All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Stephen Rust <srust@blockbridge.com>
Cc: Rob Townley <rob.townley@gmail.com>,
	Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
	linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
	linux-scsi@vger.kernel.org, martin.petersen@oracle.com,
	target-devel@vger.kernel.org, Doug Ledford <dledford@redhat.com>,
	Jason Gunthorpe <jgg@ziepe.ca>
Subject: Re: Data corruption in kernel 5.1+ with iSER attached ramdisk
Date: Tue, 3 Dec 2019 20:45:58 +0800	[thread overview]
Message-ID: <20191203124558.GA22805@ming.t460p> (raw)
In-Reply-To: <CAAFE1bfpUWCZrtR8v3S++0-+gi8DJ79X3e0XqDe93i8nuGTnNg@mail.gmail.com>

On Mon, Dec 02, 2019 at 10:50:32PM -0500, Stephen Rust wrote:
> Hi,
> 
> Another datapoint.
> 
> I enabled "isert_debug" tracing and re-ran the test. Here is a small
> snippet of the debug data. FWIW, the "length of 76" in the "lkey
> mismatch" is a pattern that repeats quite often during the exchange.

That is because ISER_HEADERS_LEN is 76.

From our trace, 76 is bvec->bv_offset, is it possible that IO buffer
just follows the ISER HEADER suppose that iser applies zero-copy?

BTW, you may try the attached test patch. If the issue can be fixed by
this patch, that means it is really caused by un-aligned buffer, and
the iser driver needs to be fixed.

From 0368ee8a756384116fa1d0415f51389d438a6e40 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 3 Dec 2019 20:00:53 +0800
Subject: [PATCH] brd: handle un-aligned bvec->bv_len

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 drivers/block/brd.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c548a5a6c1a0..9ea1894c820d 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -190,13 +190,15 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
  * Copy n bytes from src to the brd starting at sector. Does not sleep.
  */
 static void copy_to_brd(struct brd_device *brd, const void *src,
-			sector_t sector, size_t n)
+			sector_t sector, unsigned off_in_sec, size_t n)
 {
 	struct page *page;
 	void *dst;
 	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
 	size_t copy;
 
+	offset += off_in_sec;
+
 	copy = min_t(size_t, n, PAGE_SIZE - offset);
 	page = brd_lookup_page(brd, sector);
 	BUG_ON(!page);
@@ -207,7 +209,7 @@ static void copy_to_brd(struct brd_device *brd, const void *src,
 
 	if (copy < n) {
 		src += copy;
-		sector += copy >> SECTOR_SHIFT;
+		sector += (copy + off_in_sec) >> SECTOR_SHIFT;
 		copy = n - copy;
 		page = brd_lookup_page(brd, sector);
 		BUG_ON(!page);
@@ -222,13 +224,15 @@ static void copy_to_brd(struct brd_device *brd, const void *src,
  * Copy n bytes to dst from the brd starting at sector. Does not sleep.
  */
 static void copy_from_brd(void *dst, struct brd_device *brd,
-			sector_t sector, size_t n)
+			sector_t sector, unsigned off_in_sec, size_t n)
 {
 	struct page *page;
 	void *src;
 	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
 	size_t copy;
 
+	offset += off_in_sec;
+
 	copy = min_t(size_t, n, PAGE_SIZE - offset);
 	page = brd_lookup_page(brd, sector);
 	if (page) {
@@ -240,7 +244,7 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
 
 	if (copy < n) {
 		dst += copy;
-		sector += copy >> SECTOR_SHIFT;
+		sector += (copy + off_in_sec) >> SECTOR_SHIFT;
 		copy = n - copy;
 		page = brd_lookup_page(brd, sector);
 		if (page) {
@@ -257,7 +261,7 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
 			unsigned int len, unsigned int off, unsigned int op,
-			sector_t sector)
+			sector_t sector, unsigned int off_in_sec)
 {
 	void *mem;
 	int err = 0;
@@ -270,11 +274,11 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
 
 	mem = kmap_atomic(page);
 	if (!op_is_write(op)) {
-		copy_from_brd(mem + off, brd, sector, len);
+		copy_from_brd(mem + off, brd, sector, off_in_sec, len);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);
-		copy_to_brd(brd, mem + off, sector, len);
+		copy_to_brd(brd, mem + off, sector, off_in_sec, len);
 	}
 	kunmap_atomic(mem);
 
@@ -287,6 +291,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	struct brd_device *brd = bio->bi_disk->private_data;
 	struct bio_vec bvec;
 	sector_t sector;
+	unsigned offset_in_sec = 0;
 	struct bvec_iter iter;
 
 	sector = bio->bi_iter.bi_sector;
@@ -296,12 +301,14 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
+		unsigned int secs = len >> SECTOR_SHIFT;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-				  bio_op(bio), sector);
+				  bio_op(bio), sector, offset_in_sec);
 		if (err)
 			goto io_error;
-		sector += len >> SECTOR_SHIFT;
+		sector += secs;
+		offset_in_sec = len - (secs << SECTOR_SHIFT);
 	}
 
 	bio_endio(bio);
@@ -319,7 +326,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector, 0);
 	page_endio(page, op_is_write(op), err);
 	return err;
 }
-- 
2.20.1


Thanks,
Ming


WARNING: multiple messages have this Message-ID (diff)
From: Ming Lei <ming.lei@redhat.com>
To: Stephen Rust <srust@blockbridge.com>
Cc: Rob Townley <rob.townley@gmail.com>,
	Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
	linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
	linux-scsi@vger.kernel.org, martin.petersen@oracle.com,
	target-devel@vger.kernel.org, Doug Ledford <dledford@redhat.com>,
	Jason Gunthorpe <jgg@ziepe.ca>
Subject: Re: Data corruption in kernel 5.1+ with iSER attached ramdisk
Date: Tue, 03 Dec 2019 12:45:58 +0000	[thread overview]
Message-ID: <20191203124558.GA22805@ming.t460p> (raw)
In-Reply-To: <CAAFE1bfpUWCZrtR8v3S++0-+gi8DJ79X3e0XqDe93i8nuGTnNg@mail.gmail.com>

On Mon, Dec 02, 2019 at 10:50:32PM -0500, Stephen Rust wrote:
> Hi,
> 
> Another datapoint.
> 
> I enabled "isert_debug" tracing and re-ran the test. Here is a small
> snippet of the debug data. FWIW, the "length of 76" in the "lkey
> mismatch" is a pattern that repeats quite often during the exchange.

That is because ISER_HEADERS_LEN is 76.

From our trace, 76 is bvec->bv_offset, is it possible that IO buffer
just follows the ISER HEADER suppose that iser applies zero-copy?

BTW, you may try the attached test patch. If the issue can be fixed by
this patch, that means it is really caused by un-aligned buffer, and
the iser driver needs to be fixed.

From 0368ee8a756384116fa1d0415f51389d438a6e40 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 3 Dec 2019 20:00:53 +0800
Subject: [PATCH] brd: handle un-aligned bvec->bv_len

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 drivers/block/brd.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c548a5a6c1a0..9ea1894c820d 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -190,13 +190,15 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
  * Copy n bytes from src to the brd starting at sector. Does not sleep.
  */
 static void copy_to_brd(struct brd_device *brd, const void *src,
-			sector_t sector, size_t n)
+			sector_t sector, unsigned off_in_sec, size_t n)
 {
 	struct page *page;
 	void *dst;
 	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
 	size_t copy;
 
+	offset += off_in_sec;
+
 	copy = min_t(size_t, n, PAGE_SIZE - offset);
 	page = brd_lookup_page(brd, sector);
 	BUG_ON(!page);
@@ -207,7 +209,7 @@ static void copy_to_brd(struct brd_device *brd, const void *src,
 
 	if (copy < n) {
 		src += copy;
-		sector += copy >> SECTOR_SHIFT;
+		sector += (copy + off_in_sec) >> SECTOR_SHIFT;
 		copy = n - copy;
 		page = brd_lookup_page(brd, sector);
 		BUG_ON(!page);
@@ -222,13 +224,15 @@ static void copy_to_brd(struct brd_device *brd, const void *src,
  * Copy n bytes to dst from the brd starting at sector. Does not sleep.
  */
 static void copy_from_brd(void *dst, struct brd_device *brd,
-			sector_t sector, size_t n)
+			sector_t sector, unsigned off_in_sec, size_t n)
 {
 	struct page *page;
 	void *src;
 	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
 	size_t copy;
 
+	offset += off_in_sec;
+
 	copy = min_t(size_t, n, PAGE_SIZE - offset);
 	page = brd_lookup_page(brd, sector);
 	if (page) {
@@ -240,7 +244,7 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
 
 	if (copy < n) {
 		dst += copy;
-		sector += copy >> SECTOR_SHIFT;
+		sector += (copy + off_in_sec) >> SECTOR_SHIFT;
 		copy = n - copy;
 		page = brd_lookup_page(brd, sector);
 		if (page) {
@@ -257,7 +261,7 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
 			unsigned int len, unsigned int off, unsigned int op,
-			sector_t sector)
+			sector_t sector, unsigned int off_in_sec)
 {
 	void *mem;
 	int err = 0;
@@ -270,11 +274,11 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
 
 	mem = kmap_atomic(page);
 	if (!op_is_write(op)) {
-		copy_from_brd(mem + off, brd, sector, len);
+		copy_from_brd(mem + off, brd, sector, off_in_sec, len);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);
-		copy_to_brd(brd, mem + off, sector, len);
+		copy_to_brd(brd, mem + off, sector, off_in_sec, len);
 	}
 	kunmap_atomic(mem);
 
@@ -287,6 +291,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	struct brd_device *brd = bio->bi_disk->private_data;
 	struct bio_vec bvec;
 	sector_t sector;
+	unsigned offset_in_sec = 0;
 	struct bvec_iter iter;
 
 	sector = bio->bi_iter.bi_sector;
@@ -296,12 +301,14 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
+		unsigned int secs = len >> SECTOR_SHIFT;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-				  bio_op(bio), sector);
+				  bio_op(bio), sector, offset_in_sec);
 		if (err)
 			goto io_error;
-		sector += len >> SECTOR_SHIFT;
+		sector += secs;
+		offset_in_sec = len - (secs << SECTOR_SHIFT);
 	}
 
 	bio_endio(bio);
@@ -319,7 +326,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector, 0);
 	page_endio(page, op_is_write(op), err);
 	return err;
 }
-- 
2.20.1


Thanks,
Ming

  reply	other threads:[~2019-12-03 12:46 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CAAFE1bd9wuuobpe4VK7Ty175j7mWT+kRmHCNhVD+6R8MWEAqmw@mail.gmail.com>
2019-11-28  1:57 ` Data corruption in kernel 5.1+ with iSER attached ramdisk Ming Lei
2019-11-28  1:57   ` Ming Lei
     [not found]   ` <CA+VdTb_-CGaPjKUQteKVFSGqDz-5o-tuRRkJYqt8B9iOQypiwQ@mail.gmail.com>
2019-11-28  2:58     ` Ming Lei
2019-11-28  2:58       ` Ming Lei
     [not found]       ` <CAAFE1bfsXsKGyw7SU_z4NanT+wmtuJT=XejBYbHHMCDQwm73sw@mail.gmail.com>
2019-11-28  4:25         ` Stephen Rust
2019-11-28  4:25           ` Stephen Rust
2019-11-28  5:51           ` Rob Townley
2019-11-28  5:51             ` Rob Townley
2019-11-28  9:12         ` Ming Lei
2019-11-28  9:12           ` Ming Lei
2019-12-02 18:42           ` Stephen Rust
2019-12-02 18:42             ` Stephen Rust
2019-12-03  0:58             ` Ming Lei
2019-12-03  0:58               ` Ming Lei
2019-12-03  3:04               ` Stephen Rust
2019-12-03  3:04                 ` Stephen Rust
2019-12-03  3:14                 ` Ming Lei
2019-12-03  3:14                   ` Ming Lei
2019-12-03  3:26                   ` Stephen Rust
2019-12-03  3:26                     ` Stephen Rust
2019-12-03  3:50                     ` Stephen Rust
2019-12-03  3:50                       ` Stephen Rust
2019-12-03 12:45                       ` Ming Lei [this message]
2019-12-03 12:45                         ` Ming Lei
2019-12-03 19:56                         ` Stephen Rust
2019-12-03 19:56                           ` Stephen Rust
2019-12-04  1:05                           ` Ming Lei
2019-12-04  1:05                             ` Ming Lei
2019-12-04 17:23                             ` Stephen Rust
2019-12-04 17:23                               ` Stephen Rust
2019-12-04 23:02                               ` Ming Lei
2019-12-04 23:02                                 ` Ming Lei
2019-12-05  0:16                                 ` Bart Van Assche
2019-12-05  0:16                                   ` Bart Van Assche
2019-12-05 14:44                                   ` Stephen Rust
2019-12-05 14:44                                     ` Stephen Rust
2019-12-05  2:28                                 ` Stephen Rust
2019-12-05  2:28                                   ` Stephen Rust
2019-12-05  3:05                                   ` Ming Lei
2019-12-05  3:05                                     ` Ming Lei
2019-12-05  9:17                                 ` Sagi Grimberg
2019-12-05  9:17                                   ` Sagi Grimberg
2019-12-05 14:36                                   ` Stephen Rust
2019-12-05 14:36                                     ` Stephen Rust
     [not found]                                   ` <CAAFE1beqFBQS_zVYEXFTD2qu8PAF9hBSW4j1k9ZD6MhU_gWg5Q@mail.gmail.com>
2020-03-25  0:15                                     ` Sagi Grimberg
2020-03-25  0:15                                       ` Sagi Grimberg
2020-03-30 17:08                                       ` Stephen Rust
2020-03-30 17:08                                         ` Stephen Rust
2020-03-31  1:07                                         ` Sagi Grimberg
2020-03-31  1:07                                           ` Sagi Grimberg
2020-04-01  0:38                                         ` Sagi Grimberg
2020-04-01  0:38                                           ` Sagi Grimberg
2020-04-02 20:03                                           ` Stephen Rust
2020-04-02 20:03                                             ` Stephen Rust
2020-04-02 22:16                                             ` Sagi Grimberg
2020-04-02 22:16                                               ` Sagi Grimberg
2019-12-04  2:39                           ` Ming Lei
2019-12-04  2:39                             ` Ming Lei
2019-12-03  4:15                     ` Ming Lei
2019-12-03  4:15                       ` Ming Lei

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191203124558.GA22805@ming.t460p \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=dledford@redhat.com \
    --cc=hch@lst.de \
    --cc=jgg@ziepe.ca \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=rob.townley@gmail.com \
    --cc=srust@blockbridge.com \
    --cc=target-devel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.