whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit 4eaaa2b99e30305f4bc677f4abfe56c1f8b39670
parent d0897090458211f9c6b2d7f5af87f4d3b0403f69
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Wed,  5 Dec 2018 13:28:01 -0800

Merge tag 'for-linus-20181205' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A bit earlier in the week as usual, but there's a fix here that should
  go in sooner rather than later.

  Under a combination of circumstance, the direct issue path in blk-mq
  could corrupt data. This wasn't easy to hit, but the ones that are
  affected by it, seem to hit it pretty easily. Full explanation in the
  patch. None of the regular filesystem and storage testing has
  triggered it, even though it's been around since 4.19-rc1.

  Outside of that, whitelist trim tweak for certain Samsung devices for
  libata"

* tag 'for-linus-20181205' of git://git.kernel.dk/linux-block:
  blk-mq: fix corruption with direct issue
  libata: whitelist all SAMSUNG MZ7KM* solid-state disks

Diffstat:
Mblock/blk-mq.c | 26+++++++++++++++++++++++++-
Mdrivers/ata/libata-core.c | 1+
2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c @@ -1715,6 +1715,15 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: + /* + * If direct dispatch fails, we cannot allow any merging on + * this IO. Drivers (like SCSI) may have set up permanent state + * for this request, like SG tables and mappings, and if we + * merge to it later on then we'll still only do IO to the + * original part. + */ + rq->cmd_flags |= REQ_NOMERGE; + blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; @@ -1727,6 +1736,18 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, return ret; } +/* + * Don't allow direct dispatch of anything but regular reads/writes, + * as some of the other commands can potentially share request space + * with data we need for the IO scheduler. If we attempt a direct dispatch + * on those and fail, we can't safely add it to the scheduler afterwards + * without potentially overwriting data that the driver has already written. + */ +static bool blk_rq_can_direct_dispatch(struct request *rq) +{ + return req_op(rq) == REQ_OP_READ || req_op(rq) == REQ_OP_WRITE; +} + static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, @@ -1748,7 +1769,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, goto insert; } - if (q->elevator && !bypass_insert) + if (!blk_rq_can_direct_dispatch(rq) || (q->elevator && !bypass_insert)) goto insert; if (!blk_mq_get_dispatch_budget(hctx)) @@ -1810,6 +1831,9 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct request *rq = list_first_entry(list, struct request, queuelist); + if (!blk_rq_can_direct_dispatch(rq)) + break; + list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq); if (ret != BLK_STS_OK) { diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c @@ -4602,6 +4602,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, /*