[pve-devel] [PATCH qemu] fix #3738: cherry-pick "block: introduce max_hw_iov for use in scsi-generic"

[pve-devel] [PATCH qemu] fix #3738: cherry-pick "block: introduce max_hw_iov for use in scsi-generic"

[Fabian Ebner]

which fixes the bad commit 18473467d55a20d643b6c9b3a52de42f705b4d35
that was tracked down via bisecting, and has a Cc for qemu-stable as
well.

Issue was easy enough to reproduce with a single virtio-block disk
using a few runs of dd if=/dev/urandom of=file bs=1M count=1000

Commit cc071629539dc1f303175a7e2d4ab854c0a8b20f upstream.

Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
---
 ...e-max_hw_iov-for-use-in-scsi-generic.patch | 124 ++++++++++++++++++
 debian/patches/series                         |   1 +
 2 files changed, 125 insertions(+)
 create mode 100644 debian/patches/extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch

diff --git a/debian/patches/extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch b/debian/patches/extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch
new file mode 100644
index 0000000..06bc693
--- /dev/null
+++ b/debian/patches/extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch
@@ -0,0 +1,124 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Paolo Bonzini <pbonzini@redhat.com>
+Date: Thu, 23 Sep 2021 09:04:36 -0400
+Subject: [PATCH] block: introduce max_hw_iov for use in scsi-generic
+
+Linux limits the size of iovecs to 1024 (UIO_MAXIOV in the kernel
+sources, IOV_MAX in POSIX).  Because of this, on some host adapters
+requests with many iovecs are rejected with -EINVAL by the
+io_submit() or readv()/writev() system calls.
+
+In fact, the same limit applies to SG_IO as well.  To fix both the
+EINVAL and the possible performance issues from using fewer iovecs
+than allowed by Linux (some HBAs have max_segments as low as 128),
+introduce a separate entry in BlockLimits to hold the max_segments
+value from sysfs.  This new limit is used only for SG_IO and clamped
+to bs->bl.max_iov anyway, just like max_hw_transfer is clamped to
+bs->bl.max_transfer.
+
+Reported-by: Halil Pasic <pasic@linux.ibm.com>
+Cc: Hanna Reitz <hreitz@redhat.com>
+Cc: Kevin Wolf <kwolf@redhat.com>
+Cc: qemu-block@nongnu.org
+Cc: qemu-stable@nongnu.org
+Fixes: 18473467d5 ("file-posix: try BLKSECTGET on block devices too, do not round to power of 2", 2021-06-25)
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Message-Id: <20210923130436.1187591-1-pbonzini@redhat.com>
+Signed-off-by: Kevin Wolf <kwolf@redhat.com>
+---
+ block/block-backend.c          | 6 ++++++
+ block/file-posix.c             | 2 +-
+ block/io.c                     | 1 +
+ hw/scsi/scsi-generic.c         | 2 +-
+ include/block/block_int.h      | 7 +++++++
+ include/sysemu/block-backend.h | 1 +
+ 6 files changed, 17 insertions(+), 2 deletions(-)
+
+diff --git a/block/block-backend.c b/block/block-backend.c
+index 6140d133e2..ba2b5ebb10 100644
+--- a/block/block-backend.c
++++ b/block/block-backend.c
+@@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk)
+     return ROUND_DOWN(max, blk_get_request_alignment(blk));
+ }
+ 
++int blk_get_max_hw_iov(BlockBackend *blk)
++{
++    return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov,
++                        blk->root->bs->bl.max_iov);
++}
++
+ int blk_get_max_iov(BlockBackend *blk)
+ {
+     return blk->root->bs->bl.max_iov;
+diff --git a/block/file-posix.c b/block/file-posix.c
+index c62e42743d..53be0bdc1b 100644
+--- a/block/file-posix.c
++++ b/block/file-posix.c
+@@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
+ 
+         ret = hdev_get_max_segments(s->fd, &st);
+         if (ret > 0) {
+-            bs->bl.max_iov = ret;
++            bs->bl.max_hw_iov = ret;
+         }
+     }
+ }
+diff --git a/block/io.c b/block/io.c
+index 18d345a87a..bb0a254def 100644
+--- a/block/io.c
++++ b/block/io.c
+@@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
+     dst->min_mem_alignment = MAX(dst->min_mem_alignment,
+                                  src->min_mem_alignment);
+     dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov);
++    dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov);
+ }
+ 
+ typedef struct BdrvRefreshLimitsState {
+diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c
+index 665baf900e..0306ccc7b1 100644
+--- a/hw/scsi/scsi-generic.c
++++ b/hw/scsi/scsi-generic.c
+@@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len)
+         page = r->req.cmd.buf[2];
+         if (page == 0xb0) {
+             uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk);
+-            uint32_t max_iov = blk_get_max_iov(s->conf.blk);
++            uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk);
+ 
+             assert(max_transfer);
+             max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size)
+diff --git a/include/block/block_int.h b/include/block/block_int.h
+index ffe86068d4..f4c75e8ba9 100644
+--- a/include/block/block_int.h
++++ b/include/block/block_int.h
+@@ -718,6 +718,13 @@ typedef struct BlockLimits {
+      */
+     uint64_t max_hw_transfer;
+ 
++    /* Maximal number of scatter/gather elements allowed by the hardware.
++     * Applies whenever transfers to the device bypass the kernel I/O
++     * scheduler, for example with SG_IO.  If larger than max_iov
++     * or if zero, blk_get_max_hw_iov will fall back to max_iov.
++     */
++    int max_hw_iov;
++
+     /* memory alignment, in bytes so that no bounce buffer is needed */
+     size_t min_mem_alignment;
+ 
+diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h
+index 29d4fdbf63..82bae55161 100644
+--- a/include/sysemu/block-backend.h
++++ b/include/sysemu/block-backend.h
+@@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk);
+ uint32_t blk_get_max_transfer(BlockBackend *blk);
+ uint64_t blk_get_max_hw_transfer(BlockBackend *blk);
+ int blk_get_max_iov(BlockBackend *blk);
++int blk_get_max_hw_iov(BlockBackend *blk);
+ void blk_set_guest_block_size(BlockBackend *blk, int align);
+ void *blk_try_blockalign(BlockBackend *blk, size_t size);
+ void *blk_blockalign(BlockBackend *blk, size_t size);
+-- 
+2.30.2
+
diff --git a/debian/patches/series b/debian/patches/series
index 92bcf10..d953c4f 100644
--- a/debian/patches/series
+++ b/debian/patches/series
@@ -5,6 +5,7 @@ extra/0004-monitor-refactor-set-expire_password-and-allow-VNC-d.patch
 extra/0005-monitor-hmp-correctly-invert-password-argument-detec.patch
 extra/0006-qxl-fix-pre-save-logic.patch
 extra/0007-block-mirror-fix-NULL-pointer-dereference-in-mirror_.patch
+extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch
 bitmap-mirror/0001-drive-mirror-add-support-for-sync-bitmap-mode-never.patch
 bitmap-mirror/0002-drive-mirror-add-support-for-conditional-and-always-.patch
 bitmap-mirror/0003-mirror-add-check-for-bitmap-mode-without-bitmap.patch
-- 
2.30.2

[pve-devel] applied: [PATCH qemu] fix #3738: cherry-pick "block: introduce max_hw_iov for use in scsi-generic"

[Thomas Lamprecht]

On 01.12.21 14:10, Fabian Ebner wrote:
> which fixes the bad commit 18473467d55a20d643b6c9b3a52de42f705b4d35
> that was tracked down via bisecting, and has a Cc for qemu-stable as
> well.
> 
> Issue was easy enough to reproduce with a single virtio-block disk
> using a few runs of dd if=/dev/urandom of=file bs=1M count=1000
> 
> Commit cc071629539dc1f303175a7e2d4ab854c0a8b20f upstream.
> 
> Signed-off-by: Fabian Ebner <f.ebner@proxmox.com>
> ---
>  ...e-max_hw_iov-for-use-in-scsi-generic.patch | 124 ++++++++++++++++++
>  debian/patches/series                         |   1 +
>  2 files changed, 125 insertions(+)
>  create mode 100644 debian/patches/extra/0008-block-introduce-max_hw_iov-for-use-in-scsi-generic.patch
> 
>

applied, thanks!