Update Jens' entry to match the mail address of his other entries.
Acked-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Keith Busch <kbusch@kernel.org>
A file system sets STATX_DIOALIGN with zeroed alignments when the file
can't be used for direct I/O. The zero underflowed to UINT_MAX and
triggered a queue limits validation warning. Fall back to the block
device's limits when dio_mem_align isn't reported.
A file system with a block size larger than PAGE_SIZE may also report a
memory alignment that can't be expressed as a queue limit. File systems
fall back to buffered I/O for requests that don't meet their alignment,
so cap the reported limit to the largest possible value.
Fixes: 6c8dec275c ("loop: set dma_alignment from the backing file for direct I/O")
Fixes: c5059c1af2 ("zloop: set dma_alignment from the backing files for direct I/O")
Reported-by: syzbot+ac00e7bf7ac8c91af921@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=ac00e7bf7ac8c91af921
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260810164218.3721636-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The cloned bio needs to inherit the accumulated gaps between vectors so
that we can know if this bio can subscribe to the iova coalescing
optimization.
When cloning for a split, the gap only applies to the front bio since
that's as far as has been processed. The remaining bio can reset its
gaps to 0 since it advanced past the checked vectors, and will start its
accounting from there on the next split check.
Fixes: 2f6b2565d4 ("block: accumulate memory segment gaps per bio")
Reported-by: Eric Auger <eauger@redhat.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260819154937.3903312-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The bio-based drivers don't necessarily check the alignment split, and
stacking block drivers don't always handle a misalignment detected after
submitting the bio. Validate user vectors against the device's
dma_alignment as the bio is built from the iov_iter, rejecting
misaligned early with -EINVAL.
Cc: stable@vger.kernel.org
Fixes: 5ff3f74e14 ("block: simplify direct io validity check")
Fixes: 7eac331869 ("iomap: simplify direct io validity check")
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260720201057.1862857-6-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Direct I/O request's use pages handed to the backing files unchanged, so
the backing's DMA alignment requirement applies. Track dio_mem_align and
advertise it as the device's dma_alignment so we communicate proper
limits and misaligned I/O is rejected here instead of reaching the
backend.
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260720201057.1862857-5-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Direct I/O user pages are forwarded to the backing file unchanged, so
the backing's DMA alignment requirement applies to them. Track the
backing's dio_mem_align and advertise it as the loop device's
dma_alignment so we advertise proper limits and misaligned I/O is
rejected here instead of being dispatched to the backend.
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260720201057.1862857-4-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For DM_IO_BIO requests, do_region() built each destination bio by walking
the source bio's biovec and re-adding the pages one at a time, tracking
the remaining transfer in sectors. The vector lengths are byte granular
and need not be sector aligned (e.g. a misaligned O_DIRECT buffer split
across pages), so the sector-based accounting could lose a sub-sector
fragment: to_sector() truncated the remainder and the outer loop spun
forever submitting empty bios, hanging the I/O.
There is no need to rebuild the biovec at all. The destination reads into
(or writes from) exactly the same pages as the source bio, so the bio can
simply clone the source's biovec with bio_alloc_clone() and remap it to
the target device. The clone inherits the source's iterator and alignment,
and the block layer splits it to the target's limits on submission, so the
whole region maps to a single cloned bio with no manual page copying or
sector accounting.
This removes the per-page copy path (and its open-coded bvec dpages
helpers) for bio-backed I/O and fixes the hang on misaligned direct I/O to
a dm-mirror device. Page-list, vma and kmem sources keep the existing copy
path.
Fixes: 7eac331869 ("iomap: simplify direct io validity check")
Fixes: 5ff3f74e14 ("block: simplify direct io validity check")
Cc: stable@vger.kernel.org
Reported-by: Dr. David Alan Gilbert <linux@treblig.org>
Reported-by: Vjaceslavs Klimovs <vklimovs@gmail.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Offsets and lengths need to be validated against the dma alignment. This
check was skipped for sufficiently a small bio with a single bvec, which
may allow an invalid request dispatched to the driver. Force the
validation for an unaligned bvec by forcing the bio split path that
handles this condition.
Fixes: 7eac331869 ("iomap: simplify direct io validity check")
Fixes: 5ff3f74e14 ("block: simplify direct io validity check")
Reported-by: Carlos Maiolino <cem@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260612223205.465913-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A user can enable io accounting for passthrough requests, so export the
helper that checks if the request should be tracked. This will enable
stacking drivers to to report iostats for passthrough workloads. Since
the stacking request_queue may not be the one providing the request, the
API has to add a parameter for the caller to specify which one to check.
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260528010041.1533124-2-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A previous commit removed an optimization out of caution for a scenario
that turns out not to be real: all the "queue_exit" goto's are safe to
reinsert the request into the cached_rq's plug list as they are either
from a non-blocking path, or a successful merge that already holds the
queue reference. This optimization is most needed for small sequential
workloads that successfully merge into larger requests.
Fixes: dc278e9bf2 ("blk-mq: pop cached request if it is usable")
Suggested-by: Ming Lei <tom.leiming@gmail.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://patch.msgid.link/20260526153531.2365935-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When submitting a bio to blk-mq, if the task should sleep after peeking
a cached request, but before it pops it, the plug flushes and calls
blk_mq_free_plug_rqs, freeing the cached_rqs. This creates a
use-after-free bug. Fix this by popping the cached request before any
possible blocking calls if it is suitable for use.
Popping this request first holds a queue reference, so avoid any
serialization races with queue freezes and can safely proceed with
dispatching that request to the driver. This potentially increases a
timing window from when a driver wants to freeze its queue to when
requests stop being dispatched. That scenario is off the fast path
though, and drivers need to appropriately handle requests during a
freeze request anyway.
The downside is the popped element needs to be individually freed when
we performed a bio plug merge. The cached request would have had to be
freed later anyway, but this patch does it inline with building the plug
list instead of after flushing it.
Fixes: b0077e269f ("blk-mq: make sure active queue usage is held for bio_integrity_prep()")
Fixes: 7b4f36cd22 ("block: ensure we hold a queue reference when using queue limits")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260521190253.242065-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We're leaking the initial DMA mapping during iteration if we fail to
allocate the tracking descriptor for both PRP and SGL. Unmap the
iterator directly; we can't use the existing unmap helper because it
depends on the tracking descriptor being successfully allocated, so a
new one for an in-use iterator is provided.
The mappings were also leaking when the driver detects an invalid
bio_vec when mapping PRPs, so fix that too.
Fixes: b8b7570a7e ("nvme-pci: fix dma unmapping when using PRPs and not using the IOVA mapping")
Fixes: 7ce3c1dd78 ("nvme-pci: convert the data mapping to blk_rq_dma_map")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
We don't unmap P2P memory, so we don't need to track it. The dma_vec
allocation was getting leaked on the completion.
Fixes: b8b7570a7e ("nvme-pci: fix dma unmapping when using PRPs and not using the IOVA mapping")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
The local bio is always NULL, so we'd leak the bio if the integrity
mapping failed. Just get it directly from the request.
Fixes: d0d1d52231 ("blk-map: provide the bdev to bio if one exists")
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
The warning is a bit alarming, and it only prints for the very first
non-sgl capable device that receives a passthrough command. Just log an
informational message on initial discovery for every device.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
BLK_STS_INVAL indicates the IO request itself was invalid, not that the
device has failed. When raid1 treats this as a device error, it retries
on alternate mirrors which fail the same way, eventually exceeding the
read error threshold and removing the device from the array.
This happens when stacking configurations bypass bio_split_to_limits()
in the IO path: dm-raid calls md_handle_request() directly without going
through md_submit_bio(), skipping the alignment validation that would
otherwise reject invalid bios early. The invalid bio reaches the
lower block layers, which fail the bio with BLK_STS_INVAL, and raid1
wrongly interprets this as a device failure.
Add BLK_STS_INVAL to raid1_should_handle_error() so that invalid IO
errors are propagated back to the caller rather than triggering device
removal. This is consistent with the previous kernel behavior when
alignment checks were done earlier in the direct-io path.
Fixes: 5ff3f74e14 ("block: simplify direct io validity check")
Reported-by: Tomáš Trnka <trnka@scm.com>
Closes: https://lore.kernel.org/linux-block/2982107.4sosBPzcNG@electra/
Signed-off-by: Keith Busch <kbusch@kernel.org>
Tested-by: Tomáš Trnka <trnka@scm.com>
Link: https://lore.kernel.org/r/20260416140345.3872265-1-kbusch@meta.com
Signed-off-by: Yu Kuai <yukuai@fnnas.com>
If a bus has hotplug slots that implement the slot's reset_slot callback,
it is not safe to do the non-slot specific bus reset, so don't fallback to
it. If a slot reset does fail, the subsequent bus reset will attempt a 2nd
link reset on top of previous and fail to handle the hotplug events.
Fixes: 8238cb69c0 ("PCI: Make reset_subordinate hotplug safe")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260421150644.3543733-1-kbusch@meta.com
We can batch admin commands submitted through io_uring_cmd passthrough,
which means bd->last may be false and skips the doorbell write to
aggregate multiple commands per write. If a subsequent command can't be
dispatched for whatever reason, we have to provide the blk-mq ops'
commit_rqs callback in order to ensure we properly update the doorbell.
Fixes: 58e5bdeb9c ("nvme: enable uring-passthrough for admin commands")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
The command was never dispatched for the driver's "host path error", so
the command was never actually initialized and there's no corresponding
submit trace for the completion.
Reported-by: Minsik Jeon <hmi.jeon@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
There are multiple device mappers that set up their stacking limits
exactly the same for the logical, physical and minimum IO queue limits.
Provide a helper for it.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Don't depend on the defaults to be what is desired if the integrity
device was set up with 512b sector size. Always set the queue limits to
be at least what the device mapper wants.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
A user can integritysetup a device with a backing device using a 4k
logical block size, but request the dm device use 1k or 2k. This
mismatch creates an inconsistency such that the dm device would report
limits for IO that it can't actually execute. Fix this by using the
backing device's limits if they are larger.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
A bio segment may have partial interval block data with the rest
continuing into the next segments because direct-io data payloads only
need to align in memory to the device's DMA limits.
At the same time, the protection information may also be split in
multiple segments. The most likely way that may happen is if two
requests merge, or if we're directly using the io_uring user metadata.
The generate/verify, however, only ever accessed the first bip_vec.
Further, it may be possible to unalign the protection fields from the
user space buffer, or if there are odd additional opaque bytes in front
or in back of the protection information metadata region.
Change up the iteration to allow spanning multiple segments. This patch
is mostly a re-write of the protection information handling to allow any
arbitrary alignments, so it's probably easier to review the end result
rather than the diff.
Many controllers are not able to handle interval data composed of
multiple segments when PI is used, so this patch introduces a new
integrity limit that a low level driver can set to notify that it is
capable, default to false. The nvme driver is the first one to enable it
in this patch. Everyone else will force DMA alignment to the logical
block size as before to ensure interval data is always aligned within a
single segment.
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://patch.msgid.link/20260313144701.1221652-2-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use the slot reset method when resetting the bridge if the bus contains
hot plug slots. This fixes spurious hot plug events that are triggered
by the secondary bus reset that bypasses the slot's detection disabling.
Resetting a bridge's subordinate bus can be done like this:
# echo 1 > /sys/bus/pci/devices/0000:50:01.0/reset_subordinate
Prior to this patch, an example kernel message may show something like:
pcieport 0000:50:01.0: pciehp: Slot(40): Link Down
With this change, the pciehp driver ignores the link event during the
reset, so may show this message instead:
pcieport 0000:50:01.0: pciehp: Slot(40): Link Down/Up ignored
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260217160836.2709885-4-kbusch@meta.com
A PCIe hotplug slot applies to the entire secondary bus. Thus, pciehp only
allocates a single hotplug_slot for the bridge to that bus. The existing
PCI slot, though, would only match to functions on device 0, meaning any
devices beyond that, e.g., ARI functions, are not matched to any slot even
though they share it. A slot reset will break all the missing devices
because the handling skips them.
For example, ARI devices with more than 8 functions fail because their
state is not properly handled, nor is the attached driver notified of the
reset. In the best case, the device will appear unresponsive to the driver,
resulting in unexpected errors. A worse possibility may panic the kernel if
in-flight transactions trigger hardware reported errors like this real
observation:
vfio-pci 0000:01:00.0: resetting
vfio-pci 0000:01:00.0: reset done
{1}[Hardware Error]: Error 1, type: fatal
{1}[Hardware Error]: section_type: PCIe error
{1}[Hardware Error]: port_type: 0, PCIe end point
{1}[Hardware Error]: version: 0.2
{1}[Hardware Error]: command: 0x0140, status: 0x0010
{1}[Hardware Error]: device_id: 0000:01:01.0
{1}[Hardware Error]: slot: 0
{1}[Hardware Error]: secondary_bus: 0x00
{1}[Hardware Error]: vendor_id: 0x1d9b, device_id: 0x0207
{1}[Hardware Error]: class_code: 020000
{1}[Hardware Error]: bridge: secondary_status: 0x0000, control: 0x0000
{1}[Hardware Error]: aer_cor_status: 0x00008000, aer_cor_mask: 0x00002000
{1}[Hardware Error]: aer_uncor_status: 0x00010000, aer_uncor_mask: 0x00100000
{1}[Hardware Error]: aer_uncor_severity: 0x006f6030
{1}[Hardware Error]: TLP Header: 0a412800 00192080 60000004 00000004
GHES: Fatal hardware error but panic disabled
Kernel panic - not syncing: GHES: Fatal hardware error
Allow a slot to be created to claim all devices on a bus, not just a
matching device. This is done by introducing a sentinel value, named
PCI_SLOT_ALL_DEVICES, which then has the PCI slot match to any device on
the bus. This fixes slot resets for pciehp.
Since 0xff already has special meaning, the chosen value for this new
feature is 0xfe. This will not clash with any actual slot number since they
are limited to 5 bits.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260217160836.2709885-3-kbusch@meta.com
Make the code a little easier to navigate with more descriptive function
names. The two renamed functions here "try" to do to a reset, so make that
clear in the name to distinguish them from other similarly named functions:
__pci_reset_bus() -> pci_try_reset_bus()
__pci_reset_slot() -> pci_try_reset_slot()
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260217160836.2709885-2-kbusch@meta.com
Commit e7e222ad73 ("cxl: Move devm_cxl_add_nvdimm_bridge() to
cxl_pmem.ko") moves devm_cxl_add_nvdimm_bridge() into the cxl_pmem file,
which has independent config compile options for built-in or module. The
call from cxl_acpi_probe() is guarded by IS_ENABLED(CONFIG_CXL_PMEM),
which evaluates to true for both =y and =m.
When CONFIG_CXL_PMEM=m, a built-in cxl_acpi attempts to reference a
symbol exported by a module, which fails to link. CXL_PMEM cannot simply
be promoted to =y in this configuration because it depends on LIBNVDIMM,
which may itself be =m.
Add a Kconfig dependency to prevent CXL_ACPI from being built-in when
CXL_PMEM is a module. This contrains CXL_ACPI to =m when CXL_PMEM=m,
while still allowing CXL_ACPI to be freely configured when CXL_PMEM is
either built-in or disabled.
[ dj: Fix up commit reference formatting. ]
Fixes: e7e222ad73 ("cxl: Move devm_cxl_add_nvdimm_bridge() to cxl_pmem.ko")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260305204057.1516948-1-kbusch@meta.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
We need to fall back to the synchronous removal if we can't get a
reference on the module needed for the deferred removal.
Fixes: 62188639ec ("nvme-multipath: introduce delayed removal of the multipath head node")
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
The block layer allocates the set's maps once. We can't add special
purpose queues at runtime if they weren't allocated at initialization
time.
Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
If the user reduces the special queue count at runtime and resets the
controller, we need to reduce the number of queues and interrupts
requested accordingly rather than start with the pre-allocated queue
count.
Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
A user can change the polled queue count at run time. There's a brief
window during a reset where a hipri task may try to poll that queue
before the block layer has updated the queue maps, which would race with
the now interrupt driven queue and may cause double completions.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Like pci_bus_lock(), pci_slot_lock() needs to lock the bridge device to
prevent warnings like:
pcieport 0000:e2:05.0: unlocked secondary bus reset via: pciehp_reset_slot+0x55/0xa0
Take and release the lock for the bridge providing the slot for the
lock/trylock and unlock routines.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260130165953.751063-3-kbusch@meta.com
The initial state of dma_needs_unmap may be false, but change to true
while mapping the data iterator. Enabling swiotlb is one such case that
can change the result. The nvme driver needs to save the mapped dma
vectors to be unmapped later, so allocate as needed during iteration
rather than assume it was always allocated at the beginning. This fixes
a NULL dereference from accessing an uninitialized dma_vecs when the
device dma unmapping requirements change mid-iteration.
Fixes: b8b7570a7e ("nvme-pci: fix dma unmapping when using PRPs and not using the IOVA mapping")
Link: https://lore.kernel.org/linux-nvme/20260202125738.1194899-1-pradeep.pragallapati@oss.qualcomm.com/
Reported-by: Pradeep P V K <pradeep.pragallapati@oss.qualcomm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
There are no more callers of this function after commit f6b2d8b134
("btrfs: track the next file offset in struct btrfs_bio_ctrl"), so
remove the function.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ensure the dma state is initialized when we're not using the contiguous
iova, otherwise the caller may be using a stale state from a previous
request that could use the coalesed iova allocation.
Fixes: 2f6b2565d4 ("block: accumulate memory segment gaps per bio")
Reported-by: Sebastian Ott <sebott@redhat.com>
Tested-by: Sebastian Ott <sebott@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If the next discard range is contiguous with the current range being
considered, it's cheaper to expand the current range than to append an
additional bio.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Fix up the divisor calculating the number of zone sectors being read and
handle a read that straddles the zone write pointer. The length is
rounded up a sector boundary, so be sure to truncate any excess bytes
off to avoid copying past the data segment.
Fixes: 3451cf34f5 ("null_blk: allow byte aligned memory offsets")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Tested-by: Bart van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The data segment gaps the block layer tracks doesn't apply to bio's that
don't have data. Skip calculating this to fix a NULL pointer access.
Fixes: 2f6b2565d4 ("block: accumulate memory segment gaps per bio")
Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Yu Kuai <yukuai@fnnas.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The nvme virtual boundary is only required for the PRP format. Devices
that can use SGL for DMA don't need it for IO queues. Drop reporting it
for such devices; rdma fabrics controllers will continue to use the
limit as they currently don't report any boundary requirements, but tcp
and fc never needed it in the first place so they get to report no
virtual boundary.
Applications may continue to align to the same virtual boundaries for
optimization purposes if they want, and the driver will continue to
decide whether to use the PRP format the same as before if the IO allows
it.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The blk-mq dma iterator has an optimization for requests that align to
the device's iommu merge boundary. This boundary may be larger than the
device's virtual boundary, but the code had been depending on that queue
limit to know ahead of time if the request is guaranteed to align to
that optimization.
Rather than rely on that queue limit, which many devices may not report,
save the lowest set bit of any boundary gap between each segment in the
bio while checking the segments. The request stores the value for
merging and quickly checking per io if the request can use iova
optimizations.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The dma_map_bvec helper doesn't work for p2p data, so use the same
blk_map_iter method that sgl uses for this memory type.
Reported-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
The sq_head indicates the index directly in the submission queue when
the IORING_SETUP_NO_SQARRAY option is used, so use that instead of
skipping showing the entries.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Despite its name, the block layer is fine with segments smaller that the
"min_segment_size" limit. The value is an optimization limit indicating
the largest segment that can be used without considering boundary
limits. Smaller segments can take a fast path, so give it a name that
reflects that: max_fast_segment_size.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Normal rings support 64b SQEs for posting submissions, while certain
features require the ring to be configured with IORING_SETUP_SQE128, as
they need to convey more information per submission. This, in turn,
makes ALL the SQEs be 128b in size. This is somewhat wasteful and
inefficient, particularly when only certain SQEs need to be of the
bigger variant.
This adds support for setting up a ring with mixed SQE sizes, using
IORING_SETUP_SQE_MIXED. When setup in this mode, SQEs posted to the ring
may be either 64b or 128b in size. If a SQE is 128b in size, then opcode
will be set to a variante to indicate that this is the case. Any other
non-128b opcode will assume the SQ's default size.
SQEs on these types of mixed rings may also utilize NOP with skip
success set. This can happen if the ring is one (small) SQE entry away
from wrapping, and an attempt is made to get a 128b SQE. As SQEs must be
contiguous in the SQ ring, a 128b SQE cannot wrap the ring. For this
case, a single NOP SQE should be inserted with the SKIP_SUCCESS flag
set. The kernel will process this as a normal NOP and without posting a
CQE.
Signed-off-by: Keith Busch <kbusch@kernel.org>
[axboe: {} style fix and assign sqe before opcode read]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The nvme uring_cmd only uses 32b CQEs. If the ring uses a mixed CQ, then
we need to make sure we flag the completion as a 32b CQE.
On the other hand, if nvme uring_cmd was using a dedicated 32b CQE, the
posting was missing the extra memcpy because it only applied to bit CQEs
on a mixed CQ.
Fixes: e26dca67fd ("io_uring: add support for IORING_SETUP_CQE_MIXED")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can now safely provide a block device when extracting user pages for
driver and user passthrough commands. Set the bdev so the caller doesn't
have to do that later. This has an additional benefit of being able to
extract P2P pages in the passthrough path.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We only need to consider data and metadata dma mapping types separately.
The request and bio integrity payload have enough flag bits to
internally track the mapping type for each. Use these so the caller
doesn't need to track them, and provide separete request and integrity
helpers to the common code. This will make it easier to scale new
mappings, like the proposed MMIO attribute, without burdening the caller
to track such things.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Set the extraction flags to allow p2p pages for the metadata buffer if
the block device allows it. Similar to data payloads, ensure the bio
does not use merging if we see a p2p page.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We're checking length and addresses against the same alignment value, so
use the more simple iterator check.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The block layer checks all the segments for validity later, so no need
for an early check. Just reduce it to a simple position and total length
check, and defer the more invasive segment checks to the block layer.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The block layer checks all the segments for validity later, so no need
for an early check. Just reduce it to a simple position and total length
check, and defer the more invasive segment checks to the block layer.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of ensuring each vector is block size aligned while constructing
the bio, just ensure the entire size is aligned after it's built. This
makes getting bio pages more flexible to accepting device valid io
vectors that would otherwise get rejected by alignment checks.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The block layer tries to align bio vectors to the block device's logical
block size. Some cases don't have a block device, or we may need to
align to something larger, which we can't derive it from the queue
limits. Have the caller specify what they want, or allow any length
alignment if nothing was specified. Since the most common use case
relies on the block device's limits, a helper function is provided.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We're already iterating every segment, so check these for a valid IO
lengths at the same time. Individual segment lengths will not be checked
on passthrough commands. The read/write command segments must be sized
to the dma alignment.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Modify blk_rq_map_integrity_sg to use the blk-mq mapping iterator. This
produces more efficient code and converges the integrity mapping
implementations to reduce future maintenance burdens.
The function implementation moves from blk-integrity.c to blk-mq-dma.c
in order to use the types and functions private to that file.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250813153153.3260897-8-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Similar to regular data, introduce more efficient integrity mapping
helpers that does away with the scatterlist structure. This uses the
block mapping iterator to add IOVA segments if IOMMU is enabled, or maps
directly if not. This also supports P2P segements if integrity data ever
wants to allocate that type of memory.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20250813153153.3260897-7-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A large DMA mapping request can loop through dma address pinning for
many pages. In cases where THP can not be used, the repeated vmf_insert_pfn can
be costly, so let the task reschedule as need to prevent CPU stalls. Failure to
do so has potential harmful side effects, like increased memory pressure
as unrelated rcu tasks are unable to make their reclaim callbacks and
result in OOM conditions.
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: 36-....: (20999 ticks this GP) idle=b01c/1/0x4000000000000000 softirq=35839/35839 fqs=3538
rcu: hardirqs softirqs csw/system
rcu: number: 0 107 0
rcu: cputime: 50 0 10446 ==> 10556(ms)
rcu: (t=21075 jiffies g=377761 q=204059 ncpus=384)
...
<TASK>
? asm_sysvec_apic_timer_interrupt+0x16/0x20
? walk_system_ram_range+0x63/0x120
? walk_system_ram_range+0x46/0x120
? pgprot_writethrough+0x20/0x20
lookup_memtype+0x67/0xf0
track_pfn_insert+0x20/0x40
vmf_insert_pfn_prot+0x88/0x140
vfio_pci_mmap_huge_fault+0xf9/0x1b0 [vfio_pci_core]
__do_fault+0x28/0x1b0
handle_mm_fault+0xef1/0x2560
fixup_user_fault+0xf5/0x270
vaddr_get_pfns+0x169/0x2f0 [vfio_iommu_type1]
vfio_pin_pages_remote+0x162/0x8e0 [vfio_iommu_type1]
vfio_iommu_type1_ioctl+0x1121/0x1810 [vfio_iommu_type1]
? futex_wake+0x1c1/0x260
x64_sys_call+0x234/0x17a0
do_syscall_64+0x63/0x130
? exc_page_fault+0x63/0x130
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20250715184622.3561598-1-kbusch@meta.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
We need to free the descriptor that was allocated. We also don't
necessarily need to unmap each sgl entry, which was previously being
attempted unconditionally.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
NVMe devices from multiple vendors appear to get stuck in a reset state
that we can't get out of with an NVMe level Controller Reset. The kernel
would report these with messages that look like:
Device not ready; aborting reset, CSTS=0x1
These have historically required a power cycle to make them usable
again, but in many cases, a PCIe FLR is sufficient to restart operation
without a power cycle. Try it if the initial controller reset fails
during any nvme reset attempt.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The remove_work will proceed with permanently disconnecting on the
initial final path failure if the head shows no paths after the delay.
If a new path connects while the remove_work is pending, and if that new
path happens to disconnect before that remove_work executes, the delayed
removal should reset based on the most recent path disconnect time, but
queue_delayed_work() won't do anything if the work is already pending.
Attempt to cancel the delayed work when a new path connects, and use
mod_delayed_work() in case the remove_work remains pending anyway.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The sqpoll thread is dereferenced with rcu read protection in one place,
so it needs to be annotated as an __rcu type, and should consistently
use rcu helpers for access and assignment to make sparse happy.
Since most of the accesses occur under the sqd->lock, we can use
rcu_dereference_protected() without declaring an rcu read section.
Provide a simple helper to get the thread from a locked context.
Fixes: ac0b8b327a ("io_uring: fix use-after-free of sq->thread in __io_uring_show_fdinfo()")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20250611205343.1821117-1-kbusch@meta.com
[axboe: fold in fix for register.c]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The command specific status code, 0x183, was introduced in the NVMe 2.0
specification defined to "Command Size Limits Exceeded" and only ever
applied to DSM and Copy commands. Fix the name and, remove the
incorrect translation to error codes and special treatment in the
target code for it.
Fixes: 3b7c33b28a ("nvme.h: add Write Zeroes definitions")
Cc: Chaitanya Kulkarni <chaitanyak@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Introduce dma_pool_create_node(), like dma_pool_create() but taking an
additional NUMA node argument. Allocate struct dma_pool on the desired
node, and store the node on dma_pool for allocating struct dma_page.
Make dma_pool_create() an alias for dma_pool_create_node() with node set
to NUMA_NO_NODE.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Many nvme metadata formats can not strip or generate the metadata on the
controller side. For these formats, a host provided integrity buffer is
mandatory even if it isn't checked.
The block integrity read_verify and write_generate attributes prevent
allocating the metadata buffer, but we need it when the format requires
it, otherwise reads and writes will be rejected by the driver with IO
errors.
Assume the integrity buffer can be offloaded to the controller if the
metadata size is the same as the protection information size. Otherwise
provide an unchecked host buffer when the read verify or write
generation attributes are disabled. This fixes the following nvme
warning:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 371 at drivers/nvme/host/core.c:1036 nvme_setup_rw+0x122/0x210
...
RIP: 0010:nvme_setup_rw+0x122/0x210
...
Call Trace:
<TASK>
nvme_setup_cmd+0x1b4/0x280
nvme_queue_rqs+0xc4/0x1f0 [nvme]
blk_mq_dispatch_queue_requests+0x24a/0x430
blk_mq_flush_plug_list+0x50/0x140
__blk_flush_plug+0xc1/0x100
__submit_bio+0x1c1/0x360
? submit_bio_noacct_nocheck+0x2d6/0x3c0
submit_bio_noacct_nocheck+0x2d6/0x3c0
? submit_bio_noacct+0x47/0x4c0
submit_bio_wait+0x48/0xa0
__blkdev_direct_IO_simple+0xee/0x210
? current_time+0x1d/0x100
? current_time+0x1d/0x100
? __bio_clone+0xb0/0xb0
blkdev_read_iter+0xbb/0x140
vfs_read+0x239/0x310
ksys_read+0x58/0xc0
do_syscall_64+0x6c/0x180
entry_SYSCALL_64_after_hwframe+0x4b/0x53
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250509153802.3482493-1-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Allow userspace to pass a per-I/O write stream in the SQE:
__u8 write_stream;
The __u8 type matches the size the filesystems and block layer support.
Application can query the supported values from the block devices
max_write_streams sysfs attribute. Unsupported values are ignored by
file operations that do not support write streams or rejected with an
error by those that support them.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/r/20250506121732.8211-7-joshi.k@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
A zero return means the reset was successfully scheduled. We don't want
to unquiesce the queues while the reset_work is pending, as that will
just flush out requeued requests to a failed completion.
Fixes: 71a5bb153b ("nvme: ensure disabling pairs with unquiesce")
Reported-by: Dhankaran Singh Ajravat <dhankaran@meta.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The PCIe error handling has the nvme driver quiesce the device, attempt
to restart it, then wait for that restart to complete.
A PCIe DPC event also toggles the PCIe link. If the slot doesn't have
out-of-band presence detection, this will trigger a pciehp
re-enumeration.
The error handling that calls nvme_error_resume is holding the device
lock while this happens. This lock blocks pciehp's request to disconnect
the driver from proceeding.
Meanwhile the nvme's reset can't make forward progress because its
device isn't there anymore with outstanding IO, and the timeout handler
won't do anything to fix it because the device is undergoing error
handling.
End result: deadlocked.
Fix this by having the timeout handler short cut the disabling for a
disconnected PCIe device. The downside is that we're relying on an IO
timeout to clean up this mess, which could be a minute by default.
Tested-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
A VMM may send a non-fatal signal to its threads, including vCPU tasks,
at any time, and thus may signal vCPU tasks during KVM_RUN. If a vCPU
task receives the signal while its trying to spawn the huge page recovery
vhost task, then KVM_RUN will fail due to copy_process() returning
-ERESTARTNOINTR.
Rework call_once() to mark the call complete if and only if the called
function succeeds, and plumb the function's true error code back to the
call_once() invoker. This provides userspace with the correct, non-fatal
error code so that the VMM doesn't terminate the VM on -ENOMEM, and allows
subsequent KVM_RUN a succeed by virtue of retrying creation of the NX huge
page task.
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[implemented the kvm user side]
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-3-kbusch@meta.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Provide new operations for the user to request mapping an active request
to an io uring instance's buf_table. The user has to provide the index
it wants to install the buffer.
A reference count is taken on the request to ensure it can't be
completed while it is active in a ring's buf_table.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20250227223916.143006-6-kbusch@meta.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Provide an interface for the kernel to leverage the existing
pre-registered buffers that io_uring provides. User space can reference
these later to achieve zero-copy IO.
User space must register an empty fixed buffer table with io_uring in
order for the kernel to make use of it.
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20250227223916.143006-5-kbusch@meta.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
All the callers assume nvme_map_user_request() frees the request on a
failure. This wasn't happening on invalid metadata or io_uring command
flags, so we've been leaking those requests.
Fixes: 23fd22e55b ("nvme: wire up fixed buffer support for nvme passthrough")
Fixes: 7c2fd76048 ("nvme: fix metadata handling in nvme-passthrough")
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
To suppress the compiler "warning: symbol 'nvme_tls_attrs_group' was not
declared. Should it be static?"
Fixes: 1e48b34c9b ("nvme: split off TLS sysfs attributes into a separate group")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Keith Busch