similar to: [PATCH AUTOSEL 4.19 45/47] virtio-blk: improve virtqueue error to BLK_STS

From: Halil Pasic <pasic at linux.ibm.com> [ Upstream commit 3d973b2e9a625996ee997c7303cd793b9d197c65 ] Let's change the mapping between virtqueue_add errors to BLK_STS statuses, so that -ENOSPC, which indicates virtqueue full is still mapped to BLK_STS_DEV_RESOURCE, but -ENOMEM which indicates non-device specific resource outage is mapped to BLK_STS_RESOURCE. Signed-off-by: Halil

From: Halil Pasic <pasic at linux.ibm.com> [ Upstream commit 3d973b2e9a625996ee997c7303cd793b9d197c65 ] Let's change the mapping between virtqueue_add errors to BLK_STS statuses, so that -ENOSPC, which indicates virtqueue full is still mapped to BLK_STS_DEV_RESOURCE, but -ENOMEM which indicates non-device specific resource outage is mapped to BLK_STS_RESOURCE. Signed-off-by: Halil

Two patches are handling new edge cases introduced by doing DMA mappings (which can fail) in virtio core. I stumbled upon this while stress testing I/O for Protected Virtual Machines. I deliberately chose a tiny swiotlb size and have generated load with fio. With more than one virtio-blk disk in use I experienced hangs. The goal of this series is to fix those hangs. Halil Pasic (2):

Two patches are handling new edge cases introduced by doing DMA mappings (which can fail) in virtio core. I stumbled upon this while stress testing I/O for Protected Virtual Machines. I deliberately chose a tiny swiotlb size and have generated load with fio. With more than one virtio-blk disk in use I experienced hangs. The goal of this series is to fix those hangs. Halil Pasic (2):

Since nobody else is going to restart our hw_queue for us, the blk_mq_start_stopped_hw_queues() is in virtblk_done() is not sufficient necessarily sufficient to ensure that the queue will get started again. In case of global resource outage (-ENOMEM because mapping failure, because of swiotlb full) our virtqueue may be empty and we can get stuck with a stopped hw_queue. Let us not stop the queue

Hi Halil, When swiotlb full is hit for virtio_blk, there is below warning for once (the warning is not by this patch set). Is this expected or just false positive? [ 54.767257] virtio-pci 0000:00:04.0: swiotlb buffer is full (sz: 16 bytes), total 32768 (slots), used 258 (slots) [ 54.767260] virtio-pci 0000:00:04.0: overflow 0x0000000075770110+16 of DMA mask ffffffffffffffff bus limit 0 [

On 2020/7/30 ??4:30, Jeffle Xu wrote: > Before commit eded341c085b ("block: don't decrement nr_phys_segments for > physically contigous segments") applied, the generic block layer may not > guarantee that @req->nr_phys_segments equals the number of bios in the > request. When limits. at max_discard_segments == 1 and the IO scheduler is > set to scheduler except for

Commit 780bc7903a32 ("virtio_ring: Support DMA APIs") makes virtqueue_add() return -EIO when we fail to map our I/O buffers. This is a very realistic scenario for guests with encrypted memory, as swiotlb may run out of space, depending on it's size and the I/O load. The virtio-blk driver interprets -EIO form virtqueue_add() as an IO error, despite the fact that swiotlb full is in

On Tue, Mar 03, 2020 at 03:12:52PM +0100, Halil Pasic wrote: > On Thu, 13 Feb 2020 13:37:26 +0100 > Halil Pasic <pasic at linux.ibm.com> wrote: > > > Two patches are handling new edge cases introduced by doing DMA mappings > > (which can fail) in virtio core. > > > > I stumbled upon this while stress testing I/O for Protected Virtual > > Machines. I

On Thu, 13 Feb 2020 13:37:26 +0100 Halil Pasic <pasic at linux.ibm.com> wrote: > Two patches are handling new edge cases introduced by doing DMA mappings > (which can fail) in virtio core. > > I stumbled upon this while stress testing I/O for Protected Virtual > Machines. I deliberately chose a tiny swiotlb size and have generated > load with fio. With more than one

The following changes since commit 98d54f81e36ba3bf92172791eba5ca5bd813989b: Linux 5.6-rc4 (2020-03-01 16:38:46 -0600) are available in the Git repository at: https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git tags/for_linus for you to fetch changes up to 6ae4edab2fbf86ec92fbf0a8f0c60b857d90d50f: virtio_balloon: Adjust label in virtballoon_probe (2020-03-08 05:35:24 -0400)

From: Wanlong Gao <gaowanlong at cn.fujitsu.com> Tweak the error message "e2fsck -f" and "e2fsck -fy". Indicate the user to use the correct and/or forceall options. Signed-off-by: Wanlong Gao <gaowanlong at cn.fujitsu.com> --- daemon/ext2.c | 9 +++++++-- 1 files changed, 7 insertions(+), 2 deletions(-) diff --git a/daemon/ext2.c b/daemon/ext2.c index

Existing virtio-blk protocol doesn't have DISCARD/WRITE ZEROES command support, this will impact the performance when using SSD backend over file systems. The idea here is using 16 Bytes payload as one descriptor for DISCARD/WRITE ZEROES command, users can put several ranges into one command, for the purpose to support such feature, two feature flags

Existing virtio-blk protocol doesn't have DISCARD/WRITE ZEROES command support, this will impact the performance when using SSD backend over file systems. The idea here is using 16 Bytes payload as one descriptor for DISCARD/WRITE ZEROES command, users can put several ranges into one command, for the purpose to support such feature, two feature flags

From: Wanlong Gao <gaowanlong at cn.fujitsu.com> Tweak the error message "e2fsck -f" and "e2fsck -fy". Indicate the user to use the correct and/or forceall options. Signed-off-by: Wanlong Gao <gaowanlong at cn.fujitsu.com> --- daemon/ext2.c | 9 +++++++-- 1 files changed, 7 insertions(+), 2 deletions(-) diff --git a/daemon/ext2.c b/daemon/ext2.c index

From: Josh Poimboeuf <jpoimboe at redhat.com> [ Upstream commit 083db6764821996526970e42d09c1ab2f4155dd4 ] The __raw_callee_save_*() functions have an ELF symbol size of zero, which confuses objtool and other tools. Fixes a bunch of warnings like the following: arch/x86/xen/mmu_pv.o: warning: objtool: __raw_callee_save_xen_pte_val() is missing an ELF size annotation

On Wed, Jun 06, 2018 at 12:19:00PM +0800, Changpeng Liu wrote: > Existing virtio-blk protocol doesn't have DISCARD/WRITE ZEROES commands > support, this will impact the performance when using SSD backend over > file systems. > > Commit 88c85538 "virtio-blk: add discard and write zeroes features to > specification"(see https://github.com/oasis-tcs/virtio-spec)

On Thu, Jun 07, 2018 at 11:07:06PM +0000, Liu, Changpeng wrote: > > > > -----Original Message----- > > From: Stefan Hajnoczi [mailto:stefanha at redhat.com] > > Sent: Thursday, June 7, 2018 9:10 PM > > To: Liu, Changpeng <changpeng.liu at intel.com> > > Cc: virtualization at lists.linux-foundation.org; cavery at redhat.com; > > jasowang at

On 05/07/2017 10:44, Changpeng Liu wrote: > Currently virtio-blk driver does not provide discard feature flag, so the > filesystems which built on top of the block device will not send discard > command. This is okay for HDD backend, but it will impact the performance > for SSD backend. > > Add a feature flag VIRTIO_BLK_F_DISCARD and command VIRTIO_BLK_T_DISCARD > to extend

Switch from coherent DMA pools to those backed by dma_alloc_pages. This helps device with non-coherent DMA to avoid host accesses to uncached memory for every submission of a larger than single entry I/O. Signed-off-by: Christoph Hellwig <hch at lst.de> --- drivers/nvme/host/pci.c | 80 ++++++++++++++++++++--------------------- 1 file changed, 40 insertions(+), 40 deletions(-) diff --git