <ridave@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 9c02f328c966..e8bf082105d8 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1452,7 +1452,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap,
if (flushing & CEPH_CAP_XATTR_EXCL) {
arg->old_xattr_buf = __ceph_build_xattrs_blob(ci);
arg->xattr_version = ci->i_xattrs.version;
- arg->xattr_buf = ci->i_xattrs.blob;
+ arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob);
} else {
arg->xattr_buf = NULL;
arg->old_xattr_buf = NULL;
@@ -1553,6 +1553,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci)
encode_cap_msg(msg, arg);
ceph_con_send(&arg->session->s_con, msg);
ceph_buffer_put(arg->old_xattr_buf);
+ ceph_buffer_put(arg->xattr_buf);
if (arg->wake)
wake_up_all(&ci->i_cap_wq);
}
From 07045648c07c5632e0dfd5ce084d3cd0cec0258a Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 4 Jan 2024 09:21:30 +0800
Subject: [PATCH 276/637] ceph: always check dir caps asynchronously
The MDS will issue the 'Fr' caps for async dirop, while there is
buggy in kclient and it could miss releasing the async dirop caps,
which is 'Fsxr'. And then the MDS will complain with:
"[WRN] client.xxx isn't responding to mclientcaps(revoke) ..."
So when releasing the dirop async requests or when they fail we
should always make sure that being revoked caps could be released.
Link: https://tracker.ceph.com/issues/50223
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 6 ------
fs/ceph/mds_client.c | 9 ++++-----
fs/ceph/mds_client.h | 2 +-
fs/ceph/super.h | 2 --
4 files changed, 5 insertions(+), 14 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index e8bf082105d8..ad1f46c66fbf 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3216,7 +3216,6 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci,
enum put_cap_refs_mode {
PUT_CAP_REFS_SYNC = 0,
- PUT_CAP_REFS_NO_CHECK,
PUT_CAP_REFS_ASYNC,
};
@@ -3332,11 +3331,6 @@ void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had)
__ceph_put_cap_refs(ci, had, PUT_CAP_REFS_ASYNC);
}
-void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci, int had)
-{
- __ceph_put_cap_refs(ci, had, PUT_CAP_REFS_NO_CHECK);
-}
-
/*
* Release @nr WRBUFFER refs on dirty pages for the given @snapc snap
* context. Adjust per-snap dirty page accounting as appropriate.
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 548d1de379f3..f71bb9c9569f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1089,7 +1089,7 @@ void ceph_mdsc_release_request(struct kref *kref)
struct ceph_mds_request *req = container_of(kref,
struct ceph_mds_request,
r_kref);
- ceph_mdsc_release_dir_caps_no_check(req);
+ ceph_mdsc_release_dir_caps_async(req);
destroy_reply_info(&req->r_reply_info);
if (req->r_request)
ceph_msg_put(req->r_request);
@@ -4261,7 +4261,7 @@ void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req)
}
}
-void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
+void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req)
{
struct ceph_client *cl = req->r_mdsc->fsc->client;
int dcaps;
@@ -4269,8 +4269,7 @@ void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req)
dcaps = xchg(&req->r_dir_caps, 0);
if (dcaps) {
doutc(cl, "releasing r_dir_caps=%s\n", ceph_cap_string(dcaps));
- ceph_put_cap_refs_no_check_caps(ceph_inode(req->r_parent),
- dcaps);
+ ceph_put_cap_refs_async(ceph_inode(req->r_parent), dcaps);
}
}
@@ -4306,7 +4305,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
if (req->r_session->s_mds != session->s_mds)
continue;
- ceph_mdsc_release_dir_caps_no_check(req);
+ ceph_mdsc_release_dir_caps_async(req);
__send_request(session, req, true);
}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 2e6ddaa13d72..40560af38827 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -552,7 +552,7 @@ extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
struct inode *dir,
struct ceph_mds_request *req);
extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req);
-extern void ceph_mdsc_release_dir_caps_no_check(struct ceph_mds_request *req);
+extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req);
static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
{
kref_get(&req->r_kref);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b06e2bc86221..b63b4cd9b5b6 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1255,8 +1255,6 @@ extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps,
extern void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps);
extern void ceph_put_cap_refs(struct ceph_inode_info *ci, int had);
extern void ceph_put_cap_refs_async(struct ceph_inode_info *ci, int had);
-extern void ceph_put_cap_refs_no_check_caps(struct ceph_inode_info *ci,
- int had);
extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
struct ceph_snap_context *snapc);
extern void __ceph_remove_capsnap(struct inode *inode,
From 44d3b8a19b91cd2af11f918b2fd05628383172de Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?=
<amadeuszx.slawinski@linux.intel.com>
Date: Wed, 7 Feb 2024 12:26:24 +0100
Subject: [PATCH 277/637] ASoC: Intel: avs: Fix dynamic port assignment when
TDM is set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
In case TDM is set in topology on SSP0, parser will overwrite vindex
value, because it only checks if port is set. Fix this by checking whole
field value.
Fixes: e6d50e474e45 ("ASoC: Intel: avs: Improve topology parsing of dynamic strings")
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://lore.kernel.org/r/20240207112624.2132821-1-amadeuszx.slawinski@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/avs/topology.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c
index 778236d3fd28..48b3c67c9103 100644
--- a/sound/soc/intel/avs/topology.c
+++ b/sound/soc/intel/avs/topology.c
@@ -857,7 +857,7 @@ assign_copier_gtw_instance(struct snd_soc_component *comp, struct avs_tplg_modcf
}
/* If topology sets value don't overwrite it */
- if (cfg->copier.vindex.i2s.instance)
+ if (cfg->copier.vindex.val)
return;
mach = dev_get_platdata(comp->card->dev);
From 5001bfe927b594470f3a2484cb410b8b42a47903 Mon Sep 17 00:00:00 2001
From: Allison Henderson <allison.henderson@oracle.com>
Date: Mon, 5 Feb 2024 12:03:43 -0700
Subject: [PATCH 278/637] MAINTAINERS: Maintainer change for rds
At this point, Santosh has moved onto other things and I am happy
to take over the role of rds maintainer. Update the MAINTAINERS
accordingly.
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://lore.kernel.org/r/20240205190343.112436-1-allison.henderson@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 722b894f305e..e3e670ee5610 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18433,7 +18433,7 @@ S: Supported
F: drivers/infiniband/sw/rdmavt
RDS - RELIABLE DATAGRAM SOCKETS
-M: Santosh Shilimkar <santosh.shilimkar@oracle.com>
+M: Allison Henderson <allison.henderson@oracle.com>
L: netdev@vger.kernel.org
L: linux-rdma@vger.kernel.org
L: rds-devel@oss.oracle.com (moderated for non-subscribers)
From 75428f537d7cae33c7e4dd726144074f78622c09 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Mon, 5 Feb 2024 18:29:06 -0800
Subject: [PATCH 279/637] net: intel: fix old compiler regressions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The kernel build regressions/improvements email contained a couple of
issues with old compilers (in fact all the reports were on different
architectures, but all gcc 5.5) and the FIELD_PREP() and FIELD_GET()
conversions. They're all because an integer #define that should have
been declared as unsigned, was shifted to the point that it could set
the sign bit.
The fix just involves making sure the defines use the "U" identifier on
the constants to make sure they're unsigned. Should make the checkers
happier.
Confirmed with objdump before/after that there is no change to the
binaries.
Issues were reported as follows:
./drivers/net/ethernet/intel/ice/ice_base.c:238:7: note: in expansion of macro 'FIELD_GET'
(FIELD_GET(GLINT_CTL_ITR_GRAN_25_M, regval) == ICE_ITR_GRAN_US))
^
./include/linux/compiler_types.h:435:38: error: call to '__compiletime_assert_1093' declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/ice/ice_nvm.c:709:16: note: in expansion of macro ‘FIELD_GET’
orom->major = FIELD_GET(ICE_OROM_VER_MASK, combo_ver);
^
./include/linux/compiler_types.h:435:38: error: call to ‘__compiletime_assert_796’ declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/ice/ice_common.c:945:18: note: in expansion of macro ‘FIELD_GET’
u8 max_agg_bw = FIELD_GET(GL_PWR_MODE_CTL_CAR_MAX_BW_M,
^
./include/linux/compiler_types.h:435:38: error: call to ‘__compiletime_assert_420’ declared with attribute error: FIELD_GET: mask is not constant
drivers/net/ethernet/intel/i40e/i40e_dcb.c:458:8: note: in expansion of macro ‘FIELD_GET’
oui = FIELD_GET(I40E_LLDP_TLV_OUI_MASK, ouisubtype);
^
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/lkml/d03e90ca-8485-4d1b-5ec1-c3398e0e8da@linux-m68k.org/ #i40e #ice
Fixes: 62589808d73b ("i40e: field get conversion")
Fixes: 5a259f8e0baf ("ice: field get conversion")
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/20240206022906.2194214-1-jesse.brandeburg@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/intel/i40e/i40e_dcb.h | 2 +-
drivers/net/ethernet/intel/ice/ice_osdep.h | 2 +-
drivers/net/ethernet/intel/ice/ice_type.h | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 6b60dc9b7736..d76497566e40 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -43,7 +43,7 @@
#define I40E_LLDP_TLV_SUBTYPE_SHIFT 0
#define I40E_LLDP_TLV_SUBTYPE_MASK (0xFF << I40E_LLDP_TLV_SUBTYPE_SHIFT)
#define I40E_LLDP_TLV_OUI_SHIFT 8
-#define I40E_LLDP_TLV_OUI_MASK (0xFFFFFF << I40E_LLDP_TLV_OUI_SHIFT)
+#define I40E_LLDP_TLV_OUI_MASK (0xFFFFFFU << I40E_LLDP_TLV_OUI_SHIFT)
/* Defines for IEEE ETS TLV */
#define I40E_IEEE_ETS_MAXTC_SHIFT 0
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index 82bc54fec7f3..a2562f04267f 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -24,7 +24,7 @@
#define rd64(a, reg) readq((a)->hw_addr + (reg))
#define ice_flush(a) rd32((a), GLGEN_STAT)
-#define ICE_M(m, s) ((m) << (s))
+#define ICE_M(m, s) ((m ## U) << (s))
struct ice_dma_mem {
void *va;
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 41ab6d7bbd9e..a508e917ce5f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -1072,7 +1072,7 @@ struct ice_aq_get_set_rss_lut_params {
#define ICE_OROM_VER_BUILD_SHIFT 8
#define ICE_OROM_VER_BUILD_MASK (0xffff << ICE_OROM_VER_BUILD_SHIFT)
#define ICE_OROM_VER_SHIFT 24
-#define ICE_OROM_VER_MASK (0xff << ICE_OROM_VER_SHIFT)
+#define ICE_OROM_VER_MASK (0xffU << ICE_OROM_VER_SHIFT)
#define ICE_SR_PFA_PTR 0x40
#define ICE_SR_1ST_NVM_BANK_PTR 0x42
#define ICE_SR_NVM_BANK_SIZE 0x43
From ce68c035457bdd025a9961e0ba2157323090c581 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 30 Jan 2024 13:01:14 +0100
Subject: [PATCH 280/637] riscv: Fix arch_hugetlb_migration_supported() for
NAPOT
arch_hugetlb_migration_supported() must be reimplemented to add support
for NAPOT hugepages, which is done here.
Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240130120114.106003-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/hugetlb.h | 3 +++
arch/riscv/mm/hugetlbpage.c | 16 +++++++++++++---
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 4c5b0e929890..20f9c3ba2341 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -11,6 +11,9 @@ static inline void arch_clear_hugepage_flags(struct page *page)
}
#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+bool arch_hugetlb_migration_supported(struct hstate *h);
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+
#ifdef CONFIG_RISCV_ISA_SVNAPOT
#define __HAVE_ARCH_HUGE_PTE_CLEAR
void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 87406b26c3da..29c7606414d2 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -364,7 +364,7 @@ void huge_pte_clear(struct mm_struct *mm,
pte_clear(mm, addr, ptep);
}
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
{
unsigned long order;
@@ -392,7 +392,7 @@ arch_initcall(napot_hugetlbpages_init);
#else
-static __init bool is_napot_size(unsigned long size)
+static bool is_napot_size(unsigned long size)
{
return false;
}
@@ -409,7 +409,7 @@ int pmd_huge(pmd_t pmd)
return pmd_leaf(pmd);
}
-bool __init arch_hugetlb_valid_size(unsigned long size)
+static bool __hugetlb_valid_size(unsigned long size)
{
if (size == HPAGE_SIZE)
return true;
@@ -421,6 +421,16 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
return false;
}
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+ return __hugetlb_valid_size(size);
+}
+
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+ return __hugetlb_valid_size(huge_page_size(h));
+}
+
#ifdef CONFIG_CONTIG_ALLOC
static __init int gigantic_pages_init(void)
{
From 2cf963787529f615f7c93bdcf13a5e82029e7f38 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Thu, 23 Nov 2023 13:42:14 +0000
Subject: [PATCH 281/637] riscv: declare overflow_stack as exported from
traps.c
The percpu area overflow_stacks is exported from arch/riscv/kernel/traps.c
for use in the entry code, but is not declared anywhere. Add the relevant
declaration to arch/riscv/include/asm/stacktrace.h to silence the following
sparse warning:
arch/riscv/kernel/traps.c:395:1: warning: symbol '__pcpu_scope_overflow_stack' was not declared. Should it be static?
We don't add the stackinfo_get_overflow() call as for some of the other
architectures as this doesn't seem to be used yet, so just silence the
warning.
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Fixes: be97d0db5f44 ("riscv: VMAP_STACK overflow detection thread-safe")
Link: https://lore.kernel.org/r/20231123134214.81481-1-ben.dooks@codethink.co.uk
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/stacktrace.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index f7e8ef2418b9..b1495a7e06ce 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -21,4 +21,9 @@ static inline bool on_thread_stack(void)
return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
}
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+#endif /* CONFIG_VMAP_STACK */
+
#endif /* _ASM_RISCV_STACKTRACE_H */
From 3951f6add519a8e954bf78691a412f65b24f4715 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 30 Jan 2024 12:55:08 +0100
Subject: [PATCH 282/637] riscv: Fix arch_tlbbatch_flush() by clearing the
batch cpumask
We must clear the cpumask once we have flushed the batch, otherwise cpus
get accumulated and we end sending IPIs to more cpus than needed.
Fixes: 54d7431af73e ("riscv: Add support for BATCHED_UNMAP_TLB_FLUSH")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20240130115508.105386-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/mm/tlbflush.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index dffb0e5bd942..893566e004b7 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -234,4 +234,5 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+ cpumask_clear(&batch->cpumask);
}
From 1f4137e882c621f8ed4bd4da9b10cf91d059e52a Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 6 Feb 2024 09:47:21 -0800
Subject: [PATCH 283/637] nvme: move passthrough logging attribute to head
The namespace does not have attributes, but the head does. Move the new
logging attribute to that structure instead of dereferencing the wrong
type.
And while we're here, fix the reverse-tree coding style.
Fixes: 9f079dda14339e ("nvme: allow passthru cmd error logging")
Reported-by: Tasmiya Nalatwad <tasmiya@linux.vnet.ibm.com>
Tested-by: Tasmiya Nalatwad <tasmiya@linux.vnet.ibm.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/core.c | 3 +--
drivers/nvme/host/nvme.h | 2 +-
drivers/nvme/host/sysfs.c | 30 +++++++++++++++---------------
3 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 975245527c1f..246e92c05aac 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -713,7 +713,7 @@ void nvme_init_request(struct request *req, struct nvme_command *cmd)
if (req->q->queuedata) {
struct nvme_ns *ns = req->q->disk->private_data;
- logging_enabled = ns->passthru_err_log_enabled;
+ logging_enabled = ns->head->passthru_err_log_enabled;
req->timeout = NVME_IO_TIMEOUT;
} else { /* no queuedata implies admin queue */
logging_enabled = nr->ctrl->passthru_err_log_enabled;
@@ -3696,7 +3696,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
ns->disk = disk;
ns->queue = disk->queue;
- ns->passthru_err_log_enabled = false;
if (ctrl->opts && ctrl->opts->data_digest)
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 3897334e3950..7b87763e2f8a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -455,6 +455,7 @@ struct nvme_ns_head {
struct list_head entry;
struct kref ref;
bool shared;
+ bool passthru_err_log_enabled;
int instance;
struct nvme_effects_log *effects;
u64 nuse;
@@ -523,7 +524,6 @@ struct nvme_ns {
struct device cdev_device;
struct nvme_fault_inject fault_inject;
- bool passthru_err_log_enabled;
};
/* NVMe ns supports metadata actions by the controller (generate/strip) */
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index d099218e494a..f2832f70e7e0 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -48,8 +48,8 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
- int err;
bool passthru_err_log_enabled;
+ int err;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
@@ -60,25 +60,34 @@ static ssize_t nvme_adm_passthru_err_log_enabled_store(struct device *dev,
return count;
}
+static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (nvme_disk_is_ns_head(disk))
+ return disk->private_data;
+ return nvme_get_ns_from_dev(dev)->head;
+}
+
static ssize_t nvme_io_passthru_err_log_enabled_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct nvme_ns *n = dev_get_drvdata(dev);
+ struct nvme_ns_head *head = dev_to_ns_head(dev);
- return sysfs_emit(buf, n->passthru_err_log_enabled ? "on\n" : "off\n");
+ return sysfs_emit(buf, head->passthru_err_log_enabled ? "on\n" : "off\n");
}
static ssize_t nvme_io_passthru_err_log_enabled_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
- struct nvme_ns *ns = dev_get_drvdata(dev);
- int err;
+ struct nvme_ns_head *head = dev_to_ns_head(dev);
bool passthru_err_log_enabled;
+ int err;
err = kstrtobool(buf, &passthru_err_log_enabled);
if (err)
return -EINVAL;
- ns->passthru_err_log_enabled = passthru_err_log_enabled;
+ head->passthru_err_log_enabled = passthru_err_log_enabled;
return count;
}
@@ -91,15 +100,6 @@ static struct device_attribute dev_attr_io_passthru_err_log_enabled = \
__ATTR(passthru_err_log_enabled, S_IRUGO | S_IWUSR, \
nvme_io_passthru_err_log_enabled_show, nvme_io_passthru_err_log_enabled_store);
-static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev)
-{
- struct gendisk *disk = dev_to_disk(dev);
-
- if (nvme_disk_is_ns_head(disk))
- return disk->private_data;
- return nvme_get_ns_from_dev(dev)->head;
-}
-
static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
From e8c263ed6de8183e670fbd127c2512292a2ad8eb Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Mon, 5 Feb 2024 16:30:21 -0800
Subject: [PATCH 284/637] nvme-core: fix comment to reflect right functions
The functions and the attribute listed in the comment doesn't exists in
the code, (ns->logging_enabled, nvme_passthru_err_log_enabled_store()
and nvme_passthru_err_log_enabled_show())
Update the comment with right function names and a comment
ns->head->passthru_err_log_enabled,
nvme_io_passthru_err_log_enabled_store() and
nvme_io_passthru_err_log_enabled_show().
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Alan Adamson <alan.adamson@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 246e92c05aac..60537c9224bf 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3761,8 +3761,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
/*
* Set ns->disk->device->driver_data to ns so we can access
- * ns->logging_enabled in nvme_passthru_err_log_enabled_store() and
- * nvme_passthru_err_log_enabled_show().
+ * ns->head->passthru_err_log_enabled in
+ * nvme_io_passthru_err_log_enabled_[store | show]().
*/
dev_set_drvdata(disk_to_dev(ns->disk), ns);
From b5d1b4b46f856da1473c7ba9a5cdfcb55c9b2478 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:40:37 +0300
Subject: [PATCH 285/637] PCI: dwc: Fix a 64bit bug in
dw_pcie_ep_raise_msix_irq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The "msg_addr" variable is u64. However, the "aligned_offset" is an
unsigned int. This means that when the code does:
msg_addr &= ~aligned_offset;
it will unintentionally zero out the high 32 bits. Use ALIGN_DOWN() to do
the alignment instead.
Fixes: 2217fffcd63f ("PCI: dwc: endpoint: Fix dw_pcie_ep_raise_msix_irq() alignment support")
Link: https://lore.kernel.org/r/af59c7ad-ab93-40f7-ad4a-7ac0b14d37f5@moroto.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@vger.kernel.org>
---
drivers/pci/controller/dwc/pcie-designware-ep.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 5befed2dc02b..d6b66597101e 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -6,6 +6,7 @@
* Author: Kishon Vijay Abraham I <kishon@ti.com>
*/
+#include <linux/align.h>
#include <linux/bitfield.h>
#include <linux/of.h>
#include <linux/platform_device.h>
@@ -551,7 +552,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
}
aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
- msg_addr &= ~aligned_offset;
+ msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
epc->mem->window.page_size);
if (ret)
From 67057f48df79a3d73683385f521215146861684b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 26 Jan 2024 11:41:01 +0300
Subject: [PATCH 286/637] PCI: dwc: Clean up dw_pcie_ep_raise_msi_irq()
alignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
I recently changed the alignment code in dw_pcie_ep_raise_msix_irq(). The
code in dw_pcie_ep_raise_msi_irq() is similar, so update it to match, just
for consistency. (No effect on runtime, just a cleanup).
Link: https://lore.kernel.org/r/184097e0-c728-42c7-9e8a-556bd33fb612@moroto.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
drivers/pci/controller/dwc/pcie-designware-ep.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index d6b66597101e..9a437cfce073 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -483,9 +483,10 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
reg = ep_func->msi_cap + PCI_MSI_DATA_32;
msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg);
}
- aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1);
- msg_addr = ((u64)msg_addr_upper) << 32 |
- (msg_addr_lower & ~aligned_offset);
+ msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower;
+
+ aligned_offset = msg_addr & (epc->mem->window.page_size - 1);
+ msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size);
ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr,
epc->mem->window.page_size);
if (ret)
From 46f5ab762d048dad224436978315cbc2fa79c630 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 6 Feb 2024 11:22:09 +0100
Subject: [PATCH 287/637] fs: relax mount_setattr() permission checks
When we added mount_setattr() I added additional checks compared to the
legacy do_reconfigure_mnt() and do_change_type() helpers used by regular
mount(2). If that mount had a parent then verify that the caller and the
mount namespace the mount is attached to match and if not make sure that
it's an anonymous mount.
The real rootfs falls into neither category. It is neither an anoymous
mount because it is obviously attached to the initial mount namespace
but it also obviously doesn't have a parent mount. So that means legacy
mount(2) allows changing mount properties on the real rootfs but
mount_setattr(2) blocks this. I never thought much about this but of
course someone on this planet of earth changes properties on the real
rootfs as can be seen in [1].
Since util-linux finally switched to the new mount api in 2.39 not so
long ago it also relies on mount_setattr() and that surfaced this issue
when Fedora 39 finally switched to it. Fix this.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2256843
Link: https://lore.kernel.org/r/20240206-vfs-mount-rootfs-v1-1-19b335eee133@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Karel Zak <kzak@redhat.com>
Cc: stable@vger.kernel.org # v5.12+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
fs/namespace.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/namespace.c b/fs/namespace.c
index 437f60e96d40..5a51315c6678 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4472,10 +4472,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
/*
* If this is an attached mount make sure it's located in the callers
* mount namespace. If it's not don't let the caller interact with it.
- * If this is a detached mount make sure it has an anonymous mount
- * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE.
+ *
+ * If this mount doesn't have a parent it's most often simply a
+ * detached mount with an anonymous mount namespace. IOW, something
+ * that's simply not attached yet. But there are apparently also users
+ * that do change mount properties on the rootfs itself. That obviously
+ * neither has a parent nor is it a detached mount so we cannot
+ * unconditionally check for detached mounts.
*/
- if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns)))
+ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
goto out;
/*
From 36fa8d697132b4bed2312d700310e8a78b000c84 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 1 Feb 2024 22:58:36 +0100
Subject: [PATCH 288/637] netfilter: nft_compat: narrow down revision to
unsigned 8-bits
xt_find_revision() expects u8, restrict it to this datatype.
Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_compat.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index f0eeda97bfcd..001b6841a4b6 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -135,7 +135,7 @@ static void nft_target_eval_bridge(const struct nft_expr *expr,
static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
[NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING },
- [NFTA_TARGET_REV] = { .type = NLA_U32 },
+ [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_TARGET_INFO] = { .type = NLA_BINARY },
};
@@ -419,7 +419,7 @@ static void nft_match_eval(const struct nft_expr *expr,
static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
[NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING },
- [NFTA_MATCH_REV] = { .type = NLA_U32 },
+ [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_MATCH_INFO] = { .type = NLA_BINARY },
};
@@ -724,7 +724,7 @@ out_put:
static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = {
[NFTA_COMPAT_NAME] = { .type = NLA_NUL_STRING,
.len = NFT_COMPAT_NAME_MAX-1 },
- [NFTA_COMPAT_REV] = { .type = NLA_U32 },
+ [NFTA_COMPAT_REV] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_COMPAT_TYPE] = { .type = NLA_U32 },
};
From 292781c3c5485ce33bd22b2ef1b2bed709b4d672 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 1 Feb 2024 23:33:29 +0100
Subject: [PATCH 289/637] netfilter: nft_compat: reject unused compat flag
Flag (1 << 0) is ignored is set, never used, reject it it with EINVAL
instead.
Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/uapi/linux/netfilter/nf_tables.h | 2 ++
net/netfilter/nft_compat.c | 3 ++-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ca30232b7bc8..117c6a9b845b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -285,9 +285,11 @@ enum nft_rule_attributes {
/**
* enum nft_rule_compat_flags - nf_tables rule compat flags
*
+ * @NFT_RULE_COMPAT_F_UNUSED: unused
* @NFT_RULE_COMPAT_F_INV: invert the check result
*/
enum nft_rule_compat_flags {
+ NFT_RULE_COMPAT_F_UNUSED = (1 << 0),
NFT_RULE_COMPAT_F_INV = (1 << 1),
NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV,
};
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 001b6841a4b6..ed71d5ecbe0a 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -212,7 +212,8 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
return -EINVAL;
flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS]));
- if (flags & ~NFT_RULE_COMPAT_F_MASK)
+ if (flags & NFT_RULE_COMPAT_F_UNUSED ||
+ flags & ~NFT_RULE_COMPAT_F_MASK)
return -EINVAL;
if (flags & NFT_RULE_COMPAT_F_INV)
*inv = true;
From d694b754894c93fb4d71a7f3699439dec111decc Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 2 Feb 2024 00:05:23 +0100
Subject: [PATCH 290/637] netfilter: nft_compat: restrict match/target protocol
to u16
xt_check_{match,target} expects u16, but NFTA_RULE_COMPAT_PROTO is u32.
NLA_POLICY_MAX(NLA_BE32, 65535) cannot be used because .max in
nla_policy is s16, see 3e48be05f3c7 ("netlink: add attribute range
validation to policy").
Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_compat.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index ed71d5ecbe0a..1f9474fefe84 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -200,6 +200,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1]
static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
{
struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
+ u32 l4proto;
u32 flags;
int err;
@@ -218,7 +219,12 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
if (flags & NFT_RULE_COMPAT_F_INV)
*inv = true;
- *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+ l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+ if (l4proto > U16_MAX)
+ return -EINVAL;
+
+ *proto = l4proto;
+
return 0;
}
From e96fddb32931d007db12b1fce9b5e8e4c080401b Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sat, 27 Jan 2024 18:34:01 +0530
Subject: [PATCH 291/637] drm/amd/display: Fix 'panel_cntl' could be null in
'dcn21_set_backlight_level()'
'panel_cntl' structure used to control the display panel could be null,
dereferencing it could lead to a null pointer access.
Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/hwss/dcn21/dcn21_hwseq.c:269 dcn21_set_backlight_level() error: we previously assumed 'panel_cntl' could be null (see line 250)
Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.")
Cc: Yongqiang Sun <yongqiang.sun@amd.com>
Cc: Anthony Koo <Anthony.Koo@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 39 ++++++++++---------
1 file changed, 20 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 8e88dcaf88f5..a9cd39f77360 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -237,34 +237,35 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
{
struct dc_context *dc = pipe_ctx->stream->ctx;
struct abm *abm = pipe_ctx->stream_res.abm;
+ struct timing_generator *tg = pipe_ctx->stream_res.tg;
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
+ uint32_t otg_inst;
+
+ if (!abm && !tg && !panel_cntl)
+ return false;
+
+ otg_inst = tg->inst;
if (dc->dc->res_pool->dmcu) {
dce110_set_backlight_level(pipe_ctx, backlight_pwm_u16_16, frame_ramp);
return true;
}
- if (abm != NULL) {
- uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
-
- if (abm && panel_cntl) {
- if (abm->funcs && abm->funcs->set_pipe_ex) {
- abm->funcs->set_pipe_ex(abm,
- otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- } else {
- dmub_abm_set_pipe(abm,
- otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- }
- }
+ if (abm->funcs && abm->funcs->set_pipe_ex) {
+ abm->funcs->set_pipe_ex(abm,
+ otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
+ } else {
+ dmub_abm_set_pipe(abm,
+ otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
}
- if (abm && abm->funcs && abm->funcs->set_backlight_level_pwm)
+ if (abm->funcs && abm->funcs->set_backlight_level_pwm)
abm->funcs->set_backlight_level_pwm(abm, backlight_pwm_u16_16,
frame_ramp, 0, panel_cntl->inst);
else
From 66951d98d9bf45ba25acf37fe0747253fafdf298 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 31 Jan 2024 08:49:41 +0530
Subject: [PATCH 292/637] drm/amd/display: Add NULL test for 'timing generator'
in 'dcn21_set_pipe()'
In "u32 otg_inst = pipe_ctx->stream_res.tg->inst;"
pipe_ctx->stream_res.tg could be NULL, it is relying on the caller to
ensure the tg is not NULL.
Fixes: 474ac4a875ca ("drm/amd/display: Implement some asic specific abm call backs.")
Cc: Yongqiang Sun <yongqiang.sun@amd.com>
Cc: Anthony Koo <Anthony.Koo@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 24 +++++++++++--------
1 file changed, 14 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index a9cd39f77360..5c7f380a84f9 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -206,28 +206,32 @@ void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx)
void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
{
struct abm *abm = pipe_ctx->stream_res.abm;
- uint32_t otg_inst = pipe_ctx->stream_res.tg->inst;
+ struct timing_generator *tg = pipe_ctx->stream_res.tg;
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
+ uint32_t otg_inst;
+
+ if (!abm && !tg && !panel_cntl)
+ return;
+
+ otg_inst = tg->inst;
if (dmcu) {
dce110_set_pipe(pipe_ctx);
return;
}
- if (abm && panel_cntl) {
- if (abm->funcs && abm->funcs->set_pipe_ex) {
- abm->funcs->set_pipe_ex(abm,
+ if (abm->funcs && abm->funcs->set_pipe_ex) {
+ abm->funcs->set_pipe_ex(abm,
otg_inst,
SET_ABM_PIPE_NORMAL,
panel_cntl->inst,
panel_cntl->pwrseq_inst);
- } else {
- dmub_abm_set_pipe(abm, otg_inst,
- SET_ABM_PIPE_NORMAL,
- panel_cntl->inst,
- panel_cntl->pwrseq_inst);
- }
+ } else {
+ dmub_abm_set_pipe(abm, otg_inst,
+ SET_ABM_PIPE_NORMAL,
+ panel_cntl->inst,
+ panel_cntl->pwrseq_inst);
}
}
From 2103370afba74dda39ff5d2d69163c86644ce528 Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Thu, 18 Jan 2024 18:12:15 -0500
Subject: [PATCH 293/637] drm/amd/display: set odm_combine_policy based on
context in dcn32 resource
[why]
When populating dml pipes, odm combine policy should be assigned based
on the pipe topology of the context passed in. DML pipes could be
repopulated multiple times during single validate bandwidth attempt. We
need to make sure that whenever we repopulate the dml pipes it is always
aligned with the updated context. There is a case where DML pipes get
repopulated during FPO optimization after ODM combine policy is changed.
Since in the current code we reinitlaize ODM combine policy, even though
the current context has ODM combine enabled, we overwrite it despite the
pipes are already split. This causes DML to think that MPC combine is
used so we mistakenly enable MPC combine because we apply pipe split
with ODM combine policy reset. This issue doesn't impact non windowed
MPO with ODM case because the legacy policy has restricted use cases. We
don't encounter the case where both ODM and FPO optimizations are
enabled together. So we decide to leave it as is because it is about to
be replaced anyway.
Cc: stable@vger.kernel.org # 6.6+
Reviewed-by: Chaitanya Dhere <chaitanya.dhere@amd.com>
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 15 ++++++++++----
drivers/gpu/drm/amd/display/dc/inc/resource.h | 20 ++++++++-----------
.../dc/resource/dcn32/dcn32_resource.c | 16 ++++++++++++++-
3 files changed, 34 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index dd781a20692e..ba76dd4a2ce2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1288,7 +1288,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex
return updated;
}
-static bool should_allow_odm_power_optimization(struct dc *dc,
+static bool should_apply_odm_power_optimization(struct dc *dc,
struct dc_state *context, struct vba_vars_st *v, int *split,
bool *merge)
{
@@ -1392,9 +1392,12 @@ static void try_odm_power_optimization_and_revalidate(
{
int i;
unsigned int new_vlevel;
+ unsigned int cur_policy[MAX_PIPES];
- for (i = 0; i < pipe_cnt; i++)
+ for (i = 0; i < pipe_cnt; i++) {
+ cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy;
pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+ }
new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
@@ -1403,6 +1406,9 @@ static void try_odm_power_optimization_and_revalidate(
memset(merge, 0, MAX_PIPES * sizeof(bool));
*vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge);
context->bw_ctx.dml.vba.VoltageLevel = *vlevel;
+ } else {
+ for (i = 0; i < pipe_cnt; i++)
+ pipes[i].pipe.dest.odm_combine_policy = cur_policy[i];
}
}
@@ -1580,7 +1586,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc,
}
}
- if (should_allow_odm_power_optimization(dc, context, vba, split, merge))
+ if (should_apply_odm_power_optimization(dc, context, vba, split, merge))
try_odm_power_optimization_and_revalidate(
dc, context, pipes, split, merge, vlevel, *pipe_cnt);
@@ -2209,7 +2215,8 @@ bool dcn32_internal_validate_bw(struct dc *dc,
int i;
pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate);
- dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
+ if (!dc->config.enable_windowed_mpo_odm)
+ dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes);
/* repopulate_pipes = 1 means the pipes were either split or merged. In this case
* we have to re-calculate the DET allocation and run through DML once more to
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index c958ef37b78a..77a60aa9f27b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe);
int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe);
/*
- * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice
- * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for a plane with MPCC combine. otherwise
- * the number of MPC "cuts" for the plane.
+ * Get the number of MPC slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an MPC combine
+ * pipe topology.
*/
-int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head);
+int resource_get_mpc_slice_count(const struct pipe_ctx *pipe);
/*
- * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice
- * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it
- * will have 4 pieces of slice.
- * return - 0 if pipe is not used for ODM combine. otherwise
- * the number of ODM "cuts" for the timing.
+ * Get the number of ODM slices associated with the pipe.
+ * The function returns 0 if the pipe is not associated with an ODM combine
+ * pipe topology.
*/
-int resource_get_odm_slice_count(const struct pipe_ctx *otg_master);
+int resource_get_odm_slice_count(const struct pipe_ctx *pipe);
/* Get the ODM slice index counting from 0 from left most slice */
int resource_get_odm_slice_index(const struct pipe_ctx *opp_head);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c4d71e7f18af..6f10052caeef 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context(
dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
DC_FP_END();
pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
- pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ if (dc->config.enable_windowed_mpo_odm &&
+ dc->debug.enable_single_display_2to1_odm_policy) {
+ switch (resource_get_odm_slice_count(pipe)) {
+ case 2:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1;
+ break;
+ case 4:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1;
+ break;
+ default:
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ }
+ } else {
+ pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal;
+ }
pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet
pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19;
From 93bafa32a6918154aa0caf9f66679a32c2431357 Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Tue, 16 Jan 2024 19:10:45 +0800
Subject: [PATCH 294/637] drm/amdgpu: skip to program GFXDEC registers for
suspend abort
In the suspend abort cases, the gfx power rail doesn't turn off so
some GFXDEC registers/CSB can't reset to default value and at this
moment reinitialize GFXDEC/CSB will result in an unexpected error.
So let skip those program sequence for the suspend abort case.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 ++
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 8 ++++++++
3 files changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 3d8a48f46b01..6dce81a061ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1078,6 +1078,8 @@ struct amdgpu_device {
bool in_s3;
bool in_s4;
bool in_s0ix;
+ /* indicate amdgpu suspension status */
+ bool suspend_complete;
enum pp_mp1_state mp1_state;
struct amdgpu_doorbell_index doorbell_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 971acf01bea6..211501ea9169 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2476,6 +2476,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
struct drm_device *drm_dev = dev_get_drvdata(dev);
struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ adev->suspend_complete = false;
if (amdgpu_acpi_is_s0ix_active(adev))
adev->in_s0ix = true;
else if (amdgpu_acpi_is_s3_active(adev))
@@ -2490,6 +2491,7 @@ static int amdgpu_pmops_suspend_noirq(struct device *dev)
struct drm_device *drm_dev = dev_get_drvdata(dev);
struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ adev->suspend_complete = true;
if (amdgpu_acpi_should_gpu_reset(adev))
return amdgpu_asic_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 69c500910746..3bc6943365a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3034,6 +3034,14 @@ static int gfx_v9_0_cp_gfx_start(struct amdgpu_device *adev)
gfx_v9_0_cp_gfx_enable(adev, true);
+ /* Now only limit the quirk on the APU gfx9 series and already
+ * confirmed that the APU gfx10/gfx11 needn't such update.
+ */
+ if (adev->flags & AMD_IS_APU &&
+ adev->in_s3 && !adev->suspend_complete) {
+ DRM_INFO(" Will skip the CSB packet resubmit\n");
+ return 0;
+ }
r = amdgpu_ring_alloc(ring, gfx_v9_0_get_csb_size(adev) + 4 + 3);
if (r) {
DRM_ERROR("amdgpu: cp failed to lock ring (%d).\n", r);
From 6ef82ac664bb9568ca3956e0d9c9c478e25077ff Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Wed, 17 Jan 2024 13:39:37 +0800
Subject: [PATCH 295/637] drm/amdgpu: reset gpu for s3 suspend abort case
In the s3 suspend abort case some type of gfx9 power
rail not turn off from FCH side and this will put the
GPU in an unknown power status, so let's reset the gpu
to a known good power state before reinitialize gpu
device.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/soc15.c | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 15033efec2ba..c64c01e2944a 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1298,10 +1298,32 @@ static int soc15_common_suspend(void *handle)
return soc15_common_hw_fini(adev);
}
+static bool soc15_need_reset_on_resume(struct amdgpu_device *adev)
+{
+ u32 sol_reg;
+
+ sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+ /* Will reset for the following suspend abort cases.
+ * 1) Only reset limit on APU side, dGPU hasn't checked yet.
+ * 2) S3 suspend abort and TOS already launched.
+ */
+ if (adev->flags & AMD_IS_APU && adev->in_s3 &&
+ !adev->suspend_complete &&
+ sol_reg)
+ return true;
+
+ return false;
+}
+
static int soc15_common_resume(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ if (soc15_need_reset_on_resume(adev)) {
+ dev_info(adev->dev, "S3 suspend abort case, let's reset ASIC.\n");
+ soc15_asic_reset(adev);
+ }
return soc15_common_hw_init(adev);
}
From 897925dcc5dfff5b3b23ba991a89fe3ebaca6ef8 Mon Sep 17 00:00:00 2001
From: Li Ma <li.ma@amd.com>
Date: Thu, 1 Feb 2024 19:31:06 +0800
Subject: [PATCH 296/637] drm/amdgpu: remove asymmetrical irq disabling in jpeg
4.0.5 suspend
A supplement to commit: 615dd56ac5379f4239940be69139a33e79e59c67
There is an irq warning of jpeg during resume in s2idle process. No irq enabled in jpeg 4.0.5 resume.
Fixes: 615dd56ac537 ("drm/amdgpu: remove asymmetrical irq disabling in vcn 4.0.5 suspend")
Signed-off-by: Li Ma <li.ma@amd.com>
Acked-By: Saleemkhan Jamadar <saleemkhan.jamadar@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Veerabadhran Gopalakrishnan <Veerabadhran.Gopalakrishnan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c | 9 ---------
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c | 10 ----------
2 files changed, 19 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index bc38b90f8cf8..88ea58d5c4ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -674,14 +674,6 @@ static int jpeg_v4_0_set_powergating_state(void *handle,
return ret;
}
-static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev,
- struct amdgpu_irq_src *source,
- unsigned type,
- enum amdgpu_interrupt_state state)
-{
- return 0;
-}
-
static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
unsigned int type,
@@ -765,7 +757,6 @@ static void jpeg_v4_0_set_dec_ring_funcs(struct amdgpu_device *adev)
}
static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = {
- .set = jpeg_v4_0_set_interrupt_state,
.process = jpeg_v4_0_process_interrupt,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 6ede85b28cc8..78b74daf4eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -181,7 +181,6 @@ static int jpeg_v4_0_5_hw_fini(void *handle)
RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
jpeg_v4_0_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
}
- amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0);
return 0;
}
@@ -516,14 +515,6 @@ static int jpeg_v4_0_5_set_powergating_state(void *handle,
return ret;
}
-static int jpeg_v4_0_5_set_interrupt_state(struct amdgpu_device *adev,
- struct amdgpu_irq_src *source,
- unsigned type,
- enum amdgpu_interrupt_state state)
-{
- return 0;
-}
-
static int jpeg_v4_0_5_process_interrupt(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
@@ -603,7 +594,6 @@ static void jpeg_v4_0_5_set_dec_ring_funcs(struct amdgpu_device *adev)
}
static const struct amdgpu_irq_src_funcs jpeg_v4_0_5_irq_funcs = {
- .set = jpeg_v4_0_5_set_interrupt_state,
.process = jpeg_v4_0_5_process_interrupt,
};
From 280df4996c2bfc0e340ae758ab6da35748853a7e Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Tue, 23 Jan 2024 12:20:06 -0500
Subject: [PATCH 297/637] drm/amd/display: Increase eval/entry delay for DCN35
[Why]
To match firmware measurements and avoid hanging when accessing HW
that's in idle.
[How]
Increase the delays to what we've measured.
Reviewed-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 761ec9891875..2142cee6cac2 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,8 +780,8 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_z10 = false,
.ignore_pg = true,
.psp_disabled_wa = true,
- .ips2_eval_delay_us = 200,
- .ips2_entry_delay_us = 400,
+ .ips2_eval_delay_us = 1650,
+ .ips2_entry_delay_us = 800,
.static_screen_wait_frames = 2,
};
From 2dcf82a8e8dc930655787797ef8a3692b527c7a9 Mon Sep 17 00:00:00 2001
From: "Stanley.Yang" <Stanley.Yang@amd.com>
Date: Mon, 5 Feb 2024 15:55:48 +0800
Subject: [PATCH 298/637] drm/amdgpu: Fix shared buff copy to user
ta if invoke node buffer
|-------- ta type ----------|
|-------- ta id ----------|
|-------- cmd id ----------|
|------ shared buf len -----|
|------ shared buffer ------|
ta if invoke node buffer is as above, copy shared buffer data to correct location
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 468a67b302d4..ca5c86e5f7cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -362,7 +362,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
}
}
- if (copy_to_user((char *)buf, context->mem_context.shared_buf, shared_buf_len))
+ if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
ret = -EFAULT;
err_free_shared_buf:
From e6a7df96facdcf5b1f71eb3ec26f2f9f6ad61e57 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <jerry.zuo@amd.com>
Date: Mon, 22 Jan 2024 13:43:46 -0500
Subject: [PATCH 299/637] drm/amd/display: Fix MST Null Ptr for RV
The change try to fix below error specific to RV platform:
BUG: kernel NULL pointer dereference, address: 0000000000000008
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 4 PID: 917 Comm: sway Not tainted 6.3.9-arch1-1 #1 124dc55df4f5272ccb409f39ef4872fc2b3376a2
Hardware name: LENOVO 20NKS01Y00/20NKS01Y00, BIOS R12ET61W(1.31 ) 07/28/2022
RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper]
Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8>
RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224
RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280
RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850
R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000
R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224
FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0
Call Trace:
<TASK>
? __die+0x23/0x70
? page_fault_oops+0x171/0x4e0
? plist_add+0xbe/0x100
? exc_page_fault+0x7c/0x180
? asm_exc_page_fault+0x26/0x30
? drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026]
? drm_dp_atomic_find_time_slots+0x28/0x260 [drm_display_helper 0e67723696438d8e02b741593dd50d80b44c2026]
compute_mst_dsc_configs_for_link+0x2ff/0xa40 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
? fill_plane_buffer_attributes+0x419/0x510 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
compute_mst_dsc_configs_for_state+0x1e1/0x250 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
amdgpu_dm_atomic_check+0xecd/0x1190 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
drm_atomic_check_only+0x5c5/0xa40
drm_mode_atomic_ioctl+0x76e/0xbc0
? _copy_to_user+0x25/0x30
? drm_ioctl+0x296/0x4b0
? __pfx_drm_mode_atomic_ioctl+0x10/0x10
drm_ioctl_kernel+0xcd/0x170
drm_ioctl+0x26d/0x4b0
? __pfx_drm_mode_atomic_ioctl+0x10/0x10
amdgpu_drm_ioctl+0x4e/0x90 [amdgpu 62e600d2a75e9158e1cd0a243bdc8e6da040c054]
__x64_sys_ioctl+0x94/0xd0
do_syscall_64+0x60/0x90
? do_syscall_64+0x6c/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
RIP: 0033:0x7f4dad17f76f
Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <89> c>
RSP: 002b:00007ffd9ae859f0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 000055e255a55900 RCX: 00007f4dad17f76f
RDX: 00007ffd9ae85a90 RSI: 00000000c03864bc RDI: 000000000000000b
RBP: 00007ffd9ae85a90 R08: 0000000000000003 R09: 0000000000000003
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000c03864bc
R13: 000000000000000b R14: 000055e255a7fc60 R15: 000055e255a01eb0
</TASK>
Modules linked in: rfcomm snd_seq_dummy snd_hrtimer snd_seq snd_seq_device ccm cmac algif_hash algif_skcipher af_alg joydev mousedev bnep >
typec libphy k10temp ipmi_msghandler roles i2c_scmi acpi_cpufreq mac_hid nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_mas>
CR2: 0000000000000008
---[ end trace 0000000000000000 ]---
RIP: 0010:drm_dp_atomic_find_time_slots+0x5e/0x260 [drm_display_helper]
Code: 01 00 00 48 8b 85 60 05 00 00 48 63 80 88 00 00 00 3b 43 28 0f 8d 2e 01 00 00 48 8b 53 30 48 8d 04 80 48 8d 04 c2 48 8b 40 18 <48> 8>
RSP: 0018:ffff960cc2df77d8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff8afb87e81280 RCX: 0000000000000224
RDX: ffff8afb9ee37c00 RSI: ffff8afb8da1a578 RDI: ffff8afb87e81280
RBP: ffff8afb83d67000 R08: 0000000000000001 R09: ffff8afb9652f850
R10: ffff960cc2df7908 R11: 0000000000000002 R12: 0000000000000000
R13: ffff8afb8d7688a0 R14: ffff8afb8da1a578 R15: 0000000000000224
FS: 00007f4dac35ce00(0000) GS:ffff8afe30b00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000010ddc6000 CR4: 00000000003506e0
With a second DP monitor connected, drm_atomic_state in dm atomic check
sequence does not include the connector state for the old/existing/first
DP monitor. In such case, dsc determination policy would hit a null ptr
when it tries to iterate the old/existing stream that does not have a
valid connector state attached to it. When that happens, dm atomic check
should call drm_atomic_get_connector_state for a new connector state.
Existing dm has already done that, except for RV due to it does not have
official support of dsc where .num_dsc is not defined in dcn10 resource
cap, that prevent from getting drm_atomic_get_connector_state called.
So, skip dsc determination policy for ASICs that don't have DSC support.
Cc: stable@vger.kernel.org # 6.1+
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2314
Reviewed-by: Wayne Lin <wayne.lin@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Fangzhi Zuo <jerry.zuo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d292f290cd6e..59d2eee72a32 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -10731,11 +10731,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
goto fail;
}
- ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
- if (ret) {
- DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
- ret = -EINVAL;
- goto fail;
+ if (dc_resource_is_dsc_encoding_supported(dc)) {
+ ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+ if (ret) {
+ DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+ ret = -EINVAL;
+ goto fail;
+ }
}
ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
From ca8179ba11f211cdcb6c12ddd83814eaec999738 Mon Sep 17 00:00:00 2001
From: Alvin Lee <alvin.lee2@amd.com>
Date: Fri, 26 Jan 2024 16:47:20 -0500
Subject: [PATCH 300/637] drm/amd/display: Update phantom pipe enable / disable
sequence
Previously we would call apply_ctx_to_hw to enable and disable
phantom pipes. However, apply_ctx_to_hw can potentially update
non-phantom pipes as well which is undesired. Instead of calling
apply_ctx_to_hw as a whole, call the relevant helpers for each
phantom pipe when enabling / disabling which will avoid us modifying
hardware state for non-phantom pipes unknowingly.
The use case is for an FRL display where FRL_Update is requested
by the display. In this case link_state_valid flag is cleared in
a passive callback thread and should be handled in the next stream /
link update. However, due to the call to apply_ctx_to_hw for the
phantom pipes during a flip, the main pipes were modified outside
of the desired sequence (driver does not handle link_state_valid = 0
on flips).
Cc: stable@vger.kernel.org # 6.6+
Reviewed-by: Samson Tam <samson.tam@amd.com>
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/core/dc.c | 4 +-
.../amd/display/dc/hwss/dce110/dce110_hwseq.c | 4 +-
.../amd/display/dc/hwss/dce110/dce110_hwseq.h | 4 +
.../amd/display/dc/hwss/dcn20/dcn20_hwseq.c | 2 +-
.../amd/display/dc/hwss/dcn20/dcn20_hwseq.h | 4 +
.../amd/display/dc/hwss/dcn32/dcn32_hwseq.c | 74 +++++++++++++++++--
.../amd/display/dc/hwss/dcn32/dcn32_hwseq.h | 2 +
.../amd/display/dc/hwss/dcn32/dcn32_init.c | 3 +
.../drm/amd/display/dc/hwss/hw_sequencer.h | 1 +
.../display/dc/hwss/hw_sequencer_private.h | 7 ++
10 files changed, 93 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index aa7c02ba948e..2c424e435962 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3817,7 +3817,9 @@ static void commit_planes_for_stream(struct dc *dc,
* programming has completed (we turn on phantom OTG in order
* to complete the plane disable for phantom pipes).
*/
- dc->hwss.apply_ctx_to_hw(dc, context);
+
+ if (dc->hwss.disable_phantom_streams)
+ dc->hwss.disable_phantom_streams(dc, context);
}
if (update_type != UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 2352428bcea3..01493c49bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1476,7 +1476,7 @@ static enum dc_status dce110_enable_stream_timing(
return DC_OK;
}
-static enum dc_status apply_single_controller_ctx_to_hw(
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
struct pipe_ctx *pipe_ctx,
struct dc_state *context,
struct dc *dc)
@@ -2302,7 +2302,7 @@ enum dc_status dce110_apply_ctx_to_hw(
if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
continue;
- status = apply_single_controller_ctx_to_hw(
+ status = dce110_apply_single_controller_ctx_to_hw(
pipe_ctx,
context,
dc);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 08028a1779ae..ed3cc3648e8e 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -39,6 +39,10 @@ enum dc_status dce110_apply_ctx_to_hw(
struct dc *dc,
struct dc_state *context);
+enum dc_status dce110_apply_single_controller_ctx_to_hw(
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context,
+ struct dc *dc);
void dce110_enable_stream(struct pipe_ctx *pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 4853ecac53f9..931ac8ed7069 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -2561,7 +2561,7 @@ void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
tg->funcs->setup_vertical_interrupt2(tg, start_line);
}
-static void dcn20_reset_back_end_for_pipe(
+void dcn20_reset_back_end_for_pipe(
struct dc *dc,
struct pipe_ctx *pipe_ctx,
struct dc_state *context)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
index b94c85340abf..d950b3e54ec2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.h
@@ -84,6 +84,10 @@ enum dc_status dcn20_enable_stream_timing(
void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_reset_back_end_for_pipe(
+ struct dc *dc,
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context);
void dcn20_init_blank(
struct dc *dc,
struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6c9299c7683d..aa36d7a56ca8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -1474,9 +1474,44 @@ void dcn32_update_dsc_pg(struct dc *dc,
}
}
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context)
+{
+ struct dce_hwseq *hws = dc->hwseq;
+ int i;
+
+ for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
+ struct pipe_ctx *pipe_ctx_old =
+ &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (!pipe_ctx_old->stream)
+ continue;
+
+ if (dc_state_get_pipe_subvp_type(dc->current_state, pipe_ctx_old) != SUBVP_PHANTOM)
+ continue;
+
+ if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe)
+ continue;
+
+ if (!pipe_ctx->stream || pipe_need_reprogram(pipe_ctx_old, pipe_ctx) ||
+ (pipe_ctx->stream && dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)) {
+ struct clock_source *old_clk = pipe_ctx_old->clock_source;
+
+ if (hws->funcs.reset_back_end_for_pipe)
+ hws->funcs.reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
+ if (hws->funcs.enable_stream_gating)
+ hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
+ if (old_clk)
+ old_clk->funcs->cs_power_down(old_clk);
+ }
+ }
+}
+
void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
{
unsigned int i;
+ enum dc_status status = DC_OK;
+ struct dce_hwseq *hws = dc->hwseq;
for (i = 0; i < dc->res_pool->pipe_count; i++) {
struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -1497,16 +1532,39 @@ void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context)
}
}
for (i = 0; i < dc->res_pool->pipe_count; i++) {
- struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe_ctx_old =
+ &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
- if (new_pipe->stream && dc_state_get_pipe_subvp_type(context, new_pipe) == SUBVP_PHANTOM) {
- // If old context or new context has phantom pipes, apply
- // the phantom timings now. We can't change the phantom
- // pipe configuration safely without driver acquiring
- // the DMCUB lock first.
- dc->hwss.apply_ctx_to_hw(dc, context);
- break;
+ if (pipe_ctx->stream == NULL)
+ continue;
+
+ if (dc_state_get_pipe_subvp_type(context, pipe_ctx) != SUBVP_PHANTOM)
+ continue;
+
+ if (pipe_ctx->stream == pipe_ctx_old->stream &&
+ pipe_ctx->stream->link->link_state_valid) {
+ continue;
}
+
+ if (pipe_ctx_old->stream && !pipe_need_reprogram(pipe_ctx_old, pipe_ctx))
+ continue;
+
+ if (pipe_ctx->top_pipe || pipe_ctx->prev_odm_pipe)
+ continue;
+
+ if (hws->funcs.apply_single_controller_ctx_to_hw)
+ status = hws->funcs.apply_single_controller_ctx_to_hw(
+ pipe_ctx,
+ context,
+ dc);
+
+ ASSERT(status == DC_OK);
+
+#ifdef CONFIG_DRM_AMD_DC_FP
+ if (hws->funcs.resync_fifo_dccg_dio)
+ hws->funcs.resync_fifo_dccg_dio(hws, dc, context);
+#endif
}
}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
index cecf7f0f5671..069e20bc87c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.h
@@ -111,6 +111,8 @@ void dcn32_update_dsc_pg(struct dc *dc,
void dcn32_enable_phantom_streams(struct dc *dc, struct dc_state *context);
+void dcn32_disable_phantom_streams(struct dc *dc, struct dc_state *context);
+
void dcn32_init_blank(
struct dc *dc,
struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index 427cfc8c24a4..e8ac94a005b8 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -109,6 +109,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
.get_dcc_en_bits = dcn10_get_dcc_en_bits,
.commit_subvp_config = dcn32_commit_subvp_config,
.enable_phantom_streams = dcn32_enable_phantom_streams,
+ .disable_phantom_streams = dcn32_disable_phantom_streams,
.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
.update_visual_confirm_color = dcn10_update_visual_confirm_color,
.subvp_pipe_control_lock_fast = dcn32_subvp_pipe_control_lock_fast,
@@ -159,6 +160,8 @@ static const struct hwseq_private_funcs dcn32_private_funcs = {
.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
.resync_fifo_dccg_dio = dcn32_resync_fifo_dccg_dio,
.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+ .apply_single_controller_ctx_to_hw = dce110_apply_single_controller_ctx_to_hw,
+ .reset_back_end_for_pipe = dcn20_reset_back_end_for_pipe,
};
void dcn32_hw_sequencer_init_functions(struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index a54399383318..64ca7c66509b 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -379,6 +379,7 @@ struct hw_sequencer_funcs {
struct dc_cursor_attributes *cursor_attr);
void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context);
+ void (*disable_phantom_streams)(struct dc *dc, struct dc_state *context);
void (*subvp_pipe_control_lock)(struct dc *dc,
struct dc_state *context,
bool lock,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
index 6137cf09aa54..b3c62a82cb1c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
@@ -165,8 +165,15 @@ struct hwseq_private_funcs {
void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
void (*resync_fifo_dccg_dio)(struct dce_hwseq *hws, struct dc *dc,
struct dc_state *context);
+ enum dc_status (*apply_single_controller_ctx_to_hw)(
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context,
+ struct dc *dc);
bool (*is_dp_dig_pixel_rate_div_policy)(struct pipe_ctx *pipe_ctx);
#endif
+ void (*reset_back_end_for_pipe)(struct dc *dc,
+ struct pipe_ctx *pipe_ctx,
+ struct dc_state *context);
};
struct dce_hwseq {
From 29c5da1a124671caa87c4a936c625432c16ad8ca Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Date: Thu, 11 Jan 2024 14:25:27 -0700
Subject: [PATCH 301/637] drm/amd/display: Disable ODM by default for DCN35
Just ensure that ODM optimization is disabled by default.
Acked-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 2142cee6cac2..1c3d89264ef7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -2130,6 +2130,7 @@ static bool dcn35_resource_construct(
dc->dml2_options.dcn_pipe_count = pool->base.pipe_count;
dc->dml2_options.use_native_pstate_optimization = true;
dc->dml2_options.use_native_soc_bb_construction = true;
+ dc->dml2_options.minimize_dispclk_using_odm = false;
if (dc->config.EnableMinDispClkODM)
dc->dml2_options.minimize_dispclk_using_odm = true;
dc->dml2_options.enable_windowed_mpo_odm = dc->config.enable_windowed_mpo_odm;
From 55173942a63668bdc1d61812c7c9e0406aefb5bf Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 31 Jan 2024 16:34:32 +0530
Subject: [PATCH 302/637] drm/amdgpu: Avoid fetching VRAM vendor info
The present way to fetch VRAM vendor information turns out to be not
reliable on GFX 9.4.3 dGPUs as well. Avoid using the data.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 8 --------
1 file changed, 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 40a00ea0009f..e67a62db9e12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1947,14 +1947,6 @@ static int gmc_v9_0_init_mem_ranges(struct amdgpu_device *adev)
static void gmc_v9_4_3_init_vram_info(struct amdgpu_device *adev)
{
- static const u32 regBIF_BIOS_SCRATCH_4 = 0x50;
- u32 vram_info;
-
- /* Only for dGPU, vendor informaton is reliable */
- if (!amdgpu_sriov_vf(adev) && !(adev->flags & AMD_IS_APU)) {
- vram_info = RREG32(regBIF_BIOS_SCRATCH_4);
- adev->gmc.vram_vendor = vram_info & 0xF;
- }
adev->gmc.vram_type = AMDGPU_VRAM_TYPE_HBM;
adev->gmc.vram_width = 128 * 64;
}
From da48914e1fcdbf57f6b95d4552fcc088e6547ce4 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 2 Feb 2024 18:30:59 -0600
Subject: [PATCH 303/637] drm/amd/display: Clear phantom stream count and plane
count
When dc_state_destruct() was refactored the new phantom_stream_count
and phantom_plane_count members weren't cleared.
Fixes: 012a04b1d6af ("drm/amd/display: Refactor phantom resource allocation")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/core/dc_state.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 88c6436b28b6..180ac47868c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -291,11 +291,14 @@ void dc_state_destruct(struct dc_state *state)
dc_stream_release(state->phantom_streams[i]);
state->phantom_streams[i] = NULL;
}
+ state->phantom_stream_count = 0;
for (i = 0; i < state->phantom_plane_count; i++) {
dc_plane_state_release(state->phantom_planes[i]);
state->phantom_planes[i] = NULL;
}
+ state->phantom_plane_count = 0;
+
state->stream_mask = 0;
memset(&state->res_ctx, 0, sizeof(state->res_ctx));
memset(&state->pp_display_cfg, 0, sizeof(state->pp_display_cfg));
From e63e35f0164c43fbc1adb481d6604f253b9f9667 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 5 Feb 2024 14:54:05 -0700
Subject: [PATCH 304/637] drm/amd/display: Increase frame-larger-than for all
display_mode_vba files
After a recent change in LLVM, allmodconfig (which has CONFIG_KCSAN=y
and CONFIG_WERROR=y enabled) has a few new instances of
-Wframe-larger-than for the mode support and system configuration
functions:
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20v2.c:3393:6: error: stack frame size (2144) exceeds limit (2048) in 'dml20v2_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
3393 | void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
| ^
1 error generated.
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn21/display_mode_vba_21.c:3520:6: error: stack frame size (2192) exceeds limit (2048) in 'dml21_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
3520 | void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
| ^
1 error generated.
drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn20/display_mode_vba_20.c:3286:6: error: stack frame size (2128) exceeds limit (2048) in 'dml20_ModeSupportAndSystemConfigurationFull' [-Werror,-Wframe-larger-than]
3286 | void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib)
| ^
1 error generated.
Without the sanitizers enabled, there are no warnings.
This was the catalyst for commit 6740ec97bcdb ("drm/amd/display:
Increase frame warning limit with KASAN or KCSAN in dml2") and that same
change was made to dml in commit 5b750b22530f ("drm/amd/display:
Increase frame warning limit with KASAN or KCSAN in dml") but the
frame_warn_flag variable was not applied to all files. Do so now to
clear up the warnings and make all these files consistent.
Cc: stable@vger.kernel.org
Closes: https://github.com/ClangBuiltLinux/linux/issue/1990
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/dml/Makefile | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 6042a5a6a44f..59ade76ffb18 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -72,11 +72,11 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
From 58fca355ad37dcb5f785d9095db5f748b79c5dc2 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 7 Feb 2024 10:20:57 +0530
Subject: [PATCH 305/637] drm/amd/display: Implement bounds check for stream
encoder creation in DCN301
'stream_enc_regs' array is an array of dcn10_stream_enc_registers
structures. The array is initialized with four elements, corresponding
to the four calls to stream_enc_regs() in the array initializer. This
means that valid indices for this array are 0, 1, 2, and 3.
The error message 'stream_enc_regs' 4 <= 5 below, is indicating that
there is an attempt to access this array with an index of 5, which is
out of bounds. This could lead to undefined behavior
Here, eng_id is used as an index to access the stream_enc_regs array. If
eng_id is 5, this would result in an out-of-bounds access on the
stream_enc_regs array.
Thus fixing Buffer overflow error in dcn301_stream_encoder_create
reported by Smatch:
drivers/gpu/drm/amd/amdgpu/../display/dc/resource/dcn301/dcn301_resource.c:1011 dcn301_stream_encoder_create() error: buffer overflow 'stream_enc_regs' 4 <= 5
Fixes: 3a83e4e64bb1 ("drm/amd/display: Add dcn3.01 support to DC (v2)")
Cc: Roman Li <Roman.Li@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 511ff6b5b985..7538b548c572 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -999,7 +999,7 @@ static struct stream_encoder *dcn301_stream_encoder_create(enum engine_id eng_id
vpg = dcn301_vpg_create(ctx, vpg_inst);
afmt = dcn301_afmt_create(ctx, afmt_inst);
- if (!enc1 || !vpg || !afmt) {
+ if (!enc1 || !vpg || !afmt || eng_id >= ARRAY_SIZE(stream_enc_regs)) {
kfree(enc1);
kfree(vpg);
kfree(afmt);
From 534c8a5b9d5d41d30cdcac93cfa1bca5e17be009 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 8 Dec 2023 13:48:22 +0530
Subject: [PATCH 306/637] drm/amdgpu: Fix HDP flush for VFs on nbio v7.9
HDP flush remapping is not done for VFs. Keep the original offsets in VF
environment.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index e90f33780803..b4723d68eab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -431,6 +431,12 @@ static void nbio_v7_9_init_registers(struct amdgpu_device *adev)
u32 inst_mask;
int i;
+ if (amdgpu_sriov_vf(adev))
+ adev->rmmio_remap.reg_offset =
+ SOC15_REG_OFFSET(
+ NBIO, 0,
+ regBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL)
+ << 2;
WREG32_SOC15(NBIO, 0, regXCC_DOORBELL_FENCE,
0xff & ~(adev->gfx.xcc_mask));
From 4054705215ad7e6dd8e4e6ff27c39abd7667f700 Mon Sep 17 00:00:00 2001
From: Francis Pravin <francis.p@samsung.com>
Date: Wed, 7 Feb 2024 05:04:17 +0530
Subject: [PATCH 307/637] nvme: use ns->head->pi_size instead of t10_pi_tuple
structure size
Currently kernel supports 8 byte and 16 byte protection information.
So, use ns->head->pi_size instead of sizeof(struct t10_pi_tuple).
Signed-off-by: Francis Pravin <francis.p@samsung.com>
Signed-off-by: Sathyavathi M <sathya.m@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/ioctl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 18f5c1be5d67..3dfd5ae99ae0 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -228,7 +228,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
length = (io.nblocks + 1) << ns->head->lba_shift;
if ((io.control & NVME_RW_PRINFO_PRACT) &&
- ns->head->ms == sizeof(struct t10_pi_tuple)) {
+ (ns->head->ms == ns->head->pi_size)) {
/*
* Protection information is stripped/inserted by the
* controller.
From a12bc36032a2f7917068f9ce9eb26d869e54b31a Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 2 Feb 2024 16:13:17 +0800
Subject: [PATCH 308/637] ksmbd: Add kernel-doc for ksmbd_extract_sharename()
function
The ksmbd_extract_sharename() function lacked a complete kernel-doc
comment. This patch adds parameter descriptions and detailed function
behavior to improve code readability and maintainability.
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/server/misc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c
index 9e8afaa686e3..1a5faa6f6e7b 100644
--- a/fs/smb/server/misc.c
+++ b/fs/smb/server/misc.c
@@ -261,6 +261,7 @@ out_ascii:
/**
* ksmbd_extract_sharename() - get share name from tree connect request
+ * @um: pointer to a unicode_map structure for character encoding handling
* @treename: buffer containing tree name and share name
*
* Return: share name on success, otherwise error
From 108a020c64434fed4b69762879d78cd24088b4c7 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 5 Feb 2024 14:19:16 +0300
Subject: [PATCH 309/637] ksmbd: free aux buffer if ksmbd_iov_pin_rsp_read
fails
ksmbd_iov_pin_rsp_read() doesn't free the provided aux buffer if it
fails. Seems to be the caller's responsibility to clear the buffer in
error case.
Found by Linux Verification Center (linuxtesting.org).
Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/server/smb2pdu.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index ba7a72a6a4f4..0c97d3c86072 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -6173,8 +6173,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
offsetof(struct smb2_read_rsp, Buffer),
aux_payload_buf, nbytes);
- if (err)
+ if (err) {
+ kvfree(aux_payload_buf);
goto out;
+ }
kvfree(rpc_resp);
} else {
err = ksmbd_iov_pin_rsp(work, (void *)rsp,
@@ -6384,8 +6386,10 @@ int smb2_read(struct ksmbd_work *work)
err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
offsetof(struct smb2_read_rsp, Buffer),
aux_payload_buf, nbytes);
- if (err)
+ if (err) {
+ kvfree(aux_payload_buf);
goto out;
+ }
ksmbd_fd_put(work, fp);
return 0;
From e656c7a9e59607d1672d85ffa9a89031876ffe67 Mon Sep 17 00:00:00 2001
From: Prakash Sangappa <prakash.sangappa@oracle.com>
Date: Tue, 23 Jan 2024 12:04:42 -0800
Subject: [PATCH 310/637] mm: hugetlb pages should not be reserved by shmat()
if SHM_NORESERVE
For shared memory of type SHM_HUGETLB, hugetlb pages are reserved in
shmget() call. If SHM_NORESERVE flags is specified then the hugetlb pages
are not reserved. However when the shared memory is attached with the
shmat() call the hugetlb pages are getting reserved incorrectly for
SHM_HUGETLB shared memory created with SHM_NORESERVE which is a bug.
-------------------------------
Following test shows the issue.
$cat shmhtb.c
int main()
{
int shmflags = 0660 | IPC_CREAT | SHM_HUGETLB | SHM_NORESERVE;
int shmid;
shmid = shmget(SKEY, SHMSZ, shmflags);
if (shmid < 0)
{
printf("shmat: shmget() failed, %d\n", errno);
return 1;
}
printf("After shmget()\n");
system("cat /proc/meminfo | grep -i hugepages_");
shmat(shmid, NULL, 0);
printf("\nAfter shmat()\n");
system("cat /proc/meminfo | grep -i hugepages_");
shmctl(shmid, IPC_RMID, NULL);
return 0;
}
#sysctl -w vm.nr_hugepages=20
#./shmhtb
After shmget()
HugePages_Total: 20
HugePages_Free: 20
HugePages_Rsvd: 0
HugePages_Surp: 0
After shmat()
HugePages_Total: 20
HugePages_Free: 20
HugePages_Rsvd: 5 <--
HugePages_Surp: 0
--------------------------------
Fix is to ensure that hugetlb pages are not reserved for SHM_HUGETLB shared
memory in the shmat() call.
Link: https://lkml.kernel.org/r/1706040282-12388-1-git-send-email-prakash.sangappa@oracle.com
Signed-off-by: Prakash Sangappa <prakash.sangappa@oracle.com>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/hugetlbfs/inode.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 671664fed307..ee13c2ca8ad2 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -100,6 +100,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
loff_t len, vma_len;
int ret;
struct hstate *h = hstate_file(file);
+ vm_flags_t vm_flags;
/*
* vma address alignment (but not the pgoff alignment) has
@@ -141,10 +142,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
file_accessed(file);
ret = -ENOMEM;
+
+ vm_flags = vma->vm_flags;
+ /*
+ * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
+ * reserving here. Note: only for SHM hugetlbfs file, the inode
+ * flag S_PRIVATE is set.
+ */
+ if (inode->i_flags & S_PRIVATE)
+ vm_flags |= VM_NORESERVE;
+
if (!hugetlb_reserve_pages(inode,
vma->vm_pgoff >> huge_page_order(h),
len >> huge_page_shift(h), vma,
- vma->vm_flags))
+ vm_flags))
goto out;
ret = 0;
From daa694e4137571b4ebec330f9a9b4d54aa8b8089 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 22 Jan 2024 16:50:50 +0100
Subject: [PATCH 311/637] getrusage: move thread_group_cputime_adjusted()
outside of lock_task_sighand()
Patch series "getrusage: use sig->stats_lock", v2.
This patch (of 2):
thread_group_cputime() does its own locking, we can safely shift
thread_group_cputime_adjusted() which does another for_each_thread loop
outside of ->siglock protected section.
This is also preparation for the next patch which changes getrusage() to
use stats_lock instead of siglock, thread_group_cputime() takes the same
lock. With the current implementation recursive read_seqbegin_or_lock()
is fine, thread_group_cputime() can't enter the slow mode if the caller
holds stats_lock, yet this looks more safe and better performance-wise.
Link: https://lkml.kernel.org/r/20240122155023.GA26169@redhat.com
Link: https://lkml.kernel.org/r/20240122155050.GA26205@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Dylan Hatch <dylanbhatch@google.com>
Tested-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/sys.c | 38 +++++++++++++++++++++-----------------
1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/kernel/sys.c b/kernel/sys.c
index e219fcfa112d..70ad06ad852e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1785,17 +1785,19 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
struct task_struct *t;
unsigned long flags;
u64 tgutime, tgstime, utime, stime;
- unsigned long maxrss = 0;
+ unsigned long maxrss;
+ struct mm_struct *mm;
struct signal_struct *sig = p->signal;
- memset((char *)r, 0, sizeof (*r));
+ memset(r, 0, sizeof(*r));
utime = stime = 0;
+ maxrss = 0;
if (who == RUSAGE_THREAD) {
task_cputime_adjusted(current, &utime, &stime);
accumulate_thread_rusage(p, r);
maxrss = sig->maxrss;
- goto out;
+ goto out_thread;
}
if (!lock_task_sighand(p, &flags))
@@ -1819,9 +1821,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
fallthrough;
case RUSAGE_SELF:
- thread_group_cputime_adjusted(p, &tgutime, &tgstime);
- utime += tgutime;
- stime += tgstime;
r->ru_nvcsw += sig->nvcsw;
r->ru_nivcsw += sig->nivcsw;
r->ru_minflt += sig->min_flt;
@@ -1839,19 +1838,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
}
unlock_task_sighand(p, &flags);
-out:
+ if (who == RUSAGE_CHILDREN)
+ goto out_children;
+
+ thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+ utime += tgutime;
+ stime += tgstime;
+
+out_thread:
+ mm = get_task_mm(p);
+ if (mm) {
+ setmax_mm_hiwater_rss(&maxrss, mm);
+ mmput(mm);
+ }
+
+out_children:
+ r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
r->ru_utime = ns_to_kernel_old_timeval(utime);
r->ru_stime = ns_to_kernel_old_timeval(stime);
-
- if (who != RUSAGE_CHILDREN) {
- struct mm_struct *mm = get_task_mm(p);
-
- if (mm) {
- setmax_mm_hiwater_rss(&maxrss, mm);
- mmput(mm);
- }
- }
- r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
}
SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
From f7ec1cd5cc7ef3ad964b677ba82b8b77f1c93009 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 22 Jan 2024 16:50:53 +0100
Subject: [PATCH 312/637] getrusage: use sig->stats_lock rather than
lock_task_sighand()
lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call
getrusage() at the same time and the process has NR_THREADS, spin_lock_irq
will spin with irqs disabled O(NR_CPUS * NR_THREADS) time.
Change getrusage() to use sig->stats_lock, it was specifically designed
for this type of use. This way it runs lockless in the likely case.
TODO:
- Change do_task_stat() to use sig->stats_lock too, then we can
remove spin_lock_irq(siglock) in wait_task_zombie().
- Turn sig->stats_lock into seqcount_rwlock_t, this way the
readers in the slow mode won't exclude each other. See
https://lore.kernel.org/all/20230913154907.GA26210@redhat.com/
- stats_lock has to disable irqs because ->siglock can be taken
in irq context, it would be very nice to change __exit_signal()
to avoid the siglock->stats_lock dependency.
Link: https://lkml.kernel.org/r/20240122155053.GA26214@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Dylan Hatch <dylanbhatch@google.com>
Tested-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/sys.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/kernel/sys.c b/kernel/sys.c
index 70ad06ad852e..f8e543f1e38a 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1788,7 +1788,9 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
unsigned long maxrss;
struct mm_struct *mm;
struct signal_struct *sig = p->signal;
+ unsigned int seq = 0;
+retry:
memset(r, 0, sizeof(*r));
utime = stime = 0;
maxrss = 0;
@@ -1800,8 +1802,7 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
goto out_thread;
}
- if (!lock_task_sighand(p, &flags))
- return;
+ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
switch (who) {
case RUSAGE_BOTH:
@@ -1829,14 +1830,23 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
r->ru_oublock += sig->oublock;
if (maxrss < sig->maxrss)
maxrss = sig->maxrss;
+
+ rcu_read_lock();
__for_each_thread(sig, t)
accumulate_thread_rusage(t, r);
+ rcu_read_unlock();
+
break;
default:
BUG();
}
- unlock_task_sighand(p, &flags);
+
+ if (need_seqretry(&sig->stats_lock, seq)) {
+ seq = 1;
+ goto retry;
+ }
+ done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
if (who == RUSAGE_CHILDREN)
goto out_children;
From 60f92acb60a989b14e4b744501a0df0f82ef30a3 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:33:55 +0100
Subject: [PATCH 313/637] fs/proc: do_task_stat: move
thread_group_cputime_adjusted() outside of lock_task_sighand()
Patch series "fs/proc: do_task_stat: use sig->stats_".
do_task_stat() has the same problem as getrusage() had before "getrusage:
use sig->stats_lock rather than lock_task_sighand()": a hard lockup. If
NR_CPUS threads call lock_task_sighand() at the same time and the process
has NR_THREADS, spin_lock_irq will spin with irqs disabled O(NR_CPUS *
NR_THREADS) time.
This patch (of 3):
thread_group_cputime() does its own locking, we can safely shift
thread_group_cputime_adjusted() which does another for_each_thread loop
outside of ->siglock protected section.
Not only this removes for_each_thread() from the critical section with
irqs disabled, this removes another case when stats_lock is taken with
siglock held. We want to remove this dependency, then we can change the
users of stats_lock to not disable irqs.
Link: https://lkml.kernel.org/r/20240123153313.GA21832@redhat.com
Link: https://lkml.kernel.org/r/20240123153355.GA21854@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/proc/array.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff08a8957552..45ba91863808 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -511,7 +511,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
sigemptyset(&sigign);
sigemptyset(&sigcatch);
- cutime = cstime = utime = stime = 0;
+ cutime = cstime = 0;
cgtime = gtime = 0;
if (lock_task_sighand(task, &flags)) {
@@ -546,7 +546,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
min_flt += sig->min_flt;
maj_flt += sig->maj_flt;
- thread_group_cputime_adjusted(task, &utime, &stime);
gtime += sig->gtime;
if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
@@ -562,10 +561,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
if (permitted && (!whole || num_threads < 2))
wchan = !task_is_running(task);
- if (!whole) {
+
+ if (whole) {
+ thread_group_cputime_adjusted(task, &utime, &stime);
+ } else {
+ task_cputime_adjusted(task, &utime, &stime);
min_flt = task->min_flt;
maj_flt = task->maj_flt;
- task_cputime_adjusted(task, &utime, &stime);
gtime = task_gtime(task);
}
From 7601df8031fd67310af891897ef6cc0df4209305 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:33:57 +0100
Subject: [PATCH 314/637] fs/proc: do_task_stat: use sig->stats_lock to gather
the threads/children stats
lock_task_sighand() can trigger a hard lockup. If NR_CPUS threads call
do_task_stat() at the same time and the process has NR_THREADS, it will
spin with irqs disabled O(NR_CPUS * NR_THREADS) time.
Change do_task_stat() to use sig->stats_lock to gather the statistics
outside of ->siglock protected section, in the likely case this code will
run lockless.
Link: https://lkml.kernel.org/r/20240123153357.GA21857@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/proc/array.c | 58 +++++++++++++++++++++++++++----------------------
1 file changed, 32 insertions(+), 26 deletions(-)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 45ba91863808..34a47fb0c57f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
int permitted;
struct mm_struct *mm;
unsigned long long start_time;
- unsigned long cmin_flt = 0, cmaj_flt = 0;
- unsigned long min_flt = 0, maj_flt = 0;
- u64 cutime, cstime, utime, stime;
- u64 cgtime, gtime;
+ unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+ u64 cutime, cstime, cgtime, utime, stime, gtime;
unsigned long rsslim = 0;
unsigned long flags;
int exit_code = task->exit_code;
+ struct signal_struct *sig = task->signal;
+ unsigned int seq = 1;
state = *get_task_state(task);
vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
sigemptyset(&sigign);
sigemptyset(&sigcatch);
- cutime = cstime = 0;
- cgtime = gtime = 0;
if (lock_task_sighand(task, &flags)) {
- struct signal_struct *sig = task->signal;
-
if (sig->tty) {
struct pid *pgrp = tty_get_pgrp(sig->tty);
tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,27 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
num_threads = get_nr_threads(task);
collect_sigign_sigcatch(task, &sigign, &sigcatch);
- cmin_flt = sig->cmin_flt;
- cmaj_flt = sig->cmaj_flt;
- cutime = sig->cutime;
- cstime = sig->cstime;
- cgtime = sig->cgtime;
rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
- /* add up live thread stats at the group level */
if (whole) {
- struct task_struct *t;
-
- __for_each_thread(sig, t) {
- min_flt += t->min_flt;
- maj_flt += t->maj_flt;
- gtime += task_gtime(t);
- }
-
- min_flt += sig->min_flt;
- maj_flt += sig->maj_flt;
- gtime += sig->gtime;
-
if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
exit_code = sig->group_exit_code;
}
@@ -562,6 +540,34 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
if (permitted && (!whole || num_threads < 2))
wchan = !task_is_running(task);
+ do {
+ seq++; /* 2 on the 1st/lockless path, otherwise odd */
+ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+ cmin_flt = sig->cmin_flt;
+ cmaj_flt = sig->cmaj_flt;
+ cutime = sig->cutime;
+ cstime = sig->cstime;
+ cgtime = sig->cgtime;
+
+ if (whole) {
+ struct task_struct *t;
+
+ min_flt = sig->min_flt;
+ maj_flt = sig->maj_flt;
+ gtime = sig->gtime;
+
+ rcu_read_lock();
+ __for_each_thread(sig, t) {
+ min_flt += t->min_flt;
+ maj_flt += t->maj_flt;
+ gtime += task_gtime(t);
+ }
+ rcu_read_unlock();
+ }
+ } while (need_seqretry(&sig->stats_lock, seq));
+ done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
if (whole) {
thread_group_cputime_adjusted(task, &utime, &stime);
} else {
From c1be35a16b2f1fe21f4f26f9de030ad6eaaf6a25 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 23 Jan 2024 16:34:00 +0100
Subject: [PATCH 315/637] exit: wait_task_zombie: kill the no longer necessary
spin_lock_irq(siglock)
After the recent changes nobody use siglock to read the values protected
by stats_lock, we can kill spin_lock_irq(¤t->sighand->siglock) and
update the comment.
With this patch only __exit_signal() and thread_group_start_cputime() take
stats_lock under siglock.
Link: https://lkml.kernel.org/r/20240123153359.GA21866@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Dylan Hatch <dylanbhatch@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
kernel/exit.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/kernel/exit.c b/kernel/exit.c
index 3988a02efaef..dfb963d2f862 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1127,17 +1127,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
* and nobody can change them.
*
* psig->stats_lock also protects us from our sub-threads
- * which can reap other children at the same time. Until
- * we change k_getrusage()-like users to rely on this lock
- * we have to take ->siglock as well.
+ * which can reap other children at the same time.
*
* We use thread_group_cputime_adjusted() to get times for
* the thread group, which consolidates times for all threads
* in the group including the group leader.
*/
thread_group_cputime_adjusted(p, &tgutime, &tgstime);
- spin_lock_irq(¤t->sighand->siglock);
- write_seqlock(&psig->stats_lock);
+ write_seqlock_irq(&psig->stats_lock);
psig->cutime += tgutime + sig->cutime;
psig->cstime += tgstime + sig->cstime;
psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1160,8 +1157,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
- write_sequnlock(&psig->stats_lock);
- spin_unlock_irq(¤t->sighand->siglock);
+ write_sequnlock_irq(&psig->stats_lock);
}
if (wo->wo_rusage)
From 56ae10cf628b02279980d17439c6241a643959c2 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Tue, 23 Jan 2024 14:17:55 +0000
Subject: [PATCH 316/637] mm/userfaultfd: UFFDIO_MOVE implementation should use
ptep_get()
Commit c33c794828f2 ("mm: ptep_get() conversion") converted all (non-arch)
call sites to use ptep_get() instead of doing a direct dereference of the
pte. Full rationale can be found in that commit's log.
Since then, UFFDIO_MOVE has been implemented which does 7 direct pte
dereferences. Let's fix those up to use ptep_get().
I've asserted in the past that there is no reliable automated mechanism to
catch these; I'm relying on a combination of Coccinelle (which throws up a
lot of false positives) and some compiler magic to force a compiler error
on dereference. But given the frequency with which new issues are coming
up, I'll add it to my todo list to try to find an automated solution.
Link: https://lkml.kernel.org/r/20240123141755.3836179-1-ryan.roberts@arm.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/userfaultfd.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 75fcf1f783bc..7cf7d4384259 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -902,8 +902,8 @@ static int move_present_pte(struct mm_struct *mm,
double_pt_lock(dst_ptl, src_ptl);
- if (!pte_same(*src_pte, orig_src_pte) ||
- !pte_same(*dst_pte, orig_dst_pte)) {
+ if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+ !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
err = -EAGAIN;
goto out;
}
@@ -946,8 +946,8 @@ static int move_swap_pte(struct mm_struct *mm,
double_pt_lock(dst_ptl, src_ptl);
- if (!pte_same(*src_pte, orig_src_pte) ||
- !pte_same(*dst_pte, orig_dst_pte)) {
+ if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
+ !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
double_pt_unlock(dst_ptl, src_ptl);
return -EAGAIN;
}
@@ -1016,7 +1016,7 @@ retry:
}
spin_lock(dst_ptl);
- orig_dst_pte = *dst_pte;
+ orig_dst_pte = ptep_get(dst_pte);
spin_unlock(dst_ptl);
if (!pte_none(orig_dst_pte)) {
err = -EEXIST;
@@ -1024,7 +1024,7 @@ retry:
}
spin_lock(src_ptl);
- orig_src_pte = *src_pte;
+ orig_src_pte = ptep_get(src_pte);
spin_unlock(src_ptl);
if (pte_none(orig_src_pte)) {
if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
@@ -1054,7 +1054,7 @@ retry:
* page isn't freed under us
*/
spin_lock(src_ptl);
- if (!pte_same(orig_src_pte, *src_pte)) {
+ if (!pte_same(orig_src_pte, ptep_get(src_pte))) {
spin_unlock(src_ptl);
err = -EAGAIN;
goto out;
From 67b8bcbaed4777871bb0dcc888fb02a614a98ab1 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Wed, 24 Jan 2024 21:19:36 +0900
Subject: [PATCH 317/637] nilfs2: fix data corruption in dsync block recovery
for small block sizes
The helper function nilfs_recovery_copy_block() of
nilfs_recovery_dsync_blocks(), which recovers data from logs created by
data sync writes during a mount after an unclean shutdown, incorrectly
calculates the on-page offset when copying repair data to the file's page
cache. In environments where the block size is smaller than the page
size, this flaw can cause data corruption and leak uninitialized memory
bytes during the recovery process.
Fix these issues by correcting this byte offset calculation on the page.
Link: https://lkml.kernel.org/r/20240124121936.10575-1-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Tested-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/nilfs2/recovery.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0955b657938f..a9b8d77c8c1d 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
struct nilfs_recovery_block *rb,
- struct page *page)
+ loff_t pos, struct page *page)
{
struct buffer_head *bh_org;
+ size_t from = pos & ~PAGE_MASK;
void *kaddr;
bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
@@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
return -EIO;
kaddr = kmap_atomic(page);
- memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size);
+ memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
kunmap_atomic(kaddr);
brelse(bh_org);
return 0;
@@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
goto failed_inode;
}
- err = nilfs_recovery_copy_block(nilfs, rb, page);
+ err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
if (unlikely(err))
goto failed_page;
From 9cee7e8ef3e31ca25b40ca52b8585dc6935deff2 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosryahmed@google.com>
Date: Wed, 24 Jan 2024 10:00:22 +0000
Subject: [PATCH 318/637] mm: memcg: optimize parent iteration in
memcg_rstat_updated()
In memcg_rstat_updated(), we iterate the memcg being updated and its
parents to update memcg->vmstats_percpu->stats_updates in the fast path
(i.e. no atomic updates). According to my math, this is 3 memory loads
(and potentially 3 cache misses) per memcg:
- Load the address of memcg->vmstats_percpu.
- Load vmstats_percpu->stats_updates (based on some percpu calculation).
- Load the address of the parent memcg.
Avoid most of the cache misses by caching a pointer from each struct
memcg_vmstats_percpu to its parent on the corresponding CPU. In this
case, for the first memcg we have 2 memory loads (same as above):
- Load the address of memcg->vmstats_percpu.
- Load vmstats_percpu->stats_updates (based on some percpu calculation).
Then for each additional memcg, we need a single load to get the
parent's stats_updates directly. This reduces the number of loads from
O(3N) to O(2+N) -- where N is the number of memcgs we need to iterate.
Additionally, stash a pointer to memcg->vmstats in each struct
memcg_vmstats_percpu such that we can access the atomic counter that all
CPUs fold into, memcg->vmstats->stats_updates.
memcg_should_flush_stats() is changed to memcg_vmstats_needs_flush() to
accept a struct memcg_vmstats pointer accordingly.
In struct memcg_vmstats_percpu, make sure both pointers together with
stats_updates live on the same cacheline. Finally, update
mem_cgroup_alloc() to take in a parent pointer and initialize the new
cache pointers on each CPU. The percpu loop in mem_cgroup_alloc() may
look concerning, but there are multiple similar loops in the cgroup
creation path (e.g. cgroup_rstat_init()), most of which are hidden
within alloc_percpu().
According to Oliver's testing [1], this fixes multiple 30-38%
regressions in vm-scalability, will-it-scale-tlb_flush2, and
will-it-scale-fallocate1. This comes at a cost of 2 more pointers per
CPU (<2KB on a machine with 128 CPUs).
[1] https://lore.kernel.org/lkml/ZbDJsfsZt2ITyo61@xsang-OptiPlex-9020/
[yosryahmed@google.com: fix struct memcg_vmstats_percpu size and alignment]
Link: https://lkml.kernel.org/r/20240203044612.1234216-1-yosryahmed@google.com
Link: https://lkml.kernel.org/r/20240124100023.660032-1-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Fixes: 8d59d2214c23 ("mm: memcg: make stats flushing threshold per-memcg")
Tested-by: kernel test robot <oliver.sang@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401221624.cb53a8ca-oliver.sang@intel.com
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memcontrol.c | 56 ++++++++++++++++++++++++++++++-------------------
1 file changed, 35 insertions(+), 21 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 46d8d02114cf..1ed40f9d3a27 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -621,6 +621,15 @@ static inline int memcg_events_index(enum vm_event_item idx)
}
struct memcg_vmstats_percpu {
+ /* Stats updates since the last flush */
+ unsigned int stats_updates;
+
+ /* Cached pointers for fast iteration in memcg_rstat_updated() */
+ struct memcg_vmstats_percpu *parent;
+ struct memcg_vmstats *vmstats;
+
+ /* The above should fit a single cacheline for memcg_rstat_updated() */
+
/* Local (CPU and cgroup) page state & events */
long state[MEMCG_NR_STAT];
unsigned long events[NR_MEMCG_EVENTS];
@@ -632,10 +641,7 @@ struct memcg_vmstats_percpu {
/* Cgroup1: threshold notifications & softlimit tree updates */
unsigned long nr_page_events;
unsigned long targets[MEM_CGROUP_NTARGETS];
-
- /* Stats updates since the last flush */
- unsigned int stats_updates;
-};
+} ____cacheline_aligned;
struct memcg_vmstats {
/* Aggregated (CPU and subtree) page state & events */
@@ -698,36 +704,35 @@ static void memcg_stats_unlock(void)
}
-static bool memcg_should_flush_stats(struct mem_cgroup *memcg)
+static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
{
- return atomic64_read(&memcg->vmstats->stats_updates) >
+ return atomic64_read(&vmstats->stats_updates) >
MEMCG_CHARGE_BATCH * num_online_cpus();
}
static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
{
+ struct memcg_vmstats_percpu *statc;
int cpu = smp_processor_id();
- unsigned int x;
if (!val)
return;
cgroup_rstat_updated(memcg->css.cgroup, cpu);
-
- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- x = __this_cpu_add_return(memcg->vmstats_percpu->stats_updates,
- abs(val));
-
- if (x < MEMCG_CHARGE_BATCH)
+ statc = this_cpu_ptr(memcg->vmstats_percpu);
+ for (; statc; statc = statc->parent) {
+ statc->stats_updates += abs(val);
+ if (statc->stats_updates < MEMCG_CHARGE_BATCH)
continue;
/*
* If @memcg is already flush-able, increasing stats_updates is
* redundant. Avoid the overhead of the atomic update.
*/
- if (!memcg_should_flush_stats(memcg))
- atomic64_add(x, &memcg->vmstats->stats_updates);
- __this_cpu_write(memcg->vmstats_percpu->stats_updates, 0);
+ if (!memcg_vmstats_needs_flush(statc->vmstats))
+ atomic64_add(statc->stats_updates,
+ &statc->vmstats->stats_updates);
+ statc->stats_updates = 0;
}
}
@@ -756,7 +761,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
if (!memcg)
memcg = root_mem_cgroup;
- if (memcg_should_flush_stats(memcg))
+ if (memcg_vmstats_needs_flush(memcg->vmstats))
do_flush_stats(memcg);
}
@@ -770,7 +775,7 @@ void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
static void flush_memcg_stats_dwork(struct work_struct *w)
{
/*
- * Deliberately ignore memcg_should_flush_stats() here so that flushing
+ * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing
* in latency-sensitive paths is as cheap as possible.
*/
do_flush_stats(root_mem_cgroup);
@@ -5477,10 +5482,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
__mem_cgroup_free(memcg);
}
-static struct mem_cgroup *mem_cgroup_alloc(void)
+static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
{
+ struct memcg_vmstats_percpu *statc, *pstatc;
struct mem_cgroup *memcg;
- int node;
+ int node, cpu;
int __maybe_unused i;
long error = -ENOMEM;
@@ -5504,6 +5510,14 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
if (!memcg->vmstats_percpu)
goto fail;
+ for_each_possible_cpu(cpu) {
+ if (parent)
+ pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+ statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
+ statc->parent = parent ? pstatc : NULL;
+ statc->vmstats = memcg->vmstats;
+ }
+
for_each_node(node)
if (alloc_mem_cgroup_per_node_info(memcg, node))
goto fail;
@@ -5549,7 +5563,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
struct mem_cgroup *memcg, *old_memcg;
old_memcg = set_active_memcg(parent);
- memcg = mem_cgroup_alloc();
+ memcg = mem_cgroup_alloc(parent);
set_active_memcg(old_memcg);
if (IS_ERR(memcg))
return ERR_CAST(memcg);
From 2fde9e7f9e6dc38e1d7091b9705c22be945c8697 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Wed, 24 Jan 2024 16:40:14 +0800
Subject: [PATCH 319/637] mm/memory-failure: fix crash in
split_huge_page_to_list from soft_offline_page
When I did soft offline stress test, a machine was observed to crash with
the following message:
kernel BUG at include/linux/memcontrol.h:554!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 5 PID: 3837 Comm: hwpoison.sh Not tainted 6.7.0-next-20240112-00001-g8ecf3e7fb7c8-dirty #97
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
RIP: 0010:folio_memcg+0xaf/0xd0
Code: 10 5b 5d c3 cc cc cc cc 48 c7 c6 08 b1 f2 b2 48 89 ef e8 b4 c5 f8 ff 90 0f 0b 48 c7 c6 d0 b0 f2 b2 48 89 ef e8 a2 c5 f8 ff 90 <0f> 0b 48 c7 c6 08 b1 f2 b2 48 89 ef e8 90 c5 f8 ff 90 0f 0b 66 66
RSP: 0018:ffffb6c043657c98 EFLAGS: 00000296
RAX: 000000000000004b RBX: ffff932bc1d1e401 RCX: ffff933abfb5c908
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff933abfb5c900
RBP: ffffea6f04019080 R08: ffffffffb3338ce8 R09: 0000000000009ffb
R10: 00000000000004dd R11: ffffffffb3308d00 R12: ffffea6f04019080
R13: ffffea6f04019080 R14: 0000000000000001 R15: ffffb6c043657da0
FS: 00007f6c60f6b740(0000) GS:ffff933abfb40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000559c3bc8b980 CR3: 0000000107f1c000 CR4: 00000000000006f0
Call Trace:
<TASK>
split_huge_page_to_list+0x4d/0x1380
try_to_split_thp_page+0x3a/0xf0
soft_offline_page+0x1ea/0x8a0
soft_offline_page_store+0x52/0x90
kernfs_fop_write_iter+0x118/0x1b0
vfs_write+0x30b/0x430
ksys_write+0x5e/0xe0
do_syscall_64+0xb0/0x1b0
entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7f6c60d14697
Code: 10 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24
RSP: 002b:00007ffe9b72b8d8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f6c60d14697
RDX: 000000000000000c RSI: 0000559c3bc8b980 RDI: 0000000000000001
RBP: 0000559c3bc8b980 R08: 00007f6c60dd1460 R09: 000000007fffffff
R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c
R13: 00007f6c60e1a780 R14: 00007f6c60e16600 R15: 00007f6c60e15a00
The problem is that page->mapping is overloaded with slab->slab_list or
slabs fields now, so slab pages could be taken as non-LRU movable pages if
field slabs contains PAGE_MAPPING_MOVABLE or slab_list->prev is set to
LIST_POISON2. These slab pages will be treated as thp later leading to
crash in split_huge_page_to_list().
Link: https://lkml.kernel.org/r/20240126065837.2100184-1-linmiaohe@huawei.com
Link: https://lkml.kernel.org/r/20240124084014.1772906-1-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Fixes: 130d4df57390 ("mm/sl[au]b: rearrange struct slab fields to allow larger rcu_head")
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/memory-failure.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 636280d04008..9349948f1abf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1377,6 +1377,9 @@ void ClearPageHWPoisonTakenOff(struct page *page)
*/
static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
{
+ if (PageSlab(page))
+ return false;
+
/* Soft offline could migrate non-LRU movable pages */
if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
return true;
From 01c1484ac04790fe27a37f89dd3a350f99646815 Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@collabora.com>
Date: Tue, 24 Oct 2023 20:51:25 +0500
Subject: [PATCH 320/637] selftests: core: include linux/close_range.h for
CLOSE_RANGE_* macros
Correct header file is needed for getting CLOSE_RANGE_* macros.
Previously it was tested with newer glibc which didn't show the need to
include the header which was a mistake.
Link: https://lkml.kernel.org/r/20231024155137.219700-1-usama.anjum@collabora.com
Fixes: ec54424923cf ("selftests: core: remove duplicate defines")
Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Link: https://lore.kernel.org/all/7161219e-0223-d699-d6f3-81abd9abf13b@arm.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
tools/testing/selftests/core/close_range_test.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 534576f06df1..c59e4adb905d 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -12,6 +12,7 @@
#include <syscall.h>
#include <unistd.h>
#include <sys/resource.h>
+#include <linux/close_range.h>
#include "../kselftest_harness.h"
#include "../clone3/clone3_selftests.h"
From e870920bbe68e52335a4c31a059e6af6a9a59dbb Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Mon, 22 Jan 2024 22:43:05 -0800
Subject: [PATCH 321/637] arch/arm/mm: fix major fault accounting when retrying
under per-VMA lock
The change [1] missed ARM architecture when fixing major fault accounting
for page fault retry under per-VMA lock.
The user-visible effects is that it restores correct major fault
accounting that was broken after [2] was merged in 6.7 kernel. The
more detailed description is in [3] and this patch simply adds the
same fix to ARM architecture which I missed in [3].
Add missing code to fix ARM architecture fault accounting.
[1] 46e714c729c8 ("arch/mm/fault: fix major fault accounting when retrying under per-VMA lock")
[2] https://lore.kernel.org/all/20231006195318.4087158-6-willy@infradead.org/
[3] https://lore.kernel.org/all/20231226214610.109282-1-surenb@google.com/
Link: https://lkml.kernel.org/r/20240123064305.2829244-1-surenb@google.com
Fixes: 12214eba1992 ("mm: handle read faults under the VMA lock")
Reported-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
arch/arm/mm/fault.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index e96fb40b9cc3..07565b593ed6 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -298,6 +298,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
goto done;
}
count_vm_vma_lock_event(VMA_LOCK_RETRY);
+ if (fault & VM_FAULT_MAJOR)
+ flags |= FAULT_FLAG_TRIED;
/* Quick path to respond to signals */
if (fault_signal_pending(fault, regs)) {
From 4c2da3188b848d33c26d7f0f8b14f3150331c923 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Fri, 26 Jan 2024 12:25:48 +0900
Subject: [PATCH 322/637] mm/madvise: don't forget to leave lazy MMU mode in
madvise_cold_or_pageout_pte_range()
We need to leave lazy MMU mode before unlocking.
Link: https://lkml.kernel.org/r/20240126032608.355899-1-senozhatsky@chromium.org
Fixes: b2f557a21bc8 ("mm/madvise: add cond_resched() in madvise_cold_or_pageout_pte_range()")
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Jiexun Wang <wangjiexun@tinylab.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/madvise.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed5..cfa5e7288261 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -429,6 +429,7 @@ restart:
if (++batch_count == SWAP_CLUSTER_MAX) {
batch_count = 0;
if (need_resched()) {
+ arch_leave_lazy_mmu_mode();
pte_unmap_unlock(start_pte, ptl);
cond_resched();
goto restart;
From 2e601e1e8e4b330020a346c55ba111d49e0b188e Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Mon, 29 Jan 2024 20:34:38 -0500
Subject: [PATCH 323/637] mm: zswap: fix objcg use-after-free in entry
destruction
In the per-memcg LRU universe, LRU removal uses entry->objcg to determine
which list count needs to be decreased. Drop the objcg reference after
updating the LRU, to fix a possible use-after-free.
Link: https://lkml.kernel.org/r/20240130013438.565167-1-hannes@cmpxchg.org
Fixes: a65b0e7607cc ("zswap: make shrinking memcg-aware")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/zswap.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/mm/zswap.c b/mm/zswap.c
index ca25b676048e..0a94b197ed32 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -536,10 +536,6 @@ static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
*/
static void zswap_free_entry(struct zswap_entry *entry)
{
- if (entry->objcg) {
- obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
- obj_cgroup_put(entry->objcg);
- }
if (!entry->length)
atomic_dec(&zswap_same_filled_pages);
else {
@@ -548,6 +544,10 @@ static void zswap_free_entry(struct zswap_entry *entry)
atomic_dec(&entry->pool->nr_stored);
zswap_pool_put(entry->pool);
}
+ if (entry->objcg) {
+ obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
+ obj_cgroup_put(entry->objcg);
+ }
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
zswap_update_total_size();
From f2076032096775d1bb1af16b6eddbc6534575328 Mon Sep 17 00:00:00 2001
From: John Moon <john@jmoon.dev>
Date: Wed, 31 Jan 2024 03:43:18 +0000
Subject: [PATCH 324/637] mailmap: switch email address for John Moon
Add current email address as QUIC email is no longer active.
Link: https://lkml.kernel.org/r/20240131034311.46706-1-john@jmoon.dev
Signed-off-by: John Moon <john@jmoon.dev>
Acked-by: Trilok Soni <quic_tsoni@quicinc.com>
Cc: Elliot Berman <quic_eberman@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
.mailmap | 1 +
1 file changed, 1 insertion(+)
diff --git a/.mailmap b/.mailmap
index 04998f7bda81..8ae00bd3708a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -289,6 +289,7 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
John Crispin <john@phrozen.org> <blogic@openwrt.org>
John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
John Keeping <john@keeping.me.uk> <john@metanate.com>
+John Moon <john@jmoon.dev> <quic_johmoo@quicinc.com>
John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
John Stultz <johnstul@us.ibm.com>
<jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
From 79d72c68c58784a3e1cd2378669d51bfd0cb7498 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Tue, 30 Jan 2024 22:04:18 +0100
Subject: [PATCH 325/637] fs,hugetlb: fix NULL pointer dereference in
hugetlbs_fill_super
When configuring a hugetlb filesystem via the fsconfig() syscall, there is
a possible NULL dereference in hugetlbfs_fill_super() caused by assigning
NULL to ctx->hstate in hugetlbfs_parse_param() when the requested pagesize
is non valid.
E.g: Taking the following steps:
fd = fsopen("hugetlbfs", FSOPEN_CLOEXEC);
fsconfig(fd, FSCONFIG_SET_STRING, "pagesize", "1024", 0);
fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
Given that the requested "pagesize" is invalid, ctxt->hstate will be replaced
with NULL, losing its previous value, and we will print an error:
...
...
case Opt_pagesize:
ps = memparse(param->string, &rest);
ctx->hstate = h;
if (!ctx->hstate) {
pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
return -EINVAL;
}
return 0;
...
...
This is a problem because later on, we will dereference ctxt->hstate in
hugetlbfs_fill_super()
...
...
sb->s_blocksize = huge_page_size(ctx->hstate);
...
...
Causing below Oops.
Fix this by replacing cxt->hstate value only when then pagesize is known
to be valid.
kernel: hugetlbfs: Unsupported page size 0 MB
kernel: BUG: kernel NULL pointer dereference, address: 0000000000000028
kernel: #PF: supervisor read access in kernel mode
kernel: #PF: error_code(0x0000) - not-present page
kernel: PGD 800000010f66c067 P4D 800000010f66c067 PUD 1b22f8067 PMD 0
kernel: Oops: 0000 [#1] PREEMPT SMP PTI
kernel: CPU: 4 PID: 5659 Comm: syscall Tainted: G E 6.8.0-rc2-default+ #22 5a47c3fef76212addcc6eb71344aabc35190ae8f
kernel: Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0016.D04.1705030402 05/03/2017
kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0
kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28
kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246
kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004
kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000
kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004
kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000
kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400
kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000
kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0
kernel: Call Trace:
kernel: <TASK>
kernel: ? __die_body+0x1a/0x60
kernel: ? page_fault_oops+0x16f/0x4a0
kernel: ? search_bpf_extables+0x65/0x70
kernel: ? fixup_exception+0x22/0x310
kernel: ? exc_page_fault+0x69/0x150
kernel: ? asm_exc_page_fault+0x22/0x30
kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10
kernel: ? hugetlbfs_fill_super+0xb4/0x1a0
kernel: ? hugetlbfs_fill_super+0x28/0x1a0
kernel: ? __pfx_hugetlbfs_fill_super+0x10/0x10
kernel: vfs_get_super+0x40/0xa0
kernel: ? __pfx_bpf_lsm_capable+0x10/0x10
kernel: vfs_get_tree+0x25/0xd0
kernel: vfs_cmd_create+0x64/0xe0
kernel: __x64_sys_fsconfig+0x395/0x410
kernel: do_syscall_64+0x80/0x160
kernel: ? syscall_exit_to_user_mode+0x82/0x240
kernel: ? do_syscall_64+0x8d/0x160
kernel: ? syscall_exit_to_user_mode+0x82/0x240
kernel: ? do_syscall_64+0x8d/0x160
kernel: ? exc_page_fault+0x69/0x150
kernel: entry_SYSCALL_64_after_hwframe+0x6e/0x76
kernel: RIP: 0033:0x7ffbc0cb87c9
kernel: Code: 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 97 96 0d 00 f7 d8 64 89 01 48
kernel: RSP: 002b:00007ffc29d2f388 EFLAGS: 00000206 ORIG_RAX: 00000000000001af
kernel: RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007ffbc0cb87c9
kernel: RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000003
kernel: RBP: 00007ffc29d2f3b0 R08: 0000000000000000 R09: 0000000000000000
kernel: R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000
kernel: R13: 00007ffc29d2f4c0 R14: 0000000000000000 R15: 0000000000000000
kernel: </TASK>
kernel: Modules linked in: rpcsec_gss_krb5(E) auth_rpcgss(E) nfsv4(E) dns_resolver(E) nfs(E) lockd(E) grace(E) sunrpc(E) netfs(E) af_packet(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) intel_rapl_msr(E) intel_rapl_common(E) iTCO_wdt(E) intel_pmc_bxt(E) sb_edac(E) iTCO_vendor_support(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) rfkill(E) ipmi_ssif(E) kvm(E) acpi_ipmi(E) irqbypass(E) pcspkr(E) igb(E) ipmi_si(E) mei_me(E) i2c_i801(E) joydev(E) intel_pch_thermal(E) i2c_smbus(E) dca(E) lpc_ich(E) mei(E) ipmi_devintf(E) ipmi_msghandler(E) acpi_pad(E) tiny_power_button(E) button(E) fuse(E) efi_pstore(E) configfs(E) ip_tables(E) x_tables(E) ext4(E) mbcache(E) jbd2(E) hid_generic(E) usbhid(E) sd_mod(E) t10_pi(E) crct10dif_pclmul(E) crc32_pclmul(E) crc32c_intel(E) polyval_clmulni(E) ahci(E) xhci_pci(E) polyval_generic(E) gf128mul(E) ghash_clmulni_intel(E) sha512_ssse3(E) sha256_ssse3(E) xhci_pci_renesas(E) libahci(E) ehci_pci(E) sha1_ssse3(E) xhci_hcd(E) ehci_hcd(E) libata(E)
kernel: mgag200(E) i2c_algo_bit(E) usbcore(E) wmi(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) scsi_common(E) aesni_intel(E) crypto_simd(E) cryptd(E)
kernel: Unloaded tainted modules: acpi_cpufreq(E):1 fjes(E):1
kernel: CR2: 0000000000000028
kernel: ---[ end trace 0000000000000000 ]---
kernel: RIP: 0010:hugetlbfs_fill_super+0xb4/0x1a0
kernel: Code: 48 8b 3b e8 3e c6 ed ff 48 85 c0 48 89 45 20 0f 84 d6 00 00 00 48 b8 ff ff ff ff ff ff ff 7f 4c 89 e7 49 89 44 24 20 48 8b 03 <8b> 48 28 b8 00 10 00 00 48 d3 e0 49 89 44 24 18 48 8b 03 8b 40 28
kernel: RSP: 0018:ffffbe9960fcbd48 EFLAGS: 00010246
kernel: RAX: 0000000000000000 RBX: ffff9af5272ae780 RCX: 0000000000372004
kernel: RDX: ffffffffffffffff RSI: ffffffffffffffff RDI: ffff9af555e9b000
kernel: RBP: ffff9af52ee66b00 R08: 0000000000000040 R09: 0000000000370004
kernel: R10: ffffbe9960fcbd48 R11: 0000000000000040 R12: ffff9af555e9b000
kernel: R13: ffffffffa66b86c0 R14: ffff9af507d2f400 R15: ffff9af507d2f400
kernel: FS: 00007ffbc0ba4740(0000) GS:ffff9b0bd7000000(0000) knlGS:0000000000000000
kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kernel: CR2: 0000000000000028 CR3: 00000001b1ee0000 CR4: 00000000001506f0
Link: https://lkml.kernel.org/r/20240130210418.3771-1-osalvador@suse.de
Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context")
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/hugetlbfs/inode.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ee13c2ca8ad2..d746866ae3b6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1365,6 +1365,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
{
struct hugetlbfs_fs_context *ctx = fc->fs_private;
struct fs_parse_result result;
+ struct hstate *h;
char *rest;
unsigned long ps;
int opt;
@@ -1409,11 +1410,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
case Opt_pagesize:
ps = memparse(param->string, &rest);
- ctx->hstate = size_to_hstate(ps);
- if (!ctx->hstate) {
+ h = size_to_hstate(ps);
+ if (!h) {
pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
return -EINVAL;
}
+ ctx->hstate = h;
return 0;
case Opt_min_size:
From 27d3969b47cc38810b3fd65d72231940e8671e6c Mon Sep 17 00:00:00 2001
From: Chengming Zhou <zhouchengming@bytedance.com>
Date: Sun, 28 Jan 2024 13:28:49 +0000
Subject: [PATCH 326/637] mm/zswap: don't return LRU_SKIP if we have dropped
lru lock
LRU_SKIP can only be returned if we don't ever dropped lru lock, or we
need to return LRU_RETRY to restart from the head of lru list.
Otherwise, the iteration might continue from a cursor position that was
freed while the locks were dropped.
Actually we may need to introduce another LRU_STOP to really terminate the
ongoing shrinking scan process, when we encounter a warm page already in
the swap cache. The current list_lru implementation doesn't have this
function to early break from __list_lru_walk_one.
Link: https://lkml.kernel.org/r/20240126-zswap-writeback-race-v2-1-b10479847099@bytedance.com
Fixes: b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure")
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Chris Li <chriscli@google.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/zswap.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/mm/zswap.c b/mm/zswap.c
index 0a94b197ed32..350dd2fc8159 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -895,10 +895,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
* into the warmer region. We should terminate shrinking (if we're in the dynamic
* shrinker context).
*/
- if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
- ret = LRU_SKIP;
+ if (writeback_result == -EEXIST && encountered_page_in_swapcache)
*encountered_page_in_swapcache = true;
- }
goto put_unlock;
}
From 6f1f15a5e492082c8082bea56d87852b65588b5c Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linux.dev>
Date: Thu, 1 Feb 2024 10:10:08 +0800
Subject: [PATCH 327/637] MAINTAINERS: Leo Yan has moved
I will lose access to my @linaro.org email address next week, update the
MAINTAINERS file and map it in .mailmap with the new email address.
Link: https://lkml.kernel.org/r/20240201021022.886-1-leo.yan@linux.dev
Signed-off-by: Leo Yan <leo.yan@linux.dev>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
.mailmap | 1 +
MAINTAINERS | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/.mailmap b/.mailmap
index 8ae00bd3708a..ee8f03cc7f72 100644
--- a/.mailmap
+++ b/.mailmap
@@ -345,6 +345,7 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
Leon Romanovsky <leon@kernel.org> <leon@leon.nu>
Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com>
Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
+Leo Yan <leo.yan@linux.dev> <leo.yan@linaro.org>
Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
Linas Vepstas <linas@austin.ibm.com>
Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
diff --git a/MAINTAINERS b/MAINTAINERS
index 960512bec428..95b47e3cee0a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17183,7 +17183,7 @@ R: John Garry <john.g.garry@oracle.com>
R: Will Deacon <will@kernel.org>
R: James Clark <james.clark@arm.com>
R: Mike Leach <mike.leach@linaro.org>
-R: Leo Yan <leo.yan@linaro.org>
+R: Leo Yan <leo.yan@linux.dev>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
F: tools/build/feature/test-libopencsd.c
From 38296afe3c6ee07319e01bb249aa4bb47c07b534 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Wed, 31 Jan 2024 23:56:57 +0900
Subject: [PATCH 328/637] nilfs2: fix hang in nilfs_lookup_dirty_data_buffers()
Syzbot reported a hang issue in migrate_pages_batch() called by mbind()
and nilfs_lookup_dirty_data_buffers() called in the log writer of nilfs2.
While migrate_pages_batch() locks a folio and waits for the writeback to
complete, the log writer thread that should bring the writeback to
completion picks up the folio being written back in
nilfs_lookup_dirty_data_buffers() that it calls for subsequent log
creation and was trying to lock the folio. Thus causing a deadlock.
In the first place, it is unexpected that folios/pages in the middle of
writeback will be updated and become dirty. Nilfs2 adds a checksum to
verify the validity of the log being written and uses it for recovery at
mount, so data changes during writeback are suppressed. Since this is
broken, an unclean shutdown could potentially cause recovery to fail.
Investigation revealed that the root cause is that the wait for writeback
completion in nilfs_page_mkwrite() is conditional, and if the backing
device does not require stable writes, data may be modified without
waiting.
Fix these issues by making nilfs_page_mkwrite() wait for writeback to
finish regardless of the stable write requirement of the backing device.
Link: https://lkml.kernel.org/r/20240131145657.4209-1-konishi.ryusuke@gmail.com
Fixes: 1d1d1a767206 ("mm: only enforce stable page writes if the backing device requires it")
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Reported-by: syzbot+ee2ae68da3b22d04cd8d@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/00000000000047d819061004ad6c@google.com
Tested-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/nilfs2/file.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index bec33b89a075..0e3fc5ba33c7 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -107,7 +107,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
nilfs_transaction_commit(inode->i_sb);
mapped:
- folio_wait_stable(folio);
+ /*
+ * Since checksumming including data blocks is performed to determine
+ * the validity of the log to be written and used for recovery, it is
+ * necessary to wait for writeback to finish here, regardless of the
+ * stable write requirement of the backing device.
+ */
+ folio_wait_writeback(folio);
out:
sb_end_pagefault(inode->i_sb);
return vmf_fs_error(ret);
From b9e4bc1046d20e0623a80660ef8627448056f817 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 2 Feb 2024 11:19:56 -0800
Subject: [PATCH 329/637] mm/damon/sysfs-schemes: fix wrong DAMOS tried regions
update timeout setup
DAMON sysfs interface's update_schemes_tried_regions command has a timeout
of two apply intervals of the DAMOS scheme. Having zero value DAMOS
scheme apply interval means it will use the aggregation interval as the
value. However, the timeout setup logic is mistakenly using the sampling
interval insted of the aggregartion interval for the case. This could
cause earlier-than-expected timeout of the command. Fix it.
Link: https://lkml.kernel.org/r/20240202191956.88791-1-sj@kernel.org
Fixes: 7d6fa31a2fd7 ("mm/damon/sysfs-schemes: add timeout for update_schemes_tried_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/damon/sysfs-schemes.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 8dbaac6e5c2d..dd2fb5127009 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2194,7 +2194,7 @@ static void damos_tried_regions_init_upd_status(
sysfs_regions->upd_timeout_jiffies = jiffies +
2 * usecs_to_jiffies(scheme->apply_interval_us ?
scheme->apply_interval_us :
- ctx->attrs.sample_interval);
+ ctx->attrs.aggr_interval);
}
}
From 5bc09b397cbf1221f8a8aacb1152650c9195b02b Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Sun, 4 Feb 2024 01:16:45 +0900
Subject: [PATCH 330/637] nilfs2: fix potential bug in end_buffer_async_write
According to a syzbot report, end_buffer_async_write(), which handles the
completion of block device writes, may detect abnormal condition of the
buffer async_write flag and cause a BUG_ON failure when using nilfs2.
Nilfs2 itself does not use end_buffer_async_write(). But, the async_write
flag is now used as a marker by commit 7f42ec394156 ("nilfs2: fix issue
with race condition of competition between segments for dirty blocks") as
a means of resolving double list insertion of dirty blocks in
nilfs_lookup_dirty_data_buffers() and nilfs_lookup_node_buffers() and the
resulting crash.
This modification is safe as long as it is used for file data and b-tree
node blocks where the page caches are independent. However, it was
irrelevant and redundant to also introduce async_write for segment summary
and super root blocks that share buffers with the backing device. This
led to the possibility that the BUG_ON check in end_buffer_async_write
would fail as described above, if independent writebacks of the backing
device occurred in parallel.
The use of async_write for segment summary buffers has already been
removed in a previous change.
Fix this issue by removing the manipulation of the async_write flag for
the remaining super root block buffer.
Link: https://lkml.kernel.org/r/20240203161645.4992-1-konishi.ryusuke@gmail.com
Fixes: 7f42ec394156 ("nilfs2: fix issue with race condition of competition between segments for dirty blocks")
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Reported-by: syzbot+5c04210f7c7f897c1e7f@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/00000000000019a97c05fd42f8c8@google.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/nilfs2/segment.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 2590a0860eab..2bfb08052d39 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1703,7 +1703,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- set_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_folio != bd_folio) {
folio_lock(bd_folio);
@@ -1714,6 +1713,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
}
break;
}
+ set_buffer_async_write(bh);
if (bh->b_folio != fs_folio) {
nilfs_begin_folio_io(fs_folio);
fs_folio = bh->b_folio;
@@ -1800,7 +1800,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- clear_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
clear_buffer_uptodate(bh);
if (bh->b_folio != bd_folio) {
@@ -1809,6 +1808,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
}
break;
}
+ clear_buffer_async_write(bh);
if (bh->b_folio != fs_folio) {
nilfs_end_folio_io(fs_folio, err);
fs_folio = bh->b_folio;
@@ -1896,8 +1896,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
BIT(BH_NILFS_Redirected));
- set_mask_bits(&bh->b_state, clear_bits, set_bits);
if (bh == segbuf->sb_super_root) {
+ set_buffer_uptodate(bh);
+ clear_buffer_dirty(bh);
if (bh->b_folio != bd_folio) {
folio_end_writeback(bd_folio);
bd_folio = bh->b_folio;
@@ -1905,6 +1906,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
update_sr = true;
break;
}
+ set_mask_bits(&bh->b_state, clear_bits, set_bits);
if (bh->b_folio != fs_folio) {
nilfs_end_folio_io(fs_folio, 0);
fs_folio = bh->b_folio;
From ddc7d4c584704666fe7088bbd9ec2d72d0f63e65 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 1 Feb 2024 09:55:32 -0800
Subject: [PATCH 331/637] drm/xe: Fix loop in vm_bind_ioctl_ops_unwind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The logic for the unwind loop is incorrect resulting in an infinite
loop. Fix to unwind to go from the last operations list to he first.
Fixes: 617eebb9c480 ("drm/xe: Fix array of binds")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201175532.2303168-1-matthew.brost@intel.com
(cherry picked from commit 3acc1ff1a72fce00cdbd3ef1c27108a967fd5616)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30db264d34a3..d45cbf75d203 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2669,7 +2669,7 @@ static void vm_bind_ioctl_ops_unwind(struct xe_vm *vm,
{
int i;
- for (i = num_ops_list - 1; i; ++i) {
+ for (i = num_ops_list - 1; i >= 0; --i) {
struct drm_gpuva_ops *__ops = ops[i];
struct drm_gpuva_op *__op;
From fc29b6d5ab5395dcb9f35de71e0347f3a6bca542 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 31 Jan 2024 16:48:48 -0800
Subject: [PATCH 332/637] drm/xe: Take a reference in
xe_exec_queue_last_fence_get()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Take a reference in xe_exec_queue_last_fence_get(). Also fix a reference
counting underflow bug VM bind and unbind.
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-2-matthew.brost@intel.com
(cherry picked from commit a856b67a84169e065ebbeee50258936b1eacc9eb)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_exec_queue.c | 8 ++++++--
drivers/gpu/drm/xe/xe_migrate.c | 5 ++++-
drivers/gpu/drm/xe/xe_sched_job.c | 1 -
drivers/gpu/drm/xe/xe_sync.c | 2 --
drivers/gpu/drm/xe/xe_vm.c | 1 +
5 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index bcfc4127c7c5..254b1d3af4cb 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -926,20 +926,24 @@ void xe_exec_queue_last_fence_put_unlocked(struct xe_exec_queue *q)
* @q: The exec queue
* @vm: The VM the engine does a bind or exec for
*
- * Get last fence, does not take a ref
+ * Get last fence, takes a ref
*
* Returns: last fence if not signaled, dma fence stub if signaled
*/
struct dma_fence *xe_exec_queue_last_fence_get(struct xe_exec_queue *q,
struct xe_vm *vm)
{
+ struct dma_fence *fence;
+
xe_exec_queue_last_fence_lockdep_assert(q, vm);
if (q->last_fence &&
test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &q->last_fence->flags))
xe_exec_queue_last_fence_put(q, vm);
- return q->last_fence ? q->last_fence : dma_fence_get_stub();
+ fence = q->last_fence ? q->last_fence : dma_fence_get_stub();
+ dma_fence_get(fence);
+ return fence;
}
/**
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5c6c54624252..0cc31837ef26 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1204,8 +1204,11 @@ static bool no_in_syncs(struct xe_vm *vm, struct xe_exec_queue *q,
}
if (q) {
fence = xe_exec_queue_last_fence_get(q, vm);
- if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+ if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+ dma_fence_put(fence);
return false;
+ }
+ dma_fence_put(fence);
}
return true;
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 01106a1156ad..4e2ccad0e52f 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -274,7 +274,6 @@ int xe_sched_job_last_fence_add_dep(struct xe_sched_job *job, struct xe_vm *vm)
struct dma_fence *fence;
fence = xe_exec_queue_last_fence_get(job->q, vm);
- dma_fence_get(fence);
return drm_sched_job_add_dependency(&job->drm, fence);
}
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index e4c220cf9115..aab92bee1d7c 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -307,7 +307,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
/* Easy case... */
if (!num_in_fence) {
fence = xe_exec_queue_last_fence_get(q, vm);
- dma_fence_get(fence);
return fence;
}
@@ -322,7 +321,6 @@ xe_sync_in_fence_get(struct xe_sync_entry *sync, int num_sync,
}
}
fences[current_fence++] = xe_exec_queue_last_fence_get(q, vm);
- dma_fence_get(fences[current_fence - 1]);
cf = dma_fence_array_create(num_in_fence, fences,
vm->composite_fence_ctx,
vm->composite_fence_seqno++,
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d45cbf75d203..96b1833c0e8c 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1984,6 +1984,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma,
xe_exec_queue_last_fence_get(wait_exec_queue, vm);
xe_sync_entry_signal(&syncs[i], NULL, fence);
+ dma_fence_put(fence);
}
}
From 21abf108a062fa0323077b5ba3d26e2c0bba9232 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 31 Jan 2024 16:48:49 -0800
Subject: [PATCH 333/637] drm/xe: Pick correct userptr VMA to repin on REMAP op
failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A REMAP op is composed of 3 VMA's - unmap, prev map, and next map. When
op_execute fails with -EAGAIN we need to update the local VMA pointer to
the current op state and then repin the VMA if it is a userptr.
Fixes a failure seen in xe_vm.munmap-style-unbind-userptr-one-partial.
Fixes: b06d47be7c83 ("drm/xe: Port Xe to GPUVA")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240201004849.2219558-3-matthew.brost@intel.com
(cherry picked from commit 447f74d223b4f6cbab74963bf1099050c15374ce)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 22 +++++++++++++++++-----
1 file changed, 17 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 96b1833c0e8c..ca11f8381115 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2531,13 +2531,25 @@ retry_userptr:
}
drm_exec_fini(&exec);
- if (err == -EAGAIN && xe_vma_is_userptr(vma)) {
+ if (err == -EAGAIN) {
lockdep_assert_held_write(&vm->lock);
- err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
- if (!err)
- goto retry_userptr;
- trace_xe_vma_fail(vma);
+ if (op->base.op == DRM_GPUVA_OP_REMAP) {
+ if (!op->remap.unmap_done)
+ vma = gpuva_to_vma(op->base.remap.unmap->va);
+ else if (op->remap.prev)
+ vma = op->remap.prev;
+ else
+ vma = op->remap.next;
+ }
+
+ if (xe_vma_is_userptr(vma)) {
+ err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+ if (!err)
+ goto retry_userptr;
+
+ trace_xe_vma_fail(vma);
+ }
}
return err;
From 90773aaf9129ea6f47915bd3c47da261abe6a447 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 3 Jan 2024 12:48:02 +0100
Subject: [PATCH 334/637] drm/xe: circumvent bogus stringop-overflow warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
gcc-13 warns about an array overflow that it sees but that is
prevented by the "asid % NUM_PF_QUEUE" calculation:
drivers/gpu/drm/xe/xe_gt_pagefault.c: In function 'xe_guc_pagefault_handler':
include/linux/fortify-string.h:57:33: error: writing 16 bytes into a region of size 0 [-Werror=stringop-overflow=]
include/linux/fortify-string.h:689:26: note: in expansion of macro '__fortify_memcpy_chk'
689 | #define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \
| ^~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/xe/xe_gt_pagefault.c:341:17: note: in expansion of macro 'memcpy'
341 | memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
| ^~~~~~
drivers/gpu/drm/xe/xe_gt_types.h:102:25: note: at offset [1144, 265324] into destination object 'tile' of size 8
I found that rewriting the assignment using pointer addition rather than the
equivalent array index calculation prevents the warning, so use that instead.
I sent a bug report against gcc for the false positive warning.
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113214
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240103114819.2913937-1-arnd@kernel.org
(cherry picked from commit 774ef5dfc95578a9079426d5106076dcd59c4dfa)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_gt_pagefault.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 9c2fe1697d6e..73f08f1924df 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -335,7 +335,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
return -EPROTO;
asid = FIELD_GET(PFD_ASID, msg[1]);
- pf_queue = >->usm.pf_queue[asid % NUM_PF_QUEUE];
+ pf_queue = gt->usm.pf_queue + (asid % NUM_PF_QUEUE);
spin_lock_irqsave(&pf_queue->lock, flags);
full = pf_queue_full(pf_queue);
From 3aa3c5c249086ffc920e8f6d6a15bdd441153d45 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 1 Feb 2024 19:34:40 -0800
Subject: [PATCH 335/637] drm/xe: Map both mem.kernel_bb_pool and usm.bb_pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
For integrated devices we need to map both mem.kernel_bb_pool and
usm.bb_pool to be able to run batches from both pools.
Fixes: a682b6a42d4d ("drm/xe: Support device page faults on integrated platforms")
Tested-by: Brian Welty <brian.welty@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Brian Welty <brian.welty@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202033440.2351862-1-matthew.brost@intel.com
(cherry picked from commit 72f86ed3c88933d6fa09b036de93621ea71097a7)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_gt.c | 5 ++++-
drivers/gpu/drm/xe/xe_migrate.c | 23 ++++++++++++++++++-----
2 files changed, 22 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 3af2adec1295..35474ddbaf97 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -437,7 +437,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
* USM has its only SA pool to non-block behind user operations
*/
if (gt_to_xe(gt)->info.has_usm) {
- gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt), SZ_1M, 16);
+ struct xe_device *xe = gt_to_xe(gt);
+
+ gt->usm.bb_pool = xe_sa_bo_manager_init(gt_to_tile(gt),
+ IS_DGFX(xe) ? SZ_1M : SZ_512K, 16);
if (IS_ERR(gt->usm.bb_pool)) {
err = PTR_ERR(gt->usm.bb_pool);
goto err_force_wake;
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 0cc31837ef26..70480c305602 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -170,11 +170,6 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
if (!IS_DGFX(xe)) {
/* Write out batch too */
m->batch_base_ofs = NUM_PT_SLOTS * XE_PAGE_SIZE;
- if (xe->info.has_usm) {
- batch = tile->primary_gt->usm.bb_pool->bo;
- m->usm_batch_base_ofs = m->batch_base_ofs;
- }
-
for (i = 0; i < batch->size;
i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
XE_PAGE_SIZE) {
@@ -185,6 +180,24 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
entry);
level++;
}
+ if (xe->info.has_usm) {
+ xe_tile_assert(tile, batch->size == SZ_1M);
+
+ batch = tile->primary_gt->usm.bb_pool->bo;
+ m->usm_batch_base_ofs = m->batch_base_ofs + SZ_1M;
+ xe_tile_assert(tile, batch->size == SZ_512K);
+
+ for (i = 0; i < batch->size;
+ i += vm->flags & XE_VM_FLAG_64K ? XE_64K_PAGE_SIZE :
+ XE_PAGE_SIZE) {
+ entry = vm->pt_ops->pte_encode_bo(batch, i,
+ pat_index, 0);
+
+ xe_map_wr(xe, &bo->vmap, map_ofs + level * 8, u64,
+ entry);
+ level++;
+ }
+ }
} else {
u64 batch_addr = xe_bo_addr(batch, 0, XE_PAGE_SIZE);
From 11572b3f68d9933fef5c1afef4c20041701d8025 Mon Sep 17 00:00:00 2001
From: Xiaoming Wang <xiaoming.wang@intel.com>
Date: Fri, 2 Feb 2024 13:56:58 -0800
Subject: [PATCH 336/637] drm/xe/display: Fix memleak in display initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
intel_power_domains_init is called twice in xe_device_probe:
1) intel_power_domains_init()
xe_display_init_nommio()
xe_device_probe()
2) intel_power_domains_init()
intel_display_driver_probe_noirq()
xe_display_init_noirq()
xe_device_probe()
It needs remove one to avoid power_domains->power_wells double malloc.
unreferenced object 0xffff88811150ee00 (size 512):
comm "systemd-udevd", pid 506, jiffies 4294674198 (age 3605.560s)
hex dump (first 32 bytes):
10 b4 9d a0 ff ff ff ff ff ff ff ff ff ff ff ff ................
ff ff ff ff ff ff ff ff 00 00 00 00 00 00 00 00 ................
backtrace:
[<ffffffff8134b901>] __kmem_cache_alloc_node+0x1c1/0x2b0
[<ffffffff812c98b2>] __kmalloc+0x52/0x150
[<ffffffffa08b0033>] __set_power_wells+0xc3/0x360 [xe]
[<ffffffffa08562fc>] xe_display_init_nommio+0x4c/0x70 [xe]
[<ffffffffa07f0d1c>] xe_device_probe+0x3c/0x5a0 [xe]
[<ffffffffa082e48f>] xe_pci_probe+0x33f/0x5a0 [xe]
[<ffffffff817f2187>] local_pci_probe+0x47/0xa0
[<ffffffff817f3db3>] pci_device_probe+0xc3/0x1f0
[<ffffffff8192f2a2>] really_probe+0x1a2/0x410
[<ffffffff8192f598>] __driver_probe_device+0x78/0x160
[<ffffffff8192f6ae>] driver_probe_device+0x1e/0x90
[<ffffffff8192f92a>] __driver_attach+0xda/0x1d0
[<ffffffff8192c95c>] bus_for_each_dev+0x7c/0xd0
[<ffffffff8192e159>] bus_add_driver+0x119/0x220
[<ffffffff81930d00>] driver_register+0x60/0x120
[<ffffffffa05e50a0>] 0xffffffffa05e50a0
The call to intel_power_domains_cleanup() needs to stay where it is for
now. The main issue is that while the init is called by the display
side, shared by i915 and xe, the cleanup is called by a non-shared code
path. Fixing that will be done as a separate commit.
Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Signed-off-by: Xiaoming Wang <xiaoming.wang@intel.com>
[ reword commit message and explain why the fini needs to stay
where it is ]
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202215658.561298-1-lucas.demarchi@intel.com
(cherry picked from commit 86c99abb5f1b6fcd69fb268eeb2e34cb7c4f355c)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_display.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_display.c b/drivers/gpu/drm/xe/xe_display.c
index 74391d9b11ae..e4db069f0db3 100644
--- a/drivers/gpu/drm/xe/xe_display.c
+++ b/drivers/gpu/drm/xe/xe_display.c
@@ -134,8 +134,6 @@ static void xe_display_fini_nommio(struct drm_device *dev, void *dummy)
int xe_display_init_nommio(struct xe_device *xe)
{
- int err;
-
if (!xe->info.enable_display)
return 0;
@@ -145,10 +143,6 @@ int xe_display_init_nommio(struct xe_device *xe)
/* This must be called before any calls to HAS_PCH_* */
intel_detect_pch(xe);
- err = intel_power_domains_init(xe);
- if (err)
- return err;
-
return drmm_add_action_or_reset(&xe->drm, xe_display_fini_nommio, xe);
}
From 95c058c8ef1d5d9e39ab2039a5eea4d5b93f4117 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 5 Feb 2024 15:17:14 -0800
Subject: [PATCH 337/637] drm/xe: Assume large page size if VMA not yet bound
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The calculation to determine max page size of a VMA during a REMAP
operations assumes the VMA has been bound. This assumption is not true
if the VMA is from an eariler operation in an array of binds. If a VMA
has not been bound use the maximum page size which will ensure the
previous / next REMAP operations are not incorrectly skipped.
Fixes: 8f33b4f054fc ("drm/xe: Avoid doing rebinds")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240205231714.2956225-1-matthew.brost@intel.com
(cherry picked from commit 5ad6af5c91e9b942c44b657122270d935db3a813)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ca11f8381115..99f151d73154 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2200,8 +2200,10 @@ static u64 xe_vma_max_pte_size(struct xe_vma *vma)
return SZ_1G;
else if (vma->gpuva.flags & XE_VMA_PTE_2M)
return SZ_2M;
+ else if (vma->gpuva.flags & XE_VMA_PTE_4K)
+ return SZ_4K;
- return SZ_4K;
+ return SZ_1G; /* Uninitialized, used max size */
}
static u64 xe_vma_set_pte_size(struct xe_vma *vma, u64 size)
From 9e3fc1d65d4e8cf302e289847ab165ad9358fdb2 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 2 Feb 2024 17:14:36 +0000
Subject: [PATCH 338/637] drm/xe/vm: don't ignore error when in_kthread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If GUP fails and we are in_kthread, we can have pinned = 0 and ret = 0.
If that happens we call sg_alloc_append_table_from_pages() with n_pages
= 0, which is not well behaved and can trigger:
kernel BUG at include/linux/scatterlist.h:115!
depending on if the pages array happens to be zeroed or not. Even if we
don't hit that it crashes later when trying to dma_map the returned
table.
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202171435.427630-2-matthew.auld@intel.com
(cherry picked from commit 8087199cd5951c1eba26003b3e4296dbb2110adf)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 99f151d73154..a9df89413155 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -114,11 +114,8 @@ retry:
num_pages - pinned,
read_only ? 0 : FOLL_WRITE,
&pages[pinned]);
- if (ret < 0) {
- if (in_kthread)
- ret = 0;
+ if (ret < 0)
break;
- }
pinned += ret;
ret = 0;
From bf4c27b8267d7848bb81fd41e6aa07aa662f07fb Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 5 Feb 2024 20:50:10 -0800
Subject: [PATCH 339/637] drm/xe: Remove TEST_VM_ASYNC_OPS_ERROR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
TEST_VM_ASYNC_OPS_ERROR is broken and unused. Remove for now and will
pull back in a later time when it is used, fixed, and properly hidden
behind a Kconfig option. Also fixup the supported flags value.
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240206045010.2981051-1-matthew.brost@intel.com
(cherry picked from commit d9890c028d66a9e1ee3cccaa081ab5aedcbfe431)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 28 +---------------------------
drivers/gpu/drm/xe/xe_vm_types.h | 8 --------
2 files changed, 1 insertion(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a9df89413155..865e10d0a06a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -37,8 +37,6 @@
#include "generated/xe_wa_oob.h"
#include "xe_wa.h"
-#define TEST_VM_ASYNC_OPS_ERROR
-
static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
{
return vm->gpuvm.r_obj;
@@ -2062,7 +2060,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
struct drm_gem_object *obj = bo ? &bo->ttm.base : NULL;
struct drm_gpuva_ops *ops;
struct drm_gpuva_op *__op;
- struct xe_vma_op *op;
struct drm_gpuvm_bo *vm_bo;
int err;
@@ -2109,15 +2106,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
if (IS_ERR(ops))
return ops;
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- if (operation & FORCE_ASYNC_OP_ERROR) {
- op = list_first_entry_or_null(&ops->list, struct xe_vma_op,
- base.entry);
- if (op)
- op->inject_error = true;
- }
-#endif
-
drm_gpuva_for_each_op(__op, ops) {
struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
@@ -2560,13 +2548,6 @@ static int xe_vma_op_execute(struct xe_vm *vm, struct xe_vma_op *op)
lockdep_assert_held_write(&vm->lock);
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- if (op->inject_error) {
- op->inject_error = false;
- return -ENOMEM;
- }
-#endif
-
switch (op->base.op) {
case DRM_GPUVA_OP_MAP:
ret = __xe_vma_op_execute(vm, op->map.vma, op);
@@ -2726,16 +2707,9 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm,
return 0;
}
-#ifdef TEST_VM_ASYNC_OPS_ERROR
-#define SUPPORTED_FLAGS \
- (FORCE_ASYNC_OP_ERROR | DRM_XE_VM_BIND_FLAG_READONLY | \
- DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | 0xffff)
-#else
#define SUPPORTED_FLAGS \
(DRM_XE_VM_BIND_FLAG_READONLY | \
- DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL | \
- 0xffff)
-#endif
+ DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL)
#define XE_64K_PAGE_MASK 0xffffull
#define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP)
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 1fec66ae2eb2..5ac9c5bebabc 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,9 +21,6 @@ struct xe_bo;
struct xe_sync_entry;
struct xe_vm;
-#define TEST_VM_ASYNC_OPS_ERROR
-#define FORCE_ASYNC_OP_ERROR BIT(31)
-
#define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS
#define XE_VMA_DESTROYED (DRM_GPUVA_USERBITS << 1)
#define XE_VMA_ATOMIC_PTE_BIT (DRM_GPUVA_USERBITS << 2)
@@ -360,11 +357,6 @@ struct xe_vma_op {
/** @flags: operation flags */
enum xe_vma_op_flags flags;
-#ifdef TEST_VM_ASYNC_OPS_ERROR
- /** @inject_error: inject error to test async op error handling */
- bool inject_error;
-#endif
-
union {
/** @map: VMA map operation specific data */
struct xe_vma_op_map map;
From ab0beafd52b98dfb8b8244b2c6794efbc87478db Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 2 Feb 2024 10:09:34 +0100
Subject: [PATCH 340/637] netfilter: nft_set_pipapo: remove static in
nft_pipapo_get()
This has slipped through when reducing memory footprint for set
elements, remove it.
Fixes: 9dad402b89e8 ("netfilter: nf_tables: expose opaque set element as struct nft_elem_priv")
Reported-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_pipapo.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index efd523496be4..f24ecdaa1c1e 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -603,7 +603,7 @@ static struct nft_elem_priv *
nft_pipapo_get(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem, unsigned int flags)
{
- static struct nft_pipapo_elem *e;
+ struct nft_pipapo_elem *e;
e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
nft_genmask_cur(net));
From 2526dffc6d65cffa32b88556bd68e4e72e889a55 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 5 Feb 2024 11:22:29 +0100
Subject: [PATCH 341/637] gpio: remove GPIO device from the list
unconditionally in error path
Since commit 48e1b4d369cf ("gpiolib: remove the GPIO device from the list
when it's unregistered") we remove the GPIO device entry from the global
list (used to order devices by their GPIO ranges) when unregistering the
chip, not when releasing the device. It will not happen when the last
reference is put anymore. This means, we need to remove it in error path
in gpiochip_add_data_with_key() unconditionally, without checking if the
device's .release() callback is set.
Fixes: 48e1b4d369cf ("gpiolib: remove the GPIO device from the list when it's unregistered")
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpiolib.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 44c8f5743a24..8b3a0f45b574 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1005,15 +1005,15 @@ err_remove_of_chip:
err_free_gpiochip_mask:
gpiochip_remove_pin_ranges(gc);
gpiochip_free_valid_mask(gc);
+err_remove_from_list:
+ spin_lock_irqsave(&gpio_lock, flags);
+ list_del(&gdev->list);
+ spin_unlock_irqrestore(&gpio_lock, flags);
if (gdev->dev.release) {
/* release() has been registered by gpiochip_setup_dev() */
gpio_device_put(gdev);
goto err_print_message;
}
-err_remove_from_list:
- spin_lock_irqsave(&gpio_lock, flags);
- list_del(&gdev->list);
- spin_unlock_irqrestore(&gpio_lock, flags);
err_free_label:
kfree_const(gdev->label);
err_free_descs:
From 9def04e759caa5a3d741891037ae99f81e2fff01 Mon Sep 17 00:00:00 2001
From: Sinthu Raja <sinthu.raja@ti.com>
Date: Tue, 6 Feb 2024 06:29:27 +0530
Subject: [PATCH 342/637] net: ethernet: ti: cpsw_new: enable mac_managed_pm to
fix mdio
The below commit introduced a WARN when phy state is not in the states:
PHY_HALTED, PHY_READY and PHY_UP.
commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
When cpsw_new resumes, there have port in PHY_NOLINK state, so the below
warning comes out. Set mac_managed_pm be true to tell mdio that the phy
resume/suspend is managed by the mac, to fix the following warning:
WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144
CPU: 0 PID: 965 Comm: sh Tainted: G O 6.1.46-g247b2535b2 #1
Hardware name: Generic AM33XX (Flattened Device Tree)
unwind_backtrace from show_stack+0x18/0x1c
show_stack from dump_stack_lvl+0x24/0x2c
dump_stack_lvl from __warn+0x84/0x15c
__warn from warn_slowpath_fmt+0x1a8/0x1c8
warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144
mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140
dpm_run_callback from device_resume+0xb8/0x2b8
device_resume from dpm_resume+0x144/0x314
dpm_resume from dpm_resume_end+0x14/0x20
dpm_resume_end from suspend_devices_and_enter+0xd0/0x924
suspend_devices_and_enter from pm_suspend+0x2e0/0x33c
pm_suspend from state_store+0x74/0xd0
state_store from kernfs_fop_write_iter+0x104/0x1ec
kernfs_fop_write_iter from vfs_write+0x1b8/0x358
vfs_write from ksys_write+0x78/0xf8
ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe094dfa8 to 0xe094dff0)
dfa0: 00000004 005c3fb8 00000001 005c3fb8 00000004 00000001
dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000
dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66
Cc: <stable@vger.kernel.org> # v6.0+
Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM")
Signed-off-by: Sinthu Raja <sinthu.raja@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/ti/cpsw_new.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 498c50c6d1a7..087dcb67505a 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -773,6 +773,9 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
slave->slave_num);
return;
}
+
+ phy->mac_managed_pm = true;
+
slave->phy = phy;
phy_attached_info(slave->phy);
From bc4ce46b1e3d1da4309405cd4afc7c0fcddd0b90 Mon Sep 17 00:00:00 2001
From: Sinthu Raja <sinthu.raja@ti.com>
Date: Tue, 6 Feb 2024 06:29:28 +0530
Subject: [PATCH 343/637] net: ethernet: ti: cpsw: enable mac_managed_pm to fix
mdio
The below commit introduced a WARN when phy state is not in the states:
PHY_HALTED, PHY_READY and PHY_UP.
commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
When cpsw resumes, there have port in PHY_NOLINK state, so the below
warning comes out. Set mac_managed_pm be true to tell mdio that the phy
resume/suspend is managed by the mac, to fix the following warning:
WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144
CPU: 0 PID: 965 Comm: sh Tainted: G O 6.1.46-g247b2535b2 #1
Hardware name: Generic AM33XX (Flattened Device Tree)
unwind_backtrace from show_stack+0x18/0x1c
show_stack from dump_stack_lvl+0x24/0x2c
dump_stack_lvl from __warn+0x84/0x15c
__warn from warn_slowpath_fmt+0x1a8/0x1c8
warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144
mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140
dpm_run_callback from device_resume+0xb8/0x2b8
device_resume from dpm_resume+0x144/0x314
dpm_resume from dpm_resume_end+0x14/0x20
dpm_resume_end from suspend_devices_and_enter+0xd0/0x924
suspend_devices_and_enter from pm_suspend+0x2e0/0x33c
pm_suspend from state_store+0x74/0xd0
state_store from kernfs_fop_write_iter+0x104/0x1ec
kernfs_fop_write_iter from vfs_write+0x1b8/0x358
vfs_write from ksys_write+0x78/0xf8
ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe094dfa8 to 0xe094dff0)
dfa0: 00000004 005c3fb8 00000001 005c3fb8 00000004 00000001
dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000
dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66
Cc: <stable@vger.kernel.org> # v6.0+
Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
Fixes: fba863b81604 ("net: phy: make PHY PM ops a no-op if MAC driver manages PHY PM")
Signed-off-by: Sinthu Raja <sinthu.raja@ti.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/ti/cpsw.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ea85c6dd5484..c0a5abd8d9a8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
}
}
+ phy->mac_managed_pm = true;
+
slave->phy = phy;
phy_attached_info(slave->phy);
From db010ff6700f24f96e91ed56ca29cb69335008ef Mon Sep 17 00:00:00 2001
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: Tue, 6 Feb 2024 08:10:00 +0530
Subject: [PATCH 344/637] octeontx2-af: Initialize maps.
kmalloc_array() without __GFP_ZERO flag does not initialize
memory to zero. This causes issues. Use kcalloc() for maps and
bitmap_zalloc() for bitmaps.
Fixes: dd7842878633 ("octeontx2-af: Add new devlink param to configure maximum usable NIX block LFs")
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reviewed-by: Brett Creeley <bcreeley@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240206024000.1070260-1-rkannoth@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
.../ethernet/marvell/octeontx2/af/rvu_npc.c | 31 +++++++++----------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 167145bdcb75..8cfd74ad991c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -1850,8 +1850,8 @@ void npc_mcam_rsrcs_deinit(struct rvu *rvu)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
- kfree(mcam->bmap);
- kfree(mcam->bmap_reverse);
+ bitmap_free(mcam->bmap);
+ bitmap_free(mcam->bmap_reverse);
kfree(mcam->entry2pfvf_map);
kfree(mcam->cntr2pfvf_map);
kfree(mcam->entry2cntr_map);
@@ -1904,21 +1904,20 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
/* Allocate bitmaps for managing MCAM entries */
- mcam->bmap = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
- sizeof(long), GFP_KERNEL);
+ mcam->bmap = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
if (!mcam->bmap)
return -ENOMEM;
- mcam->bmap_reverse = kmalloc_array(BITS_TO_LONGS(mcam->bmap_entries),
- sizeof(long), GFP_KERNEL);
+ mcam->bmap_reverse = bitmap_zalloc(mcam->bmap_entries, GFP_KERNEL);
if (!mcam->bmap_reverse)
goto free_bmap;
mcam->bmap_fcnt = mcam->bmap_entries;
/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
- mcam->entry2pfvf_map = kmalloc_array(mcam->bmap_entries,
- sizeof(u16), GFP_KERNEL);
+ mcam->entry2pfvf_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+ GFP_KERNEL);
+
if (!mcam->entry2pfvf_map)
goto free_bmap_reverse;
@@ -1941,21 +1940,21 @@ int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
if (err)
goto free_entry_map;
- mcam->cntr2pfvf_map = kmalloc_array(mcam->counters.max,
- sizeof(u16), GFP_KERNEL);
+ mcam->cntr2pfvf_map = kcalloc(mcam->counters.max, sizeof(u16),
+ GFP_KERNEL);
if (!mcam->cntr2pfvf_map)
goto free_cntr_bmap;
/* Alloc memory for MCAM entry to counter mapping and for tracking
* counter's reference count.
*/
- mcam->entry2cntr_map = kmalloc_array(mcam->bmap_entries,
- sizeof(u16), GFP_KERNEL);
+ mcam->entry2cntr_map = kcalloc(mcam->bmap_entries, sizeof(u16),
+ GFP_KERNEL);
if (!mcam->entry2cntr_map)
goto free_cntr_map;
- mcam->cntr_refcnt = kmalloc_array(mcam->counters.max,
- sizeof(u16), GFP_KERNEL);
+ mcam->cntr_refcnt = kcalloc(mcam->counters.max, sizeof(u16),
+ GFP_KERNEL);
if (!mcam->cntr_refcnt)
goto free_entry_cntr_map;
@@ -1988,9 +1987,9 @@ free_cntr_bmap:
free_entry_map:
kfree(mcam->entry2pfvf_map);
free_bmap_reverse:
- kfree(mcam->bmap_reverse);
+ bitmap_free(mcam->bmap_reverse);
free_bmap:
- kfree(mcam->bmap);
+ bitmap_free(mcam->bmap);
return -ENOMEM;
}
From 27c5a095e2518975e20a10102908ae8231699879 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Sun, 4 Feb 2024 16:26:42 +0100
Subject: [PATCH 345/637] netfilter: ipset: Missing gc cancellations fixed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The patch fdb8e12cc2cc ("netfilter: ipset: fix performance regression
in swap operation") missed to add the calls to gc cancellations
at the error path of create operations and at module unload. Also,
because the half of the destroy operations now executed by a
function registered by call_rcu(), neither NFNL_SUBSYS_IPSET mutex
or rcu read lock is held and therefore the checking of them results
false warnings.
Fixes: 97f7cf1cd80e ("netfilter: ipset: fix performance regression in swap operation")
Reported-by: syzbot+52bbc0ad036f6f0d4a25@syzkaller.appspotmail.com
Reported-by: Brad Spengler <spender@grsecurity.net>
Reported-by: Стас Ничипорович <stasn77@gmail.com>
Tested-by: Brad Spengler <spender@grsecurity.net>
Tested-by: Стас Ничипорович <stasn77@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/ipset/ip_set_core.c | 2 ++
net/netfilter/ipset/ip_set_hash_gen.h | 4 ++--
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index bcaad9c009fe..3184cc6be4c9 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1154,6 +1154,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info,
return ret;
cleanup:
+ set->variant->cancel_gc(set);
set->variant->destroy(set);
put_out:
module_put(set->type->me);
@@ -2378,6 +2379,7 @@ ip_set_net_exit(struct net *net)
set = ip_set(inst, i);
if (set) {
ip_set(inst, i) = NULL;
+ set->variant->cancel_gc(set);
ip_set_destroy_set(set);
}
}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 1136510521a8..cf3ce72c3de6 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -432,7 +432,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
u32 i;
for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = __ipset_dereference(hbucket(t, i));
+ n = (__force struct hbucket *)hbucket(t, i);
if (!n)
continue;
if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
@@ -452,7 +452,7 @@ mtype_destroy(struct ip_set *set)
struct htype *h = set->data;
struct list_head *l, *lt;
- mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
+ mtype_ahash_destroy(set, (__force struct htable *)h->table, true);
list_for_each_safe(l, lt, &h->ad) {
list_del(l);
kfree(l);
From 2fe8a236436fe40d8d26a1af8d150fc80f04ee1a Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Tue, 6 Feb 2024 09:58:49 +0100
Subject: [PATCH 346/637] s390/qeth: Fix potential loss of L3-IP@ in case of
network issues
Symptom:
In case of a bad cable connection (e.g. dirty optics) a fast sequence of
network DOWN-UP-DOWN-UP could happen. UP triggers recovery of the qeth
interface. In case of a second DOWN while recovery is still ongoing, it
can happen that the IP@ of a Layer3 qeth interface is lost and will not
be recovered by the second UP.
Problem:
When registration of IP addresses with Layer 3 qeth devices fails, (e.g.
because of bad address format) the respective IP address is deleted from
its hash-table in the driver. If registration fails because of a ENETDOWN
condition, the address should stay in the hashtable, so a subsequent
recovery can restore it.
3caa4af834df ("qeth: keep ip-address after LAN_OFFLINE failure")
fixes this for registration failures during normal operation, but not
during recovery.
Solution:
Keep L3-IP address in case of ENETDOWN in qeth_l3_recover_ip(). For
consistency with qeth_l3_add_ip() we also keep it in case of EADDRINUSE,
i.e. for some reason the card already/still has this address registered.
Fixes: 4a71df50047f ("qeth: new qeth device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Link: https://lore.kernel.org/r/20240206085849.2902775-1-wintera@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/s390/net/qeth_l3_main.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b92a32b4b114..04c64ce0a1ca 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
if (!recover) {
hash_del(&addr->hnode);
kfree(addr);
- continue;
+ } else {
+ /* prepare for recovery */
+ addr->disp_flag = QETH_DISP_ADDR_ADD;
}
- addr->disp_flag = QETH_DISP_ADDR_ADD;
}
mutex_unlock(&card->ip_lock);
@@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
rc = qeth_l3_register_addr_entry(card, addr);
- if (!rc) {
+ if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) {
+ /* keep it in the records */
addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
} else {
+ /* bad address */
hash_del(&addr->hnode);
kfree(addr);
}
From fa173a1b4e3fd1ab5451cbc57de6fc624c824b0a Mon Sep 17 00:00:00 2001
From: Felix Huettner <felix.huettner@mail.schwarz>
Date: Mon, 5 Feb 2024 09:59:59 +0000
Subject: [PATCH 347/637] netfilter: ctnetlink: fix filtering for zone 0
previously filtering for the default zone would actually skip the zone
filter and flush all zones.
Fixes: eff3c558bb7e ("netfilter: ctnetlink: support filtering by zone")
Reported-by: Ilya Maximets <i.maximets@ovn.org>
Closes: https://lore.kernel.org/netdev/2032238f-31ac-4106-8f22-522e76df5a12@ovn.org/
Signed-off-by: Felix Huettner <felix.huettner@mail.schwarz>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_netlink.c | 12 ++++--
.../netfilter/conntrack_dump_flush.c | 43 ++++++++++++++++++-
2 files changed, 50 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 0c22a02c2035..3b846cbdc050 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -876,6 +876,7 @@ struct ctnetlink_filter_u32 {
struct ctnetlink_filter {
u8 family;
+ bool zone_filter;
u_int32_t orig_flags;
u_int32_t reply_flags;
@@ -992,9 +993,12 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
if (err)
goto err_filter;
- err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
- if (err < 0)
- goto err_filter;
+ if (cda[CTA_ZONE]) {
+ err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
+ if (err < 0)
+ goto err_filter;
+ filter->zone_filter = true;
+ }
if (!cda[CTA_FILTER])
return filter;
@@ -1148,7 +1152,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
if (filter->family && nf_ct_l3num(ct) != filter->family)
goto ignore_entry;
- if (filter->zone.id != NF_CT_DEFAULT_ZONE_ID &&
+ if (filter->zone_filter &&
!nf_ct_zone_equal_any(ct, &filter->zone))
goto ignore_entry;
diff --git a/tools/testing/selftests/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
index f18c6db13bbf..b11ea8ee6719 100644
--- a/tools/testing/selftests/netfilter/conntrack_dump_flush.c
+++ b/tools/testing/selftests/netfilter/conntrack_dump_flush.c
@@ -13,7 +13,7 @@
#include "../kselftest_harness.h"
#define TEST_ZONE_ID 123
-#define CTA_FILTER_F_CTA_TUPLE_ZONE (1 << 2)
+#define NF_CT_DEFAULT_ZONE_ID 0
static int reply_counter;
@@ -336,6 +336,9 @@ FIXTURE_SETUP(conntrack_dump_flush)
ret = conntrack_data_generate_v4(self->sock, 0xf4f4f4f4, 0xf5f5f5f5,
TEST_ZONE_ID + 2);
EXPECT_EQ(ret, 0);
+ ret = conntrack_data_generate_v4(self->sock, 0xf6f6f6f6, 0xf7f7f7f7,
+ NF_CT_DEFAULT_ZONE_ID);
+ EXPECT_EQ(ret, 0);
src = (struct in6_addr) {{
.__u6_addr32 = {
@@ -395,6 +398,26 @@ FIXTURE_SETUP(conntrack_dump_flush)
TEST_ZONE_ID + 2);
EXPECT_EQ(ret, 0);
+ src = (struct in6_addr) {{
+ .__u6_addr32 = {
+ 0xb80d0120,
+ 0x00000000,
+ 0x00000000,
+ 0x07000000
+ }
+ }};
+ dst = (struct in6_addr) {{
+ .__u6_addr32 = {
+ 0xb80d0120,
+ 0x00000000,
+ 0x00000000,
+ 0x08000000
+ }
+ }};
+ ret = conntrack_data_generate_v6(self->sock, src, dst,
+ NF_CT_DEFAULT_ZONE_ID);
+ EXPECT_EQ(ret, 0);
+
ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
EXPECT_GE(ret, 2);
if (ret > 2)
@@ -425,6 +448,24 @@ TEST_F(conntrack_dump_flush, test_flush_by_zone)
EXPECT_EQ(ret, 2);
ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
EXPECT_EQ(ret, 2);
+ ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+ EXPECT_EQ(ret, 2);
+}
+
+TEST_F(conntrack_dump_flush, test_flush_by_zone_default)
+{
+ int ret;
+
+ ret = conntrack_flush_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+ EXPECT_EQ(ret, 0);
+ ret = conntracK_count_zone(self->sock, TEST_ZONE_ID);
+ EXPECT_EQ(ret, 2);
+ ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 1);
+ EXPECT_EQ(ret, 2);
+ ret = conntracK_count_zone(self->sock, TEST_ZONE_ID + 2);
+ EXPECT_EQ(ret, 2);
+ ret = conntracK_count_zone(self->sock, NF_CT_DEFAULT_ZONE_ID);
+ EXPECT_EQ(ret, 0);
}
TEST_HARNESS_MAIN
From 38ed1c7062ada30d7c11e7a7acc749bf27aa14aa Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 5 Feb 2024 14:59:24 +0100
Subject: [PATCH 348/637] netfilter: nft_ct: reject direction for ct id
Direction attribute is ignored, reject it in case this ever needs to be
supported
Fixes: 3087c3f7c23b ("netfilter: nft_ct: Add ct id support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_ct.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index aac98a3c966e..bfd3e5a14dab 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -476,6 +476,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
break;
#endif
case NFT_CT_ID:
+ if (tb[NFTA_CT_DIRECTION])
+ return -EINVAL;
+
len = sizeof(u32);
break;
default:
From 7395dfacfff65e9938ac0889dafa1ab01e987d15 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 6 Feb 2024 00:11:40 +0100
Subject: [PATCH 349/637] netfilter: nf_tables: use timestamp to check for set
element timeout
Add a timestamp field at the beginning of the transaction, store it
in the nftables per-netns area.
Update set backend .insert, .deactivate and sync gc path to use the
timestamp, this avoids that an element expires while control plane
transaction is still unfinished.
.lookup and .update, which are used from packet path, still use the
current time to check if the element has expired. And .get path and dump
also since this runs lockless under rcu read size lock. Then, there is
async gc which also needs to check the current time since it runs
asynchronously from a workqueue.
Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tables.h | 16 ++++++++++++++--
net/netfilter/nf_tables_api.c | 4 +++-
net/netfilter/nft_set_hash.c | 8 +++++++-
net/netfilter/nft_set_pipapo.c | 18 +++++++++++-------
net/netfilter/nft_set_rbtree.c | 11 +++++++----
5 files changed, 42 insertions(+), 15 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 001226c34621..510244cc0f8f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -808,10 +808,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS);
}
-static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
+ u64 tstamp)
{
return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
- time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
+ time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+ return __nft_set_elem_expired(ext, get_jiffies_64());
}
static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -1779,6 +1785,7 @@ struct nftables_pernet {
struct list_head notify_list;
struct mutex commit_mutex;
u64 table_handle;
+ u64 tstamp;
unsigned int base_seq;
unsigned int gc_seq;
u8 validate_state;
@@ -1791,6 +1798,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net)
return net_generic(net, nf_tables_net_id);
}
+static inline u64 nft_net_tstamp(const struct net *net)
+{
+ return nft_pernet(net)->tstamp;
+}
+
#define __NFT_REDUCE_READONLY 1UL
#define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fc016befb46f..f8e3f70c35bd 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9827,6 +9827,7 @@ dead_elem:
struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
{
struct nft_set_elem_catchall *catchall, *next;
+ u64 tstamp = nft_net_tstamp(gc->net);
const struct nft_set *set = gc->set;
struct nft_elem_priv *elem_priv;
struct nft_set_ext *ext;
@@ -9836,7 +9837,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
ext = nft_set_elem_ext(set, catchall->elem);
- if (!nft_set_elem_expired(ext))
+ if (!__nft_set_elem_expired(ext, tstamp))
continue;
gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -10622,6 +10623,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
bool genid_ok;
mutex_lock(&nft_net->commit_mutex);
+ nft_net->tstamp = get_jiffies_64();
genid_ok = genid == 0 || nft_net->base_seq == genid;
if (!genid_ok)
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6c2061bfdae6..6968a3b34236 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg {
const struct nft_set *set;
const u32 *key;
u8 genmask;
+ u64 tstamp;
};
static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
@@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
return 1;
if (nft_set_elem_is_dead(&he->ext))
return 1;
- if (nft_set_elem_expired(&he->ext))
+ if (__nft_set_elem_expired(&he->ext, x->tstamp))
return 1;
if (!nft_set_elem_active(&he->ext, x->genmask))
return 1;
@@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
.genmask = nft_genmask_cur(net),
.set = set,
.key = key,
+ .tstamp = get_jiffies_64(),
};
he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
.genmask = nft_genmask_cur(net),
.set = set,
.key = elem->key.val.data,
+ .tstamp = get_jiffies_64(),
};
he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
.genmask = NFT_GENMASK_ANY,
.set = set,
.key = key,
+ .tstamp = get_jiffies_64(),
};
he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
.genmask = nft_genmask_next(net),
.set = set,
.key = elem->key.val.data,
+ .tstamp = nft_net_tstamp(net),
};
struct nft_rhash_elem *prev;
@@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set,
.genmask = nft_genmask_next(net),
.set = set,
.key = elem->key.val.data,
+ .tstamp = nft_net_tstamp(net),
};
rcu_read_lock();
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index f24ecdaa1c1e..b17c18203416 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -504,6 +504,7 @@ out:
* @set: nftables API set representation
* @data: Key data to be matched against existing elements
* @genmask: If set, check that element is active in given genmask
+ * @tstamp: timestamp to check for expired elements
*
* This is essentially the same as the lookup function, except that it matches
* key data against the uncommitted copy and doesn't use preallocated maps for
@@ -513,7 +514,8 @@ out:
*/
static struct nft_pipapo_elem *pipapo_get(const struct net *net,
const struct nft_set *set,
- const u8 *data, u8 genmask)
+ const u8 *data, u8 genmask,
+ u64 tstamp)
{
struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
struct nft_pipapo *priv = nft_set_priv(set);
@@ -566,7 +568,7 @@ next_match:
goto out;
if (last) {
- if (nft_set_elem_expired(&f->mt[b].e->ext))
+ if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
goto next_match;
if ((genmask &&
!nft_set_elem_active(&f->mt[b].e->ext, genmask)))
@@ -606,7 +608,7 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
struct nft_pipapo_elem *e;
e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
- nft_genmask_cur(net));
+ nft_genmask_cur(net), get_jiffies_64());
if (IS_ERR(e))
return ERR_CAST(e);
@@ -1173,6 +1175,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
struct nft_pipapo_match *m = priv->clone;
u8 genmask = nft_genmask_next(net);
struct nft_pipapo_elem *e, *dup;
+ u64 tstamp = nft_net_tstamp(net);
struct nft_pipapo_field *f;
const u8 *start_p, *end_p;
int i, bsize_max, err = 0;
@@ -1182,7 +1185,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
else
end = start;
- dup = pipapo_get(net, set, start, genmask);
+ dup = pipapo_get(net, set, start, genmask, tstamp);
if (!IS_ERR(dup)) {
/* Check if we already have the same exact entry */
const struct nft_data *dup_key, *dup_end;
@@ -1204,7 +1207,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
if (PTR_ERR(dup) == -ENOENT) {
/* Look for partially overlapping entries */
- dup = pipapo_get(net, set, end, nft_genmask_next(net));
+ dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp);
}
if (PTR_ERR(dup) != -ENOENT) {
@@ -1560,6 +1563,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
{
struct nft_pipapo *priv = nft_set_priv(set);
struct net *net = read_pnet(&set->net);
+ u64 tstamp = nft_net_tstamp(net);
int rules_f0, first_rule = 0;
struct nft_pipapo_elem *e;
struct nft_trans_gc *gc;
@@ -1594,7 +1598,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
/* synchronous gc never fails, there is no need to set on
* NFT_SET_ELEM_DEAD_BIT.
*/
- if (nft_set_elem_expired(&e->ext)) {
+ if (__nft_set_elem_expired(&e->ext, tstamp)) {
priv->dirty = true;
gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -1769,7 +1773,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
{
struct nft_pipapo_elem *e;
- e = pipapo_get(net, set, data, nft_genmask_next(net));
+ e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net));
if (IS_ERR(e))
return NULL;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65..5fd74f993988 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree *priv = nft_set_priv(set);
u8 cur_genmask = nft_genmask_cur(net);
u8 genmask = nft_genmask_next(net);
+ u64 tstamp = nft_net_tstamp(net);
int d;
/* Descend the tree to search for an existing element greater than the
@@ -360,7 +361,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
/* perform garbage collection to avoid bogus overlap reports
* but skip new elements in this transaction.
*/
- if (nft_set_elem_expired(&rbe->ext) &&
+ if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
nft_set_elem_active(&rbe->ext, cur_genmask)) {
const struct nft_rbtree_elem *removed_end;
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
const struct nft_rbtree *priv = nft_set_priv(set);
const struct rb_node *parent = priv->root.rb_node;
u8 genmask = nft_genmask_next(net);
+ u64 tstamp = nft_net_tstamp(net);
int d;
while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
- } else if (nft_set_elem_expired(&rbe->ext)) {
+ } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
break;
} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+ struct net *net = read_pnet(&set->net);
+ u64 tstamp = nft_net_tstamp(net);
struct rb_node *node, *next;
struct nft_trans_gc *gc;
- struct net *net;
set = nft_set_container_of(priv);
net = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
rbe_end = rbe;
continue;
}
- if (!nft_set_elem_expired(&rbe->ext))
+ if (!__nft_set_elem_expired(&rbe->ext, tstamp))
continue;
gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
From f82777e8ce6c039cdcacbcf1eb8619b99a20c06d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 6 Feb 2024 17:54:18 +0100
Subject: [PATCH 350/637] netfilter: nfnetlink_queue: un-break NF_REPEAT
Only override userspace verdict if the ct hook returns something
other than ACCEPT.
Else, this replaces NF_REPEAT (run all hooks again) with NF_ACCEPT
(move to next hook).
Fixes: 6291b3a67ad5 ("netfilter: conntrack: convert nf_conntrack_update to netfilter verdicts")
Reported-by: l.6diay@passmail.com
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nfnetlink_queue.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 171d1f52d3dd..5cf38fc0a366 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -232,18 +232,25 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict)
if (verdict == NF_ACCEPT ||
verdict == NF_REPEAT ||
verdict == NF_STOP) {
+ unsigned int ct_verdict = verdict;
+
rcu_read_lock();
ct_hook = rcu_dereference(nf_ct_hook);
if (ct_hook)
- verdict = ct_hook->update(entry->state.net, entry->skb);
+ ct_verdict = ct_hook->update(entry->state.net, entry->skb);
rcu_read_unlock();
- switch (verdict & NF_VERDICT_MASK) {
+ switch (ct_verdict & NF_VERDICT_MASK) {
+ case NF_ACCEPT:
+ /* follow userspace verdict, could be REPEAT */
+ break;
case NF_STOLEN:
nf_queue_entry_free(entry);
return;
+ default:
+ verdict = ct_verdict & NF_VERDICT_MASK;
+ break;
}
-
}
nf_reinject(entry, verdict);
}
From 60c0c230c6f046da536d3df8b39a20b9a9fd6af0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 7 Feb 2024 18:49:51 +0100
Subject: [PATCH 351/637] netfilter: nft_set_rbtree: skip end interval element
from gc
rbtree lazy gc on insert might collect an end interval element that has
been just added in this transactions, skip end interval elements that
are not yet active.
Fixes: f718863aca46 ("netfilter: nft_set_rbtree: fix overlap expiration walk")
Cc: stable@vger.kernel.org
Reported-by: lonial con <kongln9170@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_rbtree.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 5fd74f993988..9944fe479e53 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -234,7 +234,7 @@ static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set,
static const struct nft_rbtree_elem *
nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
- struct nft_rbtree_elem *rbe, u8 genmask)
+ struct nft_rbtree_elem *rbe)
{
struct nft_set *set = (struct nft_set *)__set;
struct rb_node *prev = rb_prev(&rbe->node);
@@ -253,7 +253,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv,
while (prev) {
rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
if (nft_rbtree_interval_end(rbe_prev) &&
- nft_set_elem_active(&rbe_prev->ext, genmask))
+ nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY))
break;
prev = rb_prev(prev);
@@ -365,7 +365,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
nft_set_elem_active(&rbe->ext, cur_genmask)) {
const struct nft_rbtree_elem *removed_end;
- removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask);
+ removed_end = nft_rbtree_gc_elem(set, priv, rbe);
if (IS_ERR(removed_end))
return PTR_ERR(removed_end);
From 76313d1a4aa9e30d5b43dee5efd8bcd4d8250006 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Feb 2024 21:52:46 +0100
Subject: [PATCH 352/637] netfilter: nft_set_pipapo: store index in scratch
maps
Pipapo needs a scratchpad area to keep state during matching.
This state can be large and thus cannot reside on stack.
Each set preallocates percpu areas for this.
On each match stage, one scratchpad half starts with all-zero and the other
is inited to all-ones.
At the end of each stage, the half that starts with all-ones is
always zero. Before next field is tested, pointers to the two halves
are swapped, i.e. resmap pointer turns into fill pointer and vice versa.
After the last field has been processed, pipapo stashes the
index toggle in a percpu variable, with assumption that next packet
will start with the all-zero half and sets all bits in the other to 1.
This isn't reliable.
There can be multiple sets and we can't be sure that the upper
and lower half of all set scratch map is always in sync (lookups
can be conditional), so one set might have swapped, but other might
not have been queried.
Thus we need to keep the index per-set-and-cpu, just like the
scratchpad.
Note that this bug fix is incomplete, there is a related issue.
avx2 and normal implementation might use slightly different areas of the
map array space due to the avx2 alignment requirements, so
m->scratch (generic/fallback implementation) and ->scratch_aligned
(avx) may partially overlap. scratch and scratch_aligned are not distinct
objects, the latter is just the aligned address of the former.
After this change, write to scratch_align->map_index may write to
scratch->map, so this issue becomes more prominent, we can set to 1
a bit in the supposedly-all-zero area of scratch->map[].
A followup patch will remove the scratch_aligned and makes generic and
avx code use the same (aligned) area.
Its done in a separate change to ease review.
Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_pipapo.c | 41 ++++++++++++++++++-----------
net/netfilter/nft_set_pipapo.h | 14 ++++++++--
net/netfilter/nft_set_pipapo_avx2.c | 15 +++++------
3 files changed, 44 insertions(+), 26 deletions(-)
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index b17c18203416..54d0bac140a3 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -342,9 +342,6 @@
#include "nft_set_pipapo_avx2.h"
#include "nft_set_pipapo.h"
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
-
/**
* pipapo_refill() - For each set bit, set bits from selected mapping table item
* @map: Bitmap to be scanned for set bits
@@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext)
{
struct nft_pipapo *priv = nft_set_priv(set);
+ struct nft_pipapo_scratch *scratch;
unsigned long *res_map, *fill_map;
u8 genmask = nft_genmask_cur(net);
const u8 *rp = (const u8 *)key;
@@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
local_bh_disable();
- map_index = raw_cpu_read(nft_pipapo_scratch_index);
-
m = rcu_dereference(priv->match);
if (unlikely(!m || !*raw_cpu_ptr(m->scratch)))
goto out;
- res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0);
- fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max);
+ scratch = *raw_cpu_ptr(m->scratch);
+
+ map_index = scratch->map_index;
+
+ res_map = scratch->map + (map_index ? m->bsize_max : 0);
+ fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
@@ -460,7 +460,7 @@ next_match:
b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt,
last);
if (b < 0) {
- raw_cpu_write(nft_pipapo_scratch_index, map_index);
+ scratch->map_index = map_index;
local_bh_enable();
return false;
@@ -477,7 +477,7 @@ next_match:
* current inactive bitmap is clean and can be reused as
* *next* bitmap (not initial) for the next packet.
*/
- raw_cpu_write(nft_pipapo_scratch_index, map_index);
+ scratch->map_index = map_index;
local_bh_enable();
return true;
@@ -1123,12 +1123,12 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
int i;
for_each_possible_cpu(i) {
- unsigned long *scratch;
+ struct nft_pipapo_scratch *scratch;
#ifdef NFT_PIPAPO_ALIGN
- unsigned long *scratch_aligned;
+ void *scratch_aligned;
#endif
-
- scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 +
+ scratch = kzalloc_node(struct_size(scratch, map,
+ bsize_max * 2) +
NFT_PIPAPO_ALIGN_HEADROOM,
GFP_KERNEL, cpu_to_node(i));
if (!scratch) {
@@ -1147,7 +1147,16 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
*per_cpu_ptr(clone->scratch, i) = scratch;
#ifdef NFT_PIPAPO_ALIGN
- scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch);
+ /* Align &scratch->map (not the struct itself): the extra
+ * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
+ * above guarantee we can waste up to those bytes in order
+ * to align the map field regardless of its offset within
+ * the struct.
+ */
+ BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM);
+
+ scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
+ scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
*per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
#endif
}
@@ -2136,7 +2145,7 @@ static int nft_pipapo_init(const struct nft_set *set,
m->field_count = field_count;
m->bsize_max = 0;
- m->scratch = alloc_percpu(unsigned long *);
+ m->scratch = alloc_percpu(struct nft_pipapo_scratch *);
if (!m->scratch) {
err = -ENOMEM;
goto out_scratch;
@@ -2145,7 +2154,7 @@ static int nft_pipapo_init(const struct nft_set *set,
*per_cpu_ptr(m->scratch, i) = NULL;
#ifdef NFT_PIPAPO_ALIGN
- m->scratch_aligned = alloc_percpu(unsigned long *);
+ m->scratch_aligned = alloc_percpu(struct nft_pipapo_scratch *);
if (!m->scratch_aligned) {
err = -ENOMEM;
goto out_free;
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 1040223da5fa..d3bc1551694f 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -130,6 +130,16 @@ struct nft_pipapo_field {
union nft_pipapo_map_bucket *mt;
};
+/**
+ * struct nft_pipapo_scratch - percpu data used for lookup and matching
+ * @map_index: Current working bitmap index, toggled between field matches
+ * @map: store partial matching results during lookup
+ */
+struct nft_pipapo_scratch {
+ u8 map_index;
+ unsigned long map[];
+};
+
/**
* struct nft_pipapo_match - Data used for lookup and matching
* @field_count Amount of fields in set
@@ -142,9 +152,9 @@ struct nft_pipapo_field {
struct nft_pipapo_match {
int field_count;
#ifdef NFT_PIPAPO_ALIGN
- unsigned long * __percpu *scratch_aligned;
+ struct nft_pipapo_scratch * __percpu *scratch_aligned;
#endif
- unsigned long * __percpu *scratch;
+ struct nft_pipapo_scratch * __percpu *scratch;
size_t bsize_max;
struct rcu_head rcu;
struct nft_pipapo_field f[] __counted_by(field_count);
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 52e0d026d30a..78213c73af2e 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -71,9 +71,6 @@
#define NFT_PIPAPO_AVX2_ZERO(reg) \
asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg)
-/* Current working bitmap index, toggled between field matches */
-static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index);
-
/**
* nft_pipapo_avx2_prepare() - Prepare before main algorithm body
*
@@ -1120,11 +1117,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext)
{
struct nft_pipapo *priv = nft_set_priv(set);
- unsigned long *res, *fill, *scratch;
+ struct nft_pipapo_scratch *scratch;
u8 genmask = nft_genmask_cur(net);
const u8 *rp = (const u8 *)key;
struct nft_pipapo_match *m;
struct nft_pipapo_field *f;
+ unsigned long *res, *fill;
bool map_index;
int i, ret = 0;
@@ -1146,10 +1144,11 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
kernel_fpu_end();
return false;
}
- map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index);
- res = scratch + (map_index ? m->bsize_max : 0);
- fill = scratch + (map_index ? 0 : m->bsize_max);
+ map_index = scratch->map_index;
+
+ res = scratch->map + (map_index ? m->bsize_max : 0);
+ fill = scratch->map + (map_index ? 0 : m->bsize_max);
/* Starting map doesn't need to be set for this implementation */
@@ -1221,7 +1220,7 @@ next_match:
out:
if (i % 2)
- raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index);
+ scratch->map_index = !map_index;
kernel_fpu_end();
return ret >= 0;
From 47b1c03c3c1a119435480a1e73f27197dc59131d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 Feb 2024 21:52:47 +0100
Subject: [PATCH 353/637] netfilter: nft_set_pipapo: add helper to release pcpu
scratch area
After next patch simple kfree() is not enough anymore, so add
a helper for it.
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_pipapo.c | 28 +++++++++++++++++++++++-----
1 file changed, 23 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 54d0bac140a3..5094d4c439c3 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1110,6 +1110,24 @@ static void pipapo_map(struct nft_pipapo_match *m,
f->mt[map[i].to + j].e = e;
}
+/**
+ * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address
+ * @m: Matching data
+ * @cpu: CPU number
+ */
+static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu)
+{
+ struct nft_pipapo_scratch *s;
+ void *mem;
+
+ s = *per_cpu_ptr(m->scratch, cpu);
+ if (!s)
+ return;
+
+ mem = s;
+ kfree(mem);
+}
+
/**
* pipapo_realloc_scratch() - Reallocate scratch maps for partial match results
* @clone: Copy of matching data with pending insertions and deletions
@@ -1142,7 +1160,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
return -ENOMEM;
}
- kfree(*per_cpu_ptr(clone->scratch, i));
+ pipapo_free_scratch(clone, i);
*per_cpu_ptr(clone->scratch, i) = scratch;
@@ -1369,7 +1387,7 @@ out_lt:
}
out_scratch_realloc:
for_each_possible_cpu(i)
- kfree(*per_cpu_ptr(new->scratch, i));
+ pipapo_free_scratch(new, i);
#ifdef NFT_PIPAPO_ALIGN
free_percpu(new->scratch_aligned);
#endif
@@ -1653,7 +1671,7 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
int i;
for_each_possible_cpu(i)
- kfree(*per_cpu_ptr(m->scratch, i));
+ pipapo_free_scratch(m, i);
#ifdef NFT_PIPAPO_ALIGN
free_percpu(m->scratch_aligned);
@@ -2253,7 +2271,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
free_percpu(m->scratch_aligned);
#endif
for_each_possible_cpu(cpu)
- kfree(*per_cpu_ptr(m->scratch, cpu));
+ pipapo_free_scratch(m, cpu);
free_percpu(m->scratch);
pipapo_free_fields(m);
kfree(m);
@@ -2270,7 +2288,7 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
free_percpu(priv->clone->scratch_aligned);
#endif
for_each_possible_cpu(cpu)
- kfree(*per_cpu_ptr(priv->clone->scratch, cpu));
+ pipapo_free_scratch(priv->clone, cpu);
free_percpu(priv->clone->scratch);
pipapo_free_fields(priv->clone);
From 5a8cdf6fd860ac5e6d08d72edbcecee049a7fec4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 8 Feb 2024 10:31:29 +0100
Subject: [PATCH 354/637] netfilter: nft_set_pipapo: remove scratch_aligned
pointer
use ->scratch for both avx2 and the generic implementation.
After previous change the scratch->map member is always aligned properly
for AVX2, so we can just use scratch->map in AVX2 too.
The alignoff delta is stored in the scratchpad so we can reconstruct
the correct address to free the area again.
Fixes: 7400b063969b ("nft_set_pipapo: Introduce AVX2-based lookup implementation")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_pipapo.c | 41 +++++------------------------
net/netfilter/nft_set_pipapo.h | 6 ++---
net/netfilter/nft_set_pipapo_avx2.c | 2 +-
3 files changed, 10 insertions(+), 39 deletions(-)
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 5094d4c439c3..aa1d9e93a9a0 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1125,6 +1125,7 @@ static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int c
return;
mem = s;
+ mem -= s->align_off;
kfree(mem);
}
@@ -1144,6 +1145,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
struct nft_pipapo_scratch *scratch;
#ifdef NFT_PIPAPO_ALIGN
void *scratch_aligned;
+ u32 align_off;
#endif
scratch = kzalloc_node(struct_size(scratch, map,
bsize_max * 2) +
@@ -1162,8 +1164,6 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
pipapo_free_scratch(clone, i);
- *per_cpu_ptr(clone->scratch, i) = scratch;
-
#ifdef NFT_PIPAPO_ALIGN
/* Align &scratch->map (not the struct itself): the extra
* %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node()
@@ -1175,8 +1175,12 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map);
scratch_aligned -= offsetof(struct nft_pipapo_scratch, map);
- *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned;
+ align_off = scratch_aligned - (void *)scratch;
+
+ scratch = scratch_aligned;
+ scratch->align_off = align_off;
#endif
+ *per_cpu_ptr(clone->scratch, i) = scratch;
}
return 0;
@@ -1331,11 +1335,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
if (!new->scratch)
goto out_scratch;
-#ifdef NFT_PIPAPO_ALIGN
- new->scratch_aligned = alloc_percpu(*new->scratch_aligned);
- if (!new->scratch_aligned)
- goto out_scratch;
-#endif
for_each_possible_cpu(i)
*per_cpu_ptr(new->scratch, i) = NULL;
@@ -1388,9 +1387,6 @@ out_lt:
out_scratch_realloc:
for_each_possible_cpu(i)
pipapo_free_scratch(new, i);
-#ifdef NFT_PIPAPO_ALIGN
- free_percpu(new->scratch_aligned);
-#endif
out_scratch:
free_percpu(new->scratch);
kfree(new);
@@ -1673,11 +1669,7 @@ static void pipapo_free_match(struct nft_pipapo_match *m)
for_each_possible_cpu(i)
pipapo_free_scratch(m, i);
-#ifdef NFT_PIPAPO_ALIGN
- free_percpu(m->scratch_aligned);
-#endif
free_percpu(m->scratch);
-
pipapo_free_fields(m);
kfree(m);
@@ -2171,16 +2163,6 @@ static int nft_pipapo_init(const struct nft_set *set,
for_each_possible_cpu(i)
*per_cpu_ptr(m->scratch, i) = NULL;
-#ifdef NFT_PIPAPO_ALIGN
- m->scratch_aligned = alloc_percpu(struct nft_pipapo_scratch *);
- if (!m->scratch_aligned) {
- err = -ENOMEM;
- goto out_free;
- }
- for_each_possible_cpu(i)
- *per_cpu_ptr(m->scratch_aligned, i) = NULL;
-#endif
-
rcu_head_init(&m->rcu);
nft_pipapo_for_each_field(f, i, m) {
@@ -2211,9 +2193,6 @@ static int nft_pipapo_init(const struct nft_set *set,
return 0;
out_free:
-#ifdef NFT_PIPAPO_ALIGN
- free_percpu(m->scratch_aligned);
-#endif
free_percpu(m->scratch);
out_scratch:
kfree(m);
@@ -2267,9 +2246,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
nft_set_pipapo_match_destroy(ctx, set, m);
-#ifdef NFT_PIPAPO_ALIGN
- free_percpu(m->scratch_aligned);
-#endif
for_each_possible_cpu(cpu)
pipapo_free_scratch(m, cpu);
free_percpu(m->scratch);
@@ -2284,9 +2260,6 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
if (priv->dirty)
nft_set_pipapo_match_destroy(ctx, set, m);
-#ifdef NFT_PIPAPO_ALIGN
- free_percpu(priv->clone->scratch_aligned);
-#endif
for_each_possible_cpu(cpu)
pipapo_free_scratch(priv->clone, cpu);
free_percpu(priv->clone->scratch);
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index d3bc1551694f..f59a0cd81105 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -133,10 +133,12 @@ struct nft_pipapo_field {
/**
* struct nft_pipapo_scratch - percpu data used for lookup and matching
* @map_index: Current working bitmap index, toggled between field matches
+ * @align_off: Offset to get the originally allocated address
* @map: store partial matching results during lookup
*/
struct nft_pipapo_scratch {
u8 map_index;
+ u32 align_off;
unsigned long map[];
};
@@ -144,16 +146,12 @@ struct nft_pipapo_scratch {
* struct nft_pipapo_match - Data used for lookup and matching
* @field_count Amount of fields in set
* @scratch: Preallocated per-CPU maps for partial matching results
- * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
* @bsize_max: Maximum lookup table bucket size of all fields, in longs
* @rcu Matching data is swapped on commits
* @f: Fields, with lookup and mapping tables
*/
struct nft_pipapo_match {
int field_count;
-#ifdef NFT_PIPAPO_ALIGN
- struct nft_pipapo_scratch * __percpu *scratch_aligned;
-#endif
struct nft_pipapo_scratch * __percpu *scratch;
size_t bsize_max;
struct rcu_head rcu;
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 78213c73af2e..90e275bb3e5d 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1139,7 +1139,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
*/
kernel_fpu_begin_mask(0);
- scratch = *raw_cpu_ptr(m->scratch_aligned);
+ scratch = *raw_cpu_ptr(m->scratch);
if (unlikely(!scratch)) {
kernel_fpu_end();
return false;
From c98d8836b817d11fdff4ca7749cbbe04ff7f0c64 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 31 Jan 2024 16:49:10 +0100
Subject: [PATCH 355/637] wifi: mac80211: reload info pointer in
ieee80211_tx_dequeue()
This pointer can change here since the SKB can change, so we
actually later open-coded IEEE80211_SKB_CB() again. Reload
the pointer where needed, so the monitor-mode case using it
gets fixed, and then use info-> later as well.
Cc: stable@vger.kernel.org
Fixes: 531682159092 ("mac80211: fix VLAN handling with TXQs")
Link: https://msgid.link/20240131164910.b54c28d583bc.I29450cec84ea6773cff5d9c16ff92b836c331471@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/tx.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e448ab338448..6fbb15b65902 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
*
* Transmit and frame generation functions.
*/
@@ -3927,6 +3927,7 @@ begin:
goto begin;
skb = __skb_dequeue(&tx.skbs);
+ info = IEEE80211_SKB_CB(skb);
if (!skb_queue_empty(&tx.skbs)) {
spin_lock_bh(&fq->lock);
@@ -3971,7 +3972,7 @@ begin:
}
encap_out:
- IEEE80211_SKB_CB(skb)->control.vif = vif;
+ info->control.vif = vif;
if (tx.sta &&
wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
From 2e57b77583ca34fdb6e14f253172636c52f81cf2 Mon Sep 17 00:00:00 2001
From: Daniel Gabay <daniel.gabay@intel.com>
Date: Mon, 5 Feb 2024 00:06:03 +0200
Subject: [PATCH 356/637] wifi: iwlwifi: mvm: use correct address 3 in A-MSDU
As described in IEEE sta 802.11-2020, table 9-30 (Address
field contents), A-MSDU address 3 should contain the BSSID
address.
In TX_CMD we copy the MAC header from skb, and skb address 3
holds the destination address, but it may not be identical to
the BSSID.
Using the wrong destination address appears to work with (most)
receivers without MLO, but in MLO some devices are checking for
it carefully, perhaps as a consequence of link to MLD address
translation.
Replace address 3 in the TX_CMD MAC header with the correct
address while retaining the skb address 3 unchanged.
This ensures that skb address 3 will be utilized later for
constructing the A-MSDU subframes.
Note that we fill in the MLD address, but the firmware will do the
necessary translation to link address after encryption.
Signed-off-by: Daniel Gabay <daniel.gabay@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240204235836.4583a1bf9188.I3f8e7892bdf8f86b4daa28453771a8c9817b2416@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 73 +++++++++++++++++----
1 file changed, 61 insertions(+), 12 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index db986bfc4dc3..461f26d9214e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -520,13 +520,24 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
}
}
+static void iwl_mvm_copy_hdr(void *cmd, const void *hdr, int hdrlen,
+ const u8 *addr3_override)
+{
+ struct ieee80211_hdr *out_hdr = cmd;
+
+ memcpy(cmd, hdr, hdrlen);
+ if (addr3_override)
+ memcpy(out_hdr->addr3, addr3_override, ETH_ALEN);
+}
+
/*
* Allocates and sets the Tx cmd the driver data pointers in the skb
*/
static struct iwl_device_tx_cmd *
iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
struct ieee80211_tx_info *info, int hdrlen,
- struct ieee80211_sta *sta, u8 sta_id)
+ struct ieee80211_sta *sta, u8 sta_id,
+ const u8 *addr3_override)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
struct iwl_device_tx_cmd *dev_cmd;
@@ -584,7 +595,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
cmd->len = cpu_to_le16((u16)skb->len);
/* Copy MAC header from skb into command buffer */
- memcpy(cmd->hdr, hdr, hdrlen);
+ iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
cmd->flags = cpu_to_le16(flags);
cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -599,7 +610,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
cmd->len = cpu_to_le16((u16)skb->len);
/* Copy MAC header from skb into command buffer */
- memcpy(cmd->hdr, hdr, hdrlen);
+ iwl_mvm_copy_hdr(cmd->hdr, hdr, hdrlen, addr3_override);
cmd->flags = cpu_to_le32(flags);
cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
@@ -617,7 +628,7 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
iwl_mvm_set_tx_cmd_rate(mvm, tx_cmd, info, sta, hdr->frame_control);
/* Copy MAC header from skb into command buffer */
- memcpy(tx_cmd->hdr, hdr, hdrlen);
+ iwl_mvm_copy_hdr(tx_cmd->hdr, hdr, hdrlen, addr3_override);
out:
return dev_cmd;
@@ -820,7 +831,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
IWL_DEBUG_TX(mvm, "station Id %d, queue=%d\n", sta_id, queue);
- dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id);
+ dev_cmd = iwl_mvm_set_tx_params(mvm, skb, &info, hdrlen, NULL, sta_id,
+ NULL);
if (!dev_cmd)
return -1;
@@ -1140,7 +1152,8 @@ static int iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm,
*/
static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
struct ieee80211_tx_info *info,
- struct ieee80211_sta *sta)
+ struct ieee80211_sta *sta,
+ const u8 *addr3_override)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
struct iwl_mvm_sta *mvmsta;
@@ -1172,7 +1185,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
iwl_mvm_probe_resp_set_noa(mvm, skb);
dev_cmd = iwl_mvm_set_tx_params(mvm, skb, info, hdrlen,
- sta, mvmsta->deflink.sta_id);
+ sta, mvmsta->deflink.sta_id,
+ addr3_override);
if (!dev_cmd)
goto drop;
@@ -1294,9 +1308,11 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
struct ieee80211_tx_info info;
struct sk_buff_head mpdus_skbs;
+ struct ieee80211_vif *vif;
unsigned int payload_len;
int ret;
struct sk_buff *orig_skb = skb;
+ const u8 *addr3;
if (WARN_ON_ONCE(!mvmsta))
return -1;
@@ -1307,26 +1323,59 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
memcpy(&info, skb->cb, sizeof(info));
if (!skb_is_gso(skb))
- return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+ return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) -
tcp_hdrlen(skb) + skb->data_len;
if (payload_len <= skb_shinfo(skb)->gso_size)
- return iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+ return iwl_mvm_tx_mpdu(mvm, skb, &info, sta, NULL);
__skb_queue_head_init(&mpdus_skbs);
+ vif = info.control.vif;
+ if (!vif)
+ return -1;
+
ret = iwl_mvm_tx_tso(mvm, skb, &info, sta, &mpdus_skbs);
if (ret)
return ret;
WARN_ON(skb_queue_empty(&mpdus_skbs));
- while (!skb_queue_empty(&mpdus_skbs)) {
- skb = __skb_dequeue(&mpdus_skbs);
+ /*
+ * As described in IEEE sta 802.11-2020, table 9-30 (Address
+ * field contents), A-MSDU address 3 should contain the BSSID
+ * address.
+ * Pass address 3 down to iwl_mvm_tx_mpdu() and further to set it
+ * in the command header. We need to preserve the original
+ * address 3 in the skb header to correctly create all the
+ * A-MSDU subframe headers from it.
+ */
+ switch (vif->type) {
+ case NL80211_IFTYPE_STATION:
+ addr3 = vif->cfg.ap_addr;
+ break;
+ case NL80211_IFTYPE_AP:
+ addr3 = vif->addr;
+ break;
+ default:
+ addr3 = NULL;
+ break;
+ }
- ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta);
+ while (!skb_queue_empty(&mpdus_skbs)) {
+ struct ieee80211_hdr *hdr;
+ bool amsdu;
+
+ skb = __skb_dequeue(&mpdus_skbs);
+ hdr = (void *)skb->data;
+ amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+ (*ieee80211_get_qos_ctl(hdr) &
+ IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+
+ ret = iwl_mvm_tx_mpdu(mvm, skb, &info, sta,
+ amsdu ? addr3 : NULL);
if (ret) {
/* Free skbs created as part of TSO logic that have not yet been dequeued */
__skb_queue_purge(&mpdus_skbs);
From 3012477cd510044d346c5e0465ead4732aef8349 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 5 Feb 2024 00:06:16 +0200
Subject: [PATCH 357/637] wifi: iwlwifi: clear link_id in time_event
Before sending a SESSION PROTECTION cmd the driver checks if
the link_id indicated in the time event (and for which the cmd will be
sent) is valid and exists.
Clear the te_data::link_id when FW notifies that a session protection
ended, so the check will actually fail when it should.
Fixes: 135065837310 ("wifi: iwlwifi: support link_id in SESSION_PROTECTION cmd")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240204235836.c64a6b3606c2.I35cdc08e8a3be282563163690f8ca3edb51a3854@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 218fdf1ed530..2e653a417d62 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
* Copyright (C) 2013-2015 Intel Mobile Communications GmbH
* Copyright (C) 2017 Intel Deutschland GmbH
*/
@@ -972,6 +972,7 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) {
/* End TE, notify mac80211 */
mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
+ mvmvif->time_event_data.link_id = -1;
iwl_mvm_p2p_roc_finished(mvm);
ieee80211_remain_on_channel_expired(mvm->hw);
} else if (le32_to_cpu(notif->start)) {
From c6ebb5b67641994de8bc486b33457fe0b681d6fe Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 8 Feb 2024 13:17:06 +0300
Subject: [PATCH 358/637] wifi: iwlwifi: Fix some error codes
This saves the error as PTR_ERR(wifi_pkg). The problem is that
"wifi_pkg" is a valid pointer, not an error pointer. Set the error code
to -EINVAL instead.
Fixes: 2a8084147bff ("iwlwifi: acpi: support reading and storing WRDS revision 1 and 2")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://msgid.link/9620bb77-2d7c-4d76-b255-ad824ebf8e35@moroto.mountain
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index b96f30d11644..d73d561709d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -618,7 +618,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 2) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
@@ -634,7 +634,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 1) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
@@ -650,7 +650,7 @@ int iwl_sar_get_wrds_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 0) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
@@ -707,7 +707,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 2) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
@@ -723,7 +723,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 1) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
@@ -739,7 +739,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
&tbl_rev);
if (!IS_ERR(wifi_pkg)) {
if (tbl_rev != 0) {
- ret = PTR_ERR(wifi_pkg);
+ ret = -EINVAL;
goto out_free;
}
From 65c6ee90455053cfd3067c17aaa4a42b0c766543 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 8 Feb 2024 13:17:31 +0300
Subject: [PATCH 359/637] wifi: iwlwifi: uninitialized variable in
iwl_acpi_get_ppag_table()
This is an error path and Smatch complains that "tbl_rev" is uninitialized
on this path. All the other functions follow this same patter where they
set the error code and goto out_free so that's probably what was intended
here as well.
Fixes: e8e10a37c51c ("iwlwifi: acpi: move ppag code from mvm to fw/acpi")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://msgid.link/09900c01-6540-4a32-9451-563da0029cb6@moroto.mountain
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index d73d561709d3..dcc4810cb324 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -1116,6 +1116,9 @@ int iwl_acpi_get_ppag_table(struct iwl_fw_runtime *fwrt)
goto read_table;
}
+ ret = PTR_ERR(wifi_pkg);
+ goto out_free;
+
read_table:
fwrt->ppag_ver = tbl_rev;
flags = &wifi_pkg->package.elements[1];
From b7198383ef2debe748118996f627452281cf27d7 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 6 Feb 2024 18:02:04 +0200
Subject: [PATCH 360/637] wifi: iwlwifi: mvm: fix a crash when we run out of
stations
A DoS tool that injects loads of authentication frames made our AP
crash. The iwl_mvm_is_dup() function couldn't find the per-queue
dup_data which was not allocated.
The root cause for that is that we ran out of stations in the firmware
and we didn't really add the station to the firmware, yet we didn't
return an error to mac80211.
Mac80211 was thinking that we have the station and because of that,
sta_info::uploaded was set to 1. This allowed
ieee80211_find_sta_by_ifaddr() to return a valid station object, but
that ieee80211_sta didn't have any iwl_mvm_sta object initialized and
that caused the crash mentioned earlier when we got Rx on that station.
Cc: stable@vger.kernel.org
Fixes: 57974a55d995 ("wifi: iwlwifi: mvm: refactor iwl_mvm_mac_sta_state_common()")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20240206175739.1f76c44b2486.I6a00955e2842f15f0a089db2f834adb9d10fbe35@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++
drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 4 ++++
2 files changed, 7 insertions(+)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 3447d67a8b31..53e26c3c3a9a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -3687,6 +3687,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm,
NL80211_TDLS_SETUP);
}
+ if (ret)
+ return ret;
+
for_each_sta_active_link(vif, sta, link_sta, i)
link_sta->agg.max_rc_amsdu_len = 1;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 886d00098528..af15d470c69b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -505,6 +505,10 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue,
return false;
mvm_sta = iwl_mvm_sta_from_mac80211(sta);
+
+ if (WARN_ON_ONCE(!mvm_sta->dup_data))
+ return false;
+
dup_data = &mvm_sta->dup_data[queue];
/*
From c14f09f010cc569ae7e2f6ef02374f6bfef9917e Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 8 Feb 2024 12:37:42 +0000
Subject: [PATCH 361/637] ASoC: cs35l56: Fix deadlock in ASP1 mixer register
initialization
Rewrite the handling of ASP1 TX mixer mux initialization to prevent a
deadlock during component_remove().
The firmware can overwrite the ASP1 TX mixer registers with
system-specific settings. This is mainly for hardware that uses the
ASP as a chip-to-chip link controlled by the firmware. Because of this
the driver cannot know the starting state of the ASP1 mixer muxes until
the firmware has been downloaded and rebooted.
The original workaround for this was to queue a work function from the
dsp_work() job. This work then read the register values (populating the
regmap cache the first time around) and then called
snd_soc_dapm_mux_update_power(). The problem with this is that it was
ultimately triggered by cs35l56_component_probe() queueing dsp_work,
which meant that it would be running in parallel with the rest of the
ASoC component and card initialization. To prevent accessing DAPM before
it was fully initialized the work function took the card mutex. But this
would deadlock if cs35l56_component_remove() was called before the work job
had completed, because ASoC calls component_remove() with the card mutex
held.
This new version removes the work function. Instead the regmap cache and
DAPM mux widgets are initialized the first time any of the associated ALSA
controls is read or written.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 07f7d6e7a124 ("ASoC: cs35l56: Fix for initializing ASP1 mixer registers")
Link: https://lore.kernel.org/r/20240208123742.1278104-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs35l56.c | 157 +++++++++++++++++--------------------
sound/soc/codecs/cs35l56.h | 2 +-
2 files changed, 75 insertions(+), 84 deletions(-)
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index ebed5ab1245b..98d3957c66e7 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -68,6 +68,66 @@ static const char * const cs35l56_asp1_mux_control_names[] = {
"ASP1 TX1 Source", "ASP1 TX2 Source", "ASP1 TX3 Source", "ASP1 TX4 Source"
};
+static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private *cs35l56)
+{
+ struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
+ const char *prefix = cs35l56->component->name_prefix;
+ char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+ const char *name;
+ struct snd_kcontrol *kcontrol;
+ struct soc_enum *e;
+ unsigned int val[4];
+ int i, item, ret;
+
+ if (cs35l56->asp1_mixer_widgets_initialized)
+ return 0;
+
+ /*
+ * Resume so we can read the registers from silicon if the regmap
+ * cache has not yet been populated.
+ */
+ ret = pm_runtime_resume_and_get(cs35l56->base.dev);
+ if (ret < 0)
+ return ret;
+
+ /* Wait for firmware download and reboot */
+ cs35l56_wait_dsp_ready(cs35l56);
+
+ ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
+ val, ARRAY_SIZE(val));
+
+ pm_runtime_mark_last_busy(cs35l56->base.dev);
+ pm_runtime_put_autosuspend(cs35l56->base.dev);
+
+ if (ret) {
+ dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
+ return ret;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
+ name = cs35l56_asp1_mux_control_names[i];
+
+ if (prefix) {
+ snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
+ name = full_name;
+ }
+
+ kcontrol = snd_soc_card_get_kcontrol(dapm->card, name);
+ if (!kcontrol) {
+ dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
+ continue;
+ }
+
+ e = (struct soc_enum *)kcontrol->private_value;
+ item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
+ snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+ }
+
+ cs35l56->asp1_mixer_widgets_initialized = true;
+
+ return 0;
+}
+
static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
{
@@ -78,9 +138,9 @@ static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
unsigned int addr, val;
int ret;
- /* Wait for mux to be initialized */
- cs35l56_wait_dsp_ready(cs35l56);
- flush_work(&cs35l56->mux_init_work);
+ ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+ if (ret)
+ return ret;
addr = cs35l56_asp1_mixer_regs[index];
ret = regmap_read(cs35l56->base.regmap, addr, &val);
@@ -106,9 +166,9 @@ static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
bool changed;
int ret;
- /* Wait for mux to be initialized */
- cs35l56_wait_dsp_ready(cs35l56);
- flush_work(&cs35l56->mux_init_work);
+ ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+ if (ret)
+ return ret;
addr = cs35l56_asp1_mixer_regs[index];
val = snd_soc_enum_item_to_val(e, item);
@@ -124,70 +184,6 @@ static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
return changed;
}
-static void cs35l56_mark_asp1_mixer_widgets_dirty(struct cs35l56_private *cs35l56)
-{
- struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
- const char *prefix = cs35l56->component->name_prefix;
- char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
- const char *name;
- struct snd_kcontrol *kcontrol;
- struct soc_enum *e;
- unsigned int val[4];
- int i, item, ret;
-
- /*
- * Resume so we can read the registers from silicon if the regmap
- * cache has not yet been populated.
- */
- ret = pm_runtime_resume_and_get(cs35l56->base.dev);
- if (ret < 0)
- return;
-
- ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
- val, ARRAY_SIZE(val));
-
- pm_runtime_mark_last_busy(cs35l56->base.dev);
- pm_runtime_put_autosuspend(cs35l56->base.dev);
-
- if (ret) {
- dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
- return;
- }
-
- snd_soc_card_mutex_lock(dapm->card);
- WARN_ON(!dapm->card->instantiated);
-
- for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
- name = cs35l56_asp1_mux_control_names[i];
-
- if (prefix) {
- snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
- name = full_name;
- }
-
- kcontrol = snd_soc_card_get_kcontrol(dapm->card, name);
- if (!kcontrol) {
- dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
- continue;
- }
-
- e = (struct soc_enum *)kcontrol->private_value;
- item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
- snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
- }
-
- snd_soc_card_mutex_unlock(dapm->card);
-}
-
-static void cs35l56_mux_init_work(struct work_struct *work)
-{
- struct cs35l56_private *cs35l56 = container_of(work,
- struct cs35l56_private,
- mux_init_work);
-
- cs35l56_mark_asp1_mixer_widgets_dirty(cs35l56);
-}
-
static DECLARE_TLV_DB_SCALE(vol_tlv, -10000, 25, 0);
static const struct snd_kcontrol_new cs35l56_controls[] = {
@@ -936,14 +932,6 @@ static void cs35l56_dsp_work(struct work_struct *work)
else
cs35l56_patch(cs35l56, firmware_missing);
-
- /*
- * Set starting value of ASP1 mux widgets. Updating a mux takes
- * the DAPM mutex. Post this to a separate job so that DAPM
- * power-up can wait for dsp_work to complete without deadlocking
- * on the DAPM mutex.
- */
- queue_work(cs35l56->dsp_wq, &cs35l56->mux_init_work);
err:
pm_runtime_mark_last_busy(cs35l56->base.dev);
pm_runtime_put_autosuspend(cs35l56->base.dev);
@@ -989,6 +977,13 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
debugfs_create_bool("can_hibernate", 0444, debugfs_root, &cs35l56->base.can_hibernate);
debugfs_create_bool("fw_patched", 0444, debugfs_root, &cs35l56->base.fw_patched);
+ /*
+ * The widgets for the ASP1TX mixer can't be initialized
+ * until the firmware has been downloaded and rebooted.
+ */
+ regcache_drop_region(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX4_INPUT);
+ cs35l56->asp1_mixer_widgets_initialized = false;
+
queue_work(cs35l56->dsp_wq, &cs35l56->dsp_work);
return 0;
@@ -999,7 +994,6 @@ static void cs35l56_component_remove(struct snd_soc_component *component)
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
cancel_work_sync(&cs35l56->dsp_work);
- cancel_work_sync(&cs35l56->mux_init_work);
if (cs35l56->dsp.cs_dsp.booted)
wm_adsp_power_down(&cs35l56->dsp);
@@ -1070,10 +1064,8 @@ int cs35l56_system_suspend(struct device *dev)
dev_dbg(dev, "system_suspend\n");
- if (cs35l56->component) {
+ if (cs35l56->component)
flush_work(&cs35l56->dsp_work);
- cancel_work_sync(&cs35l56->mux_init_work);
- }
/*
* The interrupt line is normally shared, but after we start suspending
@@ -1224,7 +1216,6 @@ static int cs35l56_dsp_init(struct cs35l56_private *cs35l56)
return -ENOMEM;
INIT_WORK(&cs35l56->dsp_work, cs35l56_dsp_work);
- INIT_WORK(&cs35l56->mux_init_work, cs35l56_mux_init_work);
dsp = &cs35l56->dsp;
cs35l56_init_cs_dsp(&cs35l56->base, &dsp->cs_dsp);
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 596b141e3f96..b000e7365e40 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -34,7 +34,6 @@ struct cs35l56_private {
struct wm_adsp dsp; /* must be first member */
struct cs35l56_base base;
struct work_struct dsp_work;
- struct work_struct mux_init_work;
struct workqueue_struct *dsp_wq;
struct snd_soc_component *component;
struct regulator_bulk_data supplies[CS35L56_NUM_BULK_SUPPLIES];
@@ -52,6 +51,7 @@ struct cs35l56_private {
u8 asp_slot_count;
bool tdm_mode;
bool sysclk_set;
+ bool asp1_mixer_widgets_initialized;
u8 old_sdw_clock_scale;
};
From d7332c4a4f1a7d16f054c6357fb65c597b6a86a7 Mon Sep 17 00:00:00 2001
From: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Date: Thu, 8 Feb 2024 15:34:32 +0200
Subject: [PATCH 362/637] ASoC: SOF: ipc3-topology: Fix pipeline tear down
logic
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
With the change in the widget free logic to power down the cores only
when the scheduler widgets are freed, we need to ensure that the
scheduler widget is freed only after all the widgets associated with the
scheduler are freed. This is to ensure that the secondary core that the
scheduler is scheduled to run on is kept powered on until all widgets
that need them are in use. While this works well for dynamic pipelines,
in the case of static pipelines the current logic does not take this into
account and frees all widgets in the order they occur in the
widget_list. So, modify this to ensure that the scheduler widgets are freed
only after all other types of widgets in the widget_list are freed.
Link: https://github.com/thesofproject/linux/issues/4807
Fixes: 31ed8da1c8e5 ("ASoC: SOF: sof-audio: Modify logic for enabling/disabling topology cores")
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://lore.kernel.org/r/20240208133432.1688-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/ipc3-topology.c | 69 ++++++++++++++++++++++++-----------
1 file changed, 48 insertions(+), 21 deletions(-)
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index a8832a1c1a24..d47698f4be2d 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -2360,6 +2360,44 @@ static int sof_tear_down_left_over_pipelines(struct snd_sof_dev *sdev)
return 0;
}
+static int sof_ipc3_free_widgets_in_list(struct snd_sof_dev *sdev, bool include_scheduler,
+ bool *dyn_widgets, bool verify)
+{
+ struct sof_ipc_fw_version *v = &sdev->fw_ready.version;
+ struct snd_sof_widget *swidget;
+ int ret;
+
+ list_for_each_entry(swidget, &sdev->widget_list, list) {
+ if (swidget->dynamic_pipeline_widget) {
+ *dyn_widgets = true;
+ continue;
+ }
+
+ /* Do not free widgets for static pipelines with FW older than SOF2.2 */
+ if (!verify && !swidget->dynamic_pipeline_widget &&
+ SOF_FW_VER(v->major, v->minor, v->micro) < SOF_FW_VER(2, 2, 0)) {
+ mutex_lock(&swidget->setup_mutex);
+ swidget->use_count = 0;
+ mutex_unlock(&swidget->setup_mutex);
+ if (swidget->spipe)
+ swidget->spipe->complete = 0;
+ continue;
+ }
+
+ if (include_scheduler && swidget->id != snd_soc_dapm_scheduler)
+ continue;
+
+ if (!include_scheduler && swidget->id == snd_soc_dapm_scheduler)
+ continue;
+
+ ret = sof_widget_free(sdev, swidget);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
/*
* For older firmware, this function doesn't free widgets for static pipelines during suspend.
* It only resets use_count for all widgets.
@@ -2376,29 +2414,18 @@ static int sof_ipc3_tear_down_all_pipelines(struct snd_sof_dev *sdev, bool verif
* This function is called during suspend and for one-time topology verification during
* first boot. In both cases, there is no need to protect swidget->use_count and
* sroute->setup because during suspend all running streams are suspended and during
- * topology loading the sound card unavailable to open PCMs.
+ * topology loading the sound card unavailable to open PCMs. Do not free the scheduler
+ * widgets yet so that the secondary cores do not get powered down before all the widgets
+ * associated with the scheduler are freed.
*/
- list_for_each_entry(swidget, &sdev->widget_list, list) {
- if (swidget->dynamic_pipeline_widget) {
- dyn_widgets = true;
- continue;
- }
+ ret = sof_ipc3_free_widgets_in_list(sdev, false, &dyn_widgets, verify);
+ if (ret < 0)
+ return ret;
- /* Do not free widgets for static pipelines with FW older than SOF2.2 */
- if (!verify && !swidget->dynamic_pipeline_widget &&
- SOF_FW_VER(v->major, v->minor, v->micro) < SOF_FW_VER(2, 2, 0)) {
- mutex_lock(&swidget->setup_mutex);
- swidget->use_count = 0;
- mutex_unlock(&swidget->setup_mutex);
- if (swidget->spipe)
- swidget->spipe->complete = 0;
- continue;
- }
-
- ret = sof_widget_free(sdev, swidget);
- if (ret < 0)
- return ret;
- }
+ /* free all the scheduler widgets now */
+ ret = sof_ipc3_free_widgets_in_list(sdev, true, &dyn_widgets, verify);
+ if (ret < 0)
+ return ret;
/*
* Tear down all pipelines associated with PCMs that did not get suspended
From 8c427cc2fa73684ea140999e121b7b6c1c717632 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 24 Jan 2024 00:02:34 +0900
Subject: [PATCH 363/637] tracing/probes: Fix to show a parse error for bad
type for $comm
Fix to show a parse error for bad type (non-string) for $comm/$COMM and
immediate-string. With this fix, error_log file shows appropriate error
message as below.
/sys/kernel/tracing # echo 'p vfs_read $comm:u32' >> kprobe_events
sh: write error: Invalid argument
/sys/kernel/tracing # echo 'p vfs_read \"hoge":u32' >> kprobe_events
sh: write error: Invalid argument
/sys/kernel/tracing # cat error_log
[ 30.144183] trace_kprobe: error: $comm and immediate-string only accepts string type
Command: p vfs_read $comm:u32
^
[ 62.618500] trace_kprobe: error: $comm and immediate-string only accepts string type
Command: p vfs_read \"hoge":u32
^
Link: https://lore.kernel.org/all/170602215411.215583.2238016352271091852.stgit@devnote2/
Fixes: 3dd1f7f24f8c ("tracing: probeevent: Fix to make the type of $comm string")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/trace/trace_probe.c | 7 +++++--
kernel/trace/trace_probe.h | 3 ++-
2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 4dc74d73fc1d..c6da5923e5b9 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1159,9 +1159,12 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
if (!(ctx->flags & TPARG_FL_TEVENT) &&
(strcmp(arg, "$comm") == 0 || strcmp(arg, "$COMM") == 0 ||
strncmp(arg, "\\\"", 2) == 0)) {
- /* The type of $comm must be "string", and not an array. */
- if (parg->count || (t && strcmp(t, "string")))
+ /* The type of $comm must be "string", and not an array type. */
+ if (parg->count || (t && strcmp(t, "string"))) {
+ trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0),
+ NEED_STRING_TYPE);
goto out;
+ }
parg->type = find_fetch_type("string", ctx->flags);
} else
parg->type = find_fetch_type(t, ctx->flags);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 850d9ecb6765..c1877d018269 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -515,7 +515,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \
C(NO_BTF_FIELD, "This field is not found."), \
C(BAD_BTF_TID, "Failed to get BTF type info."),\
- C(BAD_TYPE4STR, "This type does not fit for string."),
+ C(BAD_TYPE4STR, "This type does not fit for string."),\
+ C(NEED_STRING_TYPE, "$comm and immediate-string only accepts string type"),
#undef C
#define C(a, b) TP_ERR_##a
From 9a571c1e275cedacd48c66a6bddd0c23f1dffdbf Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 24 Jan 2024 00:03:02 +0900
Subject: [PATCH 364/637] tracing/probes: Fix to set arg size and fmt after
setting type from BTF
Since the BTF type setting updates probe_arg::type, the type size
calculation and setting print-fmt should be done after that.
Without this fix, the argument size and print-fmt can be wrong.
Link: https://lore.kernel.org/all/170602218196.215583.6417859469540955777.stgit@devnote2/
Fixes: b576e09701c7 ("tracing/probes: Support function parameters if BTF is available")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/trace/trace_probe.c | 25 +++++++++++++------------
1 file changed, 13 insertions(+), 12 deletions(-)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index c6da5923e5b9..34289f9c6707 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1172,18 +1172,6 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE);
goto out;
}
- parg->offset = *size;
- *size += parg->type->size * (parg->count ?: 1);
-
- ret = -ENOMEM;
- if (parg->count) {
- len = strlen(parg->type->fmttype) + 6;
- parg->fmt = kmalloc(len, GFP_KERNEL);
- if (!parg->fmt)
- goto out;
- snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
- parg->count);
- }
code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL);
if (!code)
@@ -1207,6 +1195,19 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
goto fail;
}
}
+ parg->offset = *size;
+ *size += parg->type->size * (parg->count ?: 1);
+
+ if (parg->count) {
+ len = strlen(parg->type->fmttype) + 6;
+ parg->fmt = kmalloc(len, GFP_KERNEL);
+ if (!parg->fmt) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
+ parg->count);
+ }
ret = -EINVAL;
/* Store operation */
From 9efd24ec5599ed485b7c4d9aeb731141f6285167 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Tue, 19 Sep 2023 09:28:23 +0800
Subject: [PATCH 365/637] kprobes: Remove unnecessary initial values of
variables
ri and sym is assigned first, so it does not need to initialize the
assignment.
Link: https://lore.kernel.org/all/20230919012823.7815-1-zeming@nfschina.com/
Signed-off-by: Li zeming <zeming@nfschina.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/kprobes.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d5a0ee40bf66..9d9095e81792 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1993,7 +1993,7 @@ NOKPROBE_SYMBOL(__kretprobe_find_ret_addr);
unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp,
struct llist_node **cur)
{
- struct kretprobe_instance *ri = NULL;
+ struct kretprobe_instance *ri;
kprobe_opcode_t *ret;
if (WARN_ON_ONCE(!cur))
@@ -2802,7 +2802,7 @@ static int show_kprobe_addr(struct seq_file *pi, void *v)
{
struct hlist_head *head;
struct kprobe *p, *kp;
- const char *sym = NULL;
+ const char *sym;
unsigned int i = *(loff_t *) v;
unsigned long offset = 0;
char *modname, namebuf[KSYM_NAME_LEN];
From 3ca8fbabcceb8bfe44f7f50640092fd8f1de375c Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 8 Feb 2024 16:02:50 +0000
Subject: [PATCH 366/637] Revert "kobject: Remove redundant checks for whether
ktype is NULL"
This reverts commit 1b28cb81dab7c1eedc6034206f4e8d644046ad31.
It is reported to cause problems, so revert it for now until the root
cause can be found.
Reported-by: kernel test robot <oliver.sang@intel.com>
Fixes: 1b28cb81dab7 ("kobject: Remove redundant checks for whether ktype is NULL")
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Closes: https://lore.kernel.org/oe-lkp/202402071403.e302e33a-oliver.sang@intel.com
Link: https://lore.kernel.org/r/2024020849-consensus-length-6264@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
lib/kobject.c | 24 ++++++++++++++----------
1 file changed, 14 insertions(+), 10 deletions(-)
diff --git a/lib/kobject.c b/lib/kobject.c
index 59dbcbdb1c91..72fa20f405f1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -74,10 +74,12 @@ static int create_dir(struct kobject *kobj)
if (error)
return error;
- error = sysfs_create_groups(kobj, ktype->default_groups);
- if (error) {
- sysfs_remove_dir(kobj);
- return error;
+ if (ktype) {
+ error = sysfs_create_groups(kobj, ktype->default_groups);
+ if (error) {
+ sysfs_remove_dir(kobj);
+ return error;
+ }
}
/*
@@ -589,7 +591,8 @@ static void __kobject_del(struct kobject *kobj)
sd = kobj->sd;
ktype = get_ktype(kobj);
- sysfs_remove_groups(kobj, ktype->default_groups);
+ if (ktype)
+ sysfs_remove_groups(kobj, ktype->default_groups);
/* send "remove" if the caller did not do it but sent "add" */
if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) {
@@ -666,6 +669,10 @@ static void kobject_cleanup(struct kobject *kobj)
pr_debug("'%s' (%p): %s, parent %p\n",
kobject_name(kobj), kobj, __func__, kobj->parent);
+ if (t && !t->release)
+ pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
+ kobject_name(kobj), kobj);
+
/* remove from sysfs if the caller did not do it */
if (kobj->state_in_sysfs) {
pr_debug("'%s' (%p): auto cleanup kobject_del\n",
@@ -676,13 +683,10 @@ static void kobject_cleanup(struct kobject *kobj)
parent = NULL;
}
- if (t->release) {
+ if (t && t->release) {
pr_debug("'%s' (%p): calling ktype release\n",
kobject_name(kobj), kobj);
t->release(kobj);
- } else {
- pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n",
- kobject_name(kobj), kobj);
}
/* free name if we allocated it */
@@ -1056,7 +1060,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa
{
const struct kobj_ns_type_operations *ops = NULL;
- if (parent && parent->ktype->child_ns_type)
+ if (parent && parent->ktype && parent->ktype->child_ns_type)
ops = parent->ktype->child_ns_type(parent);
return ops;
From 45be0882c5f91e1b92e645001dd1a53b3bd58c97 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 5 Feb 2024 14:43:17 -0600
Subject: [PATCH 367/637] smb3: add missing null server pointer check
Address static checker warning in cifs_ses_get_chan_index():
warn: variable dereferenced before check 'server'
To be consistent, and reduce risk, we should add another check
for null server pointer.
Fixes: 88675b22d34e ("cifs: do not search for channel if server is terminating")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/sess.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index ed4bd88dd528..476d54fceb50 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -76,7 +76,7 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
unsigned int i;
/* if the channel is waiting for termination */
- if (server->terminate)
+ if (server && server->terminate)
return CIFS_INVAL_CHAN_INDEX;
for (i = 0; i < ses->chan_count; i++) {
From 55c7788c37242702868bfac7861cdf0c358d6c3d Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Fri, 2 Feb 2024 12:38:24 -0300
Subject: [PATCH 368/637] smb: client: set correct d_type for reparse points
under DFS mounts
Send query dir requests with an info level of
SMB_FIND_FILE_FULL_DIRECTORY_INFO rather than
SMB_FIND_FILE_DIRECTORY_INFO when the client is generating its own
inode numbers (e.g. noserverino) so that reparse tags still
can be parsed directly from the responses, but server won't
send UniqueId (server inode number)
Signed-off-by: Paulo Alcantara <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/readdir.c | 15 ++++++++-------
fs/smb/client/smb2pdu.c | 6 ++++++
2 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 3b1b01d10f7d..b520eea7bfce 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -307,14 +307,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
}
static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr,
- SEARCH_ID_FULL_DIR_INFO *info,
+ const void *info,
struct cifs_sb_info *cifs_sb)
{
+ const FILE_FULL_DIRECTORY_INFO *di = info;
+
__dir_info_to_fattr(fattr, info);
- /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */
+ /* See MS-FSCC 2.4.14, 2.4.19 */
if (fattr->cf_cifsattrs & ATTR_REPARSE)
- fattr->cf_cifstag = le32_to_cpu(info->EaSize);
+ fattr->cf_cifstag = le32_to_cpu(di->EaSize);
cifs_fill_common_info(fattr, cifs_sb);
}
@@ -396,7 +398,7 @@ ffirst_retry:
} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
} else /* not srvinos - BB fixme add check for backlevel? */ {
- cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
+ cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
}
search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME;
@@ -987,10 +989,9 @@ static int cifs_filldir(char *find_entry, struct file *file,
(FIND_FILE_STANDARD_INFO *)find_entry,
cifs_sb);
break;
+ case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
case SMB_FIND_FILE_ID_FULL_DIR_INFO:
- cifs_fulldir_info_to_fattr(&fattr,
- (SEARCH_ID_FULL_DIR_INFO *)find_entry,
- cifs_sb);
+ cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb);
break;
default:
cifs_dir_info_to_fattr(&fattr,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c58fa44dd6b0..4085ce27fd38 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -5206,6 +5206,9 @@ int SMB2_query_directory_init(const unsigned int xid,
case SMB_FIND_FILE_POSIX_INFO:
req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO;
break;
+ case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+ req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION;
+ break;
default:
cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
info_level);
@@ -5275,6 +5278,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon,
/* note that posix payload are variable size */
info_buf_size = sizeof(struct smb2_posix_info);
break;
+ case SMB_FIND_FILE_FULL_DIRECTORY_INFO:
+ info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO);
+ break;
default:
cifs_tcon_dbg(VFS, "info level %u isn't supported\n",
srch_inf->info_level);
From 2a427b49d02995ea4a6ff93a1432c40fa4d36821 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 20 Nov 2023 12:25:56 -1000
Subject: [PATCH 369/637] blk-iocost: Fix an UBSAN shift-out-of-bounds warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When iocg_kick_delay() is called from a CPU different than the one which set
the delay, @now may be in the past of @iocg->delay_at leading to the
following warning:
UBSAN: shift-out-of-bounds in block/blk-iocost.c:1359:23
shift exponent 18446744073709 is too large for 64-bit type 'u64' (aka 'unsigned long long')
...
Call Trace:
<TASK>
dump_stack_lvl+0x79/0xc0
__ubsan_handle_shift_out_of_bounds+0x2ab/0x300
iocg_kick_delay+0x222/0x230
ioc_rqos_merge+0x1d7/0x2c0
__rq_qos_merge+0x2c/0x80
bio_attempt_back_merge+0x83/0x190
blk_attempt_plug_merge+0x101/0x150
blk_mq_submit_bio+0x2b1/0x720
submit_bio_noacct_nocheck+0x320/0x3e0
__swap_writepage+0x2ab/0x9d0
The underflow itself doesn't really affect the behavior in any meaningful
way; however, the past timestamp may exaggerate the delay amount calculated
later in the code, which shouldn't be a material problem given the nature of
the delay mechanism.
If @now is in the past, this CPU is racing another CPU which recently set up
the delay and there's nothing this CPU can contribute w.r.t. the delay.
Let's bail early from iocg_kick_delay() in such cases.
Reported-by: Breno Leitão <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 5160a5a53c0c ("blk-iocost: implement delay adjustment hysteresis")
Link: https://lore.kernel.org/r/ZVvc9L_CYk5LO1fT@slm.duckdns.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-iocost.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c8beec6d7df0..04d44f0bcbc8 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1353,6 +1353,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
lockdep_assert_held(&iocg->waitq.lock);
+ /*
+ * If the delay is set by another CPU, we may be in the past. No need to
+ * change anything if so. This avoids decay calculation underflow.
+ */
+ if (time_before64(now->now, iocg->delay_at))
+ return false;
+
/* calculate the current delay in effect - 1/2 every second */
tdelta = now->now - iocg->delay_at;
if (iocg->delay)
From c23de7ceae59e4ca5894c3ecf4f785c50c0fa428 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Mon, 5 Feb 2024 18:51:26 +0100
Subject: [PATCH 370/637] docs: kernel_feat.py: fix build error for missing
files
If the directory passed to the '.. kernel-feat::' directive does not
exist or the get_feat.pl script does not find any files to extract
features from, Sphinx will report the following error:
Sphinx parallel build error:
UnboundLocalError: local variable 'fname' referenced before assignment
make[2]: *** [Documentation/Makefile:102: htmldocs] Error 2
This is due to how I changed the script in c48a7c44a1d0 ("docs:
kernel_feat.py: fix potential command injection"). Before that, the
filename passed along to self.nestedParse() in this case was weirdly
just the whole get_feat.pl invocation.
We can fix it by doing what kernel_abi.py does -- just pass
self.arguments[0] as 'fname'.
Fixes: c48a7c44a1d0 ("docs: kernel_feat.py: fix potential command injection")
Cc: Justin Forbes <jforbes@fedoraproject.org>
Cc: Salvatore Bonaccorso <carnil@debian.org>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Link: https://lore.kernel.org/r/20240205175133.774271-2-vegard.nossum@oracle.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
Documentation/sphinx/kernel_feat.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/sphinx/kernel_feat.py b/Documentation/sphinx/kernel_feat.py
index b9df61eb4501..03ace5f01b5c 100644
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -109,7 +109,7 @@ class KernelFeat(Directive):
else:
out_lines += line + "\n"
- nodeList = self.nestedParse(out_lines, fname)
+ nodeList = self.nestedParse(out_lines, self.arguments[0])
return nodeList
def nestedParse(self, lines, fname):
From 4ce6e2db00de8103a0687fb0f65fd17124a51aaa Mon Sep 17 00:00:00 2001
From: Yi Sun <yi.sun@unisoc.com>
Date: Mon, 29 Jan 2024 16:52:50 +0800
Subject: [PATCH 371/637] virtio-blk: Ensure no requests in virtqueues before
deleting vqs.
Ensure no remaining requests in virtqueues before resetting vdev and
deleting virtqueues. Otherwise these requests will never be completed.
It may cause the system to become unresponsive.
Function blk_mq_quiesce_queue() can ensure that requests have become
in_flight status, but it cannot guarantee that requests have been
processed by the device. Virtqueues should never be deleted before
all requests become complete status.
Function blk_mq_freeze_queue() ensure that all requests in virtqueues
become complete status. And no requests can enter in virtqueues.
Signed-off-by: Yi Sun <yi.sun@unisoc.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://lore.kernel.org/r/20240129085250.1550594-1-yi.sun@unisoc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/block/virtio_blk.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5bf98fd6a651..2bf14a0e2815 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1593,14 +1593,15 @@ static int virtblk_freeze(struct virtio_device *vdev)
{
struct virtio_blk *vblk = vdev->priv;
+ /* Ensure no requests in virtqueues before deleting vqs. */
+ blk_mq_freeze_queue(vblk->disk->queue);
+
/* Ensure we don't receive any more interrupts */
virtio_reset_device(vdev);
/* Make sure no work handler is accessing the device. */
flush_work(&vblk->config_work);
- blk_mq_quiesce_queue(vblk->disk->queue);
-
vdev->config->del_vqs(vdev);
kfree(vblk->vqs);
@@ -1618,7 +1619,7 @@ static int virtblk_restore(struct virtio_device *vdev)
virtio_device_ready(vdev);
- blk_mq_unquiesce_queue(vblk->disk->queue);
+ blk_mq_unfreeze_queue(vblk->disk->queue);
return 0;
}
#endif
From 53c0441dd2c44ee93fddb5473885fd41e4bc2361 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 7 Feb 2024 12:59:02 +0100
Subject: [PATCH 372/637] dpll: fix possible deadlock during netlink dump
operation
Recently, I've been hitting following deadlock warning during dpll pin
dump:
[52804.637962] ======================================================
[52804.638536] WARNING: possible circular locking dependency detected
[52804.639111] 6.8.0-rc2jiri+ #1 Not tainted
[52804.639529] ------------------------------------------------------
[52804.640104] python3/2984 is trying to acquire lock:
[52804.640581] ffff88810e642678 (nlk_cb_mutex-GENERIC){+.+.}-{3:3}, at: netlink_dump+0xb3/0x780
[52804.641417]
but task is already holding lock:
[52804.642010] ffffffff83bde4c8 (dpll_lock){+.+.}-{3:3}, at: dpll_lock_dumpit+0x13/0x20
[52804.642747]
which lock already depends on the new lock.
[52804.643551]
the existing dependency chain (in reverse order) is:
[52804.644259]
-> #1 (dpll_lock){+.+.}-{3:3}:
[52804.644836] lock_acquire+0x174/0x3e0
[52804.645271] __mutex_lock+0x119/0x1150
[52804.645723] dpll_lock_dumpit+0x13/0x20
[52804.646169] genl_start+0x266/0x320
[52804.646578] __netlink_dump_start+0x321/0x450
[52804.647056] genl_family_rcv_msg_dumpit+0x155/0x1e0
[52804.647575] genl_rcv_msg+0x1ed/0x3b0
[52804.648001] netlink_rcv_skb+0xdc/0x210
[52804.648440] genl_rcv+0x24/0x40
[52804.648831] netlink_unicast+0x2f1/0x490
[52804.649290] netlink_sendmsg+0x36d/0x660
[52804.649742] __sock_sendmsg+0x73/0xc0
[52804.650165] __sys_sendto+0x184/0x210
[52804.650597] __x64_sys_sendto+0x72/0x80
[52804.651045] do_syscall_64+0x6f/0x140
[52804.651474] entry_SYSCALL_64_after_hwframe+0x46/0x4e
[52804.652001]
-> #0 (nlk_cb_mutex-GENERIC){+.+.}-{3:3}:
[52804.652650] check_prev_add+0x1ae/0x1280
[52804.653107] __lock_acquire+0x1ed3/0x29a0
[52804.653559] lock_acquire+0x174/0x3e0
[52804.653984] __mutex_lock+0x119/0x1150
[52804.654423] netlink_dump+0xb3/0x780
[52804.654845] __netlink_dump_start+0x389/0x450
[52804.655321] genl_family_rcv_msg_dumpit+0x155/0x1e0
[52804.655842] genl_rcv_msg+0x1ed/0x3b0
[52804.656272] netlink_rcv_skb+0xdc/0x210
[52804.656721] genl_rcv+0x24/0x40
[52804.657119] netlink_unicast+0x2f1/0x490
[52804.657570] netlink_sendmsg+0x36d/0x660
[52804.658022] __sock_sendmsg+0x73/0xc0
[52804.658450] __sys_sendto+0x184/0x210
[52804.658877] __x64_sys_sendto+0x72/0x80
[52804.659322] do_syscall_64+0x6f/0x140
[52804.659752] entry_SYSCALL_64_after_hwframe+0x46/0x4e
[52804.660281]
other info that might help us debug this:
[52804.661077] Possible unsafe locking scenario:
[52804.661671] CPU0 CPU1
[52804.662129] ---- ----
[52804.662577] lock(dpll_lock);
[52804.662924] lock(nlk_cb_mutex-GENERIC);
[52804.663538] lock(dpll_lock);
[52804.664073] lock(nlk_cb_mutex-GENERIC);
[52804.664490]
The issue as follows: __netlink_dump_start() calls control->start(cb)
with nlk->cb_mutex held. In control->start(cb) the dpll_lock is taken.
Then nlk->cb_mutex is released and taken again in netlink_dump(), while
dpll_lock still being held. That leads to ABBA deadlock when another
CPU races with the same operation.
Fix this by moving dpll_lock taking into dumpit() callback which ensures
correct lock taking order.
Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Link: https://lore.kernel.org/r/20240207115902.371649-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
Documentation/netlink/specs/dpll.yaml | 4 ----
drivers/dpll/dpll_netlink.c | 20 ++++++--------------
drivers/dpll/dpll_nl.c | 4 ----
drivers/dpll/dpll_nl.h | 2 --
4 files changed, 6 insertions(+), 24 deletions(-)
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index b14aed18065f..3dcc9ece272a 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -384,8 +384,6 @@ operations:
- type
dump:
- pre: dpll-lock-dumpit
- post: dpll-unlock-dumpit
reply: *dev-attrs
-
@@ -473,8 +471,6 @@ operations:
- fractional-frequency-offset
dump:
- pre: dpll-lock-dumpit
- post: dpll-unlock-dumpit
request:
attributes:
- id
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 314bb3775465..4ca9ad16cd95 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -1199,6 +1199,7 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
unsigned long i;
int ret = 0;
+ mutex_lock(&dpll_lock);
xa_for_each_marked_start(&dpll_pin_xa, i, pin, DPLL_REGISTERED,
ctx->idx) {
if (!dpll_pin_available(pin))
@@ -1218,6 +1219,8 @@ int dpll_nl_pin_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
}
genlmsg_end(skb, hdr);
}
+ mutex_unlock(&dpll_lock);
+
if (ret == -EMSGSIZE) {
ctx->idx = i;
return skb->len;
@@ -1373,6 +1376,7 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
unsigned long i;
int ret = 0;
+ mutex_lock(&dpll_lock);
xa_for_each_marked_start(&dpll_device_xa, i, dpll, DPLL_REGISTERED,
ctx->idx) {
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
@@ -1389,6 +1393,8 @@ int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
}
genlmsg_end(skb, hdr);
}
+ mutex_unlock(&dpll_lock);
+
if (ret == -EMSGSIZE) {
ctx->idx = i;
return skb->len;
@@ -1439,20 +1445,6 @@ dpll_unlock_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
mutex_unlock(&dpll_lock);
}
-int dpll_lock_dumpit(struct netlink_callback *cb)
-{
- mutex_lock(&dpll_lock);
-
- return 0;
-}
-
-int dpll_unlock_dumpit(struct netlink_callback *cb)
-{
- mutex_unlock(&dpll_lock);
-
- return 0;
-}
-
int dpll_pin_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
struct genl_info *info)
{
diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c
index eaee5be7aa64..1e95f5397cfc 100644
--- a/drivers/dpll/dpll_nl.c
+++ b/drivers/dpll/dpll_nl.c
@@ -95,9 +95,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
},
{
.cmd = DPLL_CMD_DEVICE_GET,
- .start = dpll_lock_dumpit,
.dumpit = dpll_nl_device_get_dumpit,
- .done = dpll_unlock_dumpit,
.flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
},
{
@@ -129,9 +127,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
},
{
.cmd = DPLL_CMD_PIN_GET,
- .start = dpll_lock_dumpit,
.dumpit = dpll_nl_pin_get_dumpit,
- .done = dpll_unlock_dumpit,
.policy = dpll_pin_get_dump_nl_policy,
.maxattr = DPLL_A_PIN_ID,
.flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h
index 92d4c9c4f788..f491262bee4f 100644
--- a/drivers/dpll/dpll_nl.h
+++ b/drivers/dpll/dpll_nl.h
@@ -30,8 +30,6 @@ dpll_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
void
dpll_pin_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
struct genl_info *info);
-int dpll_lock_dumpit(struct netlink_callback *cb);
-int dpll_unlock_dumpit(struct netlink_callback *cb);
int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info);
int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info);
From aa1eec2f546f2afa8c98ec41e5d8ee488165d685 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 6 Feb 2024 17:43:28 +0100
Subject: [PATCH 373/637] net/mlx5: DPLL, Fix possible use after free after
delayed work timer triggers
I managed to hit following use after free warning recently:
[ 2169.711665] ==================================================================
[ 2169.714009] BUG: KASAN: slab-use-after-free in __run_timers.part.0+0x179/0x4c0
[ 2169.716293] Write of size 8 at addr ffff88812b326a70 by task swapper/4/0
[ 2169.719022] CPU: 4 PID: 0 Comm: swapper/4 Not tainted 6.8.0-rc2jiri+ #2
[ 2169.720974] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 2169.722457] Call Trace:
[ 2169.722756] <IRQ>
[ 2169.723024] dump_stack_lvl+0x58/0xb0
[ 2169.723417] print_report+0xc5/0x630
[ 2169.723807] ? __virt_addr_valid+0x126/0x2b0
[ 2169.724268] kasan_report+0xbe/0xf0
[ 2169.724667] ? __run_timers.part.0+0x179/0x4c0
[ 2169.725116] ? __run_timers.part.0+0x179/0x4c0
[ 2169.725570] __run_timers.part.0+0x179/0x4c0
[ 2169.726003] ? call_timer_fn+0x320/0x320
[ 2169.726404] ? lock_downgrade+0x3a0/0x3a0
[ 2169.726820] ? kvm_clock_get_cycles+0x14/0x20
[ 2169.727257] ? ktime_get+0x92/0x150
[ 2169.727630] ? lapic_next_deadline+0x35/0x60
[ 2169.728069] run_timer_softirq+0x40/0x80
[ 2169.728475] __do_softirq+0x1a1/0x509
[ 2169.728866] irq_exit_rcu+0x95/0xc0
[ 2169.729241] sysvec_apic_timer_interrupt+0x6b/0x80
[ 2169.729718] </IRQ>
[ 2169.729993] <TASK>
[ 2169.730259] asm_sysvec_apic_timer_interrupt+0x16/0x20
[ 2169.730755] RIP: 0010:default_idle+0x13/0x20
[ 2169.731190] Code: c0 08 00 00 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 72 ff ff ff cc cc cc cc 8b 05 9a 7f 1f 02 85 c0 7e 07 0f 00 2d cf 69 43 00 fb f4 <fa> c3 66 66 2e 0f 1f 84 00 00 00 00 00 65 48 8b 04 25 c0 93 04 00
[ 2169.732759] RSP: 0018:ffff888100dbfe10 EFLAGS: 00000242
[ 2169.733264] RAX: 0000000000000001 RBX: ffff888100d9c200 RCX: ffffffff8241bd62
[ 2169.733925] RDX: ffffed109a848b15 RSI: 0000000000000004 RDI: ffffffff8127ac55
[ 2169.734566] RBP: 0000000000000004 R08: 0000000000000000 R09: ffffed109a848b14
[ 2169.735200] R10: ffff8884d42458a3 R11: 000000000000ba7e R12: ffffffff83d7d3a0
[ 2169.735835] R13: 1ffff110201b7fc6 R14: 0000000000000000 R15: ffff888100d9c200
[ 2169.736478] ? ct_kernel_exit.constprop.0+0xa2/0xc0
[ 2169.736954] ? do_idle+0x285/0x290
[ 2169.737323] default_idle_call+0x63/0x90
[ 2169.737730] do_idle+0x285/0x290
[ 2169.738089] ? arch_cpu_idle_exit+0x30/0x30
[ 2169.738511] ? mark_held_locks+0x1a/0x80
[ 2169.738917] ? lockdep_hardirqs_on_prepare+0x12e/0x200
[ 2169.739417] cpu_startup_entry+0x30/0x40
[ 2169.739825] start_secondary+0x19a/0x1c0
[ 2169.740229] ? set_cpu_sibling_map+0xbd0/0xbd0
[ 2169.740673] secondary_startup_64_no_verify+0x15d/0x16b
[ 2169.741179] </TASK>
[ 2169.741686] Allocated by task 1098:
[ 2169.742058] kasan_save_stack+0x1c/0x40
[ 2169.742456] kasan_save_track+0x10/0x30
[ 2169.742852] __kasan_kmalloc+0x83/0x90
[ 2169.743246] mlx5_dpll_probe+0xf5/0x3c0 [mlx5_dpll]
[ 2169.743730] auxiliary_bus_probe+0x62/0xb0
[ 2169.744148] really_probe+0x127/0x590
[ 2169.744534] __driver_probe_device+0xd2/0x200
[ 2169.744973] device_driver_attach+0x6b/0xf0
[ 2169.745402] bind_store+0x90/0xe0
[ 2169.745761] kernfs_fop_write_iter+0x1df/0x2a0
[ 2169.746210] vfs_write+0x41f/0x790
[ 2169.746579] ksys_write+0xc7/0x160
[ 2169.746947] do_syscall_64+0x6f/0x140
[ 2169.747333] entry_SYSCALL_64_after_hwframe+0x46/0x4e
[ 2169.748049] Freed by task 1220:
[ 2169.748393] kasan_save_stack+0x1c/0x40
[ 2169.748789] kasan_save_track+0x10/0x30
[ 2169.749188] kasan_save_free_info+0x3b/0x50
[ 2169.749621] poison_slab_object+0x106/0x180
[ 2169.750044] __kasan_slab_free+0x14/0x50
[ 2169.750451] kfree+0x118/0x330
[ 2169.750792] mlx5_dpll_remove+0xf5/0x110 [mlx5_dpll]
[ 2169.751271] auxiliary_bus_remove+0x2e/0x40
[ 2169.751694] device_release_driver_internal+0x24b/0x2e0
[ 2169.752191] unbind_store+0xa6/0xb0
[ 2169.752563] kernfs_fop_write_iter+0x1df/0x2a0
[ 2169.753004] vfs_write+0x41f/0x790
[ 2169.753381] ksys_write+0xc7/0x160
[ 2169.753750] do_syscall_64+0x6f/0x140
[ 2169.754132] entry_SYSCALL_64_after_hwframe+0x46/0x4e
[ 2169.754847] Last potentially related work creation:
[ 2169.755315] kasan_save_stack+0x1c/0x40
[ 2169.755709] __kasan_record_aux_stack+0x9b/0xf0
[ 2169.756165] __queue_work+0x382/0x8f0
[ 2169.756552] call_timer_fn+0x126/0x320
[ 2169.756941] __run_timers.part.0+0x2ea/0x4c0
[ 2169.757376] run_timer_softirq+0x40/0x80
[ 2169.757782] __do_softirq+0x1a1/0x509
[ 2169.758387] Second to last potentially related work creation:
[ 2169.758924] kasan_save_stack+0x1c/0x40
[ 2169.759322] __kasan_record_aux_stack+0x9b/0xf0
[ 2169.759773] __queue_work+0x382/0x8f0
[ 2169.760156] call_timer_fn+0x126/0x320
[ 2169.760550] __run_timers.part.0+0x2ea/0x4c0
[ 2169.760978] run_timer_softirq+0x40/0x80
[ 2169.761381] __do_softirq+0x1a1/0x509
[ 2169.761998] The buggy address belongs to the object at ffff88812b326a00
which belongs to the cache kmalloc-256 of size 256
[ 2169.763061] The buggy address is located 112 bytes inside of
freed 256-byte region [ffff88812b326a00, ffff88812b326b00)
[ 2169.764346] The buggy address belongs to the physical page:
[ 2169.764866] page:000000000f2b1e89 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12b324
[ 2169.765731] head:000000000f2b1e89 order:2 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[ 2169.766484] anon flags: 0x200000000000840(slab|head|node=0|zone=2)
[ 2169.767048] page_type: 0xffffffff()
[ 2169.767422] raw: 0200000000000840 ffff888100042b40 0000000000000000 dead000000000001
[ 2169.768183] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000
[ 2169.768899] page dumped because: kasan: bad access detected
[ 2169.769649] Memory state around the buggy address:
[ 2169.770116] ffff88812b326900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 2169.770805] ffff88812b326980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 2169.771485] >ffff88812b326a00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 2169.772173] ^
[ 2169.772787] ffff88812b326a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[ 2169.773477] ffff88812b326b00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[ 2169.774160] ==================================================================
[ 2169.774845] ==================================================================
I didn't manage to reproduce it. Though the issue seems to be obvious.
There is a chance that the mlx5_dpll_remove() calls
cancel_delayed_work() when the work runs and manages to re-arm itself.
In that case, after delay timer triggers next attempt to queue it,
it works with freed memory.
Fix this by using cancel_delayed_work_sync() instead which makes sure
that work is done when it returns.
Fixes: 496fd0a26bbf ("mlx5: Implement SyncE support using DPLL infrastructure")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240206164328.360313-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/mellanox/mlx5/core/dpll.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 18fed2b34fb1..928bf24d4b12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -389,7 +389,7 @@ static void mlx5_dpll_remove(struct auxiliary_device *adev)
struct mlx5_dpll *mdpll = auxiliary_get_drvdata(adev);
struct mlx5_core_dev *mdev = mdpll->mdev;
- cancel_delayed_work(&mdpll->work);
+ cancel_delayed_work_sync(&mdpll->work);
mlx5_dpll_mdev_netdev_untrack(mdpll, mdev);
destroy_workqueue(mdpll->wq);
dpll_pin_unregister(mdpll->dpll, mdpll->dpll_pin,
From 4e1d71cabb19ec2586827adfc60d68689c68c194 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 6 Feb 2024 14:16:31 -0500
Subject: [PATCH 374/637] net/handshake: Fix handshake_req_destroy_test1
Recently, handshake_req_destroy_test1 started failing:
Expected handshake_req_destroy_test == req, but
handshake_req_destroy_test == 0000000000000000
req == 0000000060f99b40
not ok 11 req_destroy works
This is because "sock_release(sock)" was replaced with "fput(filp)"
to address a memory leak. Note that sock_release() is synchronous
but fput() usually delays the final close and clean-up.
The delay is not consequential in the other cases that were changed
but handshake_req_destroy_test1 is testing that handshake_req_cancel()
followed by closing the file actually does call the ->hp_destroy
method. Thus the PTR_EQ test at the end has to be sure that the
final close is complete before it checks the pointer.
We cannot use a completion here because if ->hp_destroy is never
called (ie, there is an API bug) then the test will hang.
Reported by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/netdev/ZcKDd1to4MPANCrn@tissot.1015granger.net/T/#mac5c6299f86799f1c71776f3a07f9c566c7c3c40
Fixes: 4a0f07d71b04 ("net/handshake: Fix memory leak in __sock_create() and sock_alloc_file()")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/170724699027.91401.7839730697326806733.stgit@oracle-102.nfsv4bat.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/handshake/handshake-test.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c
index 16ed7bfd29e4..34fd1d9b2db8 100644
--- a/net/handshake/handshake-test.c
+++ b/net/handshake/handshake-test.c
@@ -471,7 +471,10 @@ static void handshake_req_destroy_test1(struct kunit *test)
handshake_req_cancel(sock->sk);
/* Act */
- fput(filp);
+ /* Ensure the close/release/put process has run to
+ * completion before checking the result.
+ */
+ __fput_sync(filp);
/* Assert */
KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req);
From 9b0ed890ac2ae233efd8b27d11aee28a19437bb8 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 7 Feb 2024 09:47:36 +0100
Subject: [PATCH 375/637] bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Do not report the XDP capability NETDEV_XDP_ACT_XSK_ZEROCOPY as the
bonding driver does not support XDP and AF_XDP in zero-copy mode even
if the real NIC drivers do.
Note that the driver used to report everything as supported before a
device was bonded. Instead of just masking out the zero-copy support
from this, have the driver report that no XDP feature is supported
until a real device is bonded. This seems to be more truthful as it is
the real drivers that decide what XDP features are supported.
Fixes: cb9e6e584d58 ("bonding: add xdp_features support")
Reported-by: Prashant Batra <prbatra.mail@gmail.com>
Link: https://lore.kernel.org/all/CAJ8uoz2ieZCopgqTvQ9ZY6xQgTbujmC6XkMTamhp68O-h_-rLg@mail.gmail.com/T/
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20240207084737.20890-1-magnus.karlsson@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/bonding/bond_main.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4e0600c7b050..a11748b8d69b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1819,6 +1819,8 @@ void bond_xdp_set_features(struct net_device *bond_dev)
bond_for_each_slave(bond, slave, iter)
val &= slave->dev->xdp_features;
+ val &= ~NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
xdp_set_features_flag(bond_dev, val);
}
@@ -5909,9 +5911,6 @@ void bond_setup(struct net_device *bond_dev)
if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
bond_dev->features |= BOND_XFRM_FEATURES;
#endif /* CONFIG_XFRM_OFFLOAD */
-
- if (bond_xdp_check(bond))
- bond_dev->xdp_features = NETDEV_XDP_ACT_MASK;
}
/* Destroy a bonding device.
From 4ab18af47a2c2a80ac11674122935700caf80cc6 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Tue, 6 Feb 2024 18:17:17 +0200
Subject: [PATCH 376/637] devlink: Fix command annotation documentation
Command example string is not read as command.
Fix command annotation.
Fixes: a8ce7b26a51e ("devlink: Expose port function commands to control migratable")
Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240206161717.466653-1-parav@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
Documentation/networking/devlink/devlink-port.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index e33ad2401ad7..562f46b41274 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using
`devlink port function set roce` command.
Users may also set the function as migratable using
-'devlink port function set migratable' command.
+`devlink port function set migratable` command.
Users may also set the IPsec crypto capability of the function using
`devlink port function set ipsec_crypto` command.
From 02d9009f4e8c27dcf10c3e39bc0666436686a219 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 7 Feb 2024 18:31:10 +0100
Subject: [PATCH 377/637] selftests: net: add more missing kernel config
The reuseport_addr_any.sh is currently skipping DCCP tests and
pmtu.sh is skipping all the FOU/GUE related cases: add the missing
options.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/38d3ca7f909736c1aef56e6244d67c82a9bba6ff.1707326987.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/config | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 3b749addd364..5e4390cac17e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -24,10 +24,14 @@ CONFIG_IFB=y
CONFIG_INET_DIAG=y
CONFIG_INET_ESP=y
CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_NET_FOU=y
+CONFIG_NET_FOU_IP_TUNNELS=y
CONFIG_IP_GRE=m
CONFIG_NETFILTER=y
CONFIG_NETFILTER_ADVANCED=y
CONFIG_NF_CONNTRACK=m
+CONFIG_IPV6_SIT=y
+CONFIG_IP_DCCP=m
CONFIG_NF_NAT=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP_NF_IPTABLES=m
@@ -62,6 +66,7 @@ CONFIG_NET_CLS_MATCHALL=m
CONFIG_NET_CLS_U32=m
CONFIG_NET_IPGRE_DEMUX=m
CONFIG_NET_IPGRE=m
+CONFIG_NET_IPIP=y
CONFIG_NET_SCH_FQ_CODEL=m
CONFIG_NET_SCH_HTB=m
CONFIG_NET_SCH_FQ=m
@@ -78,7 +83,6 @@ CONFIG_TLS=m
CONFIG_TRACEPOINTS=y
CONFIG_NET_DROP_MONITOR=m
CONFIG_NETDEVSIM=m
-CONFIG_NET_FOU=m
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_NET_SCH_INGRESS=m
From 17c8e9ac95d81d10e9619a845a68b83c9384be64 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 31 Jan 2024 13:05:13 +0100
Subject: [PATCH 378/637] RISC-V: paravirt: steal_time should be static
steal_time is not used outside paravirt.c, make it static,
as sparse suggested.
Fixes: fdf68acccfc6 ("RISC-V: paravirt: Implement steal-time support")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/kernel/paravirt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 8e114f5930ce..15c5d4048db5 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -41,7 +41,7 @@ static int __init parse_no_stealacc(char *arg)
early_param("no-steal-acc", parse_no_stealacc);
-DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
+static DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
static bool __init has_pv_steal_clock(void)
{
From 3752219b6007ee0421cc228f442f33b31f85addd Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 31 Jan 2024 13:05:14 +0100
Subject: [PATCH 379/637] RISC-V: paravirt: Use correct restricted types
__le32 and __le64 types should be used with le32_to_cpu() and
le64_to_cpu(), as sparse helpfully points out.
Fixes: fdf68acccfc6 ("RISC-V: paravirt: Implement steal-time support")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401011933.hL9zqmKo-lkp@intel.com/
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/kernel/paravirt.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
index 15c5d4048db5..0d6225fd3194 100644
--- a/arch/riscv/kernel/paravirt.c
+++ b/arch/riscv/kernel/paravirt.c
@@ -91,8 +91,8 @@ static int pv_time_cpu_down_prepare(unsigned int cpu)
static u64 pv_time_steal_clock(int cpu)
{
struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu);
- u32 sequence;
- u64 steal;
+ __le32 sequence;
+ __le64 steal;
/*
* Check the sequence field before and after reading the steal
From f072b272aa27d57cf7fe6fdedb30fb50f391974e Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Wed, 31 Jan 2024 13:05:15 +0100
Subject: [PATCH 380/637] RISC-V: KVM: Use correct restricted types
__le32 and __le64 types should be used with le32_to_cpu() and
le64_to_cpu() and __user is needed for pointers referencing
guest memory, as sparse helpfully points out.
Fixes: e9f12b5fff8a ("RISC-V: KVM: Implement SBI STA extension")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401020142.lwFEDK5v-lkp@intel.com/
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <anup@brainfault.org>
---
arch/riscv/kvm/vcpu_sbi_sta.c | 20 ++++++++++++--------
1 file changed, 12 insertions(+), 8 deletions(-)
diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c
index 01f09fe8c3b0..d8cf9ca28c61 100644
--- a/arch/riscv/kvm/vcpu_sbi_sta.c
+++ b/arch/riscv/kvm/vcpu_sbi_sta.c
@@ -26,8 +26,12 @@ void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
{
gpa_t shmem = vcpu->arch.sta.shmem;
u64 last_steal = vcpu->arch.sta.last_steal;
- u32 *sequence_ptr, sequence;
- u64 *steal_ptr, steal;
+ __le32 __user *sequence_ptr;
+ __le64 __user *steal_ptr;
+ __le32 sequence_le;
+ __le64 steal_le;
+ u32 sequence;
+ u64 steal;
unsigned long hva;
gfn_t gfn;
@@ -47,22 +51,22 @@ void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu)
return;
}
- sequence_ptr = (u32 *)(hva + offset_in_page(shmem) +
+ sequence_ptr = (__le32 __user *)(hva + offset_in_page(shmem) +
offsetof(struct sbi_sta_struct, sequence));
- steal_ptr = (u64 *)(hva + offset_in_page(shmem) +
+ steal_ptr = (__le64 __user *)(hva + offset_in_page(shmem) +
offsetof(struct sbi_sta_struct, steal));
- if (WARN_ON(get_user(sequence, sequence_ptr)))
+ if (WARN_ON(get_user(sequence_le, sequence_ptr)))
return;
- sequence = le32_to_cpu(sequence);
+ sequence = le32_to_cpu(sequence_le);
sequence += 1;
if (WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr)))
return;
- if (!WARN_ON(get_user(steal, steal_ptr))) {
- steal = le64_to_cpu(steal);
+ if (!WARN_ON(get_user(steal_le, steal_ptr))) {
+ steal = le64_to_cpu(steal_le);
vcpu->arch.sta.last_steal = READ_ONCE(current->sched_info.run_delay);
steal += vcpu->arch.sta.last_steal - last_steal;
WARN_ON(put_user(cpu_to_le64(steal), steal_ptr));
From a8b9cf62ade1bf17261a979fc97e40c2d7842353 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 10 Jan 2024 09:13:06 +0900
Subject: [PATCH 381/637] ftrace: Fix DIRECT_CALLS to use SAVE_REGS by default
The commit 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS
and !WITH_REGS") changed DIRECT_CALLS to use SAVE_ARGS when there
are multiple ftrace_ops at the same function, but since the x86 only
support to jump to direct_call from ftrace_regs_caller, when we set
the function tracer on the same target function on x86, ftrace-direct
does not work as below (this actually works on arm64.)
At first, insmod ftrace-direct.ko to put a direct_call on
'wake_up_process()'.
# insmod kernel/samples/ftrace/ftrace-direct.ko
# less trace
...
<idle>-0 [006] ..s1. 564.686958: my_direct_func: waking up rcu_preempt-17
<idle>-0 [007] ..s1. 564.687836: my_direct_func: waking up kcompactd0-63
<idle>-0 [006] ..s1. 564.690926: my_direct_func: waking up rcu_preempt-17
<idle>-0 [006] ..s1. 564.696872: my_direct_func: waking up rcu_preempt-17
<idle>-0 [007] ..s1. 565.191982: my_direct_func: waking up kcompactd0-63
Setup a function filter to the 'wake_up_process' too, and enable it.
# cd /sys/kernel/tracing/
# echo wake_up_process > set_ftrace_filter
# echo function > current_tracer
# less trace
...
<idle>-0 [006] ..s3. 686.180972: wake_up_process <-call_timer_fn
<idle>-0 [006] ..s3. 686.186919: wake_up_process <-call_timer_fn
<idle>-0 [002] ..s3. 686.264049: wake_up_process <-call_timer_fn
<idle>-0 [002] d.h6. 686.515216: wake_up_process <-kick_pool
<idle>-0 [002] d.h6. 686.691386: wake_up_process <-kick_pool
Then, only function tracer is shown on x86.
But if you enable 'kprobe on ftrace' event (which uses SAVE_REGS flag)
on the same function, it is shown again.
# echo 'p wake_up_process' >> dynamic_events
# echo 1 > events/kprobes/p_wake_up_process_0/enable
# echo > trace
# less trace
...
<idle>-0 [006] ..s2. 2710.345919: p_wake_up_process_0: (wake_up_process+0x4/0x20)
<idle>-0 [006] ..s3. 2710.345923: wake_up_process <-call_timer_fn
<idle>-0 [006] ..s1. 2710.345928: my_direct_func: waking up rcu_preempt-17
<idle>-0 [006] ..s2. 2710.349931: p_wake_up_process_0: (wake_up_process+0x4/0x20)
<idle>-0 [006] ..s3. 2710.349934: wake_up_process <-call_timer_fn
<idle>-0 [006] ..s1. 2710.349937: my_direct_func: waking up rcu_preempt-17
To fix this issue, use SAVE_REGS flag for multiple ftrace_ops flag of
direct_call by default.
Link: https://lore.kernel.org/linux-trace-kernel/170484558617.178953.1590516949390270842.stgit@devnote2
Fixes: 60c8971899f3 ("ftrace: Make DIRECT_CALLS work WITH_ARGS and !WITH_REGS")
Cc: stable@vger.kernel.org
Cc: Florent Revest <revest@chromium.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com> [arm64]
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/ftrace.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b01ae7d36021..c060d5b47910 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5325,7 +5325,17 @@ static LIST_HEAD(ftrace_direct_funcs);
static int register_ftrace_function_nolock(struct ftrace_ops *ops);
+/*
+ * If there are multiple ftrace_ops, use SAVE_REGS by default, so that direct
+ * call will be jumped from ftrace_regs_caller. Only if the architecture does
+ * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
+ * jumps from ftrace_caller for multiple ftrace_ops.
+ */
+#ifndef HAVE_DYNAMIC_FTRACE_WITH_REGS
#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
+#else
+#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
+#endif
static int check_direct_multi(struct ftrace_ops *ops)
{
From 7d708c145b2631941b8b0b4a740dc2990818c39c Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Fri, 9 Feb 2024 01:24:54 +0000
Subject: [PATCH 382/637] Revert "usb: dwc3: Support EBC feature of DWC_usb31"
This reverts commit 398aa9a7e77cf23c2a6f882ddd3dcd96f21771dc.
The update to the gadget API to support EBC feature is incomplete. It's
missing at least the following:
* New usage documentation
* Gadget capability check
* Condition for the user to check how many and which endpoints can be
used as "fifo_mode"
* Description of how it can affect completed request (e.g. dwc3 won't
update TRB on completion -- ie. how it can affect request's actual
length report)
Let's revert this until it's ready.
Fixes: 398aa9a7e77c ("usb: dwc3: Support EBC feature of DWC_usb31")
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/3042f847ff904b4dd4e4cf66a1b9df470e63439e.1707441690.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/dwc3/core.h | 1 -
drivers/usb/dwc3/gadget.c | 6 ------
drivers/usb/dwc3/gadget.h | 2 --
include/linux/usb/gadget.h | 1 -
4 files changed, 10 deletions(-)
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index e3eea965e57b..e120611a5174 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -376,7 +376,6 @@
/* Global HWPARAMS4 Register */
#define DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(n) (((n) & (0x0f << 13)) >> 13)
#define DWC3_MAX_HIBER_SCRATCHBUFS 15
-#define DWC3_EXT_BUFF_CONTROL BIT(21)
/* Global HWPARAMS6 Register */
#define DWC3_GHWPARAMS6_BCSUPPORT BIT(14)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 564976b3e2b9..4c8dd6724678 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -673,12 +673,6 @@ static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
params.param1 |= DWC3_DEPCFG_BINTERVAL_M1(bInterval_m1);
}
- if (dep->endpoint.fifo_mode) {
- if (!(dwc->hwparams.hwparams4 & DWC3_EXT_BUFF_CONTROL))
- return -EINVAL;
- params.param1 |= DWC3_DEPCFG_EBC_HWO_NOWB | DWC3_DEPCFG_USE_EBC;
- }
-
return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, ¶ms);
}
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index fd7a4e94397e..55a56cf67d73 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -26,8 +26,6 @@ struct dwc3;
#define DWC3_DEPCFG_XFER_NOT_READY_EN BIT(10)
#define DWC3_DEPCFG_FIFO_ERROR_EN BIT(11)
#define DWC3_DEPCFG_STREAM_EVENT_EN BIT(13)
-#define DWC3_DEPCFG_EBC_HWO_NOWB BIT(14)
-#define DWC3_DEPCFG_USE_EBC BIT(15)
#define DWC3_DEPCFG_BINTERVAL_M1(n) (((n) & 0xff) << 16)
#define DWC3_DEPCFG_STREAM_CAPABLE BIT(24)
#define DWC3_DEPCFG_EP_NUMBER(n) (((n) & 0x1f) << 25)
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index a771ccc038ac..6532beb587b1 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -236,7 +236,6 @@ struct usb_ep {
unsigned max_streams:16;
unsigned mult:2;
unsigned maxburst:5;
- unsigned fifo_mode:1;
u8 address;
const struct usb_endpoint_descriptor *desc;
const struct usb_ss_ep_comp_descriptor *comp_desc;
From f4653ec9861cd96a1a6a3258c4a807898ee8cf3c Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Tue, 6 Feb 2024 17:18:00 -0800
Subject: [PATCH 383/637] of: property: Improve finding the consumer of a
remote-endpoint property
We have a more accurate function to find the right consumer of a
remote-endpoint property instead of searching for a parent with
compatible string property. So, use that instead. While at it, make the
code to find the consumer a bit more flexible and based on the property
being parsed.
Fixes: f7514a663016 ("of: property: fw_devlink: Add support for remote-endpoint")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20240207011803.2637531-2-saravanak@google.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/property.c | 47 +++++++++----------------------------------
1 file changed, 10 insertions(+), 37 deletions(-)
diff --git a/drivers/of/property.c b/drivers/of/property.c
index bbf0dee2fb9c..773304be5ca6 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1063,36 +1063,6 @@ of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
return of_device_get_match_data(dev);
}
-static struct device_node *of_get_compat_node(struct device_node *np)
-{
- of_node_get(np);
-
- while (np) {
- if (!of_device_is_available(np)) {
- of_node_put(np);
- np = NULL;
- }
-
- if (of_property_present(np, "compatible"))
- break;
-
- np = of_get_next_parent(np);
- }
-
- return np;
-}
-
-static struct device_node *of_get_compat_node_parent(struct device_node *np)
-{
- struct device_node *parent, *node;
-
- parent = of_get_parent(np);
- node = of_get_compat_node(parent);
- of_node_put(parent);
-
- return node;
-}
-
static void of_link_to_phandle(struct device_node *con_np,
struct device_node *sup_np)
{
@@ -1222,10 +1192,10 @@ static struct device_node *parse_##fname(struct device_node *np, \
* parse_prop.prop_name: Name of property holding a phandle value
* parse_prop.index: For properties holding a list of phandles, this is the
* index into the list
+ * @get_con_dev: If the consumer node containing the property is never converted
+ * to a struct device, implement this ops so fw_devlink can use it
+ * to find the true consumer.
* @optional: Describes whether a supplier is mandatory or not
- * @node_not_dev: The consumer node containing the property is never converted
- * to a struct device. Instead, parse ancestor nodes for the
- * compatible property to find a node corresponding to a device.
*
* Returns:
* parse_prop() return values are
@@ -1236,8 +1206,8 @@ static struct device_node *parse_##fname(struct device_node *np, \
struct supplier_bindings {
struct device_node *(*parse_prop)(struct device_node *np,
const char *prop_name, int index);
+ struct device_node *(*get_con_dev)(struct device_node *np);
bool optional;
- bool node_not_dev;
};
DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells")
@@ -1352,7 +1322,10 @@ static const struct supplier_bindings of_supplier_bindings[] = {
{ .parse_prop = parse_pinctrl6, },
{ .parse_prop = parse_pinctrl7, },
{ .parse_prop = parse_pinctrl8, },
- { .parse_prop = parse_remote_endpoint, .node_not_dev = true, },
+ {
+ .parse_prop = parse_remote_endpoint,
+ .get_con_dev = of_graph_get_port_parent,
+ },
{ .parse_prop = parse_pwms, },
{ .parse_prop = parse_resets, },
{ .parse_prop = parse_leds, },
@@ -1403,8 +1376,8 @@ static int of_link_property(struct device_node *con_np, const char *prop_name)
while ((phandle = s->parse_prop(con_np, prop_name, i))) {
struct device_node *con_dev_np;
- con_dev_np = s->node_not_dev
- ? of_get_compat_node_parent(con_np)
+ con_dev_np = s->get_con_dev
+ ? s->get_con_dev(con_np)
: of_node_get(con_np);
matched = true;
i++;
From 782bfd03c3ae2c0e6e01b661b8e18f1de50357be Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Tue, 6 Feb 2024 17:18:01 -0800
Subject: [PATCH 384/637] of: property: Improve finding the supplier of a
remote-endpoint property
After commit 4a032827daa8 ("of: property: Simplify of_link_to_phandle()"),
remote-endpoint properties created a fwnode link from the consumer device
to the supplier endpoint. This is a tiny bit inefficient (not buggy) when
trying to create device links or detecting cycles. So, improve this the
same way we improved finding the consumer of a remote-endpoint property.
Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()")
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20240207011803.2637531-3-saravanak@google.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/property.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 773304be5ca6..a5f562a5e146 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1232,7 +1232,6 @@ DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL)
DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL)
DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL)
DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL)
-DEFINE_SIMPLE_PROP(remote_endpoint, "remote-endpoint", NULL)
DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells")
DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells")
DEFINE_SIMPLE_PROP(leds, "leds", NULL)
@@ -1298,6 +1297,17 @@ static struct device_node *parse_interrupts(struct device_node *np,
return of_irq_parse_one(np, index, &sup_args) ? NULL : sup_args.np;
}
+static struct device_node *parse_remote_endpoint(struct device_node *np,
+ const char *prop_name,
+ int index)
+{
+ /* Return NULL for index > 0 to signify end of remote-endpoints. */
+ if (!index || strcmp(prop_name, "remote-endpoint"))
+ return NULL;
+
+ return of_graph_get_remote_port_parent(np);
+}
+
static const struct supplier_bindings of_supplier_bindings[] = {
{ .parse_prop = parse_clocks, },
{ .parse_prop = parse_interconnects, },
From 8f1e0d791b5281f3a38620bc7c57763dc551be15 Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Tue, 6 Feb 2024 17:18:02 -0800
Subject: [PATCH 385/637] of: property: Add in-ports/out-ports support to
of_graph_get_port_parent()
Similar to the existing "ports" node name, coresight device tree bindings
have added "in-ports" and "out-ports" as standard node names for a
collection of ports.
Add support for these name to of_graph_get_port_parent() so that
remote-endpoint parsing can find the correct parent node for these
coresight ports too.
Signed-off-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20240207011803.2637531-4-saravanak@google.com
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/property.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/of/property.c b/drivers/of/property.c
index a5f562a5e146..b71267c6667c 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -763,7 +763,9 @@ struct device_node *of_graph_get_port_parent(struct device_node *node)
/* Walk 3 levels up only if there is 'ports' node. */
for (depth = 3; depth && node; depth--) {
node = of_get_next_parent(node);
- if (depth == 2 && !of_node_name_eq(node, "ports"))
+ if (depth == 2 && !of_node_name_eq(node, "ports") &&
+ !of_node_name_eq(node, "in-ports") &&
+ !of_node_name_eq(node, "out-ports"))
break;
}
return node;
From 44dc5c41b5b1267d4dd037d26afc0c4d3a568acb Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Fri, 9 Feb 2024 06:36:22 -0500
Subject: [PATCH 386/637] tracing: Fix wasted memory in saved_cmdlines logic
While looking at improving the saved_cmdlines cache I found a huge amount
of wasted memory that should be used for the cmdlines.
The tracing data saves pids during the trace. At sched switch, if a trace
occurred, it will save the comm of the task that did the trace. This is
saved in a "cache" that maps pids to comms and exposed to user space via
the /sys/kernel/tracing/saved_cmdlines file. Currently it only caches by
default 128 comms.
The structure that uses this creates an array to store the pids using
PID_MAX_DEFAULT (which is usually set to 32768). This causes the structure
to be of the size of 131104 bytes on 64 bit machines.
In hex: 131104 = 0x20020, and since the kernel allocates generic memory in
powers of two, the kernel would allocate 0x40000 or 262144 bytes to store
this structure. That leaves 131040 bytes of wasted space.
Worse, the structure points to an allocated array to store the comm names,
which is 16 bytes times the amount of names to save (currently 128), which
is 2048 bytes. Instead of allocating a separate array, make the structure
end with a variable length string and use the extra space for that.
This is similar to a recommendation that Linus had made about eventfs_inode names:
https://lore.kernel.org/all/20240130190355.11486-5-torvalds@linux-foundation.org/
Instead of allocating a separate string array to hold the saved comms,
have the structure end with: char saved_cmdlines[]; and round up to the
next power of two over sizeof(struct saved_cmdline_buffers) + num_cmdlines * TASK_COMM_LEN
It will use this extra space for the saved_cmdline portion.
Now, instead of saving only 128 comms by default, by using this wasted
space at the end of the structure it can save over 8000 comms and even
saves space by removing the need for allocating the other array.
Link: https://lore.kernel.org/linux-trace-kernel/20240209063622.1f7b6d5f@rorschach.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Mete Durlu <meted@linux.ibm.com>
Fixes: 939c7a4f04fcd ("tracing: Introduce saved_cmdlines_size file")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace.c | 75 ++++++++++++++++++++++----------------------
1 file changed, 37 insertions(+), 38 deletions(-)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a7c6fd934e9..9ff8a439d674 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2320,7 +2320,7 @@ struct saved_cmdlines_buffer {
unsigned *map_cmdline_to_pid;
unsigned cmdline_num;
int cmdline_idx;
- char *saved_cmdlines;
+ char saved_cmdlines[];
};
static struct saved_cmdlines_buffer *savedcmd;
@@ -2334,47 +2334,58 @@ static inline void set_cmdline(int idx, const char *cmdline)
strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
}
-static int allocate_cmdlines_buffer(unsigned int val,
- struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
{
+ int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+ kfree(s->map_cmdline_to_pid);
+ free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
+{
+ struct saved_cmdlines_buffer *s;
+ struct page *page;
+ int orig_size, size;
+ int order;
+
+ /* Figure out how much is needed to hold the given number of cmdlines */
+ orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+ order = get_order(orig_size);
+ size = 1 << (order + PAGE_SHIFT);
+ page = alloc_pages(GFP_KERNEL, order);
+ if (!page)
+ return NULL;
+
+ s = page_address(page);
+ memset(s, 0, sizeof(*s));
+
+ /* Round up to actual allocation */
+ val = (size - sizeof(*s)) / TASK_COMM_LEN;
+ s->cmdline_num = val;
+
s->map_cmdline_to_pid = kmalloc_array(val,
sizeof(*s->map_cmdline_to_pid),
GFP_KERNEL);
- if (!s->map_cmdline_to_pid)
- return -ENOMEM;
-
- s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
- if (!s->saved_cmdlines) {
- kfree(s->map_cmdline_to_pid);
- return -ENOMEM;
+ if (!s->map_cmdline_to_pid) {
+ free_saved_cmdlines_buffer(s);
+ return NULL;
}
s->cmdline_idx = 0;
- s->cmdline_num = val;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
sizeof(s->map_pid_to_cmdline));
memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
val * sizeof(*s->map_cmdline_to_pid));
- return 0;
+ return s;
}
static int trace_create_savedcmd(void)
{
- int ret;
+ savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
- savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
- if (!savedcmd)
- return -ENOMEM;
-
- ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
- if (ret < 0) {
- kfree(savedcmd);
- savedcmd = NULL;
- return -ENOMEM;
- }
-
- return 0;
+ return savedcmd ? 0 : -ENOMEM;
}
int is_tracing_stopped(void)
@@ -6056,26 +6067,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
- kfree(s->saved_cmdlines);
- kfree(s->map_cmdline_to_pid);
- kfree(s);
-}
-
static int tracing_resize_saved_cmdlines(unsigned int val)
{
struct saved_cmdlines_buffer *s, *savedcmd_temp;
- s = kmalloc(sizeof(*s), GFP_KERNEL);
+ s = allocate_cmdlines_buffer(val);
if (!s)
return -ENOMEM;
- if (allocate_cmdlines_buffer(val, s) < 0) {
- kfree(s);
- return -ENOMEM;
- }
-
preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
From e5aa6d51a2ef8c7ef7e3fe76bebe530fb68e7f08 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Fri, 9 Feb 2024 09:20:44 +0100
Subject: [PATCH 387/637] ALSA: hda/cs35l56: select intended config FW_CS_DSP
Commit 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic
CS35L56 amplifier") adds configs SND_HDA_SCODEC_CS35L56_{I2C,SPI},
which selects the non-existing config CS_DSP. Note the renaming in
commit d7cfdf17cb9d ("firmware: cs_dsp: Rename KConfig symbol CS_DSP ->
FW_CS_DSP"), though.
Select the intended config FW_CS_DSP.
This broken select command probably was not noticed as the configs also
select SND_HDA_CS_DSP_CONTROLS and this then selects FW_CS_DSP. So, the
select FW_CS_DSP could actually be dropped, but we will keep this
redundancy in place as the author originally also intended to have this
redundancy of selects in place.
Fixes: 73cfbfa9caea ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Simon Trimmer <simont@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20240209082044.3981-1-lukas.bulwahn@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index 21a90b3c4cc7..8e0ff70fb610 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -156,7 +156,7 @@ config SND_HDA_SCODEC_CS35L56_I2C
depends on I2C
depends on ACPI || COMPILE_TEST
depends on SND_SOC
- select CS_DSP
+ select FW_CS_DSP
select SND_HDA_GENERIC
select SND_SOC_CS35L56_SHARED
select SND_HDA_SCODEC_CS35L56
@@ -171,7 +171,7 @@ config SND_HDA_SCODEC_CS35L56_SPI
depends on SPI_MASTER
depends on ACPI || COMPILE_TEST
depends on SND_SOC
- select CS_DSP
+ select FW_CS_DSP
select SND_HDA_GENERIC
select SND_SOC_CS35L56_SHARED
select SND_HDA_SCODEC_CS35L56
From 727b943263dc98a7aca355cc0302158218f71543 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Fri, 9 Feb 2024 14:57:00 +0000
Subject: [PATCH 388/637] ASoC: cs35l56: Remove default from IRQ1_CFG register
The driver never uses the IRQ1_CFG register so there's no need to provide
a default value. It's set as a readable register only for debugging
through the regmap registers file.
A system-specific firmware could overwrite this register with a non-default
value. Therefore the driver can't hardcode what the initial value actually
is. As the register is only for debugging the value can be left unknown
until someone wants to read it through debugfs.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20240209145700.1555950-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs35l56-shared.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 02fba4bc0a14..995d979b6d87 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -51,7 +51,6 @@ static const struct reg_default cs35l56_reg_defaults[] = {
{ CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 },
{ CS35L56_SWIRE_DP3_CH3_INPUT, 0x00000029 },
{ CS35L56_SWIRE_DP3_CH4_INPUT, 0x00000028 },
- { CS35L56_IRQ1_CFG, 0x00000000 },
{ CS35L56_IRQ1_MASK_1, 0x83ffffff },
{ CS35L56_IRQ1_MASK_2, 0xffff7fff },
{ CS35L56_IRQ1_MASK_4, 0xe0ffffff },
From 9f208e097801f9c2088eb339a1162fff81c08b4e Mon Sep 17 00:00:00 2001
From: Christian Lamparter <chunkeey@gmail.com>
Date: Fri, 9 Feb 2024 15:59:07 +0100
Subject: [PATCH 389/637] spi: spi-ppc4xx: include missing platform_device.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
the driver currently fails to compile on 6.8-rc3 due to:
| spi-ppc4xx.c: In function ‘spi_ppc4xx_of_probe’:
| @346:36: error: invalid use of undefined type ‘struct platform_device’
| 346 | struct device_node *np = op->dev.of_node;
| | ^~
| ... (more similar errors)
it was working with 6.7. Looks like it only needed the include
and its compiling fine!
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Link: https://lore.kernel.org/r/3eb3f9c4407ba99d1cd275662081e46b9e839173.1707490664.git.chunkeey@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-ppc4xx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 03aab661be9d..412d6e678224 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/wait.h>
+#include <linux/platform_device.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
From f6a1892585cd19e63c4ef2334e26cd536d5b678d Mon Sep 17 00:00:00 2001
From: Aleksander Mazur <deweloper@wp.pl>
Date: Tue, 23 Jan 2024 14:43:00 +0100
Subject: [PATCH 390/637] x86/Kconfig: Transmeta Crusoe is CPU family 5, not 6
The kernel built with MCRUSOE is unbootable on Transmeta Crusoe. It shows
the following error message:
This kernel requires an i686 CPU, but only detected an i586 CPU.
Unable to boot - please use a kernel appropriate for your CPU.
Remove MCRUSOE from the condition introduced in commit in Fixes, effectively
changing X86_MINIMUM_CPU_FAMILY back to 5 on that machine, which matches the
CPU family given by CPUID.
[ bp: Massage commit message. ]
Fixes: 25d76ac88821 ("x86/Kconfig: Explicitly enumerate i686-class CPUs in Kconfig")
Signed-off-by: Aleksander Mazur <deweloper@wp.pl>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20240123134309.1117782-1-deweloper@wp.pl
---
arch/x86/Kconfig.cpu | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b9224cf2ee4d..2a7279d80460 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -379,7 +379,7 @@ config X86_CMOV
config X86_MINIMUM_CPU_FAMILY
int
default "64" if X86_64
- default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+ default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
default "5" if X86_32 && X86_CMPXCHG64
default "4"
From 61da7c8e2a602f66be578cbbcebe8638c10e0f48 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 30 Jan 2024 15:43:53 +0000
Subject: [PATCH 391/637] arm64/signal: Don't assume that TIF_SVE means we
saved SVE state
When we are in a syscall we will only save the FPSIMD subset even though
the task still has access to the full register set, and on context switch
we will only remove TIF_SVE when loading the register state. This means
that the signal handling code should not assume that TIF_SVE means that
the register state is stored in SVE format, it should instead check the
format that was recorded during save.
Fixes: 8c845e273104 ("arm64/sve: Leave SVE enabled on syscall if we don't context switch")
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240130-arm64-sve-signal-regs-v2-1-9fc6f9502782@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/fpsimd.c | 2 +-
arch/arm64/kernel/signal.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a5dc6f764195..25ceaee6b025 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1635,7 +1635,7 @@ void fpsimd_preserve_current_state(void)
void fpsimd_signal_preserve_current_state(void)
{
fpsimd_preserve_current_state();
- if (test_thread_flag(TIF_SVE))
+ if (current->thread.fp_type == FP_STATE_SVE)
sve_to_fpsimd(current);
}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 0e8beb3349ea..425b1bc17a3f 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
vl = task_get_sme_vl(current);
vq = sve_vq_from_vl(vl);
flags |= SVE_SIG_FLAG_SM;
- } else if (test_thread_flag(TIF_SVE)) {
+ } else if (current->thread.fp_type == FP_STATE_SVE) {
vq = sve_vq_from_vl(vl);
}
@@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
- if (add_all || test_thread_flag(TIF_SVE) ||
+ if (add_all || current->thread.fp_type == FP_STATE_SVE ||
thread_sm_enabled(¤t->thread)) {
int vl = max(sve_max_vl(), sme_max_vl());
From 719da04f2d1285922abca72b074fb6fa75d464ea Mon Sep 17 00:00:00 2001
From: Hojin Nam <hj96.nam@samsung.com>
Date: Thu, 8 Feb 2024 10:34:15 +0900
Subject: [PATCH 392/637] perf: CXL: fix mismatched cpmu event opcode
S2M NDR BI-ConflictAck opcode is described as 4 in the CXL
r3.0 3.3.9 Table 3.43. However, it is defined as 3 in macro definition.
Fixes: 5d7107c72796 ("perf: CXL Performance Monitoring Unit driver")
Signed-off-by: Hojin Nam <hj96.nam@samsung.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20240208013415epcms2p2904187c8a863f4d0d2adc980fb91a2dc@epcms2p2
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/perf/cxl_pmu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 365d964b0f6a..bc0d414a6aff 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = {
CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp, CXL_PMU_GID_S2M_NDR, BIT(0)),
CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps, CXL_PMU_GID_S2M_NDR, BIT(1)),
CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe, CXL_PMU_GID_S2M_NDR, BIT(2)),
- CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(3)),
+ CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(4)),
/* CXL rev 3.0 Table 3-46 S2M DRS opcodes */
CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata, CXL_PMU_GID_S2M_DRS, BIT(0)),
CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm, CXL_PMU_GID_S2M_DRS, BIT(1)),
From c0b26c06ed008c0898829dda4c2783b8ec478350 Mon Sep 17 00:00:00 2001
From: Seongsu Park <sgsu.park@samsung.com>
Date: Fri, 2 Feb 2024 10:33:06 +0900
Subject: [PATCH 393/637] arm64: fix typo in comments
fix typo in comments
thath -> that
Signed-off-by: Seongsu Park <sgsu.park@samsung.com>
Link: https://lore.kernel.org/r/20240202013306.883777-1-sgsu.park@samsung.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/cpufeature.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 21c824edf8ce..bd8d4ca81a48 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -83,7 +83,7 @@ struct arm64_ftr_bits {
* to full-0 denotes that this field has no override
*
* A @mask field set to full-0 with the corresponding @val field set
- * to full-1 denotes thath this field has an invalid override.
+ * to full-1 denotes that this field has an invalid override.
*/
struct arm64_ftr_override {
u64 val;
From f9daab0ad01cf9d165dbbbf106ca4e61d06e7fe8 Mon Sep 17 00:00:00 2001
From: Fangrui Song <maskray@google.com>
Date: Mon, 5 Feb 2024 23:45:52 -0800
Subject: [PATCH 394/637] arm64: jump_label: use constraints "Si" instead of
"i"
The generic constraint "i" seems to be copied from x86 or arm (and with
a redundant generic operand modifier "c"). It works with -fno-PIE but
not with -fPIE/-fPIC in GCC's aarch64 port.
The machine constraint "S", which denotes a symbol or label reference
with a constant offset, supports PIC and has been available in GCC since
2012 and in Clang since 7.0. However, Clang before 19 does not support
"S" on a symbol with a constant offset [1] (e.g.
`static_key_false(&nf_hooks_needed[pf][hook])` in
include/linux/netfilter.h), so we use "i" as a fallback.
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Fangrui Song <maskray@google.com>
Link: https://github.com/llvm/llvm-project/pull/80255 [1]
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20240206074552.541154-1-maskray@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/jump_label.h | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45d22..b7716b215f91 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -15,6 +15,10 @@
#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
+/*
+ * Prefer the constraint "S" to support PIC with GCC. Clang before 19 does not
+ * support "S" on a symbol with a constant offset, so we use "i" as a fallback.
+ */
static __always_inline bool arch_static_branch(struct static_key * const key,
const bool branch)
{
@@ -23,9 +27,9 @@ static __always_inline bool arch_static_branch(struct static_key * const key,
" .pushsection __jump_table, \"aw\" \n\t"
" .align 3 \n\t"
" .long 1b - ., %l[l_yes] - . \n\t"
- " .quad %c0 - . \n\t"
+ " .quad (%[key] - .) + %[bit0] \n\t"
" .popsection \n\t"
- : : "i"(&((char *)key)[branch]) : : l_yes);
+ : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes);
return false;
l_yes:
@@ -40,9 +44,9 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
" .pushsection __jump_table, \"aw\" \n\t"
" .align 3 \n\t"
" .long 1b - ., %l[l_yes] - . \n\t"
- " .quad %c0 - . \n\t"
+ " .quad (%[key] - .) + %[bit0] \n\t"
" .popsection \n\t"
- : : "i"(&((char *)key)[branch]) : : l_yes);
+ : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes);
return false;
l_yes:
From 50572064ec7109b00eef8880e905f55861c8b3de Mon Sep 17 00:00:00 2001
From: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Date: Fri, 9 Feb 2024 17:11:09 +0000
Subject: [PATCH 395/637] perf/arm-cmn: Workaround AmpereOneX errata
AC04_MESH_1 (incorrect child count)
AmpereOneX mesh implementation has a bug in HN-P nodes that makes them
report incorrect child count. The failing crosspoints report 8 children
while they only have two.
When the driver tries to access the inexistent child nodes, it believes it
has reached an invalid node type and probing fails. The workaround is to
ignore those incorrect child nodes and continue normally.
Signed-off-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
[ rm: rewrote simpler generalised version ]
Tested-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/ce4b1442135fe03d0de41859b04b268c88c854a3.1707498577.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/perf/arm-cmn.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index c584165b13ba..7e3aa7e2345f 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -2305,6 +2305,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
dev_dbg(cmn->dev, "ignoring external node %llx\n", reg);
continue;
}
+ /*
+ * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus
+ * child count larger than the number of valid child pointers.
+ * A child offset of 0 can only occur on CMN-600; otherwise it
+ * would imply the root node being its own grandchild, which
+ * we can safely dismiss in general.
+ */
+ if (reg == 0 && cmn->part != PART_CMN600) {
+ dev_dbg(cmn->dev, "bogus child pointer?\n");
+ continue;
+ }
arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn);
From 41044d5360685e78a869d40a168491a70cdb7e73 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Tue, 23 Jan 2024 11:55:31 -0700
Subject: [PATCH 396/637] PCI: Fix active state requirement in PME polling
The commit noted in fixes added a bogus requirement that runtime PM managed
devices need to be in the RPM_ACTIVE state for PME polling. In fact, only
devices in low power states should be polled.
However there's still a requirement that the device config space must be
accessible, which has implications for both the current state of the polled
device and the parent bridge, when present. It's not sufficient to assume
the bridge remains in D0 and cases have been observed where the bridge
passes the D0 test, but the PM state indicates RPM_SUSPENDING and config
space of the polled device becomes inaccessible during pci_pme_wakeup().
Therefore, since the bridge is already effectively required to be in the
RPM_ACTIVE state, formalize this in the code and elevate the PM usage count
to maintain the state while polling the subordinate device.
This resolves a regression reported in the bugzilla below where a
Thunderbolt/USB4 hierarchy fails to scan for an attached NVMe endpoint
downstream of a bridge in a D3hot power state.
Link: https://lore.kernel.org/r/20240123185548.1040096-1-alex.williamson@redhat.com
Fixes: d3fcd7360338 ("PCI: Fix runtime PM race with PME polling")
Reported-by: Sanath S <sanath.s@amd.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218360
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Sanath S <sanath.s@amd.com>
Reviewed-by: Rafael J. Wysocki <rafael@kernel.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/pci/pci.c | 37 ++++++++++++++++++++++---------------
1 file changed, 22 insertions(+), 15 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d8f11a078924..0a80156fe812 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2496,29 +2496,36 @@ static void pci_pme_list_scan(struct work_struct *work)
if (pdev->pme_poll) {
struct pci_dev *bridge = pdev->bus->self;
struct device *dev = &pdev->dev;
- int pm_status;
+ struct device *bdev = bridge ? &bridge->dev : NULL;
+ int bref = 0;
/*
- * If bridge is in low power state, the
- * configuration space of subordinate devices
- * may be not accessible
+ * If we have a bridge, it should be in an active/D0
+ * state or the configuration space of subordinate
+ * devices may not be accessible or stable over the
+ * course of the call.
*/
- if (bridge && bridge->current_state != PCI_D0)
- continue;
+ if (bdev) {
+ bref = pm_runtime_get_if_active(bdev, true);
+ if (!bref)
+ continue;
+
+ if (bridge->current_state != PCI_D0)
+ goto put_bridge;
+ }
/*
- * If the device is in a low power state it
- * should not be polled either.
+ * The device itself should be suspended but config
+ * space must be accessible, therefore it cannot be in
+ * D3cold.
*/
- pm_status = pm_runtime_get_if_active(dev, true);
- if (!pm_status)
- continue;
-
- if (pdev->current_state != PCI_D3cold)
+ if (pm_runtime_suspended(dev) &&
+ pdev->current_state != PCI_D3cold)
pci_pme_wakeup(pdev, NULL);
- if (pm_status > 0)
- pm_runtime_put(dev);
+put_bridge:
+ if (bref > 0)
+ pm_runtime_put(bdev);
} else {
list_del(&pme_dev->list);
kfree(pme_dev);
From 5571e41ec6e56e35f34ae9f5b3a335ef510e0ade Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 31 Jan 2024 14:27:25 -0500
Subject: [PATCH 397/637] btrfs: don't drop extent_map for free space inode on
write error
While running the CI for an unrelated change I hit the following panic
with generic/648 on btrfs_holes_spacecache.
assertion failed: block_start != EXTENT_MAP_HOLE, in fs/btrfs/extent_io.c:1385
------------[ cut here ]------------
kernel BUG at fs/btrfs/extent_io.c:1385!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 1 PID: 2695096 Comm: fsstress Kdump: loaded Tainted: G W 6.8.0-rc2+ #1
RIP: 0010:__extent_writepage_io.constprop.0+0x4c1/0x5c0
Call Trace:
<TASK>
extent_write_cache_pages+0x2ac/0x8f0
extent_writepages+0x87/0x110
do_writepages+0xd5/0x1f0
filemap_fdatawrite_wbc+0x63/0x90
__filemap_fdatawrite_range+0x5c/0x80
btrfs_fdatawrite_range+0x1f/0x50
btrfs_write_out_cache+0x507/0x560
btrfs_write_dirty_block_groups+0x32a/0x420
commit_cowonly_roots+0x21b/0x290
btrfs_commit_transaction+0x813/0x1360
btrfs_sync_file+0x51a/0x640
__x64_sys_fdatasync+0x52/0x90
do_syscall_64+0x9c/0x190
entry_SYSCALL_64_after_hwframe+0x6e/0x76
This happens because we fail to write out the free space cache in one
instance, come back around and attempt to write it again. However on
the second pass through we go to call btrfs_get_extent() on the inode to
get the extent mapping. Because this is a new block group, and with the
free space inode we always search the commit root to avoid deadlocking
with the tree, we find nothing and return a EXTENT_MAP_HOLE for the
requested range.
This happens because the first time we try to write the space cache out
we hit an error, and on an error we drop the extent mapping. This is
normal for normal files, but the free space cache inode is special. We
always expect the extent map to be correct. Thus the second time
through we end up with a bogus extent map.
Since we're deprecating this feature, the most straightforward way to
fix this is to simply skip dropping the extent map range for this failed
range.
I shortened the test by using error injection to stress the area to make
it easier to reproduce. With this patch in place we no longer panic
with my error injection test.
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/inode.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7bcc1c03437a..d232eca1bbee 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3184,8 +3184,23 @@ out:
unwritten_start += logical_len;
clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
- /* Drop extent maps for the part of the extent we didn't write. */
- btrfs_drop_extent_map_range(inode, unwritten_start, end, false);
+ /*
+ * Drop extent maps for the part of the extent we didn't write.
+ *
+ * We have an exception here for the free_space_inode, this is
+ * because when we do btrfs_get_extent() on the free space inode
+ * we will search the commit root. If this is a new block group
+ * we won't find anything, and we will trip over the assert in
+ * writepage where we do ASSERT(em->block_start !=
+ * EXTENT_MAP_HOLE).
+ *
+ * Theoretically we could also skip this for any NOCOW extent as
+ * we don't mess with the extent map tree in the NOCOW case, but
+ * for now simply skip this if we are the free space inode.
+ */
+ if (!btrfs_is_free_space_inode(inode))
+ btrfs_drop_extent_map_range(inode, unwritten_start,
+ end, false);
/*
* If the ordered extent had an IOERR or something else went
From 1693d5442c458ae8d5b0d58463b873cd879569ed Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:06 +0000
Subject: [PATCH 398/637] btrfs: add and use helper to check if block group is
used
Add a helper function to determine if a block group is being used and make
use of it at btrfs_delete_unused_bgs(). This helper will also be used in
future code changes.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/block-group.c | 3 +--
fs/btrfs/block-group.h | 7 +++++++
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index a9be9ac99222..9daef18bcbbc 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1512,8 +1512,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
}
spin_lock(&block_group->lock);
- if (block_group->reserved || block_group->pinned ||
- block_group->used || block_group->ro ||
+ if (btrfs_is_block_group_used(block_group) || block_group->ro ||
list_is_singular(&block_group->list)) {
/*
* We want to bail if we made new allocations or have
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index c4a1f01cc1c2..962b11983901 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -257,6 +257,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
return (block_group->start + block_group->length);
}
+static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg)
+{
+ lockdep_assert_held(&bg->lock);
+
+ return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0);
+}
+
static inline bool btrfs_is_block_group_data_only(
struct btrfs_block_group *block_group)
{
From f4a9f219411f318ae60d6ff7f129082a75686c6c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:14 +0000
Subject: [PATCH 399/637] btrfs: do not delete unused block group if it may be
used soon
Before deleting a block group that is in the list of unused block groups
(fs_info->unused_bgs), we check if the block group became used before
deleting it, as extents from it may have been allocated after it was added
to the list.
However even if the block group was not yet used, there may be tasks that
have only reserved space and have not yet allocated extents, and they
might be relying on the availability of the unused block group in order
to allocate extents. The reservation works first by increasing the
"bytes_may_use" field of the corresponding space_info object (which may
first require flushing delayed items, allocating a new block group, etc),
and only later a task does the actual allocation of extents.
For metadata we usually don't end up using all reserved space, as we are
pessimistic and typically account for the worst cases (need to COW every
single node in a path of a tree at maximum possible height, etc). For
data we usually reserve the exact amount of space we're going to allocate
later, except when using compression where we always reserve space based
on the uncompressed size, as compression is only triggered when writeback
starts so we don't know in advance how much space we'll actually need, or
if the data is compressible.
So don't delete an unused block group if the total size of its space_info
object minus the block group's size is less then the sum of used space and
space that may be used (space_info->bytes_may_use), as that means we have
tasks that reserved space and may need to allocate extents from the block
group. In this case, besides skipping the deletion, re-add the block group
to the list of unused block groups so that it may be reconsidered later,
in case the tasks that reserved space end up not needing to allocate
extents from it.
Allowing the deletion of the block group while we have reserved space, can
result in tasks failing to allocate metadata extents (-ENOSPC) while under
a transaction handle, resulting in a transaction abort, or failure during
writeback for the case of data extents.
CC: stable@vger.kernel.org # 6.0+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/block-group.c | 46 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 9daef18bcbbc..5fe37bc82f11 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1455,6 +1455,7 @@ out:
*/
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
{
+ LIST_HEAD(retry_list);
struct btrfs_block_group *block_group;
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
@@ -1476,6 +1477,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
spin_lock(&fs_info->unused_bgs_lock);
while (!list_empty(&fs_info->unused_bgs)) {
+ u64 used;
int trimming;
block_group = list_first_entry(&fs_info->unused_bgs,
@@ -1511,6 +1513,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
goto next;
}
+ spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
if (btrfs_is_block_group_used(block_group) || block_group->ro ||
list_is_singular(&block_group->list)) {
@@ -1522,10 +1525,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
*/
trace_btrfs_skip_unused_block_group(block_group);
spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
up_write(&space_info->groups_sem);
goto next;
}
+
+ /*
+ * The block group may be unused but there may be space reserved
+ * accounting with the existence of that block group, that is,
+ * space_info->bytes_may_use was incremented by a task but no
+ * space was yet allocated from the block group by the task.
+ * That space may or may not be allocated, as we are generally
+ * pessimistic about space reservation for metadata as well as
+ * for data when using compression (as we reserve space based on
+ * the worst case, when data can't be compressed, and before
+ * actually attempting compression, before starting writeback).
+ *
+ * So check if the total space of the space_info minus the size
+ * of this block group is less than the used space of the
+ * space_info - if that's the case, then it means we have tasks
+ * that might be relying on the block group in order to allocate
+ * extents, and add back the block group to the unused list when
+ * we finish, so that we retry later in case no tasks ended up
+ * needing to allocate extents from the block group.
+ */
+ used = btrfs_space_info_used(space_info, true);
+ if (space_info->total_bytes - block_group->length < used) {
+ /*
+ * Add a reference for the list, compensate for the ref
+ * drop under the "next" label for the
+ * fs_info->unused_bgs list.
+ */
+ btrfs_get_block_group(block_group);
+ list_add_tail(&block_group->bg_list, &retry_list);
+
+ trace_btrfs_skip_unused_block_group(block_group);
+ spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
+ up_write(&space_info->groups_sem);
+ goto next;
+ }
+
spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
/* We don't want to force the issue, only flip if it's ok. */
ret = inc_block_group_ro(block_group, 0);
@@ -1649,12 +1691,16 @@ next:
btrfs_put_block_group(block_group);
spin_lock(&fs_info->unused_bgs_lock);
}
+ list_splice_tail(&retry_list, &fs_info->unused_bgs);
spin_unlock(&fs_info->unused_bgs_lock);
mutex_unlock(&fs_info->reclaim_bgs_lock);
return;
flip_async:
btrfs_end_transaction(trans);
+ spin_lock(&fs_info->unused_bgs_lock);
+ list_splice_tail(&retry_list, &fs_info->unused_bgs);
+ spin_unlock(&fs_info->unused_bgs_lock);
mutex_unlock(&fs_info->reclaim_bgs_lock);
btrfs_put_block_group(block_group);
btrfs_discard_punt_unused_bgs_list(fs_info);
From 12c5128f101bfa47a08e4c0e1a75cfa2d0872bcd Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 25 Jan 2024 09:53:19 +0000
Subject: [PATCH 400/637] btrfs: add new unused block groups to the list of
unused block groups
Space reservations for metadata are, most of the time, pessimistic as we
reserve space for worst possible cases - where tree heights are at the
maximum possible height (8), we need to COW every extent buffer in a tree
path, need to split extent buffers, etc.
For data, we generally reserve the exact amount of space we are going to
allocate. The exception here is when using compression, in which case we
reserve space matching the uncompressed size, as the compression only
happens at writeback time and in the worst possible case we need that
amount of space in case the data is not compressible.
This means that when there's not available space in the corresponding
space_info object, we may need to allocate a new block group, and then
that block group might not be used after all. In this case the block
group is never added to the list of unused block groups and ends up
never being deleted - except if we unmount and mount again the fs, as
when reading block groups from disk we add unused ones to the list of
unused block groups (fs_info->unused_bgs). Otherwise a block group is
only added to the list of unused block groups when we deallocate the
last extent from it, so if no extent is ever allocated, the block group
is kept around forever.
This also means that if we have a bunch of tasks reserving space in
parallel we can end up allocating many block groups that end up never
being used or kept around for too long without being used, which has
the potential to result in ENOSPC failures in case for example we over
allocate too many metadata block groups and then end up in a state
without enough unallocated space to allocate a new data block group.
This is more likely to happen with metadata reservations as of kernel
6.7, namely since commit 28270e25c69a ("btrfs: always reserve space for
delayed refs when starting transaction"), because we started to always
reserve space for delayed references when starting a transaction handle
for a non-zero number of items, and also to try to reserve space to fill
the gap between the delayed block reserve's reserved space and its size.
So to avoid this, when finishing the creation a new block group, add the
block group to the list of unused block groups if it's still unused at
that time. This way the next time the cleaner kthread runs, it will delete
the block group if it's still unused and not needed to satisfy existing
space reservations.
Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.7+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/block-group.c | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5fe37bc82f11..378d9103a207 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2729,6 +2729,37 @@ next:
btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
list_del_init(&block_group->bg_list);
clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+
+ /*
+ * If the block group is still unused, add it to the list of
+ * unused block groups. The block group may have been created in
+ * order to satisfy a space reservation, in which case the
+ * extent allocation only happens later. But often we don't
+ * actually need to allocate space that we previously reserved,
+ * so the block group may become unused for a long time. For
+ * example for metadata we generally reserve space for a worst
+ * possible scenario, but then don't end up allocating all that
+ * space or none at all (due to no need to COW, extent buffers
+ * were already COWed in the current transaction and still
+ * unwritten, tree heights lower than the maximum possible
+ * height, etc). For data we generally reserve the axact amount
+ * of space we are going to allocate later, the exception is
+ * when using compression, as we must reserve space based on the
+ * uncompressed data size, because the compression is only done
+ * when writeback triggered and we don't know how much space we
+ * are actually going to need, so we reserve the uncompressed
+ * size because the data may be uncompressible in the worst case.
+ */
+ if (ret == 0) {
+ bool used;
+
+ spin_lock(&block_group->lock);
+ used = btrfs_is_block_group_used(block_group);
+ spin_unlock(&block_group->lock);
+
+ if (!used)
+ btrfs_mark_bg_unused(block_group);
+ }
}
btrfs_trans_release_chunk_metadata(trans);
}
From 38ee0cb2a2e2ade077442085638eb181b0562971 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 8 Feb 2024 14:31:10 +0200
Subject: [PATCH 401/637] selftests: net: Fix bridge backup port test flakiness
The test toggles the carrier of a bridge port in order to test the
bridge backup port feature.
Due to the linkwatch delayed work the carrier change is not always
reflected fast enough to the bridge driver and packets are not forwarded
as the test expects, resulting in failures [1].
Fix by busy waiting on the bridge port state until it changes to the
desired state following the carrier change.
[1]
# Backup port
# -----------
[...]
# TEST: swp1 carrier off [ OK ]
# TEST: No forwarding out of swp1 [FAIL]
[ 641.995910] br0: port 1(swp1) entered disabled state
# TEST: No forwarding out of vx0 [ OK ]
Fixes: b408453053fb ("selftests: net: Add bridge backup port and backup nexthop ID test")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240208123110.1063930-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../selftests/net/test_bridge_backup_port.sh | 23 +++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/tools/testing/selftests/net/test_bridge_backup_port.sh b/tools/testing/selftests/net/test_bridge_backup_port.sh
index 70a7d87ba2d2..1b3f89e2b86e 100755
--- a/tools/testing/selftests/net/test_bridge_backup_port.sh
+++ b/tools/testing/selftests/net/test_bridge_backup_port.sh
@@ -124,6 +124,16 @@ tc_check_packets()
[[ $pkts == $count ]]
}
+bridge_link_check()
+{
+ local ns=$1; shift
+ local dev=$1; shift
+ local state=$1; shift
+
+ bridge -n $ns -d -j link show dev $dev | \
+ jq -e ".[][\"state\"] == \"$state\"" &> /dev/null
+}
+
################################################################################
# Setup
@@ -259,6 +269,7 @@ backup_port()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -268,6 +279,7 @@ backup_port()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
log_test $? 0 "swp1 carrier on"
# Configure vx0 as the backup port of swp1 and check that packets are
@@ -284,6 +296,7 @@ backup_port()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -293,6 +306,7 @@ backup_port()
log_test $? 0 "Forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
log_test $? 0 "swp1 carrier on"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -314,6 +328,7 @@ backup_port()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -369,6 +384,7 @@ backup_nhid()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -382,6 +398,7 @@ backup_nhid()
log_test $? 0 "Forwarding using VXLAN FDB entry"
run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
log_test $? 0 "swp1 carrier on"
# Configure nexthop ID 10 as the backup nexthop ID of swp1 and check
@@ -398,6 +415,7 @@ backup_nhid()
log_test $? 0 "No forwarding out of vx0"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -411,6 +429,7 @@ backup_nhid()
log_test $? 0 "No forwarding using VXLAN FDB entry"
run_cmd "ip -n $sw1 link set dev swp1 carrier on"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 forwarding
log_test $? 0 "swp1 carrier on"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -441,6 +460,7 @@ backup_nhid()
log_test $? 0 "No forwarding using VXLAN FDB entry"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -497,6 +517,7 @@ backup_nhid_invalid()
log_test $? 0 "Valid nexthop as backup nexthop"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
log_test $? 0 "swp1 carrier off"
run_cmd "ip netns exec $sw1 mausezahn br0.10 -a $smac -b $dmac -A 198.51.100.1 -B 198.51.100.2 -t ip -p 100 -q -c 1"
@@ -604,7 +625,9 @@ backup_nhid_ping()
run_cmd "bridge -n $sw2 link set dev swp1 backup_nhid 10"
run_cmd "ip -n $sw1 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw1 swp1 disabled
run_cmd "ip -n $sw2 link set dev swp1 carrier off"
+ busywait $BUSYWAIT_TIMEOUT bridge_link_check $sw2 swp1 disabled
run_cmd "ip netns exec $sw1 ping -i 0.1 -c 10 -w $PING_TIMEOUT 192.0.2.66"
log_test $? 0 "Ping with backup nexthop ID"
From 93590849a05edffaefa11695fab98f621259ded2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 8 Feb 2024 17:55:26 +0200
Subject: [PATCH 402/637] selftests: forwarding: Fix layer 2 miss test
flakiness
After enabling a multicast querier on the bridge (like the test is
doing), the bridge will wait for the Max Response Delay before starting
to forward according to its MDB in order to let Membership Reports
enough time to be received and processed.
Currently, the test is waiting for exactly the default Max Response
Delay (10 seconds) which is racy and leads to failures [1].
Fix by reducing the Max Response Delay to 1 second.
[1]
[...]
# TEST: L2 miss - Multicast (IPv4) [FAIL]
# Unregistered multicast filter was hit after adding MDB entry
Fixes: 8c33266ae26a ("selftests: forwarding: Add layer 2 miss test cases")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240208155529.1199729-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../testing/selftests/net/forwarding/tc_flower_l2_miss.sh | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
index 20a7cb7222b8..c2420bb72c12 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh
@@ -209,14 +209,17 @@ test_l2_miss_multicast()
# both registered and unregistered multicast traffic.
bridge link set dev $swp2 mcast_router 2
+ # Set the Max Response Delay to 100 centiseconds (1 second) so that the
+ # bridge will start forwarding according to its MDB soon after a
+ # multicast querier is enabled.
+ ip link set dev br1 type bridge mcast_query_response_interval 100
+
# Forwarding according to MDB entries only takes place when the bridge
# detects that there is a valid querier in the network. Set the bridge
# as the querier and assign it a valid IPv6 link-local address to be
# used as the source address for MLD queries.
ip link set dev br1 type bridge mcast_querier 1
ip -6 address add fe80::1/64 nodad dev br1
- # Wait the default Query Response Interval (10 seconds) for the bridge
- # to determine that there are no other queriers in the network.
sleep 10
test_l2_miss_multicast_ipv4
@@ -224,6 +227,7 @@ test_l2_miss_multicast()
ip -6 address del fe80::1/64 dev br1
ip link set dev br1 type bridge mcast_querier 0
+ ip link set dev br1 type bridge mcast_query_response_interval 1000
bridge link set dev $swp2 mcast_router 1
}
From 7399e2ce4d424f426417496eb289458780eea985 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 8 Feb 2024 17:55:27 +0200
Subject: [PATCH 403/637] selftests: forwarding: Fix bridge MDB test flakiness
After enabling a multicast querier on the bridge (like the test is
doing), the bridge will wait for the Max Response Delay before starting
to forward according to its MDB in order to let Membership Reports
enough time to be received and processed.
Currently, the test is waiting for exactly the default Max Response
Delay (10 seconds) which is racy and leads to failures [1].
Fix by reducing the Max Response Delay to 1 second.
[1]
[...]
# TEST: IPv4 host entries forwarding tests [FAIL]
# Packet locally received after flood
Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240208155529.1199729-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/forwarding/bridge_mdb.sh | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index 61348f71728c..f94bfb6f45ec 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -1252,14 +1252,17 @@ fwd_test()
echo
log_info "# Forwarding tests"
+ # Set the Max Response Delay to 100 centiseconds (1 second) so that the
+ # bridge will start forwarding according to its MDB soon after a
+ # multicast querier is enabled.
+ ip link set dev br0 type bridge mcast_query_response_interval 100
+
# Forwarding according to MDB entries only takes place when the bridge
# detects that there is a valid querier in the network. Set the bridge
# as the querier and assign it a valid IPv6 link-local address to be
# used as the source address for MLD queries.
ip -6 address add fe80::1/64 nodad dev br0
ip link set dev br0 type bridge mcast_querier 1
- # Wait the default Query Response Interval (10 seconds) for the bridge
- # to determine that there are no other queriers in the network.
sleep 10
fwd_test_host
@@ -1267,6 +1270,7 @@ fwd_test()
ip link set dev br0 type bridge mcast_querier 0
ip -6 address del fe80::1/64 dev br0
+ ip link set dev br0 type bridge mcast_query_response_interval 1000
}
ctrl_igmpv3_is_in_test()
From dd6b34589441f2ad4698dd88a664811550148b41 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 8 Feb 2024 17:55:28 +0200
Subject: [PATCH 404/637] selftests: forwarding: Suppress grep warnings
Suppress the following grep warnings:
[...]
INFO: # Port group entries configuration tests - (*, G)
TEST: Common port group entries configuration tests (IPv4 (*, G)) [ OK ]
TEST: Common port group entries configuration tests (IPv6 (*, G)) [ OK ]
grep: warning: stray \ before /
grep: warning: stray \ before /
grep: warning: stray \ before /
TEST: IPv4 (*, G) port group entries configuration tests [ OK ]
grep: warning: stray \ before /
grep: warning: stray \ before /
grep: warning: stray \ before /
TEST: IPv6 (*, G) port group entries configuration tests [ OK ]
[...]
They do not fail the test, but do clutter the output.
Fixes: b6d00da08610 ("selftests: forwarding: Add bridge MDB test")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240208155529.1199729-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/forwarding/bridge_mdb.sh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index f94bfb6f45ec..d9d587454d20 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -329,7 +329,7 @@ __cfg_test_port_ip_star_g()
bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
check_err $? "(*, G) \"permanent\" entry has a pending group timer"
- bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+ bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
check_err $? "\"permanent\" source entry has a pending source timer"
bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -346,7 +346,7 @@ __cfg_test_port_ip_star_g()
bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
check_fail $? "(*, G) EXCLUDE entry does not have a pending group timer"
- bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+ bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
check_err $? "\"blocked\" source entry has a pending source timer"
bridge mdb del dev br0 port $swp1 grp $grp vid 10
@@ -363,7 +363,7 @@ __cfg_test_port_ip_star_g()
bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q " 0.00"
check_err $? "(*, G) INCLUDE entry has a pending group timer"
- bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "\/0.00"
+ bridge -d -s mdb get dev br0 grp $grp vid 10 | grep -q "/0.00"
check_fail $? "Source entry does not have a pending source timer"
bridge mdb del dev br0 port $swp1 grp $grp vid 10
From f97f1fcc96908c97a240ff6cb4474e155abfa0d7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 8 Feb 2024 17:55:29 +0200
Subject: [PATCH 405/637] selftests: forwarding: Fix bridge locked port test
flakiness
The redirection test case fails in the netdev CI on debug kernels
because an FDB entry is learned despite the presence of a tc filter that
redirects incoming traffic [1].
I am unable to reproduce the failure locally, but I can see how it can
happen given that learning is first enabled and only then the ingress tc
filter is configured. On debug kernels the time window between these two
operations is longer compared to regular kernels, allowing random
packets to be transmitted and trigger learning.
Fix by reversing the order and configure the ingress tc filter before
enabling learning.
[1]
[...]
# TEST: Locked port MAB redirect [FAIL]
# Locked entry created for redirected traffic
Fixes: 38c43a1ce758 ("selftests: forwarding: Add test case for traffic redirection from a locked port")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20240208155529.1199729-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/forwarding/bridge_locked_port.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
index 9af9f6964808..c62331b2e006 100755
--- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh
@@ -327,10 +327,10 @@ locked_port_mab_redirect()
RET=0
check_port_mab_support || return 0
- bridge link set dev $swp1 learning on locked on mab on
tc qdisc add dev $swp1 clsact
tc filter add dev $swp1 ingress protocol all pref 1 handle 101 flower \
action mirred egress redirect dev $swp2
+ bridge link set dev $swp1 learning on locked on mab on
ping_do $h1 192.0.2.2
check_err $? "Ping did not work with redirection"
@@ -349,8 +349,8 @@ locked_port_mab_redirect()
check_err $? "Locked entry not created after deleting filter"
bridge fdb del `mac_get $h1` vlan 1 dev $swp1 master
- tc qdisc del dev $swp1 clsact
bridge link set dev $swp1 learning off locked off mab off
+ tc qdisc del dev $swp1 clsact
log_test "Locked port MAB redirect"
}
From c6e02eefd6ace3da3369c764f15429f5647056af Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 6 Feb 2024 15:00:46 +0000
Subject: [PATCH 406/637] cifs: change tcon status when need_reconnect is set
on it
When a tcon is marked for need_reconnect, the intention
is to have it reconnected.
This change adjusts tcon->status in cifs_tree_connect
when need_reconnect is set. Also, this change has a minor
correction in resetting need_reconnect on success. It makes
sure that it is done with tc_lock held.
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/connect.c | 5 +++++
fs/smb/client/dfs.c | 7 ++++++-
fs/smb/client/file.c | 3 +++
3 files changed, 14 insertions(+), 1 deletion(-)
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index bfd568f89710..01c49b29c499 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -4228,6 +4228,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
/* only send once per connect */
spin_lock(&tcon->tc_lock);
+
+ /* if tcon is marked for needing reconnect, update state */
+ if (tcon->need_reconnect)
+ tcon->status = TID_NEED_TCON;
+
if (tcon->status == TID_GOOD) {
spin_unlock(&tcon->tc_lock);
return 0;
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index a8a1d386da65..449c59830039 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -565,6 +565,11 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
/* only send once per connect */
spin_lock(&tcon->tc_lock);
+
+ /* if tcon is marked for needing reconnect, update state */
+ if (tcon->need_reconnect)
+ tcon->status = TID_NEED_TCON;
+
if (tcon->status == TID_GOOD) {
spin_unlock(&tcon->tc_lock);
return 0;
@@ -625,8 +630,8 @@ out:
spin_lock(&tcon->tc_lock);
if (tcon->status == TID_IN_TCON)
tcon->status = TID_GOOD;
- spin_unlock(&tcon->tc_lock);
tcon->need_reconnect = false;
+ spin_unlock(&tcon->tc_lock);
}
return rc;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index b75282c204da..f391c9b803d8 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -175,6 +175,9 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
/* only send once per connect */
spin_lock(&tcon->tc_lock);
+ if (tcon->need_reconnect)
+ tcon->status = TID_NEED_RECON;
+
if (tcon->status != TID_NEED_RECON) {
spin_unlock(&tcon->tc_lock);
return;
From a39c757bf0596b17482a507f31c3ef0af0d1d2b4 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 6 Feb 2024 15:00:47 +0000
Subject: [PATCH 407/637] cifs: handle cases where multiple sessions share
connection
Based on our implementation of multichannel, it is entirely
possible that a server struct may not be found in any channel
of an SMB session.
In such cases, we should be prepared to move on and search for
the server struct in the next session.
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/connect.c | 6 ++++++
fs/smb/client/sess.c | 1 -
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 01c49b29c499..d03253f8f145 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -233,6 +233,12 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
/* check if iface is still active */
spin_lock(&ses->chan_lock);
+ if (cifs_ses_get_chan_index(ses, server) ==
+ CIFS_INVAL_CHAN_INDEX) {
+ spin_unlock(&ses->chan_lock);
+ continue;
+ }
+
if (!cifs_chan_is_iface_active(ses, server)) {
spin_unlock(&ses->chan_lock);
cifs_chan_update_iface(ses, server);
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 476d54fceb50..8f37373fd333 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -88,7 +88,6 @@ cifs_ses_get_chan_index(struct cifs_ses *ses,
if (server)
cifs_dbg(VFS, "unable to get chan index for server: 0x%llx",
server->conn_id);
- WARN_ON(1);
return CIFS_INVAL_CHAN_INDEX;
}
From a5cc98eba2592d6e3c5a4351319595ddde2a5901 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 6 Feb 2024 23:57:18 -0600
Subject: [PATCH 408/637] smb3: clarify mount warning
When a user tries to use the "sec=krb5p" mount parameter to encrypt
data on connection to a server (when authenticating with Kerberos), we
indicate that it is not supported, but do not note the equivalent
recommended mount parameter ("sec=krb5,seal") which turns on encryption
for that mount (and uses Kerberos for auth). Update the warning message.
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/fs_context.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 52cbef2eeb28..aec8dbd1f9db 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -211,7 +211,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c
switch (match_token(value, cifs_secflavor_tokens, args)) {
case Opt_sec_krb5p:
- cifs_errorf(fc, "sec=krb5p is not supported!\n");
+ cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n");
return 1;
case Opt_sec_krb5i:
ctx->sign = true;
From 6e2f90d31fe09f2b852de25125ca875aabd81367 Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Wed, 7 Feb 2024 08:24:15 -0500
Subject: [PATCH 409/637] net: openvswitch: limit the number of recursions from
action sets
The ovs module allows for some actions to recursively contain an action
list for complex scenarios, such as sampling, checking lengths, etc.
When these actions are copied into the internal flow table, they are
evaluated to validate that such actions make sense, and these calls
happen recursively.
The ovs-vswitchd userspace won't emit more than 16 recursion levels
deep. However, the module has no such limit and will happily accept
limits larger than 16 levels nested. Prevent this by tracking the
number of recursions happening and manually limiting it to 16 levels
nested.
The initial implementation of the sample action would track this depth
and prevent more than 3 levels of recursion, but this was removed to
support the clone use case, rather than limited at the current userspace
limit.
Fixes: 798c166173ff ("openvswitch: Optimize sample action for the clone use cases")
Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240207132416.1488485-2-aconole@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/openvswitch/flow_netlink.c | 49 +++++++++++++++++++++++-----------
1 file changed, 33 insertions(+), 16 deletions(-)
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 88965e2068ac..ebc5728aab4e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -48,6 +48,7 @@ struct ovs_len_tbl {
#define OVS_ATTR_NESTED -1
#define OVS_ATTR_VARIABLE -2
+#define OVS_COPY_ACTIONS_MAX_DEPTH 16
static bool actions_may_change_flow(const struct nlattr *actions)
{
@@ -2545,13 +2546,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log);
+ u32 mpls_label_count, bool log,
+ u32 depth);
static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log, bool last)
+ u32 mpls_label_count, bool log, bool last,
+ u32 depth)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
@@ -2602,7 +2605,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
return err;
err = __ovs_nla_copy_actions(net, actions, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -2617,7 +2621,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log)
+ u32 mpls_label_count, bool log,
+ u32 depth)
{
const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
int start, action_start, err, rem;
@@ -2660,7 +2665,8 @@ static int validate_and_copy_dec_ttl(struct net *net,
return action_start;
err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
- vlan_tci, mpls_label_count, log);
+ vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -2674,7 +2680,8 @@ static int validate_and_copy_clone(struct net *net,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log, bool last)
+ u32 mpls_label_count, bool log, bool last,
+ u32 depth)
{
int start, err;
u32 exec;
@@ -2694,7 +2701,8 @@ static int validate_and_copy_clone(struct net *net,
return err;
err = __ovs_nla_copy_actions(net, attr, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3063,7 +3071,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
u32 mpls_label_count,
- bool log, bool last)
+ bool log, bool last, u32 depth)
{
const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
@@ -3111,7 +3119,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
return nested_acts_start;
err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3124,7 +3133,8 @@ static int validate_and_copy_check_pkt_len(struct net *net,
return nested_acts_start;
err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
- eth_type, vlan_tci, mpls_label_count, log);
+ eth_type, vlan_tci, mpls_label_count, log,
+ depth + 1);
if (err)
return err;
@@ -3152,12 +3162,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci,
- u32 mpls_label_count, bool log)
+ u32 mpls_label_count, bool log,
+ u32 depth)
{
u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
+ if (depth > OVS_COPY_ACTIONS_MAX_DEPTH)
+ return -EOVERFLOW;
+
nla_for_each_nested(a, attr, rem) {
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
@@ -3355,7 +3369,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
err = validate_and_copy_sample(net, a, key, sfa,
eth_type, vlan_tci,
mpls_label_count,
- log, last);
+ log, last, depth);
if (err)
return err;
skip_copy = true;
@@ -3426,7 +3440,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
err = validate_and_copy_clone(net, a, key, sfa,
eth_type, vlan_tci,
mpls_label_count,
- log, last);
+ log, last, depth);
if (err)
return err;
skip_copy = true;
@@ -3440,7 +3454,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
eth_type,
vlan_tci,
mpls_label_count,
- log, last);
+ log, last,
+ depth);
if (err)
return err;
skip_copy = true;
@@ -3450,7 +3465,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
case OVS_ACTION_ATTR_DEC_TTL:
err = validate_and_copy_dec_ttl(net, a, key, sfa,
eth_type, vlan_tci,
- mpls_label_count, log);
+ mpls_label_count, log,
+ depth);
if (err)
return err;
skip_copy = true;
@@ -3495,7 +3511,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
(*sfa)->orig_len = nla_len(attr);
err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
- key->eth.vlan.tci, mpls_label_count, log);
+ key->eth.vlan.tci, mpls_label_count, log,
+ 0);
if (err)
ovs_nla_free_flow_actions(*sfa);
From bd128f62c365504e1268dc09fcccdfb1f091e93a Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Wed, 7 Feb 2024 08:24:16 -0500
Subject: [PATCH 410/637] selftests: openvswitch: Add validation for the
recursion test
Add a test case into the netlink checks that will show the number of
nested action recursions won't exceed 16. Going to 17 on a small
clone call isn't enough to exhaust the stack on (most) systems, so
it should be safe to run even on systems that don't have the fix
applied.
Signed-off-by: Aaron Conole <aconole@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240207132416.1488485-3-aconole@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../selftests/net/openvswitch/openvswitch.sh | 13 ++++
.../selftests/net/openvswitch/ovs-dpctl.py | 71 +++++++++++++++----
2 files changed, 69 insertions(+), 15 deletions(-)
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index f8499d4c87f3..36e40256ab92 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -502,7 +502,20 @@ test_netlink_checks () {
wc -l) == 2 ] || \
return 1
+ info "Checking clone depth"
ERR_MSG="Flow actions may not be safe on all matching packets"
+ PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
+ ovs_add_flow "test_netlink_checks" nv0 \
+ 'in_port(1),eth(),eth_type(0x800),ipv4()' \
+ 'clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(clone(drop)))))))))))))))))' \
+ >/dev/null 2>&1 && return 1
+ POST_TEST=$(dmesg | grep -c "${ERR_MSG}")
+
+ if [ "$PRE_TEST" == "$POST_TEST" ]; then
+ info "failed - clone depth too large"
+ return 1
+ fi
+
PRE_TEST=$(dmesg | grep -c "${ERR_MSG}")
ovs_add_flow "test_netlink_checks" nv0 \
'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(0),2' \
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index b97e621face9..5e0e539a323d 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -299,7 +299,7 @@ class ovsactions(nla):
("OVS_ACTION_ATTR_PUSH_NSH", "none"),
("OVS_ACTION_ATTR_POP_NSH", "flag"),
("OVS_ACTION_ATTR_METER", "none"),
- ("OVS_ACTION_ATTR_CLONE", "none"),
+ ("OVS_ACTION_ATTR_CLONE", "recursive"),
("OVS_ACTION_ATTR_CHECK_PKT_LEN", "none"),
("OVS_ACTION_ATTR_ADD_MPLS", "none"),
("OVS_ACTION_ATTR_DEC_TTL", "none"),
@@ -465,29 +465,42 @@ class ovsactions(nla):
print_str += "pop_mpls"
else:
datum = self.get_attr(field[0])
- print_str += datum.dpstr(more)
+ if field[0] == "OVS_ACTION_ATTR_CLONE":
+ print_str += "clone("
+ print_str += datum.dpstr(more)
+ print_str += ")"
+ else:
+ print_str += datum.dpstr(more)
return print_str
def parse(self, actstr):
+ totallen = len(actstr)
while len(actstr) != 0:
parsed = False
+ parencount = 0
if actstr.startswith("drop"):
# If no reason is provided, the implicit drop is used (i.e no
# action). If some reason is given, an explicit action is used.
- actstr, reason = parse_extract_field(
- actstr,
- "drop(",
- "([0-9]+)",
- lambda x: int(x, 0),
- False,
- None,
- )
+ reason = None
+ if actstr.startswith("drop("):
+ parencount += 1
+
+ actstr, reason = parse_extract_field(
+ actstr,
+ "drop(",
+ "([0-9]+)",
+ lambda x: int(x, 0),
+ False,
+ None,
+ )
+
if reason is not None:
self["attrs"].append(["OVS_ACTION_ATTR_DROP", reason])
parsed = True
else:
- return
+ actstr = actstr[len("drop"): ]
+ return (totallen - len(actstr))
elif parse_starts_block(actstr, "^(\d+)", False, True):
actstr, output = parse_extract_field(
@@ -504,6 +517,7 @@ class ovsactions(nla):
False,
0,
)
+ parencount += 1
self["attrs"].append(["OVS_ACTION_ATTR_RECIRC", recircid])
parsed = True
@@ -516,12 +530,22 @@ class ovsactions(nla):
for flat_act in parse_flat_map:
if parse_starts_block(actstr, flat_act[0], False):
- actstr += len(flat_act[0])
+ actstr = actstr[len(flat_act[0]):]
self["attrs"].append([flat_act[1]])
actstr = actstr[strspn(actstr, ", ") :]
parsed = True
- if parse_starts_block(actstr, "ct(", False):
+ if parse_starts_block(actstr, "clone(", False):
+ parencount += 1
+ subacts = ovsactions()
+ actstr = actstr[len("clone("):]
+ parsedLen = subacts.parse(actstr)
+ lst = []
+ self["attrs"].append(("OVS_ACTION_ATTR_CLONE", subacts))
+ actstr = actstr[parsedLen:]
+ parsed = True
+ elif parse_starts_block(actstr, "ct(", False):
+ parencount += 1
actstr = actstr[len("ct(") :]
ctact = ovsactions.ctact()
@@ -553,6 +577,7 @@ class ovsactions(nla):
natact = ovsactions.ctact.natattr()
if actstr.startswith("("):
+ parencount += 1
t = None
actstr = actstr[1:]
if actstr.startswith("src"):
@@ -607,15 +632,29 @@ class ovsactions(nla):
actstr = actstr[strspn(actstr, ", ") :]
ctact["attrs"].append(["OVS_CT_ATTR_NAT", natact])
- actstr = actstr[strspn(actstr, ",) ") :]
+ actstr = actstr[strspn(actstr, ", ") :]
self["attrs"].append(["OVS_ACTION_ATTR_CT", ctact])
parsed = True
- actstr = actstr[strspn(actstr, "), ") :]
+ actstr = actstr[strspn(actstr, ", ") :]
+ while parencount > 0:
+ parencount -= 1
+ actstr = actstr[strspn(actstr, " "):]
+ if len(actstr) and actstr[0] != ")":
+ raise ValueError("Action str: '%s' unbalanced" % actstr)
+ actstr = actstr[1:]
+
+ if len(actstr) and actstr[0] == ")":
+ return (totallen - len(actstr))
+
+ actstr = actstr[strspn(actstr, ", ") :]
+
if not parsed:
raise ValueError("Action str: '%s' not supported" % actstr)
+ return (totallen - len(actstr))
+
class ovskey(nla):
nla_flags = NLA_F_NESTED
@@ -2111,6 +2150,8 @@ def main(argv):
ovsflow = OvsFlow()
ndb = NDB()
+ sys.setrecursionlimit(100000)
+
if hasattr(args, "showdp"):
found = False
for iface in ndb.interfaces:
From aae09a6c7783e28d1bcafee85e172fe411923b22 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 7 Feb 2024 19:29:02 -0300
Subject: [PATCH 411/637] net/sched: act_mirred: Don't zero blockid when net
device is being deleted
While testing tdc with parallel tests for mirred to block we caught an
intermittent bug. The blockid was being zeroed out when a net device
was deleted and, thus, giving us an incorrect blockid value whenever
we tried to dump the mirred action. Since we don't increment the block
refcount in the control path (and only use the ID), we don't need to
zero the blockid field whenever a net device is going down.
Fixes: 42f39036cda8 ("net/sched: act_mirred: Allow mirred to block")
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20240207222902.1469398-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/act_mirred.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 12386f590b0f..0a1a9e40f237 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -533,8 +533,6 @@ static int mirred_device_event(struct notifier_block *unused,
* net_device are already rcu protected.
*/
RCU_INIT_POINTER(m->tcfm_dev, NULL);
- } else if (m->tcfm_blockid) {
- m->tcfm_blockid = 0;
}
spin_unlock_bh(&m->tcf_lock);
}
From 15faa1f67ab405d47789d4702f587ec7df7ef03e Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Tue, 6 Feb 2024 13:30:54 +0100
Subject: [PATCH 412/637] lan966x: Fix crash when adding interface under a lag
There is a crash when adding one of the lan966x interfaces under a lag
interface. The issue can be reproduced like this:
ip link add name bond0 type bond miimon 100 mode balance-xor
ip link set dev eth0 master bond0
The reason is because when adding a interface under the lag it would go
through all the ports and try to figure out which other ports are under
that lag interface. And the issue is that lan966x can have ports that are
NULL pointer as they are not probed. So then iterating over these ports
it would just crash as they are NULL pointers.
The fix consists in actually checking for NULL pointers before accessing
something from the ports. Like we do in other places.
Fixes: cabc9d49333d ("net: lan966x: Add lag support for lan966x")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240206123054.3052966-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/microchip/lan966x/lan966x_lag.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
index 41fa2523d91d..5f2cd9a8cf8f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_lag.c
@@ -37,19 +37,24 @@ static void lan966x_lag_set_aggr_pgids(struct lan966x *lan966x)
/* Now, set PGIDs for each active LAG */
for (lag = 0; lag < lan966x->num_phys_ports; ++lag) {
- struct net_device *bond = lan966x->ports[lag]->bond;
+ struct lan966x_port *port = lan966x->ports[lag];
int num_active_ports = 0;
+ struct net_device *bond;
unsigned long bond_mask;
u8 aggr_idx[16];
- if (!bond || (visited & BIT(lag)))
+ if (!port || !port->bond || (visited & BIT(lag)))
continue;
+ bond = port->bond;
bond_mask = lan966x_lag_get_mask(lan966x, bond);
for_each_set_bit(p, &bond_mask, lan966x->num_phys_ports) {
struct lan966x_port *port = lan966x->ports[p];
+ if (!port)
+ continue;
+
lan_wr(ANA_PGID_PGID_SET(bond_mask),
lan966x, ANA_PGID(p));
if (port->lag_tx_active)
From 2599bb5e0c742ba3de1af2abb56b8a103a671a22 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:36 -0800
Subject: [PATCH 413/637] net: fill in MODULE_DESCRIPTION()s for xfrm
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the XFRM interface drivers.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/xfrm/xfrm_algo.c | 1 +
net/xfrm/xfrm_user.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index 41533c631431..e6da7e8495c9 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -858,4 +858,5 @@ int xfrm_count_pfkey_enc_supported(void)
}
EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
+MODULE_DESCRIPTION("XFRM Algorithm interface");
MODULE_LICENSE("GPL");
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ad01997c3aa9..f037be190bae 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3888,5 +3888,6 @@ static void __exit xfrm_user_exit(void)
module_init(xfrm_user_init);
module_exit(xfrm_user_exit);
+MODULE_DESCRIPTION("XFRM User interface");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);
From f73f55b0fcff575fef1854c66d18767a341ebbe2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:37 -0800
Subject: [PATCH 414/637] net: fill in MODULE_DESCRIPTION()s for mpoa
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Multi-Protocol Over ATM (MPOA) driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/atm/mpc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 033871e718a3..324e3ab96bb3 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -1532,4 +1532,5 @@ static void __exit atm_mpoa_cleanup(void)
module_init(atm_mpoa_init);
module_exit(atm_mpoa_cleanup);
+MODULE_DESCRIPTION("Multi-Protocol Over ATM (MPOA) driver");
MODULE_LICENSE("GPL");
From 6e2cf0eb6926a5c51bba0aca819e91d7265c849c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:38 -0800
Subject: [PATCH 415/637] net: fill in MODULE_DESCRIPTION()s for af_key
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the PF_KEY socket helpers.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-4-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/key/af_key.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/key/af_key.c b/net/key/af_key.c
index d68d01804dc7..f79fb99271ed 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3924,5 +3924,6 @@ out_unregister_key_proto:
module_init(ipsec_pfkey_init);
module_exit(ipsec_pfkey_exit);
+MODULE_DESCRIPTION("PF_KEY socket helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(PF_KEY);
From 2898f3075e6a0b0584781272aac88377e5ced0a0 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:39 -0800
Subject: [PATCH 416/637] net: fill in MODULE_DESCRIPTION()s for 6LoWPAN
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to IPv6 over Low power Wireless Personal Area Network.
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/6lowpan/core.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7b3341cef926..850d4a185f55 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -179,4 +179,5 @@ static void __exit lowpan_module_exit(void)
module_init(lowpan_module_init);
module_exit(lowpan_module_exit);
+MODULE_DESCRIPTION("IPv6 over Low-Power Wireless Personal Area Network core module");
MODULE_LICENSE("GPL");
From 92ab08eb63bbf54caebb425ed8908758c98ae8f2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:40 -0800
Subject: [PATCH 417/637] net: fill in MODULE_DESCRIPTION()s for ipv6 modules
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the IPv6 modules.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-6-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv6/ah6.c | 1 +
net/ipv6/esp6.c | 1 +
net/ipv6/ip6_udp_tunnel.c | 1 +
net/ipv6/mip6.c | 1 +
net/ipv6/sit.c | 1 +
net/ipv6/tunnel6.c | 1 +
net/ipv6/xfrm6_tunnel.c | 1 +
7 files changed, 7 insertions(+)
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2016e90e6e1d..eb474f0987ae 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -800,5 +800,6 @@ static void __exit ah6_fini(void)
module_init(ah6_init);
module_exit(ah6_fini);
+MODULE_DESCRIPTION("IPv6 AH transformation helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_AH);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 2cc1a45742d8..6e6efe026cdc 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -1301,5 +1301,6 @@ static void __exit esp6_fini(void)
module_init(esp6_init);
module_exit(esp6_fini);
+MODULE_DESCRIPTION("IPv6 ESP transformation helpers");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP);
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a7bf0327b380..c99053189ea8 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -182,4 +182,5 @@ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,
}
EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup);
+MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 83d2a8be263f..6a16a5bd0d91 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -405,6 +405,7 @@ static void __exit mip6_fini(void)
module_init(mip6_init);
module_exit(mip6_fini);
+MODULE_DESCRIPTION("IPv6 Mobility driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_DSTOPTS);
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ROUTING);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index cc24cefdb85c..5e9f625b76e3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1956,6 +1956,7 @@ xfrm_tunnel_failed:
module_init(sit_init);
module_exit(sit_cleanup);
+MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("sit");
MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 00e8d8b1c9a7..dc4ea9b11794 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -302,4 +302,5 @@ static void __exit tunnel6_fini(void)
module_init(tunnel6_init);
module_exit(tunnel6_fini);
+MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1323f2f6928e..f6cb94f82cc3 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -401,5 +401,6 @@ static void __exit xfrm6_tunnel_fini(void)
module_init(xfrm6_tunnel_init);
module_exit(xfrm6_tunnel_fini);
+MODULE_DESCRIPTION("IPv6 XFRM tunnel driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_IPV6);
From b058a5d25d921af2be83d70844d389ecfd4a0497 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:41 -0800
Subject: [PATCH 418/637] net: fill in MODULE_DESCRIPTION()s for ipv4 modules
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the IPv4 modules.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-7-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/ah4.c | 1 +
net/ipv4/esp4.c | 1 +
net/ipv4/ip_gre.c | 1 +
net/ipv4/ip_tunnel.c | 1 +
net/ipv4/ip_vti.c | 1 +
net/ipv4/ipip.c | 1 +
net/ipv4/tunnel4.c | 1 +
net/ipv4/udp_tunnel_core.c | 1 +
net/ipv4/xfrm4_tunnel.c | 1 +
9 files changed, 9 insertions(+)
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a2e6e1fdf82b..64aec3dff8ec 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -597,5 +597,6 @@ static void __exit ah4_fini(void)
module_init(ah4_init);
module_exit(ah4_fini);
+MODULE_DESCRIPTION("IPv4 AH transformation library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f13a..4dd9e5040672 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1247,5 +1247,6 @@ static void __exit esp4_fini(void)
module_init(esp4_init);
module_exit(esp4_fini);
+MODULE_DESCRIPTION("IPv4 ESP transformation library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 5169c3c72cff..6b9cf5a24c19 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1793,6 +1793,7 @@ static void __exit ipgre_fini(void)
module_init(ipgre_init);
module_exit(ipgre_fini);
+MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("gre");
MODULE_ALIAS_RTNL_LINK("gretap");
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index beeae624c412..a4513ffb66cb 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1298,4 +1298,5 @@ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id)
}
EXPORT_SYMBOL_GPL(ip_tunnel_setup);
+MODULE_DESCRIPTION("IPv4 tunnel implementation library");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 9ab9b3ebe0cd..d1d6bb28ed6e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -721,6 +721,7 @@ static void __exit vti_fini(void)
module_init(vti_init);
module_exit(vti_fini);
+MODULE_DESCRIPTION("Virtual (secure) IP tunneling library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("vti");
MODULE_ALIAS_NETDEV("ip_vti0");
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 27b8f83c6ea2..03afa3871efc 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -658,6 +658,7 @@ static void __exit ipip_fini(void)
module_init(ipip_init);
module_exit(ipip_fini);
+MODULE_DESCRIPTION("IP/IP protocol decoder library");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("ipip");
MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 5048c47c79b2..4c1f836aae38 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -294,4 +294,5 @@ static void __exit tunnel4_fini(void)
module_init(tunnel4_init);
module_exit(tunnel4_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel library");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index a87defb2b167..860aff5f8599 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -253,4 +253,5 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
}
EXPORT_SYMBOL_GPL(udp_tunnel_dst_lookup);
+MODULE_DESCRIPTION("IPv4 Foo over UDP tunnel driver");
MODULE_LICENSE("GPL");
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 8489fa106583..8cb266af1393 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -114,5 +114,6 @@ static void __exit ipip_fini(void)
module_init(ipip_init);
module_exit(ipip_fini);
+MODULE_DESCRIPTION("IPv4 XFRM tunnel driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP);
From a46c31bf2744b9807ba5e3ac8fdae2368d8bb3fa Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:42 -0800
Subject: [PATCH 419/637] net: fill in MODULE_DESCRIPTION()s for net/sched
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the network schedulers.
Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20240208164244.3818498-8-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/em_canid.c | 1 +
net/sched/em_cmp.c | 1 +
net/sched/em_meta.c | 1 +
net/sched/em_nbyte.c | 1 +
net/sched/em_text.c | 1 +
net/sched/em_u32.c | 1 +
6 files changed, 6 insertions(+)
diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index 5ea84decec19..5337bc462755 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -222,6 +222,7 @@ static void __exit exit_em_canid(void)
tcf_em_unregister(&em_canid_ops);
}
+MODULE_DESCRIPTION("ematch classifier to match CAN IDs embedded in skb CAN frames");
MODULE_LICENSE("GPL");
module_init(init_em_canid);
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index f17b049ea530..c90ad7ea26b4 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -87,6 +87,7 @@ static void __exit exit_em_cmp(void)
tcf_em_unregister(&em_cmp_ops);
}
+MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data");
MODULE_LICENSE("GPL");
module_init(init_em_cmp);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 09d8afd04a2a..8996c73c9779 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -1006,6 +1006,7 @@ static void __exit exit_em_meta(void)
tcf_em_unregister(&em_meta_ops);
}
+MODULE_DESCRIPTION("ematch classifier for various internal kernel metadata, skb metadata and sk metadata");
MODULE_LICENSE("GPL");
module_init(init_em_meta);
diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
index a83b237cbeb0..4f9f21a05d5e 100644
--- a/net/sched/em_nbyte.c
+++ b/net/sched/em_nbyte.c
@@ -68,6 +68,7 @@ static void __exit exit_em_nbyte(void)
tcf_em_unregister(&em_nbyte_ops);
}
+MODULE_DESCRIPTION("ematch classifier for arbitrary skb multi-bytes");
MODULE_LICENSE("GPL");
module_init(init_em_nbyte);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
index f176afb70559..420c66203b17 100644
--- a/net/sched/em_text.c
+++ b/net/sched/em_text.c
@@ -147,6 +147,7 @@ static void __exit exit_em_text(void)
tcf_em_unregister(&em_text_ops);
}
+MODULE_DESCRIPTION("ematch classifier for embedded text in skbs");
MODULE_LICENSE("GPL");
module_init(init_em_text);
diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c
index 71b070da0437..fdec4db5ec89 100644
--- a/net/sched/em_u32.c
+++ b/net/sched/em_u32.c
@@ -52,6 +52,7 @@ static void __exit exit_em_u32(void)
tcf_em_unregister(&em_u32_ops);
}
+MODULE_DESCRIPTION("ematch skb classifier using 32 bit chunks of data");
MODULE_LICENSE("GPL");
module_init(init_em_u32);
From 830bd88cc151412f467423c3db0b29fe623c6487 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:43 -0800
Subject: [PATCH 420/637] net: fill in MODULE_DESCRIPTION()s for ipvtap
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the IP-VLAN based tap driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208164244.3818498-9-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ipvlan/ipvtap.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 60944a4beada..1afc4c47be73 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -237,4 +237,5 @@ static void __exit ipvtap_exit(void)
module_exit(ipvtap_exit);
MODULE_ALIAS_RTNL_LINK("ipvtap");
MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
+MODULE_DESCRIPTION("IP-VLAN based tap driver");
MODULE_LICENSE("GPL");
From 6034e059f5d34bceb4adefc3409043bf65c896ea Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Feb 2024 08:42:44 -0800
Subject: [PATCH 421/637] net: fill in MODULE_DESCRIPTION()s for
dsa_loop_bdinfo
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the DSA loopback fixed PHY module.
Suggested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20240208164244.3818498-10-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/dsa/dsa_loop_bdinfo.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/dsa/dsa_loop_bdinfo.c b/drivers/net/dsa/dsa_loop_bdinfo.c
index 237066d30704..14ca42491512 100644
--- a/drivers/net/dsa/dsa_loop_bdinfo.c
+++ b/drivers/net/dsa/dsa_loop_bdinfo.c
@@ -32,4 +32,5 @@ static int __init dsa_loop_bdinfo_init(void)
}
arch_initcall(dsa_loop_bdinfo_init)
+MODULE_DESCRIPTION("DSA mock-up switch driver");
MODULE_LICENSE("GPL");
From 4356e9f841f7fbb945521cef3577ba394c65f3fc Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 9 Feb 2024 12:39:31 -0800
Subject: [PATCH 422/637] work around gcc bugs with 'asm goto' with outputs
We've had issues with gcc and 'asm goto' before, and we created a
'asm_volatile_goto()' macro for that in the past: see commits
3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation
bug") and a9f180345f53 ("compiler/gcc4: Make quirk for
asm_volatile_goto() unconditional").
Then, much later, we ended up removing the workaround in commit
43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR
58670") because we no longer supported building the kernel with the
affected gcc versions, but we left the macro uses around.
Now, Sean Christopherson reports a new version of a very similar
problem, which is fixed by re-applying that ancient workaround. But the
problem in question is limited to only the 'asm goto with outputs'
cases, so instead of re-introducing the old workaround as-is, let's
rename and limit the workaround to just that much less common case.
It looks like there are at least two separate issues that all hit in
this area:
(a) some versions of gcc don't mark the asm goto as 'volatile' when it
has outputs:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420
which is easy to work around by just adding the 'volatile' by hand.
(b) Internal compiler errors:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422
which are worked around by adding the extra empty 'asm' as a
barrier, as in the original workaround.
but the problem Sean sees may be a third thing since it involves bad
code generation (not an ICE) even with the manually added 'volatile'.
but the same old workaround works for this case, even if this feels a
bit like voodoo programming and may only be hiding the issue.
Reported-and-tested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Andrew Pinski <quic_apinski@quicinc.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/arc/include/asm/jump_label.h | 4 ++--
arch/arm/include/asm/jump_label.h | 4 ++--
arch/arm64/include/asm/alternative-macros.h | 4 ++--
arch/arm64/include/asm/jump_label.h | 4 ++--
arch/csky/include/asm/jump_label.h | 4 ++--
arch/loongarch/include/asm/jump_label.h | 4 ++--
arch/mips/include/asm/jump_label.h | 4 ++--
arch/parisc/include/asm/jump_label.h | 4 ++--
arch/powerpc/include/asm/jump_label.h | 4 ++--
arch/powerpc/include/asm/uaccess.h | 12 ++++++------
arch/powerpc/kernel/irq_64.c | 2 +-
arch/riscv/include/asm/arch_hweight.h | 4 ++--
arch/riscv/include/asm/bitops.h | 8 ++++----
arch/riscv/include/asm/checksum.h | 2 +-
arch/riscv/include/asm/cpufeature.h | 4 ++--
arch/riscv/include/asm/jump_label.h | 4 ++--
arch/riscv/lib/csum.c | 10 +++++-----
arch/s390/include/asm/jump_label.h | 4 ++--
arch/sparc/include/asm/jump_label.h | 4 ++--
arch/um/include/asm/cpufeature.h | 2 +-
arch/x86/include/asm/cpufeature.h | 2 +-
arch/x86/include/asm/jump_label.h | 6 +++---
arch/x86/include/asm/rmwcc.h | 2 +-
arch/x86/include/asm/special_insns.h | 2 +-
arch/x86/include/asm/uaccess.h | 10 +++++-----
arch/x86/kvm/svm/svm_ops.h | 6 +++---
arch/x86/kvm/vmx/vmx.c | 4 ++--
arch/x86/kvm/vmx/vmx_ops.h | 6 +++---
arch/xtensa/include/asm/jump_label.h | 4 ++--
include/linux/compiler-gcc.h | 19 +++++++++++++++++++
include/linux/compiler_types.h | 4 ++--
net/netfilter/nft_set_pipapo_avx2.c | 2 +-
samples/bpf/asm_goto_workaround.h | 8 ++++----
tools/arch/x86/include/asm/rmwcc.h | 2 +-
tools/include/linux/compiler_types.h | 4 ++--
35 files changed, 96 insertions(+), 77 deletions(-)
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index 9d9618079739..a339223d9e05 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -31,7 +31,7 @@
static __always_inline bool arch_static_branch(struct static_key *key,
bool branch)
{
- asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
+ asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
"1: \n"
"nop \n"
".pushsection __jump_table, \"aw\" \n"
@@ -47,7 +47,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key,
bool branch)
{
- asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
+ asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n"
"1: \n"
"b %l[l_yes] \n"
".pushsection __jump_table, \"aw\" \n"
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index e12d7d096fc0..e4eb54f6cd9f 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -11,7 +11,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
WASM(nop) "\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".word 1b, %l[l_yes], %c0\n\t"
@@ -25,7 +25,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
WASM(b) " %l[l_yes]\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 210bb43cff2c..d328f549b1a6 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap)
if (!cpucap_is_possible(cpucap))
return false;
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops)
:
: [cpucap] "i" (cpucap)
@@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
if (!cpucap_is_possible(cpucap))
return false;
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap])
:
: [cpucap] "i" (cpucap)
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45d22..6aafbb789991 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
static __always_inline bool arch_static_branch(struct static_key * const key,
const bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: nop \n\t"
" .pushsection __jump_table, \"aw\" \n\t"
" .align 3 \n\t"
@@ -35,7 +35,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key * const key,
const bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: b %l[l_yes] \n\t"
" .pushsection __jump_table, \"aw\" \n\t"
" .align 3 \n\t"
diff --git a/arch/csky/include/asm/jump_label.h b/arch/csky/include/asm/jump_label.h
index 98a3f4b168bd..ef2e37a10a0f 100644
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -12,7 +12,7 @@
static __always_inline bool arch_static_branch(struct static_key *key,
bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: nop32 \n"
" .pushsection __jump_table, \"aw\" \n"
" .align 2 \n"
@@ -29,7 +29,7 @@ label:
static __always_inline bool arch_static_branch_jump(struct static_key *key,
bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: bsr32 %l[label] \n"
" .pushsection __jump_table, \"aw\" \n"
" .align 2 \n"
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 3cea299a5ef5..29acfe3de3fa 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@
static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: nop \n\t"
JUMP_TABLE_ENTRY
: : "i"(&((char *)key)[branch]) : : l_yes);
@@ -35,7 +35,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
{
- asm_volatile_goto(
+ asm goto(
"1: b %l[l_yes] \n\t"
JUMP_TABLE_ENTRY
: : "i"(&((char *)key)[branch]) : : l_yes);
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 081be98c71ef..ff5d388502d4 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -39,7 +39,7 @@ extern void jump_label_apply_nops(struct module *mod);
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+ asm goto("1:\t" B_INSN " 2f\n\t"
"2:\t.insn\n\t"
".pushsection __jump_table, \"aw\"\n\t"
WORD_INSN " 1b, %l[l_yes], %0\n\t"
@@ -53,7 +53,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
+ asm goto("1:\t" J_INSN " %l[l_yes]\n\t"
".pushsection __jump_table, \"aw\"\n\t"
WORD_INSN " 1b, %l[l_yes], %0\n\t"
".popsection\n\t"
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 94428798b6aa..317ebc5edc9f 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -12,7 +12,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".align %1\n\t"
@@ -29,7 +29,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"b,n %l[l_yes]\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".align %1\n\t"
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 93ce3ec25387..2f2a86ed2280 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"nop # arch_static_branch\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"b %l[l_yes] # arch_static_branch_jump\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".long 1b - ., %l[l_yes] - .\n\t"
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index f1f9890f50d3..de10437fd206 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -74,7 +74,7 @@ __pu_failed: \
/* -mprefixed can generate offsets beyond range, fall back hack */
#ifdef CONFIG_PPC_KERNEL_PREFIXED
#define __put_user_asm_goto(x, addr, label, op) \
- asm_volatile_goto( \
+ asm goto( \
"1: " op " %0,0(%1) # put_user\n" \
EX_TABLE(1b, %l2) \
: \
@@ -83,7 +83,7 @@ __pu_failed: \
: label)
#else
#define __put_user_asm_goto(x, addr, label, op) \
- asm_volatile_goto( \
+ asm goto( \
"1: " op "%U1%X1 %0,%1 # put_user\n" \
EX_TABLE(1b, %l2) \
: \
@@ -97,7 +97,7 @@ __pu_failed: \
__put_user_asm_goto(x, ptr, label, "std")
#else /* __powerpc64__ */
#define __put_user_asm2_goto(x, addr, label) \
- asm_volatile_goto( \
+ asm goto( \
"1: stw%X1 %0, %1\n" \
"2: stw%X1 %L0, %L1\n" \
EX_TABLE(1b, %l2) \
@@ -146,7 +146,7 @@ do { \
/* -mprefixed can generate offsets beyond range, fall back hack */
#ifdef CONFIG_PPC_KERNEL_PREFIXED
#define __get_user_asm_goto(x, addr, label, op) \
- asm_volatile_goto( \
+ asm_goto_output( \
"1: "op" %0,0(%1) # get_user\n" \
EX_TABLE(1b, %l2) \
: "=r" (x) \
@@ -155,7 +155,7 @@ do { \
: label)
#else
#define __get_user_asm_goto(x, addr, label, op) \
- asm_volatile_goto( \
+ asm_goto_output( \
"1: "op"%U1%X1 %0, %1 # get_user\n" \
EX_TABLE(1b, %l2) \
: "=r" (x) \
@@ -169,7 +169,7 @@ do { \
__get_user_asm_goto(x, addr, label, "ld")
#else /* __powerpc64__ */
#define __get_user_asm2_goto(x, addr, label) \
- asm_volatile_goto( \
+ asm_goto_output( \
"1: lwz%X1 %0, %1\n" \
"2: lwz%X1 %L0, %L1\n" \
EX_TABLE(1b, %l2) \
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
index 938e66829eae..d5c48d1b0a31 100644
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
* This allows interrupts to be unmasked without hard disabling, and
* also without new hard interrupts coming in ahead of pending ones.
*/
- asm_volatile_goto(
+ asm goto(
"1: \n"
" lbz 9,%0(13) \n"
" cmpwi 9,0 \n"
diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h
index c20236a0725b..85b2c443823e 100644
--- a/arch/riscv/include/asm/arch_hweight.h
+++ b/arch/riscv/include/asm/arch_hweight.h
@@ -20,7 +20,7 @@
static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
#ifdef CONFIG_RISCV_ISA_ZBB
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -51,7 +51,7 @@ static inline unsigned int __arch_hweight8(unsigned int w)
static __always_inline unsigned long __arch_hweight64(__u64 w)
{
# ifdef CONFIG_RISCV_ISA_ZBB
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 9ffc35537024..329d8244a9b3 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -39,7 +39,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
{
int num;
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -95,7 +95,7 @@ static __always_inline unsigned long variable__fls(unsigned long word)
{
int num;
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -154,7 +154,7 @@ static __always_inline int variable_ffs(int x)
if (!x)
return 0;
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
@@ -209,7 +209,7 @@ static __always_inline int variable_fls(unsigned int x)
if (!x)
return 0;
- asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
: : : : legacy);
diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h
index a5b60b54b101..88e6f1499e88 100644
--- a/arch/riscv/include/asm/checksum.h
+++ b/arch/riscv/include/asm/checksum.h
@@ -53,7 +53,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
unsigned long fold_temp;
- asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 5a626ed2c47a..0bd11862b760 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -80,7 +80,7 @@ riscv_has_extension_likely(const unsigned long ext)
"ext must be < RISCV_ISA_EXT_MAX");
if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE("j %l[l_no]", "nop", 0, %[ext], 1)
:
: [ext] "i" (ext)
@@ -103,7 +103,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
"ext must be < RISCV_ISA_EXT_MAX");
if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE("nop", "j %l[l_yes]", 0, %[ext], 1)
:
: [ext] "i" (ext)
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0..4a35d787c019 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
static __always_inline bool arch_static_branch(struct static_key * const key,
const bool branch)
{
- asm_volatile_goto(
+ asm goto(
" .align 2 \n\t"
" .option push \n\t"
" .option norelax \n\t"
@@ -39,7 +39,7 @@ label:
static __always_inline bool arch_static_branch_jump(struct static_key * const key,
const bool branch)
{
- asm_volatile_goto(
+ asm goto(
" .align 2 \n\t"
" .option push \n\t"
" .option norelax \n\t"
diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c
index af3df5274ccb..74af3ab520b6 100644
--- a/arch/riscv/lib/csum.c
+++ b/arch/riscv/lib/csum.c
@@ -53,7 +53,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
* support, so nop when Zbb is available and jump when Zbb is
* not available.
*/
- asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
@@ -170,7 +170,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
* support, so nop when Zbb is available and jump when Zbb is
* not available.
*/
- asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
@@ -178,7 +178,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
: no_zbb);
#ifdef CONFIG_32BIT
- asm_volatile_goto(".option push \n\
+ asm_goto_output(".option push \n\
.option arch,+zbb \n\
rori %[fold_temp], %[csum], 16 \n\
andi %[offset], %[offset], 1 \n\
@@ -193,7 +193,7 @@ do_csum_with_alignment(const unsigned char *buff, int len)
return (unsigned short)csum;
#else /* !CONFIG_32BIT */
- asm_volatile_goto(".option push \n\
+ asm_goto_output(".option push \n\
.option arch,+zbb \n\
rori %[fold_temp], %[csum], 32 \n\
add %[csum], %[fold_temp], %[csum] \n\
@@ -257,7 +257,7 @@ do_csum_no_alignment(const unsigned char *buff, int len)
* support, so nop when Zbb is available and jump when Zbb is
* not available.
*/
- asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
+ asm goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0,
RISCV_ISA_EXT_ZBB, 1)
:
:
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 895f774bbcc5..bf78cf381dfc 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -25,7 +25,7 @@
*/
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 0,%l[label]\n"
+ asm goto("0: brcl 0,%l[label]\n"
".pushsection __jump_table,\"aw\"\n"
".balign 8\n"
".long 0b-.,%l[label]-.\n"
@@ -39,7 +39,7 @@ label:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("0: brcl 15,%l[label]\n"
+ asm goto("0: brcl 15,%l[label]\n"
".pushsection __jump_table,\"aw\"\n"
".balign 8\n"
".long 0b-.,%l[label]-.\n"
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 94eb529dcb77..2718cbea826a 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -10,7 +10,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"nop\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
@@ -26,7 +26,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"b %l[l_yes]\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
index 4b6d1b526bc1..66fe06db872f 100644
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto("1: jmp 6f\n"
+ asm goto("1: jmp 6f\n"
"2:\n"
".skip -(((5f-4f) - (2b-1b)) > 0) * "
"((5f-4f) - (2b-1b)),0x90\n"
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index a26bebbdff87..a1273698fc43 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto(
+ asm goto(
ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 071572e23d3a..cbbef32517f0 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes] # objtool NOPs this \n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:
static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
".byte " __stringify(BYTES_NOP5) "\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
{
- asm_volatile_goto("1:"
+ asm goto("1:"
"jmp %l[l_yes]\n\t"
JUMP_TABLE_ENTRY
: : "i" (key), "i" (branch) : : l_yes);
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4b081e0d3306..363266cbcada 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
({ \
bool c = false; \
- asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
+ asm goto (fullop "; j" #cc " %l[cc_label]" \
: : [var] "m" (_var), ## __VA_ARGS__ \
: clobbers : cc_label); \
if (0) { \
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d6cd9344f6c7..48f8dd47cf68 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
#ifdef CONFIG_X86_USER_SHADOW_STACK
static inline int write_user_shstk_64(u64 __user *addr, u64 val)
{
- asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+ asm goto("1: wrussq %[val], (%[addr])\n"
_ASM_EXTABLE(1b, %l[fail])
:: [addr] "r" (addr), [val] "r" (val)
:: fail);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5c367c1290c3..237dc8cdd12b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);
#ifdef CONFIG_X86_32
#define __put_user_goto_u64(x, addr, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: movl %%eax,0(%1)\n" \
"2: movl %%edx,4(%1)\n" \
_ASM_EXTABLE_UA(1b, %l2) \
@@ -295,7 +295,7 @@ do { \
} while (0)
#define __get_user_asm(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: mov"itype" %[umem],%[output]\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: [output] ltype(x) \
@@ -375,7 +375,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -394,7 +394,7 @@ do { \
__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \
__typeof__(*(_ptr)) __old = *_old; \
__typeof__(*(_ptr)) __new = (_new); \
- asm_volatile_goto("\n" \
+ asm_goto_output("\n" \
"1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \
_ASM_EXTABLE_UA(1b, %l[label]) \
: CC_OUT(z) (success), \
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
* aliasing issues.
*/
#define __put_user_goto(x, addr, itype, ltype, label) \
- asm_volatile_goto("\n" \
+ asm goto("\n" \
"1: mov"itype" %0,%1\n" \
_ASM_EXTABLE_UA(1b, %l2) \
: : ltype(x), "m" (__m(addr)) \
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 36c8af87a707..4e725854c63a 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@
#define svm_asm(insn, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) "\n\t" \
+ asm goto("1: " __stringify(insn) "\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
::: clobber : fault); \
return; \
@@ -18,7 +18,7 @@ fault: \
#define svm_asm1(insn, op1, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \
+ asm goto("1: " __stringify(insn) " %0\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
:: op1 : clobber : fault); \
return; \
@@ -28,7 +28,7 @@ fault: \
#define svm_asm2(insn, op1, op2, clobber...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \
+ asm goto("1: " __stringify(insn) " %1, %0\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
:: op1, op2 : clobber : fault); \
return; \
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e262bc2ba4e5..1111d9d08903 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -738,7 +738,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
*/
static int kvm_cpu_vmxoff(void)
{
- asm_volatile_goto("1: vmxoff\n\t"
+ asm goto("1: vmxoff\n\t"
_ASM_EXTABLE(1b, %l[fault])
::: "cc", "memory" : fault);
@@ -2784,7 +2784,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
cr4_set_bits(X86_CR4_VMXE);
- asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+ asm goto("1: vmxon %[vmxon_pointer]\n\t"
_ASM_EXTABLE(1b, %l[fault])
: : [vmxon_pointer] "m"(vmxon_pointer)
: : fault);
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index f41ce3c24123..8060e5fc6dbd 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
- asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+ asm_goto_output("1: vmread %[field], %[output]\n\t"
"jna %l[do_fail]\n\t"
_ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)
#define vmx_asm1(insn, op1, error_args...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %0\n\t" \
+ asm goto("1: " __stringify(insn) " %0\n\t" \
".byte 0x2e\n\t" /* branch not taken hint */ \
"jna %l[error]\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
@@ -205,7 +205,7 @@ fault: \
#define vmx_asm2(insn, op1, op2, error_args...) \
do { \
- asm_volatile_goto("1: " __stringify(insn) " %1, %0\n\t" \
+ asm goto("1: " __stringify(insn) " %1, %0\n\t" \
".byte 0x2e\n\t" /* branch not taken hint */ \
"jna %l[error]\n\t" \
_ASM_EXTABLE(1b, %l[fault]) \
diff --git a/arch/xtensa/include/asm/jump_label.h b/arch/xtensa/include/asm/jump_label.h
index c812bf85021c..46c8596259d2 100644
--- a/arch/xtensa/include/asm/jump_label.h
+++ b/arch/xtensa/include/asm/jump_label.h
@@ -13,7 +13,7 @@
static __always_inline bool arch_static_branch(struct static_key *key,
bool branch)
{
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
"_nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".word 1b, %l[l_yes], %c0\n\t"
@@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key,
* make it reachable and wrap both into a no-transform block
* to avoid any assembler interference with this.
*/
- asm_volatile_goto("1:\n\t"
+ asm goto("1:\n\t"
".begin no-transform\n\t"
"_j %l[l_yes]\n\t"
"2:\n\t"
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index aebb65bf95a7..c1a963be7d28 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -64,6 +64,25 @@
__builtin_unreachable(); \
} while (0)
+/*
+ * GCC 'asm goto' with outputs miscompiles certain code sequences:
+ *
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422
+ *
+ * Work it around via the same compiler barrier quirk that we used
+ * to use for the old 'asm goto' workaround.
+ *
+ * Also, always mark such 'asm goto' statements as volatile: all
+ * asm goto statements are supposed to be volatile as per the
+ * documentation, but some versions of gcc didn't actually do
+ * that for asms with outputs:
+ *
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
+ */
+#define asm_goto_output(x...) \
+ do { asm volatile goto(x); asm (""); } while (0)
+
#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
#define __HAVE_BUILTIN_BSWAP32__
#define __HAVE_BUILTIN_BSWAP64__
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6f1ca49306d2..663d8791c871 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -362,8 +362,8 @@ struct ftrace_likely_data {
#define __member_size(p) __builtin_object_size(p, 1)
#endif
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
#endif
#ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 90e275bb3e5d..a3a8ddca9918 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -57,7 +57,7 @@
/* Jump to label if @reg is zero */
#define NFT_PIPAPO_AVX2_NOMATCH_GOTO(reg, label) \
- asm_volatile_goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \
+ asm goto("vptest %%ymm" #reg ", %%ymm" #reg ";" \
"je %l[" #label "]" : : : : label)
/* Store 256 bits from YMM register into memory. Contrary to bucket load
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7048bb3594d6..634e81d83efd 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -4,14 +4,14 @@
#define __ASM_GOTO_WORKAROUND_H
/*
- * This will bring in asm_volatile_goto and asm_inline macro definitions
+ * This will bring in asm_goto_output and asm_inline macro definitions
* if enabled by compiler and config options.
*/
#include <linux/types.h>
-#ifdef asm_volatile_goto
-#undef asm_volatile_goto
-#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
#endif
/*
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
index 11ff975242ca..e2ff22b379a4 100644
--- a/tools/arch/x86/include/asm/rmwcc.h
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -4,7 +4,7 @@
#define __GEN_RMWcc(fullop, var, cc, ...) \
do { \
- asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
+ asm goto (fullop "; j" cc " %l[cc_label]" \
: : "m" (var), ## __VA_ARGS__ \
: "memory" : cc_label); \
return 0; \
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
index 1bdd834bdd57..d09f9dc172a4 100644
--- a/tools/include/linux/compiler_types.h
+++ b/tools/include/linux/compiler_types.h
@@ -36,8 +36,8 @@
#include <linux/compiler-gcc.h>
#endif
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm goto(x)
#endif
#endif /* __LINUX_COMPILER_TYPES_H */
From a22b0a2be69a36511cb5b37d948b651ddf7debf3 Mon Sep 17 00:00:00 2001
From: Cosmin Tanislav <demonsingur@gmail.com>
Date: Wed, 7 Feb 2024 15:20:05 +0200
Subject: [PATCH 423/637] iio: adc: ad4130: zero-initialize clock init data
The clk_init_data struct does not have all its members
initialized, causing issues when trying to expose the internal
clock on the CLK pin.
Fix this by zero-initializing the clk_init_data struct.
Fixes: 62094060cf3a ("iio: adc: ad4130: add AD4130 driver")
Signed-off-by: Cosmin Tanislav <demonsingur@gmail.com>
Reviewed-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20240207132007.253768-1-demonsingur@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/adc/ad4130.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index feb86fe6c422..9daeac16499b 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -1821,7 +1821,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st)
{
struct device *dev = &st->spi->dev;
struct device_node *of_node = dev_of_node(dev);
- struct clk_init_data init;
+ struct clk_init_data init = {};
const char *clk_name;
int ret;
From 78367c32bebfe833cd30c855755d863a4ff3fdee Mon Sep 17 00:00:00 2001
From: Cosmin Tanislav <demonsingur@gmail.com>
Date: Wed, 7 Feb 2024 15:20:06 +0200
Subject: [PATCH 424/637] iio: adc: ad4130: only set GPIO_CTRL if pin is unused
Currently, GPIO_CTRL bits are set even if the pins are used for
measurements.
GPIO_CTRL bits should only be set if the pin is not used for
other functionality.
Fix this by only setting the GPIO_CTRL bits if the pin has no
other function.
Fixes: 62094060cf3a ("iio: adc: ad4130: add AD4130 driver")
Signed-off-by: Cosmin Tanislav <demonsingur@gmail.com>
Reviewed-by: Nuno Sa <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20240207132007.253768-2-demonsingur@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
drivers/iio/adc/ad4130.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index 9daeac16499b..62490424b6ae 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -1891,10 +1891,14 @@ static int ad4130_setup(struct iio_dev *indio_dev)
return ret;
/*
- * Configure all GPIOs for output. If configured, the interrupt function
- * of P2 takes priority over the GPIO out function.
+ * Configure unused GPIOs for output. If configured, the interrupt
+ * function of P2 takes priority over the GPIO out function.
*/
- val = AD4130_IO_CONTROL_GPIO_CTRL_MASK;
+ val = 0;
+ for (i = 0; i < AD4130_MAX_GPIOS; i++)
+ if (st->pins_fn[i + AD4130_AIN2_P1] == AD4130_PIN_FN_NONE)
+ val |= FIELD_PREP(AD4130_IO_CONTROL_GPIO_CTRL_MASK, BIT(i));
+
val |= FIELD_PREP(AD4130_IO_CONTROL_INT_PIN_SEL_MASK, st->int_pin_sel);
ret = regmap_write(st->regmap, AD4130_IO_CONTROL_REG, val);
From c57ca512f3b68ddcd62bda9cc24a8f5584ab01b1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:18 -0800
Subject: [PATCH 425/637] net: tls: factor out tls_*crypt_async_wait()
Factor out waiting for async encrypt and decrypt to finish.
There are already multiple copies and a subsequent fix will
need more. No functional changes.
Note that crypto_wait_req() returns wait->err
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tls/tls_sw.c | 96 +++++++++++++++++++++++-------------------------
1 file changed, 45 insertions(+), 51 deletions(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 31e8a94dfc11..6a73714f34cc 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -230,6 +230,20 @@ static void tls_decrypt_done(void *data, int err)
spin_unlock_bh(&ctx->decrypt_compl_lock);
}
+static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
+{
+ int pending;
+
+ spin_lock_bh(&ctx->decrypt_compl_lock);
+ reinit_completion(&ctx->async_wait.completion);
+ pending = atomic_read(&ctx->decrypt_pending);
+ spin_unlock_bh(&ctx->decrypt_compl_lock);
+ if (pending)
+ crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+
+ return ctx->async_wait.err;
+}
+
static int tls_do_decryption(struct sock *sk,
struct scatterlist *sgin,
struct scatterlist *sgout,
@@ -495,6 +509,28 @@ static void tls_encrypt_done(void *data, int err)
schedule_delayed_work(&ctx->tx_work.work, 1);
}
+static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
+{
+ int pending;
+
+ spin_lock_bh(&ctx->encrypt_compl_lock);
+ ctx->async_notify = true;
+
+ pending = atomic_read(&ctx->encrypt_pending);
+ spin_unlock_bh(&ctx->encrypt_compl_lock);
+ if (pending)
+ crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ else
+ reinit_completion(&ctx->async_wait.completion);
+
+ /* There can be no concurrent accesses, since we have no
+ * pending encrypt operations
+ */
+ WRITE_ONCE(ctx->async_notify, false);
+
+ return ctx->async_wait.err;
+}
+
static int tls_do_encryption(struct sock *sk,
struct tls_context *tls_ctx,
struct tls_sw_context_tx *ctx,
@@ -984,7 +1020,6 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
int num_zc = 0;
int orig_size;
int ret = 0;
- int pending;
if (!eor && (msg->msg_flags & MSG_EOR))
return -EINVAL;
@@ -1163,24 +1198,12 @@ trim_sgl:
if (!num_async) {
goto send_end;
} else if (num_zc) {
+ int err;
+
/* Wait for pending encryptions to get completed */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
-
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- else
- reinit_completion(&ctx->async_wait.completion);
-
- /* There can be no concurrent accesses, since we have no
- * pending encrypt operations
- */
- WRITE_ONCE(ctx->async_notify, false);
-
- if (ctx->async_wait.err) {
- ret = ctx->async_wait.err;
+ err = tls_encrypt_async_wait(ctx);
+ if (err) {
+ ret = err;
copied = 0;
}
}
@@ -1229,7 +1252,6 @@ void tls_sw_splice_eof(struct socket *sock)
ssize_t copied = 0;
bool retrying = false;
int ret = 0;
- int pending;
if (!ctx->open_rec)
return;
@@ -1264,22 +1286,7 @@ retry:
}
/* Wait for pending encryptions to get completed */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
-
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- else
- reinit_completion(&ctx->async_wait.completion);
-
- /* There can be no concurrent accesses, since we have no pending
- * encrypt operations
- */
- WRITE_ONCE(ctx->async_notify, false);
-
- if (ctx->async_wait.err)
+ if (tls_encrypt_async_wait(ctx))
goto unlock;
/* Transmit if any encryptions have completed */
@@ -2109,16 +2116,10 @@ put_on_rx_list:
recv_end:
if (async) {
- int ret, pending;
+ int ret;
/* Wait for all previously submitted records to be decrypted */
- spin_lock_bh(&ctx->decrypt_compl_lock);
- reinit_completion(&ctx->async_wait.completion);
- pending = atomic_read(&ctx->decrypt_pending);
- spin_unlock_bh(&ctx->decrypt_compl_lock);
- ret = 0;
- if (pending)
- ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ ret = tls_decrypt_async_wait(ctx);
__skb_queue_purge(&ctx->async_hold);
if (ret) {
@@ -2435,16 +2436,9 @@ void tls_sw_release_resources_tx(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
- int pending;
/* Wait for any pending async encryptions to complete */
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
-
- if (pending)
- crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ tls_encrypt_async_wait(ctx);
tls_tx_records(sk, -1);
From aec7961916f3f9e88766e2688992da6980f11b8d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:19 -0800
Subject: [PATCH 426/637] tls: fix race between async notify and socket close
The submitting thread (one which called recvmsg/sendmsg)
may exit as soon as the async crypto handler calls complete()
so any code past that point risks touching already freed data.
Try to avoid the locking and extra flags altogether.
Have the main thread hold an extra reference, this way
we can depend solely on the atomic ref counter for
synchronization.
Don't futz with reiniting the completion, either, we are now
tightly controlling when completion fires.
Reported-by: valis <sec@valis.email>
Fixes: 0cada33241d9 ("net/tls: fix race condition causing kernel panic")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/tls.h | 5 -----
net/tls/tls_sw.c | 43 ++++++++++---------------------------------
2 files changed, 10 insertions(+), 38 deletions(-)
diff --git a/include/net/tls.h b/include/net/tls.h
index 962f0c501111..340ad43971e4 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -97,9 +97,6 @@ struct tls_sw_context_tx {
struct tls_rec *open_rec;
struct list_head tx_list;
atomic_t encrypt_pending;
- /* protect crypto_wait with encrypt_pending */
- spinlock_t encrypt_compl_lock;
- int async_notify;
u8 async_capable:1;
#define BIT_TX_SCHEDULED 0
@@ -136,8 +133,6 @@ struct tls_sw_context_rx {
struct tls_strparser strp;
atomic_t decrypt_pending;
- /* protect crypto_wait with decrypt_pending*/
- spinlock_t decrypt_compl_lock;
struct sk_buff_head async_hold;
struct wait_queue_head wq;
};
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6a73714f34cc..635305bebfef 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -224,22 +224,15 @@ static void tls_decrypt_done(void *data, int err)
kfree(aead_req);
- spin_lock_bh(&ctx->decrypt_compl_lock);
- if (!atomic_dec_return(&ctx->decrypt_pending))
+ if (atomic_dec_and_test(&ctx->decrypt_pending))
complete(&ctx->async_wait.completion);
- spin_unlock_bh(&ctx->decrypt_compl_lock);
}
static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
{
- int pending;
-
- spin_lock_bh(&ctx->decrypt_compl_lock);
- reinit_completion(&ctx->async_wait.completion);
- pending = atomic_read(&ctx->decrypt_pending);
- spin_unlock_bh(&ctx->decrypt_compl_lock);
- if (pending)
+ if (!atomic_dec_and_test(&ctx->decrypt_pending))
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ atomic_inc(&ctx->decrypt_pending);
return ctx->async_wait.err;
}
@@ -267,6 +260,7 @@ static int tls_do_decryption(struct sock *sk,
aead_request_set_callback(aead_req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_decrypt_done, aead_req);
+ DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->decrypt_pending) < 1);
atomic_inc(&ctx->decrypt_pending);
} else {
aead_request_set_callback(aead_req,
@@ -455,7 +449,6 @@ static void tls_encrypt_done(void *data, int err)
struct sk_msg *msg_en;
bool ready = false;
struct sock *sk;
- int pending;
msg_en = &rec->msg_encrypted;
@@ -494,12 +487,8 @@ static void tls_encrypt_done(void *data, int err)
ready = true;
}
- spin_lock_bh(&ctx->encrypt_compl_lock);
- pending = atomic_dec_return(&ctx->encrypt_pending);
-
- if (!pending && ctx->async_notify)
+ if (atomic_dec_and_test(&ctx->encrypt_pending))
complete(&ctx->async_wait.completion);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
if (!ready)
return;
@@ -511,22 +500,9 @@ static void tls_encrypt_done(void *data, int err)
static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
{
- int pending;
-
- spin_lock_bh(&ctx->encrypt_compl_lock);
- ctx->async_notify = true;
-
- pending = atomic_read(&ctx->encrypt_pending);
- spin_unlock_bh(&ctx->encrypt_compl_lock);
- if (pending)
+ if (!atomic_dec_and_test(&ctx->encrypt_pending))
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- else
- reinit_completion(&ctx->async_wait.completion);
-
- /* There can be no concurrent accesses, since we have no
- * pending encrypt operations
- */
- WRITE_ONCE(ctx->async_notify, false);
+ atomic_inc(&ctx->encrypt_pending);
return ctx->async_wait.err;
}
@@ -577,6 +553,7 @@ static int tls_do_encryption(struct sock *sk,
/* Add the record in tx_list */
list_add_tail((struct list_head *)&rec->list, &ctx->tx_list);
+ DEBUG_NET_WARN_ON_ONCE(atomic_read(&ctx->encrypt_pending) < 1);
atomic_inc(&ctx->encrypt_pending);
rc = crypto_aead_encrypt(aead_req);
@@ -2601,7 +2578,7 @@ static struct tls_sw_context_tx *init_ctx_tx(struct tls_context *ctx, struct soc
}
crypto_init_wait(&sw_ctx_tx->async_wait);
- spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
+ atomic_set(&sw_ctx_tx->encrypt_pending, 1);
INIT_LIST_HEAD(&sw_ctx_tx->tx_list);
INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler);
sw_ctx_tx->tx_work.sk = sk;
@@ -2622,7 +2599,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx)
}
crypto_init_wait(&sw_ctx_rx->async_wait);
- spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
+ atomic_set(&sw_ctx_rx->decrypt_pending, 1);
init_waitqueue_head(&sw_ctx_rx->wq);
skb_queue_head_init(&sw_ctx_rx->rx_list);
skb_queue_head_init(&sw_ctx_rx->async_hold);
From e01e3934a1b2d122919f73bc6ddbe1cdafc4bbdb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:20 -0800
Subject: [PATCH 427/637] tls: fix race between tx work scheduling and socket
close
Similarly to previous commit, the submitting thread (recvmsg/sendmsg)
may exit as soon as the async crypto handler calls complete().
Reorder scheduling the work before calling complete().
This seems more logical in the first place, as it's
the inverse order of what the submitting thread will do.
Reported-by: valis <sec@valis.email>
Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tls/tls_sw.c | 16 ++++++----------
1 file changed, 6 insertions(+), 10 deletions(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 635305bebfef..9374a61cef00 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -447,7 +447,6 @@ static void tls_encrypt_done(void *data, int err)
struct tls_rec *rec = data;
struct scatterlist *sge;
struct sk_msg *msg_en;
- bool ready = false;
struct sock *sk;
msg_en = &rec->msg_encrypted;
@@ -483,19 +482,16 @@ static void tls_encrypt_done(void *data, int err)
/* If received record is at head of tx_list, schedule tx */
first_rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
- if (rec == first_rec)
- ready = true;
+ if (rec == first_rec) {
+ /* Schedule the transmission */
+ if (!test_and_set_bit(BIT_TX_SCHEDULED,
+ &ctx->tx_bitmask))
+ schedule_delayed_work(&ctx->tx_work.work, 1);
+ }
}
if (atomic_dec_and_test(&ctx->encrypt_pending))
complete(&ctx->async_wait.completion);
-
- if (!ready)
- return;
-
- /* Schedule the transmission */
- if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
- schedule_delayed_work(&ctx->tx_work.work, 1);
}
static int tls_encrypt_async_wait(struct tls_sw_context_tx *ctx)
From 8590541473188741055d27b955db0777569438e3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:21 -0800
Subject: [PATCH 428/637] net: tls: handle backlogging of crypto requests
Since we're setting the CRYPTO_TFM_REQ_MAY_BACKLOG flag on our
requests to the crypto API, crypto_aead_{encrypt,decrypt} can return
-EBUSY instead of -EINPROGRESS in valid situations. For example, when
the cryptd queue for AESNI is full (easy to trigger with an
artificially low cryptd.cryptd_max_cpu_qlen), requests will be enqueued
to the backlog but still processed. In that case, the async callback
will also be called twice: first with err == -EINPROGRESS, which it
seems we can just ignore, then with err == 0.
Compared to Sabrina's original patch this version uses the new
tls_*crypt_async_wait() helpers and converts the EBUSY to
EINPROGRESS to avoid having to modify all the error handling
paths. The handling is identical.
Fixes: a54667f6728c ("tls: Add support for encryption using async offload accelerator")
Fixes: 94524d8fc965 ("net/tls: Add support for async decryption of tls records")
Co-developed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/netdev/9681d1febfec295449a62300938ed2ae66983f28.1694018970.git.sd@queasysnail.net/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tls/tls_sw.c | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9374a61cef00..63bef5666e36 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -196,6 +196,17 @@ static void tls_decrypt_done(void *data, int err)
struct sock *sk;
int aead_size;
+ /* If requests get too backlogged crypto API returns -EBUSY and calls
+ * ->complete(-EINPROGRESS) immediately followed by ->complete(0)
+ * to make waiting for backlog to flush with crypto_wait_req() easier.
+ * First wait converts -EBUSY -> -EINPROGRESS, and the second one
+ * -EINPROGRESS -> 0.
+ * We have a single struct crypto_async_request per direction, this
+ * scheme doesn't help us, so just ignore the first ->complete().
+ */
+ if (err == -EINPROGRESS)
+ return;
+
aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead);
aead_size = ALIGN(aead_size, __alignof__(*dctx));
dctx = (void *)((u8 *)aead_req + aead_size);
@@ -269,6 +280,10 @@ static int tls_do_decryption(struct sock *sk,
}
ret = crypto_aead_decrypt(aead_req);
+ if (ret == -EBUSY) {
+ ret = tls_decrypt_async_wait(ctx);
+ ret = ret ?: -EINPROGRESS;
+ }
if (ret == -EINPROGRESS) {
if (darg->async)
return 0;
@@ -449,6 +464,9 @@ static void tls_encrypt_done(void *data, int err)
struct sk_msg *msg_en;
struct sock *sk;
+ if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */
+ return;
+
msg_en = &rec->msg_encrypted;
sk = rec->sk;
@@ -553,6 +571,10 @@ static int tls_do_encryption(struct sock *sk,
atomic_inc(&ctx->encrypt_pending);
rc = crypto_aead_encrypt(aead_req);
+ if (rc == -EBUSY) {
+ rc = tls_encrypt_async_wait(ctx);
+ rc = rc ?: -EINPROGRESS;
+ }
if (!rc || rc != -EINPROGRESS) {
atomic_dec(&ctx->encrypt_pending);
sge->offset -= prot->prepend_size;
From 32b55c5ff9103b8508c1e04bfa5a08c64e7a925f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 6 Feb 2024 17:18:22 -0800
Subject: [PATCH 429/637] net: tls: fix use-after-free with partial reads and
async decrypt
tls_decrypt_sg doesn't take a reference on the pages from clear_skb,
so the put_page() in tls_decrypt_done releases them, and we trigger
a use-after-free in process_rx_list when we try to read from the
partially-read skb.
Fixes: fd31f3996af2 ("tls: rx: decrypt into a fresh skb")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tls/tls_sw.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 63bef5666e36..a6eff21ade23 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -63,6 +63,7 @@ struct tls_decrypt_ctx {
u8 iv[TLS_MAX_IV_SIZE];
u8 aad[TLS_MAX_AAD_SIZE];
u8 tail;
+ bool free_sgout;
struct scatterlist sg[];
};
@@ -187,7 +188,6 @@ static void tls_decrypt_done(void *data, int err)
struct aead_request *aead_req = data;
struct crypto_aead *aead = crypto_aead_reqtfm(aead_req);
struct scatterlist *sgout = aead_req->dst;
- struct scatterlist *sgin = aead_req->src;
struct tls_sw_context_rx *ctx;
struct tls_decrypt_ctx *dctx;
struct tls_context *tls_ctx;
@@ -224,7 +224,7 @@ static void tls_decrypt_done(void *data, int err)
}
/* Free the destination pages if skb was not decrypted inplace */
- if (sgout != sgin) {
+ if (dctx->free_sgout) {
/* Skip the first S/G entry as it points to AAD */
for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
if (!sg)
@@ -1583,6 +1583,7 @@ static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
} else if (out_sg) {
memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
}
+ dctx->free_sgout = !!pages;
/* Prepare and submit AEAD request */
err = tls_do_decryption(sk, sgin, sgout, dctx->iv,
From 49d821064c44cb5ffdf272905236012ea9ce50e3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:23 -0800
Subject: [PATCH 430/637] selftests: tls: use exact comparison in recv_partial
This exact case was fail for async crypto and we weren't
catching it.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/tls.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 7799e042a971..bc36c91c4480 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1002,12 +1002,12 @@ TEST_F(tls, recv_partial)
memset(recv_mem, 0, sizeof(recv_mem));
EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
- EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first),
- MSG_WAITALL), -1);
+ EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first),
+ MSG_WAITALL), strlen(test_str_first));
EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
memset(recv_mem, 0, sizeof(recv_mem));
- EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second),
- MSG_WAITALL), -1);
+ EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second),
+ MSG_WAITALL), strlen(test_str_second));
EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
0);
}
From ac437a51ce662364062f704e321227f6728e6adc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 Feb 2024 17:18:24 -0800
Subject: [PATCH 431/637] net: tls: fix returned read length with async decrypt
We double count async, non-zc rx data. The previous fix was
lucky because if we fully zc async_copy_bytes is 0 so we add 0.
Decrypted already has all the bytes we handled, in all cases.
We don't have to adjust anything, delete the erroneous line.
Fixes: 4d42cd6bc2ac ("tls: rx: fix return value for async crypto")
Co-developed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tls/tls_sw.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index a6eff21ade23..9fbc70200cd0 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2132,7 +2132,6 @@ recv_end:
else
err = process_rx_list(ctx, msg, &control, 0,
async_copy_bytes, is_peek);
- decrypted += max(err, 0);
}
copied += decrypted;
From 1a1c93e7f8141749ecb10165a95e95ad484bb85f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 9 Feb 2024 18:34:05 -0500
Subject: [PATCH 432/637] bcachefs: Fix missing bch2_err_class() calls
We aren't supposed to be leaking our private error codes outside of
fs/bcachefs/.
Fixes:
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/fs.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index ec419b8e2c43..77ae65542db9 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -435,7 +435,7 @@ static int bch2_link(struct dentry *old_dentry, struct inode *vdir,
bch2_subvol_is_ro(c, inode->ei_subvol) ?:
__bch2_link(c, inode, dir, dentry);
if (unlikely(ret))
- return ret;
+ return bch2_err_class(ret);
ihold(&inode->v);
d_instantiate(dentry, &inode->v);
@@ -487,8 +487,9 @@ static int bch2_unlink(struct inode *vdir, struct dentry *dentry)
struct bch_inode_info *dir= to_bch_ei(vdir);
struct bch_fs *c = dir->v.i_sb->s_fs_info;
- return bch2_subvol_is_ro(c, dir->ei_subvol) ?:
+ int ret = bch2_subvol_is_ro(c, dir->ei_subvol) ?:
__bch2_unlink(vdir, dentry, false);
+ return bch2_err_class(ret);
}
static int bch2_symlink(struct mnt_idmap *idmap,
@@ -523,7 +524,7 @@ static int bch2_symlink(struct mnt_idmap *idmap,
return 0;
err:
iput(&inode->v);
- return ret;
+ return bch2_err_class(ret);
}
static int bch2_mkdir(struct mnt_idmap *idmap,
@@ -641,7 +642,7 @@ err:
src_inode,
dst_inode);
- return ret;
+ return bch2_err_class(ret);
}
static void bch2_setattr_copy(struct mnt_idmap *idmap,
From 7dcfb87af9731d051decb9f99ec3cc35cf684865 Mon Sep 17 00:00:00 2001
From: Su Yue <glass.su@suse.com>
Date: Fri, 9 Feb 2024 21:41:31 +0800
Subject: [PATCH 433/637] bcachefs: fix kmemleak in __bch2_read_super error
handling path
During xfstest tests, there are some kmemleak reports e.g. generic/051 with
if USE_KMEMLEAK=yes:
====================================================================
EXPERIMENTAL kmemleak reported some memory leaks! Due to the way kmemleak
works, the leak might be from an earlier test, or something totally unrelated.
unreferenced object 0xffff9ef905aaf778 (size 8):
comm "mount.bcachefs", pid 169844, jiffies 4295281209 (age 87.040s)
hex dump (first 8 bytes):
a5 cc cc cc cc cc cc cc ........
backtrace:
[<ffffffff87fd9a43>] __kmem_cache_alloc_node+0x1f3/0x2c0
[<ffffffff87f49b66>] kmalloc_trace+0x26/0xb0
[<ffffffffc0a3fefe>] __bch2_read_super+0xfe/0x4e0 [bcachefs]
[<ffffffffc0a3ad22>] bch2_fs_open+0x262/0x1710 [bcachefs]
[<ffffffffc09c9e24>] bch2_mount+0x4c4/0x640 [bcachefs]
[<ffffffff88080c90>] legacy_get_tree+0x30/0x60
[<ffffffff8802c748>] vfs_get_tree+0x28/0xf0
[<ffffffff88061fe5>] path_mount+0x475/0xb60
[<ffffffff880627e5>] __x64_sys_mount+0x105/0x140
[<ffffffff88932642>] do_syscall_64+0x42/0xf0
[<ffffffff88a000e6>] entry_SYSCALL_64_after_hwframe+0x6e/0x76
unreferenced object 0xffff9ef96cdc4fc0 (size 32):
comm "mount.bcachefs", pid 169844, jiffies 4295281209 (age 87.040s)
hex dump (first 32 bytes):
2f 64 65 76 2f 6d 61 70 70 65 72 2f 74 65 73 74 /dev/mapper/test
2d 31 00 cc cc cc cc cc cc cc cc cc cc cc cc cc -1..............
backtrace:
[<ffffffff87fd9a43>] __kmem_cache_alloc_node+0x1f3/0x2c0
[<ffffffff87f4a081>] __kmalloc_node_track_caller+0x51/0x150
[<ffffffff87f3adc2>] kstrdup+0x32/0x60
[<ffffffffc0a3ff1a>] __bch2_read_super+0x11a/0x4e0 [bcachefs]
[<ffffffffc0a3ad22>] bch2_fs_open+0x262/0x1710 [bcachefs]
[<ffffffffc09c9e24>] bch2_mount+0x4c4/0x640 [bcachefs]
[<ffffffff88080c90>] legacy_get_tree+0x30/0x60
[<ffffffff8802c748>] vfs_get_tree+0x28/0xf0
[<ffffffff88061fe5>] path_mount+0x475/0xb60
[<ffffffff880627e5>] __x64_sys_mount+0x105/0x140
[<ffffffff88932642>] do_syscall_64+0x42/0xf0
[<ffffffff88a000e6>] entry_SYSCALL_64_after_hwframe+0x6e/0x76
====================================================================
The leak happens if bdev_open_by_path() failed to open a block device
then it goes label 'out' directly without call of bch2_free_super().
Fix it by going to label 'err' instead of 'out' if bdev_open_by_path()
fails.
Signed-off-by: Su Yue <glass.su@suse.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/super-io.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index d60c7d27a047..36988add581f 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -717,7 +717,7 @@ retry:
if (IS_ERR(sb->bdev_handle)) {
ret = PTR_ERR(sb->bdev_handle);
- goto out;
+ goto err;
}
sb->bdev = sb->bdev_handle->bdev;
From 04eb57930e4e471d8f16455a748df2009d43c139 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 10 Feb 2024 16:28:52 -0500
Subject: [PATCH 434/637] bcachefs: fix missing endiannes conversion in
sb_members
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/sb-members.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index a45354d2acde..eff5ce18c69c 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -421,7 +421,7 @@ void bch2_dev_errors_reset(struct bch_dev *ca)
m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx);
for (unsigned i = 0; i < ARRAY_SIZE(m->errors_at_reset); i++)
m->errors_at_reset[i] = cpu_to_le64(atomic64_read(&ca->errors[i]));
- m->errors_reset_time = ktime_get_real_seconds();
+ m->errors_reset_time = cpu_to_le64(ktime_get_real_seconds());
bch2_write_super(c);
mutex_unlock(&c->sb_lock);
From 7d99a70b65951108d82e1618c67abe69c3ed7720 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 10 Feb 2024 14:43:59 +0100
Subject: [PATCH 435/637] ASoC: Intel: Boards: Fix NULL pointer deref in
BYT/CHT boards
Since commit 13f58267cda3 ("ASoC: soc.h: don't create dummy Component
via COMP_DUMMY()") dummy snd_soc_dai_link.codecs entries no longer
have a name set.
This means that when looking for the codec dai_link the machine
driver can no longer unconditionally run strcmp() on
snd_soc_dai_link.codecs[0].name since this may now be NULL.
Add a check for snd_soc_dai_link.codecs[0].name being NULL to all
BYT/CHT machine drivers to avoid NULL pointer dereferences in
their probe() methods.
Fixes: 13f58267cda3 ("ASoC: soc.h: don't create dummy Component via COMP_DUMMY()")
Cc: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240210134400.24913-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/boards/bytcht_cx2072x.c | 3 ++-
sound/soc/intel/boards/bytcht_da7213.c | 3 ++-
sound/soc/intel/boards/bytcht_es8316.c | 3 ++-
sound/soc/intel/boards/bytcr_rt5640.c | 3 ++-
sound/soc/intel/boards/bytcr_rt5651.c | 3 ++-
sound/soc/intel/boards/bytcr_wm5102.c | 3 ++-
sound/soc/intel/boards/cht_bsw_rt5645.c | 3 ++-
sound/soc/intel/boards/cht_bsw_rt5672.c | 3 ++-
8 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/sound/soc/intel/boards/bytcht_cx2072x.c b/sound/soc/intel/boards/bytcht_cx2072x.c
index 10a84a2c1036..c014d85a08b2 100644
--- a/sound/soc/intel/boards/bytcht_cx2072x.c
+++ b/sound/soc/intel/boards/bytcht_cx2072x.c
@@ -241,7 +241,8 @@ static int snd_byt_cht_cx2072x_probe(struct platform_device *pdev)
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_cht_cx2072x_dais); i++) {
- if (!strcmp(byt_cht_cx2072x_dais[i].codecs->name,
+ if (byt_cht_cx2072x_dais[i].codecs->name &&
+ !strcmp(byt_cht_cx2072x_dais[i].codecs->name,
"i2c-14F10720:00")) {
dai_index = i;
break;
diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
index 7e5eea690023..f4ac3ddd148b 100644
--- a/sound/soc/intel/boards/bytcht_da7213.c
+++ b/sound/soc/intel/boards/bytcht_da7213.c
@@ -245,7 +245,8 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(dailink); i++) {
- if (!strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
+ if (dailink[i].codecs->name &&
+ !strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
dai_index = i;
break;
}
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 1564a88a885e..2fcec2e02bb5 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -546,7 +546,8 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_cht_es8316_dais); i++) {
- if (!strcmp(byt_cht_es8316_dais[i].codecs->name,
+ if (byt_cht_es8316_dais[i].codecs->name &&
+ !strcmp(byt_cht_es8316_dais[i].codecs->name,
"i2c-ESSX8316:00")) {
dai_index = i;
break;
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 42466b4b1ca4..03be5e26ec4a 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -1652,7 +1652,8 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_rt5640_dais); i++) {
- if (!strcmp(byt_rt5640_dais[i].codecs->name,
+ if (byt_rt5640_dais[i].codecs->name &&
+ !strcmp(byt_rt5640_dais[i].codecs->name,
"i2c-10EC5640:00")) {
dai_index = i;
break;
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index f9fe8414f454..80c841b000a3 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -910,7 +910,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_rt5651_dais); i++) {
- if (!strcmp(byt_rt5651_dais[i].codecs->name,
+ if (byt_rt5651_dais[i].codecs->name &&
+ !strcmp(byt_rt5651_dais[i].codecs->name,
"i2c-10EC5651:00")) {
dai_index = i;
break;
diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c
index 6978ebde6693..cccb5e90c0fe 100644
--- a/sound/soc/intel/boards/bytcr_wm5102.c
+++ b/sound/soc/intel/boards/bytcr_wm5102.c
@@ -605,7 +605,8 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev)
/* find index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_wm5102_dais); i++) {
- if (!strcmp(byt_wm5102_dais[i].codecs->name,
+ if (byt_wm5102_dais[i].codecs->name &&
+ !strcmp(byt_wm5102_dais[i].codecs->name,
"wm5102-codec")) {
dai_index = i;
break;
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index c952a96cde7e..7773f61064f4 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -571,7 +571,8 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
/* set correct codec name */
for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
- if (!strcmp(card->dai_link[i].codecs->name,
+ if (card->dai_link[i].codecs->name &&
+ !strcmp(card->dai_link[i].codecs->name,
"i2c-10EC5645:00")) {
card->dai_link[i].codecs->name = drv->codec_name;
dai_index = i;
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index 8cf0b33cc02e..be2d1a8dbca8 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -466,7 +466,8 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
/* find index of codec dai */
for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
- if (!strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
+ if (cht_dailink[i].codecs->name &&
+ !strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
dai_index = i;
break;
}
From 930375d34de67e129566caca008de0bbc54a4646 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 10 Feb 2024 14:44:00 +0100
Subject: [PATCH 436/637] ASoC: Intel: cht_bsw_rt5645: Cleanup codec_name
handling
4 fixes / cleanups to the rt5645 mc driver's codec_name handling:
1. In the for loop looking for the dai_index for the codec, replace
card->dai_link[i] with cht_dailink[i]. The for loop already uses
ARRAY_SIZE(cht_dailink) as bound and card->dai_link is just a pointer to
cht_dailink using card->dai_link only obfuscates that cht_dailink is being
modified directly rather then say a copy of cht_dailink. Using
cht_dailink[i] also makes the code consistent with other machine drivers.
2. Don't set cht_dailink[dai_index].codecs->name in the for loop,
this immediately gets overridden using acpi_dev_name(adev) directly
below the loop.
3. Add a missing break to the loop.
4. Remove the now no longer used (only set, never read) codec_name field
from struct cht_mc_private.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20240210134400.24913-3-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/boards/cht_bsw_rt5645.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 7773f61064f4..eb41b7115d01 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -40,7 +40,6 @@ struct cht_acpi_card {
struct cht_mc_private {
struct snd_soc_jack jack;
struct cht_acpi_card *acpi_card;
- char codec_name[SND_ACPI_I2C_ID_LEN];
struct clk *mclk;
};
@@ -567,15 +566,14 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
}
card->dev = &pdev->dev;
- sprintf(drv->codec_name, "i2c-%s:00", drv->acpi_card->codec_id);
/* set correct codec name */
for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
- if (card->dai_link[i].codecs->name &&
- !strcmp(card->dai_link[i].codecs->name,
+ if (cht_dailink[i].codecs->name &&
+ !strcmp(cht_dailink[i].codecs->name,
"i2c-10EC5645:00")) {
- card->dai_link[i].codecs->name = drv->codec_name;
dai_index = i;
+ break;
}
/* fixup codec name based on HID */
From 6f98e44984d5eff599906c0376c027df985bf38b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 10 Feb 2024 17:40:06 +0100
Subject: [PATCH 437/637] spi: ppc4xx: Fix fallout from include cleanup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The driver uses several symbols declared in <linux/platform_device.h>,
e.g module_platform_driver(). Include this header explicitly now that
<linux/of_platform.h> doesn't include <linux/platform_device.h> any
more.
Fixes: ef175b29a242 ("of: Stop circularly including of_device.h and of_platform.h")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20240210164006.208149-6-u.kleine-koenig@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-ppc4xx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 412d6e678224..2290b40459ef 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -31,6 +31,7 @@
#include <linux/of_platform.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
+#include <linux/platform_device.h>
#include <linux/spi/spi.h>
#include <linux/spi/spi_bitbang.h>
From de4af897ddf242aea18ee90d3ad2e21b4e64359c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 10 Feb 2024 17:40:07 +0100
Subject: [PATCH 438/637] spi: ppc4xx: Fix fallout from rename in struct
spi_bitbang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
I failed to adapt this driver because it's not enabled in a powerpc
allmodconfig build and also wasn't hit by my grep expertise. Fix
accordingly.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202402100815.XQXw9XCF-lkp@intel.com/
Fixes: 2259233110d9 ("spi: bitbang: Follow renaming of SPI "master" to "controller"")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20240210164006.208149-7-u.kleine-koenig@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-ppc4xx.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 2290b40459ef..2d5536efa9f8 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -364,22 +364,22 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
/* Setup the state for the bitbang driver */
bbp = &hw->bitbang;
- bbp->master = hw->host;
+ bbp->ctlr = hw->host;
bbp->setup_transfer = spi_ppc4xx_setupxfer;
bbp->txrx_bufs = spi_ppc4xx_txrx;
bbp->use_dma = 0;
- bbp->master->setup = spi_ppc4xx_setup;
- bbp->master->cleanup = spi_ppc4xx_cleanup;
- bbp->master->bits_per_word_mask = SPI_BPW_MASK(8);
- bbp->master->use_gpio_descriptors = true;
+ bbp->ctlr->setup = spi_ppc4xx_setup;
+ bbp->ctlr->cleanup = spi_ppc4xx_cleanup;
+ bbp->ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
+ bbp->ctlr->use_gpio_descriptors = true;
/*
* The SPI core will count the number of GPIO descriptors to figure
* out the number of chip selects available on the platform.
*/
- bbp->master->num_chipselect = 0;
+ bbp->ctlr->num_chipselect = 0;
/* the spi->mode bits understood by this driver: */
- bbp->master->mode_bits =
+ bbp->ctlr->mode_bits =
SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST;
/* Get the clock for the OPB */
From b3aa619a8b4706f35cb62f780c14e68796b37f3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Sat, 10 Feb 2024 17:40:08 +0100
Subject: [PATCH 439/637] spi: ppc4xx: Drop write-only variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Since commit 24778be20f87 ("spi: convert drivers to use
bits_per_word_mask") the bits_per_word variable is only written to. The
check that was there before isn't needed any more as the spi core
ensures that only 8 bit transfers are used, so the variable can go away
together with all assignments to it.
Fixes: 24778be20f87 ("spi: convert drivers to use bits_per_word_mask")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20240210164006.208149-8-u.kleine-koenig@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-ppc4xx.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 2d5536efa9f8..942c3117ab3a 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -168,10 +168,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
int scr;
u8 cdm = 0;
u32 speed;
- u8 bits_per_word;
/* Start with the generic configuration for this device. */
- bits_per_word = spi->bits_per_word;
speed = spi->max_speed_hz;
/*
@@ -179,9 +177,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t)
* the transfer to overwrite the generic configuration with zeros.
*/
if (t) {
- if (t->bits_per_word)
- bits_per_word = t->bits_per_word;
-
if (t->speed_hz)
speed = min(t->speed_hz, spi->max_speed_hz);
}
From 6ef5d5b92f7117b324efaac72b3db27ae8bb3082 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sun, 11 Feb 2024 12:58:34 +0300
Subject: [PATCH 440/637] ASoC: rt5645: Fix deadlock in
rt5645_jack_detect_work()
There is a path in rt5645_jack_detect_work(), where rt5645->jd_mutex
is left locked forever. That may lead to deadlock
when rt5645_jack_detect_work() is called for the second time.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: cdba4301adda ("ASoC: rt5650: add mutex to avoid the jack detection failure")
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Link: https://lore.kernel.org/r/1707645514-21196-1-git-send-email-khoroshilov@ispras.ru
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/rt5645.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 5150d6ee3748..0cc2fa131d48 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3317,6 +3317,7 @@ static void rt5645_jack_detect_work(struct work_struct *work)
report, SND_JACK_HEADPHONE);
snd_soc_jack_report(rt5645->mic_jack,
report, SND_JACK_MICROPHONE);
+ mutex_unlock(&rt5645->jd_mutex);
return;
case 4:
val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020;
From c4b603c6e2df3a17831731d8bbec5c16fa7bbdf8 Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Date: Fri, 9 Feb 2024 01:43:14 +0200
Subject: [PATCH 441/637] ASoC: SOF: amd: Fix locking in ACP IRQ handler
A recent change in acp_irq_thread() was meant to address a potential race
condition while trying to acquire the hardware semaphore responsible for
the synchronization between firmware and host IPC interrupts.
This resulted in an improper use of the IPC spinlock, causing normal
kernel memory allocations (which may sleep) inside atomic contexts:
1707255557.133976 kernel: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:315
...
1707255557.134757 kernel: sof_ipc3_rx_msg+0x70/0x130 [snd_sof]
1707255557.134793 kernel: acp_sof_ipc_irq_thread+0x1e0/0x550 [snd_sof_amd_acp]
1707255557.134855 kernel: acp_irq_thread+0xa3/0x130 [snd_sof_amd_acp]
1707255557.134904 kernel: ? irq_thread+0xb5/0x1e0
1707255557.134947 kernel: ? __pfx_irq_thread_fn+0x10/0x10
1707255557.134985 kernel: irq_thread_fn+0x23/0x60
Moreover, there are attempts to lock a mutex from the same atomic
context:
1707255557.136357 kernel: =============================
1707255557.136393 kernel: [ BUG: Invalid wait context ]
1707255557.136413 kernel: 6.8.0-rc3-next-20240206-audio-next #9 Tainted: G W
1707255557.136432 kernel: -----------------------------
1707255557.136451 kernel: irq/66-AudioDSP/502 is trying to lock:
1707255557.136470 kernel: ffff965152f26af8 (&sb->s_type->i_mutex_key#2){+.+.}-{3:3}, at: start_creating.part.0+0x5f/0x180
...
1707255557.137429 kernel: start_creating.part.0+0x5f/0x180
1707255557.137457 kernel: __debugfs_create_file+0x61/0x210
1707255557.137475 kernel: snd_sof_debugfs_io_item+0x75/0xc0 [snd_sof]
1707255557.137494 kernel: sof_ipc3_do_rx_work+0x7cf/0x9f0 [snd_sof]
1707255557.137513 kernel: sof_ipc3_rx_msg+0xb3/0x130 [snd_sof]
1707255557.137532 kernel: acp_sof_ipc_irq_thread+0x1e0/0x550 [snd_sof_amd_acp]
1707255557.137551 kernel: acp_irq_thread+0xa3/0x130 [snd_sof_amd_acp]
Fix the issues by reducing the lock scope in acp_irq_thread(), so that
it guards only the hardware semaphore acquiring attempt. Additionally,
restore the initial locking in acp_sof_ipc_irq_thread() to synchronize
the handling of immediate replies from DSP core.
Fixes: 802134c8c2c8 ("ASoC: SOF: amd: Refactor spinlock_irq(&sdev->ipc_lock) sequence in irq_handler")
Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Link: https://lore.kernel.org/r/20240208234315.2182048-1-cristian.ciocaltea@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/amd/acp-ipc.c | 2 ++
sound/soc/sof/amd/acp.c | 17 ++++++++---------
2 files changed, 10 insertions(+), 9 deletions(-)
diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c
index 2743f07a5e08..b44b1b1adb6e 100644
--- a/sound/soc/sof/amd/acp-ipc.c
+++ b/sound/soc/sof/amd/acp-ipc.c
@@ -188,11 +188,13 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context)
dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write);
if (dsp_ack) {
+ spin_lock_irq(&sdev->ipc_lock);
/* handle immediate reply from DSP core */
acp_dsp_ipc_get_reply(sdev);
snd_sof_ipc_reply(sdev, 0);
/* set the done bit */
acp_dsp_ipc_dsp_done(sdev);
+ spin_unlock_irq(&sdev->ipc_lock);
ipc_irq = true;
}
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index 32a741fcb84f..07632ae6ccf5 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -355,21 +355,20 @@ static irqreturn_t acp_irq_thread(int irq, void *context)
unsigned int count = ACP_HW_SEM_RETRY_COUNT;
spin_lock_irq(&sdev->ipc_lock);
- while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset)) {
- /* Wait until acquired HW Semaphore lock or timeout */
- count--;
- if (!count) {
- dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
- spin_unlock_irq(&sdev->ipc_lock);
- return IRQ_NONE;
- }
+ /* Wait until acquired HW Semaphore lock or timeout */
+ while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset) && --count)
+ ;
+ spin_unlock_irq(&sdev->ipc_lock);
+
+ if (!count) {
+ dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
+ return IRQ_NONE;
}
sof_ops(sdev)->irq_thread(irq, sdev);
/* Unlock or Release HW Semaphore */
snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset, 0x0);
- spin_unlock_irq(&sdev->ipc_lock);
return IRQ_HANDLED;
};
From 841c35169323cd833294798e58b9bf63fa4fa1de Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 11 Feb 2024 12:18:13 -0800
Subject: [PATCH 442/637] Linux 6.8-rc4
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index a171eafce2a3..7e0b2ad98905 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
From cffe487026be13eaf37ea28b783d9638ab147204 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 8 Feb 2024 13:18:46 +0300
Subject: [PATCH 443/637] cifs: fix underflow in parse_server_interfaces()
In this loop, we step through the buffer and after each item we check
if the size_left is greater than the minimum size we need. However,
the problem is that "bytes_left" is type ssize_t while sizeof() is type
size_t. That means that because of type promotion, the comparison is
done as an unsigned and if we have negative bytes left the loop
continues instead of ending.
Fixes: fe856be475f7 ("CIFS: parse and store info on iface queries")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/smb2ops.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 83c898afc835..755f1c66b573 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -619,7 +619,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
goto out;
}
- while (bytes_left >= sizeof(*p)) {
+ while (bytes_left >= (ssize_t)sizeof(*p)) {
memset(&tmp_iface, 0, sizeof(tmp_iface));
tmp_iface.speed = le64_to_cpu(p->LinkSpeed);
tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0;
From 79520587fe42cd4988aff8695d60621e689109cb Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Fri, 9 Feb 2024 11:25:42 +0000
Subject: [PATCH 444/637] cifs: update the same create_guid on replay
File open requests made to the server contain a
CreateGuid, which is used by the server to identify
the open request. If the same request needs to be
replayed, it needs to be sent with the same CreateGuid
in the durable handle v2 context.
Without doing so, we could end up leaking handles on
the server when:
1. multichannel is used AND
2. connection goes down, but not for all channels
This is because the replayed open request would have a
new CreateGuid and the server will treat this as a new
request and open a new handle.
This change fixes this by reusing the existing create_guid
stored in the cached fid struct.
REF: MS-SMB2 4.9 Replay Create Request on an Alternate Channel
Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/cached_dir.c | 1 +
fs/smb/client/cifsglob.h | 1 +
fs/smb/client/smb2ops.c | 4 ++++
fs/smb/client/smb2pdu.c | 10 ++++++++--
4 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 1daeb5714faa..3de5047a7ff9 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -242,6 +242,7 @@ replay_again:
.desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES,
.disposition = FILE_OPEN,
.fid = pfid,
+ .replay = !!(retries),
};
rc = SMB2_open_init(tcon, server,
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index c86a72c9d9ec..53c75cfb33ab 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1378,6 +1378,7 @@ struct cifs_open_parms {
struct cifs_fid *fid;
umode_t mode;
bool reconnect:1;
+ bool replay:1; /* indicates that this open is for a replay */
};
struct cifs_fid {
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 755f1c66b573..6b3c384ead0d 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1204,6 +1204,7 @@ replay_again:
.disposition = FILE_OPEN,
.create_options = cifs_create_options(cifs_sb, 0),
.fid = &fid,
+ .replay = !!(retries),
};
rc = SMB2_open_init(tcon, server,
@@ -1569,6 +1570,7 @@ replay_again:
.disposition = FILE_OPEN,
.create_options = cifs_create_options(cifs_sb, create_options),
.fid = &fid,
+ .replay = !!(retries),
};
if (qi.flags & PASSTHRU_FSCTL) {
@@ -2295,6 +2297,7 @@ replay_again:
.disposition = FILE_OPEN,
.create_options = cifs_create_options(cifs_sb, 0),
.fid = fid,
+ .replay = !!(retries),
};
rc = SMB2_open_init(tcon, server,
@@ -2681,6 +2684,7 @@ replay_again:
.disposition = FILE_OPEN,
.create_options = cifs_create_options(cifs_sb, 0),
.fid = &fid,
+ .replay = !!(retries),
};
rc = SMB2_open_init(tcon, server,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 4085ce27fd38..608ee05491e2 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2404,8 +2404,13 @@ create_durable_v2_buf(struct cifs_open_parms *oparms)
*/
buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout);
buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
- generate_random_uuid(buf->dcontext.CreateGuid);
- memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+
+ /* for replay, we should not overwrite the existing create guid */
+ if (!oparms->replay) {
+ generate_random_uuid(buf->dcontext.CreateGuid);
+ memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
+ } else
+ memcpy(buf->dcontext.CreateGuid, pfid->create_guid, 16);
/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
buf->Name[0] = 'D';
@@ -3142,6 +3147,7 @@ replay_again:
/* reinitialize for possible replay */
flags = 0;
server = cifs_pick_channel(ses);
+ oparms->replay = !!(retries);
cifs_dbg(FYI, "create/open\n");
if (!ses || !server)
From 28083ff18d3f65ecd64857f4495623135dd1f132 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Wed, 7 Feb 2024 11:24:46 +0100
Subject: [PATCH 445/637] accel/ivpu: Fix DevTLB errors on suspend/resume and
recovery
Issue IP reset before shutdown in order to
complete all upstream requests to the SOC.
Without this DevTLB is complaining about
incomplete transactions and NPU cannot resume from
suspend.
This problem is only happening on recent IFWI
releases.
IP reset in rare corner cases can mess up PCI
configuration, so save it before the reset.
After this happens it is also impossible to
issue PLL requests and D0->D3->D0 cycle is needed
to recover the NPU. Add WP 0 request on power up,
so the PUNIT is always notified about NPU reset.
Use D0/D3 cycle for recovery as it can recover
from failed IP reset and FLR cannot.
Fixes: 3f7c0634926d ("accel/ivpu/37xx: Fix hangs related to MMIO reset")
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240207102446.3126981-1-jacek.lawrynowicz@linux.intel.com
---
drivers/accel/ivpu/ivpu_hw_37xx.c | 44 ++++++++++++++++++++++---------
drivers/accel/ivpu/ivpu_pm.c | 39 +++++++++++++++------------
2 files changed, 54 insertions(+), 29 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 77accd029c4a..89af1006df55 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -510,16 +510,6 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev)
return ret;
}
-static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev)
-{
- ivpu_boot_dpu_active_drive(vdev, false);
- ivpu_boot_pwr_island_isolation_drive(vdev, true);
- ivpu_boot_pwr_island_trickle_drive(vdev, false);
- ivpu_boot_pwr_island_drive(vdev, false);
-
- return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0);
-}
-
static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev)
{
u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES);
@@ -616,12 +606,37 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev)
return 0;
}
+static int ivpu_hw_37xx_ip_reset(struct ivpu_device *vdev)
+{
+ int ret;
+ u32 val;
+
+ if (IVPU_WA(punit_disabled))
+ return 0;
+
+ ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+ if (ret) {
+ ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n");
+ return ret;
+ }
+
+ val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET);
+ val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val);
+ REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val);
+
+ ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US);
+ if (ret)
+ ivpu_err(vdev, "Timed out waiting for RESET completion\n");
+
+ return ret;
+}
+
static int ivpu_hw_37xx_reset(struct ivpu_device *vdev)
{
int ret = 0;
- if (ivpu_boot_pwr_domain_disable(vdev)) {
- ivpu_err(vdev, "Failed to disable power domain\n");
+ if (ivpu_hw_37xx_ip_reset(vdev)) {
+ ivpu_err(vdev, "Failed to reset NPU\n");
ret = -EIO;
}
@@ -661,6 +676,11 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
{
int ret;
+ /* PLL requests may fail when powering down, so issue WP 0 here */
+ ret = ivpu_pll_disable(vdev);
+ if (ret)
+ ivpu_warn(vdev, "Failed to disable PLL: %d\n", ret);
+
ret = ivpu_hw_37xx_d0i3_disable(vdev);
if (ret)
ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index f501f27ebafd..5f73854234ba 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -58,11 +58,14 @@ static int ivpu_suspend(struct ivpu_device *vdev)
{
int ret;
+ /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+ pci_save_state(to_pci_dev(vdev->drm.dev));
+
ret = ivpu_shutdown(vdev);
- if (ret) {
+ if (ret)
ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
- return ret;
- }
+
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
return ret;
}
@@ -71,6 +74,9 @@ static int ivpu_resume(struct ivpu_device *vdev)
{
int ret;
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+ pci_restore_state(to_pci_dev(vdev->drm.dev));
+
retry:
ret = ivpu_hw_power_up(vdev);
if (ret) {
@@ -120,15 +126,20 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
ivpu_fw_log_dump(vdev);
-retry:
- ret = pci_try_reset_function(to_pci_dev(vdev->drm.dev));
- if (ret == -EAGAIN && !drm_dev_is_unplugged(&vdev->drm)) {
- cond_resched();
- goto retry;
- }
+ atomic_inc(&vdev->pm->reset_counter);
+ atomic_set(&vdev->pm->reset_pending, 1);
+ down_write(&vdev->pm->reset_lock);
- if (ret && ret != -EAGAIN)
- ivpu_err(vdev, "Failed to reset VPU: %d\n", ret);
+ ivpu_suspend(vdev);
+ ivpu_pm_prepare_cold_boot(vdev);
+ ivpu_jobs_abort_all(vdev);
+
+ ret = ivpu_resume(vdev);
+ if (ret)
+ ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+
+ up_write(&vdev->pm->reset_lock);
+ atomic_set(&vdev->pm->reset_pending, 0);
kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
pm_runtime_mark_last_busy(vdev->drm.dev);
@@ -200,9 +211,6 @@ int ivpu_pm_suspend_cb(struct device *dev)
ivpu_suspend(vdev);
ivpu_pm_prepare_warm_boot(vdev);
- pci_save_state(to_pci_dev(dev));
- pci_set_power_state(to_pci_dev(dev), PCI_D3hot);
-
ivpu_dbg(vdev, PM, "Suspend done.\n");
return 0;
@@ -216,9 +224,6 @@ int ivpu_pm_resume_cb(struct device *dev)
ivpu_dbg(vdev, PM, "Resume..\n");
- pci_set_power_state(to_pci_dev(dev), PCI_D0);
- pci_restore_state(to_pci_dev(dev));
-
ret = ivpu_resume(vdev);
if (ret)
ivpu_err(vdev, "Failed to resume: %d\n", ret);
From bc4cbc9d260ba8358ca63662919f4bb223cb603b Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:29 +0100
Subject: [PATCH 446/637] tools/rtla: Fix Makefile compiler options for clang
The following errors are showing up when compiling rtla with clang:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects
-fexceptions -fstack-protector-strong
-fasynchronous-unwind-tables -fstack-clash-protection -Wall
-Werror=format-security -Wp,-D_FORTIFY_SOURCE=2
-Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
$(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c
clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument]
warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option]
1 warning generated.
clang -o rtla -ggdb src/osnoise.o src/osnoise_hist.o src/osnoise_top.o
src/rtla.o src/timerlat_aa.o src/timerlat.o src/timerlat_hist.o
src/timerlat_top.o src/timerlat_u.o src/trace.o src/utils.o $(pkg-config --libs libtracefs)
src/osnoise.o: file not recognized: file format not recognized
clang: error: linker command failed with exit code 1 (use -v to see invocation)
make: *** [Makefile:110: rtla] Error 1
Solve these issues by:
- removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang
- informing the linker about -flto=auto
Link: https://lore.kernel.org/linux-trace-kernel/567ac1b94effc228ce9a0225b9df7232a9b35b55.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Fixes: 1a7b22ab15eb ("tools/rtla: Build with EXTRA_{C,LD}FLAGS")
Suggested-by: Donald Zickus <dzickus@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/Makefile | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index 2456a399eb9a..afd18c678ff5 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
-fasynchronous-unwind-tables -fstack-clash-protection
WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
+ifeq ($(CC),clang)
+ FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+ WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs)
CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS)
-LDFLAGS := -ggdb $(EXTRA_LDFLAGS)
+LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS)
LIBS := $$($(PKG_CONFIG) --libs libtracefs)
SRC := $(wildcard src/*.c)
From 64dc40f7523369912d7adb22c8cb655f71610505 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:30 +0100
Subject: [PATCH 447/637] tools/rtla: Fix uninitialized
bucket/data->bucket_size warning
When compiling rtla with clang, I am getting the following warnings:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
[..]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
-fstack-protector-strong -fasynchronous-unwind-tables
-fstack-clash-protection -Wall -Werror=format-security
-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
$(pkg-config --cflags libtracefs)
-c -o src/osnoise_hist.o src/osnoise_hist.c
src/osnoise_hist.c:138:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
138 | if (data->bucket_size)
| ^~~~~~~~~~~~~~~~~
src/osnoise_hist.c:149:6: note: uninitialized use occurs here
149 | if (bucket < entries)
| ^~~~~~
src/osnoise_hist.c:138:2: note: remove the 'if' if its condition is always true
138 | if (data->bucket_size)
| ^~~~~~~~~~~~~~~~~~~~~~
139 | bucket = duration / data->bucket_size;
src/osnoise_hist.c:132:12: note: initialize the variable 'bucket' to silence this warning
132 | int bucket;
| ^
| = 0
1 warning generated.
[...]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
-fstack-protector-strong -fasynchronous-unwind-tables
-fstack-clash-protection -Wall -Werror=format-security
-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
$(pkg-config --cflags libtracefs)
-c -o src/timerlat_hist.o src/timerlat_hist.c
src/timerlat_hist.c:181:6: warning: variable 'bucket' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
181 | if (data->bucket_size)
| ^~~~~~~~~~~~~~~~~
src/timerlat_hist.c:204:6: note: uninitialized use occurs here
204 | if (bucket < entries)
| ^~~~~~
src/timerlat_hist.c:181:2: note: remove the 'if' if its condition is always true
181 | if (data->bucket_size)
| ^~~~~~~~~~~~~~~~~~~~~~
182 | bucket = latency / data->bucket_size;
src/timerlat_hist.c:175:12: note: initialize the variable 'bucket' to silence this warning
175 | int bucket;
| ^
| = 0
1 warning generated.
This is a legit warning, but data->bucket_size is always > 0 (see
timerlat_hist_parse_args()), so the if is not necessary.
Remove the unneeded if (data->bucket_size) to avoid the warning.
Link: https://lkml.kernel.org/r/6e1b1665cd99042ae705b3e0fc410858c4c42346.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode")
Fixes: 829a6c0b5698 ("rtla/osnoise: Add the hist mode")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/src/osnoise_hist.c | 3 +--
tools/tracing/rtla/src/timerlat_hist.c | 3 +--
2 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 8f81fa007364..67128171c29d 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -135,8 +135,7 @@ static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
if (params->output_divisor)
duration = duration / params->output_divisor;
- if (data->bucket_size)
- bucket = duration / data->bucket_size;
+ bucket = duration / data->bucket_size;
total_duration = duration * count;
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 47d3d8b53cb2..3a5b8c409e7d 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -178,8 +178,7 @@ timerlat_hist_update(struct osnoise_tool *tool, int cpu,
if (params->output_divisor)
latency = latency / params->output_divisor;
- if (data->bucket_size)
- bucket = latency / data->bucket_size;
+ bucket = latency / data->bucket_size;
if (!context) {
hist = data->hist[cpu].irq;
From 30369084ac6e27479a347899e74f523e6ca29b89 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:31 +0100
Subject: [PATCH 448/637] tools/rtla: Fix clang warning about mount_point var
size
clang is reporting this warning:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
-fstack-protector-strong -fasynchronous-unwind-tables
-fstack-clash-protection -Wall -Werror=format-security
-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
$(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c
src/utils.c:548:66: warning: 'fscanf' may overflow; destination buffer in argument 3 has size 1024, but the corresponding specifier may require size 1025 [-Wfortify-source]
548 | while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n", mount_point, type) == 2) {
| ^
Increase mount_point variable size to MAX_PATH+1 to avoid the overflow.
Link: https://lkml.kernel.org/r/1b46712e93a2f4153909514a36016959dcc4021c.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: a957cbc02531 ("rtla: Add -C cgroup support")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/src/utils.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index c769d7b3842c..b998b24edf1e 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -536,7 +536,7 @@ int set_cpu_dma_latency(int32_t latency)
*/
static const int find_mount(const char *fs, char *mp, int sizeof_mp)
{
- char mount_point[MAX_PATH];
+ char mount_point[MAX_PATH+1];
char type[100];
int found = 0;
FILE *fp;
From 084ce16df0f060efd371092a09a7ae74a536dc11 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:32 +0100
Subject: [PATCH 449/637] tools/rtla: Remove unused sched_getattr() function
Clang is reporting:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions -fstack-protector-strong -fasynchronous-unwind-tables -fstack-clash-protection -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS $(pkg-config --cflags libtracefs) -c -o src/utils.o src/utils.c
src/utils.c:241:19: warning: unused function 'sched_getattr' [-Wunused-function]
241 | static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
| ^~~~~~~~~~~~~
1 warning generated.
Which is correct, so remove the unused function.
Link: https://lkml.kernel.org/r/eaed7ba122c4ae88ce71277c824ef41cbf789385.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: b1696371d865 ("rtla: Helper functions for rtla")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/src/utils.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index b998b24edf1e..5fcd6495ff05 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -238,12 +238,6 @@ static inline int sched_setattr(pid_t pid, const struct sched_attr *attr,
return syscall(__NR_sched_setattr, pid, attr, flags);
}
-static inline int sched_getattr(pid_t pid, struct sched_attr *attr,
- unsigned int size, unsigned int flags)
-{
- return syscall(__NR_sched_getattr, pid, attr, size, flags);
-}
-
int __set_sched_attr(int pid, struct sched_attr *attr)
{
int flags = 0;
From f9b2c87105c989a7b259c6da87673ada96dce2f8 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:33 +0100
Subject: [PATCH 450/637] tools/rv: Fix Makefile compiler options for clang
The following errors are showing up when compiling rv with clang:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
[...]
clang -O -g -DVERSION=\"6.8.0-rc1\" -flto=auto -ffat-lto-objects
-fexceptions -fstack-protector-strong -fasynchronous-unwind-tables
-fstack-clash-protection -Wall -Werror=format-security
-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
-Wno-maybe-uninitialized $(pkg-config --cflags libtracefs)
-I include -c -o src/utils.o src/utils.c
clang: warning: optimization flag '-ffat-lto-objects' is not supported [-Wignored-optimization-argument]
warning: unknown warning option '-Wno-maybe-uninitialized'; did you mean '-Wno-uninitialized'? [-Wunknown-warning-option]
1 warning generated.
clang -o rv -ggdb src/in_kernel.o src/rv.o src/trace.o src/utils.o $(pkg-config --libs libtracefs)
src/in_kernel.o: file not recognized: file format not recognized
clang: error: linker command failed with exit code 1 (use -v to see invocation)
make: *** [Makefile:110: rv] Error 1
Solve these issues by:
- removing -ffat-lto-objects and -Wno-maybe-uninitialized if using clang
- informing the linker about -flto=auto
Link: https://lkml.kernel.org/r/ed94a8ddc2ca8c8ef663cfb7ae9dd196c4a66b33.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Fixes: 4bc4b131d44c ("rv: Add rv tool")
Suggested-by: Donald Zickus <dzickus@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/verification/rv/Makefile | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 3d0f3888a58c..485f8aeddbe0 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -28,10 +28,15 @@ FOPTS := -flto=auto -ffat-lto-objects -fexceptions -fstack-protector-strong \
-fasynchronous-unwind-tables -fstack-clash-protection
WOPTS := -Wall -Werror=format-security -Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS -Wno-maybe-uninitialized
+ifeq ($(CC),clang)
+ FOPTS := $(filter-out -ffat-lto-objects, $(FOPTS))
+ WOPTS := $(filter-out -Wno-maybe-uninitialized, $(WOPTS))
+endif
+
TRACEFS_HEADERS := $$($(PKG_CONFIG) --cflags libtracefs)
CFLAGS := -O -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(MOPTS) $(WOPTS) $(TRACEFS_HEADERS) $(EXTRA_CFLAGS) -I include
-LDFLAGS := -ggdb $(EXTRA_LDFLAGS)
+LDFLAGS := -flto=auto -ggdb $(EXTRA_LDFLAGS)
LIBS := $$($(PKG_CONFIG) --libs libtracefs)
SRC := $(wildcard src/*.c)
From 61ec586bc0815959d3314cf7ce242529c977b357 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot@kernel.org>
Date: Tue, 6 Feb 2024 12:05:34 +0100
Subject: [PATCH 451/637] tools/rv: Fix curr_reactor uninitialized variable
clang is reporting:
$ make HOSTCC=clang CC=clang LLVM_IAS=1
clang -O -g -DVERSION=\"6.8.0-rc3\" -flto=auto -fexceptions
-fstack-protector-strong -fasynchronous-unwind-tables
-fstack-clash-protection -Wall -Werror=format-security
-Wp,-D_FORTIFY_SOURCE=2 -Wp,-D_GLIBCXX_ASSERTIONS
$(pkg-config --cflags libtracefs) -I include
-c -o src/in_kernel.o src/in_kernel.c
[...]
src/in_kernel.c:227:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
227 | if (!end)
| ^~~~
src/in_kernel.c:242:9: note: uninitialized use occurs here
242 | return curr_reactor;
| ^~~~~~~~~~~~
src/in_kernel.c:227:2: note: remove the 'if' if its condition is always false
227 | if (!end)
| ^~~~~~~~~
228 | goto out_free;
| ~~~~~~~~~~~~~
src/in_kernel.c:221:6: warning: variable 'curr_reactor' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
221 | if (!start)
| ^~~~~~
src/in_kernel.c:242:9: note: uninitialized use occurs here
242 | return curr_reactor;
| ^~~~~~~~~~~~
src/in_kernel.c:221:2: note: remove the 'if' if its condition is always false
221 | if (!start)
| ^~~~~~~~~~~
222 | goto out_free;
| ~~~~~~~~~~~~~
src/in_kernel.c:215:20: note: initialize the variable 'curr_reactor' to silence this warning
215 | char *curr_reactor;
| ^
| = NULL
2 warnings generated.
Which is correct. Setting curr_reactor to NULL avoids the problem.
Link: https://lkml.kernel.org/r/3a35551149e5ee0cb0950035afcb8082c3b5d05b.1707217097.git.bristot@kernel.org
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Donald Zickus <dzickus@redhat.com>
Fixes: 6d60f89691fc ("tools/rv: Add in-kernel monitor interface")
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/verification/rv/src/in_kernel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/verification/rv/src/in_kernel.c b/tools/verification/rv/src/in_kernel.c
index ad28582bcf2b..f04479ecc96c 100644
--- a/tools/verification/rv/src/in_kernel.c
+++ b/tools/verification/rv/src/in_kernel.c
@@ -210,9 +210,9 @@ static char *ikm_read_reactor(char *monitor_name)
static char *ikm_get_current_reactor(char *monitor_name)
{
char *reactors = ikm_read_reactor(monitor_name);
+ char *curr_reactor = NULL;
char *start;
char *end;
- char *curr_reactor;
if (!reactors)
return NULL;
From 962ac2dce56bb3aad1f82a4bbe3ada57a020287c Mon Sep 17 00:00:00 2001
From: Manasi Navare <navaremanasi@chromium.org>
Date: Mon, 5 Feb 2024 20:46:19 +0000
Subject: [PATCH 452/637] drm/i915/dsc: Fix the macro that calculates
DSCC_/DSCA_ PPS reg address
Commit bd077259d0a9 ("drm/i915/vdsc: Add function to read any PPS
register") defines a new macro to calculate the DSC PPS register
addresses with PPS number as an input. This macro correctly calculates
the addresses till PPS 11 since the addresses increment by 4. So in that
case the following macro works correctly to give correct register
address:
_MMIO(_DSCA_PPS_0 + (pps) * 4)
However after PPS 11, the register address for PPS 12 increments by 12
because of RC Buffer memory allocation in between. Because of this
discontinuity in the address space, the macro calculates wrong addresses
for PPS 12 - 16 resulting into incorrect DSC PPS parameter value
read/writes causing DSC corruption.
This fixes it by correcting this macro to add the offset of 12 for PPS
>=12.
v3: Add correct paranthesis for pps argument (Jani Nikula)
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10172
Fixes: bd077259d0a9 ("drm/i915/vdsc: Add function to read any PPS register")
Cc: Suraj Kandpal <suraj.kandpal@intel.com>
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Sean Paul <sean@poorly.run>
Cc: Drew Davenport <ddavenport@chromium.org>
Signed-off-by: Manasi Navare <navaremanasi@chromium.org>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240205204619.1991673-1-navaremanasi@chromium.org
(cherry picked from commit 6074be620c31dc2ae11af96a1a5ea95580976fb5)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/display/intel_vdsc_regs.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 64f440fdc22b..8b21dc8e26d5 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -51,8 +51,8 @@
#define DSCC_PICTURE_PARAMETER_SET_0 _MMIO(0x6BA00)
#define _DSCA_PPS_0 0x6B200
#define _DSCC_PPS_0 0x6BA00
-#define DSCA_PPS(pps) _MMIO(_DSCA_PPS_0 + (pps) * 4)
-#define DSCC_PPS(pps) _MMIO(_DSCC_PPS_0 + (pps) * 4)
+#define DSCA_PPS(pps) _MMIO(_DSCA_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
+#define DSCC_PPS(pps) _MMIO(_DSCC_PPS_0 + ((pps) < 12 ? (pps) : (pps) + 12) * 4)
#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB 0x78270
#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB 0x78370
#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC 0x78470
From ad26d56d080780bbfcc1696ca0c0cce3e2124ef6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 8 Feb 2024 17:45:52 +0200
Subject: [PATCH 453/637] drm/i915/dp: Limit SST link rate to <=8.1Gbps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Limit the link rate to HBR3 or below (<=8.1Gbps) in SST mode.
UHBR (10Gbps+) link rates require 128b/132b channel encoding
which we have not yet hooked up into the SST/no-sideband codepaths.
Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240208154552.14545-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 6061811d72e14f41f71b6a025510920b187bfcca)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
drivers/gpu/drm/i915/display/intel_dp.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f5ef95da5534..ae647d03af25 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2355,6 +2355,9 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
limits->min_rate = intel_dp_common_rate(intel_dp, 0);
limits->max_rate = intel_dp_max_link_rate(intel_dp);
+ /* FIXME 128b/132b SST support missing */
+ limits->max_rate = min(limits->max_rate, 810000);
+
limits->min_lane_count = 1;
limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
From 119ff04864a24470b1e531bb53e5c141aa8fefb0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Feb 2024 14:43:21 +0000
Subject: [PATCH 454/637] tcp: move tp->scaling_ratio to tcp_sock_read_txrx
group
tp->scaling_ratio is a read mostly field, used in rx and tx fast paths.
Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Wei Wang <weiwan@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/networking/net_cachelines/tcp_sock.rst | 2 +-
include/linux/tcp.h | 2 +-
net/ipv4/tcp.c | 3 ++-
3 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 97d7a5c8e01c..803912291479 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -38,7 +38,7 @@ u32 max_window read_mostly -
u32 mss_cache read_mostly read_mostly tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx)
u32 window_clamp read_mostly read_write tcp_rcv_space_adjust,__tcp_select_window
u32 rcv_ssthresh read_mostly - __tcp_select_window
-u82 scaling_ratio
+u8 scaling_ratio read_mostly read_mostly tcp_win_from_space
struct tcp_rack
u16 advmss - read_mostly tcp_rcv_space_adjust
u8 compressed_ack
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 89b290d8c8dc..168f5dca6609 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -221,6 +221,7 @@ struct tcp_sock {
u32 lost_out; /* Lost packets */
u32 sacked_out; /* SACK'd packets */
u16 tcp_header_len; /* Bytes of tcp header to send */
+ u8 scaling_ratio; /* see tcp_win_from_space() */
u8 chrono_type : 2, /* current chronograph type */
repair : 1,
is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
@@ -352,7 +353,6 @@ struct tcp_sock {
u32 compressed_ack_rcv_nxt;
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
- u8 scaling_ratio; /* see tcp_win_from_space() */
/* Information of the most recently (s)acked skb */
struct tcp_rack {
u64 mstamp; /* (Re)sent time of the skb */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7e2481b9eae1..c82dc42f57c6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void)
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
- CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio);
+ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32);
/* RX read-mostly hotpath cache lines */
CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
From 666a877deab2bcf8fd11c962d69e687e18168a6f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Feb 2024 14:43:22 +0000
Subject: [PATCH 455/637] tcp: move tp->tcp_usec_ts to tcp_sock_read_txrx group
tp->tcp_usec_ts is a read mostly field, used in rx and tx fast paths.
Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Wei Wang <weiwan@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/networking/net_cachelines/tcp_sock.rst | 2 +-
include/linux/tcp.h | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 803912291479..1c154cbd1848 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -44,7 +44,7 @@ u16 advmss - read_m
u8 compressed_ack
u8:2 dup_ack_counter
u8:1 tlp_retrans
-u8:1 tcp_usec_ts
+u8:1 tcp_usec_ts read_mostly read_mostly
u32 chrono_start read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
u32[3] chrono_stat read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
u8:2 chrono_type read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 168f5dca6609..a1c47a6d69b0 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -224,6 +224,7 @@ struct tcp_sock {
u8 scaling_ratio; /* see tcp_win_from_space() */
u8 chrono_type : 2, /* current chronograph type */
repair : 1,
+ tcp_usec_ts : 1, /* TSval values in usec */
is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
__cacheline_group_end(tcp_sock_read_txrx);
@@ -368,8 +369,7 @@ struct tcp_sock {
u8 compressed_ack;
u8 dup_ack_counter:2,
tlp_retrans:1, /* TLP is a retransmission */
- tcp_usec_ts:1, /* TSval values in usec */
- unused:4;
+ unused:5;
u8 thin_lto : 1,/* Use linear timeouts for thin streams */
recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
From c353c7b7ffb7ae6ed8f3339906fe33c8be6cf344 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Feb 2024 14:43:23 +0000
Subject: [PATCH 456/637] net-device: move lstats in net_device_read_txrx
dev->lstats is notably used from loopback ndo_start_xmit()
and other virtual drivers.
Per cpu stats updates are dirtying per-cpu data,
but the pointer itself is read-only.
Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Simon Horman <horms@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/networking/net_cachelines/net_device.rst | 4 ++--
include/linux/netdevice.h | 10 +++++-----
net/core/dev.c | 3 ++-
3 files changed, 9 insertions(+), 8 deletions(-)
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index e75a53593bb9..dceb49d56a91 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -136,8 +136,8 @@ struct_netpoll_info* npinfo -
possible_net_t nd_net - read_mostly (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish
void* ml_priv
enum_netdev_ml_priv_type ml_priv_type
-struct_pcpu_lstats__percpu* lstats
-struct_pcpu_sw_netstats__percpu* tstats
+struct_pcpu_lstats__percpu* lstats read_mostly dev_lstats_add()
+struct_pcpu_sw_netstats__percpu* tstats read_mostly dev_sw_netstats_tx_add()
struct_pcpu_dstats__percpu* dstats
struct_garp_port* garp_port
struct_mrp_port* mrp_port
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 118c40258d07..ef7bfbb98497 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2141,6 +2141,11 @@ struct net_device {
/* TXRX read-mostly hotpath */
__cacheline_group_begin(net_device_read_txrx);
+ union {
+ struct pcpu_lstats __percpu *lstats;
+ struct pcpu_sw_netstats __percpu *tstats;
+ struct pcpu_dstats __percpu *dstats;
+ };
unsigned int flags;
unsigned short hard_header_len;
netdev_features_t features;
@@ -2395,11 +2400,6 @@ struct net_device {
enum netdev_ml_priv_type ml_priv_type;
enum netdev_stat_type pcpu_stat_type:8;
- union {
- struct pcpu_lstats __percpu *lstats;
- struct pcpu_sw_netstats __percpu *tstats;
- struct pcpu_dstats __percpu *dstats;
- };
#if IS_ENABLED(CONFIG_GARP)
struct garp_port __rcu *garp_port;
diff --git a/net/core/dev.c b/net/core/dev.c
index cb2dab0feee0..9bb792cecc16 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11652,11 +11652,12 @@ static void __init net_dev_struct_check(void)
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
/* TXRX read-mostly hotpath */
+ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
- CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+ CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
/* RX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
From 14f08c976ffe0d2117c6199c32663df1cbc45c65 Mon Sep 17 00:00:00 2001
From: limingming3 <limingming890315@gmail.com>
Date: Wed, 7 Feb 2024 14:51:42 +0800
Subject: [PATCH 457/637] tools/rtla: Replace setting prio with nice for
SCHED_OTHER
Since the sched_priority for SCHED_OTHER is always 0, it makes no
sence to set it.
Setting nice for SCHED_OTHER seems more meaningful.
Link: https://lkml.kernel.org/r/20240207065142.1753909-1-limingming3@lixiang.com
Cc: stable@vger.kernel.org
Fixes: b1696371d865 ("rtla: Helper functions for rtla")
Signed-off-by: limingming3 <limingming3@lixiang.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/src/utils.c | 6 +++---
tools/tracing/rtla/src/utils.h | 2 ++
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
index 5fcd6495ff05..9ac71a66840c 100644
--- a/tools/tracing/rtla/src/utils.c
+++ b/tools/tracing/rtla/src/utils.c
@@ -473,13 +473,13 @@ int parse_prio(char *arg, struct sched_attr *sched_param)
if (prio == INVALID_VAL)
return -1;
- if (prio < sched_get_priority_min(SCHED_OTHER))
+ if (prio < MIN_NICE)
return -1;
- if (prio > sched_get_priority_max(SCHED_OTHER))
+ if (prio > MAX_NICE)
return -1;
sched_param->sched_policy = SCHED_OTHER;
- sched_param->sched_priority = prio;
+ sched_param->sched_nice = prio;
break;
default:
return -1;
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
index 04ed1e650495..d44513e6c66a 100644
--- a/tools/tracing/rtla/src/utils.h
+++ b/tools/tracing/rtla/src/utils.h
@@ -9,6 +9,8 @@
*/
#define BUFF_U64_STR_SIZE 24
#define MAX_PATH 1024
+#define MAX_NICE 20
+#define MIN_NICE -19
#define container_of(ptr, type, member)({ \
const typeof(((type *)0)->member) *__mptr = (ptr); \
From b5f319360371087d52070d8f3fc7789e80ce69a6 Mon Sep 17 00:00:00 2001
From: John Kacur <jkacur@redhat.com>
Date: Fri, 2 Feb 2024 19:16:07 -0500
Subject: [PATCH 458/637] tools/rtla: Exit with EXIT_SUCCESS when help is
invoked
Fix rtla so that the following commands exit with 0 when help is invoked
rtla osnoise top -h
rtla osnoise hist -h
rtla timerlat top -h
rtla timerlat hist -h
Link: https://lore.kernel.org/linux-trace-devel/20240203001607.69703-1-jkacur@redhat.com
Cc: stable@vger.kernel.org
Fixes: 1eeb6328e8b3 ("rtla/timerlat: Add timerlat hist mode")
Signed-off-by: John Kacur <jkacur@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
tools/tracing/rtla/src/osnoise_hist.c | 6 +++++-
tools/tracing/rtla/src/osnoise_top.c | 6 +++++-
tools/tracing/rtla/src/timerlat_hist.c | 6 +++++-
tools/tracing/rtla/src/timerlat_top.c | 6 +++++-
4 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 67128171c29d..01870d50942a 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -479,7 +479,11 @@ static void osnoise_hist_usage(char *usage)
for (i = 0; msg[i]; i++)
fprintf(stderr, "%s\n", msg[i]);
- exit(1);
+
+ if (usage)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
}
/*
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index f7c959be8677..457360db0767 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -331,7 +331,11 @@ static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
for (i = 0; msg[i]; i++)
fprintf(stderr, "%s\n", msg[i]);
- exit(1);
+
+ if (usage)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
}
/*
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 3a5b8c409e7d..dbf154082f95 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -545,7 +545,11 @@ static void timerlat_hist_usage(char *usage)
for (i = 0; msg[i]; i++)
fprintf(stderr, "%s\n", msg[i]);
- exit(1);
+
+ if (usage)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
}
/*
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 1640f121baca..3e9af2c38688 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -375,7 +375,11 @@ static void timerlat_top_usage(char *usage)
for (i = 0; msg[i]; i++)
fprintf(stderr, "%s\n", msg[i]);
- exit(1);
+
+ if (usage)
+ exit(EXIT_FAILURE);
+
+ exit(EXIT_SUCCESS);
}
/*
From bdd70eb68913c960acb895b00a8c62eb64715b1f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 8 Feb 2024 19:03:49 +0100
Subject: [PATCH 459/637] mptcp: drop the push_pending field
Such field is there to avoid acquiring the data lock in a few spots,
but it adds complexity to the already non trivial locking schema.
All the relevant call sites (mptcp-level re-injection, set socket
options), are slow-path, drop such field in favor of 'cb_flags', adding
the relevant locking.
This patch could be seen as an improvement, instead of a fix. But it
simplifies the next patch. The 'Fixes' tag has been added to help having
this series backported to stable.
Fixes: e9d09baca676 ("mptcp: avoid atomic bit manipulation when possible")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/protocol.c | 12 ++++++------
net/mptcp/protocol.h | 1 -
2 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 028e8b473626..2111819016af 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1505,8 +1505,11 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
void mptcp_check_and_set_pending(struct sock *sk)
{
- if (mptcp_send_head(sk))
- mptcp_sk(sk)->push_pending |= BIT(MPTCP_PUSH_PENDING);
+ if (mptcp_send_head(sk)) {
+ mptcp_data_lock(sk);
+ mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING);
+ mptcp_data_unlock(sk);
+ }
}
static int __subflow_push_pending(struct sock *sk, struct sock *ssk,
@@ -3142,7 +3145,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
WRITE_ONCE(msk->flags, 0);
msk->cb_flags = 0;
- msk->push_pending = 0;
msk->recovery = false;
msk->can_ack = false;
msk->fully_established = false;
@@ -3330,8 +3332,7 @@ static void mptcp_release_cb(struct sock *sk)
struct mptcp_sock *msk = mptcp_sk(sk);
for (;;) {
- unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
- msk->push_pending;
+ unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED);
struct list_head join_list;
if (!flags)
@@ -3347,7 +3348,6 @@ static void mptcp_release_cb(struct sock *sk)
* datapath acquires the msk socket spinlock while helding
* the subflow socket lock
*/
- msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3517f2d24a22..b905f1868298 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -286,7 +286,6 @@ struct mptcp_sock {
int rmem_released;
unsigned long flags;
unsigned long cb_flags;
- unsigned long push_pending;
bool recovery; /* closing subflow write queue reinjected */
bool can_ack;
bool fully_established;
From 013e3179dbd2bc756ce1dd90354abac62f65b739 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 8 Feb 2024 19:03:50 +0100
Subject: [PATCH 460/637] mptcp: fix rcv space initialization
mptcp_rcv_space_init() is supposed to happen under the msk socket
lock, but active msk socket does that without such protection.
Leverage the existing mptcp_propagate_state() helper to that extent.
We need to ensure mptcp_rcv_space_init will happen before
mptcp_rcv_space_adjust(), and the release_cb does not assure that:
explicitly check for such condition.
While at it, move the wnd_end initialization out of mptcp_rcv_space_init(),
it never belonged there.
Note that the race does not produce ill effect in practice, but
change allows cleaning-up and defying better the locking model.
Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/protocol.c | 10 ++++++----
net/mptcp/protocol.h | 3 ++-
net/mptcp/subflow.c | 4 ++--
3 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 2111819016af..7632eafb683b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1963,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (copied <= 0)
return;
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, msk->first);
+
msk->rcvq_space.copied += copied;
mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC);
@@ -3160,6 +3163,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
msk->bytes_received = 0;
msk->bytes_sent = 0;
msk->bytes_retrans = 0;
+ msk->rcvspace_init = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3247,6 +3251,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
{
const struct tcp_sock *tp = tcp_sk(ssk);
+ msk->rcvspace_init = 1;
msk->rcvq_space.copied = 0;
msk->rcvq_space.rtt_us = 0;
@@ -3257,8 +3262,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
-
- WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
@@ -3478,10 +3481,9 @@ void mptcp_finish_connect(struct sock *ssk)
WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
WRITE_ONCE(msk->snd_nxt, msk->write_seq);
WRITE_ONCE(msk->snd_una, msk->write_seq);
+ WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
mptcp_pm_new_connection(msk, ssk, 0);
-
- mptcp_rcv_space_init(msk, ssk);
}
void mptcp_sock_graft(struct sock *sk, struct socket *parent)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b905f1868298..9f5ee82e3473 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -304,7 +304,8 @@ struct mptcp_sock {
nodelay:1,
fastopening:1,
in_accept_queue:1,
- free_first:1;
+ free_first:1,
+ rcvspace_init:1;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0dcb721c89d1..56b2ac2f2f22 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state)
struct mptcp_sock *msk = mptcp_sk(sk);
__mptcp_propagate_sndbuf(sk, msk->first);
+ if (!msk->rcvspace_init)
+ mptcp_rcv_space_init(msk, msk->first);
if (sk->sk_state == TCP_SYN_SENT) {
mptcp_set_state(sk, state);
sk->sk_state_change(sk);
@@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
}
} else if (mptcp_check_fallback(sk)) {
fallback:
- mptcp_rcv_space_init(msk, sk);
mptcp_propagate_state(parent, sk);
}
return;
@@ -1744,7 +1745,6 @@ static void subflow_state_change(struct sock *sk)
msk = mptcp_sk(parent);
if (subflow_simultaneous_connect(sk)) {
mptcp_do_fallback(sk);
- mptcp_rcv_space_init(msk, sk);
pr_fallback(msk);
subflow->conn_finished = 1;
mptcp_propagate_state(parent, sk);
From 3f83d8a77eeeb47011b990fd766a421ee64f1d73 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 8 Feb 2024 19:03:51 +0100
Subject: [PATCH 461/637] mptcp: fix more tx path fields initialization
The 'msk->write_seq' and 'msk->snd_nxt' are always updated under
the msk socket lock, except at MPC handshake completiont time.
Builds-up on the previous commit to move such init under the relevant
lock.
There are no known problems caused by the potential race, the
primary goal is consistency.
Fixes: 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packets")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/protocol.c | 6 ++----
net/mptcp/subflow.c | 13 +++++++++++--
2 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7632eafb683b..8cb6a873dae9 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3478,10 +3478,8 @@ void mptcp_finish_connect(struct sock *ssk)
* accessing the field below
*/
WRITE_ONCE(msk->local_key, subflow->local_key);
- WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
- WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- WRITE_ONCE(msk->snd_una, msk->write_seq);
- WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
+ WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+ WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
mptcp_pm_new_connection(msk, ssk, 0);
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 56b2ac2f2f22..c2df34ebcf28 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -421,12 +421,21 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
void __mptcp_sync_state(struct sock *sk, int state)
{
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sock *ssk = msk->first;
- __mptcp_propagate_sndbuf(sk, msk->first);
+ subflow = mptcp_subflow_ctx(ssk);
+ __mptcp_propagate_sndbuf(sk, ssk);
if (!msk->rcvspace_init)
- mptcp_rcv_space_init(msk, msk->first);
+ mptcp_rcv_space_init(msk, ssk);
+
if (sk->sk_state == TCP_SYN_SENT) {
+ /* subflow->idsn is always available is TCP_SYN_SENT state,
+ * even for the FASTOPEN scenarios
+ */
+ WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
mptcp_set_state(sk, state);
sk->sk_state_change(sk);
}
From e4a0fa47e816e186f6b4c0055d07eeec42d11871 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 8 Feb 2024 19:03:52 +0100
Subject: [PATCH 462/637] mptcp: corner case locking for rx path fields
initialization
Most MPTCP-level related fields are under the mptcp data lock
protection, but are written one-off without such lock at MPC
complete time, both for the client and the server
Leverage the mptcp_propagate_state() infrastructure to move such
initialization under the proper lock client-wise.
The server side critical init steps are done by
mptcp_subflow_fully_established(): ensure the caller properly held the
relevant lock, and avoid acquiring the same lock in the nested scopes.
There are no real potential races, as write access to such fields
is implicitly serialized by the MPTCP state machine; the primary
goal is consistency.
Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/fastopen.c | 6 ++---
net/mptcp/options.c | 9 +++----
net/mptcp/protocol.c | 9 ++++---
net/mptcp/protocol.h | 9 +++----
net/mptcp/subflow.c | 56 +++++++++++++++++++++++++-------------------
5 files changed, 50 insertions(+), 39 deletions(-)
diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 74698582a285..ad28da655f8b 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
mptcp_data_unlock(sk);
}
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
struct sock *sk = (struct sock *)msk;
struct sk_buff *skb;
- mptcp_data_lock(sk);
skb = skb_peek_tail(&sk->sk_receive_queue);
if (skb) {
WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
@@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_
}
pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
- mptcp_data_unlock(sk);
}
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index d2527d189a79..e3e96a49f922 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
- subflow->fully_established = 1;
- WRITE_ONCE(msk->fully_established, true);
- goto check_notify;
+ goto set_fully_established;
}
/* If the first established packet does not contain MP_CAPABLE + data
@@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
set_fully_established:
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
- mptcp_subflow_fully_established(subflow, mp_opt);
+
+ mptcp_data_lock((struct sock *)msk);
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
+ mptcp_data_unlock((struct sock *)msk);
check_notify:
/* if the subflow is not already linked into the conn_list, we can't
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 8cb6a873dae9..8ef2927ebca2 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3186,6 +3186,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC);
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
if (!nsk)
@@ -3226,7 +3227,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
/* The msk maintain a ref to each subflow in the connections list */
WRITE_ONCE(msk->first, ssk);
- list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list);
+ subflow = mptcp_subflow_ctx(ssk);
+ list_add(&subflow->node, &msk->conn_list);
sock_hold(ssk);
/* new mpc subflow takes ownership of the newly
@@ -3241,6 +3243,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
__mptcp_propagate_sndbuf(nsk, ssk);
mptcp_rcv_space_init(msk, ssk);
+
+ if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK)
+ __mptcp_subflow_fully_established(msk, subflow, mp_opt);
bh_unlock_sock(nsk);
/* note: the newly allocated socket refcount is 2 now */
@@ -3478,8 +3483,6 @@ void mptcp_finish_connect(struct sock *ssk)
* accessing the field below
*/
WRITE_ONCE(msk->local_key, subflow->local_key);
- WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
- WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
mptcp_pm_new_connection(msk, ssk, 0);
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 9f5ee82e3473..fefcbf585411 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
unsigned int mptcp_close_timeout(const struct sock *sk);
int mptcp_get_pm_type(const struct net *net);
const char *mptcp_get_scheduler(const struct net *net);
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt);
bool __mptcp_retransmit_pending_data(struct sock *sk);
void mptcp_check_and_set_pending(struct sock *sk);
void __mptcp_push_pending(struct sock *sk, unsigned int flags);
@@ -952,8 +953,8 @@ void mptcp_event_pm_listener(const struct sock *ssk,
enum mptcp_event_type event);
bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
-void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt);
+void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt);
void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
struct request_sock *req);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c2df34ebcf28..c34ecadee120 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -441,20 +441,6 @@ void __mptcp_sync_state(struct sock *sk, int state)
}
}
-static void mptcp_propagate_state(struct sock *sk, struct sock *ssk)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- mptcp_data_lock(sk);
- if (!sock_owned_by_user(sk)) {
- __mptcp_sync_state(sk, ssk->sk_state);
- } else {
- msk->pending_state = ssk->sk_state;
- __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
- }
- mptcp_data_unlock(sk);
-}
-
static void subflow_set_remote_key(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow,
const struct mptcp_options_received *mp_opt)
@@ -476,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
}
+static void mptcp_propagate_state(struct sock *sk, struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ mptcp_data_lock(sk);
+ if (mp_opt) {
+ /* Options are available only in the non fallback cases
+ * avoid updating rx path fields otherwise
+ */
+ WRITE_ONCE(msk->snd_una, subflow->idsn + 1);
+ WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd);
+ subflow_set_remote_key(msk, subflow, mp_opt);
+ }
+
+ if (!sock_owned_by_user(sk)) {
+ __mptcp_sync_state(sk, ssk->sk_state);
+ } else {
+ msk->pending_state = ssk->sk_state;
+ __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags);
+ }
+ mptcp_data_unlock(sk);
+}
+
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -510,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
if (mp_opt.deny_join_id0)
WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
- subflow_set_remote_key(msk, subflow, &mp_opt);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, &mp_opt);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
@@ -556,7 +566,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
}
} else if (mptcp_check_fallback(sk)) {
fallback:
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
return;
@@ -741,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk)
kfree_rcu(ctx, rcu);
}
-void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
- const struct mptcp_options_received *mp_opt)
+void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow,
+ const struct mptcp_options_received *mp_opt)
{
- struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
subflow_set_remote_key(msk, subflow, mp_opt);
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
if (subflow->is_mptfo)
- mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
+ __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
}
static struct sock *subflow_syn_recv_sock(const struct sock *sk,
@@ -844,7 +853,6 @@ create_child:
* mpc option
*/
if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
- mptcp_subflow_fully_established(ctx, &mp_opt);
mptcp_pm_fully_established(owner, child);
ctx->pm_notified = 1;
}
@@ -1756,7 +1764,7 @@ static void subflow_state_change(struct sock *sk)
mptcp_do_fallback(sk);
pr_fallback(msk);
subflow->conn_finished = 1;
- mptcp_propagate_state(parent, sk);
+ mptcp_propagate_state(parent, sk, subflow, NULL);
}
/* as recvmsg() does not acquire the subflow socket for ssk selection
From f012d796a6de662692159c539689e47e662853a8 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang@kernel.org>
Date: Thu, 8 Feb 2024 19:03:53 +0100
Subject: [PATCH 463/637] mptcp: check addrs list in userspace_pm_get_local_id
Before adding a new entry in mptcp_userspace_pm_get_local_id(), it's
better to check whether this address is already in userspace pm local
address list. If it's in the list, no need to add a new entry, just
return it's address ID and use this address.
Fixes: 8b20137012d9 ("mptcp: read attributes of addr entries managed by userspace PMs")
Cc: stable@vger.kernel.org
Signed-off-by: Geliang Tang <geliang.tang@linux.dev>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/pm_userspace.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index efecbe3cf415..4f3901d5b8ef 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -130,10 +130,21 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
struct mptcp_addr_info *skc)
{
- struct mptcp_pm_addr_entry new_entry;
+ struct mptcp_pm_addr_entry *entry = NULL, *e, new_entry;
__be16 msk_sport = ((struct inet_sock *)
inet_sk((struct sock *)msk))->inet_sport;
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&e->addr, skc, false)) {
+ entry = e;
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+ if (entry)
+ return entry->addr.id;
+
memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
new_entry.addr = *skc;
new_entry.addr.id = 0;
From 337cebbd850f94147cee05252778f8f78b8c337f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 8 Feb 2024 19:03:54 +0100
Subject: [PATCH 464/637] mptcp: really cope with fastopen race
Fastopen and PM-trigger subflow shutdown can race, as reported by
syzkaller.
In my first attempt to close such race, I missed the fact that
the subflow status can change again before the subflow_state_change
callback is invoked.
Address the issue additionally copying with all the states directly
reachable from TCP_FIN_WAIT1.
Fixes: 1e777f39b4d7 ("mptcp: add MSG_FASTOPEN sendmsg flag support")
Fixes: 4fd19a307016 ("mptcp: fix inconsistent state on fastopen race")
Cc: stable@vger.kernel.org
Reported-by: syzbot+c53d4d3ddb327e80bc51@syzkaller.appspotmail.com
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/458
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mptcp/protocol.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fefcbf585411..ed50f2015dc3 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1129,7 +1129,8 @@ static inline bool subflow_simultaneous_connect(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
- return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) &&
+ return (1 << sk->sk_state) &
+ (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING) &&
is_active_ssk(subflow) &&
!subflow->conn_finished;
}
From 68990d006d42b6ef7910fa263f87e9e0d812113b Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang@kernel.org>
Date: Thu, 8 Feb 2024 19:03:55 +0100
Subject: [PATCH 465/637] MAINTAINERS: update Geliang's email address
Update my email-address in MAINTAINERS and .mailmap entries to my
kernel.org account.
Suggested-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.mailmap | 9 +++++----
MAINTAINERS | 2 +-
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/.mailmap b/.mailmap
index 04998f7bda81..327e7eddd146 100644
--- a/.mailmap
+++ b/.mailmap
@@ -191,10 +191,11 @@ Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
-Geliang Tang <geliang.tang@linux.dev> <geliang.tang@suse.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@xiaomi.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@gmail.com>
-Geliang Tang <geliang.tang@linux.dev> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <geliang.tang@linux.dev>
+Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
+Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 3dfe7ea25320..aa9776031121 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15324,7 +15324,7 @@ K: \bmdo_
NETWORKING [MPTCP]
M: Matthieu Baerts <matttbe@kernel.org>
M: Mat Martineau <martineau@kernel.org>
-R: Geliang Tang <geliang.tang@linux.dev>
+R: Geliang Tang <geliang@kernel.org>
L: netdev@vger.kernel.org
L: mptcp@lists.linux.dev
S: Maintained
From 9a0c32d698c1d0c4a6f5642ac017da31febad1eb Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@redhat.com>
Date: Fri, 2 Feb 2024 01:05:50 +0100
Subject: [PATCH 466/637] drm/nouveau: don't fini scheduler if not initialized
nouveau_abi16_ioctl_channel_alloc() and nouveau_cli_init() simply call
their corresponding *_fini() counterpart. This can lead to
nouveau_sched_fini() being called without struct nouveau_sched ever
being initialized in the first place.
Instead of embedding struct nouveau_sched into struct nouveau_cli and
struct nouveau_chan_abi16, allocate struct nouveau_sched separately,
such that we can check for the corresponding pointer to be NULL in the
particular *_fini() functions.
It makes sense to allocate struct nouveau_sched separately anyway, since
in a subsequent commit we can also avoid to allocate a struct
nouveau_sched in nouveau_abi16_ioctl_channel_alloc() at all, if the
VM_BIND uAPI has been disabled due to the legacy uAPI being used.
Fixes: 5f03a507b29e ("drm/nouveau: implement 1:1 scheduler - entity relationship")
Reported-by: Timur Tabi <ttabi@nvidia.com>
Tested-by: Timur Tabi <ttabi@nvidia.com>
Closes: https://lore.kernel.org/nouveau/20240131213917.1545604-1-ttabi@nvidia.com/
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202000606.3526-1-dakr@redhat.com
---
drivers/gpu/drm/nouveau/nouveau_abi16.c | 10 ++++---
drivers/gpu/drm/nouveau/nouveau_abi16.h | 2 +-
drivers/gpu/drm/nouveau/nouveau_drm.c | 7 +++--
drivers/gpu/drm/nouveau/nouveau_drv.h | 2 +-
drivers/gpu/drm/nouveau/nouveau_exec.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_sched.c | 38 +++++++++++++++++++++++--
drivers/gpu/drm/nouveau/nouveau_sched.h | 6 ++--
drivers/gpu/drm/nouveau/nouveau_uvmm.c | 2 +-
8 files changed, 53 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390..ca4b5ab3e59e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
struct nouveau_abi16_ntfy *ntfy, *temp;
/* Cancel all jobs from the entity's queue. */
- drm_sched_entity_fini(&chan->sched.entity);
+ if (chan->sched)
+ drm_sched_entity_fini(&chan->sched->entity);
if (chan->chan)
nouveau_channel_idle(chan->chan);
- nouveau_sched_fini(&chan->sched);
+ if (chan->sched)
+ nouveau_sched_destroy(&chan->sched);
/* cleanup notifier state */
list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -337,8 +339,8 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
if (ret)
goto done;
- ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
- chan->chan->dma.ib_max);
+ ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+ chan->chan->dma.ib_max);
if (ret)
goto done;
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c75..11c8c4a80079 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -26,7 +26,7 @@ struct nouveau_abi16_chan {
struct nouveau_bo *ntfy;
struct nouveau_vma *ntfy_vma;
struct nvkm_mm heap;
- struct nouveau_sched sched;
+ struct nouveau_sched *sched;
};
struct nouveau_abi16 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6f6c31a9937b..a947e1d5f309 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
WARN_ON(!list_empty(&cli->worker));
usif_client_fini(cli);
- nouveau_sched_fini(&cli->sched);
+ if (cli->sched)
+ nouveau_sched_destroy(&cli->sched);
if (uvmm)
nouveau_uvmm_fini(uvmm);
nouveau_vmm_fini(&cli->svm);
@@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
cli->mem = &mems[ret];
/* Don't pass in the (shared) sched_wq in order to let
- * nouveau_sched_init() create a dedicated one for VM_BIND jobs.
+ * nouveau_sched_create() create a dedicated one for VM_BIND jobs.
*
* This is required to ensure that for VM_BIND jobs free_job() work and
* run_job() work can always run concurrently and hence, free_job() work
@@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
* locks which indirectly or directly are held for allocations
* elsewhere.
*/
- ret = nouveau_sched_init(&cli->sched, drm, NULL, 1);
+ ret = nouveau_sched_create(&cli->sched, drm, NULL, 1);
if (ret)
goto done;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8a6d94c8b163..e239c6bf4afa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -98,7 +98,7 @@ struct nouveau_cli {
bool disabled;
} uvmm;
- struct nouveau_sched sched;
+ struct nouveau_sched *sched;
const struct nvif_mclass *mem;
diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index bc5d71b79ab2..e65c0ef23bc7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
if (ret)
goto out;
- args.sched = &chan16->sched;
+ args.sched = chan16->sched;
args.file_priv = file_priv;
args.chan = chan;
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9c..32fa2e273965 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = {
.free_job = nouveau_sched_free_job,
};
-int
+static int
nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
struct workqueue_struct *wq, u32 credit_limit)
{
@@ -453,7 +453,30 @@ fail_wq:
return ret;
}
-void
+int
+nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+ struct workqueue_struct *wq, u32 credit_limit)
+{
+ struct nouveau_sched *sched;
+ int ret;
+
+ sched = kzalloc(sizeof(*sched), GFP_KERNEL);
+ if (!sched)
+ return -ENOMEM;
+
+ ret = nouveau_sched_init(sched, drm, wq, credit_limit);
+ if (ret) {
+ kfree(sched);
+ return ret;
+ }
+
+ *psched = sched;
+
+ return 0;
+}
+
+
+static void
nouveau_sched_fini(struct nouveau_sched *sched)
{
struct drm_gpu_scheduler *drm_sched = &sched->base;
@@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched)
if (sched->wq)
destroy_workqueue(sched->wq);
}
+
+void
+nouveau_sched_destroy(struct nouveau_sched **psched)
+{
+ struct nouveau_sched *sched = *psched;
+
+ nouveau_sched_fini(sched);
+ kfree(sched);
+
+ *psched = NULL;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index a6528f5981e6..e1f01a23e6f6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -111,8 +111,8 @@ struct nouveau_sched {
} job;
};
-int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
- struct workqueue_struct *wq, u32 credit_limit);
-void nouveau_sched_fini(struct nouveau_sched *sched);
+int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+ struct workqueue_struct *wq, u32 credit_limit);
+void nouveau_sched_destroy(struct nouveau_sched **psched);
#endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 4f223c972c6a..0a0a11dc9ec0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
if (ret)
return ret;
- args.sched = &cli->sched;
+ args.sched = cli->sched;
args.file_priv = file_priv;
ret = nouveau_uvmm_vm_bind(&args);
From a1d8700d906444167899e5a3c64a11ba50c0badd Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@redhat.com>
Date: Fri, 2 Feb 2024 01:05:51 +0100
Subject: [PATCH 467/637] drm/nouveau: omit to create schedulers using the
legacy uAPI
Omit to create scheduler instances when using the legacy uAPI. When
using the legacy NOUVEAU_GEM_PUSHBUF ioctl no scheduler instance is
required, hence omit creating scheduler instances in
nouveau_abi16_ioctl_channel_alloc().
Tested-by: Timur Tabi <ttabi@nvidia.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202000606.3526-2-dakr@redhat.com
---
drivers/gpu/drm/nouveau/nouveau_abi16.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index ca4b5ab3e59e..d1bb8151a1df 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -339,10 +339,16 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
if (ret)
goto done;
- ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
- chan->chan->dma.ib_max);
- if (ret)
- goto done;
+ /* If we're not using the VM_BIND uAPI, we don't need a scheduler.
+ *
+ * The client lock is already acquired by nouveau_abi16_get().
+ */
+ if (nouveau_cli_uvmm(cli)) {
+ ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+ chan->chan->dma.ib_max);
+ if (ret)
+ goto done;
+ }
init->channel = chan->chan->chid;
From 5b3fbd61b9d1f4ed2db95aaf03f9adae0373784d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 9 Feb 2024 01:55:18 -0800
Subject: [PATCH 468/637] net: sysfs: Fix /sys/class/net/<iface> path for
statistics
The Documentation/ABI/testing/sysfs-class-net-statistics documentation
is pointing to the wrong path for the interface. Documentation is
pointing to /sys/class/<iface>, instead of /sys/class/net/<iface>.
Fix it by adding the `net/` directory before the interface.
Fixes: 6044f9700645 ("net: sysfs: document /sys/class/net/statistics/*")
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../ABI/testing/sysfs-class-net-statistics | 48 +++++++++----------
1 file changed, 24 insertions(+), 24 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics
index 55db27815361..53e508c6936a 100644
--- a/Documentation/ABI/testing/sysfs-class-net-statistics
+++ b/Documentation/ABI/testing/sysfs-class-net-statistics
@@ -1,4 +1,4 @@
-What: /sys/class/<iface>/statistics/collisions
+What: /sys/class/net/<iface>/statistics/collisions
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -6,7 +6,7 @@ Description:
Indicates the number of collisions seen by this network device.
This value might not be relevant with all MAC layers.
-What: /sys/class/<iface>/statistics/multicast
+What: /sys/class/net/<iface>/statistics/multicast
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -14,7 +14,7 @@ Description:
Indicates the number of multicast packets received by this
network device.
-What: /sys/class/<iface>/statistics/rx_bytes
+What: /sys/class/net/<iface>/statistics/rx_bytes
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -23,7 +23,7 @@ Description:
See the network driver for the exact meaning of when this
value is incremented.
-What: /sys/class/<iface>/statistics/rx_compressed
+What: /sys/class/net/<iface>/statistics/rx_compressed
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
network device. This value might only be relevant for interfaces
that support packet compression (e.g: PPP).
-What: /sys/class/<iface>/statistics/rx_crc_errors
+What: /sys/class/net/<iface>/statistics/rx_crc_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -41,7 +41,7 @@ Description:
by this network device. Note that the specific meaning might
depend on the MAC layer used by the interface.
-What: /sys/class/<iface>/statistics/rx_dropped
+What: /sys/class/net/<iface>/statistics/rx_dropped
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -51,7 +51,7 @@ Description:
packet processing. See the network driver for the exact
meaning of this value.
-What: /sys/class/<iface>/statistics/rx_errors
+What: /sys/class/net/<iface>/statistics/rx_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -59,7 +59,7 @@ Description:
Indicates the number of receive errors on this network device.
See the network driver for the exact meaning of this value.
-What: /sys/class/<iface>/statistics/rx_fifo_errors
+What: /sys/class/net/<iface>/statistics/rx_fifo_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -68,7 +68,7 @@ Description:
network device. See the network driver for the exact
meaning of this value.
-What: /sys/class/<iface>/statistics/rx_frame_errors
+What: /sys/class/net/<iface>/statistics/rx_frame_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -78,7 +78,7 @@ Description:
on the MAC layer protocol used. See the network driver for
the exact meaning of this value.
-What: /sys/class/<iface>/statistics/rx_length_errors
+What: /sys/class/net/<iface>/statistics/rx_length_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -87,7 +87,7 @@ Description:
error, oversized or undersized. See the network driver for the
exact meaning of this value.
-What: /sys/class/<iface>/statistics/rx_missed_errors
+What: /sys/class/net/<iface>/statistics/rx_missed_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -96,7 +96,7 @@ Description:
due to lack of capacity in the receive side. See the network
driver for the exact meaning of this value.
-What: /sys/class/<iface>/statistics/rx_nohandler
+What: /sys/class/net/<iface>/statistics/rx_nohandler
Date: February 2016
KernelVersion: 4.6
Contact: netdev@vger.kernel.org
@@ -104,7 +104,7 @@ Description:
Indicates the number of received packets that were dropped on
an inactive device by the network core.
-What: /sys/class/<iface>/statistics/rx_over_errors
+What: /sys/class/net/<iface>/statistics/rx_over_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -114,7 +114,7 @@ Description:
(e.g: larger than MTU). See the network driver for the exact
meaning of this value.
-What: /sys/class/<iface>/statistics/rx_packets
+What: /sys/class/net/<iface>/statistics/rx_packets
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -122,7 +122,7 @@ Description:
Indicates the total number of good packets received by this
network device.
-What: /sys/class/<iface>/statistics/tx_aborted_errors
+What: /sys/class/net/<iface>/statistics/tx_aborted_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -132,7 +132,7 @@ Description:
a medium collision). See the network driver for the exact
meaning of this value.
-What: /sys/class/<iface>/statistics/tx_bytes
+What: /sys/class/net/<iface>/statistics/tx_bytes
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -143,7 +143,7 @@ Description:
transmitted packets or all packets that have been queued for
transmission.
-What: /sys/class/<iface>/statistics/tx_carrier_errors
+What: /sys/class/net/<iface>/statistics/tx_carrier_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -152,7 +152,7 @@ Description:
because of carrier errors (e.g: physical link down). See the
network driver for the exact meaning of this value.
-What: /sys/class/<iface>/statistics/tx_compressed
+What: /sys/class/net/<iface>/statistics/tx_compressed
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -161,7 +161,7 @@ Description:
this might only be relevant for devices that support
compression (e.g: PPP).
-What: /sys/class/<iface>/statistics/tx_dropped
+What: /sys/class/net/<iface>/statistics/tx_dropped
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -170,7 +170,7 @@ Description:
See the driver for the exact reasons as to why the packets were
dropped.
-What: /sys/class/<iface>/statistics/tx_errors
+What: /sys/class/net/<iface>/statistics/tx_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -179,7 +179,7 @@ Description:
a network device. See the driver for the exact reasons as to
why the packets were dropped.
-What: /sys/class/<iface>/statistics/tx_fifo_errors
+What: /sys/class/net/<iface>/statistics/tx_fifo_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -188,7 +188,7 @@ Description:
FIFO error. See the driver for the exact reasons as to why the
packets were dropped.
-What: /sys/class/<iface>/statistics/tx_heartbeat_errors
+What: /sys/class/net/<iface>/statistics/tx_heartbeat_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -197,7 +197,7 @@ Description:
reported as heartbeat errors. See the driver for the exact
reasons as to why the packets were dropped.
-What: /sys/class/<iface>/statistics/tx_packets
+What: /sys/class/net/<iface>/statistics/tx_packets
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
@@ -206,7 +206,7 @@ Description:
device. See the driver for whether this reports the number of all
attempted or successful transmissions.
-What: /sys/class/<iface>/statistics/tx_window_errors
+What: /sys/class/net/<iface>/statistics/tx_window_errors
Date: April 2005
KernelVersion: 2.6.12
Contact: netdev@vger.kernel.org
From 551539a8606e28cb2a130f8ef3e9834235b456c4 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 11 Feb 2024 22:27:35 +0100
Subject: [PATCH 469/637] ASoC: rt5645: Make LattePanda board DMI match more
precise
The DMI strings used for the LattePanda board DMI quirks are very generic.
Using the dmidecode database from https://linux-hardware.org/ shows
that the chosen DMI strings also match the following 2 laptops
which also have a rt5645 codec:
Insignia NS-P11W7100 https://linux-hardware.org/?computer=E092FFF8BA04
Insignia NS-P10W8100 https://linux-hardware.org/?computer=AFB6C0BF7934
All 4 hw revisions of the LattePanda board have "S70CR" in their BIOS
version DMI strings:
DF-BI-7-S70CR100-*
DF-BI-7-S70CR110-*
DF-BI-7-S70CR200-*
LP-BS-7-S70CR700-*
See e.g. https://linux-hardware.org/?computer=D98250A817C0
Add a partial (non exact) DMI match on this string to make the LattePanda
board DMI match more precise to avoid false-positive matches.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://msgid.link/r/20240211212736.179605-1-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/rt5645.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 0cc2fa131d48..69de78ad5da8 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3838,6 +3838,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"),
DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"),
+ /*
+ * Above strings are too generic, LattePanda BIOS versions for
+ * all 4 hw revisions are:
+ * DF-BI-7-S70CR100-*
+ * DF-BI-7-S70CR110-*
+ * DF-BI-7-S70CR200-*
+ * LP-BS-7-S70CR700-*
+ * Do a partial match for S70CR to avoid false positive matches.
+ */
+ DMI_MATCH(DMI_BIOS_VERSION, "S70CR"),
},
.driver_data = (void *)&lattepanda_board_platform_data,
},
From d6755a53b8dde434220a164c756190345772843a Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 11 Feb 2024 22:27:36 +0100
Subject: [PATCH 470/637] ASoC: rt5645: Add DMI quirk for inverted jack-detect
on MeeGoPad T8
The MeeGoPad T8 uses the standard rt5645 jd_mode=3 setting for jack-detect,
but the used jack connector outputs an inverted jack-detect signal.
Add a DMI quirk for this.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://msgid.link/r/20240211212736.179605-2-hdegoede@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/rt5645.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 69de78ad5da8..20191a4473c2 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -3693,6 +3693,11 @@ static const struct rt5645_platform_data jd_mode3_monospk_platform_data = {
.mono_speaker = true,
};
+static const struct rt5645_platform_data jd_mode3_inv_data = {
+ .jd_mode = 3,
+ .inv_jd1_1 = true,
+};
+
static const struct rt5645_platform_data jd_mode3_platform_data = {
.jd_mode = 3,
};
@@ -3882,6 +3887,16 @@ static const struct dmi_system_id dmi_platform_data[] = {
},
.driver_data = (void *)&intel_braswell_platform_data,
},
+ {
+ .ident = "Meegopad T08",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Default string"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
+ DMI_MATCH(DMI_BOARD_NAME, "T3 MRD"),
+ DMI_MATCH(DMI_BOARD_VERSION, "V1.1"),
+ },
+ .driver_data = (void *)&jd_mode3_inv_data,
+ },
{ }
};
From e56c671c2272d939d48a66be7e73b92b74c560c2 Mon Sep 17 00:00:00 2001
From: Vaishnav Achath <vaishnav.a@ti.com>
Date: Mon, 12 Feb 2024 17:30:49 +0530
Subject: [PATCH 471/637] spi: omap2-mcspi: Revert FIFO support without DMA
MCSPI controller have few limitations regarding the transaction
size when the FIFO buffer is enabled and the WCNT feature is used
to find the end of word, in this case if WCNT is not a multiple of
the FIFO Almost Empty Level (AEL), then the FIFO empty event is not
generated correctly. In addition to this limitation, few other unknown
sequence of events that causes the FIFO empty status to not reflect the
exact status were found when FIFO is being used without DMA enabled
during extended testing in AM65x platform. Till the exact root cause
is found and fixed, revert the FIFO support without DMA.
See J721E Technical Reference Manual (SPRUI1C), section 12.1.5
for further details: http://www.ti.com/lit/pdf/spruil1
This reverts commit 75223bbea840e ("spi: omap2-mcspi: Add FIFO support
without DMA")
Signed-off-by: Vaishnav Achath <vaishnav.a@ti.com>
Link: https://msgid.link/r/20240212120049.438495-1-vaishnav.a@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-omap2-mcspi.c | 137 ++--------------------------------
1 file changed, 8 insertions(+), 129 deletions(-)
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index a0c9fea908f5..ddf1c684bcc7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -53,8 +53,6 @@
/* per-register bitmasks: */
#define OMAP2_MCSPI_IRQSTATUS_EOW BIT(17)
-#define OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY BIT(0)
-#define OMAP2_MCSPI_IRQSTATUS_RX0_FULL BIT(2)
#define OMAP2_MCSPI_MODULCTRL_SINGLE BIT(0)
#define OMAP2_MCSPI_MODULCTRL_MS BIT(2)
@@ -293,7 +291,7 @@ static void omap2_mcspi_set_mode(struct spi_controller *ctlr)
}
static void omap2_mcspi_set_fifo(const struct spi_device *spi,
- struct spi_transfer *t, int enable, int dma_enabled)
+ struct spi_transfer *t, int enable)
{
struct spi_controller *ctlr = spi->controller;
struct omap2_mcspi_cs *cs = spi->controller_state;
@@ -314,28 +312,20 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi,
max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH / 2;
else
max_fifo_depth = OMAP2_MCSPI_MAX_FIFODEPTH;
- if (dma_enabled)
- wcnt = t->len / bytes_per_word;
- else
- wcnt = 0;
+
+ wcnt = t->len / bytes_per_word;
if (wcnt > OMAP2_MCSPI_MAX_FIFOWCNT)
goto disable_fifo;
xferlevel = wcnt << 16;
if (t->rx_buf != NULL) {
chconf |= OMAP2_MCSPI_CHCONF_FFER;
- if (dma_enabled)
- xferlevel |= (bytes_per_word - 1) << 8;
- else
- xferlevel |= (max_fifo_depth - 1) << 8;
+ xferlevel |= (bytes_per_word - 1) << 8;
}
if (t->tx_buf != NULL) {
chconf |= OMAP2_MCSPI_CHCONF_FFET;
- if (dma_enabled)
- xferlevel |= bytes_per_word - 1;
- else
- xferlevel |= (max_fifo_depth - 1);
+ xferlevel |= bytes_per_word - 1;
}
mcspi_write_reg(ctlr, OMAP2_MCSPI_XFERLEVEL, xferlevel);
@@ -892,113 +882,6 @@ out:
return count - c;
}
-static unsigned
-omap2_mcspi_txrx_piofifo(struct spi_device *spi, struct spi_transfer *xfer)
-{
- struct omap2_mcspi_cs *cs = spi->controller_state;
- struct omap2_mcspi *mcspi;
- unsigned int count, c;
- unsigned int iter, cwc;
- int last_request;
- void __iomem *base = cs->base;
- void __iomem *tx_reg;
- void __iomem *rx_reg;
- void __iomem *chstat_reg;
- void __iomem *irqstat_reg;
- int word_len, bytes_per_word;
- u8 *rx;
- const u8 *tx;
-
- mcspi = spi_controller_get_devdata(spi->controller);
- count = xfer->len;
- c = count;
- word_len = cs->word_len;
- bytes_per_word = mcspi_bytes_per_word(word_len);
-
- /*
- * We store the pre-calculated register addresses on stack to speed
- * up the transfer loop.
- */
- tx_reg = base + OMAP2_MCSPI_TX0;
- rx_reg = base + OMAP2_MCSPI_RX0;
- chstat_reg = base + OMAP2_MCSPI_CHSTAT0;
- irqstat_reg = base + OMAP2_MCSPI_IRQSTATUS;
-
- if (c < (word_len >> 3))
- return 0;
-
- rx = xfer->rx_buf;
- tx = xfer->tx_buf;
-
- do {
- /* calculate number of words in current iteration */
- cwc = min((unsigned int)mcspi->fifo_depth / bytes_per_word,
- c / bytes_per_word);
- last_request = cwc != (mcspi->fifo_depth / bytes_per_word);
- if (tx) {
- if (mcspi_wait_for_reg_bit(irqstat_reg,
- OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY) < 0) {
- dev_err(&spi->dev, "TX Empty timed out\n");
- goto out;
- }
- writel_relaxed(OMAP2_MCSPI_IRQSTATUS_TX0_EMPTY, irqstat_reg);
-
- for (iter = 0; iter < cwc; iter++, tx += bytes_per_word) {
- if (bytes_per_word == 1)
- writel_relaxed(*tx, tx_reg);
- else if (bytes_per_word == 2)
- writel_relaxed(*((u16 *)tx), tx_reg);
- else if (bytes_per_word == 4)
- writel_relaxed(*((u32 *)tx), tx_reg);
- }
- }
-
- if (rx) {
- if (!last_request &&
- mcspi_wait_for_reg_bit(irqstat_reg,
- OMAP2_MCSPI_IRQSTATUS_RX0_FULL) < 0) {
- dev_err(&spi->dev, "RX_FULL timed out\n");
- goto out;
- }
- writel_relaxed(OMAP2_MCSPI_IRQSTATUS_RX0_FULL, irqstat_reg);
-
- for (iter = 0; iter < cwc; iter++, rx += bytes_per_word) {
- if (last_request &&
- mcspi_wait_for_reg_bit(chstat_reg,
- OMAP2_MCSPI_CHSTAT_RXS) < 0) {
- dev_err(&spi->dev, "RXS timed out\n");
- goto out;
- }
- if (bytes_per_word == 1)
- *rx = readl_relaxed(rx_reg);
- else if (bytes_per_word == 2)
- *((u16 *)rx) = readl_relaxed(rx_reg);
- else if (bytes_per_word == 4)
- *((u32 *)rx) = readl_relaxed(rx_reg);
- }
- }
-
- if (last_request) {
- if (mcspi_wait_for_reg_bit(chstat_reg,
- OMAP2_MCSPI_CHSTAT_EOT) < 0) {
- dev_err(&spi->dev, "EOT timed out\n");
- goto out;
- }
- if (mcspi_wait_for_reg_bit(chstat_reg,
- OMAP2_MCSPI_CHSTAT_TXFFE) < 0) {
- dev_err(&spi->dev, "TXFFE timed out\n");
- goto out;
- }
- omap2_mcspi_set_enable(spi, 0);
- }
- c -= cwc * bytes_per_word;
- } while (c >= bytes_per_word);
-
-out:
- omap2_mcspi_set_enable(spi, 1);
- return count - c;
-}
-
static u32 omap2_mcspi_calc_divisor(u32 speed_hz, u32 ref_clk_hz)
{
u32 div;
@@ -1323,9 +1206,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
ctlr->cur_msg_mapped &&
ctlr->can_dma(ctlr, spi, t))
- omap2_mcspi_set_fifo(spi, t, 1, 1);
- else if (t->len > OMAP2_MCSPI_MAX_FIFODEPTH)
- omap2_mcspi_set_fifo(spi, t, 1, 0);
+ omap2_mcspi_set_fifo(spi, t, 1);
omap2_mcspi_set_enable(spi, 1);
@@ -1338,8 +1219,6 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
ctlr->cur_msg_mapped &&
ctlr->can_dma(ctlr, spi, t))
count = omap2_mcspi_txrx_dma(spi, t);
- else if (mcspi->fifo_depth > 0)
- count = omap2_mcspi_txrx_piofifo(spi, t);
else
count = omap2_mcspi_txrx_pio(spi, t);
@@ -1352,7 +1231,7 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
omap2_mcspi_set_enable(spi, 0);
if (mcspi->fifo_depth > 0)
- omap2_mcspi_set_fifo(spi, t, 0, 0);
+ omap2_mcspi_set_fifo(spi, t, 0);
out:
/* Restore defaults if they were overriden */
@@ -1375,7 +1254,7 @@ out:
omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH));
if (mcspi->fifo_depth > 0 && t)
- omap2_mcspi_set_fifo(spi, t, 0, 0);
+ omap2_mcspi_set_fifo(spi, t, 0);
return status;
}
From 8f44e3808200c1434c26ef459722f88f48b306df Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 12 Feb 2024 10:20:27 +0200
Subject: [PATCH 472/637] spi: intel-pci: Add support for Lunar Lake-M SPI
serial flash
Add Intel Lunar Lake-M PCI ID to the driver list of supported devices.
This is the same controller found in previous generations.
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://msgid.link/r/20240212082027.2462849-1-mika.westerberg@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-intel-pci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index 07d20ca1164c..4337ca51d7aa 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -85,6 +85,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
{ PCI_VDEVICE(INTEL, 0xa2a4), (unsigned long)&cnl_info },
{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
+ { PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info },
{ },
};
MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
From 2f0dbb24f78a333433a2b875c0b76bf55c119cd4 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sun, 11 Feb 2024 16:58:17 +0000
Subject: [PATCH 473/637] regmap: kunit: Ensure that changed bytes are actually
different
During the cache sync test we verify that values we expect to have been
written only to the cache do not appear in the hardware. This works most
of the time but since we randomly generate both the original and new values
there is a low probability that these values may actually be the same.
Wrap get_random_bytes() to ensure that the values are different, there
are other tests which should have similar verification that we actually
changed something.
While we're at it refactor the test to use three changed values rather
than attempting to use one of them twice, that just complicates checking
that our new values are actually new.
We use random generation to try to avoid data dependencies in the tests.
Reported-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/r/20240211-regmap-kunit-random-change-v3-1-e387a9ea4468@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/base/regmap/regmap-kunit.c | 54 +++++++++++++++++++++---------
1 file changed, 38 insertions(+), 16 deletions(-)
diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
index 4eb18f5d3265..0d957c5f1bcc 100644
--- a/drivers/base/regmap/regmap-kunit.c
+++ b/drivers/base/regmap/regmap-kunit.c
@@ -9,6 +9,23 @@
#define BLOCK_TEST_SIZE 12
+static void get_changed_bytes(void *orig, void *new, size_t size)
+{
+ char *o = orig;
+ char *n = new;
+ int i;
+
+ get_random_bytes(new, size);
+
+ /*
+ * This could be nicer and more efficient but we shouldn't
+ * super care.
+ */
+ for (i = 0; i < size; i++)
+ while (n[i] == o[i])
+ get_random_bytes(&n[i], 1);
+}
+
static const struct regmap_config test_regmap_config = {
.max_register = BLOCK_TEST_SIZE,
.reg_stride = 1,
@@ -1252,7 +1269,7 @@ static void raw_sync(struct kunit *test)
struct regmap *map;
struct regmap_config config;
struct regmap_ram_data *data;
- u16 val[2];
+ u16 val[3];
u16 *hw_buf;
unsigned int rval;
int i;
@@ -1266,17 +1283,13 @@ static void raw_sync(struct kunit *test)
hw_buf = (u16 *)data->vals;
- get_random_bytes(&val, sizeof(val));
+ get_changed_bytes(&hw_buf[2], &val[0], sizeof(val));
/* Do a regular write and a raw write in cache only mode */
regcache_cache_only(map, true);
- KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val, sizeof(val)));
- if (config.val_format_endian == REGMAP_ENDIAN_BIG)
- KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
- be16_to_cpu(val[0])));
- else
- KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 6,
- le16_to_cpu(val[0])));
+ KUNIT_EXPECT_EQ(test, 0, regmap_raw_write(map, 2, val,
+ sizeof(u16) * 2));
+ KUNIT_EXPECT_EQ(test, 0, regmap_write(map, 4, val[2]));
/* We should read back the new values, and defaults for the rest */
for (i = 0; i < config.max_register + 1; i++) {
@@ -1285,24 +1298,34 @@ static void raw_sync(struct kunit *test)
switch (i) {
case 2:
case 3:
- case 6:
if (config.val_format_endian == REGMAP_ENDIAN_BIG) {
KUNIT_EXPECT_EQ(test, rval,
- be16_to_cpu(val[i % 2]));
+ be16_to_cpu(val[i - 2]));
} else {
KUNIT_EXPECT_EQ(test, rval,
- le16_to_cpu(val[i % 2]));
+ le16_to_cpu(val[i - 2]));
}
break;
+ case 4:
+ KUNIT_EXPECT_EQ(test, rval, val[i - 2]);
+ break;
default:
KUNIT_EXPECT_EQ(test, config.reg_defaults[i].def, rval);
break;
}
}
+
+ /*
+ * The value written via _write() was translated by the core,
+ * translate the original copy for comparison purposes.
+ */
+ if (config.val_format_endian == REGMAP_ENDIAN_BIG)
+ val[2] = cpu_to_be16(val[2]);
+ else
+ val[2] = cpu_to_le16(val[2]);
/* The values should not appear in the "hardware" */
- KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], val, sizeof(val));
- KUNIT_EXPECT_MEMNEQ(test, &hw_buf[6], val, sizeof(u16));
+ KUNIT_EXPECT_MEMNEQ(test, &hw_buf[2], &val[0], sizeof(val));
for (i = 0; i < config.max_register + 1; i++)
data->written[i] = false;
@@ -1313,8 +1336,7 @@ static void raw_sync(struct kunit *test)
KUNIT_EXPECT_EQ(test, 0, regcache_sync(map));
/* The values should now appear in the "hardware" */
- KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], val, sizeof(val));
- KUNIT_EXPECT_MEMEQ(test, &hw_buf[6], val, sizeof(u16));
+ KUNIT_EXPECT_MEMEQ(test, &hw_buf[2], &val[0], sizeof(val));
regmap_exit(map);
}
From 2c80a2b715df75881359d07dbaacff8ad411f40e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 12 Feb 2024 12:22:17 +0100
Subject: [PATCH 474/637] nouveau/svm: fix kvcalloc() argument order
The conversion to kvcalloc() mixed up the object size and count
arguments, causing a warning:
drivers/gpu/drm/nouveau/nouveau_svm.c: In function 'nouveau_svm_fault_buffer_ctor':
drivers/gpu/drm/nouveau/nouveau_svm.c:1010:40: error: 'kvcalloc' sizes specified with 'sizeof' in the earlier argument and not in the later argument [-Werror=calloc-transposed-args]
1010 | buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL);
| ^
drivers/gpu/drm/nouveau/nouveau_svm.c:1010:40: note: earlier argument should specify number of elements, later size of each element
The behavior is still correct aside from the warning, but fixing it avoids
the warnings and can help the compiler track the individual objects better.
Fixes: 71e4bbca070e ("nouveau/svm: Use kvcalloc() instead of kvzalloc()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240212112230.1117284-1-arnd@kernel.org
---
drivers/gpu/drm/nouveau/nouveau_svm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index cc03e0c22ff3..5e4565c5011a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -1011,7 +1011,7 @@ nouveau_svm_fault_buffer_ctor(struct nouveau_svm *svm, s32 oclass, int id)
if (ret)
return ret;
- buffer->fault = kvcalloc(sizeof(*buffer->fault), buffer->entries, GFP_KERNEL);
+ buffer->fault = kvcalloc(buffer->entries, sizeof(*buffer->fault), GFP_KERNEL);
if (!buffer->fault)
return -ENOMEM;
From f7fe85b229bc30cb5dc95b4e9015a601c9e3a8cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Attila=20T=C5=91k=C3=A9s?= <attitokes@gmail.com>
Date: Sat, 10 Feb 2024 21:36:38 +0200
Subject: [PATCH 475/637] ASoC: amd: yc: Fix non-functional mic on Lenovo 82UU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Like many other models, the Lenovo 82UU (Yoga Slim 7 Pro 14ARH7)
needs a quirk entry for the internal microphone to function.
Signed-off-by: Attila Tőkés <attitokes@gmail.com>
Link: https://msgid.link/r/20240210193638.144028-1-attitokes@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 80ad60d485ea..cc231185d72c 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -234,6 +234,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "82UG"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "82UU"),
+ }
+ },
{
.driver_data = &acp6x_card,
.matches = {
From 83ef106fa732aea8558253641cd98e8a895604d7 Mon Sep 17 00:00:00 2001
From: Viken Dadhaniya <quic_vdadhani@quicinc.com>
Date: Mon, 12 Feb 2024 18:22:39 +0530
Subject: [PATCH 476/637] i2c: qcom-geni: Correct I2C TRE sequence
For i2c read operation in GSI mode, we are getting timeout
due to malformed TRE basically incorrect TRE sequence
in gpi(drivers/dma/qcom/gpi.c) driver.
I2C driver has geni_i2c_gpi(I2C_WRITE) function which generates GO TRE and
geni_i2c_gpi(I2C_READ)generates DMA TRE. Hence to generate GO TRE before
DMA TRE, we should move geni_i2c_gpi(I2C_WRITE) before
geni_i2c_gpi(I2C_READ) inside the I2C GSI mode transfer function
i.e. geni_i2c_gpi_xfer().
TRE stands for Transfer Ring Element - which is basically an element with
size of 4 words. It contains all information like slave address,
clk divider, dma address value data size etc).
Mainly we have 3 TREs(Config, GO and DMA tre).
- CONFIG TRE : consists of internal register configuration which is
required before start of the transfer.
- DMA TRE : contains DDR/Memory address, called as DMA descriptor.
- GO TRE : contains Transfer directions, slave ID, Delay flags, Length
of the transfer.
I2c driver calls GPI driver API to config each TRE depending on the
protocol.
For read operation tre sequence will be as below which is not aligned
to hardware programming guide.
- CONFIG tre
- DMA tre
- GO tre
As per Qualcomm's internal Hardware Programming Guide, we should configure
TREs in below sequence for any RX only transfer.
- CONFIG tre
- GO tre
- DMA tre
Fixes: d8703554f4de ("i2c: qcom-geni: Add support for GPI DMA")
Reviewed-by: Andi Shyti <andi.shyti@kernel.org>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Tested-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org> # qrb5165-rb5
Co-developed-by: Mukesh Kumar Savaliya <quic_msavaliy@quicinc.com>
Signed-off-by: Mukesh Kumar Savaliya <quic_msavaliy@quicinc.com>
Signed-off-by: Viken Dadhaniya <quic_vdadhani@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
drivers/i2c/busses/i2c-qcom-geni.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index 0d2e7171e3a6..da94df466e83 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -613,20 +613,20 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i
peripheral.addr = msgs[i].addr;
- if (msgs[i].flags & I2C_M_RD) {
- ret = geni_i2c_gpi(gi2c, &msgs[i], &config,
- &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c);
- if (ret)
- goto err;
- }
-
ret = geni_i2c_gpi(gi2c, &msgs[i], &config,
&tx_addr, &tx_buf, I2C_WRITE, gi2c->tx_c);
if (ret)
goto err;
- if (msgs[i].flags & I2C_M_RD)
+ if (msgs[i].flags & I2C_M_RD) {
+ ret = geni_i2c_gpi(gi2c, &msgs[i], &config,
+ &rx_addr, &rx_buf, I2C_READ, gi2c->rx_c);
+ if (ret)
+ goto err;
+
dma_async_issue_pending(gi2c->rx_c);
+ }
+
dma_async_issue_pending(gi2c->tx_c);
timeout = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT);
From 7d8c67dd5d4f2ed1907e192c73dd948d35145641 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 12 Jan 2024 10:59:03 -0800
Subject: [PATCH 477/637] xen/xenbus: document will_handle argument for
xenbus_watch_path()
Commit 2e85d32b1c86 ("xen/xenbus: Add 'will_handle' callback support in
xenbus_watch_path()") added will_handle argument to xenbus_watch_path()
and its wrapper, xenbus_watch_pathfmt(), but didn't document it on the
kerneldoc comments of the function. This is causing warnings that
reported by kernel test robot. Add the documentation to fix it.
Fixes: 2e85d32b1c86 ("xen/xenbus: Add 'will_handle' callback support in xenbus_watch_path()")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401121154.FI8jDGun-lkp@intel.com/
Signed-off-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20240112185903.83737-1-sj@kernel.org
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/xenbus/xenbus_client.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 32835b4b9bc5..51b3124b0d56 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -116,14 +116,15 @@ EXPORT_SYMBOL_GPL(xenbus_strstate);
* @dev: xenbus device
* @path: path to watch
* @watch: watch to register
+ * @will_handle: events queuing determine callback
* @callback: callback to register
*
* Register a @watch on the given path, using the given xenbus_watch structure
- * for storage, and the given @callback function as the callback. On success,
- * the given @path will be saved as @watch->node, and remains the
- * caller's to free. On error, @watch->node will
- * be NULL, the device will switch to %XenbusStateClosing, and the error will
- * be saved in the store.
+ * for storage, @will_handle function as the callback to determine if each
+ * event need to be queued, and the given @callback function as the callback.
+ * On success, the given @path will be saved as @watch->node, and remains the
+ * caller's to free. On error, @watch->node will be NULL, the device will
+ * switch to %XenbusStateClosing, and the error will be saved in the store.
*
* Returns: %0 on success or -errno on error
*/
@@ -158,11 +159,13 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path);
* xenbus_watch_pathfmt - register a watch on a sprintf-formatted path
* @dev: xenbus device
* @watch: watch to register
+ * @will_handle: events queuing determine callback
* @callback: callback to register
* @pathfmt: format of path to watch
*
* Register a watch on the given @path, using the given xenbus_watch
- * structure for storage, and the given @callback function as the
+ * structure for storage, @will_handle function as the callback to determine if
+ * each event need to be queued, and the given @callback function as the
* callback. On success, the watched path (@path/@path2) will be saved
* as @watch->node, and becomes the caller's to kfree().
* On error, watch->node will be NULL, so the caller has nothing to
From 4508ec17357094e2075f334948393ddedbb75157 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Sun, 11 Feb 2024 20:19:30 -0300
Subject: [PATCH 478/637] smb: client: set correct id, uid and cruid for
multiuser automounts
When uid, gid and cruid are not specified, we need to dynamically
set them into the filesystem context used for automounting otherwise
they'll end up reusing the values from the parent mount.
Fixes: 9fd29a5bae6e ("cifs: use fs_context for automounts")
Reported-by: Shane Nehring <snehring@iastate.edu>
Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2259257
Cc: stable@vger.kernel.org # 6.2+
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/namespace.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c
index a6968573b775..4a517b280f2b 100644
--- a/fs/smb/client/namespace.c
+++ b/fs/smb/client/namespace.c
@@ -168,6 +168,21 @@ static char *automount_fullpath(struct dentry *dentry, void *page)
return s;
}
+static void fs_context_set_ids(struct smb3_fs_context *ctx)
+{
+ kuid_t uid = current_fsuid();
+ kgid_t gid = current_fsgid();
+
+ if (ctx->multiuser) {
+ if (!ctx->uid_specified)
+ ctx->linux_uid = uid;
+ if (!ctx->gid_specified)
+ ctx->linux_gid = gid;
+ }
+ if (!ctx->cruid_specified)
+ ctx->cred_uid = uid;
+}
+
/*
* Create a vfsmount that we can automount
*/
@@ -205,6 +220,7 @@ static struct vfsmount *cifs_do_automount(struct path *path)
tmp.leaf_fullpath = NULL;
tmp.UNC = tmp.prepath = NULL;
tmp.dfs_root_ses = NULL;
+ fs_context_set_ids(&tmp);
rc = smb3_fs_context_dup(ctx, &tmp);
if (rc) {
From 8bde59b20de06339d598e8b05e5195f7c631c38b Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Sun, 11 Feb 2024 20:19:31 -0300
Subject: [PATCH 479/637] smb: client: handle path separator of created SMB
symlinks
Convert path separator to CIFS_DIR_SEP(cifs_sb) from symlink target
before sending it over the wire otherwise the created SMB symlink may
become innaccesible from server side.
Fixes: 514d793e27a3 ("smb: client: allow creating symlinks via reparse points")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/smb2ops.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 6b3c384ead0d..4695433fcf39 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -5217,7 +5217,7 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
struct inode *new;
struct kvec iov;
__le16 *path;
- char *sym;
+ char *sym, sep = CIFS_DIR_SEP(cifs_sb);
u16 len, plen;
int rc = 0;
@@ -5231,7 +5231,8 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
.symlink_target = sym,
};
- path = cifs_convert_path_to_utf16(symname, cifs_sb);
+ convert_delimiter(sym, sep);
+ path = cifs_convert_path_to_utf16(sym, cifs_sb);
if (!path) {
rc = -ENOMEM;
goto out;
@@ -5254,7 +5255,10 @@ static int smb2_create_reparse_symlink(const unsigned int xid,
buf->PrintNameLength = cpu_to_le16(plen);
memcpy(buf->PathBuffer, path, plen);
buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0);
+ if (*sym != sep)
+ buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE);
+ convert_delimiter(sym, '/');
iov.iov_base = buf;
iov.iov_len = len;
new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
From 3693bb4465e6e32a204a5b86d3ec7e6b9f7e67c2 Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Fri, 19 Jan 2024 17:49:48 +0800
Subject: [PATCH 480/637] x86/xen: Add some null pointer checking to smp.c
kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure. Ensure the allocation was successful
by checking the pointer validity.
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401161119.iof6BQsf-lkp@intel.com/
Suggested-by: Markus Elfring <Markus.Elfring@web.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20240119094948.275390-1-chentao@kylinos.cn
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/xen/smp.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 4b0d6fff88de..1fb9a1644d94 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu)
char *resched_name, *callfunc_name, *debug_name;
resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+ if (!resched_name)
+ goto fail_mem;
per_cpu(xen_resched_irq, cpu).name = resched_name;
rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
cpu,
@@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu)
per_cpu(xen_resched_irq, cpu).irq = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+ if (!callfunc_name)
+ goto fail_mem;
per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
cpu,
@@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu)
if (!xen_fifo_events) {
debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+ if (!debug_name)
+ goto fail_mem;
+
per_cpu(xen_debug_irq, cpu).name = debug_name;
rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
xen_debug_interrupt,
@@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu)
}
callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+ if (!callfunc_name)
+ goto fail_mem;
+
per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
cpu,
@@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu)
return 0;
+ fail_mem:
+ rc = -ENOMEM;
fail:
xen_smp_intr_free(cpu);
return rc;
From d55347bfe4e66dce2e1e7501e5492f4af3e315f8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 11 Feb 2024 08:08:37 -0800
Subject: [PATCH 481/637] MIPS: Add 'memory' clobber to csum_ipv6_magic()
inline assembler
After 'lib: checksum: Use aligned accesses for ip_fast_csum and
csum_ipv6_magic tests' was applied, the test_csum_ipv6_magic unit test
started failing for all mips platforms, both little and bit endian.
Oddly enough, adding debug code into test_csum_ipv6_magic() made the
problem disappear.
The gcc manual says:
"The "memory" clobber tells the compiler that the assembly code performs
memory reads or writes to items other than those listed in the input
and output operands (for example, accessing the memory pointed to by one
of the input parameters)
"
This is definitely the case for csum_ipv6_magic(). Indeed, adding the
'memory' clobber fixes the problem.
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
arch/mips/include/asm/checksum.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 4044eaf989ac..0921ddda11a4 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
" .set pop"
: "=&r" (sum), "=&r" (tmp)
: "r" (saddr), "r" (daddr),
- "0" (htonl(len)), "r" (htonl(proto)), "r" (sum));
+ "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)
+ : "memory");
return csum_fold(sum);
}
From 11ba1728be3edb6928791f4c622f154ebe228ae6 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:26 +0000
Subject: [PATCH 482/637] ptrace: Introduce exception_ip arch hook
On architectures with delay slot, architecture level instruction
pointer (or program counter) in pt_regs may differ from where
exception was triggered.
Introduce exception_ip hook to invoke architecture code and determine
actual instruction pointer to the exception.
Link: https://lore.kernel.org/lkml/00d1b813-c55f-4365-8d81-d70258e10b16@app.fastmail.com/
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
arch/mips/include/asm/ptrace.h | 2 ++
arch/mips/kernel/ptrace.c | 7 +++++++
include/linux/ptrace.h | 4 ++++
3 files changed, 13 insertions(+)
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index daf3cf244ea9..701a233583c2 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -154,6 +154,8 @@ static inline long regs_return_value(struct pt_regs *regs)
}
#define instruction_pointer(regs) ((regs)->cp0_epc)
+extern unsigned long exception_ip(struct pt_regs *regs);
+#define exception_ip(regs) exception_ip(regs)
#define profile_pc(regs) instruction_pointer(regs)
extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index d9df543f7e2c..59288c13b581 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -31,6 +31,7 @@
#include <linux/seccomp.h>
#include <linux/ftrace.h>
+#include <asm/branch.h>
#include <asm/byteorder.h>
#include <asm/cpu.h>
#include <asm/cpu-info.h>
@@ -48,6 +49,12 @@
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
+unsigned long exception_ip(struct pt_regs *regs)
+{
+ return exception_epc(regs);
+}
+EXPORT_SYMBOL(exception_ip);
+
/*
* Called by kernel/ptrace.c when detaching..
*
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eaaef3ffec22..90507d4afcd6 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs)
#define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
#endif
+#ifndef exception_ip
+#define exception_ip(x) instruction_pointer(x)
+#endif
+
extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
From 9d6e21ddf20293b3880ae55b9d14de91c5891c59 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:27 +0000
Subject: [PATCH 483/637] MIPS: Clear Cause.BD in instruction_pointer_set
Clear Cause.BD after we use instruction_pointer_set to override
EPC.
This can prevent exception_epc check against instruction code at
new return address.
It won't be considered as "in delay slot" after epc being overridden
anyway.
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
arch/mips/include/asm/ptrace.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 701a233583c2..d14d0e37ad02 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{
regs->cp0_epc = val;
+ regs->cp0_cause &= ~CAUSEF_BD;
}
/* Query offset/name of register from its name/offset */
From 8fa5070833886268e4fb646daaca99f725b378e9 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 2 Feb 2024 12:30:28 +0000
Subject: [PATCH 484/637] mm/memory: Use exception ip to search exception
tables
On architectures with delay slot, instruction_pointer() may differ
from where exception was triggered.
Use exception_ip we just introduced to search exception tables to
get rid of the problem.
Fixes: 4bce37a68ff8 ("mips/mm: Convert to using lock_mm_and_find_vma()")
Reported-by: Xi Ruoyao <xry111@xry111.site>
Link: https://lore.kernel.org/r/75e9fd7b08562ad9b456a5bdaacb7cc220311cc9.camel@xry111.site/
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
mm/memory.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 89bcae0b224d..15f8b10ea17c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5478,7 +5478,7 @@ static inline bool get_mmap_lock_carefully(struct mm_struct *mm, struct pt_regs
return true;
if (regs && !user_mode(regs)) {
- unsigned long ip = instruction_pointer(regs);
+ unsigned long ip = exception_ip(regs);
if (!search_exception_tables(ip))
return false;
}
@@ -5503,7 +5503,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
{
mmap_read_unlock(mm);
if (regs && !user_mode(regs)) {
- unsigned long ip = instruction_pointer(regs);
+ unsigned long ip = exception_ip(regs);
if (!search_exception_tables(ip))
return false;
}
From d794734c9bbfe22f86686dc2909c25f5ffe1a572 Mon Sep 17 00:00:00 2001
From: Steve Wahl <steve.wahl@hpe.com>
Date: Fri, 26 Jan 2024 10:48:41 -0600
Subject: [PATCH 485/637] x86/mm/ident_map: Use gbpages only where full GB page
should be mapped.
When ident_pud_init() uses only gbpages to create identity maps, large
ranges of addresses not actually requested can be included in the
resulting table; a 4K request will map a full GB. On UV systems, this
ends up including regions that will cause hardware to halt the system
if accessed (these are marked "reserved" by BIOS). Even processor
speculation into these regions is enough to trigger the system halt.
Only use gbpages when map creation requests include the full GB page
of space. Fall back to using smaller 2M pages when only portions of a
GB page are included in the request.
No attempt is made to coalesce mapping requests. If a request requires
a map entry at the 2M (pmd) level, subsequent mapping requests within
the same 1G region will also be at the pmd level, even if adjacent or
overlapping such requests could have been combined to map a full
gbpage. Existing usage starts with larger regions and then adds
smaller regions, so this should not have any great consequence.
[ dhansen: fix up comment formatting, simplifty changelog ]
Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20240126164841.170866-1-steve.wahl%40hpe.com
---
arch/x86/mm/ident_map.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 968d7005f4a7..f50cc210a981 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
for (; addr < end; addr = next) {
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
+ bool use_gbpage;
next = (addr & PUD_MASK) + PUD_SIZE;
if (next > end)
next = end;
- if (info->direct_gbpages) {
+ /* if this is already a gbpage, this portion is already mapped */
+ if (pud_large(*pud))
+ continue;
+
+ /* Is using a gbpage allowed? */
+ use_gbpage = info->direct_gbpages;
+
+ /* Don't use gbpage if it maps more than the requested region. */
+ /* at the begining: */
+ use_gbpage &= ((addr & ~PUD_MASK) == 0);
+ /* ... or at the end: */
+ use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+ /* Never overwrite existing mappings */
+ use_gbpage &= !pud_present(*pud);
+
+ if (use_gbpage) {
pud_t pudval;
- if (pud_present(*pud))
- continue;
-
- addr &= PUD_MASK;
pudval = __pud((addr - info->offset) | info->page_flag);
set_pud(pud, pudval);
continue;
From 73d9629e1c8c1982f13688c4d1019c3994647ccc Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 8 Feb 2024 10:03:33 -0800
Subject: [PATCH 486/637] i40e: Do not allow untrusted VF to remove
administratively set MAC
Currently when PF administratively sets VF's MAC address and the VF
is put down (VF tries to delete all MACs) then the MAC is removed
from MAC filters and primary VF MAC is zeroed.
Do not allow untrusted VF to remove primary MAC when it was set
administratively by PF.
Reproducer:
1) Create VF
2) Set VF interface up
3) Administratively set the VF's MAC
4) Put VF interface down
[root@host ~]# echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs
[root@host ~]# ip link set enp2s0f0v0 up
[root@host ~]# ip link set enp2s0f0 vf 0 mac fe:6c:b5:da:c7:7d
[root@host ~]# ip link show enp2s0f0
23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff
vf 0 link/ether fe:6c:b5:da:c7:7d brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
[root@host ~]# ip link set enp2s0f0v0 down
[root@host ~]# ip link show enp2s0f0
23: enp2s0f0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
link/ether 3c:ec:ef:b7:dd:04 brd ff:ff:ff:ff:ff:ff
vf 0 link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff, spoof checking on, link-state auto, trust off
Fixes: 700bbf6c1f9e ("i40e: allow VF to remove any MAC filter")
Fixes: ceb29474bbbc ("i40e: Add support for VF to specify its primary MAC address")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20240208180335.1844996-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../ethernet/intel/i40e/i40e_virtchnl_pf.c | 38 ++++++++++++++++---
1 file changed, 33 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 908cdbd3ec5d..b34c71770887 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2848,6 +2848,24 @@ error_param:
(u8 *)&stats, sizeof(stats));
}
+/**
+ * i40e_can_vf_change_mac
+ * @vf: pointer to the VF info
+ *
+ * Return true if the VF is allowed to change its MAC filters, false otherwise
+ */
+static bool i40e_can_vf_change_mac(struct i40e_vf *vf)
+{
+ /* If the VF MAC address has been set administratively (via the
+ * ndo_set_vf_mac command), then deny permission to the VF to
+ * add/delete unicast MAC addresses, unless the VF is trusted
+ */
+ if (vf->pf_set_mac && !vf->trusted)
+ return false;
+
+ return true;
+}
+
#define I40E_MAX_MACVLAN_PER_HW 3072
#define I40E_MAX_MACVLAN_PER_PF(num_ports) (I40E_MAX_MACVLAN_PER_HW / \
(num_ports))
@@ -2907,8 +2925,8 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf,
* The VF may request to set the MAC address filter already
* assigned to it so do not return an error in that case.
*/
- if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
- !is_multicast_ether_addr(addr) && vf->pf_set_mac &&
+ if (!i40e_can_vf_change_mac(vf) &&
+ !is_multicast_ether_addr(addr) &&
!ether_addr_equal(addr, vf->default_lan_addr.addr)) {
dev_err(&pf->pdev->dev,
"VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n");
@@ -3114,19 +3132,29 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
ret = -EINVAL;
goto error_param;
}
- if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
- was_unimac_deleted = true;
}
vsi = pf->vsi[vf->lan_vsi_idx];
spin_lock_bh(&vsi->mac_filter_hash_lock);
/* delete addresses from the list */
- for (i = 0; i < al->num_elements; i++)
+ for (i = 0; i < al->num_elements; i++) {
+ const u8 *addr = al->list[i].addr;
+
+ /* Allow to delete VF primary MAC only if it was not set
+ * administratively by PF or if VF is trusted.
+ */
+ if (ether_addr_equal(addr, vf->default_lan_addr.addr) &&
+ i40e_can_vf_change_mac(vf))
+ was_unimac_deleted = true;
+ else
+ continue;
+
if (i40e_del_mac_filter(vsi, al->list[i].addr)) {
ret = -EINVAL;
spin_unlock_bh(&vsi->mac_filter_hash_lock);
goto error_param;
}
+ }
spin_unlock_bh(&vsi->mac_filter_hash_lock);
From c2b3ec36b422a331e153a9e40d14adcf82685cee Mon Sep 17 00:00:00 2001
From: Maxim Galaganov <max@internet.ru>
Date: Fri, 9 Feb 2024 16:25:11 +0300
Subject: [PATCH 487/637] selftests: net: ip_local_port_range: define
IPPROTO_MPTCP
Older glibc's netinet/in.h may leave IPPROTO_MPTCP undefined when
building ip_local_port_range.c, that leads to "error: use of undeclared
identifier 'IPPROTO_MPTCP'".
Define IPPROTO_MPTCP in such cases, just like in other MPTCP selftests.
Fixes: 122db5e3634b ("selftests/net: add MPTCP coverage for IP_LOCAL_PORT_RANGE")
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Closes: https://lore.kernel.org/netdev/CA+G9fYvGO5q4o_Td_kyQgYieXWKw6ktMa-Q0sBu6S-0y3w2aEQ@mail.gmail.com/
Signed-off-by: Maxim Galaganov <max@internet.ru>
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
Link: https://lore.kernel.org/r/20240209132512.254520-1-max@internet.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/ip_local_port_range.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c
index 0f217a1cc837..6ebd58869a63 100644
--- a/tools/testing/selftests/net/ip_local_port_range.c
+++ b/tools/testing/selftests/net/ip_local_port_range.c
@@ -16,6 +16,10 @@
#define IP_LOCAL_PORT_RANGE 51
#endif
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
static __u32 pack_port_range(__u16 lo, __u16 hi)
{
return (hi << 16) | (lo << 0);
From c73729b64bb692186da080602cd13612783f52ac Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 8 Nov 2023 17:01:03 +0100
Subject: [PATCH 488/637] i40e: Fix waiting for queues of all VSIs to be
disabled
The function i40e_pf_wait_queues_disabled() iterates all PF's VSIs
up to 'pf->hw.func_caps.num_vsis' but this is incorrect because
the real number of VSIs can be up to 'pf->num_alloc_vsi' that
can be higher. Fix this loop.
Fixes: 69129dc39fac ("i40e: Modify Tx disable wait flow in case of DCB reconfiguration")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6e7fd473abfd..7a416e923b36 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5360,7 +5360,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf)
{
int v, ret = 0;
- for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+ for (v = 0; v < pf->num_alloc_vsi; v++) {
if (pf->vsi[v]) {
ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]);
if (ret)
From 343bb39e1f25a73a38a03d98ca383495c0ed6e92 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Thu, 30 Nov 2023 20:31:34 +0100
Subject: [PATCH 489/637] i40e: Fix wrong mask used during DCB config
Mask used for clearing PRTDCB_RETSTCC register in function
i40e_dcb_hw_rx_ets_bw_config() is incorrect as there is used
define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT instead of define
I40E_PRTDCB_RETSTCC_ETSTC_MASK.
The PRTDCB_RETSTCC register is used to configure whether ETS
or strict priority is used as TSA in Rx for particular TC.
In practice it means that once the register is set to use ETS
as TSA then it is not possible to switch back to strict priority
without CoreR reset.
Fix the value in the clearing mask.
Fixes: 90bc8e003be2 ("i40e: Add hardware configuration for software based DCB")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_dcb.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 9d88ed6105fd..8db1eb0c1768 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1523,7 +1523,7 @@ void i40e_dcb_hw_rx_ets_bw_config(struct i40e_hw *hw, u8 *bw_share,
reg = rd32(hw, I40E_PRTDCB_RETSTCC(i));
reg &= ~(I40E_PRTDCB_RETSTCC_BWSHARE_MASK |
I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK |
- I40E_PRTDCB_RETSTCC_ETSTC_SHIFT);
+ I40E_PRTDCB_RETSTCC_ETSTC_MASK);
reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_BWSHARE_MASK,
bw_share[i]);
reg |= FIELD_PREP(I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK,
From 89a373e9131d4200038a0ef232dad80212209de0 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 6 Feb 2024 13:41:31 +0100
Subject: [PATCH 490/637] i40e: avoid double calling i40e_pf_rxq_wait()
Currently, when interface is being brought down and
i40e_vsi_stop_rings() is called, i40e_pf_rxq_wait() is called two times,
which is wrong. To showcase this scenario, simplified call stack looks
as follows:
i40e_vsi_stop_rings()
i40e_control wait rx_q()
i40e_control_rx_q()
i40e_pf_rxq_wait()
i40e_vsi_wait_queues_disabled()
i40e_pf_rxq_wait() // redundant call
To fix this, let us s/i40e_control_wait_rx_q/i40e_control_rx_q within
i40e_vsi_stop_rings().
Fixes: 65662a8dcdd0 ("i40e: Fix logic of disabling queues")
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 12 +++---------
1 file changed, 3 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7a416e923b36..06078c4d54e8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4926,7 +4926,7 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
- int pf_q, err, q_end;
+ int pf_q, q_end;
/* When port TX is suspended, don't wait */
if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
@@ -4936,16 +4936,10 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
- for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) {
- err = i40e_control_wait_rx_q(pf, pf_q, false);
- if (err)
- dev_info(&pf->pdev->dev,
- "VSI seid %d Rx ring %d disable timeout\n",
- vsi->seid, pf_q);
- }
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ i40e_control_rx_q(pf, pf_q, false);
msleep(I40E_DISABLE_TX_GAP_MSEC);
- pf_q = vsi->base_queue;
for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
From 6ed8187bb36c14f5ea91be0bf20117379df2d25a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 6 Feb 2024 13:41:32 +0100
Subject: [PATCH 491/637] i40e: take into account XDP Tx queues when stopping
rings
Seth reported that on his side XDP traffic can not survive a round of
down/up against i40e interface. Dmesg output was telling us that we were
not able to disable the very first XDP ring. That was due to the fact
that in i40e_vsi_stop_rings() in a pre-work that is done before calling
i40e_vsi_wait_queues_disabled(), XDP Tx queues were not taken into the
account.
To fix this, let us distinguish between Rx and Tx queue boundaries and
take into the account XDP queues for Tx side.
Reported-by: Seth Forshee <sforshee@kernel.org>
Closes: https://lore.kernel.org/netdev/ZbkE7Ep1N1Ou17sA@do-x1extreme/
Fixes: 65662a8dcdd0 ("i40e: Fix logic of disabling queues")
Tested-by: Seth Forshee <sforshee@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 06078c4d54e8..54eb55464e31 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4926,21 +4926,23 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
- int pf_q, q_end;
+ u32 pf_q, tx_q_end, rx_q_end;
/* When port TX is suspended, don't wait */
if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
return i40e_vsi_stop_rings_no_wait(vsi);
- q_end = vsi->base_queue + vsi->num_queue_pairs;
- for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
- i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
+ tx_q_end = vsi->base_queue +
+ vsi->alloc_queue_pairs * (i40e_enabled_xdp_vsi(vsi) ? 2 : 1);
+ for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
+ i40e_pre_tx_queue_cfg(&pf->hw, pf_q, false);
- for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ rx_q_end = vsi->base_queue + vsi->num_queue_pairs;
+ for (pf_q = vsi->base_queue; pf_q < rx_q_end; pf_q++)
i40e_control_rx_q(pf, pf_q, false);
msleep(I40E_DISABLE_TX_GAP_MSEC);
- for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ for (pf_q = vsi->base_queue; pf_q < tx_q_end; pf_q++)
wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
i40e_vsi_wait_queues_disabled(vsi);
From 1692b9775e745f84b69dc8ad0075b0855a43db4e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 8 Feb 2024 09:48:27 +0000
Subject: [PATCH 492/637] net: stmmac: xgmac: use #define for string constants
The cited commit introduces and uses the string constants dpp_tx_err and
dpp_rx_err. These are assigned to constant fields of the array
dwxgmac3_error_desc.
It has been reported that on GCC 6 and 7.5.0 this results in warnings
such as:
.../dwxgmac2_core.c:836:20: error: initialiser element is not constant
{ true, "TDPES0", dpp_tx_err },
I have been able to reproduce this using: GCC 7.5.0, 8.4.0, 9.4.0 and 10.5.0.
But not GCC 13.2.0.
So it seems this effects older compilers but not newer ones.
As Jon points out in his report, the minimum compiler supported by
the kernel is GCC 5.1, so it does seem that this ought to be fixed.
It is not clear to me what combination of 'const', if any, would address
this problem. So this patch takes of using #defines for the string
constants
Compile tested only.
Fixes: 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Closes: https://lore.kernel.org/netdev/c25eb595-8d91-40ea-9f52-efa15ebafdbc@nvidia.com/
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202402081135.lAxxBXHk-lkp@intel.com/
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240208-xgmac-const-v1-1-e69a1eeabfc8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../ethernet/stmicro/stmmac/dwxgmac2_core.c | 69 ++++++++++---------
1 file changed, 35 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 323c57f03c93..1af2f89a0504 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -830,41 +830,42 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
};
-static const char * const dpp_rx_err = "Read Rx Descriptor Parity checker Error";
-static const char * const dpp_tx_err = "Read Tx Descriptor Parity checker Error";
+#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error"
+#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error"
+
static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
- { true, "TDPES0", dpp_tx_err },
- { true, "TDPES1", dpp_tx_err },
- { true, "TDPES2", dpp_tx_err },
- { true, "TDPES3", dpp_tx_err },
- { true, "TDPES4", dpp_tx_err },
- { true, "TDPES5", dpp_tx_err },
- { true, "TDPES6", dpp_tx_err },
- { true, "TDPES7", dpp_tx_err },
- { true, "TDPES8", dpp_tx_err },
- { true, "TDPES9", dpp_tx_err },
- { true, "TDPES10", dpp_tx_err },
- { true, "TDPES11", dpp_tx_err },
- { true, "TDPES12", dpp_tx_err },
- { true, "TDPES13", dpp_tx_err },
- { true, "TDPES14", dpp_tx_err },
- { true, "TDPES15", dpp_tx_err },
- { true, "RDPES0", dpp_rx_err },
- { true, "RDPES1", dpp_rx_err },
- { true, "RDPES2", dpp_rx_err },
- { true, "RDPES3", dpp_rx_err },
- { true, "RDPES4", dpp_rx_err },
- { true, "RDPES5", dpp_rx_err },
- { true, "RDPES6", dpp_rx_err },
- { true, "RDPES7", dpp_rx_err },
- { true, "RDPES8", dpp_rx_err },
- { true, "RDPES9", dpp_rx_err },
- { true, "RDPES10", dpp_rx_err },
- { true, "RDPES11", dpp_rx_err },
- { true, "RDPES12", dpp_rx_err },
- { true, "RDPES13", dpp_rx_err },
- { true, "RDPES14", dpp_rx_err },
- { true, "RDPES15", dpp_rx_err },
+ { true, "TDPES0", DPP_TX_ERR },
+ { true, "TDPES1", DPP_TX_ERR },
+ { true, "TDPES2", DPP_TX_ERR },
+ { true, "TDPES3", DPP_TX_ERR },
+ { true, "TDPES4", DPP_TX_ERR },
+ { true, "TDPES5", DPP_TX_ERR },
+ { true, "TDPES6", DPP_TX_ERR },
+ { true, "TDPES7", DPP_TX_ERR },
+ { true, "TDPES8", DPP_TX_ERR },
+ { true, "TDPES9", DPP_TX_ERR },
+ { true, "TDPES10", DPP_TX_ERR },
+ { true, "TDPES11", DPP_TX_ERR },
+ { true, "TDPES12", DPP_TX_ERR },
+ { true, "TDPES13", DPP_TX_ERR },
+ { true, "TDPES14", DPP_TX_ERR },
+ { true, "TDPES15", DPP_TX_ERR },
+ { true, "RDPES0", DPP_RX_ERR },
+ { true, "RDPES1", DPP_RX_ERR },
+ { true, "RDPES2", DPP_RX_ERR },
+ { true, "RDPES3", DPP_RX_ERR },
+ { true, "RDPES4", DPP_RX_ERR },
+ { true, "RDPES5", DPP_RX_ERR },
+ { true, "RDPES6", DPP_RX_ERR },
+ { true, "RDPES7", DPP_RX_ERR },
+ { true, "RDPES8", DPP_RX_ERR },
+ { true, "RDPES9", DPP_RX_ERR },
+ { true, "RDPES10", DPP_RX_ERR },
+ { true, "RDPES11", DPP_RX_ERR },
+ { true, "RDPES12", DPP_RX_ERR },
+ { true, "RDPES13", DPP_RX_ERR },
+ { true, "RDPES14", DPP_RX_ERR },
+ { true, "RDPES15", DPP_RX_ERR },
};
static void dwxgmac3_handle_dma_err(struct net_device *ndev,
From 2f74258d997c8b93627041d94daa265b5f0d1b4d Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 9 Feb 2024 16:13:07 -0800
Subject: [PATCH 493/637] ionic: minimal work with 0 budget
We should be doing as little as possible besides freeing Tx
space when our napi routines are called with budget of 0, so
jump out before doing anything besides Tx cleaning.
See commit afbed3f74830 ("net/mlx5e: do as little as possible in napi poll when budget is 0")
for more info.
Fixes: fe8c30b50835 ("ionic: separate interrupt for Tx and Rx")
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240210001307.48450-1-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 54cd96b035d6..6f4776759863 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -579,6 +579,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
work_done = ionic_cq_service(cq, budget,
ionic_tx_service, NULL, NULL);
+ if (unlikely(!budget))
+ return budget;
+
if (work_done < budget && napi_complete_done(napi, work_done)) {
ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR);
flags |= IONIC_INTR_CRED_UNMASK;
@@ -607,6 +610,9 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
u32 work_done = 0;
u32 flags = 0;
+ if (unlikely(!budget))
+ return budget;
+
lif = cq->bound_q->lif;
idev = &lif->ionic->idev;
@@ -656,6 +662,9 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT,
ionic_tx_service, NULL, NULL);
+ if (unlikely(!budget))
+ return budget;
+
rx_work_done = ionic_cq_service(rxcq, budget,
ionic_rx_service, NULL, NULL);
From 3e36031cc0540ca97b615cbb940331892cbd3d21 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 9 Feb 2024 16:20:02 -0800
Subject: [PATCH 494/637] pds_core: no health-thread in VF path
The VFs don't run the health thread, so don't try to
stop or restart the non-existent timer or work item.
Fixes: d9407ff11809 ("pds_core: Prevent health thread from running during reset/remove")
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://lore.kernel.org/r/20240210002002.49483-1-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/amd/pds_core/main.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index cdbf053b5376..0050c5894563 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -451,6 +451,9 @@ static void pdsc_remove(struct pci_dev *pdev)
static void pdsc_stop_health_thread(struct pdsc *pdsc)
{
+ if (pdsc->pdev->is_virtfn)
+ return;
+
timer_shutdown_sync(&pdsc->wdtimer);
if (pdsc->health_work.func)
cancel_work_sync(&pdsc->health_work);
@@ -458,6 +461,9 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc)
static void pdsc_restart_health_thread(struct pdsc *pdsc)
{
+ if (pdsc->pdev->is_virtfn)
+ return;
+
timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
mod_timer(&pdsc->wdtimer, jiffies + 1);
}
From 9f30831390ede02d9fcd54fd9ea5a585ab649f4a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 9 Feb 2024 18:12:48 +0000
Subject: [PATCH 495/637] net: add rcu safety to rtnl_prop_list_size()
rtnl_prop_list_size() can be called while alternative names
are added or removed concurrently.
if_nlmsg_size() / rtnl_calcit() can indeed be called
without RTNL held.
Use explicit RCU protection to avoid UAF.
Fixes: 88f4fb0c7496 ("net: rtnetlink: put alternative names to getlink message")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20240209181248.96637-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/core/dev.c | 2 +-
net/core/rtnetlink.c | 15 +++++++++------
2 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 9bb792cecc16..73a021973007 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
return -ENOMEM;
netdev_name_node_add(net, name_node);
/* The node that holds dev->name acts as a head of per-device list. */
- list_add_tail(&name_node->list, &dev->name_node->list);
+ list_add_tail_rcu(&name_node->list, &dev->name_node->list);
return 0;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f6f29eb03ec2..9c4f427f3a50 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void)
static size_t rtnl_prop_list_size(const struct net_device *dev)
{
struct netdev_name_node *name_node;
- size_t size;
+ unsigned int cnt = 0;
- if (list_empty(&dev->name_node->list))
+ rcu_read_lock();
+ list_for_each_entry_rcu(name_node, &dev->name_node->list, list)
+ cnt++;
+ rcu_read_unlock();
+
+ if (!cnt)
return 0;
- size = nla_total_size(0);
- list_for_each_entry(name_node, &dev->name_node->list, list)
- size += nla_total_size(ALTIFNAMSIZ);
- return size;
+
+ return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ);
}
static size_t rtnl_proto_down_size(const struct net_device *dev)
From 4cbec7e89a416294c46e71c967b57b9119fe0054 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Fri, 9 Feb 2024 15:52:47 -0600
Subject: [PATCH 496/637] scsi: target: Fix unmap setup during configuration
This issue was found and also debugged by Carl Lei <me@xecycle.info>.
If the device is not enabled, iblock/file will have not setup their
se_device to bdev/file mappings. If a user tries to config the unmap
settings at this time, we will then crash trying to access a NULL pointer
where the bdev/file should be.
This patch adds a check to make sure the device is configured before
we try to call the configure_unmap callout.
Fixes: 34bd1dcacf0d ("scsi: target: Detect UNMAP support post configuration")
Reported-by: Carl Lei <me@xecycle.info>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20240209215247.5213-1-michael.christie@oracle.com
Reviewed-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/target/target_core_configfs.c | 48 ++++++++++++++++++---------
1 file changed, 32 insertions(+), 16 deletions(-)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index a5f58988130a..c1fbcdd16182 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -759,6 +759,29 @@ static ssize_t emulate_tas_store(struct config_item *item,
return count;
}
+static int target_try_configure_unmap(struct se_device *dev,
+ const char *config_opt)
+{
+ if (!dev->transport->configure_unmap) {
+ pr_err("Generic Block Discard not supported\n");
+ return -ENOSYS;
+ }
+
+ if (!target_dev_configured(dev)) {
+ pr_err("Generic Block Discard setup for %s requires device to be configured\n",
+ config_opt);
+ return -ENODEV;
+ }
+
+ if (!dev->transport->configure_unmap(dev)) {
+ pr_err("Generic Block Discard setup for %s failed\n",
+ config_opt);
+ return -ENOSYS;
+ }
+
+ return 0;
+}
+
static ssize_t emulate_tpu_store(struct config_item *item,
const char *page, size_t count)
{
@@ -776,11 +799,9 @@ static ssize_t emulate_tpu_store(struct config_item *item,
* Discard supported is detected iblock_create_virtdevice().
*/
if (flag && !da->max_unmap_block_desc_count) {
- if (!dev->transport->configure_unmap ||
- !dev->transport->configure_unmap(dev)) {
- pr_err("Generic Block Discard not supported\n");
- return -ENOSYS;
- }
+ ret = target_try_configure_unmap(dev, "emulate_tpu");
+ if (ret)
+ return ret;
}
da->emulate_tpu = flag;
@@ -806,11 +827,9 @@ static ssize_t emulate_tpws_store(struct config_item *item,
* Discard supported is detected iblock_create_virtdevice().
*/
if (flag && !da->max_unmap_block_desc_count) {
- if (!dev->transport->configure_unmap ||
- !dev->transport->configure_unmap(dev)) {
- pr_err("Generic Block Discard not supported\n");
- return -ENOSYS;
- }
+ ret = target_try_configure_unmap(dev, "emulate_tpws");
+ if (ret)
+ return ret;
}
da->emulate_tpws = flag;
@@ -1022,12 +1041,9 @@ static ssize_t unmap_zeroes_data_store(struct config_item *item,
* Discard supported is detected iblock_configure_device().
*/
if (flag && !da->max_unmap_block_desc_count) {
- if (!dev->transport->configure_unmap ||
- !dev->transport->configure_unmap(dev)) {
- pr_err("dev[%p]: Thin Provisioning LBPRZ will not be set because max_unmap_block_desc_count is zero\n",
- da->da_dev);
- return -ENOSYS;
- }
+ ret = target_try_configure_unmap(dev, "unmap_zeroes_data");
+ if (ret)
+ return ret;
}
da->unmap_zeroes_data = flag;
pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
From 977fe773dcc7098d8eaf4ee6382cb51e13e784cb Mon Sep 17 00:00:00 2001
From: Lee Duncan <lduncan@suse.com>
Date: Fri, 9 Feb 2024 10:07:34 -0800
Subject: [PATCH 497/637] scsi: Revert "scsi: fcoe: Fix potential deadlock on
&fip->ctlr_lock"
This reverts commit 1a1975551943f681772720f639ff42fbaa746212.
This commit causes interrupts to be lost for FCoE devices, since it changed
sping locks from "bh" to "irqsave".
Instead, a work queue should be used, and will be addressed in a separate
commit.
Fixes: 1a1975551943 ("scsi: fcoe: Fix potential deadlock on &fip->ctlr_lock")
Signed-off-by: Lee Duncan <lduncan@suse.com>
Link: https://lore.kernel.org/r/c578cdcd46b60470535c4c4a953e6a1feca0dffd.1707500786.git.lduncan@suse.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/fcoe/fcoe_ctlr.c | 20 ++++++++------------
1 file changed, 8 insertions(+), 12 deletions(-)
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 19eee108db02..5c8d1ba3f8f3 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip)
{
struct fcoe_fcf *sel;
struct fcoe_fcf *fcf;
- unsigned long flags;
mutex_lock(&fip->ctlr_mutex);
- spin_lock_irqsave(&fip->ctlr_lock, flags);
+ spin_lock_bh(&fip->ctlr_lock);
kfree_skb(fip->flogi_req);
fip->flogi_req = NULL;
list_for_each_entry(fcf, &fip->fcfs, list)
fcf->flogi_sent = 0;
- spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+ spin_unlock_bh(&fip->ctlr_lock);
sel = fip->sel_fcf;
if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr))
@@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
{
struct fc_frame *fp;
struct fc_frame_header *fh;
- unsigned long flags;
u16 old_xid;
u8 op;
u8 mac[ETH_ALEN];
@@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
op = FIP_DT_FLOGI;
if (fip->mode == FIP_MODE_VN2VN)
break;
- spin_lock_irqsave(&fip->ctlr_lock, flags);
+ spin_lock_bh(&fip->ctlr_lock);
kfree_skb(fip->flogi_req);
fip->flogi_req = skb;
fip->flogi_req_send = 1;
- spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+ spin_unlock_bh(&fip->ctlr_lock);
schedule_work(&fip->timer_work);
return -EINPROGRESS;
case ELS_FDISC:
@@ -1707,11 +1705,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip)
static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
{
struct fcoe_fcf *fcf;
- unsigned long flags;
int error;
mutex_lock(&fip->ctlr_mutex);
- spin_lock_irqsave(&fip->ctlr_lock, flags);
+ spin_lock_bh(&fip->ctlr_lock);
LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n");
fcf = fcoe_ctlr_select(fip);
if (!fcf || fcf->flogi_sent) {
@@ -1722,7 +1719,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
fcoe_ctlr_solicit(fip, NULL);
error = fcoe_ctlr_flogi_send_locked(fip);
}
- spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+ spin_unlock_bh(&fip->ctlr_lock);
mutex_unlock(&fip->ctlr_mutex);
return error;
}
@@ -1739,9 +1736,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip)
static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
{
struct fcoe_fcf *fcf;
- unsigned long flags;
- spin_lock_irqsave(&fip->ctlr_lock, flags);
+ spin_lock_bh(&fip->ctlr_lock);
fcf = fip->sel_fcf;
if (!fcf || !fip->flogi_req_send)
goto unlock;
@@ -1768,7 +1764,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip)
} else /* XXX */
LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n");
unlock:
- spin_unlock_irqrestore(&fip->ctlr_lock, flags);
+ spin_unlock_bh(&fip->ctlr_lock);
}
/**
From 379a58caa19930e010b7efa1c1f3b9411d3d2ca3 Mon Sep 17 00:00:00 2001
From: Lee Duncan <lduncan@suse.com>
Date: Fri, 9 Feb 2024 10:07:35 -0800
Subject: [PATCH 498/637] scsi: fnic: Move fnic_fnic_flush_tx() to a work queue
Rather than call 'fnic_flush_tx()' from interrupt context we should be
moving it onto a work queue to avoid any locking issues.
Fixes: 1a1975551943 ("scsi: fcoe: Fix potential deadlock on &fip->ctlr_lock")
Co-developed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Lee Duncan <lduncan@suse.com>
Link: https://lore.kernel.org/r/ce5ffa5d0ff82c2b2e283b3b4bff23291d49b05c.1707500786.git.lduncan@suse.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/fnic/fnic.h | 3 ++-
drivers/scsi/fnic/fnic_fcs.c | 5 +++--
drivers/scsi/fnic/fnic_main.c | 1 +
drivers/scsi/fnic/fnic_scsi.c | 4 ++--
4 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 2074937c05bc..ce73f08ee889 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -305,6 +305,7 @@ struct fnic {
unsigned int copy_wq_base;
struct work_struct link_work;
struct work_struct frame_work;
+ struct work_struct flush_work;
struct sk_buff_head frame_queue;
struct sk_buff_head tx_queue;
@@ -363,7 +364,7 @@ void fnic_handle_event(struct work_struct *work);
int fnic_rq_cmpl_handler(struct fnic *fnic, int);
int fnic_alloc_rq_frame(struct vnic_rq *rq);
void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
-void fnic_flush_tx(struct fnic *);
+void fnic_flush_tx(struct work_struct *work);
void fnic_eth_send(struct fcoe_ctlr *, struct sk_buff *skb);
void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *);
void fnic_update_mac(struct fc_lport *, u8 *new);
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 5e312a55cc7d..a08293b2ad9f 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -1182,7 +1182,7 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
/**
* fnic_flush_tx() - send queued frames.
- * @fnic: fnic device
+ * @work: pointer to work element
*
* Send frames that were waiting to go out in FC or Ethernet mode.
* Whenever changing modes we purge queued frames, so these frames should
@@ -1190,8 +1190,9 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
*
* Called without fnic_lock held.
*/
-void fnic_flush_tx(struct fnic *fnic)
+void fnic_flush_tx(struct work_struct *work)
{
+ struct fnic *fnic = container_of(work, struct fnic, flush_work);
struct sk_buff *skb;
struct fc_frame *fp;
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 5ed1d897311a..29eead383eb9 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -830,6 +830,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
spin_lock_init(&fnic->vlans_lock);
INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame);
INIT_WORK(&fnic->event_work, fnic_handle_event);
+ INIT_WORK(&fnic->flush_work, fnic_flush_tx);
skb_queue_head_init(&fnic->fip_frame_queue);
INIT_LIST_HEAD(&fnic->evlist);
INIT_LIST_HEAD(&fnic->vlans);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 8d7fc5284293..fc4cee91b175 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -680,7 +680,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
spin_unlock_irqrestore(&fnic->fnic_lock, flags);
- fnic_flush_tx(fnic);
+ queue_work(fnic_event_queue, &fnic->flush_work);
reset_cmpl_handler_end:
fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET);
@@ -736,7 +736,7 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic,
}
spin_unlock_irqrestore(&fnic->fnic_lock, flags);
- fnic_flush_tx(fnic);
+ queue_work(fnic_event_queue, &fnic->flush_work);
queue_work(fnic_event_queue, &fnic->frame_work);
} else {
spin_unlock_irqrestore(&fnic->fnic_lock, flags);
From b2c52b8c128ea07f1632c516cec0d72cb63b5599 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Sun, 28 Jan 2024 17:50:43 +0100
Subject: [PATCH 499/637] xen/privcmd: Use memdup_array_user() in alloc_ioreq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
* The function “memdup_array_user” was added with the
commit 313ebe47d75558511aa1237b6e35c663b5c0ec6f ("string.h: add
array-wrappers for (v)memdup_user()").
Thus use it accordingly.
This issue was detected by using the Coccinelle software.
* Delete a label which became unnecessary with this refactoring.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/41e333f7-1f3a-41b6-a121-a3c0ae54e36f@web.de
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/privcmd.c | 15 +++++----------
1 file changed, 5 insertions(+), 10 deletions(-)
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 35b6e306026a..67dfa4778864 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1223,18 +1223,13 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
kioreq->ioreq = (struct ioreq *)(page_to_virt(pages[0]));
mmap_write_unlock(mm);
- size = sizeof(*ports) * kioreq->vcpus;
- ports = kzalloc(size, GFP_KERNEL);
- if (!ports) {
- ret = -ENOMEM;
+ ports = memdup_array_user(u64_to_user_ptr(ioeventfd->ports),
+ kioreq->vcpus, sizeof(*ports));
+ if (IS_ERR(ports)) {
+ ret = PTR_ERR(ports);
goto error_kfree;
}
- if (copy_from_user(ports, u64_to_user_ptr(ioeventfd->ports), size)) {
- ret = -EFAULT;
- goto error_kfree_ports;
- }
-
for (i = 0; i < kioreq->vcpus; i++) {
kioreq->ports[i].vcpu = i;
kioreq->ports[i].port = ports[i];
@@ -1256,7 +1251,7 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd)
error_unbind:
while (--i >= 0)
unbind_from_irqhandler(irq_from_evtchn(ports[i]), &kioreq->ports[i]);
-error_kfree_ports:
+
kfree(ports);
error_kfree:
kfree(kioreq);
From 2528dcbea94496f080aad9311327baedc11831d7 Mon Sep 17 00:00:00 2001
From: "Ricardo B. Marliere" <ricardo@marliere.net>
Date: Sat, 3 Feb 2024 15:53:37 -0300
Subject: [PATCH 500/637] xen: pcpu: make xen_pcpu_subsys const
Now that the driver core can properly handle constant struct bus_type,
move the xen_pcpu_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ricardo B. Marliere <ricardo@marliere.net>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20240203-bus_cleanup-xen-v1-1-c2f5fe89ed95@marliere.net
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/pcpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index 508655273145..c63f317e3df3 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -65,7 +65,7 @@ struct pcpu {
uint32_t flags;
};
-static struct bus_type xen_pcpu_subsys = {
+static const struct bus_type xen_pcpu_subsys = {
.name = "xen_cpu",
.dev_name = "xen_cpu",
};
From b0f2f82c9c16427722b8782371c2efe82b1f815c Mon Sep 17 00:00:00 2001
From: "Ricardo B. Marliere" <ricardo@marliere.net>
Date: Sat, 3 Feb 2024 15:53:38 -0300
Subject: [PATCH 501/637] xen: balloon: make balloon_subsys const
Now that the driver core can properly handle constant struct bus_type,
move the balloon_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ricardo B. Marliere <ricardo@marliere.net>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20240203-bus_cleanup-xen-v1-2-c2f5fe89ed95@marliere.net
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/xen-balloon.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index 8cd583db20b1..b293d7652f15 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -237,7 +237,7 @@ static const struct attribute_group *balloon_groups[] = {
NULL
};
-static struct bus_type balloon_subsys = {
+static const struct bus_type balloon_subsys = {
.name = BALLOON_CLASS_NAME,
.dev_name = BALLOON_CLASS_NAME,
};
From bf5802238dc181b1f7375d358af1d01cd72d1c11 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 6 Feb 2024 09:03:24 -0800
Subject: [PATCH 502/637] xen/gntalloc: Replace UAPI 1-element array
Without changing the structure size (since it is UAPI), add a proper
flexible array member, and reference it in the kernel so that it will
not be trip the array-bounds sanitizer[1].
Link: https://github.com/KSPP/linux/issues/113 [1]
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: xen-devel@lists.xenproject.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20240206170320.work.437-kees@kernel.org
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/gntalloc.c | 2 +-
include/uapi/xen/gntalloc.h | 5 ++++-
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index 26ffb8755ffb..f93f73ecefee 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
rc = -EFAULT;
goto out_free;
}
- if (copy_to_user(arg->gref_ids, gref_ids,
+ if (copy_to_user(arg->gref_ids_flex, gref_ids,
sizeof(gref_ids[0]) * op.count)) {
rc = -EFAULT;
goto out_free;
diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h
index 48d2790ef928..3109282672f3 100644
--- a/include/uapi/xen/gntalloc.h
+++ b/include/uapi/xen/gntalloc.h
@@ -31,7 +31,10 @@ struct ioctl_gntalloc_alloc_gref {
__u64 index;
/* The grant references of the newly created grant, one per page */
/* Variable size, depending on count */
- __u32 gref_ids[1];
+ union {
+ __u32 gref_ids[1];
+ __DECLARE_FLEX_ARRAY(__u32, gref_ids_flex);
+ };
};
#define GNTALLOC_FLAG_WRITABLE 1
From b0344d6854d25a8b3b901c778b1728885dd99007 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Fri, 9 Feb 2024 17:24:49 -0800
Subject: [PATCH 503/637] irqchip/irq-brcmstb-l2: Add write memory barrier
before exit
It was observed on Broadcom devices that use GIC v3 architecture L1
interrupt controllers as the parent of brcmstb-l2 interrupt controllers
that the deactivation of the parent interrupt could happen before the
brcmstb-l2 deasserted its output. This would lead the GIC to reactivate the
interrupt only to find that no L2 interrupt was pending. The result was a
spurious interrupt invoking handle_bad_irq() with its associated
messaging. While this did not create a functional problem it is a waste of
cycles.
The hazard exists because the memory mapped bus writes to the brcmstb-l2
registers are buffered and the GIC v3 architecture uses a very efficient
system register write to deactivate the interrupt.
Add a write memory barrier prior to invoking chained_irq_exit() to
introduce a dsb(st) on those systems to ensure the system register write
cannot be executed until the memory mapped writes are visible to the
system.
[ florian: Added Fixes tag ]
Fixes: 7f646e92766e ("irqchip: brcmstb-l2: Add Broadcom Set Top Box Level-2 interrupt controller")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240210012449.3009125-1-florian.fainelli@broadcom.com
---
drivers/irqchip/irq-brcmstb-l2.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 5559c943f03f..2b0b3175cea0 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -2,7 +2,7 @@
/*
* Generic Broadcom Set Top Box Level 2 Interrupt controller driver
*
- * Copyright (C) 2014-2017 Broadcom
+ * Copyright (C) 2014-2024 Broadcom
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -112,6 +112,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
generic_handle_domain_irq(b->domain, irq);
} while (status);
out:
+ /* Don't ack parent before all device writes are done */
+ wmb();
+
chained_irq_exit(chip, desc);
}
From fa765c4b4aed2d64266b694520ecb025c862c5a9 Mon Sep 17 00:00:00 2001
From: Maximilian Heyne <mheyne@amazon.de>
Date: Wed, 24 Jan 2024 16:31:28 +0000
Subject: [PATCH 504/637] xen/events: close evtchn after mapping cleanup
shutdown_pirq and startup_pirq are not taking the
irq_mapping_update_lock because they can't due to lock inversion. Both
are called with the irq_desc->lock being taking. The lock order,
however, is first irq_mapping_update_lock and then irq_desc->lock.
This opens multiple races:
- shutdown_pirq can be interrupted by a function that allocates an event
channel:
CPU0 CPU1
shutdown_pirq {
xen_evtchn_close(e)
__startup_pirq {
EVTCHNOP_bind_pirq
-> returns just freed evtchn e
set_evtchn_to_irq(e, irq)
}
xen_irq_info_cleanup() {
set_evtchn_to_irq(e, -1)
}
}
Assume here event channel e refers here to the same event channel
number.
After this race the evtchn_to_irq mapping for e is invalid (-1).
- __startup_pirq races with __unbind_from_irq in a similar way. Because
__startup_pirq doesn't take irq_mapping_update_lock it can grab the
evtchn that __unbind_from_irq is currently freeing and cleaning up. In
this case even though the event channel is allocated, its mapping can
be unset in evtchn_to_irq.
The fix is to first cleanup the mappings and then close the event
channel. In this way, when an event channel gets allocated it's
potential previous evtchn_to_irq mappings are guaranteed to be unset already.
This is also the reverse order of the allocation where first the event
channel is allocated and then the mappings are setup.
On a 5.10 kernel prior to commit 3fcdaf3d7634 ("xen/events: modify internal
[un]bind interfaces"), we hit a BUG like the following during probing of NVMe
devices. The issue is that during nvme_setup_io_queues, pci_free_irq
is called for every device which results in a call to shutdown_pirq.
With many nvme devices it's therefore likely to hit this race during
boot because there will be multiple calls to shutdown_pirq and
startup_pirq are running potentially in parallel.
------------[ cut here ]------------
blkfront: xvda: barrier or flush: disabled; persistent grants: enabled; indirect descriptors: enabled; bounce buffer: enabled
kernel BUG at drivers/xen/events/events_base.c:499!
invalid opcode: 0000 [#1] SMP PTI
CPU: 44 PID: 375 Comm: kworker/u257:23 Not tainted 5.10.201-191.748.amzn2.x86_64 #1
Hardware name: Xen HVM domU, BIOS 4.11.amazon 08/24/2006
Workqueue: nvme-reset-wq nvme_reset_work
RIP: 0010:bind_evtchn_to_cpu+0xdf/0xf0
Code: 5d 41 5e c3 cc cc cc cc 44 89 f7 e8 2b 55 ad ff 49 89 c5 48 85 c0 0f 84 64 ff ff ff 4c 8b 68 30 41 83 fe ff 0f 85 60 ff ff ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00
RSP: 0000:ffffc9000d533b08 EFLAGS: 00010046
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000006
RDX: 0000000000000028 RSI: 00000000ffffffff RDI: 00000000ffffffff
RBP: ffff888107419680 R08: 0000000000000000 R09: ffffffff82d72b00
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000001ed
R13: 0000000000000000 R14: 00000000ffffffff R15: 0000000000000002
FS: 0000000000000000(0000) GS:ffff88bc8b500000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000002610001 CR4: 00000000001706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
? show_trace_log_lvl+0x1c1/0x2d9
? show_trace_log_lvl+0x1c1/0x2d9
? set_affinity_irq+0xdc/0x1c0
? __die_body.cold+0x8/0xd
? die+0x2b/0x50
? do_trap+0x90/0x110
? bind_evtchn_to_cpu+0xdf/0xf0
? do_error_trap+0x65/0x80
? bind_evtchn_to_cpu+0xdf/0xf0
? exc_invalid_op+0x4e/0x70
? bind_evtchn_to_cpu+0xdf/0xf0
? asm_exc_invalid_op+0x12/0x20
? bind_evtchn_to_cpu+0xdf/0xf0
? bind_evtchn_to_cpu+0xc5/0xf0
set_affinity_irq+0xdc/0x1c0
irq_do_set_affinity+0x1d7/0x1f0
irq_setup_affinity+0xd6/0x1a0
irq_startup+0x8a/0xf0
__setup_irq+0x639/0x6d0
? nvme_suspend+0x150/0x150
request_threaded_irq+0x10c/0x180
? nvme_suspend+0x150/0x150
pci_request_irq+0xa8/0xf0
? __blk_mq_free_request+0x74/0xa0
queue_request_irq+0x6f/0x80
nvme_create_queue+0x1af/0x200
nvme_create_io_queues+0xbd/0xf0
nvme_setup_io_queues+0x246/0x320
? nvme_irq_check+0x30/0x30
nvme_reset_work+0x1c8/0x400
process_one_work+0x1b0/0x350
worker_thread+0x49/0x310
? process_one_work+0x350/0x350
kthread+0x11b/0x140
? __kthread_bind_mask+0x60/0x60
ret_from_fork+0x22/0x30
Modules linked in:
---[ end trace a11715de1eee1873 ]---
Fixes: d46a78b05c0e ("xen: implement pirq type event channels")
Cc: stable@vger.kernel.org
Co-debugged-by: Andrew Panyakin <apanyaki@amazon.com>
Signed-off-by: Maximilian Heyne <mheyne@amazon.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20240124163130.31324-1-mheyne@amazon.de
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/events/events_base.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index b8cfea7812d6..3b9f080109d7 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -923,8 +923,8 @@ static void shutdown_pirq(struct irq_data *data)
return;
do_mask(info, EVT_MASK_REASON_EXPLICIT);
- xen_evtchn_close(evtchn);
xen_irq_info_cleanup(info);
+ xen_evtchn_close(evtchn);
}
static void enable_pirq(struct irq_data *data)
@@ -956,6 +956,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
{
evtchn_port_t evtchn;
+ bool close_evtchn = false;
if (!info) {
xen_irq_free_desc(irq);
@@ -975,7 +976,7 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
struct xenbus_device *dev;
if (!info->is_static)
- xen_evtchn_close(evtchn);
+ close_evtchn = true;
switch (info->type) {
case IRQT_VIRQ:
@@ -995,6 +996,9 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq)
}
xen_irq_info_cleanup(info);
+
+ if (close_evtchn)
+ xen_evtchn_close(evtchn);
}
xen_free_irq(info);
From f1acf1ac84d2ae97b7889b87223c1064df850069 Mon Sep 17 00:00:00 2001
From: Allison Henderson <allison.henderson@oracle.com>
Date: Thu, 8 Feb 2024 19:28:54 -0700
Subject: [PATCH 505/637] net:rds: Fix possible deadlock in rds_message_put
Functions rds_still_queued and rds_clear_recv_queue lock a given socket
in order to safely iterate over the incoming rds messages. However
calling rds_inc_put while under this lock creates a potential deadlock.
rds_inc_put may eventually call rds_message_purge, which will lock
m_rs_lock. This is the incorrect locking order since m_rs_lock is
meant to be locked before the socket. To fix this, we move the message
item to a local list or variable that wont need rs_recv_lock protection.
Then we can safely call rds_inc_put on any item stored locally after
rs_recv_lock is released.
Fixes: bdbe6fbc6a2f ("RDS: recv.c")
Reported-by: syzbot+f9db6ff27b9bfdcfeca0@syzkaller.appspotmail.com
Reported-by: syzbot+dcd73ff9291e6d34b3ab@syzkaller.appspotmail.com
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://lore.kernel.org/r/20240209022854.200292-1-allison.henderson@oracle.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/rds/recv.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c71b923764fd..5627f80013f8 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -425,6 +425,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
struct sock *sk = rds_rs_to_sk(rs);
int ret = 0;
unsigned long flags;
+ struct rds_incoming *to_drop = NULL;
write_lock_irqsave(&rs->rs_recv_lock, flags);
if (!list_empty(&inc->i_item)) {
@@ -435,11 +436,14 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
list_del_init(&inc->i_item);
- rds_inc_put(inc);
+ to_drop = inc;
}
}
write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+ if (to_drop)
+ rds_inc_put(to_drop);
+
rdsdebug("inc %p rs %p still %d dropped %d\n", inc, rs, ret, drop);
return ret;
}
@@ -758,16 +762,21 @@ void rds_clear_recv_queue(struct rds_sock *rs)
struct sock *sk = rds_rs_to_sk(rs);
struct rds_incoming *inc, *tmp;
unsigned long flags;
+ LIST_HEAD(to_drop);
write_lock_irqsave(&rs->rs_recv_lock, flags);
list_for_each_entry_safe(inc, tmp, &rs->rs_recv_queue, i_item) {
rds_recv_rcvbuf_delta(rs, sk, inc->i_conn->c_lcong,
-be32_to_cpu(inc->i_hdr.h_len),
inc->i_hdr.h_dport);
+ list_move(&inc->i_item, &to_drop);
+ }
+ write_unlock_irqrestore(&rs->rs_recv_lock, flags);
+
+ list_for_each_entry_safe(inc, tmp, &to_drop, i_item) {
list_del_init(&inc->i_item);
rds_inc_put(inc);
}
- write_unlock_irqrestore(&rs->rs_recv_lock, flags);
}
/*
From f1c2765c6afcd1f71f76ed8c9bf94acedab4cecb Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Tue, 30 Jan 2024 16:27:20 +0800
Subject: [PATCH 506/637] irqchip/loongson-eiointc: Use correct struct type in
eiointc_domain_alloc()
eiointc_domain_alloc() uses struct eiointc, which is not defined, for a
pointer. Older compilers treat that as a forward declaration and due to
assignment of a void pointer there is no warning emitted. As the variable
is then handed in as a void pointer argument to irq_domain_set_info() the
code is functional.
Use struct eiointc_priv instead.
[ tglx: Rewrote changelog ]
Fixes: dd281e1a1a93 ("irqchip: Add Loongson Extended I/O interrupt controller support")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://lore.kernel.org/r/20240130082722.2912576-2-maobibo@loongson.cn
---
drivers/irqchip/irq-loongson-eiointc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c
index 1623cd779175..b3736bdd4b9f 100644
--- a/drivers/irqchip/irq-loongson-eiointc.c
+++ b/drivers/irqchip/irq-loongson-eiointc.c
@@ -241,7 +241,7 @@ static int eiointc_domain_alloc(struct irq_domain *domain, unsigned int virq,
int ret;
unsigned int i, type;
unsigned long hwirq = 0;
- struct eiointc *priv = domain->host_data;
+ struct eiointc_priv *priv = domain->host_data;
ret = irq_domain_translate_onecell(domain, arg, &hwirq, &type);
if (ret)
From 8ad032cc8c499af6f3289c796f411e8874b50fdb Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 1 Feb 2024 15:17:50 +0300
Subject: [PATCH 507/637] irqchip/qcom-mpm: Fix IS_ERR() vs NULL check in
qcom_mpm_init()
devm_ioremap() doesn't return error pointers, it returns NULL on error.
Update the check accordingly.
Fixes: 221b110d87c2 ("irqchip/qcom-mpm: Support passing a slice of SRAM as reg space")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Link: https://lore.kernel.org/r/22e1f4de-edce-4791-bd2d-2b2e98529492@moroto.mountain
---
drivers/irqchip/irq-qcom-mpm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index cda5838d2232..7942d8eb3d00 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -389,8 +389,8 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent)
/* Don't use devm_ioremap_resource, as we're accessing a shared region. */
priv->base = devm_ioremap(dev, res.start, resource_size(&res));
of_node_put(msgram_np);
- if (IS_ERR(priv->base))
- return PTR_ERR(priv->base);
+ if (!priv->base)
+ return -ENOMEM;
} else {
/* Otherwise, fall back to simple MMIO. */
priv->base = devm_platform_ioremap_resource(pdev, 0);
From 6ac86372102b477083db99a9af8246fb916271b5 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 25 Jan 2024 09:15:59 +0100
Subject: [PATCH 508/637] gpiolib: add gpiod_to_gpio_device() stub for !GPIOLIB
Add empty stub of gpiod_to_gpio_device() when GPIOLIB is not enabled.
Cc: <stable@vger.kernel.org>
Fixes: 370232d096e3 ("gpiolib: provide gpiod_to_gpio_device()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
include/linux/gpio/driver.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 9a5c6c76e653..012797e7106d 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -819,6 +819,12 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
return ERR_PTR(-ENODEV);
}
+static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc)
+{
+ WARN_ON(1);
+ return ERR_PTR(-ENODEV);
+}
+
static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
unsigned int offset)
{
From ebe0c15b135b1e4092c25b95d89e9a5899467499 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 25 Jan 2024 09:16:00 +0100
Subject: [PATCH 509/637] gpiolib: add gpio_device_get_base() stub for !GPIOLIB
Add empty stub of gpio_device_get_base() when GPIOLIB is not enabled.
Cc: <stable@vger.kernel.org>
Fixes: 8c85a102fc4e ("gpiolib: provide gpio_device_get_base()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
include/linux/gpio/driver.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 012797e7106d..c1df7698edb0 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -825,6 +825,12 @@ static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc)
return ERR_PTR(-ENODEV);
}
+static inline int gpio_device_get_base(struct gpio_device *gdev)
+{
+ WARN_ON(1);
+ return -ENODEV;
+}
+
static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
unsigned int offset)
{
From 2df8aa3cad407044f2febdbbdf220c6dae839c79 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 25 Jan 2024 09:16:01 +0100
Subject: [PATCH 510/637] gpiolib: add gpio_device_get_label() stub for
!GPIOLIB
Add empty stub of gpio_device_get_label() when GPIOLIB is not enabled.
Cc: <stable@vger.kernel.org>
Fixes: d1f7728259ef ("gpiolib: provide gpio_device_get_label()")
Suggested-by: kernel test robot <lkp@intel.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
include/linux/gpio/driver.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c1df7698edb0..7f75c9a51874 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -831,6 +831,12 @@ static inline int gpio_device_get_base(struct gpio_device *gdev)
return -ENODEV;
}
+static inline const char *gpio_device_get_label(struct gpio_device *gdev)
+{
+ WARN_ON(1);
+ return NULL;
+}
+
static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
unsigned int offset)
{
From 8929f95b2b587791a7dcd04cc91520194a76d3a6 Mon Sep 17 00:00:00 2001
From: Keqi Wang <wangkeqi_chris@163.com>
Date: Fri, 9 Feb 2024 17:16:59 +0800
Subject: [PATCH 511/637] connector/cn_proc: revert "connector: Fix
proc_event_num_listeners count not cleared"
This reverts commit c46bfba1337d ("connector: Fix proc_event_num_listeners
count not cleared").
It is not accurate to reset proc_event_num_listeners according to
cn_netlink_send_mult() return value -ESRCH.
In the case of stress-ng netlink-proc, -ESRCH will always be returned,
because netlink_broadcast_filtered will return -ESRCH,
which may cause stress-ng netlink-proc performance degradation.
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202401112259.b23a1567-oliver.sang@intel.com
Fixes: c46bfba1337d ("connector: Fix proc_event_num_listeners count not cleared")
Signed-off-by: Keqi Wang <wangkeqi_chris@163.com>
Link: https://lore.kernel.org/r/20240209091659.68723-1-wangkeqi_chris@163.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/connector/cn_proc.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 3d5e6d705fc6..44b19e696176 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg)
filter_data[1] = 0;
}
- if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
- cn_filter, (void *)filter_data) == -ESRCH)
- atomic_set(&proc_event_num_listeners, 0);
+ cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+ cn_filter, (void *)filter_data);
local_unlock(&local_event.lock);
}
From 902d6d013f75b68f31d208c6f3ff9cdca82648a7 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 13 Sep 2023 16:18:34 +0800
Subject: [PATCH 512/637] ceph: always queue a writeback when revoking the Fb
caps
In case there is 'Fw' dirty caps and 'CHECK_CAPS_FLUSH' is set we
will always ignore queue a writeback. Queue a writeback is very
important because it will block kclient flushing the snapcaps to
MDS and which will block MDS waiting for revoking the 'Fb' caps.
Link: https://tracker.ceph.com/issues/50223
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 48 ++++++++++++++++++++++++------------------------
1 file changed, 24 insertions(+), 24 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ad1f46c66fbf..bce3a840f15c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2156,6 +2156,30 @@ retry:
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
+ /* completed revocation? going down and there are no caps? */
+ if (revoking) {
+ if ((revoking & cap_used) == 0) {
+ doutc(cl, "completed revocation of %s\n",
+ ceph_cap_string(cap->implemented & ~cap->issued));
+ goto ack;
+ }
+
+ /*
+ * If the "i_wrbuffer_ref" was increased by mmap or generic
+ * cache write just before the ceph_check_caps() is called,
+ * the Fb capability revoking will fail this time. Then we
+ * must wait for the BDI's delayed work to flush the dirty
+ * pages and to release the "i_wrbuffer_ref", which will cost
+ * at most 5 seconds. That means the MDS needs to wait at
+ * most 5 seconds to finished the Fb capability's revocation.
+ *
+ * Let's queue a writeback for it.
+ */
+ if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
+ (revoking & CEPH_CAP_FILE_BUFFER))
+ queue_writeback = true;
+ }
+
if (cap == ci->i_auth_cap &&
(cap->issued & CEPH_CAP_FILE_WR)) {
/* request larger max_size from MDS? */
@@ -2183,30 +2207,6 @@ retry:
}
}
- /* completed revocation? going down and there are no caps? */
- if (revoking) {
- if ((revoking & cap_used) == 0) {
- doutc(cl, "completed revocation of %s\n",
- ceph_cap_string(cap->implemented & ~cap->issued));
- goto ack;
- }
-
- /*
- * If the "i_wrbuffer_ref" was increased by mmap or generic
- * cache write just before the ceph_check_caps() is called,
- * the Fb capability revoking will fail this time. Then we
- * must wait for the BDI's delayed work to flush the dirty
- * pages and to release the "i_wrbuffer_ref", which will cost
- * at most 5 seconds. That means the MDS needs to wait at
- * most 5 seconds to finished the Fb capability's revocation.
- *
- * Let's queue a writeback for it.
- */
- if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref &&
- (revoking & CEPH_CAP_FILE_BUFFER))
- queue_writeback = true;
- }
-
/* want more caps from mds? */
if (want & ~cap->mds_wanted) {
if (want & ~(cap->mds_wanted | cap->issued))
From dbc347ef7f0c53aa4a5383238a804d7ebbb0b5ca Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 14 Sep 2023 10:29:16 +0800
Subject: [PATCH 513/637] ceph: add ceph_cap_unlink_work to fire check_caps()
immediately
When unlinking a file the check caps could be delayed for more than
5 seconds, but in MDS side it maybe waiting for the clients to
release caps.
This will use the cap_wq work queue and a dedicated list to help
fire the check_caps() and dirty buffer flushing immediately.
Link: https://tracker.ceph.com/issues/50223
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Milind Changire <mchangir@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 17 +++++++++++++++-
fs/ceph/mds_client.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
fs/ceph/mds_client.h | 5 +++++
3 files changed, 69 insertions(+), 1 deletion(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index bce3a840f15c..7fb4aae97412 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4772,7 +4772,22 @@ int ceph_drop_caps_for_unlink(struct inode *inode)
if (__ceph_caps_dirty(ci)) {
struct ceph_mds_client *mdsc =
ceph_inode_to_fs_client(inode)->mdsc;
- __cap_delay_requeue_front(mdsc, ci);
+
+ doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode,
+ ceph_vinop(inode));
+ spin_lock(&mdsc->cap_unlink_delay_lock);
+ ci->i_ceph_flags |= CEPH_I_FLUSH;
+ if (!list_empty(&ci->i_cap_delay_list))
+ list_del_init(&ci->i_cap_delay_list);
+ list_add_tail(&ci->i_cap_delay_list,
+ &mdsc->cap_unlink_delay_list);
+ spin_unlock(&mdsc->cap_unlink_delay_lock);
+
+ /*
+ * Fire the work immediately, because the MDS maybe
+ * waiting for caps release.
+ */
+ ceph_queue_cap_unlink_work(mdsc);
}
}
spin_unlock(&ci->i_ceph_lock);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f71bb9c9569f..3ab9c268a8bb 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2484,6 +2484,50 @@ void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr)
}
}
+void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc)
+{
+ struct ceph_client *cl = mdsc->fsc->client;
+ if (mdsc->stopping)
+ return;
+
+ if (queue_work(mdsc->fsc->cap_wq, &mdsc->cap_unlink_work)) {
+ doutc(cl, "caps unlink work queued\n");
+ } else {
+ doutc(cl, "failed to queue caps unlink work\n");
+ }
+}
+
+static void ceph_cap_unlink_work(struct work_struct *work)
+{
+ struct ceph_mds_client *mdsc =
+ container_of(work, struct ceph_mds_client, cap_unlink_work);
+ struct ceph_client *cl = mdsc->fsc->client;
+
+ doutc(cl, "begin\n");
+ spin_lock(&mdsc->cap_unlink_delay_lock);
+ while (!list_empty(&mdsc->cap_unlink_delay_list)) {
+ struct ceph_inode_info *ci;
+ struct inode *inode;
+
+ ci = list_first_entry(&mdsc->cap_unlink_delay_list,
+ struct ceph_inode_info,
+ i_cap_delay_list);
+ list_del_init(&ci->i_cap_delay_list);
+
+ inode = igrab(&ci->netfs.inode);
+ if (inode) {
+ spin_unlock(&mdsc->cap_unlink_delay_lock);
+ doutc(cl, "on %p %llx.%llx\n", inode,
+ ceph_vinop(inode));
+ ceph_check_caps(ci, CHECK_CAPS_FLUSH);
+ iput(inode);
+ spin_lock(&mdsc->cap_unlink_delay_lock);
+ }
+ }
+ spin_unlock(&mdsc->cap_unlink_delay_lock);
+ doutc(cl, "done\n");
+}
+
/*
* requests
*/
@@ -5359,6 +5403,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
INIT_LIST_HEAD(&mdsc->cap_delay_list);
INIT_LIST_HEAD(&mdsc->cap_wait_list);
spin_lock_init(&mdsc->cap_delay_lock);
+ INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
+ spin_lock_init(&mdsc->cap_unlink_delay_lock);
INIT_LIST_HEAD(&mdsc->snap_flush_list);
spin_lock_init(&mdsc->snap_flush_lock);
mdsc->last_cap_flush_tid = 1;
@@ -5367,6 +5413,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
spin_lock_init(&mdsc->cap_dirty_lock);
init_waitqueue_head(&mdsc->cap_flushing_wq);
INIT_WORK(&mdsc->cap_reclaim_work, ceph_cap_reclaim_work);
+ INIT_WORK(&mdsc->cap_unlink_work, ceph_cap_unlink_work);
err = ceph_metric_init(&mdsc->metric);
if (err)
goto err_mdsmap;
@@ -5640,6 +5687,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
ceph_cleanup_global_and_empty_realms(mdsc);
cancel_work_sync(&mdsc->cap_reclaim_work);
+ cancel_work_sync(&mdsc->cap_unlink_work);
cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
doutc(cl, "done\n");
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 40560af38827..03f8ff00874f 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -462,6 +462,8 @@ struct ceph_mds_client {
unsigned long last_renew_caps; /* last time we renewed our caps */
struct list_head cap_delay_list; /* caps with delayed release */
spinlock_t cap_delay_lock; /* protects cap_delay_list */
+ struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */
+ spinlock_t cap_unlink_delay_lock; /* protects cap_unlink_delay_list */
struct list_head snap_flush_list; /* cap_snaps ready to flush */
spinlock_t snap_flush_lock;
@@ -475,6 +477,8 @@ struct ceph_mds_client {
struct work_struct cap_reclaim_work;
atomic_t cap_reclaim_pending;
+ struct work_struct cap_unlink_work;
+
/*
* Cap reservations
*
@@ -574,6 +578,7 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc);
extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr);
+extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc);
extern int ceph_iterate_session_caps(struct ceph_mds_session *session,
int (*cb)(struct inode *, int mds, void *),
void *arg);
From 1741a8269e1c51fa08d4bfdf34667387a6eb10ec Mon Sep 17 00:00:00 2001
From: Manuel Fombuena <fombuena@outlook.com>
Date: Sun, 11 Feb 2024 19:04:29 +0000
Subject: [PATCH 514/637] HID: multitouch: Add required quirk for Synaptics
0xcddc device
Add support for the pointing stick (Accupoint) and 2 mouse buttons.
Present on some Toshiba/dynabook Portege X30 and X40 laptops.
It should close https://bugzilla.kernel.org/show_bug.cgi?id=205817
Signed-off-by: Manuel Fombuena <fombuena@outlook.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
drivers/hid/hid-multitouch.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index fd5b0637dad6..3e91e4d6ba6f 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2151,6 +2151,10 @@ static const struct hid_device_id mt_devices[] = {
HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
USB_VENDOR_ID_SYNAPTICS, 0xcd7e) },
+ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+ HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+ USB_VENDOR_ID_SYNAPTICS, 0xcddc) },
+
{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
USB_VENDOR_ID_SYNAPTICS, 0xce08) },
From 846297e11e8ae428f8b00156a0cfe2db58100702 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 13 Feb 2024 10:12:04 +0000
Subject: [PATCH 515/637] irqchip/gic-v3-its: Handle non-coherent GICv4
redistributors
Although the GICv3 code base has gained some handling of systems failing to
handle the shareability attributes, the GICv4 side of things has been
firmly ignored.
This is unfortunate, as the new recent addition of the "dma-noncoherent" is
supposed to apply to all of the GICR tables, and not just the ones that are
common to v3 and v4.
Add some checks to handle the VPROPBASE/VPENDBASE shareability and
cacheability attributes in the same way we deal with the other GICR_BASE
registers, wrapping the flag check in a helper for improved readability.
Note that this has been found by inspection only, as I don't have access to
HW that suffers from this particular issue.
Fixes: 3a0fff0fb6a3 ("irqchip/gic-v3: Enable non-coherent redistributors/ITSes DT probing")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Link: https://lore.kernel.org/r/20240213101206.2137483-2-maz@kernel.org
---
drivers/irqchip/irq-gic-v3-its.c | 37 +++++++++++++++++++++-----------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d097001c1e3e..fec1b58470df 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -207,6 +207,11 @@ static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its)
return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]);
}
+static bool rdists_support_shareable(void)
+{
+ return !(gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE);
+}
+
static u16 get_its_list(struct its_vm *vm)
{
struct its_node *its;
@@ -2710,10 +2715,12 @@ static u64 inherit_vpe_l1_table_from_its(void)
break;
}
val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12);
- val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
- FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
- val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
- FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+ if (rdists_support_shareable()) {
+ val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK,
+ FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser));
+ val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK,
+ FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser));
+ }
val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
return val;
@@ -2936,8 +2943,10 @@ static int allocate_vpe_l1_table(void)
WARN_ON(!IS_ALIGNED(pa, psz));
val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12);
- val |= GICR_VPROPBASER_RaWb;
- val |= GICR_VPROPBASER_InnerShareable;
+ if (rdists_support_shareable()) {
+ val |= GICR_VPROPBASER_RaWb;
+ val |= GICR_VPROPBASER_InnerShareable;
+ }
val |= GICR_VPROPBASER_4_1_Z;
val |= GICR_VPROPBASER_4_1_VALID;
@@ -3126,7 +3135,7 @@ static void its_cpu_init_lpis(void)
gicr_write_propbaser(val, rbase + GICR_PROPBASER);
tmp = gicr_read_propbaser(rbase + GICR_PROPBASER);
- if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+ if (!rdists_support_shareable())
tmp &= ~GICR_PROPBASER_SHAREABILITY_MASK;
if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) {
@@ -3153,7 +3162,7 @@ static void its_cpu_init_lpis(void)
gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
- if (gic_rdists->flags & RDIST_FLAGS_FORCE_NON_SHAREABLE)
+ if (!rdists_support_shareable())
tmp &= ~GICR_PENDBASER_SHAREABILITY_MASK;
if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) {
@@ -3880,14 +3889,18 @@ static void its_vpe_schedule(struct its_vpe *vpe)
val = virt_to_phys(page_address(vpe->its_vm->vprop_page)) &
GENMASK_ULL(51, 12);
val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
- val |= GICR_VPROPBASER_RaWb;
- val |= GICR_VPROPBASER_InnerShareable;
+ if (rdists_support_shareable()) {
+ val |= GICR_VPROPBASER_RaWb;
+ val |= GICR_VPROPBASER_InnerShareable;
+ }
gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
val = virt_to_phys(page_address(vpe->vpt_page)) &
GENMASK_ULL(51, 16);
- val |= GICR_VPENDBASER_RaWaWb;
- val |= GICR_VPENDBASER_InnerShareable;
+ if (rdists_support_shareable()) {
+ val |= GICR_VPENDBASER_RaWaWb;
+ val |= GICR_VPENDBASER_InnerShareable;
+ }
/*
* There is no good way of finding out if the pending table is
* empty as we can race against the doorbell interrupt very
From 8b02da04ad978827e5ccd675acf170198f747a7a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 13 Feb 2024 10:12:05 +0000
Subject: [PATCH 516/637] irqchip/gic-v3-its: Restore quirk probing for
ACPI-based systems
While refactoring the way the ITSs are probed, the handling of quirks
applicable to ACPI-based platforms was lost. As a result, systems such as
HIP07 lose their GICv4 functionnality, and some other may even fail to
boot, unless they are configured to boot with DT.
Move the enabling of quirks into its_probe_one(), making it common to all
firmware implementations.
Fixes: 9585a495ac93 ("irqchip/gic-v3-its: Split allocation from initialisation of its_node")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240213101206.2137483-3-maz@kernel.org
---
drivers/irqchip/irq-gic-v3-its.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index fec1b58470df..250b4562f308 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -5091,6 +5091,8 @@ static int __init its_probe_one(struct its_node *its)
u32 ctlr;
int err;
+ its_enable_quirks(its);
+
if (is_v4(its)) {
if (!(its->typer & GITS_TYPER_VMOVP)) {
err = its_compute_its_list_map(its);
@@ -5442,7 +5444,6 @@ static int __init its_of_probe(struct device_node *node)
if (!its)
return -ENOMEM;
- its_enable_quirks(its);
err = its_probe_one(its);
if (err) {
its_node_destroy(its);
From af9acbfc2c4b72c378d0b9a2ee023ed01055d3e2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 13 Feb 2024 10:12:06 +0000
Subject: [PATCH 517/637] irqchip/gic-v3-its: Fix GICv4.1 VPE affinity update
When updating the affinity of a VPE, the VMOVP command is currently skipped
if the two CPUs are part of the same VPE affinity.
But this is wrong, as the doorbell corresponding to this VPE is still
delivered on the 'old' CPU, which screws up the balancing. Furthermore,
offlining that 'old' CPU results in doorbell interrupts generated for this
VPE being discarded.
The harsh reality is that VMOVP cannot be elided when a set_affinity()
request occurs. It needs to be obeyed, and if an optimisation is to be
made, it is at the point where the affinity change request is made (such as
in KVM).
Drop the VMOVP elision altogether, and only use the vpe_table_mask
to try and stay within the same ITS affinity group if at all possible.
Fixes: dd3f050a216e (irqchip/gic-v4.1: Implement the v4.1 flavour of VMOVP)
Reported-by: Kunkun Jiang <jiangkunkun@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240213101206.2137483-4-maz@kernel.org
---
drivers/irqchip/irq-gic-v3-its.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 250b4562f308..53abd4779914 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3826,8 +3826,9 @@ static int its_vpe_set_affinity(struct irq_data *d,
bool force)
{
struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
- int from, cpu = cpumask_first(mask_val);
+ struct cpumask common, *table_mask;
unsigned long flags;
+ int from, cpu;
/*
* Changing affinity is mega expensive, so let's be as lazy as
@@ -3843,19 +3844,22 @@ static int its_vpe_set_affinity(struct irq_data *d,
* taken on any vLPI handling path that evaluates vpe->col_idx.
*/
from = vpe_to_cpuid_lock(vpe, &flags);
+ table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
+
+ /*
+ * If we are offered another CPU in the same GICv4.1 ITS
+ * affinity, pick this one. Otherwise, any CPU will do.
+ */
+ if (table_mask && cpumask_and(&common, mask_val, table_mask))
+ cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common);
+ else
+ cpu = cpumask_first(mask_val);
+
if (from == cpu)
goto out;
vpe->col_idx = cpu;
- /*
- * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD
- * is sharing its VPE table with the current one.
- */
- if (gic_data_rdist_cpu(cpu)->vpe_table_mask &&
- cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask))
- goto out;
-
its_send_vmovp(vpe);
its_vpe_db_proxy_move(vpe, from, cpu);
From bdab6c94bb24758081625e619330b04cfd56570a Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Fri, 9 Feb 2024 14:52:32 +0800
Subject: [PATCH 518/637] HID: Intel-ish-hid: Ishtp: Fix sensor reads after
ACPI S3 suspend
After legacy suspend/resume via ACPI S3, sensor read operation fails
with timeout. Also, it will cause delay in resume operation as there
will be retries on failure.
This is caused by commit f645a90e8ff7 ("HID: intel-ish-hid:
ishtp-hid-client: use helper functions for connection"), which used
helper functions to simplify connect, reset and disconnect process.
Also avoid freeing and allocating client buffers again during reconnect
process.
But there is a case, when ISH firmware resets after ACPI S3 suspend,
ishtp bus driver frees client buffers. Since there is no realloc again
during reconnect, there are no client buffers available to send connection
requests to the firmware. Without successful connection to the firmware,
subsequent sensor reads will timeout.
To address this issue, ishtp bus driver does not free client buffers on
warm reset after S3 resume. Simply add the buffers from the read list
to free list of buffers.
Fixes: f645a90e8ff7 ("HID: intel-ish-hid: ishtp-hid-client: use helper functions for connection")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218442
Signed-off-by: Even Xu <even.xu@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
drivers/hid/intel-ish-hid/ishtp/bus.c | 2 ++
drivers/hid/intel-ish-hid/ishtp/client.c | 4 +++-
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index aa6cb033bb06..03d5601ce807 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -722,6 +722,8 @@ void ishtp_bus_remove_all_clients(struct ishtp_device *ishtp_dev,
spin_lock_irqsave(&ishtp_dev->cl_list_lock, flags);
list_for_each_entry(cl, &ishtp_dev->cl_list, link) {
cl->state = ISHTP_CL_DISCONNECTED;
+ if (warm_reset && cl->device->reference_count)
+ continue;
/*
* Wake any pending process. The waiter would check dev->state
diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 82c907f01bd3..8a7f2f6a4f86 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -49,7 +49,9 @@ static void ishtp_read_list_flush(struct ishtp_cl *cl)
list_for_each_entry_safe(rb, next, &cl->dev->read_list.list, list)
if (rb->cl && ishtp_cl_cmp_id(cl, rb->cl)) {
list_del(&rb->list);
- ishtp_io_rb_free(rb);
+ spin_lock(&cl->free_list_spinlock);
+ list_add_tail(&rb->list, &cl->free_rb_list.list);
+ spin_unlock(&cl->free_list_spinlock);
}
spin_unlock_irqrestore(&cl->dev->read_list_spinlock, flags);
}
From 25236c91b5ab4a26a56ba2e79b8060cf4e047839 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Feb 2024 14:04:53 -0800
Subject: [PATCH 519/637] af_unix: Fix task hung while purging oob_skb in GC.
syzbot reported a task hung; at the same time, GC was looping infinitely
in list_for_each_entry_safe() for OOB skb. [0]
syzbot demonstrated that the list_for_each_entry_safe() was not actually
safe in this case.
A single skb could have references for multiple sockets. If we free such
a skb in the list_for_each_entry_safe(), the current and next sockets could
be unlinked in a single iteration.
unix_notinflight() uses list_del_init() to unlink the socket, so the
prefetched next socket forms a loop itself and list_for_each_entry_safe()
never stops.
Here, we must use while() and make sure we always fetch the first socket.
[0]:
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 5065 Comm: syz-executor236 Not tainted 6.8.0-rc3-syzkaller-00136-g1f719a2f3fa6 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
RIP: 0010:preempt_count arch/x86/include/asm/preempt.h:26 [inline]
RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline]
RIP: 0010:__sanitizer_cov_trace_pc+0xd/0x60 kernel/kcov.c:207
Code: cc cc cc cc 66 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 65 48 8b 14 25 40 c2 03 00 <65> 8b 05 b4 7c 78 7e a9 00 01 ff 00 48 8b 34 24 74 0f f6 c4 01 74
RSP: 0018:ffffc900033efa58 EFLAGS: 00000283
RAX: ffff88807b077800 RBX: ffff88807b077800 RCX: 1ffffffff27b1189
RDX: ffff88802a5a3b80 RSI: ffffffff8968488d RDI: ffff88807b077f70
RBP: ffffc900033efbb0 R08: 0000000000000001 R09: fffffbfff27a900c
R10: ffffffff93d48067 R11: ffffffff8ae000eb R12: ffff88807b077800
R13: dffffc0000000000 R14: ffff88807b077e40 R15: 0000000000000001
FS: 0000000000000000(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564f4fc1e3a8 CR3: 000000000d57a000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<NMI>
</NMI>
<TASK>
unix_gc+0x563/0x13b0 net/unix/garbage.c:319
unix_release_sock+0xa93/0xf80 net/unix/af_unix.c:683
unix_release+0x91/0xf0 net/unix/af_unix.c:1064
__sock_release+0xb0/0x270 net/socket.c:659
sock_close+0x1c/0x30 net/socket.c:1421
__fput+0x270/0xb80 fs/file_table.c:376
task_work_run+0x14f/0x250 kernel/task_work.c:180
exit_task_work include/linux/task_work.h:38 [inline]
do_exit+0xa8a/0x2ad0 kernel/exit.c:871
do_group_exit+0xd4/0x2a0 kernel/exit.c:1020
__do_sys_exit_group kernel/exit.c:1031 [inline]
__se_sys_exit_group kernel/exit.c:1029 [inline]
__x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1029
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xd5/0x270 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x6f/0x77
RIP: 0033:0x7f9d6cbdac09
Code: Unable to access opcode bytes at 0x7f9d6cbdabdf.
RSP: 002b:00007fff5952feb8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9d6cbdac09
RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000000
RBP: 00007f9d6cc552b0 R08: ffffffffffffffb8 R09: 0000000000000006
R10: 0000000000000006 R11: 0000000000000246 R12: 00007f9d6cc552b0
R13: 0000000000000000 R14: 00007f9d6cc55d00 R15: 00007f9d6cbabe70
</TASK>
Reported-by: syzbot+4fa4a2d1f5a5ee06f006@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=4fa4a2d1f5a5ee06f006
Fixes: 1279f9d9dec2 ("af_unix: Call kfree_skb() for dead unix_(sk)->oob_skb in GC.")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240209220453.96053-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/unix/garbage.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8f63f0b4bf01..2ff7ddbaa782 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -315,10 +315,11 @@ void unix_gc(void)
__skb_queue_purge(&hitlist);
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
- list_for_each_entry_safe(u, next, &gc_candidates, link) {
- struct sk_buff *skb = u->oob_skb;
+ while (!list_empty(&gc_candidates)) {
+ u = list_entry(gc_candidates.next, struct unix_sock, link);
+ if (u->oob_skb) {
+ struct sk_buff *skb = u->oob_skb;
- if (skb) {
u->oob_skb = NULL;
kfree_skb(skb);
}
From ab41a31dd5e2681803642b6d08590b61867840ec Mon Sep 17 00:00:00 2001
From: Tatsunosuke Tobita <tatsunosuke.tobita@wacom.com>
Date: Thu, 1 Feb 2024 13:40:55 +0900
Subject: [PATCH 520/637] HID: wacom: generic: Avoid reporting a serial of '0'
to userspace
The xf86-input-wacom driver does not treat '0' as a valid serial
number and will drop any input report which contains an
MSC_SERIAL = 0 event. The kernel driver already takes care to
avoid sending any MSC_SERIAL event if the value of serial[0] == 0
(which is the case for devices that don't actually report a
serial number), but this is not quite sufficient.
Only the lower 32 bits of the serial get reported to userspace,
so if this portion of the serial is zero then there can still
be problems.
This commit allows the driver to report either the lower 32 bits
if they are non-zero or the upper 32 bits otherwise.
Signed-off-by: Jason Gerecke <jason.gerecke@wacom.com>
Signed-off-by: Tatsunosuke Tobita <tatsunosuke.tobita@wacom.com>
Fixes: f85c9dc678a5 ("HID: wacom: generic: Support tool ID and additional tool types")
CC: stable@vger.kernel.org # v4.10
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
drivers/hid/wacom_wac.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index da8a01fedd39..fbe10fbc5769 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2575,7 +2575,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev,
wacom_wac->hid_data.tipswitch);
input_report_key(input, wacom_wac->tool[0], sense);
if (wacom_wac->serial[0]) {
- input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]);
+ /*
+ * xf86-input-wacom does not accept a serial number
+ * of '0'. Report the low 32 bits if possible, but
+ * if they are zero, report the upper ones instead.
+ */
+ __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu;
+ __u32 serial_hi = wacom_wac->serial[0] >> 32;
+ input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi));
input_report_abs(input, ABS_MISC, sense ? id : 0);
}
From e083dd032eeba9e28e4703cd5aaf4a409ebc3837 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 10 Feb 2024 22:11:52 -0800
Subject: [PATCH 521/637] net: ti: icssg-prueth: add dependency for PTP
When CONFIG_PTP_1588_CLOCK=m and CONFIG_TI_ICSSG_PRUETH=y, there are
kconfig dependency warnings and build errors referencing PTP functions.
Fix these by making TI_ICSSG_PRUETH depend on PTP_1588_CLOCK_OPTIONAL.
Fixes these build errors and warnings:
WARNING: unmet direct dependencies detected for TI_ICSS_IEP
Depends on [m]: NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_TI [=y] && PTP_1588_CLOCK_OPTIONAL [=m] && TI_PRUSS [=y]
Selected by [y]:
- TI_ICSSG_PRUETH [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_TI [=y] && PRU_REMOTEPROC [=y] && ARCH_K3 [=y] && OF [=y] && TI_K3_UDMA_GLUE_LAYER [=y]
aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_get_ptp_clock_idx':
icss_iep.c:(.text+0x1d4): undefined reference to `ptp_clock_index'
aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_exit':
icss_iep.c:(.text+0xde8): undefined reference to `ptp_clock_unregister'
aarch64-linux-ld: drivers/net/ethernet/ti/icssg/icss_iep.o: in function `icss_iep_init':
icss_iep.c:(.text+0x176c): undefined reference to `ptp_clock_register'
Fixes: 186734c15886 ("net: ti: icssg-prueth: add packet timestamping and ptp support")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Roger Quadros <rogerq@ti.com>
Cc: Md Danish Anwar <danishanwar@ti.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org
Reviewed-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://lore.kernel.org/r/20240211061152.14696-1-rdunlap@infradead.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/ti/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index be01450c20dc..1530d13984d4 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -189,6 +189,7 @@ config TI_ICSSG_PRUETH
select TI_K3_CPPI_DESC_POOL
depends on PRU_REMOTEPROC
depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
+ depends on PTP_1588_CLOCK_OPTIONAL
help
Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem.
This subsystem is available starting with the AM65 platform.
From d463bcd7eb341b5b6e6d9263a3bce9f405c2af98 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 13 Feb 2024 10:04:17 +0200
Subject: [PATCH 522/637] ASoC: SOF: Intel: pci-tgl: Change the default paths
and firmware names
The currently used paths and firmware name reflects the reference firmware
convention:
default_fw_path: intel/avs/{platform_name}
default_lib_path: intel/avs-lib/{platform_name}
default_tplg_path: intel/avs-tplg
default_fw_filename: dsp_basefw.bin
The SOF supports building the firmware for cAVS2.5 platforms using IPC4 and
it is the preferred IPC4 implementation to be used on these devices.
Change the paths and firmware names to reflect this:
default_fw_path: intel/sof-ipc4/{platform_name}
default_lib_path: intel/sof-ipc4-lib/{platform_name}
default_tplg_path: intel/sof-ipc4-tplg
default_fw_filename: sof-{platform_name}.ri
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://msgid.link/r/20240213080418.21256-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/intel/pci-tgl.c | 64 +++++++++++++++++------------------
1 file changed, 32 insertions(+), 32 deletions(-)
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index 0660d4b2ac96..a361ee9d1107 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -33,18 +33,18 @@ static const struct sof_dev_desc tgl_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/tgl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/tgl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-tgl.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-tgl.ri",
},
.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -66,18 +66,18 @@ static const struct sof_dev_desc tglh_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/tgl-h",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/tgl-h",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/tgl-h",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/tgl-h",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-tgl-h.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-tgl-h.ri",
},
.nocodec_tplg_filename = "sof-tgl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -98,18 +98,18 @@ static const struct sof_dev_desc ehl_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/ehl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/ehl",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/ehl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/ehl",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-ehl.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-ehl.ri",
},
.nocodec_tplg_filename = "sof-ehl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -131,18 +131,18 @@ static const struct sof_dev_desc adls_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/adl-s",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-s",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/adl-s",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-s",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-adl-s.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-adl-s.ri",
},
.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -164,18 +164,18 @@ static const struct sof_dev_desc adl_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/adl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/adl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-adl.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-adl.ri",
},
.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -197,18 +197,18 @@ static const struct sof_dev_desc adl_n_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/adl-n",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/adl-n",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/adl-n",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/adl-n",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-adl-n.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-adl-n.ri",
},
.nocodec_tplg_filename = "sof-adl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -230,18 +230,18 @@ static const struct sof_dev_desc rpls_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/rpl-s",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl-s",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/rpl-s",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl-s",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-rpl-s.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-rpl-s.ri",
},
.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
.ops = &sof_tgl_ops,
@@ -263,18 +263,18 @@ static const struct sof_dev_desc rpl_desc = {
.dspless_mode_supported = true, /* Only supported for HDaudio */
.default_fw_path = {
[SOF_IPC_TYPE_3] = "intel/sof",
- [SOF_IPC_TYPE_4] = "intel/avs/rpl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4/rpl",
},
.default_lib_path = {
- [SOF_IPC_TYPE_4] = "intel/avs-lib/rpl",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/rpl",
},
.default_tplg_path = {
[SOF_IPC_TYPE_3] = "intel/sof-tplg",
- [SOF_IPC_TYPE_4] = "intel/avs-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_3] = "sof-rpl.ri",
- [SOF_IPC_TYPE_4] = "dsp_basefw.bin",
+ [SOF_IPC_TYPE_4] = "sof-rpl.ri",
},
.nocodec_tplg_filename = "sof-rpl-nocodec.tplg",
.ops = &sof_tgl_ops,
From b029482011bffd57319507c2bf4c5a7e06eca756 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 13 Feb 2024 10:04:18 +0200
Subject: [PATCH 523/637] ASoC: SOF: Intel: pci-lnl: Change the topology path
to intel/sof-ipc4-tplg
The firmware release which going to introduce support for Lunar Lake will
use the documented default topology directory for IPC4:
intel/sof-ipc4-tplg
Change the default path accordingly before sof-bin (sof-firmware) release
includes Lunar Lake firmware and topologies.
Link: https://github.com/thesofproject/sof-docs/blob/master/getting_started/intel_debug/introduction.rst#2-topology-file
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Mengdong Lin <mengdong.lin@intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Chao Song <chao.song@linux.intel.com>
Link: https://msgid.link/r/20240213080418.21256-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/intel/pci-lnl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c
index 78a57eb9cbc3..b26ffe767fab 100644
--- a/sound/soc/sof/intel/pci-lnl.c
+++ b/sound/soc/sof/intel/pci-lnl.c
@@ -36,7 +36,7 @@ static const struct sof_dev_desc lnl_desc = {
[SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl",
},
.default_tplg_path = {
- [SOF_IPC_TYPE_4] = "intel/sof-ace-tplg",
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
.default_fw_filename = {
[SOF_IPC_TYPE_4] = "sof-lnl.ri",
From 5b5089e2a1e753ffe9ee2bf101a9e06784ec5e1a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Feb 2024 11:10:46 +0100
Subject: [PATCH 524/637] ASoC: q6dsp: fix event handler prototype
clang-16 points out a mismatch in function types that was hidden
by a typecast:
sound/soc/qcom/qdsp6/q6apm-dai.c:355:38: error: cast from 'void (*)(uint32_t, uint32_t, uint32_t *, void *)' (aka 'void (*)(unsigned int, unsigned int, unsigned int *, void *)') to 'q6apm_cb' (aka 'void (*)(unsigned int, unsigned int, void *, void *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict]
355 | prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler, prtd, graph_id);
sound/soc/qcom/qdsp6/q6apm-dai.c:499:38: error: cast from 'void (*)(uint32_t, uint32_t, uint32_t *, void *)' (aka 'void (*)(unsigned int, unsigned int, unsigned int *, void *)') to 'q6apm_cb' (aka 'void (*)(unsigned int, unsigned int, void *, void *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict]
499 | prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler_compr, prtd, graph_id);
The only difference here is the 'payload' argument, which is not even
used in this function, so just fix its type and remove the cast.
Fixes: 88b60bf047fd ("ASoC: q6dsp: q6apm-dai: Add open/free compress DAI callbacks")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://msgid.link/r/20240213101105.459402-1-arnd@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/qcom/qdsp6/q6apm-dai.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c
index 052e40cb38fe..00bbd291be5c 100644
--- a/sound/soc/qcom/qdsp6/q6apm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6apm-dai.c
@@ -123,7 +123,7 @@ static struct snd_pcm_hardware q6apm_dai_hardware_playback = {
.fifo_size = 0,
};
-static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, void *priv)
+static void event_handler(uint32_t opcode, uint32_t token, void *payload, void *priv)
{
struct q6apm_dai_rtd *prtd = priv;
struct snd_pcm_substream *substream = prtd->substream;
@@ -157,7 +157,7 @@ static void event_handler(uint32_t opcode, uint32_t token, uint32_t *payload, vo
}
static void event_handler_compr(uint32_t opcode, uint32_t token,
- uint32_t *payload, void *priv)
+ void *payload, void *priv)
{
struct q6apm_dai_rtd *prtd = priv;
struct snd_compr_stream *substream = prtd->cstream;
@@ -352,7 +352,7 @@ static int q6apm_dai_open(struct snd_soc_component *component,
spin_lock_init(&prtd->lock);
prtd->substream = substream;
- prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler, prtd, graph_id);
+ prtd->graph = q6apm_graph_open(dev, event_handler, prtd, graph_id);
if (IS_ERR(prtd->graph)) {
dev_err(dev, "%s: Could not allocate memory\n", __func__);
ret = PTR_ERR(prtd->graph);
@@ -496,7 +496,7 @@ static int q6apm_dai_compr_open(struct snd_soc_component *component,
return -ENOMEM;
prtd->cstream = stream;
- prtd->graph = q6apm_graph_open(dev, (q6apm_cb)event_handler_compr, prtd, graph_id);
+ prtd->graph = q6apm_graph_open(dev, event_handler_compr, prtd, graph_id);
if (IS_ERR(prtd->graph)) {
ret = PTR_ERR(prtd->graph);
kfree(prtd);
From c40aad7c81e5fba34b70123ed7ce3397fa62a4d2 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 13 Feb 2024 13:52:33 +0200
Subject: [PATCH 525/637] ASoC: SOF: ipc4-pcm: Workaround for crashed firmware
on system suspend
When the system is suspended while audio is active, the
sof_ipc4_pcm_hw_free() is invoked to reset the pipelines since during
suspend the DSP is turned off, streams will be re-started after resume.
If the firmware crashes during while audio is running (or when we reset
the stream before suspend) then the sof_ipc4_set_multi_pipeline_state()
will fail with IPC error and the state change is interrupted.
This will cause misalignment between the kernel and firmware state on next
DSP boot resulting errors returned by firmware for IPC messages, eventually
failing the audio resume.
On stream close the errors are ignored so the kernel state will be
corrected on the next DSP boot, so the second boot after the DSP panic.
If sof_ipc4_trigger_pipelines() is called from sof_ipc4_pcm_hw_free() then
state parameter is SOF_IPC4_PIPE_RESET and only in this case.
Treat a forced pipeline reset similarly to how we treat a pcm_free by
ignoring error on state sending to allow the kernel's state to be
consistent with the state the firmware will have after the next boot.
Link: https://github.com/thesofproject/sof/issues/8721
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://msgid.link/r/20240213115233.15716-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/ipc4-pcm.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 85d3f390e4b2..07eb5c6d4adf 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -413,7 +413,18 @@ skip_pause_transition:
ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list);
if (ret < 0) {
dev_err(sdev->dev, "failed to set final state %d for all pipelines\n", state);
- goto free;
+ /*
+ * workaround: if the firmware is crashed while setting the
+ * pipelines to reset state we must ignore the error code and
+ * reset it to 0.
+ * Since the firmware is crashed we will not send IPC messages
+ * and we are going to see errors printed, but the state of the
+ * widgets will be correct for the next boot.
+ */
+ if (sdev->fw_state != SOF_FW_CRASHED || state != SOF_IPC4_PIPE_RESET)
+ goto free;
+
+ ret = 0;
}
/* update RUNNING/RESET state for all pipelines that were just triggered */
From fcbe4873089c84da641df75cda9cac2e9addbb4b Mon Sep 17 00:00:00 2001
From: Curtis Malainey <cujomalainey@chromium.org>
Date: Tue, 13 Feb 2024 14:38:34 +0200
Subject: [PATCH 526/637] ASoC: SOF: IPC3: fix message bounds on ipc ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
commit 74ad8ed65121 ("ASoC: SOF: ipc3: Implement rx_msg IPC ops")
introduced a new allocation before the upper bounds check in
do_rx_work. As a result A DSP can cause bad allocations if spewing
garbage.
Fixes: 74ad8ed65121 ("ASoC: SOF: ipc3: Implement rx_msg IPC ops")
Reported-by: Tim Van Patten <timvp@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Curtis Malainey <cujomalainey@chromium.org>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://msgid.link/r/20240213123834.4827-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/ipc3.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/sof/ipc3.c b/sound/soc/sof/ipc3.c
index fb40378ad084..c03dd513fbff 100644
--- a/sound/soc/sof/ipc3.c
+++ b/sound/soc/sof/ipc3.c
@@ -1067,7 +1067,7 @@ static void sof_ipc3_rx_msg(struct snd_sof_dev *sdev)
return;
}
- if (hdr.size < sizeof(hdr)) {
+ if (hdr.size < sizeof(hdr) || hdr.size > SOF_IPC_MSG_MAX_SIZE) {
dev_err(sdev->dev, "The received message size is invalid\n");
return;
}
From 24b6332c2d4ff08fb7601ac8f751a5ba51e0ebd3 Mon Sep 17 00:00:00 2001
From: Tomasz Kudela <ramzes005@gmail.com>
Date: Tue, 13 Feb 2024 12:56:14 +0100
Subject: [PATCH 527/637] ALSA: hda: Add Lenovo Legion 7i gen7 sound quirk
Add sound support for the Legion 7i gen7 laptop (16IAX7).
Signed-off-by: Tomasz Kudela <ramzes005@gmail.com>
Link: https://lore.kernel.org/r/20240213115614.10420-1-ramzes005@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/cs35l41_hda_property.c | 2 ++
sound/pci/hda/patch_realtek.c | 1 +
2 files changed, 3 insertions(+)
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index d74cf11eef1e..57b21285ab6a 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -95,6 +95,7 @@ static const struct cs35l41_config cs35l41_config_table[] = {
{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
{ "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+ { "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
{ "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
{ "17AA38B5", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
{ "17AA38B6", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
@@ -431,6 +432,7 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
{ "CSC3551", "10431F12", generic_dsd_config },
{ "CSC3551", "10431F1F", generic_dsd_config },
{ "CSC3551", "10431F62", generic_dsd_config },
+ { "CSC3551", "17AA386F", generic_dsd_config },
{ "CSC3551", "17AA38B4", generic_dsd_config },
{ "CSC3551", "17AA38B5", generic_dsd_config },
{ "CSC3551", "17AA38B6", generic_dsd_config },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e045d3e76a45..98886b803bc5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10262,6 +10262,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6),
SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
From b671cd3d456315f63171a670769356a196cf7fd0 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Mon, 21 Aug 2023 16:02:01 -0400
Subject: [PATCH 528/637] drm/prime: Support page array >= 4GB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Without unsigned long typecast, the size is passed in as zero if page
array size >= 4GB, nr_pages >= 0x100000, then sg list converted will
have the first and the last chunk lost.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230821200201.24685-1-Philip.Yang@amd.com
---
drivers/gpu/drm/drm_prime.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 834a5e28abbe..7352bde299d5 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -820,7 +820,7 @@ struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
if (max_segment == 0)
max_segment = UINT_MAX;
err = sg_alloc_table_from_pages_segment(sg, pages, nr_pages, 0,
- nr_pages << PAGE_SHIFT,
+ (unsigned long)nr_pages << PAGE_SHIFT,
max_segment, GFP_KERNEL);
if (err) {
kfree(sg);
From 269e31aecdd0b70f53a05def79480f15cbcc0fd6 Mon Sep 17 00:00:00 2001
From: Ralf Schlatterbeck <rsc@runtux.com>
Date: Fri, 2 Feb 2024 12:53:30 +0100
Subject: [PATCH 529/637] spi-mxs: Fix chipselect glitch
There was a change in the mxs-dma engine that uses a new custom flag.
The change was not applied to the mxs spi driver.
This results in chipselect being deasserted too early.
This fixes the chipselect problem by using the new flag in the mxs-spi
driver.
Fixes: ceeeb99cd821 ("dmaengine: mxs: rename custom flag")
Signed-off-by: Ralf Schlatterbeck <rsc@runtux.com>
Link: https://msgid.link/r/20240202115330.wxkbfmvd76sy3a6a@runtux.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-mxs.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index 1bf080339b5a..88cbe4f00cc3 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -39,6 +39,7 @@
#include <linux/spi/spi.h>
#include <linux/spi/mxs-spi.h>
#include <trace/events/spi.h>
+#include <linux/dma/mxs-dma.h>
#define DRIVER_NAME "mxs-spi"
@@ -252,7 +253,7 @@ static int mxs_spi_txrx_dma(struct mxs_spi *spi,
desc = dmaengine_prep_slave_sg(ssp->dmach,
&dma_xfer[sg_count].sg, 1,
(flags & TXRX_WRITE) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
- DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+ DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END);
if (!desc) {
dev_err(ssp->dev,
From b6802b61a9d0e99dcfa6fff7c50db7c48a9623d3 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 12 Feb 2024 13:55:34 -0800
Subject: [PATCH 530/637] drm/crtc: fix uninitialized variable use even harder
DRM_MODESET_LOCK_ALL_BEGIN() has a hidden trap-door (aka retry loop),
which means we can't rely too much on variable initializers.
Fixes: 6e455f5dcdd1 ("drm/crtc: fix uninitialized variable use")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> # sc7180, sdm845
Link: https://patchwork.freedesktop.org/patch/msgid/20240212215534.190682-1-robdclark@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
drivers/gpu/drm/drm_crtc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index cb90e70d85e8..65f9f66933bb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -904,6 +904,7 @@ out:
connector_set = NULL;
fb = NULL;
mode = NULL;
+ num_connectors = 0;
DRM_MODESET_LOCK_ALL_END(dev, ctx, ret);
From 79bd7eab8366b29eaa099908d5694cb473684b9d Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Tue, 13 Feb 2024 00:26:46 -0800
Subject: [PATCH 531/637] nvme-fabrics: fix I/O connect error handling
In nvmf_connect_io_queue(), if connect I/O command fails, we log the
error and continue for authentication. This overrides error captured
from __nvme_submit_sync_cmd(), causing wrong return value.
Add goto out_free_data after logging connect error to fix the issue.
Fixes: f50fff73d620c ("nvme: implement In-Band authentication")
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/fabrics.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 3499acbf6a82..495c171daead 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -534,6 +534,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
if (ret) {
nvmf_log_connect_error(ctrl, ret, le32_to_cpu(res.u32),
&cmd, data);
+ goto out_free_data;
}
result = le32_to_cpu(res.u32);
if (result & (NVME_CONNECT_AUTHREQ_ATR | NVME_CONNECT_AUTHREQ_ASCR)) {
From 4e06ec0774f5bebf10e27bc7a5ace4b48ae0fa56 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Wed, 24 Jan 2024 13:07:33 -0600
Subject: [PATCH 532/637] dt-bindings: ufs: samsung,exynos-ufs: Add size
constraints on "samsung,sysreg"
The 'phandle-array' type is a bit ambiguous. It can be either just an
array of phandles or an array of phandles plus args. "samsung,sysreg" is
the latter and needs to be constrained to a single entry with a phandle and
offset.
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20240124190733.1554314-1-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
.../devicetree/bindings/ufs/samsung,exynos-ufs.yaml | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
index 88cc1e3a0c88..b2b509b3944d 100644
--- a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml
@@ -55,9 +55,12 @@ properties:
samsung,sysreg:
$ref: /schemas/types.yaml#/definitions/phandle-array
- description: Should be phandle/offset pair. The phandle to the syscon node
- which indicates the FSYSx sysreg interface and the offset of
- the control register for UFS io coherency setting.
+ items:
+ - items:
+ - description: phandle to FSYSx sysreg node
+ - description: offset of the control register for UFS io coherency setting
+ description:
+ Phandle and offset to the FSYSx sysreg for UFS io coherency setting.
dma-coherent: true
From 29f6975332479f92233594901c649ff4d71f8cb6 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Mon, 5 Feb 2024 11:10:25 -0800
Subject: [PATCH 533/637] nvme: implement support for relaxed effects
NVM Express TP4167 provides a way for controllers to report a relaxed
execution constraint. Specifically, it notifies of exclusivity for IO
vs. admin commands instead of grouping these together. If set, then we
don't need to freeze IO in order to execute that admin command. The
freezing distrupts IO processes, so it's nice to avoid that if the
controller tells us it's not necessary.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/core.c | 4 ++++
include/linux/nvme.h | 1 +
2 files changed, 5 insertions(+)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 60537c9224bf..0a96362912ce 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1153,6 +1153,10 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
} else {
effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+
+ /* Ignore execution restrictions if any relaxation bits are set */
+ if (effects & NVME_CMD_EFFECTS_CSER_MASK)
+ effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
}
return effects;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index bc605ec4a3fd..3ef4053ea950 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -646,6 +646,7 @@ enum {
NVME_CMD_EFFECTS_NCC = 1 << 2,
NVME_CMD_EFFECTS_NIC = 1 << 3,
NVME_CMD_EFFECTS_CCC = 1 << 4,
+ NVME_CMD_EFFECTS_CSER_MASK = GENMASK(15, 14),
NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16),
NVME_CMD_EFFECTS_UUID_SEL = 1 << 19,
NVME_CMD_EFFECTS_SCOPE_MASK = GENMASK(31, 20),
From bdbddb109c75365d22ec4826f480c5e75869e1cb Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Tue, 13 Feb 2024 14:24:34 +0100
Subject: [PATCH 534/637] tracing: Fix HAVE_DYNAMIC_FTRACE_WITH_REGS ifdef
Commit a8b9cf62ade1 ("ftrace: Fix DIRECT_CALLS to use SAVE_REGS by
default") attempted to fix an issue with direct trampolines on x86, see
its description for details. However, it wrongly referenced the
HAVE_DYNAMIC_FTRACE_WITH_REGS config option and the problem is still
present.
Add the missing "CONFIG_" prefix for the logic to work as intended.
Link: https://lore.kernel.org/linux-trace-kernel/20240213132434.22537-1-petr.pavlu@suse.com
Fixes: a8b9cf62ade1 ("ftrace: Fix DIRECT_CALLS to use SAVE_REGS by default")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/ftrace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index c060d5b47910..83ba342aef31 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5331,7 +5331,7 @@ static int register_ftrace_function_nolock(struct ftrace_ops *ops);
* not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it
* jumps from ftrace_caller for multiple ftrace_ops.
*/
-#ifndef HAVE_DYNAMIC_FTRACE_WITH_REGS
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS
#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS)
#else
#define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS)
From a6eaa24f1cc2c7aecec6047556bdfe32042094c3 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Mon, 5 Feb 2024 07:53:40 +0100
Subject: [PATCH 535/637] tracing: Use ring_buffer_record_is_set_on() in
tracer_tracing_is_on()
tracer_tracing_is_on() checks whether record_disabled is not zero. This
checks both the record_disabled counter and the RB_BUFFER_OFF flag.
Reading the source it looks like this function should only check for
the RB_BUFFER_OFF flag. Therefore use ring_buffer_record_is_set_on().
This fixes spurious fails in the 'test for function traceon/off triggers'
test from the ftrace testsuite when the system is under load.
Link: https://lore.kernel.org/linux-trace-kernel/20240205065340.2848065-1-svens@linux.ibm.com
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Tested-By: Mete Durlu <meted@linux.ibm.com>
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9ff8a439d674..aa54810e8b56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1532,7 +1532,7 @@ void disable_trace_on_warning(void)
bool tracer_tracing_is_on(struct trace_array *tr)
{
if (tr->array_buffer.buffer)
- return ring_buffer_record_is_on(tr->array_buffer.buffer);
+ return ring_buffer_record_is_set_on(tr->array_buffer.buffer);
return !tr->buffer_disabled;
}
From feefe1f49d26bad9d8997096e3a200280fa7b1c5 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 31 Jan 2024 17:18:04 +0000
Subject: [PATCH 536/637] btrfs: don't reserve space for checksums when writing
to nocow files
Currently when doing a write to a file we always reserve metadata space
for inserting data checksums. However we don't need to do it if we have
a nodatacow file (-o nodatacow mount option or chattr +C) or if checksums
are disabled (-o nodatasum mount option), as in that case we are only
adding unnecessary pressure to metadata reservations.
For example on x86_64, with the default node size of 16K, a 4K buffered
write into a nodatacow file is reserving 655360 bytes of metadata space,
as it's accounting for checksums. After this change, which stops reserving
space for checksums if we have a nodatacow file or checksums are disabled,
we only need to reserve 393216 bytes of metadata.
CC: stable@vger.kernel.org # 6.1+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/delalloc-space.c | 29 +++++++++++++++++++----------
1 file changed, 19 insertions(+), 10 deletions(-)
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2833e8ef4c09..acf9f4b6c044 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
u64 reserve_size = 0;
u64 qgroup_rsv_size = 0;
- u64 csum_leaves;
unsigned outstanding_extents;
lockdep_assert_held(&inode->lock);
@@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
outstanding_extents);
reserve_size += btrfs_calc_metadata_size(fs_info, 1);
}
- csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
- inode->csum_bytes);
- reserve_size += btrfs_calc_insert_metadata_size(fs_info,
- csum_leaves);
+ if (!(inode->flags & BTRFS_INODE_NODATASUM)) {
+ u64 csum_leaves;
+
+ csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
+ reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves);
+ }
/*
* For qgroup rsv, the calculation is very simple:
* account one nodesize for each outstanding extent
@@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
spin_unlock(&block_rsv->lock);
}
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+static void calc_inode_reservations(struct btrfs_inode *inode,
u64 num_bytes, u64 disk_num_bytes,
u64 *meta_reserve, u64 *qgroup_reserve)
{
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
u64 nr_extents = count_max_extents(fs_info, num_bytes);
- u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+ u64 csum_leaves;
u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
+ if (inode->flags & BTRFS_INODE_NODATASUM)
+ csum_leaves = 0;
+ else
+ csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+
*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
nr_extents + csum_leaves);
@@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
* everything out and try again, which is bad. This way we just
* over-reserve slightly, and clean up the mess when we are done.
*/
- calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+ calc_inode_reservations(inode, num_bytes, disk_num_bytes,
&meta_reserve, &qgroup_reserve);
ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
noflush);
@@ -359,7 +366,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
nr_extents = count_max_extents(fs_info, num_bytes);
spin_lock(&inode->lock);
btrfs_mod_outstanding_extents(inode, nr_extents);
- inode->csum_bytes += disk_num_bytes;
+ if (!(inode->flags & BTRFS_INODE_NODATASUM))
+ inode->csum_bytes += disk_num_bytes;
btrfs_calculate_inode_block_rsv_size(fs_info, inode);
spin_unlock(&inode->lock);
@@ -393,7 +401,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
spin_lock(&inode->lock);
- inode->csum_bytes -= num_bytes;
+ if (!(inode->flags & BTRFS_INODE_NODATASUM))
+ inode->csum_bytes -= num_bytes;
btrfs_calculate_inode_block_rsv_size(fs_info, inode);
spin_unlock(&inode->lock);
From 1bd96c92c6a0a4d43815eb685c15aa4b78879dc9 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 2 Feb 2024 12:09:22 +0000
Subject: [PATCH 537/637] btrfs: reject encoded write if inode has nodatasum
flag set
Currently we allow an encoded write against inodes that have the NODATASUM
flag set, either because they are NOCOW files or they were created while
the filesystem was mounted with "-o nodatasum". This results in having
compressed extents without corresponding checksums, which is a filesystem
inconsistency reported by 'btrfs check'.
For example, running btrfs/281 with MOUNT_OPTIONS="-o nodatacow" triggers
this and 'btrfs check' errors out with:
[1/7] checking root items
[2/7] checking extents
[3/7] checking free space tree
[4/7] checking fs roots
root 256 inode 257 errors 1040, bad file extent, some csum missing
root 256 inode 258 errors 1040, bad file extent, some csum missing
ERROR: errors found in fs roots
(...)
So reject encoded writes if the target inode has NODATASUM set.
CC: stable@vger.kernel.org # 6.1+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/inode.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d232eca1bbee..5f39462dceb0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10288,6 +10288,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
return -EINVAL;
+ /*
+ * Compressed extents should always have checksums, so error out if we
+ * have a NOCOW file or inode was created while mounted with NODATASUM.
+ */
+ if (inode->flags & BTRFS_INODE_NODATASUM)
+ return -EINVAL;
+
orig_count = iov_iter_count(from);
/* The extent size must be sane. */
From 88e81a67773017a2b93f6d5fe7c78bb0c5a6e4dd Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 12 Feb 2024 21:50:53 +0000
Subject: [PATCH 538/637] btrfs: zoned: fix chunk map leak when loading block
group zone info
At btrfs_load_block_group_zone_info() we never drop a reference on the
chunk map we have looked up, therefore leaking a reference on it. So
add the missing btrfs_free_chunk_map() at the end of the function.
Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps")
Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/zoned.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index ac9bbe0c4ffe..afeb1dc1f43a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1687,6 +1687,7 @@ out:
}
bitmap_free(active);
kfree(zone_info);
+ btrfs_free_chunk_map(map);
return ret;
}
From 2f6397e448e689adf57e6788c90f913abd7e1af8 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 2 Feb 2024 14:32:17 +0000
Subject: [PATCH 539/637] btrfs: don't refill whole delayed refs block reserve
when starting transaction
Since commit 28270e25c69a ("btrfs: always reserve space for delayed refs
when starting transaction") we started not only to reserve metadata space
for the delayed refs a caller of btrfs_start_transaction() might generate
but also to try to fully refill the delayed refs block reserve, because
there are several case where we generate delayed refs and haven't reserved
space for them, relying on the global block reserve. Relying too much on
the global block reserve is not always safe, and can result in hitting
-ENOSPC during transaction commits or worst, in rare cases, being unable
to mount a filesystem that needs to do orphan cleanup or anything that
requires modifying the filesystem during mount, and has no more
unallocated space and the metadata space is nearly full. This was
explained in detail in that commit's change log.
However the gap between the reserved amount and the size of the delayed
refs block reserve can be huge, so attempting to reserve space for such
a gap can result in allocating many metadata block groups that end up
not being used. After a recent patch, with the subject:
"btrfs: add new unused block groups to the list of unused block groups"
We started to add new block groups that are unused to the list of unused
block groups, to avoid having them around for a very long time in case
they are never used, because a block group is only added to the list of
unused block groups when we deallocate the last extent or when mounting
the filesystem and the block group has 0 bytes used. This is not a problem
introduced by the commit mentioned earlier, it always existed as our
metadata space reservations are, most of the time, pessimistic and end up
not using all the space they reserved, so we can occasionally end up with
one or two unused metadata block groups for a long period. However after
that commit mentioned earlier, we are just more pessimistic in the
metadata space reservations when starting a transaction and therefore the
issue is more likely to happen.
This however is not always enough because we might create unused metadata
block groups when reserving metadata space at a high rate if there's
always a gap in the delayed refs block reserve and the cleaner kthread
isn't triggered often enough or is busy with other work (running delayed
iputs, cleaning deleted roots, etc), not to mention the block group's
allocated space is only usable for a new block group after the transaction
used to remove it is committed.
A user reported that he's getting a lot of allocated metadata block groups
but the usage percentage of metadata space was very low compared to the
total allocated space, specially after running a series of block group
relocations.
So for now stop trying to refill the gap in the delayed refs block reserve
and reserve space only for the delayed refs we are expected to generate
when starting a transaction.
CC: stable@vger.kernel.org # 6.7+
Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/9cdbf0ca9cdda1b4c84e15e548af7d7f9f926382.camel@intelfx.name/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H6802ayLHUJFztzZAVzBLJAGdFx=6FHNNy87+obZXXZpQ@mail.gmail.com/
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Reported-by: Heddxh <g311571057@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CAE93xANEby6RezOD=zcofENYZOT-wpYygJyauyUAZkLv6XVFOA@mail.gmail.com/
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/transaction.c | 38 ++------------------------------------
1 file changed, 2 insertions(+), 36 deletions(-)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5b3333ceef04..c52807d97efa 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -564,56 +564,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
u64 num_bytes,
u64 *delayed_refs_bytes)
{
- struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info;
- u64 extra_delayed_refs_bytes = 0;
- u64 bytes;
+ u64 bytes = num_bytes + *delayed_refs_bytes;
int ret;
- /*
- * If there's a gap between the size of the delayed refs reserve and
- * its reserved space, than some tasks have added delayed refs or bumped
- * its size otherwise (due to block group creation or removal, or block
- * group item update). Also try to allocate that gap in order to prevent
- * using (and possibly abusing) the global reserve when committing the
- * transaction.
- */
- if (flush == BTRFS_RESERVE_FLUSH_ALL &&
- !btrfs_block_rsv_full(delayed_refs_rsv)) {
- spin_lock(&delayed_refs_rsv->lock);
- if (delayed_refs_rsv->size > delayed_refs_rsv->reserved)
- extra_delayed_refs_bytes = delayed_refs_rsv->size -
- delayed_refs_rsv->reserved;
- spin_unlock(&delayed_refs_rsv->lock);
- }
-
- bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes;
-
/*
* We want to reserve all the bytes we may need all at once, so we only
* do 1 enospc flushing cycle per transaction start.
*/
ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
- if (ret == 0) {
- if (extra_delayed_refs_bytes > 0)
- btrfs_migrate_to_delayed_refs_rsv(fs_info,
- extra_delayed_refs_bytes);
- return 0;
- }
-
- if (extra_delayed_refs_bytes > 0) {
- bytes -= extra_delayed_refs_bytes;
- ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
- if (ret == 0)
- return 0;
- }
/*
* If we are an emergency flush, which can steal from the global block
* reserve, then attempt to not reserve space for the delayed refs, as
* we will consume space for them from the global block reserve.
*/
- if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
+ if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
bytes -= *delayed_refs_bytes;
*delayed_refs_bytes = 0;
ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
From e58779f47e5eeb4fc9e3707951b81fbe31de5e3b Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Feb 2024 10:39:41 +0100
Subject: [PATCH 540/637] selftests: net: cope with slow env in gro.sh test
The gro self-tests sends the packets to be aggregated with
multiple write operations.
When running is slow environment, it's hard to guarantee that
the GRO engine will wait for the last packet in an intended
train.
The above causes almost deterministic failures in our CI for
the 'large' test-case.
Address the issue explicitly ignoring failures for such case
in slow environments (KSFT_MACHINE_SLOW==true).
Fixes: 7d1575014a63 ("selftests/net: GRO coalesce test")
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/97d3ba83f5a2bfeb36f6bc0fb76724eb3dafb608.1707729403.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/gro.sh | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 19352f106c1d..02c21ff4ca81 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -31,6 +31,11 @@ run_test() {
1>>log.txt
wait "${server_pid}"
exit_code=$?
+ if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \
+ ${exit_code} -ne 0 ]]; then
+ echo "Ignoring errors due to slow environment" 1>&2
+ exit_code=0
+ fi
if [[ "${exit_code}" -eq 0 ]]; then
break;
fi
From a7ee79b9c4553498c78552d12321d85b645f02ca Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Feb 2024 10:43:31 +0100
Subject: [PATCH 541/637] selftests: net: cope with slow env in so_txtime.sh
test
The mentioned test is failing in slow environments:
# SO_TXTIME ipv4 clock monotonic
# ./so_txtime: recv: timeout: Resource temporarily unavailable
not ok 1 selftests: net: so_txtime.sh # exit=1
Tuning the tolerance in the test binary is error-prone and doomed
to failures is slow-enough environment.
Just resort to suppress any error in such cases. Note to suppress
them we need first to refactor a bit the code moving it to explicit
error handling.
Fixes: af5136f95045 ("selftests/net: SO_TXTIME with ETF and FQ")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/2142d9ed4b5c5aa07dd1b455779625d91b175373.1707730902.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/so_txtime.sh | 29 ++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh
index 3f06f4d286a9..5e861ad32a42 100755
--- a/tools/testing/selftests/net/so_txtime.sh
+++ b/tools/testing/selftests/net/so_txtime.sh
@@ -5,6 +5,7 @@
set -e
+readonly ksft_skip=4
readonly DEV="veth0"
readonly BIN="./so_txtime"
@@ -46,7 +47,7 @@ ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}"
ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad
ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad
-do_test() {
+run_test() {
local readonly IP="$1"
local readonly CLOCK="$2"
local readonly TXARGS="$3"
@@ -64,12 +65,25 @@ do_test() {
fi
local readonly START="$(date +%s%N --date="+ 0.1 seconds")"
+
ip netns exec "${NS2}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${RXARGS}" -r &
ip netns exec "${NS1}" "${BIN}" -"${IP}" -c "${CLOCK}" -t "${START}" -S "${SADDR}" -D "${DADDR}" "${TXARGS}"
wait "$!"
}
+do_test() {
+ run_test $@
+ [ $? -ne 0 ] && ret=1
+}
+
+do_fail_test() {
+ run_test $@
+ [ $? -eq 0 ] && ret=1
+}
+
ip netns exec "${NS1}" tc qdisc add dev "${DEV}" root fq
+set +e
+ret=0
do_test 4 mono a,-1 a,-1
do_test 6 mono a,0 a,0
do_test 6 mono a,10 a,10
@@ -77,13 +91,20 @@ do_test 4 mono a,10,b,20 a,10,b,20
do_test 6 mono a,20,b,10 b,20,a,20
if ip netns exec "${NS1}" tc qdisc replace dev "${DEV}" root etf clockid CLOCK_TAI delta 400000; then
- ! do_test 4 tai a,-1 a,-1
- ! do_test 6 tai a,0 a,0
+ do_fail_test 4 tai a,-1 a,-1
+ do_fail_test 6 tai a,0 a,0
do_test 6 tai a,10 a,10
do_test 4 tai a,10,b,20 a,10,b,20
do_test 6 tai a,20,b,10 b,10,a,20
else
echo "tc ($(tc -V)) does not support qdisc etf. skipping"
+ [ $ret -eq 0 ] && ret=$ksft_skip
fi
-echo OK. All tests passed
+if [ $ret -eq 0 ]; then
+ echo OK. All tests passed
+elif [[ $ret -ne $ksft_skip && -n "$KSFT_MACHINE_SLOW" ]]; then
+ echo "Ignoring errors due to slow environment" 1>&2
+ ret=0
+fi
+exit $ret
From a71d0908e32f3dd41e355d83eeadd44d94811fd6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Feb 2024 11:19:23 +0100
Subject: [PATCH 542/637] selftests: net: more strict check in net_helper
The helper waiting for a listener port can match any socket whose
hexadecimal representation of source or destination addresses
matches that of the given port.
Additionally, any socket state is accepted.
All the above can let the helper return successfully before the
relevant listener is actually ready, with unexpected results.
So far I could not find any related failure in the netdev CI, but
the next patch is going to make the critical event more easily
reproducible.
Address the issue matching the port hex only vs the relevant socket
field and additionally checking the socket state for TCP sockets.
Fixes: 3bdd9fd29cb0 ("selftests/net: synchronize udpgro tests' tx and rx connection")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/192b3dbc443d953be32991d1b0ca432bd4c65008.1707731086.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/net_helper.sh | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
index 4fe0befa13fb..6596fe03c77f 100644
--- a/tools/testing/selftests/net/net_helper.sh
+++ b/tools/testing/selftests/net/net_helper.sh
@@ -8,13 +8,16 @@ wait_local_port_listen()
local listener_ns="${1}"
local port="${2}"
local protocol="${3}"
- local port_hex
+ local pattern
local i
- port_hex="$(printf "%04X" "${port}")"
+ pattern=":$(printf "%04X" "${port}") "
+
+ # for tcp protocol additionally check the socket state
+ [ ${protocol} = "tcp" ] && pattern="${pattern}0A"
for i in $(seq 10); do
- if ip netns exec "${listener_ns}" cat /proc/net/"${protocol}"* | \
- grep -q "${port_hex}"; then
+ if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
+ /proc/net/"${protocol}"* | grep -q "${pattern}"; then
break
fi
sleep 0.1
From 20622dc934e178ef11fad396eb272597f21bffe2 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 12 Feb 2024 11:19:24 +0100
Subject: [PATCH 543/637] selftests: net: more pmtu.sh fixes
The netdev CI is reporting failures for the pmtu test:
[ 115.929264] br0: port 2(vxlan_a) entered forwarding state
# 2024/02/08 17:33:22 socat[7871] E bind(7, {AF=10 [0000:0000:0000:0000:0000:0000:0000:0000]:50000}, 28): Address already in use
# 2024/02/08 17:33:22 socat[7877] E write(7, 0x5598fb6ff000, 8192): Connection refused
# TEST: IPv6, bridged vxlan4: PMTU exceptions [FAIL]
# File size 0 mismatches exepcted value in locally bridged vxlan test
The root cause is apparently a socket created by a previous iteration
of the relevant loop still lasting in LAST_ACK state.
Note that even the file size check is racy, the receiver process dumping
the file could still be running in background
Allow the listener to bound on the same local port via SO_REUSEADDR and
collect file output file size only after the listener completion.
Fixes: 136a1b434bbb ("selftests: net: test vxlan pmtu exceptions with tcp")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/4f51c11a1ce7ca7a4dabd926cffff63dadac9ba1.1707731086.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/pmtu.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index d65fdd407d73..cfc84958025a 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1336,16 +1336,16 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
else
TCPDST="TCP:[${dst}]:50000"
fi
- ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile &
+ ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000,reuseaddr STDOUT > $tmpoutfile &
local socat_pid=$!
wait_local_port_listen ${NS_B} 50000 tcp
dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
+ wait ${socat_pid}
size=$(du -sb $tmpoutfile)
size=${size%%/tmp/*}
- wait ${socat_pid}
[ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1
done
From c60d847be7b8e69e419e02a2b3d19c2842a3c35d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 12 Feb 2024 19:30:52 +0000
Subject: [PATCH 544/637] KVM: arm64: Fix double-free following
kvm_pgtable_stage2_free_unlinked()
kvm_pgtable_stage2_free_unlinked() does the final put_page() on the
root page of the sub-tree before returning, so remove the additional
put_page() invocations in the callers.
Cc: Ricardo Koller <ricarkol@google.com>
Fixes: f6a27d6dc51b2 ("KVM: arm64: Drop last page ref in kvm_pgtable_stage2_free_removed()")
Signed-off-by: Will Deacon <will@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240212193052.27765-1-will@kernel.org
---
arch/arm64/kvm/hyp/pgtable.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c651df904fe3..ab9d05fcf98b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1419,7 +1419,6 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
level + 1);
if (ret) {
kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
- mm_ops->put_page(pgtable);
return ERR_PTR(ret);
}
@@ -1502,7 +1501,6 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
if (!stage2_try_break_pte(ctx, mmu)) {
kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
- mm_ops->put_page(childp);
return -EAGAIN;
}
From b6ddaa63f728d26c12048aed76be99c24f435c41 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Fri, 19 Jan 2024 11:08:40 -0800
Subject: [PATCH 545/637] drm/rockchip: vop2: add a missing unlock in
vop2_crtc_atomic_enable()
Unlock before returning on the error path.
Fixes: 5a028e8f062f ("drm/rockchip: vop2: Add support for rk3588")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20240119190841.1619443-1-harshit.m.mogalapalli@oracle.com
---
drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 85b3b4871a1d..fdd768bbd487 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -1985,8 +1985,10 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
clock = vop2_set_intf_mux(vp, rkencoder->crtc_endpoint_id, polflags);
}
- if (!clock)
+ if (!clock) {
+ vop2_unlock(vop2);
return;
+ }
if (vcstate->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
!(vp_data->feature & VOP2_VP_FEATURE_OUTPUT_10BIT))
From 0db0c1770834f39e11a2902e20e1f11a482f4465 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Fri, 9 Feb 2024 11:18:40 +0000
Subject: [PATCH 546/637] ASoC: cs35l56: Workaround for ACPI with broken
spk-id-gpios property
The ACPI in some SoundWire laptops has a spk-id-gpios property but
it points to the wrong Device node. This patch adds a workaround to
try to get the GPIO directly from the correct Device node.
If the attempt to get the GPIOs from the property fails, the workaround
looks for the SDCA node "AF01", which is where the GpioIo resource is
defined. If this exists, a spk-id-gpios mapping is added to that node
and then the GPIO is got from that node using the property.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://msgid.link/r/20240209111840.1543630-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/cs35l56.c | 93 ++++++++++++++++++++++++++++++++++++++
1 file changed, 93 insertions(+)
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 98d3957c66e7..2c1313e34cce 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -5,6 +5,7 @@
// Copyright (C) 2023 Cirrus Logic, Inc. and
// Cirrus Logic International Semiconductor Ltd.
+#include <linux/acpi.h>
#include <linux/completion.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
@@ -15,6 +16,7 @@
#include <linux/module.h>
#include <linux/pm.h>
#include <linux/pm_runtime.h>
+#include <linux/property.h>
#include <linux/regmap.h>
#include <linux/regulator/consumer.h>
#include <linux/slab.h>
@@ -1260,6 +1262,94 @@ static int cs35l56_get_firmware_uid(struct cs35l56_private *cs35l56)
return 0;
}
+/*
+ * Some SoundWire laptops have a spk-id-gpios property but it points to
+ * the wrong ACPI Device node so can't be used to get the GPIO. Try to
+ * find the SDCA node containing the GpioIo resource and add a GPIO
+ * mapping to it.
+ */
+static const struct acpi_gpio_params cs35l56_af01_first_gpio = { 0, 0, false };
+static const struct acpi_gpio_mapping cs35l56_af01_spkid_gpios_mapping[] = {
+ { "spk-id-gpios", &cs35l56_af01_first_gpio, 1 },
+ { }
+};
+
+static void cs35l56_acpi_dev_release_driver_gpios(void *adev)
+{
+ acpi_dev_remove_driver_gpios(adev);
+}
+
+static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l56)
+{
+ struct fwnode_handle *af01_fwnode;
+ const union acpi_object *obj;
+ struct gpio_desc *desc;
+ int ret;
+
+ /* Find the SDCA node containing the GpioIo */
+ af01_fwnode = device_get_named_child_node(cs35l56->base.dev, "AF01");
+ if (!af01_fwnode) {
+ dev_dbg(cs35l56->base.dev, "No AF01 node\n");
+ return -ENOENT;
+ }
+
+ ret = acpi_dev_get_property(ACPI_COMPANION(cs35l56->base.dev),
+ "spk-id-gpios", ACPI_TYPE_PACKAGE, &obj);
+ if (ret) {
+ dev_dbg(cs35l56->base.dev, "Could not get spk-id-gpios package: %d\n", ret);
+ return -ENOENT;
+ }
+
+ /* The broken properties we can handle are a 4-element package (one GPIO) */
+ if (obj->package.count != 4) {
+ dev_warn(cs35l56->base.dev, "Unexpected spk-id element count %d\n",
+ obj->package.count);
+ return -ENOENT;
+ }
+
+ /* Add a GPIO mapping if it doesn't already have one */
+ if (!fwnode_property_present(af01_fwnode, "spk-id-gpios")) {
+ struct acpi_device *adev = to_acpi_device_node(af01_fwnode);
+
+ /*
+ * Can't use devm_acpi_dev_add_driver_gpios() because the
+ * mapping isn't being added to the node pointed to by
+ * ACPI_COMPANION().
+ */
+ ret = acpi_dev_add_driver_gpios(adev, cs35l56_af01_spkid_gpios_mapping);
+ if (ret) {
+ return dev_err_probe(cs35l56->base.dev, ret,
+ "Failed to add gpio mapping to AF01\n");
+ }
+
+ ret = devm_add_action_or_reset(cs35l56->base.dev,
+ cs35l56_acpi_dev_release_driver_gpios,
+ adev);
+ if (ret)
+ return ret;
+
+ dev_dbg(cs35l56->base.dev, "Added spk-id-gpios mapping to AF01\n");
+ }
+
+ desc = fwnode_gpiod_get_index(af01_fwnode, "spk-id", 0, GPIOD_IN, NULL);
+ if (IS_ERR(desc)) {
+ ret = PTR_ERR(desc);
+ return dev_err_probe(cs35l56->base.dev, ret, "Get GPIO from AF01 failed\n");
+ }
+
+ ret = gpiod_get_value_cansleep(desc);
+ gpiod_put(desc);
+
+ if (ret < 0) {
+ dev_err_probe(cs35l56->base.dev, ret, "Error reading spk-id GPIO\n");
+ return ret;
+ }
+
+ dev_info(cs35l56->base.dev, "Got spk-id from AF01\n");
+
+ return ret;
+}
+
int cs35l56_common_probe(struct cs35l56_private *cs35l56)
{
int ret;
@@ -1304,6 +1394,9 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
}
ret = cs35l56_get_speaker_id(&cs35l56->base);
+ if (ACPI_COMPANION(cs35l56->base.dev) && cs35l56->sdw_peripheral && (ret == -ENOENT))
+ ret = cs35l56_try_get_broken_sdca_spkid_gpio(cs35l56);
+
if ((ret < 0) && (ret != -ENOENT))
goto err;
From 8d30528a170905ede9ab6ab81f229e441808590b Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Mon, 12 Feb 2024 23:58:24 -0800
Subject: [PATCH 547/637] nvmet: remove superfluous initialization
Remove superfluous initialization of status variable in
nvmet_execute_admin_connect() and nvmet_execute_io_connect(), since it
will get overwritten by nvmet_copy_from_sgl().
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/target/fabrics-cmd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index d8da840a1c0e..9964ffe347d2 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -209,7 +209,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
struct nvmf_connect_command *c = &req->cmd->connect;
struct nvmf_connect_data *d;
struct nvmet_ctrl *ctrl = NULL;
- u16 status = 0;
+ u16 status;
int ret;
if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
@@ -290,7 +290,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
struct nvmf_connect_data *d;
struct nvmet_ctrl *ctrl;
u16 qid = le16_to_cpu(c->qid);
- u16 status = 0;
+ u16 status;
if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
return;
From 4e07447503f01766ae976207eb3b947437ed8dbc Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 10 Feb 2024 21:01:40 -0500
Subject: [PATCH 548/637] bcachefs: Clamp replicas_required to replicas
This prevents going emergency read only when the user has specified
replicas_required > replicas.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/bcachefs.h | 12 ++++++++++++
fs/bcachefs/btree_update_interior.c | 3 ++-
fs/bcachefs/io_write.c | 1 +
fs/bcachefs/journal_io.c | 4 +++-
fs/bcachefs/journal_reclaim.c | 2 +-
fs/bcachefs/super.c | 4 ++--
6 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index b80c6c9efd8c..69d0d60d50e3 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -1249,6 +1249,18 @@ static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
return stdio;
}
+static inline unsigned metadata_replicas_required(struct bch_fs *c)
+{
+ return min(c->opts.metadata_replicas,
+ c->opts.metadata_replicas_required);
+}
+
+static inline unsigned data_replicas_required(struct bch_fs *c)
+{
+ return min(c->opts.data_replicas,
+ c->opts.data_replicas_required);
+}
+
#define BKEY_PADDED_ONSTACK(key, pad) \
struct { struct bkey_i key; __u64 key ## _pad[pad]; }
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 17a5938aa71a..4530b14ff2c3 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -280,7 +280,8 @@ retry:
writepoint_ptr(&c->btree_write_point),
&devs_have,
res->nr_replicas,
- c->opts.metadata_replicas_required,
+ min(res->nr_replicas,
+ c->opts.metadata_replicas_required),
watermark, 0, cl, &wp);
if (unlikely(ret))
return ERR_PTR(ret);
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index ef3a53f9045a..2c098ac017b3 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -1564,6 +1564,7 @@ CLOSURE_CALLBACK(bch2_write)
BUG_ON(!op->write_point.v);
BUG_ON(bkey_eq(op->pos, POS_MAX));
+ op->nr_replicas_required = min_t(unsigned, op->nr_replicas_required, op->nr_replicas);
op->start_time = local_clock();
bch2_keylist_init(&op->insert_keys, op->inline_keys);
wbio_init(bio)->put_bio = false;
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index bfd6585e746d..47805193f18c 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1478,6 +1478,8 @@ static int journal_write_alloc(struct journal *j, struct journal_buf *w)
c->opts.foreground_target;
unsigned i, replicas = 0, replicas_want =
READ_ONCE(c->opts.metadata_replicas);
+ unsigned replicas_need = min_t(unsigned, replicas_want,
+ READ_ONCE(c->opts.metadata_replicas_required));
rcu_read_lock();
retry:
@@ -1526,7 +1528,7 @@ done:
BUG_ON(bkey_val_u64s(&w->key.k) > BCH_REPLICAS_MAX);
- return replicas >= c->opts.metadata_replicas_required ? 0 : -EROFS;
+ return replicas >= replicas_need ? 0 : -EROFS;
}
static void journal_buf_realloc(struct journal *j, struct journal_buf *buf)
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 820d25e19e5f..2cf626315652 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -205,7 +205,7 @@ void bch2_journal_space_available(struct journal *j)
j->can_discard = can_discard;
- if (nr_online < c->opts.metadata_replicas_required) {
+ if (nr_online < metadata_replicas_required(c)) {
ret = JOURNAL_ERR_insufficient_devices;
goto out;
}
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index b9911402b175..6b23e11825e6 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1428,10 +1428,10 @@ bool bch2_dev_state_allowed(struct bch_fs *c, struct bch_dev *ca,
required = max(!(flags & BCH_FORCE_IF_METADATA_DEGRADED)
? c->opts.metadata_replicas
- : c->opts.metadata_replicas_required,
+ : metadata_replicas_required(c),
!(flags & BCH_FORCE_IF_DATA_DEGRADED)
? c->opts.data_replicas
- : c->opts.data_replicas_required);
+ : data_replicas_required(c));
return nr_rw >= required;
case BCH_MEMBER_STATE_failed:
From 2eeccee86dc75a584a8c7e67a8b824d5168c978f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 12 Feb 2024 20:05:48 -0500
Subject: [PATCH 549/637] bcachefs: Fix check_version_upgrade()
When also downgrading, check_version_upgrade() could pick a new version
greater than the latest supported version.
Fixes:
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/recovery.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 9127d0e3ca2f..21e13bb4335b 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -577,8 +577,9 @@ u64 bch2_recovery_passes_from_stable(u64 v)
static bool check_version_upgrade(struct bch_fs *c)
{
- unsigned latest_compatible = bch2_latest_compatible_version(c->sb.version);
unsigned latest_version = bcachefs_metadata_version_current;
+ unsigned latest_compatible = min(latest_version,
+ bch2_latest_compatible_version(c->sb.version));
unsigned old_version = c->sb.version_upgrade_complete ?: c->sb.version;
unsigned new_version = 0;
@@ -597,7 +598,7 @@ static bool check_version_upgrade(struct bch_fs *c)
new_version = latest_version;
break;
case BCH_VERSION_UPGRADE_none:
- new_version = old_version;
+ new_version = min(old_version, latest_version);
break;
}
}
@@ -774,7 +775,7 @@ int bch2_fs_recovery(struct bch_fs *c)
goto err;
}
- if (!(c->opts.nochanges && c->opts.norecovery)) {
+ if (!c->opts.nochanges) {
mutex_lock(&c->sb_lock);
bool write_sb = false;
@@ -804,7 +805,7 @@ int bch2_fs_recovery(struct bch_fs *c)
if (bch2_check_version_downgrade(c)) {
struct printbuf buf = PRINTBUF;
- prt_str(&buf, "Version downgrade required:\n");
+ prt_str(&buf, "Version downgrade required:");
__le64 passes = ext->recovery_passes_required[0];
bch2_sb_set_downgrade(c,
@@ -812,7 +813,7 @@ int bch2_fs_recovery(struct bch_fs *c)
BCH_VERSION_MINOR(c->sb.version));
passes = ext->recovery_passes_required[0] & ~passes;
if (passes) {
- prt_str(&buf, " running recovery passes: ");
+ prt_str(&buf, "\n running recovery passes: ");
prt_bitflags(&buf, bch2_recovery_passes,
bch2_recovery_passes_from_stable(le64_to_cpu(passes)));
}
From 816054f40a5fdaaed05d9e7f603d2824eeee7e62 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 13 Feb 2024 20:26:09 -0500
Subject: [PATCH 550/637] bcachefs: Fix missing va_end()
Fixes: https://lore.kernel.org/linux-bcachefs/202402131603.E953E2CF@keescook/T/#u
Reported-by: coverity scan
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
fs/bcachefs/printbuf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/bcachefs/printbuf.c b/fs/bcachefs/printbuf.c
index accf246c3233..b27d22925929 100644
--- a/fs/bcachefs/printbuf.c
+++ b/fs/bcachefs/printbuf.c
@@ -56,6 +56,7 @@ void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list args)
va_copy(args2, args);
len = vsnprintf(out->buf + out->pos, printbuf_remaining(out), fmt, args2);
+ va_end(args2);
} while (len + 1 >= printbuf_remaining(out) &&
!bch2_printbuf_make_room(out, len + 1));
From 1fba2bf8e9d5a27b7394856181b6200de7260b79 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 14 Feb 2024 11:00:41 +1100
Subject: [PATCH 551/637] Revert "powerpc/pseries/iommu: Fix iommu
initialisation during DLPAR add"
This reverts commit ed8b94f6e0acd652ce69bd69d678a0c769172df8.
Gaurav reported that there are still problems with the patch and it
should be reverted pending a fuller fix.
Link: https://lore.kernel.org/all/4f6fc1ac-7a76-4447-9d0e-f55c0be373f8@linux.ibm.com/
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
arch/powerpc/include/asm/ppc-pci.h | 3 ---
arch/powerpc/kernel/iommu.c | 21 +++++----------------
arch/powerpc/platforms/pseries/pci_dlpar.c | 4 ----
3 files changed, 5 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index c3a3f3df36d1..ce2b1b5eebdd 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -29,9 +29,6 @@ void *pci_traverse_device_nodes(struct device_node *start,
void *(*fn)(struct device_node *, void *),
void *data);
extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
-extern void ppc_iommu_register_device(struct pci_controller *phb);
-extern void ppc_iommu_unregister_device(struct pci_controller *phb);
-
/* From rtas_pci.h */
extern void init_pci_config_tokens (void);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c6f62e130d55..ebe259bdd462 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1388,21 +1388,6 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
NULL,
};
-void ppc_iommu_register_device(struct pci_controller *phb)
-{
- iommu_device_sysfs_add(&phb->iommu, phb->parent,
- spapr_tce_iommu_groups, "iommu-phb%04x",
- phb->global_number);
- iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
- phb->parent);
-}
-
-void ppc_iommu_unregister_device(struct pci_controller *phb)
-{
- iommu_device_unregister(&phb->iommu);
- iommu_device_sysfs_remove(&phb->iommu);
-}
-
/*
* This registers IOMMU devices of PHBs. This needs to happen
* after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1413,7 +1398,11 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
struct pci_controller *hose;
list_for_each_entry(hose, &hose_list, list_node) {
- ppc_iommu_register_device(hose);
+ iommu_device_sysfs_add(&hose->iommu, hose->parent,
+ spapr_tce_iommu_groups, "iommu-phb%04x",
+ hose->global_number);
+ iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
+ hose->parent);
}
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4448386268d9..4ba824568119 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -35,8 +35,6 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
pseries_msi_allocate_domains(phb);
- ppc_iommu_register_device(phb);
-
/* Create EEH devices for the PHB */
eeh_phb_pe_create(phb);
@@ -78,8 +76,6 @@ int remove_phb_dynamic(struct pci_controller *phb)
}
}
- ppc_iommu_unregister_device(phb);
-
pseries_msi_free_domains(phb);
/* Keep a reference so phb isn't freed yet */
From f1acb109505d983779bbb7e20a1ee6244d2b5736 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 12 Feb 2024 17:42:44 +1100
Subject: [PATCH 552/637] powerpc/kasan: Limit KASAN thread size increase to
32KB
KASAN is seen to increase stack usage, to the point that it was reported
to lead to stack overflow on some 32-bit machines (see link).
To avoid overflows the stack size was doubled for KASAN builds in
commit 3e8635fb2e07 ("powerpc/kasan: Force thread size increase with
KASAN").
However with a 32KB stack size to begin with, the doubling leads to a
64KB stack, which causes build errors:
arch/powerpc/kernel/switch.S:249: Error: operand out of range (0x000000000000fe50 is not between 0xffffffffffff8000 and 0x0000000000007fff)
Although the asm could be reworked, in practice a 32KB stack seems
sufficient even for KASAN builds - the additional usage seems to be in
the 2-3KB range for a 64-bit KASAN build.
So only increase the stack for KASAN if the stack size is < 32KB.
Fixes: 18f14afe2816 ("powerpc/64s: Increase default stack size to 32KB")
Reported-by: Spoorthy <spoorthy@linux.ibm.com>
Reported-by: Benjamin Gray <bgray@linux.ibm.com>
Reviewed-by: Benjamin Gray <bgray@linux.ibm.com>
Link: https://lore.kernel.org/linuxppc-dev/bug-207129-206035@https.bugzilla.kernel.org%2F/
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240212064244.3924505-1-mpe@ellerman.id.au
---
arch/powerpc/include/asm/thread_info.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index bf5dde1a4114..15c5691dd218 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@
#ifdef __KERNEL__
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
#define MIN_THREAD_SHIFT (CONFIG_THREAD_SHIFT + 1)
#else
#define MIN_THREAD_SHIFT CONFIG_THREAD_SHIFT
From eb6d871f4ba49ac8d0537e051fe983a3a4027f61 Mon Sep 17 00:00:00 2001
From: David Engraf <david.engraf@sysgo.com>
Date: Wed, 7 Feb 2024 10:27:58 +0100
Subject: [PATCH 553/637] powerpc/cputable: Add missing PPC_FEATURE_BOOKE on
PPC64 Book-E
Commit e320a76db4b0 ("powerpc/cputable: Split cpu_specs[] out of
cputable.h") moved the cpu_specs to separate header files. Previously
PPC_FEATURE_BOOKE was enabled by CONFIG_PPC_BOOK3E_64. The definition in
cpu_specs_e500mc.h for PPC64 no longer enables PPC_FEATURE_BOOKE.
This breaks user space reading the ELF hwcaps and expect
PPC_FEATURE_BOOKE. Debugging an application with gdb is no longer
working on e5500/e6500 because the 64-bit detection relies on
PPC_FEATURE_BOOKE for Book-E.
Fixes: e320a76db4b0 ("powerpc/cputable: Split cpu_specs[] out of cputable.h")
Cc: stable@vger.kernel.org # v6.1+
Signed-off-by: David Engraf <david.engraf@sysgo.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240207092758.1058893-1-david.engraf@sysgo.com
---
arch/powerpc/kernel/cpu_specs_e500mc.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
index ceb06b109f83..2ae8e9a7b461 100644
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@
#ifdef CONFIG_PPC64
#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
- PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+ PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+ PPC_FEATURE_BOOKE)
#else
#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
PPC_FEATURE_BOOKE)
From ea73179e64131bcd29ba6defd33732abdf8ca14b Mon Sep 17 00:00:00 2001
From: Naveen N Rao <naveen@kernel.org>
Date: Tue, 13 Feb 2024 23:24:10 +0530
Subject: [PATCH 554/637] powerpc/ftrace: Ignore ftrace locations in exit text
sections
Michael reported that we are seeing an ftrace bug on bootup when KASAN
is enabled and we are using -fpatchable-function-entry:
ftrace: allocating 47780 entries in 18 pages
ftrace-powerpc: 0xc0000000020b3d5c: No module provided for non-kernel address
------------[ ftrace bug ]------------
ftrace faulted on modifying
[<c0000000020b3d5c>] 0xc0000000020b3d5c
Initializing ftrace call sites
ftrace record flags: 0
(0)
expected tramp: c00000000008cef4
------------[ cut here ]------------
WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2180 ftrace_bug+0x3c0/0x424
Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 6.5.0-rc3-00120-g0f71dcfb4aef #860
Hardware name: IBM pSeries (emulated by qemu) POWER9 (raw) 0x4e1202 0xf000005 of:SLOF,HEAD hv:linux,kvm pSeries
NIP: c0000000003aa81c LR: c0000000003aa818 CTR: 0000000000000000
REGS: c0000000033cfab0 TRAP: 0700 Not tainted (6.5.0-rc3-00120-g0f71dcfb4aef)
MSR: 8000000002021033 <SF,VEC,ME,IR,DR,RI,LE> CR: 28028240 XER: 00000000
CFAR: c0000000002781a8 IRQMASK: 3
...
NIP [c0000000003aa81c] ftrace_bug+0x3c0/0x424
LR [c0000000003aa818] ftrace_bug+0x3bc/0x424
Call Trace:
ftrace_bug+0x3bc/0x424 (unreliable)
ftrace_process_locs+0x5f4/0x8a0
ftrace_init+0xc0/0x1d0
start_kernel+0x1d8/0x484
With CONFIG_FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY=y and
CONFIG_KASAN=y, compiler emits nops in functions that it generates for
registering and unregistering global variables (unlike with -pg and
-mprofile-kernel where calls to _mcount() are not generated in those
functions). Those functions then end up in INIT_TEXT and EXIT_TEXT
respectively. We don't expect to see any profiled functions in
EXIT_TEXT, so ftrace_init_nop() assumes that all addresses that aren't
in the core kernel text belongs to a module. Since these functions do
not match that criteria, we see the above bug.
Address this by having ftrace ignore all locations in the text exit
sections of vmlinux.
Fixes: 0f71dcfb4aef ("powerpc/ftrace: Add support for -fpatchable-function-entry")
Cc: stable@vger.kernel.org # v6.6+
Reported-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Naveen N Rao <naveen@kernel.org>
Reviewed-by: Benjamin Gray <bgray@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240213175410.1091313-1-naveen@kernel.org
---
arch/powerpc/include/asm/ftrace.h | 10 ++--------
arch/powerpc/include/asm/sections.h | 1 +
arch/powerpc/kernel/trace/ftrace.c | 12 ++++++++++++
arch/powerpc/kernel/trace/ftrace_64_pg.c | 5 +++++
arch/powerpc/kernel/vmlinux.lds.S | 2 ++
5 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 1ebd2ca97f12..107fc5a48456 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -20,14 +20,6 @@
#ifndef __ASSEMBLY__
extern void _mcount(void);
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
- if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
- addr += MCOUNT_INSN_SIZE;
-
- return addr;
-}
-
unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
unsigned long sp);
@@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
#ifdef CONFIG_FUNCTION_TRACER
extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
void ftrace_free_init_tramp(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
#else
static inline void ftrace_free_init_tramp(void) { }
+static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
#endif
#endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index ea26665f82cf..f43f3a6b0051 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t;
extern char __head_end[];
extern char __srwx_boundary[];
+extern char __exittext_begin[], __exittext_end[];
/* Patch sites */
extern s32 patch__call_flush_branch_caches1;
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 82010629cf88..d8d6b4fd9a14 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,10 +27,22 @@
#include <asm/ftrace.h>
#include <asm/syscall.h>
#include <asm/inst.h>
+#include <asm/sections.h>
#define NUM_FTRACE_TRAMPS 2
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+ if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+ return 0;
+
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+ addr += MCOUNT_INSN_SIZE;
+
+ return addr;
+}
+
static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
{
ppc_inst_t op;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 7b85c3b460a3..12fab1803bcf 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -37,6 +37,11 @@
#define NUM_FTRACE_TRAMPS 8
static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+ return addr;
+}
+
static ppc_inst_t
ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
{
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 1c5970df3233..f420df7888a7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -281,7 +281,9 @@ SECTIONS
* to deal with references from __bug_table
*/
.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+ __exittext_begin = .;
EXIT_TEXT
+ __exittext_end = .;
}
. = ALIGN(PAGE_SIZE);
From cbecc9fcbbec60136b0180ba0609c829afed5c81 Mon Sep 17 00:00:00 2001
From: Shrikanth Hegde <sshegde@linux.ibm.com>
Date: Tue, 13 Feb 2024 10:56:35 +0530
Subject: [PATCH 555/637] powerpc/pseries: fix accuracy of stolen time
powerVM hypervisor updates the VPA fields with stolen time data.
It currently reports enqueue_dispatch_tb and ready_enqueue_tb for
this purpose. In linux these two fields are used to report the stolen time.
The VPA fields are updated at the TB frequency. On powerPC its mostly
set at 512Mhz. Hence this needs a conversion to ns when reporting it
back as rest of the kernel timings are in ns. This conversion is already
handled in tb_to_ns function. So use that function to report accurate
stolen time.
Observed this issue and used an Capped Shared Processor LPAR(SPLPAR) to
simplify the experiments. In all these cases, 100% VP Load is run using
stress-ng workload. Values of stolen time is in percentages as reported
by mpstat. With the patch values are close to expected.
6.8.rc1 +Patch
12EC/12VP 0.0 0.0
12EC/24VP 25.7 50.2
12EC/36VP 37.3 69.2
12EC/48VP 38.5 78.3
Fixes: 0e8a63132800 ("powerpc/pseries: Implement CONFIG_PARAVIRT_TIME_ACCOUNTING")
Cc: stable@vger.kernel.org # v6.1+
Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20240213052635.231597-1-sshegde@linux.ibm.com
---
arch/powerpc/platforms/pseries/lpar.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4561667832ed..4e9916bb03d7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
{
struct lppaca *lppaca = &lppaca_of(cpu);
- return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
- be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+ /*
+ * VPA steal time counters are reported at TB frequency. Hence do a
+ * conversion to ns before returning
+ */
+ return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+ be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
}
#endif
From 706c1fa1ab09f11a131fc4d699ce4c0224b1cb2d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jean-Lo=C3=AFc=20Charroud?= <lagiraudiere+linux@free.fr>
Date: Wed, 14 Feb 2024 00:38:31 +0100
Subject: [PATCH 556/637] ALSA: hda/realtek: cs35l41: Add internal speaker
support for ASUS UM3402 with missing DSD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Add the values for the missing DSD properties to the cs35l41 config table.
Signed-off-by: Jean-Loïc Charroud <lagiraudiere+linux@free.fr>
Link: https://lore.kernel.org/r/1435594585.650325975.1707867511062.JavaMail.zimbra@free.fr
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/cs35l41_hda_property.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 57b21285ab6a..87dcb367e239 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -91,6 +91,7 @@ static const struct cs35l41_config cs35l41_config_table[] = {
{ "10431D1F", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
{ "10431DA2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
{ "10431E02", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+ { "10431E12", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
{ "10431EE2", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
@@ -428,6 +429,7 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
{ "CSC3551", "10431D1F", generic_dsd_config },
{ "CSC3551", "10431DA2", generic_dsd_config },
{ "CSC3551", "10431E02", generic_dsd_config },
+ { "CSC3551", "10431E12", generic_dsd_config },
{ "CSC3551", "10431EE2", generic_dsd_config },
{ "CSC3551", "10431F12", generic_dsd_config },
{ "CSC3551", "10431F1F", generic_dsd_config },
From b91050448897663b60b6d15525c8c3ecae28a368 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jean-Lo=C3=AFc=20Charroud?= <lagiraudiere+linux@free.fr>
Date: Wed, 14 Feb 2024 00:42:12 +0100
Subject: [PATCH 557/637] ALSA: hda/realtek: cs35l41: Fix device ID / model
name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The patch 51d976079976c800ef19ed1b542602fcf63f0edb ("ALSA: hda/realtek:
Add quirks for ASUS Zenbook 2022 Models") modified the entry 1043:1e2e
from "ASUS UM3402" to "ASUS UM6702RA/RC" and added another entry for
"ASUS UM3402" with 104e:1ee2.
The first entry was correct, while the new one corresponds to model
"ASUS UM6702RA/RC"
Fix the model names for both devices.
Fixes: 51d976079976 ("ALSA: hda/realtek: Add quirks for ASUS Zenbook 2022 Models")
Signed-off-by: Jean-Loïc Charroud <lagiraudiere+linux@free.fr>
Link: https://lore.kernel.org/r/1656546983.650349575.1707867732866.JavaMail.zimbra@free.fr
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 98886b803bc5..c8adef01e9ec 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10051,11 +10051,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
- SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
- SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
From 852d432a14dbcd34e15a3a3910c5c6869a6d1929 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jean-Lo=C3=AFc=20Charroud?= <lagiraudiere+linux@free.fr>
Date: Wed, 14 Feb 2024 00:44:24 +0100
Subject: [PATCH 558/637] ALSA: hda/realtek: cs35l41: Fix order and duplicates
in quirks table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Move entry {0x1043, 0x16a3, "ASUS UX3402VA"} following device ID order.
Remove duplicate entry for device {0x1043, 0x1f62, "ASUS UX7602ZM"}.
Fixes: 51d976079976 ("ALSA: hda/realtek: Add quirks for ASUS Zenbook 2022 Models")
Signed-off-by: Jean-Loïc Charroud <lagiraudiere+linux@free.fr>
Link: https://lore.kernel.org/r/1969151851.650354669.1707867864074.JavaMail.zimbra@free.fr
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c8adef01e9ec..5d0517465f08 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10005,6 +10005,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x16d3, "ASUS UX5304VA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
@@ -10048,8 +10049,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
From 858b31133dbec88465bcc0a006f4dc43173662b8 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Mon, 12 Feb 2024 00:30:38 +0530
Subject: [PATCH 559/637] octeontx2-af: Remove the PF_FUNC validation for NPC
transmit rules
NPC transmit side mcam rules can use the pcifunc (in packet metadata
added by hardware) of transmitting device for mcam lookup similar to
the channel of receiving device at receive side.
The commit 18603683d766 ("octeontx2-af: Remove channel verification
while installing MCAM rules") removed the receive side channel
verification to save hardware MCAM filters while switching packets
across interfaces but missed removing transmit side checks.
This patch removes transmit side rules validation.
Fixes: 18603683d766 ("octeontx2-af: Remove channel verification while installing MCAM rules")
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../ethernet/marvell/octeontx2/af/rvu_npc.c | 32 -------------------
1 file changed, 32 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 8cfd74ad991c..e5d6156655ba 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -61,28 +61,6 @@ int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena)
return 0;
}
-static int npc_mcam_verify_pf_func(struct rvu *rvu,
- struct mcam_entry *entry_data, u8 intf,
- u16 pcifunc)
-{
- u16 pf_func, pf_func_mask;
-
- if (is_npc_intf_rx(intf))
- return 0;
-
- pf_func_mask = (entry_data->kw_mask[0] >> 32) &
- NPC_KEX_PF_FUNC_MASK;
- pf_func = (entry_data->kw[0] >> 32) & NPC_KEX_PF_FUNC_MASK;
-
- pf_func = be16_to_cpu((__force __be16)pf_func);
- if (pf_func_mask != NPC_KEX_PF_FUNC_MASK ||
- ((pf_func & ~RVU_PFVF_FUNC_MASK) !=
- (pcifunc & ~RVU_PFVF_FUNC_MASK)))
- return -EINVAL;
-
- return 0;
-}
-
void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
{
int blkaddr;
@@ -2851,12 +2829,6 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
else
nix_intf = pfvf->nix_rx_intf;
- if (!is_pffunc_af(pcifunc) &&
- npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
- rc = NPC_MCAM_INVALID_REQ;
- goto exit;
- }
-
/* For AF installed rules, the nix_intf should be set to target NIX */
if (is_pffunc_af(req->hdr.pcifunc))
nix_intf = req->intf;
@@ -3208,10 +3180,6 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
if (!is_npc_interface_valid(rvu, req->intf))
return NPC_MCAM_INVALID_REQ;
- if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
- req->hdr.pcifunc))
- return NPC_MCAM_INVALID_REQ;
-
/* Try to allocate a MCAM entry */
entry_req.hdr.pcifunc = req->hdr.pcifunc;
entry_req.contig = true;
From 6cf9ff463317217d95732a6cce6fbdd12508921a Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 12 Feb 2024 17:34:02 +0300
Subject: [PATCH 560/637] net: smc: fix spurious error message from
__sock_release()
Commit 67f562e3e147 ("net/smc: transfer fasync_list in case of fallback")
leaves the socket's fasync list pointer within a container socket as well.
When the latter is destroyed, '__sock_release()' warns about its non-empty
fasync list, which is a dangling pointer to previously freed fasync list
of an underlying TCP socket. Fix this spurious warning by nullifying
fasync list of a container socket.
Fixes: 67f562e3e147 ("net/smc: transfer fasync_list in case of fallback")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/smc/af_smc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index a2cb30af46cb..0f53a5c6fd9d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -924,6 +924,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
smc->clcsock->file->private_data = smc->clcsock;
smc->clcsock->wq.fasync_list =
smc->sk.sk_socket->wq.fasync_list;
+ smc->sk.sk_socket->wq.fasync_list = NULL;
/* There might be some wait entries remaining
* in smc sk->sk_wq and they should be woken up
From 5d07e432cb387b9f7d4f0e07245705744c7fb05b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Feb 2024 11:07:50 +0100
Subject: [PATCH 561/637] bnad: fix work_queue type mismatch
clang-16 warns about a function pointer cast:
drivers/net/ethernet/brocade/bna/bnad.c:1995:4: error: cast from 'void (*)(struct delayed_work *)' to 'work_func_t' (aka 'void (*)(struct work_struct *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict]
1995 | (work_func_t)bnad_tx_cleanup);
drivers/net/ethernet/brocade/bna/bnad.c:2252:4: error: cast from 'void (*)(void *)' to 'work_func_t' (aka 'void (*)(struct work_struct *)') converts to incompatible function type [-Werror,-Wcast-function-type-strict]
2252 | (work_func_t)(bnad_rx_cleanup));
The problem here is mixing up work_struct and delayed_work, which relies
the former being the first member of the latter.
Change the code to use consistent types here to address the warning and
make it more robust against workqueue interface changes.
Side note: the use of a delayed workqueue for cleaning up TX descriptors
is probably a bad idea since this introduces a noticeable delay. The
driver currently does not appear to use BQL, but if one wanted to add
that, this would have to be changed as well.
Fixes: 01b54b145185 ("bna: tx rx cleanup fix")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/brocade/bna/bnad.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 31191b520b58..c32174484a96 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1091,10 +1091,10 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
* Free all TxQs buffers and then notify TX_E_CLEANUP_DONE to Tx fsm.
*/
static void
-bnad_tx_cleanup(struct delayed_work *work)
+bnad_tx_cleanup(struct work_struct *work)
{
struct bnad_tx_info *tx_info =
- container_of(work, struct bnad_tx_info, tx_cleanup_work);
+ container_of(work, struct bnad_tx_info, tx_cleanup_work.work);
struct bnad *bnad = NULL;
struct bna_tcb *tcb;
unsigned long flags;
@@ -1170,7 +1170,7 @@ bnad_cb_rx_stall(struct bnad *bnad, struct bna_rx *rx)
* Free all RxQs buffers and then notify RX_E_CLEANUP_DONE to Rx fsm.
*/
static void
-bnad_rx_cleanup(void *work)
+bnad_rx_cleanup(struct work_struct *work)
{
struct bnad_rx_info *rx_info =
container_of(work, struct bnad_rx_info, rx_cleanup_work);
@@ -1991,8 +1991,7 @@ bnad_setup_tx(struct bnad *bnad, u32 tx_id)
}
tx_info->tx = tx;
- INIT_DELAYED_WORK(&tx_info->tx_cleanup_work,
- (work_func_t)bnad_tx_cleanup);
+ INIT_DELAYED_WORK(&tx_info->tx_cleanup_work, bnad_tx_cleanup);
/* Register ISR for the Tx object */
if (intr_info->intr_type == BNA_INTR_T_MSIX) {
@@ -2248,8 +2247,7 @@ bnad_setup_rx(struct bnad *bnad, u32 rx_id)
rx_info->rx = rx;
spin_unlock_irqrestore(&bnad->bna_lock, flags);
- INIT_WORK(&rx_info->rx_cleanup_work,
- (work_func_t)(bnad_rx_cleanup));
+ INIT_WORK(&rx_info->rx_cleanup_work, bnad_rx_cleanup);
/*
* Init NAPI, so that state is set to NAPI_STATE_SCHED,
From 9b23fceb4158a3636ce4a2bda28ab03dcfa6a26f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Feb 2024 11:16:34 +0100
Subject: [PATCH 562/637] ethernet: cpts: fix function pointer cast warnings
clang-16 warns about the mismatched prototypes for the devm_* callbacks:
drivers/net/ethernet/ti/cpts.c:691:12: error: cast from 'void (*)(struct clk_hw *)' to 'void (*)(void *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict]
691 | (void(*)(void *))clk_hw_unregister_mux,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/device.h:406:34: note: expanded from macro 'devm_add_action_or_reset'
406 | __devm_add_action_or_reset(dev, action, data, #action)
| ^~~~~~
drivers/net/ethernet/ti/cpts.c:703:12: error: cast from 'void (*)(struct device_node *)' to 'void (*)(void *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict]
703 | (void(*)(void *))of_clk_del_provider,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/device.h:406:34: note: expanded from macro 'devm_add_action_or_reset'
406 | __devm_add_action_or_reset(dev, action, data, #action)
Use separate helper functions for this instead, using the expected prototypes
with a void* argument.
Fixes: a3047a81ba13 ("net: ethernet: ti: cpts: add support for ext rftclk selection")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/ti/cpts.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index bcccf43d368b..dbbea9146040 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -638,6 +638,16 @@ static void cpts_calc_mult_shift(struct cpts *cpts)
freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC));
}
+static void cpts_clk_unregister(void *clk)
+{
+ clk_hw_unregister_mux(clk);
+}
+
+static void cpts_clk_del_provider(void *np)
+{
+ of_clk_del_provider(np);
+}
+
static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
{
struct device_node *refclk_np;
@@ -687,9 +697,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
goto mux_fail;
}
- ret = devm_add_action_or_reset(cpts->dev,
- (void(*)(void *))clk_hw_unregister_mux,
- clk_hw);
+ ret = devm_add_action_or_reset(cpts->dev, cpts_clk_unregister, clk_hw);
if (ret) {
dev_err(cpts->dev, "add clkmux unreg action %d", ret);
goto mux_fail;
@@ -699,8 +707,7 @@ static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
if (ret)
goto mux_fail;
- ret = devm_add_action_or_reset(cpts->dev,
- (void(*)(void *))of_clk_del_provider,
+ ret = devm_add_action_or_reset(cpts->dev, cpts_clk_del_provider,
refclk_np);
if (ret) {
dev_err(cpts->dev, "add clkmux provider unreg action %d", ret);
From 6cdedc18ba7b9dacc36466e27e3267d201948c8d Mon Sep 17 00:00:00 2001
From: Ziqi Zhao <astrajoan@yahoo.com>
Date: Fri, 21 Jul 2023 09:22:26 -0700
Subject: [PATCH 563/637] can: j1939: prevent deadlock by changing
j1939_socks_lock to rwlock
The following 3 locks would race against each other, causing the
deadlock situation in the Syzbot bug report:
- j1939_socks_lock
- active_session_list_lock
- sk_session_queue_lock
A reasonable fix is to change j1939_socks_lock to an rwlock, since in
the rare situations where a write lock is required for the linked list
that j1939_socks_lock is protecting, the code does not attempt to
acquire any more locks. This would break the circular lock dependency,
where, for example, the current thread already locks j1939_socks_lock
and attempts to acquire sk_session_queue_lock, and at the same time,
another thread attempts to acquire j1939_socks_lock while holding
sk_session_queue_lock.
NOTE: This patch along does not fix the unregister_netdevice bug
reported by Syzbot; instead, it solves a deadlock situation to prepare
for one or more further patches to actually fix the Syzbot bug, which
appears to be a reference counting problem within the j1939 codebase.
Reported-by: <syzbot+1591462f226d9cbf0564@syzkaller.appspotmail.com>
Signed-off-by: Ziqi Zhao <astrajoan@yahoo.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/all/20230721162226.8639-1-astrajoan@yahoo.com
[mkl: remove unrelated newline change]
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
net/can/j1939/j1939-priv.h | 2 +-
net/can/j1939/main.c | 2 +-
net/can/j1939/socket.c | 24 ++++++++++++------------
3 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 16af1a7f80f6..74f15592d170 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -86,7 +86,7 @@ struct j1939_priv {
unsigned int tp_max_packet_size;
/* lock for j1939_socks list */
- spinlock_t j1939_socks_lock;
+ rwlock_t j1939_socks_lock;
struct list_head j1939_socks;
struct kref rx_kref;
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index ecff1c947d68..a6fb89fa6278 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -274,7 +274,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
return ERR_PTR(-ENOMEM);
j1939_tp_init(priv);
- spin_lock_init(&priv->j1939_socks_lock);
+ rwlock_init(&priv->j1939_socks_lock);
INIT_LIST_HEAD(&priv->j1939_socks);
mutex_lock(&j1939_netdev_lock);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 14c431663233..94cfc2315e54 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -80,16 +80,16 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk)
jsk->state |= J1939_SOCK_BOUND;
j1939_priv_get(priv);
- spin_lock_bh(&priv->j1939_socks_lock);
+ write_lock_bh(&priv->j1939_socks_lock);
list_add_tail(&jsk->list, &priv->j1939_socks);
- spin_unlock_bh(&priv->j1939_socks_lock);
+ write_unlock_bh(&priv->j1939_socks_lock);
}
static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk)
{
- spin_lock_bh(&priv->j1939_socks_lock);
+ write_lock_bh(&priv->j1939_socks_lock);
list_del_init(&jsk->list);
- spin_unlock_bh(&priv->j1939_socks_lock);
+ write_unlock_bh(&priv->j1939_socks_lock);
j1939_priv_put(priv);
jsk->state &= ~J1939_SOCK_BOUND;
@@ -329,13 +329,13 @@ bool j1939_sk_recv_match(struct j1939_priv *priv, struct j1939_sk_buff_cb *skcb)
struct j1939_sock *jsk;
bool match = false;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
match = j1939_sk_recv_match_one(jsk, skcb);
if (match)
break;
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
return match;
}
@@ -344,11 +344,11 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb)
{
struct j1939_sock *jsk;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
j1939_sk_recv_one(jsk, skb);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
}
static void j1939_sk_sock_destruct(struct sock *sk)
@@ -1080,12 +1080,12 @@ void j1939_sk_errqueue(struct j1939_session *session,
}
/* spread RX notifications to all sockets subscribed to this session */
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
if (j1939_sk_recv_match_one(jsk, &session->skcb))
__j1939_sk_errqueue(session, &jsk->sk, type);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
};
void j1939_sk_send_loop_abort(struct sock *sk, int err)
@@ -1273,7 +1273,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
struct j1939_sock *jsk;
int error_code = ENETDOWN;
- spin_lock_bh(&priv->j1939_socks_lock);
+ read_lock_bh(&priv->j1939_socks_lock);
list_for_each_entry(jsk, &priv->j1939_socks, list) {
jsk->sk.sk_err = error_code;
if (!sock_flag(&jsk->sk, SOCK_DEAD))
@@ -1281,7 +1281,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
j1939_sk_queue_drop_all(priv, jsk, error_code);
}
- spin_unlock_bh(&priv->j1939_socks_lock);
+ read_unlock_bh(&priv->j1939_socks_lock);
}
static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
From efe7cf828039aedb297c1f9920b638fffee6aabc Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 20 Oct 2023 15:38:14 +0200
Subject: [PATCH 564/637] can: j1939: Fix UAF in j1939_sk_match_filter during
setsockopt(SO_J1939_FILTER)
Lock jsk->sk to prevent UAF when setsockopt(..., SO_J1939_FILTER, ...)
modifies jsk->filters while receiving packets.
Following trace was seen on affected system:
==================================================================
BUG: KASAN: slab-use-after-free in j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939]
Read of size 4 at addr ffff888012144014 by task j1939/350
CPU: 0 PID: 350 Comm: j1939 Tainted: G W OE 6.5.0-rc5 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
Call Trace:
print_report+0xd3/0x620
? kasan_complete_mode_report_info+0x7d/0x200
? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939]
kasan_report+0xc2/0x100
? j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939]
__asan_load4+0x84/0xb0
j1939_sk_recv_match_one+0x1af/0x2d0 [can_j1939]
j1939_sk_recv+0x20b/0x320 [can_j1939]
? __kasan_check_write+0x18/0x20
? __pfx_j1939_sk_recv+0x10/0x10 [can_j1939]
? j1939_simple_recv+0x69/0x280 [can_j1939]
? j1939_ac_recv+0x5e/0x310 [can_j1939]
j1939_can_recv+0x43f/0x580 [can_j1939]
? __pfx_j1939_can_recv+0x10/0x10 [can_j1939]
? raw_rcv+0x42/0x3c0 [can_raw]
? __pfx_j1939_can_recv+0x10/0x10 [can_j1939]
can_rcv_filter+0x11f/0x350 [can]
can_receive+0x12f/0x190 [can]
? __pfx_can_rcv+0x10/0x10 [can]
can_rcv+0xdd/0x130 [can]
? __pfx_can_rcv+0x10/0x10 [can]
__netif_receive_skb_one_core+0x13d/0x150
? __pfx___netif_receive_skb_one_core+0x10/0x10
? __kasan_check_write+0x18/0x20
? _raw_spin_lock_irq+0x8c/0xe0
__netif_receive_skb+0x23/0xb0
process_backlog+0x107/0x260
__napi_poll+0x69/0x310
net_rx_action+0x2a1/0x580
? __pfx_net_rx_action+0x10/0x10
? __pfx__raw_spin_lock+0x10/0x10
? handle_irq_event+0x7d/0xa0
__do_softirq+0xf3/0x3f8
do_softirq+0x53/0x80
</IRQ>
<TASK>
__local_bh_enable_ip+0x6e/0x70
netif_rx+0x16b/0x180
can_send+0x32b/0x520 [can]
? __pfx_can_send+0x10/0x10 [can]
? __check_object_size+0x299/0x410
raw_sendmsg+0x572/0x6d0 [can_raw]
? __pfx_raw_sendmsg+0x10/0x10 [can_raw]
? apparmor_socket_sendmsg+0x2f/0x40
? __pfx_raw_sendmsg+0x10/0x10 [can_raw]
sock_sendmsg+0xef/0x100
sock_write_iter+0x162/0x220
? __pfx_sock_write_iter+0x10/0x10
? __rtnl_unlock+0x47/0x80
? security_file_permission+0x54/0x320
vfs_write+0x6ba/0x750
? __pfx_vfs_write+0x10/0x10
? __fget_light+0x1ca/0x1f0
? __rcu_read_unlock+0x5b/0x280
ksys_write+0x143/0x170
? __pfx_ksys_write+0x10/0x10
? __kasan_check_read+0x15/0x20
? fpregs_assert_state_consistent+0x62/0x70
__x64_sys_write+0x47/0x60
do_syscall_64+0x60/0x90
? do_syscall_64+0x6d/0x90
? irqentry_exit+0x3f/0x50
? exc_page_fault+0x79/0xf0
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Allocated by task 348:
kasan_save_stack+0x2a/0x50
kasan_set_track+0x29/0x40
kasan_save_alloc_info+0x1f/0x30
__kasan_kmalloc+0xb5/0xc0
__kmalloc_node_track_caller+0x67/0x160
j1939_sk_setsockopt+0x284/0x450 [can_j1939]
__sys_setsockopt+0x15c/0x2f0
__x64_sys_setsockopt+0x6b/0x80
do_syscall_64+0x60/0x90
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Freed by task 349:
kasan_save_stack+0x2a/0x50
kasan_set_track+0x29/0x40
kasan_save_free_info+0x2f/0x50
__kasan_slab_free+0x12e/0x1c0
__kmem_cache_free+0x1b9/0x380
kfree+0x7a/0x120
j1939_sk_setsockopt+0x3b2/0x450 [can_j1939]
__sys_setsockopt+0x15c/0x2f0
__x64_sys_setsockopt+0x6b/0x80
do_syscall_64+0x60/0x90
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Fixes: 9d71dd0c70099 ("can: add support of SAE J1939 protocol")
Reported-by: Sili Luo <rootlab@huawei.com>
Suggested-by: Sili Luo <rootlab@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/all/20231020133814.383996-1-o.rempel@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
net/can/j1939/j1939-priv.h | 1 +
net/can/j1939/socket.c | 22 ++++++++++++++++++----
2 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 74f15592d170..31a93cae5111 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -301,6 +301,7 @@ struct j1939_sock {
int ifindex;
struct j1939_addr addr;
+ spinlock_t filters_lock;
struct j1939_filter *filters;
int nfilters;
pgn_t pgn_rx_filter;
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 94cfc2315e54..305dd72c844c 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk,
static bool j1939_sk_match_filter(struct j1939_sock *jsk,
const struct j1939_sk_buff_cb *skcb)
{
- const struct j1939_filter *f = jsk->filters;
- int nfilter = jsk->nfilters;
+ const struct j1939_filter *f;
+ int nfilter;
+
+ spin_lock_bh(&jsk->filters_lock);
+
+ f = jsk->filters;
+ nfilter = jsk->nfilters;
if (!nfilter)
/* receive all when no filters are assigned */
- return true;
+ goto filter_match_found;
for (; nfilter; ++f, --nfilter) {
if ((skcb->addr.pgn & f->pgn_mask) != f->pgn)
@@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk,
continue;
if ((skcb->addr.src_name & f->name_mask) != f->name)
continue;
- return true;
+ goto filter_match_found;
}
+
+ spin_unlock_bh(&jsk->filters_lock);
return false;
+
+filter_match_found:
+ spin_unlock_bh(&jsk->filters_lock);
+ return true;
}
static bool j1939_sk_recv_match_one(struct j1939_sock *jsk,
@@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk)
atomic_set(&jsk->skb_pending, 0);
spin_lock_init(&jsk->sk_session_queue_lock);
INIT_LIST_HEAD(&jsk->sk_session_queue);
+ spin_lock_init(&jsk->filters_lock);
/* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */
sock_set_flag(sk, SOCK_RCU_FREE);
@@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname,
}
lock_sock(&jsk->sk);
+ spin_lock_bh(&jsk->filters_lock);
ofilters = jsk->filters;
jsk->filters = filters;
jsk->nfilters = count;
+ spin_unlock_bh(&jsk->filters_lock);
release_sock(&jsk->sk);
kfree(ofilters);
return 0;
From 2aa0a5e65eae27dbd96faca92c84ecbf6f492d42 Mon Sep 17 00:00:00 2001
From: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Date: Mon, 6 Nov 2023 19:01:58 +0100
Subject: [PATCH 565/637] can: netlink: Fix TDCO calculation using the old data
bittiming
The TDCO calculation was done using the currently applied data bittiming,
instead of the newly computed data bittiming, which means that the TDCO
had an invalid value unless setting the same data bittiming twice.
Fixes: d99755f71a80 ("can: netlink: add interface for CAN-FD Transmitter Delay Compensation (TDC)")
Signed-off-by: Maxime Jayat <maxime.jayat@mobile-devices.fr>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/40579c18-63c0-43a4-8d4c-f3a6c1c0b417@munic.io
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
drivers/net/can/dev/netlink.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 036d85ef07f5..dfdc039d92a6 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -346,7 +346,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
/* Neither of TDC parameters nor TDC flags are
* provided: do calculation
*/
- can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming,
+ can_calc_tdco(&priv->tdc, priv->tdc_const, &dbt,
&priv->ctrlmode, priv->ctrlmode_supported);
} /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly
* turned off. TDC is disabled: do nothing
From 0846dd77c8349ec92ca0079c9c71d130f34cb192 Mon Sep 17 00:00:00 2001
From: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Date: Tue, 13 Feb 2024 10:05:22 -0600
Subject: [PATCH 566/637] powerpc/iommu: Fix the missing iommu_group_put()
during platform domain attach
The function spapr_tce_platform_iommu_attach_dev() is missing to call
iommu_group_put() when the domain is already set. This refcount leak
shows up with BUG_ON() during DLPAR remove operation as:
KernelBug: Kernel bug in state 'None': kernel BUG at arch/powerpc/platforms/pseries/iommu.c:100!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=8192 NUMA pSeries
<snip>
Hardware name: IBM,9080-HEX POWER10 (raw) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_016) hv:phyp pSeries
NIP: c0000000000ff4d4 LR: c0000000000ff4cc CTR: 0000000000000000
REGS: c0000013aed5f840 TRAP: 0700 Tainted: G I (6.8.0-rc3-autotest-g99bd3cb0d12e)
MSR: 8000000000029033 <SF,EE,ME,IR,DR,RI,LE> CR: 44002402 XER: 20040000
CFAR: c000000000a0d170 IRQMASK: 0
...
NIP iommu_reconfig_notifier+0x94/0x200
LR iommu_reconfig_notifier+0x8c/0x200
Call Trace:
iommu_reconfig_notifier+0x8c/0x200 (unreliable)
notifier_call_chain+0xb8/0x19c
blocking_notifier_call_chain+0x64/0x98
of_reconfig_notify+0x44/0xdc
of_detach_node+0x78/0xb0
ofdt_write.part.0+0x86c/0xbb8
proc_reg_write+0xf4/0x150
vfs_write+0xf8/0x488
ksys_write+0x84/0x140
system_call_exception+0x138/0x330
system_call_vectored_common+0x15c/0x2ec
The patch adds the missing iommu_group_put() call.
Fixes: a8ca9fc9134c ("powerpc/iommu: Do not do platform domain attach atctions after probe")
Reported-by: Venkat Rao Bagalkote <venkat88@linux.vnet.ibm.com>
Closes: https://lore.kernel.org/all/274e0d2b-b5cc-475e-94e6-8427e88e271d@linux.vnet.ibm.com/
Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.vnet.ibm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/170784021983.6249.10039296655906636112.stgit@linux.ibm.com
---
arch/powerpc/kernel/iommu.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ebe259bdd462..df17b33b89d1 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1290,8 +1290,10 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
int ret = -EINVAL;
/* At first attach the ownership is already set */
- if (!domain)
+ if (!domain) {
+ iommu_group_put(grp);
return 0;
+ }
if (!grp)
return -ENODEV;
From 8746c6c9dfa31d269c65dd52ab42fde0720b7d91 Mon Sep 17 00:00:00 2001
From: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Date: Wed, 14 Feb 2024 18:48:52 +0530
Subject: [PATCH 567/637] drm/buddy: Fix alloc_range() error handling code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Few users have observed display corruption when they boot
the machine to KDE Plasma or playing games. We have root
caused the problem that whenever alloc_range() couldn't
find the required memory blocks the function was returning
SUCCESS in some of the corner cases.
The right approach would be if the total allocated size
is less than the required size, the function should
return -ENOSPC.
Cc: <stable@vger.kernel.org> # 6.7+
Fixes: 0a1844bf0b53 ("drm/buddy: Improve contiguous memory allocation")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3097
Tested-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20240207174456.341121-1-Arunpravin.PaneerSelvam@amd.com/
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240214131853.5934-1-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/drm_buddy.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index f57e6d74fb0e..c1a99bf4dffd 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -539,6 +539,12 @@ static int __alloc_range(struct drm_buddy *mm,
} while (1);
list_splice_tail(&allocated, blocks);
+
+ if (total_allocated < size) {
+ err = -ENOSPC;
+ goto err_free;
+ }
+
return 0;
err_undo:
From a64056bb5a3215bd31c8ce17d609ba0f4d5c55ea Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Wed, 14 Feb 2024 18:48:53 +0530
Subject: [PATCH 568/637] drm/tests/drm_buddy: add alloc_contiguous test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Sanity check DRM_BUDDY_CONTIGUOUS_ALLOCATION.
v2: Fix checkpatch warnings.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240214131853.5934-2-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/tests/drm_buddy_test.c | 89 ++++++++++++++++++++++++++
1 file changed, 89 insertions(+)
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index ea2af6bd9abe..fee6bec757d1 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -8,6 +8,7 @@
#include <linux/prime_numbers.h>
#include <linux/sched/signal.h>
+#include <linux/sizes.h>
#include <drm/drm_buddy.h>
@@ -18,6 +19,93 @@ static inline u64 get_size(int order, u64 chunk_size)
return (1 << order) * chunk_size;
}
+static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+{
+ u64 mm_size, ps = SZ_4K, i, n_pages, total;
+ struct drm_buddy_block *block;
+ struct drm_buddy mm;
+ LIST_HEAD(left);
+ LIST_HEAD(middle);
+ LIST_HEAD(right);
+ LIST_HEAD(allocated);
+
+ mm_size = 16 * 3 * SZ_4K;
+
+ KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+
+ /*
+ * Idea is to fragment the address space by alternating block
+ * allocations between three different lists; one for left, middle and
+ * right. We can then free a list to simulate fragmentation. In
+ * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+ * including the try_harder path.
+ */
+
+ i = 0;
+ n_pages = mm_size / ps;
+ do {
+ struct list_head *list;
+ int slot = i % 3;
+
+ if (slot == 0)
+ list = &left;
+ else if (slot == 1)
+ list = &middle;
+ else
+ list = &right;
+ KUNIT_ASSERT_FALSE_MSG(test,
+ drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ ps, ps, list, 0),
+ "buddy_alloc hit an error size=%d\n",
+ ps);
+ } while (++i < n_pages);
+
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%d\n", 3 * ps);
+
+ drm_buddy_free_list(&mm, &middle);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 3 * ps);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &right);
+ KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc didn't error size=%llu\n", 3 * ps);
+ /*
+ * At this point we should have enough contiguous space for 2 blocks,
+ * however they are never buddies (since we freed middle and right) so
+ * will require the try_harder logic to find them.
+ */
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 2 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%d\n", 2 * ps);
+
+ drm_buddy_free_list(&mm, &left);
+ KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ 3 * ps, ps, &allocated,
+ DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ "buddy_alloc hit an error size=%d\n", 3 * ps);
+
+ total = 0;
+ list_for_each_entry(block, &allocated, link)
+ total += drm_buddy_block_size(&mm, block);
+
+ KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
+
+ drm_buddy_free_list(&mm, &allocated);
+ drm_buddy_fini(&mm);
+}
+
static void drm_test_buddy_alloc_pathological(struct kunit *test)
{
u64 mm_size, size, start = 0;
@@ -280,6 +368,7 @@ static struct kunit_case drm_buddy_tests[] = {
KUNIT_CASE(drm_test_buddy_alloc_optimistic),
KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
KUNIT_CASE(drm_test_buddy_alloc_pathological),
+ KUNIT_CASE(drm_test_buddy_alloc_contiguous),
{}
};
From e20f378d993b1034eebe3ae78e67f3ed10e75356 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 9 Feb 2024 16:34:54 +0000
Subject: [PATCH 569/637] nvmem: include bit index in cell sysfs file name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Creating sysfs files for all Cells caused a boot failure for linux-6.8-rc1 on
Apple M1, which (in downstream dts files) has multiple nvmem cells that use the
same byte address. This causes the device probe to fail with
[ 0.605336] sysfs: cannot create duplicate filename '/devices/platform/soc@200000000/2922bc000.efuse/apple_efuses_nvmem0/cells/efuse@a10'
[ 0.605347] CPU: 7 PID: 1 Comm: swapper/0 Tainted: G S 6.8.0-rc1-arnd-5+ #133
[ 0.605355] Hardware name: Apple Mac Studio (M1 Ultra, 2022) (DT)
[ 0.605362] Call trace:
[ 0.605365] show_stack+0x18/0x2c
[ 0.605374] dump_stack_lvl+0x60/0x80
[ 0.605383] dump_stack+0x18/0x24
[ 0.605388] sysfs_warn_dup+0x64/0x80
[ 0.605395] sysfs_add_bin_file_mode_ns+0xb0/0xd4
[ 0.605402] internal_create_group+0x268/0x404
[ 0.605409] sysfs_create_groups+0x38/0x94
[ 0.605415] devm_device_add_groups+0x50/0x94
[ 0.605572] nvmem_populate_sysfs_cells+0x180/0x1b0
[ 0.605682] nvmem_register+0x38c/0x470
[ 0.605789] devm_nvmem_register+0x1c/0x6c
[ 0.605895] apple_efuses_probe+0xe4/0x120
[ 0.606000] platform_probe+0xa8/0xd0
As far as I can tell, this is a problem for any device with multiple cells on
different bits of the same address. Avoid the issue by changing the file name
to include the first bit number.
Fixes: 0331c611949f ("nvmem: core: Expose cells through sysfs")
Link: https://github.com/AsahiLinux/linux/blob/bd0a1a7d4/arch/arm64/boot/dts/apple/t600x-dieX.dtsi#L156
Cc: <regressions@lists.linux.dev>
Cc: Miquel Raynal <miquel.raynal@bootlin.com>
Cc: Rafał Miłecki <rafal@milecki.pl>
Cc: Chen-Yu Tsai <wenst@chromium.org>
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <asahi@lists.linux.dev>
Cc: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Eric Curtin <ecurtin@redhat.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20240209163454.98051-1-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/ABI/testing/sysfs-nvmem-cells | 16 ++++++++--------
drivers/nvmem/core.c | 5 +++--
2 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-nvmem-cells b/Documentation/ABI/testing/sysfs-nvmem-cells
index 7af70adf3690..c7c9444f92a8 100644
--- a/Documentation/ABI/testing/sysfs-nvmem-cells
+++ b/Documentation/ABI/testing/sysfs-nvmem-cells
@@ -4,18 +4,18 @@ KernelVersion: 6.5
Contact: Miquel Raynal <miquel.raynal@bootlin.com>
Description:
The "cells" folder contains one file per cell exposed by the
- NVMEM device. The name of the file is: <name>@<where>, with
- <name> being the cell name and <where> its location in the NVMEM
- device, in hexadecimal (without the '0x' prefix, to mimic device
- tree node names). The length of the file is the size of the cell
- (when known). The content of the file is the binary content of
- the cell (may sometimes be ASCII, likely without trailing
- character).
+ NVMEM device. The name of the file is: "<name>@<byte>,<bit>",
+ with <name> being the cell name and <where> its location in
+ the NVMEM device, in hexadecimal bytes and bits (without the
+ '0x' prefix, to mimic device tree node names). The length of
+ the file is the size of the cell (when known). The content of
+ the file is the binary content of the cell (may sometimes be
+ ASCII, likely without trailing character).
Note: This file is only present if CONFIG_NVMEM_SYSFS
is enabled.
Example::
- hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d
+ hexdump -C /sys/bus/nvmem/devices/1-00563/cells/product-name@d,0
00000000 54 4e 34 38 4d 2d 50 2d 44 4e |TN48M-P-DN|
0000000a
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 980123fb4dde..eb357ac2e54a 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -460,8 +460,9 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
list_for_each_entry(entry, &nvmem->cells, node) {
sysfs_bin_attr_init(&attrs[i]);
attrs[i].attr.name = devm_kasprintf(&nvmem->dev, GFP_KERNEL,
- "%s@%x", entry->name,
- entry->offset);
+ "%s@%x,%x", entry->name,
+ entry->offset,
+ entry->bit_offset);
attrs[i].attr.mode = 0444;
attrs[i].size = entry->bytes;
attrs[i].read = &nvmem_cell_attr_read;
From 2394ac4145ea91b92271e675a09af2a9ea6840b7 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 14 Feb 2024 11:20:46 -0500
Subject: [PATCH 570/637] tracing: Inform kmemleak of saved_cmdlines allocation
The allocation of the struct saved_cmdlines_buffer structure changed from:
s = kmalloc(sizeof(*s), GFP_KERNEL);
s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
to:
orig_size = sizeof(*s) + val * TASK_COMM_LEN;
order = get_order(orig_size);
size = 1 << (order + PAGE_SHIFT);
page = alloc_pages(GFP_KERNEL, order);
if (!page)
return NULL;
s = page_address(page);
memset(s, 0, sizeof(*s));
s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
Where that s->saved_cmdlines allocation looks to be a dangling allocation
to kmemleak. That's because kmemleak only keeps track of kmalloc()
allocations. For allocations that use page_alloc() directly, the kmemleak
needs to be explicitly informed about it.
Add kmemleak_alloc() and kmemleak_free() around the page allocation so
that it doesn't give the following false positive:
unreferenced object 0xffff8881010c8000 (size 32760):
comm "swapper", pid 0, jiffies 4294667296
hex dump (first 32 bytes):
ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................
ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................
backtrace (crc ae6ec1b9):
[<ffffffff86722405>] kmemleak_alloc+0x45/0x80
[<ffffffff8414028d>] __kmalloc_large_node+0x10d/0x190
[<ffffffff84146ab1>] __kmalloc+0x3b1/0x4c0
[<ffffffff83ed7103>] allocate_cmdlines_buffer+0x113/0x230
[<ffffffff88649c34>] tracer_alloc_buffers.isra.0+0x124/0x460
[<ffffffff8864a174>] early_trace_init+0x14/0xa0
[<ffffffff885dd5ae>] start_kernel+0x12e/0x3c0
[<ffffffff885f5758>] x86_64_start_reservations+0x18/0x30
[<ffffffff885f582b>] x86_64_start_kernel+0x7b/0x80
[<ffffffff83a001c3>] secondary_startup_64_no_verify+0x15e/0x16b
Link: https://lore.kernel.org/linux-trace-kernel/87r0hfnr9r.fsf@kernel.org/
Link: https://lore.kernel.org/linux-trace-kernel/20240214112046.09a322d6@gandalf.local.home
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 44dc5c41b5b1 ("tracing: Fix wasted memory in saved_cmdlines logic")
Reported-by: Kalle Valo <kvalo@kernel.org>
Tested-by: Kalle Valo <kvalo@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index aa54810e8b56..8198bfc54b58 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -39,6 +39,7 @@
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/panic_notifier.h>
+#include <linux/kmemleak.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/fs.h>
@@ -2339,6 +2340,7 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
kfree(s->map_cmdline_to_pid);
+ kmemleak_free(s);
free_pages((unsigned long)s, order);
}
@@ -2358,6 +2360,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
return NULL;
s = page_address(page);
+ kmemleak_alloc(s, size, 1, GFP_KERNEL);
memset(s, 0, sizeof(*s));
/* Round up to actual allocation */
From c56d055893cbe97848611855d1c97d0ab171eccc Mon Sep 17 00:00:00 2001
From: Kunwu Chan <chentao@kylinos.cn>
Date: Mon, 15 Jan 2024 16:28:25 +0800
Subject: [PATCH 571/637] igb: Fix string truncation warnings in
igb_set_fw_version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit 1978d3ead82c ("intel: fix string truncation warnings")
fixes '-Wformat-truncation=' warnings in igb_main.c by using kasprintf.
drivers/net/ethernet/intel/igb/igb_main.c:3092:53: warning：‘%d’ directive output may be truncated writing between 1 and 5 bytes into a region of size between 1 and 13 [-Wformat-truncation=]
3092 | "%d.%d, 0x%08x, %d.%d.%d",
| ^~
drivers/net/ethernet/intel/igb/igb_main.c:3092:34: note：directive argument in the range [0, 65535]
3092 | "%d.%d, 0x%08x, %d.%d.%d",
| ^~~~~~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/intel/igb/igb_main.c:3092:34: note：directive argument in the range [0, 65535]
drivers/net/ethernet/intel/igb/igb_main.c:3090:25: note：‘snprintf’ output between 23 and 43 bytes into a destination of size 32
kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure.
Fix this warning by using a larger space for adapter->fw_version,
and then fall back and continue to use snprintf.
Fixes: 1978d3ead82c ("intel: fix string truncation warnings")
Signed-off-by: Kunwu Chan <chentao@kylinos.cn>
Cc: Kunwu Chan <kunwu.chan@hotmail.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/igb/igb.h | 2 +-
drivers/net/ethernet/intel/igb/igb_main.c | 35 ++++++++++++-----------
2 files changed, 19 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index a2b759531cb7..3c2dc7bdebb5 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -637,7 +637,7 @@ struct igb_adapter {
struct timespec64 period;
} perout[IGB_N_PEROUT];
- char fw_version[32];
+ char fw_version[48];
#ifdef CONFIG_IGB_HWMON
struct hwmon_buff *igb_hwmon_buff;
bool ets;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 4df8d4153aa5..cebb44f51d5f 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3069,7 +3069,6 @@ void igb_set_fw_version(struct igb_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
struct e1000_fw_version fw;
- char *lbuf;
igb_get_fw_version(hw, &fw);
@@ -3077,34 +3076,36 @@ void igb_set_fw_version(struct igb_adapter *adapter)
case e1000_i210:
case e1000_i211:
if (!(igb_get_flash_presence_i210(hw))) {
- lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d",
- fw.invm_major, fw.invm_minor,
- fw.invm_img_type);
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%2d.%2d-%d",
+ fw.invm_major, fw.invm_minor,
+ fw.invm_img_type);
break;
}
fallthrough;
default:
/* if option rom is valid, display its version too */
if (fw.or_valid) {
- lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d",
- fw.eep_major, fw.eep_minor,
- fw.etrack_id, fw.or_major, fw.or_build,
- fw.or_patch);
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%d.%d, 0x%08x, %d.%d.%d",
+ fw.eep_major, fw.eep_minor, fw.etrack_id,
+ fw.or_major, fw.or_build, fw.or_patch);
/* no option rom */
} else if (fw.etrack_id != 0X0000) {
- lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x",
- fw.eep_major, fw.eep_minor,
- fw.etrack_id);
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%d.%d, 0x%08x",
+ fw.eep_major, fw.eep_minor, fw.etrack_id);
} else {
- lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major,
- fw.eep_minor, fw.eep_build);
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%d.%d.%d",
+ fw.eep_major, fw.eep_minor, fw.eep_build);
}
break;
}
-
- /* the truncate happens here if it doesn't fit */
- strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version));
- kfree(lbuf);
}
/**
From 55ea989977f4e11a1c3bdfabb51295090bb0f7d6 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Wed, 24 Jan 2024 07:57:00 +0200
Subject: [PATCH 572/637] igc: Remove temporary workaround
PHY_CONTROL register works as defined in the IEEE 802.3 specification
(IEEE 802.3-2008 22.2.4.1). Tidy up the temporary workaround.
User impact: PHY can now be powered down when the ethernet link is down.
Testing hints: ip link set down <device> (or just disconnect the
ethernet cable).
Oldest tested NVM version is: 1045:740.
Fixes: 5586838fe9ce ("igc: Add code for PHY support")
Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/igc/igc_phy.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 7cd8716d2ffa..861f37076861 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -130,11 +130,7 @@ void igc_power_down_phy_copper(struct igc_hw *hw)
/* The PHY will retain its settings across a power down/up cycle */
hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
mii_reg |= MII_CR_POWER_DOWN;
-
- /* Temporary workaround - should be removed when PHY will implement
- * IEEE registers as properly
- */
- /* hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);*/
+ hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
usleep_range(1000, 2000);
}
From d8bdd795d383a23e38ac48a40d3d223caf47b290 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Wed, 14 Feb 2024 17:05:38 +0100
Subject: [PATCH 573/637] lsm: fix integer overflow in lsm_set_self_attr()
syscall
security_setselfattr() has an integer overflow bug that leads to
out-of-bounds access when userspace provides bogus input:
`lctx->ctx_len + sizeof(*lctx)` is checked against `lctx->len` (and,
redundantly, also against `size`), but there are no checks on
`lctx->ctx_len`.
Therefore, userspace can provide an `lsm_ctx` with `->ctx_len` set to a
value between `-sizeof(struct lsm_ctx)` and -1, and this bogus `->ctx_len`
will then be passed to an LSM module as a buffer length, causing LSM
modules to perform out-of-bounds accesses.
The following reproducer will demonstrate this under ASAN (if AppArmor is
loaded as an LSM):
```
struct lsm_ctx {
uint64_t id;
uint64_t flags;
uint64_t len;
uint64_t ctx_len;
char ctx[];
};
int main(void) {
size_t size = sizeof(struct lsm_ctx);
struct lsm_ctx *ctx = malloc(size);
ctx->id = 104/*LSM_ID_APPARMOR*/;
ctx->flags = 0;
ctx->len = size;
ctx->ctx_len = -sizeof(struct lsm_ctx);
syscall(
460/*__NR_lsm_set_self_attr*/,
/*attr=*/ 100/*LSM_ATTR_CURRENT*/,
/*ctx=*/ ctx,
/*size=*/ size,
/*flags=*/ 0
);
}
```
Fixes: a04a1198088a ("LSM: syscalls for current process attributes")
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
[PM: subj tweak, removed ref to ASAN splat that isn't included]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
security/security.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/security/security.c b/security/security.c
index 3aaad75c9ce8..7035ee35a393 100644
--- a/security/security.c
+++ b/security/security.c
@@ -29,6 +29,7 @@
#include <linux/backing-dev.h>
#include <linux/string.h>
#include <linux/msg.h>
+#include <linux/overflow.h>
#include <net/flow.h>
/* How many LSMs were built into the kernel? */
@@ -4015,6 +4016,7 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
struct security_hook_list *hp;
struct lsm_ctx *lctx;
int rc = LSM_RET_DEFAULT(setselfattr);
+ u64 required_len;
if (flags)
return -EINVAL;
@@ -4027,8 +4029,9 @@ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
if (IS_ERR(lctx))
return PTR_ERR(lctx);
- if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) ||
- lctx->len < lctx->ctx_len + sizeof(*lctx)) {
+ if (size < lctx->len ||
+ check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) ||
+ lctx->len < required_len) {
rc = -EINVAL;
goto free_out;
}
From 3b9ab248bc45abf8c2365ed3eec86cdefd4d626a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 2 Feb 2024 10:31:42 +0900
Subject: [PATCH 574/637] kbuild: use 4-space indentation when followed by
conditionals
GNU Make manual [1] clearly forbids a tab at the beginning of the
conditional directive line:
"Extra spaces are allowed and ignored at the beginning of the
conditional directive line, but a tab is not allowed."
This will not work for the next release of GNU Make, hence commit
82175d1f9430 ("kbuild: Replace tabs with spaces when followed by
conditionals") replaced the inappropriate tabs with 8 spaces.
However, the 8-space indentation cannot be visually distinguished.
Linus suggested 2-4 spaces for those nested if-statements. [2]
This commit redoes the replacement with 4 spaces.
[1]: https://www.gnu.org/software/make/manual/make.html#Conditional-Syntax
[2]: https://lore.kernel.org/all/CAHk-=whJKZNZWsa-VNDKafS_VfY4a5dAjG-r8BZgWk_a-xSepw@mail.gmail.com/
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
Makefile | 12 ++++++------
arch/m68k/Makefile | 4 ++--
arch/parisc/Makefile | 4 ++--
arch/x86/Makefile | 8 ++++----
4 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/Makefile b/Makefile
index 7e0b2ad98905..ed80c7d98a7e 100644
--- a/Makefile
+++ b/Makefile
@@ -294,15 +294,15 @@ may-sync-config := 1
single-build :=
ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
- ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
+ ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
need-config :=
- endif
+ endif
endif
ifneq ($(filter $(no-sync-config-targets), $(MAKECMDGOALS)),)
- ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
+ ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
may-sync-config :=
- endif
+ endif
endif
need-compiler := $(may-sync-config)
@@ -323,9 +323,9 @@ endif
# We cannot build single targets and the others at the same time
ifneq ($(filter $(single-targets), $(MAKECMDGOALS)),)
single-build := 1
- ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
+ ifneq ($(filter-out $(single-targets), $(MAKECMDGOALS)),)
mixed-build := 1
- endif
+ endif
endif
# For "make -j clean all", "make -j mrproper defconfig all", etc.
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 76ef1a67c361..0abcf994ce55 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -15,10 +15,10 @@
KBUILD_DEFCONFIG := multi_defconfig
ifdef cross_compiling
- ifeq ($(CROSS_COMPILE),)
+ ifeq ($(CROSS_COMPILE),)
CROSS_COMPILE := $(call cc-cross-prefix, \
m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-)
- endif
+ endif
endif
#
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 7486b3b30594..316f84f1d15c 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -50,12 +50,12 @@ export CROSS32CC
# Set default cross compiler for kernel build
ifdef cross_compiling
- ifeq ($(CROSS_COMPILE),)
+ ifeq ($(CROSS_COMPILE),)
CC_SUFFIXES = linux linux-gnu unknown-linux-gnu suse-linux
CROSS_COMPILE := $(call cc-cross-prefix, \
$(foreach a,$(CC_ARCHES), \
$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
- endif
+ endif
endif
ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2264db14a25d..da8f3caf2781 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y)
# temporary until string.h is fixed
KBUILD_CFLAGS += -ffreestanding
- ifeq ($(CONFIG_STACKPROTECTOR),y)
- ifeq ($(CONFIG_SMP),y)
+ ifeq ($(CONFIG_STACKPROTECTOR),y)
+ ifeq ($(CONFIG_SMP),y)
KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
- else
+ else
KBUILD_CFLAGS += -mstack-protector-guard=global
- endif
endif
+ endif
else
BITS := 64
UTS_MACHINE := x86_64
From f44bff19268517ee98e80e944cad0f04f1db72e3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 12 Feb 2024 12:19:04 +0100
Subject: [PATCH 575/637] i2c: pasemi: split driver into two separate modules
On powerpc, it is possible to compile test both the new apple (arm) and
old pasemi (powerpc) drivers for the i2c hardware at the same time,
which leads to a warning about linking the same object file twice:
scripts/Makefile.build:244: drivers/i2c/busses/Makefile: i2c-pasemi-core.o is added to multiple modules: i2c-apple i2c-pasemi
Rework the driver to have an explicit helper module, letting Kbuild
take care of whether this should be built-in or a loadable driver.
Fixes: 9bc5f4f660ff ("i2c: pasemi: Split pci driver to its own file")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
drivers/i2c/busses/Makefile | 6 ++----
drivers/i2c/busses/i2c-pasemi-core.c | 6 ++++++
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 3757b9391e60..aa0ee8ecd6f2 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -90,10 +90,8 @@ obj-$(CONFIG_I2C_NPCM) += i2c-npcm7xx.o
obj-$(CONFIG_I2C_OCORES) += i2c-ocores.o
obj-$(CONFIG_I2C_OMAP) += i2c-omap.o
obj-$(CONFIG_I2C_OWL) += i2c-owl.o
-i2c-pasemi-objs := i2c-pasemi-core.o i2c-pasemi-pci.o
-obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi.o
-i2c-apple-objs := i2c-pasemi-core.o i2c-pasemi-platform.o
-obj-$(CONFIG_I2C_APPLE) += i2c-apple.o
+obj-$(CONFIG_I2C_PASEMI) += i2c-pasemi-core.o i2c-pasemi-pci.o
+obj-$(CONFIG_I2C_APPLE) += i2c-pasemi-core.o i2c-pasemi-platform.o
obj-$(CONFIG_I2C_PCA_PLATFORM) += i2c-pca-platform.o
obj-$(CONFIG_I2C_PNX) += i2c-pnx.o
obj-$(CONFIG_I2C_PXA) += i2c-pxa.o
diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c
index 7d54a9f34c74..bd8becbdeeb2 100644
--- a/drivers/i2c/busses/i2c-pasemi-core.c
+++ b/drivers/i2c/busses/i2c-pasemi-core.c
@@ -369,6 +369,7 @@ int pasemi_i2c_common_probe(struct pasemi_smbus *smbus)
return 0;
}
+EXPORT_SYMBOL_GPL(pasemi_i2c_common_probe);
irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
{
@@ -378,3 +379,8 @@ irqreturn_t pasemi_irq_handler(int irq, void *dev_id)
complete(&smbus->irq_completion);
return IRQ_HANDLED;
}
+EXPORT_SYMBOL_GPL(pasemi_irq_handler);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Olof Johansson <olof@lixom.net>");
+MODULE_DESCRIPTION("PA Semi PWRficient SMBus driver");
From c1c9d0f6f7f1dbf29db996bd8e166242843a5f21 Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Wed, 14 Feb 2024 15:59:39 +0100
Subject: [PATCH 576/637] i2c: i801: Fix block process call transactions
According to the Intel datasheets, software must reset the block
buffer index twice for block process call transactions: once before
writing the outgoing data to the buffer, and once again before
reading the incoming data from the buffer.
The driver is currently missing the second reset, causing the wrong
portion of the block buffer to be read.
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Reported-by: Piotr Zakowski <piotr.zakowski@intel.com>
Closes: https://lore.kernel.org/linux-i2c/20240213120553.7b0ab120@endymion.delvare/
Fixes: 315cd67c9453 ("i2c: i801: Add Block Write-Block Read Process Call support")
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
drivers/i2c/busses/i2c-i801.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 3932e8d96a17..2c36b36d7d51 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -498,11 +498,10 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
/* Set block buffer mode */
outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv));
- inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
-
if (read_write == I2C_SMBUS_WRITE) {
len = data->block[0];
outb_p(len, SMBHSTDAT0(priv));
+ inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
for (i = 0; i < len; i++)
outb_p(data->block[i+1], SMBBLKDAT(priv));
}
@@ -520,6 +519,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv,
}
data->block[0] = len;
+ inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */
for (i = 0; i < len; i++)
data->block[i + 1] = inb_p(SMBBLKDAT(priv));
}
From 6388cfd0e69b56ca640610f1bf29334619d18142 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Sat, 10 Feb 2024 16:20:04 +0100
Subject: [PATCH 577/637] docs: kconfig: Fix grammar and formatting
- Remove unnecessary spaces
- Fix grammar s/to solution/solution/
Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
Documentation/kbuild/Kconfig.recursion-issue-01 | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/Documentation/kbuild/Kconfig.recursion-issue-01 b/Documentation/kbuild/Kconfig.recursion-issue-01
index e8877db0461f..ac49836d8ecf 100644
--- a/Documentation/kbuild/Kconfig.recursion-issue-01
+++ b/Documentation/kbuild/Kconfig.recursion-issue-01
@@ -16,13 +16,13 @@
# that are possible for CORE. So for example if CORE_BELL_A_ADVANCED is 'y',
# CORE must be 'y' too.
#
-# * What influences CORE_BELL_A_ADVANCED ?
+# * What influences CORE_BELL_A_ADVANCED?
#
# As the name implies CORE_BELL_A_ADVANCED is an advanced feature of
# CORE_BELL_A so naturally it depends on CORE_BELL_A. So if CORE_BELL_A is 'y'
# we know CORE_BELL_A_ADVANCED can be 'y' too.
#
-# * What influences CORE_BELL_A ?
+# * What influences CORE_BELL_A?
#
# CORE_BELL_A depends on CORE, so CORE influences CORE_BELL_A.
#
@@ -34,7 +34,7 @@
# the "recursive dependency detected" error.
#
# Reading the Documentation/kbuild/Kconfig.recursion-issue-01 file it may be
-# obvious that an easy to solution to this problem should just be the removal
+# obvious that an easy solution to this problem should just be the removal
# of the "select CORE" from CORE_BELL_A_ADVANCED as that is implicit already
# since CORE_BELL_A depends on CORE. Recursive dependency issues are not always
# so trivial to resolve, we provide another example below of practical
From e3a9ee963ad8ba677ca925149812c5932b49af69 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 12 Feb 2024 19:05:10 -0700
Subject: [PATCH 578/637] kbuild: Fix changing ELF file type for output of
gen_btf for big endian
Commit 90ceddcb4950 ("bpf: Support llvm-objcopy for vmlinux BTF")
changed the ELF type of .btf.vmlinux.bin.o to ET_REL via dd, which works
fine for little endian platforms:
00000000 7f 45 4c 46 02 01 01 00 00 00 00 00 00 00 00 00 |.ELF............|
-00000010 03 00 b7 00 01 00 00 00 00 00 00 80 00 80 ff ff |................|
+00000010 01 00 b7 00 01 00 00 00 00 00 00 80 00 80 ff ff |................|
However, for big endian platforms, it changes the wrong byte, resulting
in an invalid ELF file type, which ld.lld rejects:
00000000 7f 45 4c 46 02 02 01 00 00 00 00 00 00 00 00 00 |.ELF............|
-00000010 00 03 00 16 00 00 00 01 00 00 00 00 00 10 00 00 |................|
+00000010 01 03 00 16 00 00 00 01 00 00 00 00 00 10 00 00 |................|
Type: <unknown>: 103
ld.lld: error: .btf.vmlinux.bin.o: unknown file type
Fix this by updating the entire 16-bit e_type field rather than just a
single byte, so that everything works correctly for all platforms and
linkers.
00000000 7f 45 4c 46 02 02 01 00 00 00 00 00 00 00 00 00 |.ELF............|
-00000010 00 03 00 16 00 00 00 01 00 00 00 00 00 10 00 00 |................|
+00000010 00 01 00 16 00 00 00 01 00 00 00 00 00 10 00 00 |................|
Type: REL (Relocatable file)
While in the area, update the comment to mention that binutils 2.35+
matches LLD's behavior of rejecting an ET_EXEC input, which occurred
after the comment was added.
Cc: stable@vger.kernel.org
Fixes: 90ceddcb4950 ("bpf: Support llvm-objcopy for vmlinux BTF")
Link: https://github.com/llvm/llvm-project/pull/75643
Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/link-vmlinux.sh | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index a432b171be82..7862a8101747 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -135,8 +135,13 @@ gen_btf()
${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \
--strip-all ${1} ${2} 2>/dev/null
# Change e_type to ET_REL so that it can be used to link final vmlinux.
- # Unlike GNU ld, lld does not allow an ET_EXEC input.
- printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none
+ # GNU ld 2.35+ and lld do not allow an ET_EXEC input.
+ if is_enabled CONFIG_CPU_BIG_ENDIAN; then
+ et_rel='\0\1'
+ else
+ et_rel='\1\0'
+ fi
+ printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none
}
# Create ${2} .S file with all symbols from the ${1} object file
From dae4a0171e25884787da32823b3081b4c2acebb2 Mon Sep 17 00:00:00 2001
From: Andrew Ballance <andrewjballance@gmail.com>
Date: Tue, 13 Feb 2024 19:23:05 -0600
Subject: [PATCH 579/637] gen_compile_commands: fix invalid escape sequence
warning
With python 3.12, '\#' results in this warning
SyntaxWarning: invalid escape sequence '\#'
Signed-off-by: Andrew Ballance <andrewjballance@gmail.com>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/clang-tools/gen_compile_commands.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py
index 5dea4479240b..e4fb686dfaa9 100755
--- a/scripts/clang-tools/gen_compile_commands.py
+++ b/scripts/clang-tools/gen_compile_commands.py
@@ -170,7 +170,7 @@ def process_line(root_directory, command_prefix, file_path):
# escape the pound sign '#', either as '\#' or '$(pound)' (depending on the
# kernel version). The compile_commands.json file is not interepreted
# by Make, so this code replaces the escaped version with '#'.
- prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#')
+ prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#')
# Return the canonical path, eliminating any symbolic links encountered in the path.
abs_path = os.path.realpath(os.path.join(root_directory, file_path))
From 5d9a16b2a4d9e8fa028892ded43f6501bc2969e5 Mon Sep 17 00:00:00 2001
From: Radek Krejci <radek.krejci@oracle.com>
Date: Wed, 14 Feb 2024 10:14:07 +0100
Subject: [PATCH 580/637] modpost: trim leading spaces when processing source
files list
get_line() does not trim the leading spaces, but the
parse_source_files() expects to get lines with source files paths where
the first space occurs after the file path.
Fixes: 70f30cfe5b89 ("modpost: use read_text_file() and get_line() for reading text files")
Signed-off-by: Radek Krejci <radek.krejci@oracle.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/mod/sumversion.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index 31066bfdba04..dc4878502276 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -326,7 +326,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
/* Sum all files in the same dir or subdirs. */
while ((line = get_line(&pos))) {
- char* p = line;
+ char* p;
+
+ /* trim the leading spaces away */
+ while (isspace(*line))
+ line++;
+ p = line;
if (strncmp(line, "source_", sizeof("source_")-1) == 0) {
p = strrchr(line, ' ');
From f6374a82fc85bf911d033e2fa791372ce3356270 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 8 Feb 2024 15:46:03 +0100
Subject: [PATCH 581/637] netfilter: nft_set_pipapo: fix missing : in kdoc
Add missing : in kdoc field names.
Fixes: 8683f4b9950d ("nft_set_pipapo: Prepare for vectorised implementation: helpers")
Reported-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_pipapo.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index f59a0cd81105..3842c7341a9f 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -144,10 +144,10 @@ struct nft_pipapo_scratch {
/**
* struct nft_pipapo_match - Data used for lookup and matching
- * @field_count Amount of fields in set
+ * @field_count: Amount of fields in set
* @scratch: Preallocated per-CPU maps for partial matching results
* @bsize_max: Maximum lookup table bucket size of all fields, in longs
- * @rcu Matching data is swapped on commits
+ * @rcu: Matching data is swapped on commits
* @f: Fields, with lookup and mapping tables
*/
struct nft_pipapo_match {
From 0f1ae2821fa4b13ab0f5ad7ff89fa57efcb04fe0 Mon Sep 17 00:00:00 2001
From: Kyle Swenson <kyle.swenson@est.tech>
Date: Thu, 8 Feb 2024 23:56:31 +0000
Subject: [PATCH 582/637] netfilter: nat: restore default DNAT behavior
When a DNAT rule is configured via iptables with different port ranges,
iptables -t nat -A PREROUTING -p tcp -d 10.0.0.2 -m tcp --dport 32000:32010
-j DNAT --to-destination 192.168.0.10:21000-21010
we seem to be DNATing to some random port on the LAN side. While this is
expected if --random is passed to the iptables command, it is not
expected without passing --random. The expected behavior (and the
observed behavior prior to the commit in the "Fixes" tag) is the traffic
will be DNAT'd to 192.168.0.10:21000 unless there is a tuple collision
with that destination. In that case, we expect the traffic to be
instead DNAT'd to 192.168.0.10:21001, so on so forth until the end of
the range.
This patch intends to restore the behavior observed prior to the "Fixes"
tag.
Fixes: 6ed5943f8735 ("netfilter: nat: remove l4 protocol port rovers")
Signed-off-by: Kyle Swenson <kyle.swenson@est.tech>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_nat_core.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index c3d7ecbc777c..016c816d91cb 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -551,8 +551,11 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
find_free_id:
if (range->flags & NF_NAT_RANGE_PROTO_OFFSET)
off = (ntohs(*keyptr) - ntohs(range->base_proto.all));
- else
+ else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) ||
+ maniptype != NF_NAT_MANIP_DST)
off = get_random_u16();
+ else
+ off = 0;
attempts = range_size;
if (attempts > NF_NAT_MAX_ATTEMPTS)
From 84443741faab9045d53f022a9ac6a6633067a481 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 14 Feb 2024 15:42:35 +0100
Subject: [PATCH 583/637] netfilter: nf_tables: fix bidirectional offload
regression
Commit 8f84780b84d6 ("netfilter: flowtable: allow unidirectional rules")
made unidirectional flow offload possible, while completely ignoring (and
breaking) bidirectional flow offload for nftables.
Add the missing flag that was left out as an exercise for the reader :)
Cc: Vlad Buslov <vladbu@nvidia.com>
Fixes: 8f84780b84d6 ("netfilter: flowtable: allow unidirectional rules")
Reported-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_flow_offload.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 397351fa4d5f..ab9576098701 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -361,6 +361,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
}
+ __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags);
ret = flow_offload_add(flowtable, flow);
if (ret < 0)
goto err_flow_add;
From a37ee9e117ef73bbc2f5c0b31911afd52d229861 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 14 Feb 2024 08:23:05 -0700
Subject: [PATCH 584/637] io_uring/net: fix multishot accept overflow handling
If we hit CQ ring overflow when attempting to post a multishot accept
completion, we don't properly save the result or return code. This
results in losing the accepted fd value.
Instead, we return the result from the poll operation that triggered
the accept retry. This is generally POLLIN|POLLPRI|POLLRDNORM|POLLRDBAND
which is 0xc3, or 195, which looks like a valid file descriptor, but it
really has no connection to that.
Handle this like we do for other multishot completions - assign the
result, and return IOU_STOP_MULTISHOT to cancel any further completions
from this request when overflow is hit. This preserves the result, as we
should, and tells the application that the request needs to be re-armed.
Cc: stable@vger.kernel.org
Fixes: 515e26961295 ("io_uring: revert "io_uring fix multishot accept ordering"")
Link: https://github.com/axboe/liburing/issues/1062
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/net.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/io_uring/net.c b/io_uring/net.c
index 43bc9a5f96f9..161622029147 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1372,7 +1372,7 @@ retry:
* has already been done
*/
if (issue_flags & IO_URING_F_MULTISHOT)
- ret = IOU_ISSUE_SKIP_COMPLETE;
+ return IOU_ISSUE_SKIP_COMPLETE;
return ret;
}
if (ret == -ERESTARTSYS)
@@ -1397,7 +1397,8 @@ retry:
ret, IORING_CQE_F_MORE))
goto retry;
- return -ECANCELED;
+ io_req_set_res(req, ret, 0);
+ return IOU_STOP_MULTISHOT;
}
int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
From dadd1701ae11a204dd4bea8086905a9576c4b63c Mon Sep 17 00:00:00 2001
From: Dave Ertman <david.m.ertman@intel.com>
Date: Tue, 13 Feb 2024 10:39:55 -0800
Subject: [PATCH 585/637] ice: Add check for lport extraction to LAG init
To fully support initializing the LAG support code, a DDP package that
extracts the logical port from the metadata is required. If such a
package is not present, there could be difficulties in supporting some
bond types.
Add a check into the initialization flow that will bypass the new paths
if any of the support pieces are missing.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Fixes: df006dd4b1dc ("ice: Add initial support framework for LAG")
Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20240213183957.1483857-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/intel/ice/ice_lag.c | 25 ++++++++++++++++++++++--
drivers/net/ethernet/intel/ice/ice_lag.h | 3 +++
2 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 2a25323105e5..467372d541d2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -151,6 +151,27 @@ ice_lag_find_hw_by_lport(struct ice_lag *lag, u8 lport)
return NULL;
}
+/**
+ * ice_pkg_has_lport_extract - check if lport extraction supported
+ * @hw: HW struct
+ */
+static bool ice_pkg_has_lport_extract(struct ice_hw *hw)
+{
+ int i;
+
+ for (i = 0; i < hw->blk[ICE_BLK_SW].es.count; i++) {
+ u16 offset;
+ u8 fv_prot;
+
+ ice_find_prot_off(hw, ICE_BLK_SW, ICE_SW_DEFAULT_PROFILE, i,
+ &fv_prot, &offset);
+ if (fv_prot == ICE_FV_PROT_MDID &&
+ offset == ICE_LP_EXT_BUF_OFFSET)
+ return true;
+ }
+ return false;
+}
+
/**
* ice_lag_find_primary - returns pointer to primary interfaces lag struct
* @lag: local interfaces lag struct
@@ -1206,7 +1227,7 @@ static void ice_lag_del_prune_list(struct ice_lag *lag, struct ice_pf *event_pf)
}
/**
- * ice_lag_init_feature_support_flag - Check for NVM support for LAG
+ * ice_lag_init_feature_support_flag - Check for package and NVM support for LAG
* @pf: PF struct
*/
static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
@@ -1219,7 +1240,7 @@ static void ice_lag_init_feature_support_flag(struct ice_pf *pf)
else
ice_clear_feature_support(pf, ICE_F_ROCE_LAG);
- if (caps->sriov_lag)
+ if (caps->sriov_lag && ice_pkg_has_lport_extract(&pf->hw))
ice_set_feature_support(pf, ICE_F_SRIOV_LAG);
else
ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index ede833dfa658..183b38792ef2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -17,6 +17,9 @@ enum ice_lag_role {
#define ICE_LAG_INVALID_PORT 0xFF
#define ICE_LAG_RESET_RETRIES 5
+#define ICE_SW_DEFAULT_PROFILE 0
+#define ICE_FV_PROT_MDID 255
+#define ICE_LP_EXT_BUF_OFFSET 32
struct ice_pf;
struct ice_vf;
From 2ec197fda25f57afccac7f2846e509471488614c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 13 Feb 2024 06:20:55 -0800
Subject: [PATCH 586/637] selftests: tls: increase the wait in
poll_partial_rec_async
Test runners on debug kernels occasionally fail with:
# # RUN tls_err.13_aes_gcm.poll_partial_rec_async ...
# # tls.c:1883:poll_partial_rec_async:Expected poll(&pfd, 1, 5) (0) == 1 (1)
# # tls.c:1870:poll_partial_rec_async:Expected status (256) == 0 (0)
# # poll_partial_rec_async: Test failed at step #17
# # FAIL tls_err.13_aes_gcm.poll_partial_rec_async
# not ok 699 tls_err.13_aes_gcm.poll_partial_rec_async
# # FAILED: 698 / 699 tests passed.
This points to the second poll() in the test which is expected
to wait for the sender to send the rest of the data.
Apparently under some conditions that doesn't happen within 5ms,
bump the timeout to 20ms.
Fixes: 23fcb62bc19c ("selftests: tls: add tests for poll behavior")
Link: https://lore.kernel.org/r/20240213142055.395564-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/tls.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index bc36c91c4480..49c84602707f 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1874,13 +1874,13 @@ TEST_F(tls_err, poll_partial_rec_async)
/* Child should sleep in poll(), never get a wake */
pfd.fd = self->cfd2;
pfd.events = POLLIN;
- EXPECT_EQ(poll(&pfd, 1, 5), 0);
+ EXPECT_EQ(poll(&pfd, 1, 20), 0);
EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */
pfd.fd = self->cfd2;
pfd.events = POLLIN;
- EXPECT_EQ(poll(&pfd, 1, 5), 1);
+ EXPECT_EQ(poll(&pfd, 1, 20), 1);
exit(!_metadata->passed);
}
From 9377de4cb3e8fb6c494fa2f5ae2c3780d3e73822 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 8 Feb 2024 14:21:15 +0100
Subject: [PATCH 587/637] drm/xe/vm: Avoid reserving zero fences
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The function xe_vm_prepare_vma was blindly accepting zero as the
number of fences and forwarded that to drm_exec_prepare_obj.
However, that leads to an out-of-bounds shift in the
dma_resv_reserve_fences() and while one could argue that the
dma_resv code should be robust against that, avoid attempting
to reserve zero fences.
Relevant stack trace:
[773.183188] ------------[ cut here ]------------
[773.183199] UBSAN: shift-out-of-bounds in ../include/linux/log2.h:57:13
[773.183241] shift exponent 64 is too large for 64-bit type 'long unsigned int'
[773.183254] CPU: 2 PID: 1816 Comm: xe_evict Tainted: G U 6.8.0-rc3-xe #1
[773.183256] Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 2014 10/14/2022
[773.183257] Call Trace:
[773.183258] <TASK>
[773.183260] dump_stack_lvl+0xaf/0xd0
[773.183266] dump_stack+0x10/0x20
[773.183283] ubsan_epilogue+0x9/0x40
[773.183286] __ubsan_handle_shift_out_of_bounds+0x10f/0x170
[773.183293] dma_resv_reserve_fences.cold+0x2b/0x48
[773.183295] ? ww_mutex_lock+0x3c/0x110
[773.183301] drm_exec_prepare_obj+0x45/0x60 [drm_exec]
[773.183313] xe_vm_prepare_vma+0x33/0x70 [xe]
[773.183375] xe_vma_destroy_unlocked+0x55/0xa0 [xe]
[773.183427] xe_vm_close_and_put+0x526/0x940 [xe]
Fixes: 2714d5093620 ("drm/xe: Convert pagefaulting code to use drm_exec")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240208132115.3132-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit eb538b5574251a449f40b1ee35efc631228c8992)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_vm.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 865e10d0a06a..7b00faa67287 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -995,9 +995,16 @@ int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
int err;
XE_WARN_ON(!vm);
- err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
- if (!err && bo && !bo->vm)
- err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+ if (num_shared)
+ err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
+ else
+ err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+ if (!err && bo && !bo->vm) {
+ if (num_shared)
+ err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
+ else
+ err = drm_exec_lock_obj(exec, &bo->ttm.base);
+ }
return err;
}
From c2626b7387210cff741be9fb91d317f02a70347c Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Mon, 5 Feb 2024 15:31:11 +0000
Subject: [PATCH 588/637] drm/xe/display: fix i915_gem_object_is_shmem()
wrapper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
shmem ensures the memory is cleared on allocation, however here we are
using TTM, which doesn't natively support shmem (other than for swap),
but instead just allocates normal system memory. And we only zero such
memory for userspace allocations. In the case of intel_fbdev we are
missing the memset_io() since display path incorrectly thinks object is
shmem based.
Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240205153110.38340-2-matthew.auld@intel.com
(cherry picked from commit 63fb531fbfda81bda652546a39333b565aea324d)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
index 68d9f6116bdf..777c20ceabab 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/gem/i915_gem_object.h
@@ -10,7 +10,7 @@
#include "xe_bo.h"
-#define i915_gem_object_is_shmem(obj) ((obj)->flags & XE_BO_CREATE_SYSTEM_BIT)
+#define i915_gem_object_is_shmem(obj) (0) /* We don't use shmem */
static inline dma_addr_t i915_gem_object_get_dma_address(const struct xe_bo *bo, pgoff_t n)
{
From 8cb92dc730d8ae5f803dae1a6eb91fb9603f4237 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 9 Feb 2024 12:26:55 +0100
Subject: [PATCH 589/637] drm/xe/pt: Allow for stricter type- and range
checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Distinguish between xe_pt and the xe_pt_dir subclass when
allocating and freeing. Also use a fixed-size array for the
xe_pt_dir page entries to make life easier for dynamic range-
checkers. Finally rename the page-directory child pointer array
to "children".
While no functional change, this fixes ubsan splats similar to:
[ 51.463021] ------------[ cut here ]------------
[ 51.463022] UBSAN: array-index-out-of-bounds in drivers/gpu/drm/xe/xe_pt.c:47:9
[ 51.463023] index 0 is out of range for type 'xe_ptw *[*]'
[ 51.463024] CPU: 5 PID: 2778 Comm: xe_vm Tainted: G U 6.8.0-rc1+ #218
[ 51.463026] Hardware name: ASUS System Product Name/PRIME B560M-A AC, BIOS 2001 02/01/2023
[ 51.463027] Call Trace:
[ 51.463028] <TASK>
[ 51.463029] dump_stack_lvl+0x47/0x60
[ 51.463030] __ubsan_handle_out_of_bounds+0x95/0xd0
[ 51.463032] xe_pt_destroy+0xa5/0x150 [xe]
[ 51.463088] __xe_pt_unbind_vma+0x36c/0x9b0 [xe]
[ 51.463144] xe_vm_unbind+0xd8/0x580 [xe]
[ 51.463204] ? drm_exec_prepare_obj+0x3f/0x60 [drm_exec]
[ 51.463208] __xe_vma_op_execute+0x5da/0x910 [xe]
[ 51.463268] ? __drm_gpuvm_sm_unmap+0x1cb/0x220 [drm_gpuvm]
[ 51.463272] ? radix_tree_node_alloc.constprop.0+0x89/0xc0
[ 51.463275] ? drm_gpuva_it_remove+0x1f3/0x2a0 [drm_gpuvm]
[ 51.463279] ? drm_gpuva_remove+0x2f/0xc0 [drm_gpuvm]
[ 51.463283] xe_vm_bind_ioctl+0x1a55/0x20b0 [xe]
[ 51.463344] ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
[ 51.463414] drm_ioctl_kernel+0xb6/0x120
[ 51.463416] drm_ioctl+0x287/0x4e0
[ 51.463418] ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
[ 51.463481] __x64_sys_ioctl+0x94/0xd0
[ 51.463484] do_syscall_64+0x86/0x170
[ 51.463486] ? syscall_exit_to_user_mode+0x7d/0x200
[ 51.463488] ? do_syscall_64+0x96/0x170
[ 51.463490] ? do_syscall_64+0x96/0x170
[ 51.463492] entry_SYSCALL_64_after_hwframe+0x6e/0x76
[ 51.463494] RIP: 0033:0x7f246bfe817d
[ 51.463498] Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
[ 51.463501] RSP: 002b:00007ffc1bd19ad0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[ 51.463502] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f246bfe817d
[ 51.463504] RDX: 00007ffc1bd19b60 RSI: 0000000040886445 RDI: 0000000000000003
[ 51.463505] RBP: 00007ffc1bd19b20 R08: 0000000000000000 R09: 0000000000000000
[ 51.463506] R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffc1bd19b60
[ 51.463508] R13: 0000000040886445 R14: 0000000000000003 R15: 0000000000010000
[ 51.463510] </TASK>
[ 51.463517] ---[ end trace ]---
v2
- Fix kerneldoc warning (Matthew Brost)
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240209112655.4872-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 157261c58b283f5c83e3f9087eca63be8d591ab8)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_pt.c | 39 +++++++++++++++++++++------------
drivers/gpu/drm/xe/xe_pt_walk.c | 2 +-
drivers/gpu/drm/xe/xe_pt_walk.h | 19 +++-------------
3 files changed, 29 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index e45b37c3f0c2..ac19bfa3f798 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -20,8 +20,8 @@
struct xe_pt_dir {
struct xe_pt pt;
- /** @dir: Directory structure for the xe_pt_walk functionality */
- struct xe_ptw_dir dir;
+ /** @children: Array of page-table child nodes */
+ struct xe_ptw *children[XE_PDES];
};
#if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -44,7 +44,7 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
{
- return container_of(pt_dir->dir.entries[index], struct xe_pt, base);
+ return container_of(pt_dir->children[index], struct xe_pt, base);
}
static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -65,6 +65,14 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
XE_PTE_NULL;
}
+static void xe_pt_free(struct xe_pt *pt)
+{
+ if (pt->level)
+ kfree(as_xe_pt_dir(pt));
+ else
+ kfree(pt);
+}
+
/**
* xe_pt_create() - Create a page-table.
* @vm: The vm to create for.
@@ -85,15 +93,19 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
{
struct xe_pt *pt;
struct xe_bo *bo;
- size_t size;
int err;
- size = !level ? sizeof(struct xe_pt) : sizeof(struct xe_pt_dir) +
- XE_PDES * sizeof(struct xe_ptw *);
- pt = kzalloc(size, GFP_KERNEL);
+ if (level) {
+ struct xe_pt_dir *dir = kzalloc(sizeof(*dir), GFP_KERNEL);
+
+ pt = (dir) ? &dir->pt : NULL;
+ } else {
+ pt = kzalloc(sizeof(*pt), GFP_KERNEL);
+ }
if (!pt)
return ERR_PTR(-ENOMEM);
+ pt->level = level;
bo = xe_bo_create_pin_map(vm->xe, tile, vm, SZ_4K,
ttm_bo_type_kernel,
XE_BO_CREATE_VRAM_IF_DGFX(tile) |
@@ -106,8 +118,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
goto err_kfree;
}
pt->bo = bo;
- pt->level = level;
- pt->base.dir = level ? &as_xe_pt_dir(pt)->dir : NULL;
+ pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
if (vm->xef)
xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -116,7 +127,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
return pt;
err_kfree:
- kfree(pt);
+ xe_pt_free(pt);
return ERR_PTR(err);
}
@@ -193,7 +204,7 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
deferred);
}
}
- kfree(pt);
+ xe_pt_free(pt);
}
/**
@@ -358,7 +369,7 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
struct iosys_map *map = &parent->bo->vmap;
if (unlikely(xe_child))
- parent->base.dir->entries[offset] = &xe_child->base;
+ parent->base.children[offset] = &xe_child->base;
xe_pt_write(xe_walk->vm->xe, map, offset, pte);
parent->num_live++;
@@ -853,7 +864,7 @@ static void xe_pt_commit_bind(struct xe_vma *vma,
xe_pt_destroy(xe_pt_entry(pt_dir, j_),
xe_vma_vm(vma)->flags, deferred);
- pt_dir->dir.entries[j_] = &newpte->base;
+ pt_dir->children[j_] = &newpte->base;
}
kfree(entries[i].pt_entries);
}
@@ -1507,7 +1518,7 @@ xe_pt_commit_unbind(struct xe_vma *vma,
xe_pt_destroy(xe_pt_entry(pt_dir, i),
xe_vma_vm(vma)->flags, deferred);
- pt_dir->dir.entries[i] = NULL;
+ pt_dir->children[i] = NULL;
}
}
}
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index 8f6c8d063f39..b8b3d2aea492 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,7 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
u64 addr, u64 end, struct xe_pt_walk *walk)
{
pgoff_t offset = xe_pt_offset(addr, level, walk);
- struct xe_ptw **entries = parent->dir ? parent->dir->entries : NULL;
+ struct xe_ptw **entries = parent->children ? parent->children : NULL;
const struct xe_pt_walk_ops *ops = walk->ops;
enum page_walk_action action;
struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index ec3d1e9efa6d..5ecc4d2f0f65 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -8,28 +8,15 @@
#include <linux/pagewalk.h>
#include <linux/types.h>
-struct xe_ptw_dir;
-
/**
* struct xe_ptw - base class for driver pagetable subclassing.
- * @dir: Pointer to an array of children if any.
+ * @children: Pointer to an array of children if any.
*
* Drivers could subclass this, and if it's a page-directory, typically
- * embed the xe_ptw_dir::entries array in the same allocation.
+ * embed an array of xe_ptw pointers.
*/
struct xe_ptw {
- struct xe_ptw_dir *dir;
-};
-
-/**
- * struct xe_ptw_dir - page directory structure
- * @entries: Array holding page directory children.
- *
- * It is the responsibility of the user to ensure @entries is
- * correctly sized.
- */
-struct xe_ptw_dir {
- struct xe_ptw *entries[0];
+ struct xe_ptw **children;
};
/**
From 455dae7549aed709707feda5d6b3e085b37d33f7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Feb 2024 10:56:48 +0100
Subject: [PATCH 590/637] drm/xe: avoid function cast warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
clang-16 warns about a cast between incompatible function types:
drivers/gpu/drm/xe/xe_range_fence.c:155:10: error: cast from 'void (*)(const void *)' to 'void (*)(struct xe_range_fence *)' converts to incompatible function type [-Werror,-Wcast-function-type-strict]
155 | .free = (void (*)(struct xe_range_fence *rfence)) kfree,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Avoid this with a trivial helper function that calls kfree() here.
v2:
- s/* rfence/*rfence/ (Thomas)
Fixes: 845f64bdbfc9 ("drm/xe: Introduce a range-fence utility")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240213095719.454865-1-arnd@kernel.org
(cherry picked from commit f2c9364db57992b1496db4ae5e67ab14926be3ec)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/xe/xe_range_fence.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c
index d35d9ec58e86..372378e89e98 100644
--- a/drivers/gpu/drm/xe/xe_range_fence.c
+++ b/drivers/gpu/drm/xe/xe_range_fence.c
@@ -151,6 +151,11 @@ xe_range_fence_tree_next(struct xe_range_fence *rfence, u64 start, u64 last)
return xe_range_fence_tree_iter_next(rfence, start, last);
}
+static void xe_range_fence_free(struct xe_range_fence *rfence)
+{
+ kfree(rfence);
+}
+
const struct xe_range_fence_ops xe_range_fence_kfree_ops = {
- .free = (void (*)(struct xe_range_fence *rfence)) kfree,
+ .free = xe_range_fence_free,
};
From 488b6d91b07112eaaaa4454332c1480894d4e06e Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Tue, 13 Feb 2024 03:04:28 -0800
Subject: [PATCH 591/637] net-timestamp: make sk_tskey more predictable in
error path
When SOF_TIMESTAMPING_OPT_ID is used to ambiguate timestamped datagrams,
the sk_tskey can become unpredictable in case of any error happened
during sendmsg(). Move increment later in the code and make decrement of
sk_tskey in error path. This solution is still racy in case of multiple
threads doing snedmsg() over the very same socket in parallel, but still
makes error path much more predictable.
Fixes: 09c2d251b707 ("net-timestamp: add key to disambiguate concurrent datagrams")
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240213110428.1681540-1-vadfed@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/ipv4/ip_output.c | 13 ++++++++-----
net/ipv6/ip6_output.c | 13 ++++++++-----
2 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 41537d18eecf..67d846622365 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -972,8 +972,8 @@ static int __ip_append_data(struct sock *sk,
unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
+ bool paged, hold_tskey, extra_uref = false;
unsigned int wmem_alloc_delta = 0;
- bool paged, extra_uref = false;
u32 tskey = 0;
skb = skb_peek_tail(queue);
@@ -982,10 +982,6 @@ static int __ip_append_data(struct sock *sk,
mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
paged = !!cork->gso_size;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
- tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
@@ -1052,6 +1048,11 @@ static int __ip_append_data(struct sock *sk,
cork->length += length;
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+ if (hold_tskey)
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
/* So, what's going on in the loop below?
*
* We use calculated fragment length to generate chained skb,
@@ -1274,6 +1275,8 @@ error:
cork->length -= length;
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+ if (hold_tskey)
+ atomic_dec(&sk->sk_tskey);
return err;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a722a43dd668..31b86fe661aa 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1424,11 +1424,11 @@ static int __ip6_append_data(struct sock *sk,
bool zc = false;
u32 tskey = 0;
struct rt6_info *rt = (struct rt6_info *)cork->dst;
+ bool paged, hold_tskey, extra_uref = false;
struct ipv6_txoptions *opt = v6_cork->opt;
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
unsigned int wmem_alloc_delta = 0;
- bool paged, extra_uref = false;
skb = skb_peek_tail(queue);
if (!skb) {
@@ -1440,10 +1440,6 @@ static int __ip6_append_data(struct sock *sk,
mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
orig_mtu = mtu;
- if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
- tskey = atomic_inc_return(&sk->sk_tskey) - 1;
-
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
@@ -1538,6 +1534,11 @@ emsgsize:
flags &= ~MSG_SPLICE_PAGES;
}
+ hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
+ if (hold_tskey)
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
@@ -1794,6 +1795,8 @@ error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc);
+ if (hold_tskey)
+ atomic_dec(&sk->sk_tskey);
return err;
}
From fb091ff394792c018527b3211bbdfae93ea4ac02 Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 14 Feb 2024 17:55:18 +0000
Subject: [PATCH 592/637] arm64: Subscribe Microsoft Azure Cobalt 100 to ARM
Neoverse N2 errata
Add the MIDR value of Microsoft Azure Cobalt 100, which is a Microsoft
implemented CPU based on r0p0 of the ARM Neoverse N2 CPU, and therefore
suffers from all the same errata.
CC: stable@vger.kernel.org # 5.15+
Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20240214175522.2457857-1-eahariha@linux.microsoft.com
Signed-off-by: Will Deacon <will@kernel.org>
---
Documentation/arch/arm64/silicon-errata.rst | 7 +++++++
arch/arm64/include/asm/cputype.h | 4 ++++
arch/arm64/kernel/cpu_errata.c | 3 +++
3 files changed, 14 insertions(+)
diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index e8c2ce1f9df6..45a7f4932fe0 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -243,3 +243,10 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| ASR | ASR8601 | #8601001 | N/A |
+----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 |
++----------------+-----------------+-----------------+-----------------------------+
+| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 |
++----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 7c7493cb571f..52f076afeb96 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
#define ARM_CPU_IMP_HISI 0x48
#define ARM_CPU_IMP_APPLE 0x61
#define ARM_CPU_IMP_AMPERE 0xC0
+#define ARM_CPU_IMP_MICROSOFT 0x6D
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -135,6 +136,8 @@
#define AMPERE_CPU_PART_AMPERE1 0xAC3
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
#define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 967c7c7a4e7d..76b8dd37092a 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -374,6 +374,7 @@ static const struct midr_range erratum_1463225[] = {
static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
#ifdef CONFIG_ARM64_ERRATUM_2139208
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+ MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
#endif
#ifdef CONFIG_ARM64_ERRATUM_2119858
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -387,6 +388,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
static const struct midr_range tsb_flush_fail_cpus[] = {
#ifdef CONFIG_ARM64_ERRATUM_2067961
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+ MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
#endif
#ifdef CONFIG_ARM64_ERRATUM_2054223
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -399,6 +401,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
static struct midr_range trbe_write_out_of_range_cpus[] = {
#ifdef CONFIG_ARM64_ERRATUM_2253138
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+ MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
#endif
#ifdef CONFIG_ARM64_ERRATUM_2224489
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
From 2813926261e436d33bc74486b51cce60b76edf78 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 13 Feb 2024 18:24:38 +0000
Subject: [PATCH 593/637] arm64/sve: Lower the maximum allocation for the SVE
ptrace regset
Doug Anderson observed that ChromeOS crashes are being reported which
include failing allocations of order 7 during core dumps due to ptrace
allocating storage for regsets:
chrome: page allocation failure: order:7,
mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO),
nodemask=(null),cpuset=urgent,mems_allowed=0
...
regset_get_alloc+0x1c/0x28
elf_core_dump+0x3d8/0xd8c
do_coredump+0xeb8/0x1378
with further investigation showing that this is:
[ 66.957385] DOUG: Allocating 279584 bytes
which is the maximum size of the SVE regset. As Doug observes it is not
entirely surprising that such a large allocation of contiguous memory might
fail on a long running system.
The SVE regset is currently sized to hold SVE registers with a VQ of
SVE_VQ_MAX which is 512, substantially more than the architectural maximum
of 16 which we might see even in a system emulating the limits of the
architecture. Since we don't expose the size we tell the regset core
externally let's define ARCH_SVE_VQ_MAX with the actual architectural
maximum and use that for the regset, we'll still overallocate most of the
time but much less so which will be helpful even if the core is fixed to
not require contiguous allocations.
Specify ARCH_SVE_VQ_MAX in terms of the maximum value that can be written
into ZCR_ELx.LEN (where this is set in the hardware). For consistency
update the maximum SME vector length to be specified in the same style
while we are at it.
We could also teach the ptrace core about runtime discoverable regset sizes
but that would be a more invasive change and this is being observed in
practical systems.
Reported-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20240213-arm64-sve-ptrace-regset-size-v2-1-c7600ca74b9b@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/fpsimd.h | 12 ++++++------
arch/arm64/kernel/ptrace.c | 3 ++-
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 50e5f25d3024..481d94416d69 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -62,13 +62,13 @@ static inline void cpacr_restore(unsigned long cpacr)
* When we defined the maximum SVE vector length we defined the ABI so
* that the maximum vector length included all the reserved for future
* expansion bits in ZCR rather than those just currently defined by
- * the architecture. While SME follows a similar pattern the fact that
- * it includes a square matrix means that any allocations that attempt
- * to cover the maximum potential vector length (such as happen with
- * the regset used for ptrace) end up being extremely large. Define
- * the much lower actual limit for use in such situations.
+ * the architecture. Using this length to allocate worst size buffers
+ * results in excessively large allocations, and this effect is even
+ * more pronounced for SME due to ZA. Define more suitable VLs for
+ * these situations.
*/
-#define SME_VQ_MAX 16
+#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1)
+#define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1)
struct task_struct;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index dc6cf0e37194..e3bef38fc2e2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1500,7 +1500,8 @@ static const struct user_regset aarch64_regsets[] = {
#ifdef CONFIG_ARM64_SVE
[REGSET_SVE] = { /* Scalable Vector Extension */
.core_note_type = NT_ARM_SVE,
- .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+ .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX,
+ SVE_PT_REGS_SVE),
SVE_VQ_BYTES),
.size = SVE_VQ_BYTES,
.align = SVE_VQ_BYTES,
From e5b2e810daf9f2d87fe132eb4d2a85fb08a0db98 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Tue, 13 Feb 2024 09:33:39 -0800
Subject: [PATCH 594/637] net: bcmasp: Handle RX buffer allocation failure
The buffer_pg variable needs to hold an order-5 allocation (32 x
PAGE_SIZE) which, under memory pressure may fail to be allocated. Deal
with that error condition properly to avoid doing a NULL pointer
de-reference in the subsequent call to dma_map_page().
In addition, the err_reclaim_tx error label in bcmasp_netif_init() needs
to ensure that the TX NAPI object is properly deleted, otherwise
unregister_netdev() will spin forever attempting to test and clear
the NAPI_STATE_HASHED bit.
Fixes: 490cb412007d ("net: bcmasp: Add support for ASP2.0 Ethernet controller")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Justin Chen <justin.chen@broadcom.com>
Link: https://lore.kernel.org/r/20240213173339.3438713-1-florian.fainelli@broadcom.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 53e542881255..f59557b0cd51 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -684,6 +684,8 @@ static int bcmasp_init_rx(struct bcmasp_intf *intf)
intf->rx_buf_order = get_order(RING_BUFFER_SIZE);
buffer_pg = alloc_pages(GFP_KERNEL, intf->rx_buf_order);
+ if (!buffer_pg)
+ return -ENOMEM;
dma = dma_map_page(kdev, buffer_pg, 0, RING_BUFFER_SIZE,
DMA_FROM_DEVICE);
@@ -1092,6 +1094,7 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect)
return 0;
err_reclaim_tx:
+ netif_napi_del(&intf->tx_napi);
bcmasp_reclaim_free_all_tx(intf);
err_phy_disconnect:
if (phydev)
From a951884d82886d8453d489f84f20ac168d062b38 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Feb 2024 09:32:08 +0100
Subject: [PATCH 595/637] kallsyms: ignore ARMv4 thunks along with others
lld is now able to build ARMv4 and ARMv4T kernels, which means it can
generate thunks for those (__ARMv4PILongThunk_*, __ARMv4PILongBXThunk_*)
that can interfere with kallsyms table generation since they do not get
ignore like the corresponding ARMv5+ ones are:
Inconsistent kallsyms data
Try "make KALLSYMS_EXTRA_PASS=1" as a workaround
Replace the hardcoded list of thunk symbols with a more general regex that
covers this one along with future symbols that follow the same pattern.
Fixes: 5eb6e280432d ("ARM: 9289/1: Allow pre-ARMv5 builds with ld.lld 16.0.0 and newer")
Fixes: efe6e3068067 ("kallsyms: fix nonconverging kallsyms table with lld")
Suggested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/mksysmap | 13 ++-----------
1 file changed, 2 insertions(+), 11 deletions(-)
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 9ba1c9da0a40..57ff5656d566 100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -48,17 +48,8 @@ ${NM} -n ${1} | sed >${2} -e "
/ __kvm_nvhe_\\$/d
/ __kvm_nvhe_\.L/d
-# arm64 lld
-/ __AArch64ADRPThunk_/d
-
-# arm lld
-/ __ARMV5PILongThunk_/d
-/ __ARMV7PILongThunk_/d
-/ __ThumbV7PILongThunk_/d
-
-# mips lld
-/ __LA25Thunk_/d
-/ __microLA25Thunk_/d
+# lld arm/aarch64/mips thunks
+/ __[[:alnum:]]*Thunk_/d
# CFI type identifiers
/ __kcfi_typeid_/d
From 4e45170d9acc2d5ae8f545bf3f2f67504a361338 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 14 Feb 2024 11:22:24 +0300
Subject: [PATCH 596/637] net: sctp: fix skb leak in sctp_inq_free()
In case of GSO, 'chunk->skb' pointer may point to an entry from
fraglist created in 'sctp_packet_gso_append()'. To avoid freeing
random fraglist entry (and so undefined behavior and/or memory
leak), introduce 'sctp_inq_chunk_free()' helper to ensure that
'chunk->skb' is set to 'chunk->head_skb' (i.e. fraglist head)
before calling 'sctp_chunk_free()', and use the aforementioned
helper in 'sctp_inq_pop()' as well.
Reported-by: syzbot+8bb053b5d63595ab47db@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?id=0d8351bbe54fd04a492c2daab0164138db008042
Fixes: 90017accff61 ("sctp: Add GSO support")
Suggested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/20240214082224.10168-1-dmantipov@yandex.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sctp/inqueue.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 7182c5a450fb..5c1652181805 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -38,6 +38,14 @@ void sctp_inq_init(struct sctp_inq *queue)
INIT_WORK(&queue->immediate, NULL);
}
+/* Properly release the chunk which is being worked on. */
+static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk)
+{
+ if (chunk->head_skb)
+ chunk->skb = chunk->head_skb;
+ sctp_chunk_free(chunk);
+}
+
/* Release the memory associated with an SCTP inqueue. */
void sctp_inq_free(struct sctp_inq *queue)
{
@@ -53,7 +61,7 @@ void sctp_inq_free(struct sctp_inq *queue)
* free it as well.
*/
if (queue->in_progress) {
- sctp_chunk_free(queue->in_progress);
+ sctp_inq_chunk_free(queue->in_progress);
queue->in_progress = NULL;
}
}
@@ -130,9 +138,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
goto new_skb;
}
- if (chunk->head_skb)
- chunk->skb = chunk->head_skb;
- sctp_chunk_free(chunk);
+ sctp_inq_chunk_free(chunk);
chunk = queue->in_progress = NULL;
} else {
/* Nothing to do. Next chunk in the packet, please. */
From dc34ebd5c018b0edf47f39d11083ad8312733034 Mon Sep 17 00:00:00 2001
From: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Date: Wed, 14 Feb 2024 09:01:50 +0000
Subject: [PATCH 597/637] pppoe: Fix memory leak in pppoe_sendmsg()
syzbot reports a memory leak in pppoe_sendmsg [1].
The problem is in the pppoe_recvmsg() function that handles errors
in the wrong order. For the skb_recv_datagram() function, check
the pointer to skb for NULL first, and then check the 'error' variable,
because the skb_recv_datagram() function can set 'error'
to -EAGAIN in a loop but return a correct pointer to socket buffer
after a number of attempts, though 'error' remains set to -EAGAIN.
skb_recv_datagram
__skb_recv_datagram // Loop. if (err == -EAGAIN) then
// go to the next loop iteration
__skb_try_recv_datagram // if (skb != NULL) then return 'skb'
// else if a signal is received then
// return -EAGAIN
Found by InfoTeCS on behalf of Linux Verification Center
(linuxtesting.org) with Syzkaller.
Link: https://syzkaller.appspot.com/bug?extid=6bdfd184eac7709e5cc9 [1]
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+6bdfd184eac7709e5cc9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=6bdfd184eac7709e5cc9
Signed-off-by: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://lore.kernel.org/r/20240214085814.3894917-1-Ilia.Gavrilov@infotecs.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ppp/pppoe.c | 23 +++++++++--------------
1 file changed, 9 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 8e7238e97d0a..2ea4f4890d23 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -1007,26 +1007,21 @@ static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
struct sk_buff *skb;
int error = 0;
- if (sk->sk_state & PPPOX_BOUND) {
- error = -EIO;
- goto end;
- }
+ if (sk->sk_state & PPPOX_BOUND)
+ return -EIO;
skb = skb_recv_datagram(sk, flags, &error);
- if (error < 0)
- goto end;
+ if (!skb)
+ return error;
- if (skb) {
- total_len = min_t(size_t, total_len, skb->len);
- error = skb_copy_datagram_msg(skb, 0, m, total_len);
- if (error == 0) {
- consume_skb(skb);
- return total_len;
- }
+ total_len = min_t(size_t, total_len, skb->len);
+ error = skb_copy_datagram_msg(skb, 0, m, total_len);
+ if (error == 0) {
+ consume_skb(skb);
+ return total_len;
}
kfree_skb(skb);
-end:
return error;
}
From ed4adc07207d9165a4b3b36199231a22e9f51a55 Mon Sep 17 00:00:00 2001
From: Paul Barker <paul.barker.ct@bp.renesas.com>
Date: Wed, 14 Feb 2024 15:12:04 +0000
Subject: [PATCH 598/637] net: ravb: Count packets instead of descriptors in
GbEth RX path
The units of "work done" in the RX path should be packets instead of
descriptors, as large packets can be spread over multiple descriptors.
Fixes: 1c59eb678cbd ("ravb: Fillup ravb_rx_gbeth() stub")
Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Link: https://lore.kernel.org/r/20240214151204.2976-1-paul.barker.ct@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/renesas/ravb_main.c | 22 +++++++++-------------
1 file changed, 9 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 0e3731f50fc2..f7566cfa45ca 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -772,29 +772,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
struct ravb_rx_desc *desc;
struct sk_buff *skb;
dma_addr_t dma_addr;
+ int rx_packets = 0;
u8 desc_status;
- int boguscnt;
u16 pkt_len;
u8 die_dt;
int entry;
int limit;
+ int i;
entry = priv->cur_rx[q] % priv->num_rx_ring[q];
- boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
+ limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
stats = &priv->stats[q];
- boguscnt = min(boguscnt, *quota);
- limit = boguscnt;
desc = &priv->gbeth_rx_ring[entry];
- while (desc->die_dt != DT_FEMPTY) {
+ for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) {
/* Descriptor type must be checked before all other reads */
dma_rmb();
desc_status = desc->msc;
pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
- if (--boguscnt < 0)
- break;
-
/* We use 0-byte descriptors to mark the DMA mapping errors */
if (!pkt_len)
continue;
@@ -820,7 +816,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
skb_put(skb, pkt_len);
skb->protocol = eth_type_trans(skb, ndev);
napi_gro_receive(&priv->napi[q], skb);
- stats->rx_packets++;
+ rx_packets++;
stats->rx_bytes += pkt_len;
break;
case DT_FSTART:
@@ -848,7 +844,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
eth_type_trans(priv->rx_1st_skb, ndev);
napi_gro_receive(&priv->napi[q],
priv->rx_1st_skb);
- stats->rx_packets++;
+ rx_packets++;
stats->rx_bytes += pkt_len;
break;
}
@@ -887,9 +883,9 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q)
desc->die_dt = DT_FEMPTY;
}
- *quota -= limit - (++boguscnt);
-
- return boguscnt <= 0;
+ stats->rx_packets += rx_packets;
+ *quota -= rx_packets;
+ return *quota == 0;
}
/* Packet receive function for Ethernet AVB */
From 32f03f4002c5df837fb920eb23fcd2f4af9b0b23 Mon Sep 17 00:00:00 2001
From: Eniac Zhang <eniac-xw.zhang@hp.com>
Date: Thu, 15 Feb 2024 15:49:22 +0000
Subject: [PATCH 599/637] ALSA: hda/realtek: fix mute/micmute LED For HP mt645
The HP mt645 G7 Thin Client uses an ALC236 codec and needs the
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF quirk to make the mute and
micmute LEDs work.
There are two variants of the USB-C PD chip on this device. Each uses
a different BIOS and board ID, hence the two entries.
Signed-off-by: Eniac Zhang <eniac-xw.zhang@hp.com>
Signed-off-by: Alexandru Gagniuc <alexandru.gagniuc@hp.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20240215154922.778394-1-alexandru.gagniuc@hp.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5d0517465f08..0ec1312bffd5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9930,6 +9930,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9937,6 +9938,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b59, "HP Elite mt645 G7 Mobile Thin Client U89", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
From 41c25e193b2befc22462aa41591d397fab174ca1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 15 Feb 2024 16:31:44 +0100
Subject: [PATCH 600/637] ALSA: usb-audio: More relaxed check of MIDI jack
names
The USB audio driver tries to retrieve MIDI jack name strings that can
be used for rawmidi substream names and sequencer port names, but its
checking is too strict: often the firmware provides the jack info for
unexpected directions, and then we miss the info although it's
present.
In this patch, the code to extract the jack info is changed to allow
both in and out directions in a single loop. That is, the former two
functions to obtain the descriptor pointers for jack in and out are
changed to a single function that returns iJack of the corresponding
jack ID, no matter which direction is used. It's a code
simplification at the same time as well as the fix.
Fixes: eb596e0fd13c ("ALSA: usb-audio: generate midi streaming substream names from jack names")
Link: https://lore.kernel.org/r/20240215153144.26047-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/midi.c | 77 +++++++++++++++++-------------------------------
1 file changed, 27 insertions(+), 50 deletions(-)
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 6b0993258e03..c1f2e5a03de9 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1742,50 +1742,44 @@ static void snd_usbmidi_get_port_info(struct snd_rawmidi *rmidi, int number,
}
}
-static struct usb_midi_in_jack_descriptor *find_usb_in_jack_descriptor(
- struct usb_host_interface *hostif, uint8_t jack_id)
+/* return iJack for the corresponding jackID */
+static int find_usb_ijack(struct usb_host_interface *hostif, uint8_t jack_id)
{
unsigned char *extra = hostif->extra;
int extralen = hostif->extralen;
+ struct usb_descriptor_header *h;
+ struct usb_midi_out_jack_descriptor *outjd;
+ struct usb_midi_in_jack_descriptor *injd;
+ size_t sz;
while (extralen > 4) {
- struct usb_midi_in_jack_descriptor *injd =
- (struct usb_midi_in_jack_descriptor *)extra;
+ h = (struct usb_descriptor_header *)extra;
+ if (h->bDescriptorType != USB_DT_CS_INTERFACE)
+ goto next;
- if (injd->bLength >= sizeof(*injd) &&
- injd->bDescriptorType == USB_DT_CS_INTERFACE &&
- injd->bDescriptorSubtype == UAC_MIDI_IN_JACK &&
- injd->bJackID == jack_id)
- return injd;
- if (!extra[0])
- break;
- extralen -= extra[0];
- extra += extra[0];
- }
- return NULL;
-}
-
-static struct usb_midi_out_jack_descriptor *find_usb_out_jack_descriptor(
- struct usb_host_interface *hostif, uint8_t jack_id)
-{
- unsigned char *extra = hostif->extra;
- int extralen = hostif->extralen;
-
- while (extralen > 4) {
- struct usb_midi_out_jack_descriptor *outjd =
- (struct usb_midi_out_jack_descriptor *)extra;
-
- if (outjd->bLength >= sizeof(*outjd) &&
- outjd->bDescriptorType == USB_DT_CS_INTERFACE &&
+ outjd = (struct usb_midi_out_jack_descriptor *)h;
+ if (h->bLength >= sizeof(*outjd) &&
outjd->bDescriptorSubtype == UAC_MIDI_OUT_JACK &&
- outjd->bJackID == jack_id)
- return outjd;
+ outjd->bJackID == jack_id) {
+ sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
+ if (outjd->bLength < sz)
+ goto next;
+ return *(extra + sz - 1);
+ }
+
+ injd = (struct usb_midi_in_jack_descriptor *)h;
+ if (injd->bLength >= sizeof(*injd) &&
+ injd->bDescriptorSubtype == UAC_MIDI_IN_JACK &&
+ injd->bJackID == jack_id)
+ return injd->iJack;
+
+next:
if (!extra[0])
break;
extralen -= extra[0];
extra += extra[0];
}
- return NULL;
+ return 0;
}
static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
@@ -1796,13 +1790,10 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
const char *name_format;
struct usb_interface *intf;
struct usb_host_interface *hostif;
- struct usb_midi_in_jack_descriptor *injd;
- struct usb_midi_out_jack_descriptor *outjd;
uint8_t jack_name_buf[32];
uint8_t *default_jack_name = "MIDI";
uint8_t *jack_name = default_jack_name;
uint8_t iJack;
- size_t sz;
int res;
struct snd_rawmidi_substream *substream =
@@ -1816,21 +1807,7 @@ static void snd_usbmidi_init_substream(struct snd_usb_midi *umidi,
intf = umidi->iface;
if (intf && jack_id >= 0) {
hostif = intf->cur_altsetting;
- iJack = 0;
- if (stream != SNDRV_RAWMIDI_STREAM_OUTPUT) {
- /* in jacks connect to outs */
- outjd = find_usb_out_jack_descriptor(hostif, jack_id);
- if (outjd) {
- sz = USB_DT_MIDI_OUT_SIZE(outjd->bNrInputPins);
- if (outjd->bLength >= sz)
- iJack = *(((uint8_t *) outjd) + sz - sizeof(uint8_t));
- }
- } else {
- /* and out jacks connect to ins */
- injd = find_usb_in_jack_descriptor(hostif, jack_id);
- if (injd)
- iJack = injd->iJack;
- }
+ iJack = find_usb_ijack(hostif, jack_id);
if (iJack != 0) {
res = usb_string(umidi->dev, iJack, jack_name_buf,
ARRAY_SIZE(jack_name_buf));
From 5b8e3464071a4401978a91d2e9f0beca308996c2 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:35 -0800
Subject: [PATCH 601/637] net: fill in MODULE_DESCRIPTION()s for xen-netback
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the Xen backend network module.
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Paul Durrant <paul@xen.org>
Link: https://lore.kernel.org/r/20240214152741.670178-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/xen-netback/netback.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index fab361a250d6..ef76850d9bcd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1778,5 +1778,6 @@ static void __exit netback_fini(void)
}
module_exit(netback_fini);
+MODULE_DESCRIPTION("Xen backend network device module");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_ALIAS("xen-backend:vif");
From c0872309ac8432e309824ece24238e8fd2768ef8 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:36 -0800
Subject: [PATCH 602/637] net: fill in MODULE_DESCRIPTION()s for
ieee802154/fakelb
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the IEEE 802.15.4 loopback driver.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240214152741.670178-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ieee802154/fakelb.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 35e55f198e05..2930141d7dd2 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -259,4 +259,5 @@ static __exit void fake_remove_module(void)
module_init(fakelb_init_module);
module_exit(fake_remove_module);
+MODULE_DESCRIPTION("IEEE 802.15.4 loopback driver");
MODULE_LICENSE("GPL");
From 44c1197bcef49bdf1021bef7cdb32520b2bc1ce4 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:37 -0800
Subject: [PATCH 603/637] net: fill in MODULE_DESCRIPTION()s for plip
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the PLIP (parallel port) network module
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240214152741.670178-4-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/plip/plip.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c
index 40ce8abe6999..cc7d1113ece0 100644
--- a/drivers/net/plip/plip.c
+++ b/drivers/net/plip/plip.c
@@ -1437,4 +1437,5 @@ static int __init plip_init (void)
module_init(plip_init);
module_exit(plip_cleanup_module);
+MODULE_DESCRIPTION("PLIP (parallel port) network module");
MODULE_LICENSE("GPL");
From 4ad9e85874393eec74edf2d2c7b7c7ba11f78d20 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:38 -0800
Subject: [PATCH 604/637] net: fill in MODULE_DESCRIPTION()s for fddik/skfp
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the SysKonnect FDDI PCI module.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240214152741.670178-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/fddi/skfp/skfddi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c
index 2b6a607ac0b7..a273362c9e70 100644
--- a/drivers/net/fddi/skfp/skfddi.c
+++ b/drivers/net/fddi/skfp/skfddi.c
@@ -153,6 +153,7 @@ static const struct pci_device_id skfddi_pci_tbl[] = {
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(pci, skfddi_pci_tbl);
+MODULE_DESCRIPTION("SysKonnect FDDI PCI driver");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Mirko Lindner <mlindner@syskonnect.de>");
From e1e5ef2aefc2ab77dacf77626f9f25f332ba91b7 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:39 -0800
Subject: [PATCH 605/637] net: fill in MODULE_DESCRIPTION()s for ppp
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the PPP modules.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240214152741.670178-6-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ppp/bsd_comp.c | 1 +
drivers/net/ppp/ppp_async.c | 1 +
drivers/net/ppp/ppp_deflate.c | 1 +
drivers/net/ppp/ppp_generic.c | 1 +
drivers/net/ppp/ppp_synctty.c | 1 +
5 files changed, 5 insertions(+)
diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c
index db0dc36d12e3..55954594e157 100644
--- a/drivers/net/ppp/bsd_comp.c
+++ b/drivers/net/ppp/bsd_comp.c
@@ -1166,5 +1166,6 @@ static void __exit bsdcomp_cleanup(void)
module_init(bsdcomp_init);
module_exit(bsdcomp_cleanup);
+MODULE_DESCRIPTION("PPP BSD-Compress compression module");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS));
diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c
index 125793d8aefa..c33c3db3cc08 100644
--- a/drivers/net/ppp/ppp_async.c
+++ b/drivers/net/ppp/ppp_async.c
@@ -87,6 +87,7 @@ struct asyncppp {
static int flag_time = HZ;
module_param(flag_time, int, 0);
MODULE_PARM_DESC(flag_time, "ppp_async: interval between flagged packets (in clock ticks)");
+MODULE_DESCRIPTION("PPP async serial channel module");
MODULE_LICENSE("GPL");
MODULE_ALIAS_LDISC(N_PPP);
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index e6d48e5c65a3..4d2ff63f2ee2 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -630,6 +630,7 @@ static void __exit deflate_cleanup(void)
module_init(deflate_init);
module_exit(deflate_cleanup);
+MODULE_DESCRIPTION("PPP Deflate compression module");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE));
MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT));
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 0193af2d31c9..3dd52bf28f15 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3604,6 +3604,7 @@ EXPORT_SYMBOL(ppp_input_error);
EXPORT_SYMBOL(ppp_output_wakeup);
EXPORT_SYMBOL(ppp_register_compressor);
EXPORT_SYMBOL(ppp_unregister_compressor);
+MODULE_DESCRIPTION("Generic PPP layer driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0);
MODULE_ALIAS_RTNL_LINK("ppp");
diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c
index 52d05ce4a281..45bf59ac8f57 100644
--- a/drivers/net/ppp/ppp_synctty.c
+++ b/drivers/net/ppp/ppp_synctty.c
@@ -724,5 +724,6 @@ ppp_sync_cleanup(void)
module_init(ppp_sync_init);
module_exit(ppp_sync_cleanup);
+MODULE_DESCRIPTION("PPP synchronous TTY channel module");
MODULE_LICENSE("GPL");
MODULE_ALIAS_LDISC(N_SYNC_PPP);
From 9de69f0e99585d84baab4fbb0b3b97c02cf069f1 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:40 -0800
Subject: [PATCH 606/637] net: fill in MODULE_DESCRIPTION()s for mdio_devres
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the PHY MDIO helpers.
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240214152741.670178-7-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/phy/mdio_devres.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c
index 69b829e6ab35..7fd3377dbd79 100644
--- a/drivers/net/phy/mdio_devres.c
+++ b/drivers/net/phy/mdio_devres.c
@@ -131,4 +131,5 @@ int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
EXPORT_SYMBOL(__devm_of_mdiobus_register);
#endif /* CONFIG_OF_MDIO */
+MODULE_DESCRIPTION("Network MDIO bus devres helpers");
MODULE_LICENSE("GPL");
From 538b22e74287864014b3be7481042fb904a0cc0d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 14 Feb 2024 07:27:41 -0800
Subject: [PATCH 607/637] net: fill in MODULE_DESCRIPTION()s for missing arcnet
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to the ARC modules.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240214152741.670178-8-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/arcnet/arc-rawmode.c | 1 +
drivers/net/arcnet/arc-rimi.c | 1 +
drivers/net/arcnet/capmode.c | 1 +
drivers/net/arcnet/com20020-pci.c | 1 +
drivers/net/arcnet/com20020.c | 1 +
drivers/net/arcnet/com20020_cs.c | 1 +
drivers/net/arcnet/com90io.c | 1 +
drivers/net/arcnet/com90xx.c | 1 +
drivers/net/arcnet/rfc1051.c | 1 +
drivers/net/arcnet/rfc1201.c | 1 +
10 files changed, 10 insertions(+)
diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c
index 8c651fdee039..57f1729066f2 100644
--- a/drivers/net/arcnet/arc-rawmode.c
+++ b/drivers/net/arcnet/arc-rawmode.c
@@ -186,4 +186,5 @@ static void __exit arcnet_raw_exit(void)
module_init(arcnet_raw_init);
module_exit(arcnet_raw_exit);
+MODULE_DESCRIPTION("ARCnet raw mode packet interface module");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c
index 8c3ccc7c83cd..53d10a04d1bd 100644
--- a/drivers/net/arcnet/arc-rimi.c
+++ b/drivers/net/arcnet/arc-rimi.c
@@ -312,6 +312,7 @@ module_param(node, int, 0);
module_param(io, int, 0);
module_param(irq, int, 0);
module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx RIM I chipset driver");
MODULE_LICENSE("GPL");
static struct net_device *my_dev;
diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c
index c09b567845e1..7a0a79973769 100644
--- a/drivers/net/arcnet/capmode.c
+++ b/drivers/net/arcnet/capmode.c
@@ -265,4 +265,5 @@ static void __exit capmode_module_exit(void)
module_init(capmode_module_init);
module_exit(capmode_module_exit);
+MODULE_DESCRIPTION("ARCnet CAP mode packet interface module");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c
index 7b5c8bb02f11..c5e571ec94c9 100644
--- a/drivers/net/arcnet/com20020-pci.c
+++ b/drivers/net/arcnet/com20020-pci.c
@@ -61,6 +61,7 @@ module_param(timeout, int, 0);
module_param(backplane, int, 0);
module_param(clockp, int, 0);
module_param(clockm, int, 0);
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCI driver");
MODULE_LICENSE("GPL");
static void led_tx_set(struct led_classdev *led_cdev,
diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c
index 06e1651b594b..a0053e3992a3 100644
--- a/drivers/net/arcnet/com20020.c
+++ b/drivers/net/arcnet/com20020.c
@@ -399,6 +399,7 @@ EXPORT_SYMBOL(com20020_found);
EXPORT_SYMBOL(com20020_netdev_ops);
#endif
+MODULE_DESCRIPTION("ARCnet COM20020 chipset core driver");
MODULE_LICENSE("GPL");
#ifdef MODULE
diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c
index dc3253b318da..75f08aa7528b 100644
--- a/drivers/net/arcnet/com20020_cs.c
+++ b/drivers/net/arcnet/com20020_cs.c
@@ -97,6 +97,7 @@ module_param(backplane, int, 0);
module_param(clockp, int, 0);
module_param(clockm, int, 0);
+MODULE_DESCRIPTION("ARCnet COM20020 chipset PCMCIA driver");
MODULE_LICENSE("GPL");
/*====================================================================*/
diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c
index 37b47749fc8b..3b463fbc6402 100644
--- a/drivers/net/arcnet/com90io.c
+++ b/drivers/net/arcnet/com90io.c
@@ -350,6 +350,7 @@ static char device[9]; /* use eg. device=arc1 to change name */
module_param_hw(io, int, ioport, 0);
module_param_hw(irq, int, irq, 0);
module_param_string(device, device, sizeof(device), 0);
+MODULE_DESCRIPTION("ARCnet COM90xx IO mapped chipset driver");
MODULE_LICENSE("GPL");
#ifndef MODULE
diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c
index f49dae194284..b3b287c16561 100644
--- a/drivers/net/arcnet/com90xx.c
+++ b/drivers/net/arcnet/com90xx.c
@@ -645,6 +645,7 @@ static void com90xx_copy_from_card(struct net_device *dev, int bufnum,
TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count));
}
+MODULE_DESCRIPTION("ARCnet COM90xx normal chipset driver");
MODULE_LICENSE("GPL");
static int __init com90xx_init(void)
diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c
index a7752a5b647f..46519ca63a0a 100644
--- a/drivers/net/arcnet/rfc1051.c
+++ b/drivers/net/arcnet/rfc1051.c
@@ -78,6 +78,7 @@ static void __exit arcnet_rfc1051_exit(void)
module_init(arcnet_rfc1051_init);
module_exit(arcnet_rfc1051_exit);
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1051) module");
MODULE_LICENSE("GPL");
/* Determine a packet's protocol ID.
diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c
index a4c856282674..0edf35d971c5 100644
--- a/drivers/net/arcnet/rfc1201.c
+++ b/drivers/net/arcnet/rfc1201.c
@@ -35,6 +35,7 @@
#include "arcdevice.h"
+MODULE_DESCRIPTION("ARCNet packet format (RFC 1201) module");
MODULE_LICENSE("GPL");
static __be16 type_trans(struct sk_buff *skb, struct net_device *dev);
From 9b6326354cf9a41521b79287da3bfab022ae0b6d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Wed, 14 Feb 2024 23:05:56 +0100
Subject: [PATCH 608/637] tracing/synthetic: Fix trace_string() return value
Fix trace_string() by assigning the string length to the return variable
which got lost in commit ddeea494a16f ("tracing/synthetic: Use union
instead of casts") and caused trace_string() to always return 0.
Link: https://lore.kernel.org/linux-trace-kernel/20240214220555.711598-1-thorsten.blum@toblux.com
Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fixes: ddeea494a16f ("tracing/synthetic: Use union instead of casts")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace_events_synth.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index e7af286af4f1..c82b401a294d 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry,
if (is_dynamic) {
union trace_synth_field *data = &entry->fields[*n_u64];
+ len = fetch_store_strlen((unsigned long)str_val);
data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size;
- data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val);
+ data->as_dynamic.len = len;
ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry);
From 8c7bfd8262319fd3f127a5380f593ea76f1b88a2 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Tue, 13 Feb 2024 09:23:40 -0800
Subject: [PATCH 609/637] drm/msm: Wire up tlb ops
The brute force iommu_flush_iotlb_all() was good enough for unmap, but
in some cases a map operation could require removing a table pte entry
to replace with a block entry. This also requires tlb invalidation.
Missing this was resulting an obscure iova fault on what should be a
valid buffer address.
Thanks to Robin Murphy for helping me understand the cause of the fault.
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: stable@vger.kernel.org
Fixes: b145c6e65eb0 ("drm/msm: Add support to create a local pagetable")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/578117/
---
drivers/gpu/drm/msm/msm_iommu.c | 32 +++++++++++++++++++++++++++++---
1 file changed, 29 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 5cc8d358cc97..d5512037c38b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -21,6 +21,8 @@ struct msm_iommu_pagetable {
struct msm_mmu base;
struct msm_mmu *parent;
struct io_pgtable_ops *pgtbl_ops;
+ const struct iommu_flush_ops *tlb;
+ struct device *iommu_dev;
unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */
phys_addr_t ttbr;
u32 asid;
@@ -201,11 +203,33 @@ static const struct msm_mmu_funcs pagetable_funcs = {
static void msm_iommu_tlb_flush_all(void *cookie)
{
+ struct msm_iommu_pagetable *pagetable = cookie;
+ struct adreno_smmu_priv *adreno_smmu;
+
+ if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+ return;
+
+ adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+ pagetable->tlb->tlb_flush_all((void *)adreno_smmu->cookie);
+
+ pm_runtime_put_autosuspend(pagetable->iommu_dev);
}
static void msm_iommu_tlb_flush_walk(unsigned long iova, size_t size,
size_t granule, void *cookie)
{
+ struct msm_iommu_pagetable *pagetable = cookie;
+ struct adreno_smmu_priv *adreno_smmu;
+
+ if (!pm_runtime_get_if_in_use(pagetable->iommu_dev))
+ return;
+
+ adreno_smmu = dev_get_drvdata(pagetable->parent->dev);
+
+ pagetable->tlb->tlb_flush_walk(iova, size, granule, (void *)adreno_smmu->cookie);
+
+ pm_runtime_put_autosuspend(pagetable->iommu_dev);
}
static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
@@ -213,7 +237,7 @@ static void msm_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
{
}
-static const struct iommu_flush_ops null_tlb_ops = {
+static const struct iommu_flush_ops tlb_ops = {
.tlb_flush_all = msm_iommu_tlb_flush_all,
.tlb_flush_walk = msm_iommu_tlb_flush_walk,
.tlb_add_page = msm_iommu_tlb_add_page,
@@ -254,10 +278,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
/* The incoming cfg will have the TTBR1 quirk enabled */
ttbr0_cfg.quirks &= ~IO_PGTABLE_QUIRK_ARM_TTBR1;
- ttbr0_cfg.tlb = &null_tlb_ops;
+ ttbr0_cfg.tlb = &tlb_ops;
pagetable->pgtbl_ops = alloc_io_pgtable_ops(ARM_64_LPAE_S1,
- &ttbr0_cfg, iommu->domain);
+ &ttbr0_cfg, pagetable);
if (!pagetable->pgtbl_ops) {
kfree(pagetable);
@@ -279,6 +303,8 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
/* Needed later for TLB flush */
pagetable->parent = parent;
+ pagetable->tlb = ttbr1_cfg->tlb;
+ pagetable->iommu_dev = ttbr1_cfg->iommu_dev;
pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap;
pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr;
From 8a566f94104df87a067458351675129bb4e1ece2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Feb 2024 16:22:55 +0200
Subject: [PATCH 610/637] seq_buf: Don't use "proxy" headers
Update header inclusions to follow IWYU (Include What You Use)
principle.
Link: https://lkml.kernel.org/r/20240215142255.400264-1-andriy.shevchenko@linux.intel.com
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
include/linux/seq_buf.h | 5 ++++-
lib/seq_buf.c | 14 ++++++++++++--
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index c44f4b47b945..07b26e751060 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -2,7 +2,10 @@
#ifndef _LINUX_SEQ_BUF_H
#define _LINUX_SEQ_BUF_H
-#include <linux/fs.h>
+#include <linux/bug.h>
+#include <linux/minmax.h>
+#include <linux/seq_file.h>
+#include <linux/types.h>
/*
* Trace sequences are used to allow a function to call several other functions
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 010c730ca7fc..dfbfdc497d85 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -13,9 +13,19 @@
* seq_buf_init() more than once to reset the seq_buf to start
* from scratch.
*/
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
+
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/hex.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
#include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
/**
* seq_buf_can_fit - can the new data fit in the current buffer?
From 6efe4d18796934b8ada66c1c446510e7f2d9b972 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Feb 2024 17:25:06 +0200
Subject: [PATCH 611/637] seq_buf: Fix kernel documentation
There are plenty of issues with the kernel documentation here:
- misspelled word "sequence"
- different style of returned value descriptions
- missed Return sections
- unaligned style of ASCII / NUL-terminated / etc
- wrong function references
Fix all these.
Link: https://lkml.kernel.org/r/20240215152506.598340-1-andriy.shevchenko@linux.intel.com
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
include/linux/seq_buf.h | 12 ++++++------
lib/seq_buf.c | 35 ++++++++++++++++++-----------------
2 files changed, 24 insertions(+), 23 deletions(-)
diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 07b26e751060..fe41da005970 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -13,7 +13,7 @@
*/
/**
- * seq_buf - seq buffer structure
+ * struct seq_buf - seq buffer structure
* @buffer: pointer to the buffer
* @size: size of the buffer
* @len: the amount of data inside the buffer
@@ -80,10 +80,10 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
}
/**
- * seq_buf_str - get %NUL-terminated C string from seq_buf
+ * seq_buf_str - get NUL-terminated C string from seq_buf
* @s: the seq_buf handle
*
- * This makes sure that the buffer in @s is nul terminated and
+ * This makes sure that the buffer in @s is NUL-terminated and
* safe to read as a string.
*
* Note, if this is called when the buffer has overflowed, then
@@ -93,7 +93,7 @@ static inline unsigned int seq_buf_used(struct seq_buf *s)
* After this function is called, s->buffer is safe to use
* in string operations.
*
- * Returns @s->buf after making sure it is terminated.
+ * Returns: @s->buf after making sure it is terminated.
*/
static inline const char *seq_buf_str(struct seq_buf *s)
{
@@ -113,7 +113,7 @@ static inline const char *seq_buf_str(struct seq_buf *s)
* @s: the seq_buf handle
* @bufp: the beginning of the buffer is stored here
*
- * Return the number of bytes available in the buffer, or zero if
+ * Returns: the number of bytes available in the buffer, or zero if
* there's no space.
*/
static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
@@ -135,7 +135,7 @@ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp)
* @num: the number of bytes to commit
*
* Commit @num bytes of data written to a buffer previously acquired
- * by seq_buf_get. To signal an error condition, or that the data
+ * by seq_buf_get_buf(). To signal an error condition, or that the data
* didn't fit in the available space, pass a negative @num value.
*/
static inline void seq_buf_commit(struct seq_buf *s, int num)
diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index dfbfdc497d85..f3f3436d60a9 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -32,7 +32,7 @@
* @s: the seq_buf descriptor
* @len: The length to see if it can fit in the current buffer
*
- * Returns true if there's enough unused space in the seq_buf buffer
+ * Returns: true if there's enough unused space in the seq_buf buffer
* to fit the amount of new data according to @len.
*/
static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
@@ -45,7 +45,7 @@ static bool seq_buf_can_fit(struct seq_buf *s, size_t len)
* @m: the seq_file descriptor that is the destination
* @s: the seq_buf descriptor that is the source.
*
- * Returns zero on success, non zero otherwise
+ * Returns: zero on success, non-zero otherwise.
*/
int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
{
@@ -60,9 +60,9 @@ int seq_buf_print_seq(struct seq_file *m, struct seq_buf *s)
* @fmt: printf format string
* @args: va_list of arguments from a printf() type function
*
- * Writes a vnprintf() format into the sequencce buffer.
+ * Writes a vnprintf() format into the sequence buffer.
*
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
{
@@ -88,7 +88,7 @@ int seq_buf_vprintf(struct seq_buf *s, const char *fmt, va_list args)
*
* Writes a printf() format into the sequence buffer.
*
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
{
@@ -104,12 +104,12 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
EXPORT_SYMBOL_GPL(seq_buf_printf);
/**
- * seq_buf_do_printk - printk seq_buf line by line
+ * seq_buf_do_printk - printk() seq_buf line by line
* @s: seq_buf descriptor
* @lvl: printk level
*
* printk()-s a multi-line sequential buffer line by line. The function
- * makes sure that the buffer in @s is nul terminated and safe to read
+ * makes sure that the buffer in @s is NUL-terminated and safe to read
* as a string.
*/
void seq_buf_do_printk(struct seq_buf *s, const char *lvl)
@@ -149,7 +149,7 @@ EXPORT_SYMBOL_GPL(seq_buf_do_printk);
* This function will take the format and the binary array and finish
* the conversion into the ASCII string within the buffer.
*
- * Returns zero on success, -1 on overflow.
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
{
@@ -177,7 +177,7 @@ int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary)
*
* Copy a simple string into the sequence buffer.
*
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_puts(struct seq_buf *s, const char *str)
{
@@ -206,7 +206,7 @@ EXPORT_SYMBOL_GPL(seq_buf_puts);
*
* Copy a single character into the sequence buffer.
*
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_putc(struct seq_buf *s, unsigned char c)
{
@@ -222,7 +222,7 @@ int seq_buf_putc(struct seq_buf *s, unsigned char c)
EXPORT_SYMBOL_GPL(seq_buf_putc);
/**
- * seq_buf_putmem - write raw data into the sequenc buffer
+ * seq_buf_putmem - write raw data into the sequence buffer
* @s: seq_buf descriptor
* @mem: The raw memory to copy into the buffer
* @len: The length of the raw memory to copy (in bytes)
@@ -231,7 +231,7 @@ EXPORT_SYMBOL_GPL(seq_buf_putc);
* buffer and a strcpy() would not work. Using this function allows
* for such cases.
*
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
{
@@ -259,7 +259,7 @@ int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len)
* raw memory into the buffer it writes its ASCII representation of it
* in hex characters.
*
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
unsigned int len)
@@ -307,7 +307,7 @@ int seq_buf_putmem_hex(struct seq_buf *s, const void *mem,
*
* Write a path name into the sequence buffer.
*
- * Returns the number of written bytes on success, -1 on overflow
+ * Returns: the number of written bytes on success, -1 on overflow.
*/
int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
{
@@ -342,6 +342,7 @@ int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc)
* or until it reaches the end of the content in the buffer (@s->len),
* whichever comes first.
*
+ * Returns:
* On success, it returns a positive number of the number of bytes
* it copied.
*
@@ -392,11 +393,11 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, size_t start, int cnt)
* linebuf size is maximal length for one line.
* 32 * 3 - maximum bytes per line, each printed into 2 chars + 1 for
* separating space
- * 2 - spaces separating hex dump and ascii representation
- * 32 - ascii representation
+ * 2 - spaces separating hex dump and ASCII representation
+ * 32 - ASCII representation
* 1 - terminating '\0'
*
- * Returns zero on success, -1 on overflow
+ * Returns: zero on success, -1 on overflow.
*/
int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, int prefix_type,
int rowsize, int groupsize,
From 68fb3ca0e408e00db1c3f8fccdfa19e274c033be Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 15 Feb 2024 11:14:33 -0800
Subject: [PATCH 612/637] update workarounds for gcc "asm goto" issue
In commit 4356e9f841f7 ("work around gcc bugs with 'asm goto' with
outputs") I did the gcc workaround unconditionally, because the cause of
the bad code generation wasn't entirely clear.
In the meantime, Jakub Jelinek debugged the issue, and has come up with
a fix in gcc [2], which also got backported to the still maintained
branches of gcc-11, gcc-12 and gcc-13.
Note that while the fix technically wasn't in the original gcc-14
branch, Jakub says:
"while it is true that no GCC 14 snapshots until today (or whenever the
fix will be committed) have the fix, for GCC trunk it is up to the
distros to use the latest snapshot if they use it at all and would
allow better testing of the kernel code without the workaround, so
that if there are other issues they won't be discovered years later.
Most userland code doesn't actually use asm goto with outputs..."
so we will consider gcc-14 to be fixed - if somebody is using gcc
snapshots of the gcc-14 before the fix, they should upgrade.
Note that while the bug goes back to gcc-11, in practice other gcc
changes seem to have effectively hidden it since gcc-12.1 as per a
bisect by Jakub. So even a gcc-14 snapshot without the fix likely
doesn't show actual problems.
Also, make the default 'asm_goto_output()' macro mark the asm as
volatile by hand, because of an unrelated gcc issue [1] where it doesn't
match the documented behavior ("asm goto is always volatile").
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 [1]
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 [2]
Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/
Requested-by: Jakub Jelinek <jakub@redhat.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Andrew Pinski <quic_apinski@quicinc.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/compiler-gcc.h | 7 ++++---
include/linux/compiler_types.h | 9 ++++++++-
init/Kconfig | 9 +++++++++
3 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index c1a963be7d28..75bd1692d2e3 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -67,10 +67,9 @@
/*
* GCC 'asm goto' with outputs miscompiles certain code sequences:
*
- * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420
- * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
*
- * Work it around via the same compiler barrier quirk that we used
+ * Work around it via the same compiler barrier quirk that we used
* to use for the old 'asm goto' workaround.
*
* Also, always mark such 'asm goto' statements as volatile: all
@@ -80,8 +79,10 @@
*
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619
*/
+#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND
#define asm_goto_output(x...) \
do { asm volatile goto(x); asm (""); } while (0)
+#endif
#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
#define __HAVE_BUILTIN_BSWAP32__
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 663d8791c871..0caf354cb94b 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -362,8 +362,15 @@ struct ftrace_likely_data {
#define __member_size(p) __builtin_object_size(p, 1)
#endif
+/*
+ * Some versions of gcc do not mark 'asm goto' volatile:
+ *
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979
+ *
+ * We do it here by hand, because it doesn't hurt.
+ */
#ifndef asm_goto_output
-#define asm_goto_output(x...) asm goto(x)
+#define asm_goto_output(x...) asm volatile goto(x)
#endif
#ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/init/Kconfig b/init/Kconfig
index deda3d14135b..8426d59cc634 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -89,6 +89,15 @@ config CC_HAS_ASM_GOTO_TIED_OUTPUT
# Detect buggy gcc and clang, fixed in gcc-11 clang-14.
def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null)
+config GCC_ASM_GOTO_OUTPUT_WORKAROUND
+ bool
+ depends on CC_IS_GCC && CC_HAS_ASM_GOTO_OUTPUT
+ # Fixed in GCC 14, 13.3, 12.4 and 11.5
+ # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921
+ default y if GCC_VERSION < 110500
+ default y if GCC_VERSION >= 120000 && GCC_VERSION < 120400
+ default y if GCC_VERSION >= 130000 && GCC_VERSION < 130300
+
config TOOLS_SUPPORT_RELR
def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh)
From d16df040c8dad25c962b4404d2d534bfea327c6a Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Thu, 8 Feb 2024 16:23:29 -0500
Subject: [PATCH 613/637] drm/amdgpu: make damage clips support configurable
We have observed that there are quite a number of PSR-SU panels on the
market that are unable to keep up with what user space throws at them,
resulting in hangs and random black screens. So, make damage clips
support configurable and disable it by default for PSR-SU displays.
Cc: stable@vger.kernel.org
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 13 +++++++++++++
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 +++++++
3 files changed, 21 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6dce81a061ab..517117a0796f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -200,6 +200,7 @@ extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dc_visual_confirm;
extern uint amdgpu_dm_abm_level;
extern int amdgpu_backlight;
+extern int amdgpu_damage_clips;
extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 211501ea9169..586f4d03039d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -211,6 +211,7 @@ int amdgpu_seamless = -1; /* auto */
uint amdgpu_debug_mask;
int amdgpu_agp = -1; /* auto */
int amdgpu_wbrf = -1;
+int amdgpu_damage_clips = -1; /* auto */
static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
@@ -859,6 +860,18 @@ int amdgpu_backlight = -1;
MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))");
module_param_named(backlight, amdgpu_backlight, bint, 0444);
+/**
+ * DOC: damageclips (int)
+ * Enable or disable damage clips support. If damage clips support is disabled,
+ * we will force full frame updates, irrespective of what user space sends to
+ * us.
+ *
+ * Defaults to -1 (where it is enabled unless a PSR-SU display is detected).
+ */
+MODULE_PARM_DESC(damageclips,
+ "Damage clips support (0 = disable, 1 = enable, -1 auto (default))");
+module_param_named(damageclips, amdgpu_damage_clips, int, 0444);
+
/**
* DOC: tmz (int)
* Trusted Memory Zone (TMZ) is a method to protect data being written
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 59d2eee72a32..d5ef07af9906 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5219,6 +5219,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
struct drm_plane_state *new_plane_state,
struct drm_crtc_state *crtc_state,
struct dc_flip_addrs *flip_addrs,
+ bool is_psr_su,
bool *dirty_regions_changed)
{
struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state);
@@ -5243,6 +5244,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
num_clips = drm_plane_get_damage_clips_count(new_plane_state);
clips = drm_plane_get_damage_clips(new_plane_state);
+ if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 &&
+ is_psr_su)))
+ goto ffu;
+
if (!dm_crtc_state->mpo_requested) {
if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS)
goto ffu;
@@ -8298,6 +8303,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
fill_dc_dirty_rects(plane, old_plane_state,
new_plane_state, new_crtc_state,
&bundle->flip_addrs[planes_count],
+ acrtc_state->stream->link->psr_settings.psr_version ==
+ DC_PSR_VERSION_SU_1,
&dirty_rects_changed);
/*
From a0c9956a8d5a808c173028f1e388377a890a2fdb Mon Sep 17 00:00:00 2001
From: Kent Russell <kent.russell@amd.com>
Date: Tue, 6 Feb 2024 12:45:44 -0500
Subject: [PATCH 614/637] drm/amdkfd: Fix L2 cache size reporting in GFX9.4.3
Its currently incorrectly multiplied by number of XCCs in the partition
Fixes: be457b2252b6 ("drm/amdkfd: Update cache info for GFX 9.4.3")
Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index e5f7c92eebcb..6ed2ec381aaa 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1638,12 +1638,10 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext,
else
mode = UNKNOWN_MEMORY_PARTITION_MODE;
- if (pcache->cache_level == 2)
- pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc;
- else if (mode)
- pcache->cache_size = pcache_info[cache_type].cache_size / mode;
- else
- pcache->cache_size = pcache_info[cache_type].cache_size;
+ pcache->cache_size = pcache_info[cache_type].cache_size;
+ /* Partition mode only affects L3 cache size */
+ if (mode && pcache->cache_level == 3)
+ pcache->cache_size /= mode;
if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE)
pcache->cache_type |= HSA_CACHE_TYPE_DATA;
From 17ba9cde11c2bfebbd70867b0a2ac4a22e573379 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 9 Feb 2024 16:02:42 +0300
Subject: [PATCH 615/637] drm/amd/display: Fix && vs || typos
These ANDs should be ORs or it will lead to a NULL dereference.
Fixes: fb5a3d037082 ("drm/amd/display: Add NULL test for 'timing generator' in 'dcn21_set_pipe()'")
Fixes: 886571d217d7 ("drm/amd/display: Fix 'panel_cntl' could be null in 'dcn21_set_backlight_level()'")
Reviewed-by: Anthony Koo <anthony.koo@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
index 5c7f380a84f9..7252f5f781f0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
@@ -211,7 +211,7 @@ void dcn21_set_pipe(struct pipe_ctx *pipe_ctx)
struct dmcu *dmcu = pipe_ctx->stream->ctx->dc->res_pool->dmcu;
uint32_t otg_inst;
- if (!abm && !tg && !panel_cntl)
+ if (!abm || !tg || !panel_cntl)
return;
otg_inst = tg->inst;
@@ -245,7 +245,7 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx,
struct panel_cntl *panel_cntl = pipe_ctx->stream->link->panel_cntl;
uint32_t otg_inst;
- if (!abm && !tg && !panel_cntl)
+ if (!abm || !tg || !panel_cntl)
return false;
otg_inst = tg->inst;
From 7edb5830ecb0033184ee2fa01ae8af17d56450ec Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 5 Feb 2024 16:07:36 +0530
Subject: [PATCH 616/637] drm/amd/display: Initialize 'wait_time_microsec'
variable in link_dp_training_dpia.c
wait_time_microsec = max(wait_time_microsec, (uint32_t)
DPIA_CLK_SYNC_DELAY);
Above line is trying to assign the maximum value between
'wait_time_microsec' and 'DPIA_CLK_SYNC_DELAY' to wait_time_microsec.
However, 'wait_time_microsec' has not been assigned a value before this
line, initialize 'wait_time_microsec' at the point of declaration.
Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/link/protocols/link_dp_training_dpia.c:697 dpia_training_eq_non_transparent() error: uninitialized symbol 'wait_time_microsec'.
Fixes: 630168a97314 ("drm/amd/display: move dp link training logic to link_dp_training")
Cc: Wenjing Liu <wenjing.liu@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../drm/amd/display/dc/link/protocols/link_dp_training_dpia.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
index e8dda44b23cb..5d36bab0029c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c
@@ -619,7 +619,7 @@ static enum link_training_result dpia_training_eq_non_transparent(
uint32_t retries_eq = 0;
enum dc_status status;
enum dc_dp_training_pattern tr_pattern;
- uint32_t wait_time_microsec;
+ uint32_t wait_time_microsec = 0;
enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
union lane_align_status_updated dpcd_lane_status_updated = {0};
union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {0};
From 88c6d84dd8f70e498f89972449e6ebb7aa1309c0 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 5 Feb 2024 15:07:02 +0530
Subject: [PATCH 617/637] drm/amd/display: Fix possible use of uninitialized
'max_chunks_fbc_mode' in 'calculate_bandwidth()'
'max_chunks_fbc_mode' is only declared and assigned a value under a
specific condition in the following lines:
if (data->fbc_en[i] == 1) {
max_chunks_fbc_mode = 128 - dmif_chunk_buff_margin;
}
If 'data->fbc_en[i]' is not equal to 1 for any i, max_chunks_fbc_mode
will not be initialized if it's used outside of this for loop.
Ensure that 'max_chunks_fbc_mode' is properly initialized before it's
used. Initialize it to a default value right after its declaration to
ensure that it gets a value assigned under all possible control flow
paths.
Thus fixing the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/basics/dce_calcs.c:914 calculate_bandwidth() error: uninitialized symbol 'max_chunks_fbc_mode'.
drivers/gpu/drm/amd/amdgpu/../display/dc/basics/dce_calcs.c:917 calculate_bandwidth() error: uninitialized symbol 'max_chunks_fbc_mode'.
Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)")
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index f2dfa96f9ef5..39530b2ea495 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -94,7 +94,7 @@ static void calculate_bandwidth(
const uint32_t s_high = 7;
const uint32_t dmif_chunk_buff_margin = 1;
- uint32_t max_chunks_fbc_mode;
+ uint32_t max_chunks_fbc_mode = 0;
int32_t num_cursor_lines;
int32_t i, j, k;
From ccc514b7e7acbd301219cbaec0fc0bfe5741acee Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 5 Feb 2024 16:54:10 +0530
Subject: [PATCH 618/637] drm/amd/display: Fix possible buffer overflow in
'find_dcfclk_for_voltage()'
when 'find_dcfclk_for_voltage()' function is looping over
VG_NUM_SOC_VOLTAGE_LEVELS (which is 8), but the size of the DcfClocks
array is VG_NUM_DCFCLK_DPM_LEVELS (which is 7).
When the loop variable i reaches 7, the function tries to access
clock_table->DcfClocks[7]. However, since the size of the DcfClocks
array is 7, the valid indices are 0 to 6. Index 7 is beyond the size of
the array, leading to a buffer overflow.
Reported by smatch & thus fixing the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/clk_mgr/dcn301/vg_clk_mgr.c:550 find_dcfclk_for_voltage() error: buffer overflow 'clock_table->DcfClocks' 7 <= 7
Fixes: 3a83e4e64bb1 ("drm/amd/display: Add dcn3.01 support to DC (v2)")
Cc: Roman Li <Roman.Li@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index a5489fe6875f..aa9fd1dc550a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -546,6 +546,8 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta
int i;
for (i = 0; i < VG_NUM_SOC_VOLTAGE_LEVELS; i++) {
+ if (i >= VG_NUM_DCFCLK_DPM_LEVELS)
+ break;
if (clock_table->SocVoltage[i] == voltage)
return clock_table->DcfClocks[i];
}
From 3a9626c816db901def438dc2513622e281186d39 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 7 Feb 2024 23:52:55 -0600
Subject: [PATCH 619/637] drm/amd: Stop evicting resources on APUs in suspend
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
commit 5095d5418193 ("drm/amd: Evict resources during PM ops prepare()
callback") intentionally moved the eviction of resources to earlier in
the suspend process, but this introduced a subtle change that it occurs
before adev->in_s0ix or adev->in_s3 are set. This meant that APUs
actually started to evict resources at suspend time as well.
Explicitly set s0ix or s3 in the prepare() stage, and unset them if the
prepare() stage failed.
v2: squash in warning fix from Stephen Rothwell
Reported-by: Jürg Billeter <j@bitron.ch>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3132#note_2271038
Fixes: 5095d5418193 ("drm/amd: Evict resources during PM ops prepare() callback")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 15 +++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +++++++++--
3 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 517117a0796f..79827a6dcd7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1550,9 +1550,11 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev);
#else
static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
+static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { }
#endif
#if defined(CONFIG_DRM_AMD_DC)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 2deebece810e..cc21ed67a330 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -1519,4 +1519,19 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
#endif /* CONFIG_AMD_PMC */
}
+/**
+ * amdgpu_choose_low_power_state
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * Choose the target low power state for the GPU
+ */
+void amdgpu_choose_low_power_state(struct amdgpu_device *adev)
+{
+ if (amdgpu_acpi_is_s0ix_active(adev))
+ adev->in_s0ix = true;
+ else if (amdgpu_acpi_is_s3_active(adev))
+ adev->in_s3 = true;
+}
+
#endif /* CONFIG_SUSPEND */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fdde7488d0ed..d4b3d044935c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4514,13 +4514,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
struct amdgpu_device *adev = drm_to_adev(dev);
int i, r;
+ amdgpu_choose_low_power_state(adev);
+
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
/* Evict the majority of BOs before starting suspend sequence */
r = amdgpu_device_evict_resources(adev);
if (r)
- return r;
+ goto unprepare;
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.valid)
@@ -4529,10 +4531,15 @@ int amdgpu_device_prepare(struct drm_device *dev)
continue;
r = adev->ip_blocks[i].version->funcs->prepare_suspend((void *)adev);
if (r)
- return r;
+ goto unprepare;
}
return 0;
+
+unprepare:
+ adev->in_s0ix = adev->in_s3 = false;
+
+ return r;
}
/**
From 916361685319098f696b798ef1560f69ed96e934 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 7 Feb 2024 23:52:54 -0600
Subject: [PATCH 620/637] Revert "drm/amd: flush any delayed gfxoff on suspend
entry"
commit ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring
callbacks") caused GFXOFF control to be used more heavily and the
codepath that was removed from commit 0dee72639533 ("drm/amd: flush any
delayed gfxoff on suspend entry") now can be exercised at suspend again.
Users report that by using GNOME to suspend the lockscreen trigger will
cause SDMA traffic and the system can deadlock.
This reverts commit 0dee726395333fea833eaaf838bc80962df886c8.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring callbacks")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 9 ++++++++-
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d4b3d044935c..94bdb5fa6ebc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4576,7 +4576,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);
cancel_delayed_work_sync(&adev->delayed_init_work);
- flush_delayed_work(&adev->gfx.gfx_off_delay_work);
amdgpu_ras_suspend(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index b9674c57c436..6ddc8e3360e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -723,8 +723,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
if (adev->gfx.gfx_off_req_count == 0 &&
!adev->gfx.gfx_off_state) {
- schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+ /* If going to s2idle, no need to wait */
+ if (adev->in_s0ix) {
+ if (!amdgpu_dpm_set_powergating_by_smu(adev,
+ AMD_IP_BLOCK_TYPE_GFX, true))
+ adev->gfx.gfx_off_state = true;
+ } else {
+ schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
delay);
+ }
}
} else {
if (adev->gfx.gfx_off_req_count == 0) {
From 94b38b895dec8c0ef093140a141e191b60ff614c Mon Sep 17 00:00:00 2001
From: Zhikai Zhai <zhikai.zhai@amd.com>
Date: Mon, 29 Jan 2024 17:02:18 +0800
Subject: [PATCH 621/637] drm/amd/display: Add align done check
[WHY]
We Double-check link status if training successful,
but miss the lane align status.
[HOW]
Add the lane align status check
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Zhikai Zhai <zhikai.zhai@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../gpu/drm/amd/display/dc/link/protocols/link_dp_training.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 5a0b04518956..16a62e018712 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -517,6 +517,7 @@ enum link_training_result dp_check_link_loss_status(
{
enum link_training_result status = LINK_TRAINING_SUCCESS;
union lane_status lane_status;
+ union lane_align_status_updated dpcd_lane_status_updated;
uint8_t dpcd_buf[6] = {0};
uint32_t lane;
@@ -532,10 +533,12 @@ enum link_training_result dp_check_link_loss_status(
* check lanes status
*/
lane_status.raw = dp_get_nibble_at_index(&dpcd_buf[2], lane);
+ dpcd_lane_status_updated.raw = dpcd_buf[4];
if (!lane_status.bits.CHANNEL_EQ_DONE_0 ||
!lane_status.bits.CR_DONE_0 ||
- !lane_status.bits.SYMBOL_LOCKED_0) {
+ !lane_status.bits.SYMBOL_LOCKED_0 ||
+ !dp_is_interlane_aligned(dpcd_lane_status_updated)) {
/* if one of the channel equalization, clock
* recovery or symbol lock is dropped
* consider it as (link has been
From a538dabf772c169641e151834e161e241802ab33 Mon Sep 17 00:00:00 2001
From: Sohaib Nadeem <sohaib.nadeem@amd.com>
Date: Mon, 29 Jan 2024 17:33:40 -0500
Subject: [PATCH 622/637] Revert "drm/amd/display: increased min_dcfclk_mhz and
min_fclk_mhz"
[why]:
This reverts commit 2ff33c759a4247c84ec0b7815f1f223e155ba82a.
The commit caused corruption when running some applications in fullscreen
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Sohaib Nadeem <sohaib.nadeem@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index ba76dd4a2ce2..a0a65e099104 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -2760,7 +2760,7 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
struct _vcs_dpi_voltage_scaling_st entry = {0};
struct clk_limit_table_entry max_clk_data = {0};
- unsigned int min_dcfclk_mhz = 399, min_fclk_mhz = 599;
+ unsigned int min_dcfclk_mhz = 199, min_fclk_mhz = 299;
static const unsigned int num_dcfclk_stas = 5;
unsigned int dcfclk_sta_targets[DC__VOLTAGE_STATES] = {199, 615, 906, 1324, 1564};
From a589fa17cc4456df75f16fa3b49e8da0112e5100 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Tue, 6 Feb 2024 09:34:25 +0530
Subject: [PATCH 623/637] drm/amd/display: Fix possible NULL dereference on
device remove/driver unload
As part of a cleanup amdgpu_dm_fini() function, which is typically
called when a device is being shut down or a driver is being unloaded
The below error message suggests that there is a potential null pointer
dereference issue with adev->dm.dc.
In the below, line of code where adev->dm.dc is used without a preceding
null check:
for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
To fix this issue, add a null check for adev->dm.dc before this line.
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:1959 amdgpu_dm_fini() error: we previously assumed 'adev->dm.dc' could be null (see line 1943)
Fixes: 006c26a0f1c8 ("drm/amd/display: Fix crash on device remove/driver unload")
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d5ef07af9906..e0f121b221f5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1956,7 +1956,7 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
&adev->dm.dmub_bo_gpu_addr,
&adev->dm.dmub_bo_cpu_addr);
- if (adev->dm.hpd_rx_offload_wq) {
+ if (adev->dm.hpd_rx_offload_wq && adev->dm.dc) {
for (i = 0; i < adev->dm.dc->caps.max_links; i++) {
if (adev->dm.hpd_rx_offload_wq[i].wq) {
destroy_workqueue(adev->dm.hpd_rx_offload_wq[i].wq);
From deb110292180cd501f6fde2a0178d65fcbcabb0c Mon Sep 17 00:00:00 2001
From: Tom Chung <chiahsuan.chung@amd.com>
Date: Tue, 30 Jan 2024 15:34:08 +0800
Subject: [PATCH 624/637] drm/amd/display: Preserve original aspect ratio in
create stream
[Why]
The original picture aspect ratio in mode struct may have chance be
overwritten with wrong aspect ratio data in create_stream_for_sink().
It will create a different VIC output and cause HDMI compliance test
failed.
[How]
Preserve the original picture aspect ratio data during create the
stream.
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e0f121b221f5..cf875751971f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6199,7 +6199,9 @@ create_stream_for_sink(struct drm_connector *connector,
if (recalculate_timing) {
freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
drm_mode_copy(&saved_mode, &mode);
+ saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
drm_mode_copy(&mode, freesync_mode);
+ mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
} else {
decide_crtc_timing_for_drm_display_mode(
&mode, preferred_mode, scale);
From 46806e59a87790760870d216f54951a5b4d545bc Mon Sep 17 00:00:00 2001
From: Roman Li <roman.li@amd.com>
Date: Tue, 30 Jan 2024 18:07:24 -0500
Subject: [PATCH 625/637] drm/amd/display: Fix array-index-out-of-bounds in
dcn35_clkmgr
[Why]
There is a potential memory access violation while
iterating through array of dcn35 clks.
[How]
Limit iteration per array size.
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 14cec1c7b718..e64890259235 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -655,10 +655,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
+ uint32_t num_memps, num_fclk, num_dcfclk;
int i;
/* Determine min/max p-state values. */
- for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+ num_memps = (clock_table->NumMemPstatesEnabled > NUM_MEM_PSTATE_LEVELS) ? NUM_MEM_PSTATE_LEVELS :
+ clock_table->NumMemPstatesEnabled;
+ for (i = 0; i < num_memps; i++) {
uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
@@ -670,7 +673,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
min_dram_speed_mts = max_dram_speed_mts;
min_pstate = max_pstate;
- for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+ for (i = 0; i < num_memps; i++) {
uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
@@ -699,9 +702,13 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
- max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
+ num_fclk = (clock_table->NumFclkLevelsEnabled > NUM_FCLK_DPM_LEVELS) ? NUM_FCLK_DPM_LEVELS :
+ clock_table->NumFclkLevelsEnabled;
+ max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, num_fclk);
- for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+ num_dcfclk = (clock_table->NumFclkLevelsEnabled > NUM_DCFCLK_DPM_LEVELS) ? NUM_DCFCLK_DPM_LEVELS :
+ clock_table->NumDcfClkLevelsEnabled;
+ for (i = 0; i < num_dcfclk; i++) {
int j;
/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
From 0484e05d048b66d01d1f3c1d2306010bb57d8738 Mon Sep 17 00:00:00 2001
From: Sohaib Nadeem <sohaib.nadeem@amd.com>
Date: Wed, 31 Jan 2024 16:40:37 -0500
Subject: [PATCH 626/637] drm/amd/display: fixed integer types and null check
locations
[why]:
issues fixed:
- comparison with wider integer type in loop condition which can cause
infinite loops
- pointer dereference before null check
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Reviewed-by: Josip Pavic <josip.pavic@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Sohaib Nadeem <sohaib.nadeem@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../gpu/drm/amd/display/dc/bios/bios_parser2.c | 16 ++++++++++------
.../drm/amd/display/dc/link/link_validation.c | 2 +-
2 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 960c4b4f6ddf..05f392501c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1850,19 +1850,21 @@ static enum bp_result get_firmware_info_v3_2(
/* Vega12 */
smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2,
DATA_TABLES(smu_info));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
if (!smu_info_v3_2)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_2->gpuclk_ss_percentage);
+
info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10;
} else if (revision.minor == 3) {
/* Vega20 */
smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3,
DATA_TABLES(smu_info));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
if (!smu_info_v3_3)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", smu_info_v3_3->gpuclk_ss_percentage);
+
info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10;
}
@@ -2422,10 +2424,11 @@ static enum bp_result get_integrated_info_v11(
info_v11 = GET_IMAGE(struct atom_integrated_system_info_v1_11,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
if (info_v11 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v11->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v11->gpucapinfo);
/*
@@ -2637,11 +2640,12 @@ static enum bp_result get_integrated_info_v2_1(
info_v2_1 = GET_IMAGE(struct atom_integrated_system_info_v2_1,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
if (info_v2_1 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_1->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v2_1->gpucapinfo);
/*
@@ -2799,11 +2803,11 @@ static enum bp_result get_integrated_info_v2_2(
info_v2_2 = GET_IMAGE(struct atom_integrated_system_info_v2_2,
DATA_TABLES(integratedsysteminfo));
- DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
-
if (info_v2_2 == NULL)
return BP_RESULT_BADBIOSTABLE;
+ DC_LOG_BIOS("gpuclk_ss_percentage (unit of 0.001 percent): %d\n", info_v2_2->gpuclk_ss_percentage);
+
info->gpu_cap_info =
le32_to_cpu(info_v2_2->gpucapinfo);
/*
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index 8fe66c367850..5b0bc7f6a188 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -361,7 +361,7 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un
struct dc_link *dpia_link[MAX_DPIA_NUM] = {0};
int num_dpias = 0;
- for (uint8_t i = 0; i < num_streams; ++i) {
+ for (unsigned int i = 0; i < num_streams; ++i) {
if (stream[i].signal == SIGNAL_TYPE_DISPLAY_PORT) {
/* new dpia sst stream, check whether it exceeds max dpia */
if (num_dpias >= MAX_DPIA_NUM)
From 2f542421a47e8246e9b7d2c6508fe3a6e6c63078 Mon Sep 17 00:00:00 2001
From: Thong <thong.thai@amd.com>
Date: Tue, 6 Feb 2024 18:05:16 -0500
Subject: [PATCH 627/637] drm/amdgpu/soc21: update VCN 4 max HEVC encoding
resolution
Update the maximum resolution reported for HEVC encoding on VCN 4
devices to reflect its 8K encoding capability.
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3159
Signed-off-by: Thong <thong.thai@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/soc21.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 48c6efcdeac9..4d7188912edf 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
/* SOC21 */
static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
- {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
- {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
From a82197e3a5f45450cbaf92095d8a51249dc44c79 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sun, 11 Feb 2024 09:04:19 +0530
Subject: [PATCH 628/637] drm/amdgpu/display: Initialize gamma correction mode
variable in dcn30_get_gamcor_current()
The dcn30_get_gamcor_current() function is responsible for determining
the current gamma correction mode used by the display controller.
However, the 'mode' variable, which stores the gamma correction mode,
was not initialized before its first usage, leading to an uninitialized
symbol error.
Thus initializes the 'mode' variable with a default value of LUT_BYPASS
before the conditional statements in the function, improves code clarity
and stability, ensuring correct behavior of the
dcn30_get_gamcor_current() function in determining the gamma correction
mode.
Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn30/dcn30_dpp_cm.c:77 dpp30_get_gamcor_current() error: uninitialized symbol 'mode'.
Fixes: 03f54d7d3448 ("drm/amd/display: Add DCN3 DPP")
Cc: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Cc: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Roman Li <roman.li@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
index e43f77c11c00..5f97a868ada3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp_cm.c
@@ -56,16 +56,13 @@ static void dpp3_enable_cm_block(
static enum dc_lut_mode dpp30_get_gamcor_current(struct dpp *dpp_base)
{
- enum dc_lut_mode mode;
+ enum dc_lut_mode mode = LUT_BYPASS;
uint32_t state_mode;
uint32_t lut_mode;
struct dcn3_dpp *dpp = TO_DCN30_DPP(dpp_base);
REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_MODE_CURRENT, &state_mode);
- if (state_mode == 0)
- mode = LUT_BYPASS;
-
if (state_mode == 2) {//Programmable RAM LUT
REG_GET(CM_GAMCOR_CONTROL, CM_GAMCOR_SELECT_CURRENT, &lut_mode);
if (lut_mode == 0)
From 0d555e481c1333c8ae170198ca111947c22fc9c9 Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Tue, 23 Jan 2024 12:20:06 -0500
Subject: [PATCH 629/637] drm/amd/display: Increase ips2_eval delay for DCN35
[Why]
New worst-case measurement observed at 1897us.
[How]
Increase to 2000us to cover the new worst case + margin.
Reviewed-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 1c3d89264ef7..5fdcda8f8602 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -780,7 +780,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_z10 = false,
.ignore_pg = true,
.psp_disabled_wa = true,
- .ips2_eval_delay_us = 1650,
+ .ips2_eval_delay_us = 2000,
.ips2_entry_delay_us = 800,
.static_screen_wait_frames = 2,
};
From e3de58f8fd5bda8685bb87bf7457bbc10479765b Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Wed, 31 Jan 2024 19:33:49 -0500
Subject: [PATCH 630/637] drm/amdkfd: update SIMD distribution algo for GFXIP
9.4.2 onwards
In certain cooperative group dispatch scenarios the default SPI resource
allocation may cause reduced per-CU workgroup occupancy. Set
COMPUTE_RESOURCE_LIMITS.FORCE_SIMD_DIST=1 to mitigate soft hang
scenarions.
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Suggested-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 9 +++++++++
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 4 +++-
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 42d881809dc7..697b6d530d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -303,6 +303,15 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
update_cu_mask(mm, mqd, minfo, 0);
set_priority(m, q);
+ if (minfo && KFD_GC_VERSION(mm->dev) >= IP_VERSION(9, 4, 2)) {
+ if (minfo->update_flag & UPDATE_FLAG_IS_GWS)
+ m->compute_resource_limits |=
+ COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+ else
+ m->compute_resource_limits &=
+ ~COMPUTE_RESOURCE_LIMITS__FORCE_SIMD_DIST_MASK;
+ }
+
q->is_active = QUEUE_IS_ACTIVE(*q);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 677281c0793e..80320b8603fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -532,6 +532,7 @@ struct queue_properties {
enum mqd_update_flag {
UPDATE_FLAG_DBG_WA_ENABLE = 1,
UPDATE_FLAG_DBG_WA_DISABLE = 2,
+ UPDATE_FLAG_IS_GWS = 4, /* quirk for gfx9 IP */
};
struct mqd_update_info {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 43eff221eae5..4858112f9a53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -95,6 +95,7 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
void *gws)
{
+ struct mqd_update_info minfo = {0};
struct kfd_node *dev = NULL;
struct process_queue_node *pqn;
struct kfd_process_device *pdd;
@@ -146,9 +147,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
}
pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
+ minfo.update_flag = gws ? UPDATE_FLAG_IS_GWS : 0;
return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
- pqn->q, NULL);
+ pqn->q, &minfo);
}
void kfd_process_dequeue_from_all_devices(struct kfd_process *p)
From a8ac4bcaeb660c5eeb273507e8dbf713ba56de44 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Fri, 9 Feb 2024 20:23:19 -0500
Subject: [PATCH 631/637] drm/amdgpu: Fix implicit assumtion in gfx11 debug
flags
Gfx11 debug flags mask is currently set with an implicit assumption that
no other mqd update flags exist. This needs to be fixed with newly
introduced flag UPDATE_FLAG_IS_GWS by the previous patch.
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index d722cbd31783..826bc4f6c8a7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -55,8 +55,8 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
m = get_mqd(mqd);
if (has_wa_flag) {
- uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
- 0xffff : 0xffffffff;
+ uint32_t wa_mask =
+ (minfo->update_flag & UPDATE_FLAG_DBG_WA_ENABLE) ? 0xffff : 0xffffffff;
m->compute_static_thread_mgmt_se0 = wa_mask;
m->compute_static_thread_mgmt_se1 = wa_mask;
From 14db5f64a971fce3d8ea35de4dfc7f443a3efb92 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 8 Feb 2024 17:26:59 +0900
Subject: [PATCH 632/637] zonefs: Improve error handling
Write error handling is racy and can sometime lead to the error recovery
path wrongly changing the inode size of a sequential zone file to an
incorrect value which results in garbage data being readable at the end
of a file. There are 2 problems:
1) zonefs_file_dio_write() updates a zone file write pointer offset
after issuing a direct IO with iomap_dio_rw(). This update is done
only if the IO succeed for synchronous direct writes. However, for
asynchronous direct writes, the update is done without waiting for
the IO completion so that the next asynchronous IO can be
immediately issued. However, if an asynchronous IO completes with a
failure right before the i_truncate_mutex lock protecting the update,
the update may change the value of the inode write pointer offset
that was corrected by the error path (zonefs_io_error() function).
2) zonefs_io_error() is called when a read or write error occurs. This
function executes a report zone operation using the callback function
zonefs_io_error_cb(), which does all the error recovery handling
based on the current zone condition, write pointer position and
according to the mount options being used. However, depending on the
zoned device being used, a report zone callback may be executed in a
context that is different from the context of __zonefs_io_error(). As
a result, zonefs_io_error_cb() may be executed without the inode
truncate mutex lock held, which can lead to invalid error processing.
Fix both problems as follows:
- Problem 1: Perform the inode write pointer offset update before a
direct write is issued with iomap_dio_rw(). This is safe to do as
partial direct writes are not supported (IOMAP_DIO_PARTIAL is not
set) and any failed IO will trigger the execution of zonefs_io_error()
which will correct the inode write pointer offset to reflect the
current state of the one on the device.
- Problem 2: Change zonefs_io_error_cb() into zonefs_handle_io_error()
and call this function directly from __zonefs_io_error() after
obtaining the zone information using blkdev_report_zones() with a
simple callback function that copies to a local stack variable the
struct blk_zone obtained from the device. This ensures that error
handling is performed holding the inode truncate mutex.
This change also simplifies error handling for conventional zone files
by bypassing the execution of report zones entirely. This is safe to
do because the condition of conventional zones cannot be read-only or
offline and conventional zone files are always fully mapped with a
constant file size.
Reported-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Fixes: 8dcc1a9d90c1 ("fs: New zonefs file system")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
---
fs/zonefs/file.c | 42 +++++++++++++++++++-----------
fs/zonefs/super.c | 66 +++++++++++++++++++++++++++--------------------
2 files changed, 65 insertions(+), 43 deletions(-)
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 6ab2318a9c8e..dba5dcb62bef 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -348,7 +348,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
struct zonefs_inode_info *zi = ZONEFS_I(inode);
if (error) {
- zonefs_io_error(inode, true);
+ /*
+ * For Sync IOs, error recovery is called from
+ * zonefs_file_dio_write().
+ */
+ if (!is_sync_kiocb(iocb))
+ zonefs_io_error(inode, true);
return error;
}
@@ -491,6 +496,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
ret = -EINVAL;
goto inode_unlock;
}
+ /*
+ * Advance the zone write pointer offset. This assumes that the
+ * IO will succeed, which is OK to do because we do not allow
+ * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO
+ * fails, the error path will correct the write pointer offset.
+ */
+ z->z_wpoffset += count;
+ zonefs_inode_account_active(inode);
mutex_unlock(&zi->i_truncate_mutex);
}
@@ -504,20 +517,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
if (ret == -ENOTBLK)
ret = -EBUSY;
- if (zonefs_zone_is_seq(z) &&
- (ret > 0 || ret == -EIOCBQUEUED)) {
- if (ret > 0)
- count = ret;
-
- /*
- * Update the zone write pointer offset assuming the write
- * operation succeeded. If it did not, the error recovery path
- * will correct it. Also do active seq file accounting.
- */
- mutex_lock(&zi->i_truncate_mutex);
- z->z_wpoffset += count;
- zonefs_inode_account_active(inode);
- mutex_unlock(&zi->i_truncate_mutex);
+ /*
+ * For a failed IO or partial completion, trigger error recovery
+ * to update the zone write pointer offset to a correct value.
+ * For asynchronous IOs, zonefs_file_write_dio_end_io() may already
+ * have executed error recovery if the IO already completed when we
+ * reach here. However, we cannot know that and execute error recovery
+ * again (that will not change anything).
+ */
+ if (zonefs_zone_is_seq(z)) {
+ if (ret > 0 && ret != count)
+ ret = -EIO;
+ if (ret < 0 && ret != -EIOCBQUEUED)
+ zonefs_io_error(inode, true);
}
inode_unlock:
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 93971742613a..b6e8e7c96251 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -246,16 +246,18 @@ static void zonefs_inode_update_mode(struct inode *inode)
z->z_mode = inode->i_mode;
}
-struct zonefs_ioerr_data {
- struct inode *inode;
- bool write;
-};
-
static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
- struct zonefs_ioerr_data *err = data;
- struct inode *inode = err->inode;
+ struct blk_zone *z = data;
+
+ *z = *zone;
+ return 0;
+}
+
+static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone,
+ bool write)
+{
struct zonefs_zone *z = zonefs_inode_zone(inode);
struct super_block *sb = inode->i_sb;
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
@@ -270,8 +272,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
data_size = zonefs_check_zone_condition(sb, z, zone);
isize = i_size_read(inode);
if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) &&
- !err->write && isize == data_size)
- return 0;
+ !write && isize == data_size)
+ return;
/*
* At this point, we detected either a bad zone or an inconsistency
@@ -292,7 +294,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
* In all cases, warn about inode size inconsistency and handle the
* IO error according to the zone condition and to the mount options.
*/
- if (zonefs_zone_is_seq(z) && isize != data_size)
+ if (isize != data_size)
zonefs_warn(sb,
"inode %lu: invalid size %lld (should be %lld)\n",
inode->i_ino, isize, data_size);
@@ -352,8 +354,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
zonefs_i_size_write(inode, data_size);
z->z_wpoffset = data_size;
zonefs_inode_account_active(inode);
-
- return 0;
}
/*
@@ -367,23 +367,25 @@ void __zonefs_io_error(struct inode *inode, bool write)
{
struct zonefs_zone *z = zonefs_inode_zone(inode);
struct super_block *sb = inode->i_sb;
- struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
unsigned int noio_flag;
- unsigned int nr_zones = 1;
- struct zonefs_ioerr_data err = {
- .inode = inode,
- .write = write,
- };
+ struct blk_zone zone;
int ret;
/*
- * The only files that have more than one zone are conventional zone
- * files with aggregated conventional zones, for which the inode zone
- * size is always larger than the device zone size.
+ * Conventional zone have no write pointer and cannot become read-only
+ * or offline. So simply fake a report for a single or aggregated zone
+ * and let zonefs_handle_io_error() correct the zone inode information
+ * according to the mount options.
*/
- if (z->z_size > bdev_zone_sectors(sb->s_bdev))
- nr_zones = z->z_size >>
- (sbi->s_zone_sectors_shift + SECTOR_SHIFT);
+ if (!zonefs_zone_is_seq(z)) {
+ zone.start = z->z_sector;
+ zone.len = z->z_size >> SECTOR_SHIFT;
+ zone.wp = zone.start + zone.len;
+ zone.type = BLK_ZONE_TYPE_CONVENTIONAL;
+ zone.cond = BLK_ZONE_COND_NOT_WP;
+ zone.capacity = zone.len;
+ goto handle_io_error;
+ }
/*
* Memory allocations in blkdev_report_zones() can trigger a memory
@@ -394,12 +396,20 @@ void __zonefs_io_error(struct inode *inode, bool write)
* the GFP_NOIO context avoids both problems.
*/
noio_flag = memalloc_noio_save();
- ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones,
- zonefs_io_error_cb, &err);
- if (ret != nr_zones)
+ ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1,
+ zonefs_io_error_cb, &zone);
+ memalloc_noio_restore(noio_flag);
+
+ if (ret != 1) {
zonefs_err(sb, "Get inode %lu zone information failed %d\n",
inode->i_ino, ret);
- memalloc_noio_restore(noio_flag);
+ zonefs_warn(sb, "remounting filesystem read-only\n");
+ sb->s_flags |= SB_RDONLY;
+ return;
+ }
+
+handle_io_error:
+ zonefs_handle_io_error(inode, &zone, write);
}
static struct kmem_cache *zonefs_inode_cachep;
From 4860abb91f3d7fbaf8147d54782149bb1fc45892 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 6 Feb 2024 16:34:22 -0600
Subject: [PATCH 633/637] smb: Fix regression in writes when non-standard
maximum write size negotiated
The conversion to netfs in the 6.3 kernel caused a regression when
maximum write size is set by the server to an unexpected value which is
not a multiple of 4096 (similarly if the user overrides the maximum
write size by setting mount parm "wsize", but sets it to a value that
is not a multiple of 4096). When negotiated write size is not a
multiple of 4096 the netfs code can skip the end of the final
page when doing large sequential writes, causing data corruption.
This section of code is being rewritten/removed due to a large
netfs change, but until that point (ie for the 6.3 kernel until now)
we can not support non-standard maximum write sizes.
Add a warning if a user specifies a wsize on mount that is not
a multiple of 4096 (and round down), also add a change where we
round down the maximum write size if the server negotiates a value
that is not a multiple of 4096 (we also have to check to make sure that
we do not round it down to zero).
Reported-by: R. Diez" <rdiez-2006@rd10.de>
Fixes: d08089f649a0 ("cifs: Change the I/O paths to use an iterator rather than a page list")
Suggested-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Acked-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Tested-by: Matthew Ruffell <matthew.ruffell@canonical.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Cc: stable@vger.kernel.org # v6.3+
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/smb/client/connect.c | 14 ++++++++++++--
fs/smb/client/fs_context.c | 11 +++++++++++
2 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index d03253f8f145..ac9595504f4b 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -3444,8 +3444,18 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
* the user on mount
*/
if ((cifs_sb->ctx->wsize == 0) ||
- (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx)))
- cifs_sb->ctx->wsize = server->ops->negotiate_wsize(tcon, ctx);
+ (cifs_sb->ctx->wsize > server->ops->negotiate_wsize(tcon, ctx))) {
+ cifs_sb->ctx->wsize =
+ round_down(server->ops->negotiate_wsize(tcon, ctx), PAGE_SIZE);
+ /*
+ * in the very unlikely event that the server sent a max write size under PAGE_SIZE,
+ * (which would get rounded down to 0) then reset wsize to absolute minimum eg 4096
+ */
+ if (cifs_sb->ctx->wsize == 0) {
+ cifs_sb->ctx->wsize = PAGE_SIZE;
+ cifs_dbg(VFS, "wsize too small, reset to minimum ie PAGE_SIZE, usually 4096\n");
+ }
+ }
if ((cifs_sb->ctx->rsize == 0) ||
(cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index aec8dbd1f9db..4b2f5aa2ea0e 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1111,6 +1111,17 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case Opt_wsize:
ctx->wsize = result.uint_32;
ctx->got_wsize = true;
+ if (ctx->wsize % PAGE_SIZE != 0) {
+ ctx->wsize = round_down(ctx->wsize, PAGE_SIZE);
+ if (ctx->wsize == 0) {
+ ctx->wsize = PAGE_SIZE;
+ cifs_dbg(VFS, "wsize too small, reset to minimum %ld\n", PAGE_SIZE);
+ } else {
+ cifs_dbg(VFS,
+ "wsize rounded down to %d to multiple of PAGE_SIZE %ld\n",
+ ctx->wsize, PAGE_SIZE);
+ }
+ }
break;
case Opt_acregmax:
ctx->acregmax = HZ * result.uint_32;
From 172c0cf519fb52860157c57067f1a58cfc0aa861 Mon Sep 17 00:00:00 2001
From: Siddharth Vadapalli <s-vadapalli@ti.com>
Date: Fri, 16 Feb 2024 12:29:26 +0530
Subject: [PATCH 634/637] MAINTAINERS: Add Siddharth Vadapalli as PCI TI
DRA7XX/J721E reviewer
Since I have been contributing to the driver for a while and wish to help
with the review process, add myself as a reviewer.
Link: https://lore.kernel.org/r/20240216065926.473805-1-s-vadapalli@ti.com
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d1052fa6a69..a80c590d0035 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16832,6 +16832,7 @@ F: drivers/pci/controller/dwc/*designware*
PCI DRIVER FOR TI DRA7XX/J721E
M: Vignesh Raghavendra <vigneshr@ti.com>
+R: Siddharth Vadapalli <s-vadapalli@ti.com>
L: linux-omap@vger.kernel.org
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
From 9704669c386f9bbfef2e002e7e690c56b7dcf5de Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Sat, 17 Feb 2024 21:25:42 +0900
Subject: [PATCH 635/637] tracing/probes: Fix to search structure fields
correctly
Fix to search a field from the structure which has anonymous union
correctly.
Since the reference `type` pointer was updated in the loop, the search
loop suddenly aborted where it hits an anonymous union. Thus it can not
find the field after the anonymous union. This avoids updating the
cursor `type` pointer in the loop.
Link: https://lore.kernel.org/all/170791694361.389532.10047514554799419688.stgit@devnote2/
Fixes: 302db0f5b3d8 ("tracing/probes: Add a function to search a member of a struct/union")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
kernel/trace/trace_btf.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c
index ca224d53bfdc..5bbdbcbbde3c 100644
--- a/kernel/trace/trace_btf.c
+++ b/kernel/trace/trace_btf.c
@@ -91,8 +91,8 @@ retry:
for_each_member(i, type, member) {
if (!member->name_off) {
/* Anonymous union/struct: push it for later use */
- type = btf_type_skip_modifiers(btf, member->type, &tid);
- if (type && top < BTF_ANON_STACK_MAX) {
+ if (btf_type_skip_modifiers(btf, member->type, &tid) &&
+ top < BTF_ANON_STACK_MAX) {
anon_stack[top].tid = tid;
anon_stack[top++].offset =
cur_offset + member->offset;
From 5928d411557ec5d53832cdd39fc443704a3e5b77 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Sat, 17 Feb 2024 13:55:31 +0100
Subject: [PATCH 636/637] Documentation: Document the Linux Kernel CVE process
The Linux kernel project now has the ability to assign CVEs to fixed
issues, so document the process and how individual developers can get a
CVE if one is not automatically assigned for their fixes.
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Lee Jones <lee@kernel.org>
Link: https://lore.kernel.org/r/2024021731-essence-sadness-28fd@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/process/cve.rst | 121 ++++++++++++++++++++++++
Documentation/process/index.rst | 1 +
Documentation/process/security-bugs.rst | 5 +-
MAINTAINERS | 5 +
4 files changed, 129 insertions(+), 3 deletions(-)
create mode 100644 Documentation/process/cve.rst
diff --git a/Documentation/process/cve.rst b/Documentation/process/cve.rst
new file mode 100644
index 000000000000..5e2753eff729
--- /dev/null
+++ b/Documentation/process/cve.rst
@@ -0,0 +1,121 @@
+====
+CVEs
+====
+
+Common Vulnerabilities and Exposure (CVE®) numbers were developed as an
+unambiguous way to identify, define, and catalog publicly disclosed
+security vulnerabilities. Over time, their usefulness has declined with
+regards to the kernel project, and CVE numbers were very often assigned
+in inappropriate ways and for inappropriate reasons. Because of this,
+the kernel development community has tended to avoid them. However, the
+combination of continuing pressure to assign CVEs and other forms of
+security identifiers, and ongoing abuses by individuals and companies
+outside of the kernel community has made it clear that the kernel
+community should have control over those assignments.
+
+The Linux kernel developer team does have the ability to assign CVEs for
+potential Linux kernel security issues. This assignment is independent
+of the :doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+A list of all assigned CVEs for the Linux kernel can be found in the
+archives of the linux-cve mailing list, as seen on
+https://lore.kernel.org/linux-cve-announce/. To get notice of the
+assigned CVEs, please `subscribe
+<https://subspace.kernel.org/subscribing.html>`_ to that mailing list.
+
+Process
+=======
+
+As part of the normal stable release process, kernel changes that are
+potentially security issues are identified by the developers responsible
+for CVE number assignments and have CVE numbers automatically assigned
+to them. These assignments are published on the linux-cve-announce
+mailing list as announcements on a frequent basis.
+
+Note, due to the layer at which the Linux kernel is in a system, almost
+any bug might be exploitable to compromise the security of the kernel,
+but the possibility of exploitation is often not evident when the bug is
+fixed. Because of this, the CVE assignment team is overly cautious and
+assign CVE numbers to any bugfix that they identify. This
+explains the seemingly large number of CVEs that are issued by the Linux
+kernel team.
+
+If the CVE assignment team misses a specific fix that any user feels
+should have a CVE assigned to it, please email them at <cve@kernel.org>
+and the team there will work with you on it. Note that no potential
+security issues should be sent to this alias, it is ONLY for assignment
+of CVEs for fixes that are already in released kernel trees. If you
+feel you have found an unfixed security issue, please follow the
+:doc:`normal Linux kernel security bug reporting
+process<../process/security-bugs>`.
+
+No CVEs will be automatically assigned for unfixed security issues in
+the Linux kernel; assignment will only automatically happen after a fix
+is available and applied to a stable kernel tree, and it will be tracked
+that way by the git commit id of the original fix. If anyone wishes to
+have a CVE assigned before an issue is resolved with a commit, please
+contact the kernel CVE assignment team at <cve@kernel.org> to get an
+identifier assigned from their batch of reserved identifiers.
+
+No CVEs will be assigned for any issue found in a version of the kernel
+that is not currently being actively supported by the Stable/LTS kernel
+team. A list of the currently supported kernel branches can be found at
+https://kernel.org/releases.html
+
+Disputes of assigned CVEs
+=========================
+
+The authority to dispute or modify an assigned CVE for a specific kernel
+change lies solely with the maintainers of the relevant subsystem
+affected. This principle ensures a high degree of accuracy and
+accountability in vulnerability reporting. Only those individuals with
+deep expertise and intimate knowledge of the subsystem can effectively
+assess the validity and scope of a reported vulnerability and determine
+its appropriate CVE designation. Any attempt to modify or dispute a CVE
+outside of this designated authority could lead to confusion, inaccurate
+reporting, and ultimately, compromised systems.
+
+Invalid CVEs
+============
+
+If a security issue is found in a Linux kernel that is only supported by
+a Linux distribution due to the changes that have been made by that
+distribution, or due to the distribution supporting a kernel version
+that is no longer one of the kernel.org supported releases, then a CVE
+can not be assigned by the Linux kernel CVE team, and must be asked for
+from that Linux distribution itself.
+
+Any CVE that is assigned against the Linux kernel for an actively
+supported kernel version, by any group other than the kernel assignment
+CVE team should not be treated as a valid CVE. Please notify the
+kernel CVE assignment team at <cve@kernel.org> so that they can work to
+invalidate such entries through the CNA remediation process.
+
+Applicability of specific CVEs
+==============================
+
+As the Linux kernel can be used in many different ways, with many
+different ways of accessing it by external users, or no access at all,
+the applicability of any specific CVE is up to the user of Linux to
+determine, it is not up to the CVE assignment team. Please do not
+contact us to attempt to determine the applicability of any specific
+CVE.
+
+Also, as the source tree is so large, and any one system only uses a
+small subset of the source tree, any users of Linux should be aware that
+large numbers of assigned CVEs are not relevant for their systems.
+
+In short, we do not know your use case, and we do not know what portions
+of the kernel that you use, so there is no way for us to determine if a
+specific CVE is relevant for your system.
+
+As always, it is best to take all released kernel changes, as they are
+tested together in a unified whole by many community members, and not as
+individual cherry-picked changes. Also note that for many bugs, the
+solution to the overall problem is not found in a single change, but by
+the sum of many fixes on top of each other. Ideally CVEs will be
+assigned to all fixes for all issues, but sometimes we will fail to
+notice fixes, therefore assume that some changes without a CVE assigned
+might be relevant to take.
+
diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst
index 6cb732dfcc72..de9cbb7bd7eb 100644
--- a/Documentation/process/index.rst
+++ b/Documentation/process/index.rst
@@ -81,6 +81,7 @@ of special classes of bugs: regressions and security problems.
handling-regressions
security-bugs
+ cve
embargoed-hardware-issues
Maintainer information
diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 692a3ba56cca..56c560a00b37 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -99,9 +99,8 @@ CVE assignment
The security team does not assign CVEs, nor do we require them for
reports or fixes, as this can needlessly complicate the process and may
delay the bug handling. If a reporter wishes to have a CVE identifier
-assigned, they should find one by themselves, for example by contacting
-MITRE directly. However under no circumstances will a patch inclusion
-be delayed to wait for a CVE identifier to arrive.
+assigned for a confirmed issue, they can contact the :doc:`kernel CVE
+assignment team<../process/cve>` to obtain one.
Non-disclosure agreements
-------------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index 8999497011a2..4423fdfdd8ae 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5610,6 +5610,11 @@ S: Maintained
F: Documentation/devicetree/bindings/net/can/ctu,ctucanfd.yaml
F: drivers/net/can/ctucanfd/
+CVE ASSIGNMENT CONTACT
+M: CVE Assignment Team <cve@kernel.org>
+S: Maintained
+F: Documentation/process/cve.rst
+
CW1200 WLAN driver
S: Orphan
F: drivers/net/wireless/st/cw1200/
From b401b621758e46812da61fa58a67c3fd8d91de0d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 18 Feb 2024 12:56:25 -0800
Subject: [PATCH 637/637] Linux 6.8-rc5
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index ed80c7d98a7e..41fa8a2565f5 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*