diff --git a/.mailmap b/.mailmap index 1ad68731fb47..ada8ad696b2e 100644 --- a/.mailmap +++ b/.mailmap @@ -17,7 +17,7 @@ Aleksey Gorelov Al Viro Al Viro Andreas Herrmann -Andrew Morton +Andrew Morton Andrew Vasquez Andy Adamson Archit Taneja @@ -102,6 +102,8 @@ Rudolf Marek Rui Saraiva Sachin P Sant Sam Ravnborg +Santosh Shilimkar +Santosh Shilimkar Sascha Hauer S.Çağlar Onur Shiraz Hashim diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 32602c667b4a..7892e6fddb66 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -38,21 +38,30 @@ int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1, return hfsplus_strcmp(&k1->cat.name, &k2->cat.name); } -void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, - u32 parent, struct qstr *str) +/* Generates key for catalog file/folders record. */ +int hfsplus_cat_build_key(struct super_block *sb, + hfsplus_btree_key *key, u32 parent, struct qstr *str) { - int len; + int len, err; key->cat.parent = cpu_to_be32(parent); - if (str) { - hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN, - str->name, str->len); - len = be16_to_cpu(key->cat.name.length); - } else { - key->cat.name.length = 0; - len = 0; - } + err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN, + str->name, str->len); + if (unlikely(err < 0)) + return err; + + len = be16_to_cpu(key->cat.name.length); key->key_len = cpu_to_be16(6 + 2 * len); + return 0; +} + +/* Generates key for catalog thread record. */ +void hfsplus_cat_build_key_with_cnid(struct super_block *sb, + hfsplus_btree_key *key, u32 parent) +{ + key->cat.parent = cpu_to_be32(parent); + key->cat.name.length = 0; + key->key_len = cpu_to_be16(6); } static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent, @@ -167,11 +176,16 @@ static int hfsplus_fill_cat_thread(struct super_block *sb, hfsplus_cat_entry *entry, int type, u32 parentid, struct qstr *str) { + int err; + entry->type = cpu_to_be16(type); entry->thread.reserved = 0; entry->thread.parentID = cpu_to_be32(parentid); - hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN, + err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN, str->name, str->len); + if (unlikely(err < 0)) + return err; + return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2; } @@ -183,7 +197,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid, int err; u16 type; - hfsplus_cat_build_key(sb, fd->search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid); err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry)); if (err) return err; @@ -250,11 +264,16 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, if (err) return err; - hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ? HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD, dir->i_ino, str); + if (unlikely(entry_size < 0)) { + err = entry_size; + goto err2; + } + err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) @@ -265,7 +284,10 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, if (err) goto err2; - hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); + err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); + if (unlikely(err)) + goto err1; + entry_size = hfsplus_cat_build_record(&entry, cnid, inode); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err != -ENOENT) { @@ -288,7 +310,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, return 0; err1: - hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); if (!hfs_brec_find(&fd, hfs_find_rec_by_key)) hfs_brec_remove(&fd); err2: @@ -313,7 +335,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) if (!str) { int len; - hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -329,7 +351,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) off + 2, len); fd.search_key->key_len = cpu_to_be16(6 + len); } else - hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); + err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str); + if (unlikely(err)) + goto out; err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) @@ -360,7 +384,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) if (err) goto out; - hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; @@ -405,7 +429,11 @@ int hfsplus_rename_cat(u32 cnid, dst_fd = src_fd; /* find the old dir entry and read the data */ - hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); + err = hfsplus_cat_build_key(sb, src_fd.search_key, + src_dir->i_ino, src_name); + if (unlikely(err)) + goto out; + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; @@ -419,7 +447,11 @@ int hfsplus_rename_cat(u32 cnid, type = be16_to_cpu(entry.type); /* create new dir entry with the data from the old entry */ - hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); + err = hfsplus_cat_build_key(sb, dst_fd.search_key, + dst_dir->i_ino, dst_name); + if (unlikely(err)) + goto out; + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) @@ -436,7 +468,11 @@ int hfsplus_rename_cat(u32 cnid, dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC; /* finally remove the old entry */ - hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); + err = hfsplus_cat_build_key(sb, src_fd.search_key, + src_dir->i_ino, src_name); + if (unlikely(err)) + goto out; + err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; @@ -449,7 +485,7 @@ int hfsplus_rename_cat(u32 cnid, src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC; /* remove old thread entry */ - hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid); err = hfs_brec_find(&src_fd, hfs_find_rec_by_key); if (err) goto out; @@ -459,9 +495,14 @@ int hfsplus_rename_cat(u32 cnid, goto out; /* create new thread entry */ - hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL); + hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, type, dst_dir->i_ino, dst_name); + if (unlikely(entry_size < 0)) { + err = entry_size; + goto out; + } + err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key); if (err != -ENOENT) { if (!err) diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 610a3260bef1..435bea231cc6 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -44,7 +44,10 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry, err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); if (err) return ERR_PTR(err); - hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name); + err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, + &dentry->d_name); + if (unlikely(err < 0)) + goto fail; again: err = hfs_brec_read(&fd, &entry, sizeof(entry)); if (err) { @@ -97,9 +100,11 @@ again: be32_to_cpu(entry.file.permissions.dev); str.len = sprintf(name, "iNode%d", linkid); str.name = name; - hfsplus_cat_build_key(sb, fd.search_key, + err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_SB(sb)->hidden_dir->i_ino, &str); + if (unlikely(err < 0)) + goto fail; goto again; } } else if (!dentry->d_fsdata) @@ -145,7 +150,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx) err = -ENOMEM; goto out; } - hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, inode->i_ino); err = hfs_brec_find(&fd, hfs_find_rec_by_key); if (err) goto out; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index eb5e059f481a..b0441d65fa54 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -443,8 +443,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2); int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2); -void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, +int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key, u32 parent, struct qstr *str); +void hfsplus_cat_build_key_with_cnid(struct super_block *sb, + hfsplus_btree_key *key, u32 parent); void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms); int hfsplus_find_cat(struct super_block *sb, u32 cnid, struct hfs_find_data *fd); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 4cf2024b87da..593af2fdcc2d 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -515,7 +515,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) err = hfs_find_init(sbi->cat_tree, &fd); if (err) goto out_put_root; - hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str); + err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str); + if (unlikely(err < 0)) + goto out_put_root; if (!hfs_brec_read(&fd, &entry, sizeof(entry))) { hfs_find_exit(&fd); if (entry.type != cpu_to_be16(HFSPLUS_FOLDER)) diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index a93bf9892256..fcae9ef1a328 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5662,7 +5662,7 @@ int ocfs2_remove_btree_range(struct inode *inode, struct ocfs2_extent_tree *et, u32 cpos, u32 phys_cpos, u32 len, int flags, struct ocfs2_cached_dealloc_ctxt *dealloc, - u64 refcount_loc) + u64 refcount_loc, bool refcount_tree_locked) { int ret, credits = 0, extra_blocks = 0; u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); @@ -5676,11 +5676,13 @@ int ocfs2_remove_btree_range(struct inode *inode, BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); - ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, - &ref_tree, NULL); - if (ret) { - mlog_errno(ret); - goto bail; + if (!refcount_tree_locked) { + ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, + &ref_tree, NULL); + if (ret) { + mlog_errno(ret); + goto bail; + } } ret = ocfs2_prepare_refcount_change_for_del(inode, @@ -7021,6 +7023,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb, u64 refcount_loc = le64_to_cpu(di->i_refcount_loc); struct ocfs2_extent_tree et; struct ocfs2_cached_dealloc_ctxt dealloc; + struct ocfs2_refcount_tree *ref_tree = NULL; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); ocfs2_init_dealloc_ctxt(&dealloc); @@ -7130,9 +7133,18 @@ start: phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno); + if ((flags & OCFS2_EXT_REFCOUNTED) && trunc_len && !ref_tree) { + status = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, + &ref_tree, NULL); + if (status) { + mlog_errno(status); + goto bail; + } + } + status = ocfs2_remove_btree_range(inode, &et, trunc_cpos, phys_cpos, trunc_len, flags, &dealloc, - refcount_loc); + refcount_loc, true); if (status < 0) { mlog_errno(status); goto bail; @@ -7147,6 +7159,8 @@ start: goto start; bail: + if (ref_tree) + ocfs2_unlock_refcount_tree(osb, ref_tree, 1); ocfs2_schedule_truncate_log_flush(osb, 1); diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index ca381c584127..fb09b97db162 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -142,7 +142,7 @@ int ocfs2_remove_btree_range(struct inode *inode, struct ocfs2_extent_tree *et, u32 cpos, u32 phys_cpos, u32 len, int flags, struct ocfs2_cached_dealloc_ctxt *dealloc, - u64 refcount_loc); + u64 refcount_loc, bool refcount_tree_locked); int ocfs2_num_free_extents(struct ocfs2_super *osb, struct ocfs2_extent_tree *et); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index d9f222987f24..46d93e941f3d 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -894,7 +894,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) } } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) { int i; @@ -915,7 +915,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) page_cache_release(wc->w_target_page); } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); +} +static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +{ + ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); } @@ -2042,11 +2046,19 @@ out_write_size: ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, wc->w_di_bh); + /* unlock pages before dealloc since it needs acquiring j_trans_barrier + * lock, or it will cause a deadlock since journal commit threads holds + * this lock and will ask for the page lock when flushing the data. + * put it here to preserve the unlock order. + */ + ocfs2_unlock_pages(wc); + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); - ocfs2_free_write_ctxt(wc); + brelse(wc->w_di_bh); + kfree(wc); return copied; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 79d56dc981bc..319e786175af 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -4479,7 +4479,7 @@ int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh) p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno); ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0, - &dealloc, 0); + &dealloc, 0, false); if (ret) { mlog_errno(ret); goto out; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 3689b3592042..a6944b25fd5b 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -695,14 +695,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm, res->inflight_assert_workers); } -static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res) -{ - spin_lock(&res->spinlock); - __dlm_lockres_grab_inflight_worker(dlm, res); - spin_unlock(&res->spinlock); -} - static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { @@ -1646,6 +1638,7 @@ send_response: } mlog(0, "%u is the owner of %.*s, cleaning everyone else\n", dlm->node_num, res->lockname.len, res->lockname.name); + spin_lock(&res->spinlock); ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx, DLM_ASSERT_MASTER_MLE_CLEANUP); if (ret < 0) { @@ -1653,7 +1646,8 @@ send_response: response = DLM_MASTER_RESP_ERROR; dlm_lockres_put(res); } else - dlm_lockres_grab_inflight_worker(dlm, res); + __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); } else { if (res) dlm_lockres_put(res); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 69fb9f75b082..3950693dd0f6 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1803,7 +1803,7 @@ static int ocfs2_remove_inode_range(struct inode *inode, ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos, phys_cpos, trunc_len, flags, - &dealloc, refcount_loc); + &dealloc, refcount_loc, false); if (ret < 0) { mlog_errno(ret); goto out; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index aa1eee06420f..d3ebf2e61853 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -12,6 +12,9 @@ #include #include #include +#ifdef CONFIG_CMA +#include +#endif #include #include #include "internal.h" @@ -137,6 +140,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE "AnonHugePages: %8lu kB\n" +#endif +#ifdef CONFIG_CMA + "CmaTotal: %8lu kB\n" + "CmaFree: %8lu kB\n" #endif , K(i.totalram), @@ -187,11 +194,15 @@ static int meminfo_proc_show(struct seq_file *m, void *v) vmi.used >> 10, vmi.largest_chunk >> 10 #ifdef CONFIG_MEMORY_FAILURE - ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) + , atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE - ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * + , K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) * HPAGE_PMD_NR) +#endif +#ifdef CONFIG_CMA + , K(totalcma_pages) + , K(global_page_state(NR_FREE_CMA_PAGES)) #endif ); diff --git a/include/linux/cma.h b/include/linux/cma.h index a93438beb33c..9384ba66e975 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -15,6 +15,7 @@ struct cma; +extern unsigned long totalcma_pages; extern phys_addr_t cma_get_base(struct cma *cma); extern unsigned long cma_get_size(struct cma *cma); diff --git a/lib/show_mem.c b/lib/show_mem.c index 5e256271b47b..7de89f4a36cf 100644 --- a/lib/show_mem.c +++ b/lib/show_mem.c @@ -8,6 +8,7 @@ #include #include #include +#include void show_mem(unsigned int filter) { @@ -38,7 +39,12 @@ void show_mem(unsigned int filter) printk("%lu pages RAM\n", total); printk("%lu pages HighMem/MovableOnly\n", highmem); +#ifdef CONFIG_CMA + printk("%lu pages reserved\n", (reserved - totalcma_pages)); + printk("%lu pages cma reserved\n", totalcma_pages); +#else printk("%lu pages reserved\n", reserved); +#endif #ifdef CONFIG_QUICKLIST printk("%lu pages in pagetable cache\n", quicklist_total_size()); diff --git a/mm/cma.c b/mm/cma.c index f8917629cbdd..a85ae28709a3 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -337,6 +337,7 @@ int __init cma_declare_contiguous(phys_addr_t base, if (ret) goto err; + totalcma_pages += (size / PAGE_SIZE); pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M, &base); return 0; diff --git a/mm/memory.c b/mm/memory.c index 6efe36a998ba..d8aebc52265f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2996,6 +2996,12 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (set_page_dirty(fault_page)) dirtied = 1; + /* + * Take a local copy of the address_space - page.mapping may be zeroed + * by truncate after unlock_page(). The address_space itself remains + * pinned by vma->vm_file's reference. We rely on unlock_page()'s + * release semantics to prevent the compiler from undoing this copying. + */ mapping = fault_page->mapping; unlock_page(fault_page); if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e58725aff7e9..f22c55947181 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -162,12 +162,6 @@ static const struct mempolicy_operations { enum mpol_rebind_step step); } mpol_ops[MPOL_MAX]; -/* Check that the nodemask contains at least one populated zone */ -static int is_valid_nodemask(const nodemask_t *nodemask) -{ - return nodes_intersects(*nodemask, node_states[N_MEMORY]); -} - static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; @@ -202,7 +196,7 @@ static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { - if (!is_valid_nodemask(nodes)) + if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; @@ -234,7 +228,7 @@ static int mpol_set_nodemask(struct mempolicy *pol, nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1); + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fa974d87f60d..7633c503a116 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -111,6 +111,7 @@ static DEFINE_SPINLOCK(managed_page_count_lock); unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; +unsigned long totalcma_pages __read_mostly; /* * When calculating the number of globally allowed dirty pages, there * is a certain number of per-zone reserves that should not be @@ -5586,7 +5587,7 @@ void __init mem_init_print_info(const char *str) pr_info("Memory: %luK/%luK available " "(%luK kernel code, %luK rwdata, %luK rodata, " - "%luK init, %luK bss, %luK reserved" + "%luK init, %luK bss, %luK reserved, %luK cma-reserved" #ifdef CONFIG_HIGHMEM ", %luK highmem" #endif @@ -5594,7 +5595,8 @@ void __init mem_init_print_info(const char *str) nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10), codesize >> 10, datasize >> 10, rosize >> 10, (init_data_size + init_code_size) >> 10, bss_size >> 10, - (physpages - totalram_pages) << (PAGE_SHIFT-10), + (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT-10), + totalcma_pages << (PAGE_SHIFT-10), #ifdef CONFIG_HIGHMEM totalhigh_pages << (PAGE_SHIFT-10), #endif diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 4d0a063145ec..b72403927aa4 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -884,19 +884,6 @@ static struct notifier_block zs_cpu_nb = { .notifier_call = zs_cpu_notifier }; -static void zs_unregister_cpu_notifier(void) -{ - int cpu; - - cpu_notifier_register_begin(); - - for_each_online_cpu(cpu) - zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); - __unregister_cpu_notifier(&zs_cpu_nb); - - cpu_notifier_register_done(); -} - static int zs_register_cpu_notifier(void) { int cpu, uninitialized_var(ret); @@ -914,6 +901,19 @@ static int zs_register_cpu_notifier(void) return notifier_to_errno(ret); } +static void zs_unregister_cpu_notifier(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) + zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); + __unregister_cpu_notifier(&zs_cpu_nb); + + cpu_notifier_register_done(); +} + static void init_zs_size_classes(void) { int nr; @@ -925,31 +925,6 @@ static void init_zs_size_classes(void) zs_size_classes = nr; } -static void __exit zs_exit(void) -{ -#ifdef CONFIG_ZPOOL - zpool_unregister_driver(&zs_zpool_driver); -#endif - zs_unregister_cpu_notifier(); -} - -static int __init zs_init(void) -{ - int ret = zs_register_cpu_notifier(); - - if (ret) { - zs_unregister_cpu_notifier(); - return ret; - } - - init_zs_size_classes(); - -#ifdef CONFIG_ZPOOL - zpool_register_driver(&zs_zpool_driver); -#endif - return 0; -} - static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage) { return pages_per_zspage * PAGE_SIZE / size; @@ -967,6 +942,202 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) return true; } +unsigned long zs_get_total_pages(struct zs_pool *pool) +{ + return atomic_long_read(&pool->pages_allocated); +} +EXPORT_SYMBOL_GPL(zs_get_total_pages); + +/** + * zs_map_object - get address of allocated object from handle. + * @pool: pool from which the object was allocated + * @handle: handle returned from zs_malloc + * + * Before using an object allocated from zs_malloc, it must be mapped using + * this function. When done with the object, it must be unmapped using + * zs_unmap_object. + * + * Only one object can be mapped per cpu at a time. There is no protection + * against nested mappings. + * + * This function returns with preemption and page faults disabled. + */ +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + struct page *pages[2]; + + BUG_ON(!handle); + + /* + * Because we use per-cpu mapping areas shared among the + * pools/users, we can't allow mapping in interrupt context + * because it can corrupt another users mappings. + */ + BUG_ON(in_interrupt()); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = &get_cpu_var(zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ + area->vm_addr = kmap_atomic(page); + return area->vm_addr + off; + } + + /* this object spans two pages */ + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + return __zs_map_object(area, pages, off, class->size); +} +EXPORT_SYMBOL_GPL(zs_map_object); + +void zs_unmap_object(struct zs_pool *pool, unsigned long handle) +{ + struct page *page; + unsigned long obj_idx, off; + + unsigned int class_idx; + enum fullness_group fg; + struct size_class *class; + struct mapping_area *area; + + BUG_ON(!handle); + + obj_handle_to_location(handle, &page, &obj_idx); + get_zspage_mapping(get_first_page(page), &class_idx, &fg); + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + + area = this_cpu_ptr(&zs_map_area); + if (off + class->size <= PAGE_SIZE) + kunmap_atomic(area->vm_addr); + else { + struct page *pages[2]; + + pages[0] = page; + pages[1] = get_next_page(page); + BUG_ON(!pages[1]); + + __zs_unmap_object(area, pages, off, class->size); + } + put_cpu_var(zs_map_area); +} +EXPORT_SYMBOL_GPL(zs_unmap_object); + +/** + * zs_malloc - Allocate block of given size from pool. + * @pool: pool to allocate from + * @size: size of block to allocate + * + * On success, handle to the allocated object is returned, + * otherwise 0. + * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. + */ +unsigned long zs_malloc(struct zs_pool *pool, size_t size) +{ + unsigned long obj; + struct link_free *link; + struct size_class *class; + void *vaddr; + + struct page *first_page, *m_page; + unsigned long m_objidx, m_offset; + + if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) + return 0; + + class = pool->size_class[get_size_class_index(size)]; + + spin_lock(&class->lock); + first_page = find_get_zspage(class); + + if (!first_page) { + spin_unlock(&class->lock); + first_page = alloc_zspage(class, pool->flags); + if (unlikely(!first_page)) + return 0; + + set_zspage_mapping(first_page, class->index, ZS_EMPTY); + atomic_long_add(class->pages_per_zspage, + &pool->pages_allocated); + spin_lock(&class->lock); + } + + obj = (unsigned long)first_page->freelist; + obj_handle_to_location(obj, &m_page, &m_objidx); + m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + + vaddr = kmap_atomic(m_page); + link = (struct link_free *)vaddr + m_offset / sizeof(*link); + first_page->freelist = link->next; + memset(link, POISON_INUSE, sizeof(*link)); + kunmap_atomic(vaddr); + + first_page->inuse++; + /* Now move the zspage to another fullness group, if required */ + fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + return obj; +} +EXPORT_SYMBOL_GPL(zs_malloc); + +void zs_free(struct zs_pool *pool, unsigned long obj) +{ + struct link_free *link; + struct page *first_page, *f_page; + unsigned long f_objidx, f_offset; + void *vaddr; + + int class_idx; + struct size_class *class; + enum fullness_group fullness; + + if (unlikely(!obj)) + return; + + obj_handle_to_location(obj, &f_page, &f_objidx); + first_page = get_first_page(f_page); + + get_zspage_mapping(first_page, &class_idx, &fullness); + class = pool->size_class[class_idx]; + f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); + + spin_lock(&class->lock); + + /* Insert this object in containing zspage's freelist */ + vaddr = kmap_atomic(f_page); + link = (struct link_free *)(vaddr + f_offset); + link->next = first_page->freelist; + kunmap_atomic(vaddr); + first_page->freelist = (void *)obj; + + first_page->inuse--; + fullness = fix_fullness_group(pool, first_page); + spin_unlock(&class->lock); + + if (fullness == ZS_EMPTY) { + atomic_long_sub(class->pages_per_zspage, + &pool->pages_allocated); + free_zspage(first_page); + } +} +EXPORT_SYMBOL_GPL(zs_free); + /** * zs_create_pool - Creates an allocation pool to work from. * @flags: allocation flags used to allocate pool metadata @@ -1075,201 +1246,30 @@ void zs_destroy_pool(struct zs_pool *pool) } EXPORT_SYMBOL_GPL(zs_destroy_pool); -/** - * zs_malloc - Allocate block of given size from pool. - * @pool: pool to allocate from - * @size: size of block to allocate - * - * On success, handle to the allocated object is returned, - * otherwise 0. - * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. - */ -unsigned long zs_malloc(struct zs_pool *pool, size_t size) +static int __init zs_init(void) { - unsigned long obj; - struct link_free *link; - struct size_class *class; - void *vaddr; + int ret = zs_register_cpu_notifier(); - struct page *first_page, *m_page; - unsigned long m_objidx, m_offset; - - if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) - return 0; - - class = pool->size_class[get_size_class_index(size)]; - - spin_lock(&class->lock); - first_page = find_get_zspage(class); - - if (!first_page) { - spin_unlock(&class->lock); - first_page = alloc_zspage(class, pool->flags); - if (unlikely(!first_page)) - return 0; - - set_zspage_mapping(first_page, class->index, ZS_EMPTY); - atomic_long_add(class->pages_per_zspage, - &pool->pages_allocated); - spin_lock(&class->lock); + if (ret) { + zs_unregister_cpu_notifier(); + return ret; } - obj = (unsigned long)first_page->freelist; - obj_handle_to_location(obj, &m_page, &m_objidx); - m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); + init_zs_size_classes(); - vaddr = kmap_atomic(m_page); - link = (struct link_free *)vaddr + m_offset / sizeof(*link); - first_page->freelist = link->next; - memset(link, POISON_INUSE, sizeof(*link)); - kunmap_atomic(vaddr); - - first_page->inuse++; - /* Now move the zspage to another fullness group, if required */ - fix_fullness_group(pool, first_page); - spin_unlock(&class->lock); - - return obj; +#ifdef CONFIG_ZPOOL + zpool_register_driver(&zs_zpool_driver); +#endif + return 0; } -EXPORT_SYMBOL_GPL(zs_malloc); -void zs_free(struct zs_pool *pool, unsigned long obj) +static void __exit zs_exit(void) { - struct link_free *link; - struct page *first_page, *f_page; - unsigned long f_objidx, f_offset; - void *vaddr; - - int class_idx; - struct size_class *class; - enum fullness_group fullness; - - if (unlikely(!obj)) - return; - - obj_handle_to_location(obj, &f_page, &f_objidx); - first_page = get_first_page(f_page); - - get_zspage_mapping(first_page, &class_idx, &fullness); - class = pool->size_class[class_idx]; - f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); - - spin_lock(&class->lock); - - /* Insert this object in containing zspage's freelist */ - vaddr = kmap_atomic(f_page); - link = (struct link_free *)(vaddr + f_offset); - link->next = first_page->freelist; - kunmap_atomic(vaddr); - first_page->freelist = (void *)obj; - - first_page->inuse--; - fullness = fix_fullness_group(pool, first_page); - spin_unlock(&class->lock); - - if (fullness == ZS_EMPTY) { - atomic_long_sub(class->pages_per_zspage, - &pool->pages_allocated); - free_zspage(first_page); - } +#ifdef CONFIG_ZPOOL + zpool_unregister_driver(&zs_zpool_driver); +#endif + zs_unregister_cpu_notifier(); } -EXPORT_SYMBOL_GPL(zs_free); - -/** - * zs_map_object - get address of allocated object from handle. - * @pool: pool from which the object was allocated - * @handle: handle returned from zs_malloc - * - * Before using an object allocated from zs_malloc, it must be mapped using - * this function. When done with the object, it must be unmapped using - * zs_unmap_object. - * - * Only one object can be mapped per cpu at a time. There is no protection - * against nested mappings. - * - * This function returns with preemption and page faults disabled. - */ -void *zs_map_object(struct zs_pool *pool, unsigned long handle, - enum zs_mapmode mm) -{ - struct page *page; - unsigned long obj_idx, off; - - unsigned int class_idx; - enum fullness_group fg; - struct size_class *class; - struct mapping_area *area; - struct page *pages[2]; - - BUG_ON(!handle); - - /* - * Because we use per-cpu mapping areas shared among the - * pools/users, we can't allow mapping in interrupt context - * because it can corrupt another users mappings. - */ - BUG_ON(in_interrupt()); - - obj_handle_to_location(handle, &page, &obj_idx); - get_zspage_mapping(get_first_page(page), &class_idx, &fg); - class = pool->size_class[class_idx]; - off = obj_idx_to_offset(page, obj_idx, class->size); - - area = &get_cpu_var(zs_map_area); - area->vm_mm = mm; - if (off + class->size <= PAGE_SIZE) { - /* this object is contained entirely within a page */ - area->vm_addr = kmap_atomic(page); - return area->vm_addr + off; - } - - /* this object spans two pages */ - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); - - return __zs_map_object(area, pages, off, class->size); -} -EXPORT_SYMBOL_GPL(zs_map_object); - -void zs_unmap_object(struct zs_pool *pool, unsigned long handle) -{ - struct page *page; - unsigned long obj_idx, off; - - unsigned int class_idx; - enum fullness_group fg; - struct size_class *class; - struct mapping_area *area; - - BUG_ON(!handle); - - obj_handle_to_location(handle, &page, &obj_idx); - get_zspage_mapping(get_first_page(page), &class_idx, &fg); - class = pool->size_class[class_idx]; - off = obj_idx_to_offset(page, obj_idx, class->size); - - area = this_cpu_ptr(&zs_map_area); - if (off + class->size <= PAGE_SIZE) - kunmap_atomic(area->vm_addr); - else { - struct page *pages[2]; - - pages[0] = page; - pages[1] = get_next_page(page); - BUG_ON(!pages[1]); - - __zs_unmap_object(area, pages, off, class->size); - } - put_cpu_var(zs_map_area); -} -EXPORT_SYMBOL_GPL(zs_unmap_object); - -unsigned long zs_get_total_pages(struct zs_pool *pool) -{ - return atomic_long_read(&pool->pages_allocated); -} -EXPORT_SYMBOL_GPL(zs_get_total_pages); module_init(zs_init); module_exit(zs_exit); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b3831f4ba845..4e511221a0c1 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,22 +1,23 @@ TARGETS = breakpoints TARGETS += cpu-hotplug TARGETS += efivarfs +TARGETS += exec +TARGETS += firmware +TARGETS += ftrace TARGETS += kcmp TARGETS += memfd TARGETS += memory-hotplug -TARGETS += mqueue TARGETS += mount +TARGETS += mqueue TARGETS += net -TARGETS += ptrace -TARGETS += timers -TARGETS += vm TARGETS += powerpc -TARGETS += user -TARGETS += sysctl -TARGETS += firmware -TARGETS += ftrace -TARGETS += exec +TARGETS += ptrace TARGETS += size +TARGETS += sysctl +TARGETS += timers +TARGETS += user +TARGETS += vm +#Please keep the TARGETS list alphabetically sorted TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug