From 868e6139c5212e7d9de8332806aacfeafb349320 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Sun, 27 Mar 2022 11:33:16 -0600 Subject: [PATCH 01/10] block: move lower_48_bits() to block The function is not generally applicable enough to be included in the core kernel header. Move it to block since it's the only subsystem using it. Suggested-by: Linus Torvalds Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220327173316.315-1-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/kernel.h | 9 --------- include/linux/t10-pi.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -63,15 +63,6 @@ } \ ) -/** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); From b97687527be85a55e12804c98745c5619eadcc32 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 12 Apr 2022 21:59:16 +0000 Subject: [PATCH 02/10] asm-generic: fix __get_unaligned_be48() on 32 bit platforms While testing the new macros for working with 48 bit containers, I faced a weird problem: 32 + 16: 0x2ef6e8da 0x79e60000 48: 0xffffe8da + 0x79e60000 All the bits starting from the 32nd were getting 1d in 9/10 cases. The debug showed: p[0]: 0x00002e0000000000 p[1]: 0x00002ef600000000 p[2]: 0xffffffffe8000000 p[3]: 0xffffffffe8da0000 p[4]: 0xffffffffe8da7900 p[5]: 0xffffffffe8da79e6 that the value becomes a garbage after the third OR, i.e. on `p[2] << 24`. When the 31st bit is 1 and there's no explicit cast to an unsigned, it's being considered as a signed int and getting sign-extended on OR, so `e8000000` becomes `ffffffffe8000000` and messes up the result. Cast the @p[2] to u64 as well to avoid this. Now: 32 + 16: 0x7ef6a490 0xddc10000 48: 0x7ef6a490 + 0xddc10000 p[0]: 0x00007e0000000000 p[1]: 0x00007ef600000000 p[2]: 0x00007ef6a4000000 p[3]: 0x00007ef6a4900000 p[4]: 0x00007ef6a490dd00 p[5]: 0x00007ef6a490ddc1 Fixes: c2ea5fcf53d5 ("asm-generic: introduce be48 unaligned accessors") Signed-off-by: Alexander Lobakin Link: https://lore.kernel.org/r/20220412215220.75677-1-alobakin@pm.me Signed-off-by: Jens Axboe --- include/asm-generic/unaligned.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 8fc637379899..df30f11b4a46 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -143,7 +143,7 @@ static inline void put_unaligned_be48(const u64 val, void *p) static inline u64 __get_unaligned_be48(const u8 *p) { - return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } From 8535c0185d14ea41f0efd6a357961b05daf6687e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 14 Apr 2022 16:44:43 +0800 Subject: [PATCH 03/10] block: fix offset/size check in bio_trim() Unit of bio->bi_iter.bi_size is bytes, but unit of offset/size is sector. Fix the above issue in checking offset/size in bio_trim(). Fixes: e83502ca5f1e ("block: fix argument type of bio_trim()") Cc: Chaitanya Kulkarni Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220414084443.1736850-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/bio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bio.c b/block/bio.c index cdd7b2915c53..4259125e16ab 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1598,7 +1598,7 @@ EXPORT_SYMBOL(bio_split); void bio_trim(struct bio *bio, sector_t offset, sector_t size) { if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || - offset + size > bio->bi_iter.bi_size)) + offset + size > bio_sectors(bio))) return; size <<= 9; From 3e3876d322aef82416ecc496a4d4a587e0fdf7a3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 13 Apr 2022 16:48:36 +0800 Subject: [PATCH 04/10] block: null_blk: end timed out poll request When poll request is timed out, it is removed from the poll list, but not completed, so the request is leaked, and never get chance to complete. Fix the issue by ending it in timeout handler. Fixes: 0a593fbbc245 ("null_blk: poll queue support") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220413084836.1571995-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/null_blk/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 05b1120e6623..c441a4972064 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1600,7 +1600,7 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) * Only fake timeouts need to execute blk_mq_complete_request() here. */ cmd->error = BLK_STS_TIMEOUT; - if (cmd->fake_timeout) + if (cmd->fake_timeout || hctx->type == HCTX_TYPE_POLL) blk_mq_complete_request(rq); return BLK_EH_DONE; } From b42b6f4485e3f0970e11f73df6202eeaf9f53a3e Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 10 Apr 2022 20:12:49 -0700 Subject: [PATCH 05/10] nvme: don't print verbose errors for internal passthrough requests Use the RQF_QUIET flag to skip the newly added verbose error reporting, and set the flag in __nvme_submit_sync_cmd, which is used for most internal passthrough requests where we do expect errors (e.g. due to probing for optional functionality). This is similar to what the SCSI verbose error logging does. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Alan Adamson Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Tested-by: Alan Adamson Tested-by: Yi Zhang Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index efb85c6d8e2d..be9fc9818e65 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -366,7 +366,7 @@ static inline void nvme_end_req(struct request *req) { blk_status_t status = nvme_error_status(nvme_req(req)->status); - if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS)) + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) nvme_log_error(req); nvme_end_req_zoned(req); nvme_trace_bio_complete(req); @@ -1015,6 +1015,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; } + req->rq_flags |= RQF_QUIET; ret = nvme_execute_rq(req, at_head); if (result && ret >= 0) *result = nvme_req(req)->result; From 00ff400e6deee00f7b15e200205b2708b63b8cf6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 Apr 2022 08:05:27 +0200 Subject: [PATCH 06/10] nvme: add a quirk to disable namespace identifiers Add a quirk to disable using and exporting namespace identifiers for controllers where they are broken beyond repair. The most directly visible problem with non-unique namespace identifiers is that they break the /dev/disk/by-id/ links, with the link for a supposedly unique identifier now pointing to one of multiple possible namespaces that share the same ID, and a somewhat random selection of which one actually shows up. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni --- drivers/nvme/host/core.c | 24 ++++++++++++++++++------ drivers/nvme/host/nvme.h | 5 +++++ 2 files changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index be9fc9818e65..e1846d04817f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1288,6 +1288,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_EUI64_LEN; memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN); return NVME_NIDT_EUI64_LEN; case NVME_NIDT_NGUID: @@ -1296,6 +1298,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_NGUID_LEN; memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN); return NVME_NIDT_NGUID_LEN; case NVME_NIDT_UUID: @@ -1304,6 +1308,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_UUID_LEN; uuid_copy(&ids->uuid, data + sizeof(*cur)); return NVME_NIDT_UUID_LEN; case NVME_NIDT_CSI: @@ -1400,12 +1406,18 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); - if (ctrl->vs >= NVME_VS(1, 2, 0) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + } return 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1393bbf82d71..a2b53ca63335 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -144,6 +144,11 @@ enum nvme_quirks { * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), + + /* + * Reports garbage in the namespace identifiers (eui64, nguid, uuid). + */ + NVME_QUIRK_BOGUS_NID = (1 << 18), }; /* From a98a945b80f8684121d477ae68ebc01da953da1f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 Apr 2022 08:05:27 +0200 Subject: [PATCH 07/10] nvme-pci: disable namespace identifiers for the MAXIO MAP1002/1202 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The MAXIO MAP1002/1202 controllers reports completely bogus Namespace identifiers that even change after suspend cycles. Disable using the Identifiers entirely. Reported-by: 金韬 Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Tested-by: 金韬 --- drivers/nvme/host/pci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d817ca17463e..c45dbe8a7dcd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3447,6 +3447,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), From 66dd346b84d79fde20832ed691a54f4881eac20d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Apr 2022 07:07:56 +0200 Subject: [PATCH 08/10] nvme-pci: disable namespace identifiers for Qemu controllers Qemu unconditionally reports a UUID, which depending on the qemu version is either all-null (which is incorrect but harmless) or contains a single bit set for all controllers. In addition it can also optionally report a eui64 which needs to be manually set. Disable namespace identifiers for Qemu controlles entirely even if in some cases they could be set correctly through manual intervention. Reported-by: Luis Chamberlain Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg --- drivers/nvme/host/pci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c45dbe8a7dcd..3aacf1c0d5a5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3409,7 +3409,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | - NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, + { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ From ccf16413e520164eb718cf8b22a30438da80ff23 Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Thu, 14 Apr 2022 15:40:56 -0700 Subject: [PATCH 09/10] block/compat_ioctl: fix range check in BLKGETSIZE kernel ulong and compat_ulong_t may not be same width. Use type directly to eliminate mismatches. This would result in truncation rather than EFBIG for 32bit mode for large disks. Reviewed-by: Bart Van Assche Signed-off-by: Khazhismel Kumykov Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220414224056.2875681-1-khazhy@google.com Signed-off-by: Jens Axboe --- block/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/ioctl.c b/block/ioctl.c index 4a86340133e4..f8703db99c73 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -629,7 +629,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - if (bdev_nr_sectors(bdev) > ~0UL) + if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev)); From 3d973a76e54c30772e72128ab0552ca75e588893 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Mar 2022 17:38:15 +0100 Subject: [PATCH 10/10] block: don't print I/O error warning for dead disks When a disk has been marked dead, don't print warnings for I/O errors as they are very much expected. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220323163815.1526998-1-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index ed3ed86f7dd2..c4370d276170 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -794,7 +794,8 @@ bool blk_update_request(struct request *req, blk_status_t error, #endif if (unlikely(error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET))) { + !(req->rq_flags & RQF_QUIET)) && + !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); }