qemu/block-introduce-max_hw_iov-for-use-in-sc.patch
Li Zhang 9cc71e44f4 Accepting request 924265 from home:lizhang:branches:Virtualization
- Stable fixes from upstream
* Patches added:
  block-introduce-max_hw_iov-for-use-in-sc.patch
  hmp-Unbreak-change-vnc.patch
  qemu-nbd-Change-default-cache-mode-to-wr.patch
  target-arm-Don-t-skip-M-profile-reset-en.patch
  vhost-vsock-fix-migration-issue-when-seq.patch
  virtio-mem-pci-Fix-memory-leak-when-crea.patch
  virtio-net-fix-use-after-unmap-free-for-.patch

OBS-URL: https://build.opensuse.org/request/show/924265
OBS-URL: https://build.opensuse.org/package/show/Virtualization/qemu?expand=0&rev=675
2021-10-08 16:10:31 +00:00

124 lines
5.1 KiB
Diff

From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 23 Sep 2021 09:04:36 -0400
Subject: block: introduce max_hw_iov for use in scsi-generic
Git-commit: cc071629539dc1f303175a7e2d4ab854c0a8b20f
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>
Signed-off-by: Li Zhang <li.zhang@suse.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 deb55c272ead88648c9c66ebf2e4..6320752aa2a104503300d69a4f03 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1978,6 +1978,12 @@ 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 cb9bffe0471c39e85146780b4a77..1567edb3d5cb4e85af27dc390843 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 a19942718b5d00cb1e54bc9e8228..f38e7f81d8e4c4a3fdf9a47496ab 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 665baf900e45883d462430db8475..0306ccc7b1e4827a67aaed926f93 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 f1a54db0f8ce693399d0352f69ce..c31cbd034a1b5a427c876709ac66 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -702,6 +702,13 @@ 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 9ac5f7bbd3a17d87d8a59abb3a65..5daec61f6ecce87e94825cff01af 100644
--- a/include/sysemu/block-backend.h
+++ b/include/sysemu/block-backend.h
@@ -210,6 +210,7 @@ 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);