| Age | Commit message (Collapse) | Author |
|---|
|
Introduce several new KVM uAPIs to ultimately create a guest-first memory
subsystem within KVM, a.k.a. guest_memfd. Guest-first memory allows KVM
to provide features, enhancements, and optimizations that are kludgly
or outright impossible to implement in a generic memory subsystem.
The core KVM ioctl() for guest_memfd is KVM_CREATE_GUEST_MEMFD, which
similar to the generic memfd_create(), creates an anonymous file and
returns a file descriptor that refers to it. Again like "regular"
memfd files, guest_memfd files live in RAM, have volatile storage,
and are automatically released when the last reference is dropped.
The key differences between memfd files (and every other memory subystem)
is that guest_memfd files are bound to their owning virtual machine,
cannot be mapped, read, or written by userspace, and cannot be resized.
guest_memfd files do however support PUNCH_HOLE, which can be used to
convert a guest memory area between the shared and guest-private states.
A second KVM ioctl(), KVM_SET_MEMORY_ATTRIBUTES, allows userspace to
specify attributes for a given page of guest memory. In the long term,
it will likely be extended to allow userspace to specify per-gfn RWX
protections, including allowing memory to be writable in the guest
without it also being writable in host userspace.
The immediate and driving use case for guest_memfd are Confidential
(CoCo) VMs, specifically AMD's SEV-SNP, Intel's TDX, and KVM's own pKVM.
For such use cases, being able to map memory into KVM guests without
requiring said memory to be mapped into the host is a hard requirement.
While SEV+ and TDX prevent untrusted software from reading guest private
data by encrypting guest memory, pKVM provides confidentiality and
integrity *without* relying on memory encryption. In addition, with
SEV-SNP and especially TDX, accessing guest private memory can be fatal
to the host, i.e. KVM must be prevent host userspace from accessing
guest memory irrespective of hardware behavior.
Long term, guest_memfd may be useful for use cases beyond CoCo VMs,
for example hardening userspace against unintentional accesses to guest
memory. As mentioned earlier, KVM's ABI uses userspace VMA protections to
define the allow guest protection (with an exception granted to mapping
guest memory executable), and similarly KVM currently requires the guest
mapping size to be a strict subset of the host userspace mapping size.
Decoupling the mappings sizes would allow userspace to precisely map
only what is needed and with the required permissions, without impacting
guest performance.
A guest-first memory subsystem also provides clearer line of sight to
things like a dedicated memory pool (for slice-of-hardware VMs) and
elimination of "struct page" (for offload setups where userspace _never_
needs to DMA from or into guest memory).
guest_memfd is the result of 3+ years of development and exploration;
taking on memory management responsibilities in KVM was not the first,
second, or even third choice for supporting CoCo VMs. But after many
failed attempts to avoid KVM-specific backing memory, and looking at
where things ended up, it is quite clear that of all approaches tried,
guest_memfd is the simplest, most robust, and most extensible, and the
right thing to do for KVM and the kernel at-large.
The "development cycle" for this version is going to be very short;
ideally, next week I will merge it as is in kvm/next, taking this through
the KVM tree for 6.8 immediately after the end of the merge window.
The series is still based on 6.6 (plus KVM changes for 6.7) so it
will require a small fixup for changes to get_file_rcu() introduced in
6.7 by commit 0ede61d8589c ("file: convert to SLAB_TYPESAFE_BY_RCU").
The fixup will be done as part of the merge commit, and most of the text
above will become the commit message for the merge.
Pending post-merge work includes:
- hugepage support
- looking into using the restrictedmem framework for guest memory
- introducing a testing mechanism to poison memory, possibly using
the same memory attributes introduced here
- SNP and TDX support
There are two non-KVM patches buried in the middle of this series:
fs: Rename anon_inode_getfile_secure() and anon_inode_getfd_secure()
mm: Add AS_UNMOVABLE to mark mapping as completely unmovable
The first is small and mostly suggested-by Christian Brauner; the second
a bit less so but it was written by an mm person (Vlastimil Babka).
|
|
The call to the inode_init_security_anon() LSM hook is not the sole
reason to use anon_inode_getfile_secure() or anon_inode_getfd_secure().
For example, the functions also allow one to create a file with non-zero
size, without needing a full-blown filesystem. In this case, you don't
need a "secure" version, just unique inodes; the current name of the
functions is confusing and does not explain well the difference with
the more "standard" anon_inode_getfile() and anon_inode_getfd().
Of course, there is another side of the coin; neither io_uring nor
userfaultfd strictly speaking need distinct inodes, and it is not
that clear anymore that anon_inode_create_get{file,fd}() allow the LSM
to intercept and block the inode's creation. If one was so inclined,
anon_inode_getfile_secure() and anon_inode_getfd_secure() could be kept,
using the shared inode or a new one depending on CONFIG_SECURITY.
However, this is probably overkill, and potentially a cause of bugs in
different configurations. Therefore, just add a comment to io_uring
and userfaultfd explaining the choice of the function.
While at it, remove the export for what is now anon_inode_create_getfd().
There is no in-tree module that uses it, and the old name is gone anyway.
If anybody actually needs the symbol, they can ask or they can just use
anon_inode_create_getfile(), which will be exported very soon for use
in KVM.
Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Pull io_uring futex support from Jens Axboe:
"This adds support for using futexes through io_uring - first futex
wake and wait, and then the vectored variant of waiting, futex waitv.
For both wait/wake/waitv, we support the bitset variant, as the
'normal' variants can be easily implemented on top of that.
PI and requeue are not supported through io_uring, just the above
mentioned parts. This may change in the future, but in the spirit of
keeping this small (and based on what people have been asking for),
this is what we currently have.
Wake support is pretty straight forward, most of the thought has gone
into the wait side to avoid needing to offload wait operations to a
blocking context. Instead, we rely on the usual callbacks to retry and
post a completion event, when appropriate.
As far as I can recall, the first request for futex support with
io_uring came from Andres Freund, working on postgres. His aio rework
of postgres was one of the early adopters of io_uring, and futex
support was a natural extension for that. This is relevant from both a
usability point of view, as well as for effiency and performance. In
Andres's words, for the former:
Futex wait support in io_uring makes it a lot easier to avoid
deadlocks in concurrent programs that have their own buffer pool:
Obviously pages in the application buffer pool have to be locked
during IO. If the initiator of IO A needs to wait for a held lock
B, the holder of lock B might wait for the IO A to complete. The
ability to wait for a lock and IO completions at the same time
provides an efficient way to avoid such deadlocks
and in terms of effiency, even without unlocking the full potential
yet, Andres says:
Futex wake support in io_uring is useful because it allows for more
efficient directed wakeups. For some "locks" postgres has queues
implemented in userspace, with wakeup logic that cannot easily be
implemented with FUTEX_WAKE_BITSET on a single "futex word"
(imagine waiting for journal flushes to have completed up to a
certain point).
Thus a "lock release" sometimes need to wake up many processes in a
row. A quick-and-dirty conversion to doing these wakeups via
io_uring lead to a 3% throughput increase, with 12% fewer context
switches, albeit in a fairly extreme workload"
* tag 'io_uring-futex-2023-10-30' of git://git.kernel.dk/linux:
io_uring: add support for vectored futex waits
futex: make the vectored futex operations available
futex: make futex_parse_waitv() available as a helper
futex: add wake_data to struct futex_q
io_uring: add support for futex wake and wait
futex: abstract out a __futex_wake_mark() helper
futex: factor out the futex wake handling
futex: move FUTEX2_VALID_MASK to futex.h
|
|
Pull io_uring updates from Jens Axboe:
"This contains the core io_uring updates, of which there are not many,
and adds support for using WAITID through io_uring and hence not
needing to block on these kinds of events.
Outside of that, tweaks to the legacy provided buffer handling and
some cleanups related to cancelations for uring_cmd support"
* tag 'for-6.7/io_uring-2023-10-30' of git://git.kernel.dk/linux:
io_uring/poll: use IOU_F_TWQ_LAZY_WAKE for wakeups
io_uring/kbuf: Use slab for struct io_buffer objects
io_uring/kbuf: Allow the full buffer id space for provided buffers
io_uring/kbuf: Fix check of BID wrapping in provided buffers
io_uring/rsrc: cleanup io_pin_pages()
io_uring: cancelable uring_cmd
io_uring: retain top 8bits of uring_cmd flags for kernel internal use
io_uring: add IORING_OP_WAITID support
exit: add internal include file with helpers
exit: add kernel_waitid_prepare() helper
exit: move core of do_wait() into helper
exit: abstract out should_wake helper for child_wait_callback()
io_uring/rw: add support for IORING_OP_READ_MULTISHOT
io_uring/rw: mark readv/writev as vectored in the opcode definition
io_uring/rw: split io_read() into a helper
|
|
If we specify a valid CQ ring address but an invalid SQ ring address,
we'll correctly spot this and free the allocated pages and clear them
to NULL. However, we don't clear the ring page count, and hence will
attempt to free the pages again. We've already cleared the address of
the page array when freeing them, but we don't check for that. This
causes the following crash:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
Oops [#1]
Modules linked in:
CPU: 0 PID: 20 Comm: kworker/u2:1 Not tainted 6.6.0-rc5-dirty #56
Hardware name: ucbbar,riscvemu-bare (DT)
Workqueue: events_unbound io_ring_exit_work
epc : io_pages_free+0x2a/0x58
ra : io_rings_free+0x3a/0x50
epc : ffffffff808811a2 ra : ffffffff80881406 sp : ffff8f80000c3cd0
status: 0000000200000121 badaddr: 0000000000000000 cause: 000000000000000d
[<ffffffff808811a2>] io_pages_free+0x2a/0x58
[<ffffffff80881406>] io_rings_free+0x3a/0x50
[<ffffffff80882176>] io_ring_exit_work+0x37e/0x424
[<ffffffff80027234>] process_one_work+0x10c/0x1f4
[<ffffffff8002756e>] worker_thread+0x252/0x31c
[<ffffffff8002f5e4>] kthread+0xc4/0xe0
[<ffffffff8000332a>] ret_from_fork+0xa/0x1c
Check for a NULL array in io_pages_free(), but also clear the page counts
when we free them to be on the safer side.
Reported-by: rtm@csail.mit.edu
Fixes: 03d89a2de25b ("io_uring: support for user allocated memory for rings/sqes")
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
The allocation of struct io_buffer for metadata of provided buffers is
done through a custom allocator that directly gets pages and
fragments them. But, slab would do just fine, as this is not a hot path
(in fact, it is a deprecated feature) and, by keeping a custom allocator
implementation we lose benefits like tracking, poisoning,
sanitizers. Finally, the custom code is more complex and requires
keeping the list of pages in struct ctx for no good reason. This patch
cleans this path up and just uses slab.
I microbenchmarked it by forcing the allocation of a large number of
objects with the least number of io_uring commands possible (keeping
nbufs=USHRT_MAX), with and without the patch. There is a slight
increase in time spent in the allocation with slab, of course, but even
when allocating to system resources exhaustion, which is not very
realistic and happened around 1/2 billion provided buffers for me, it
wasn't a significant hit in system time. Specially if we think of a
real-world scenario, an application doing register/unregister of
provided buffers will hit ctx->io_buffers_cache more often than actually
going to slab.
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/20231005000531.30800-4-krisman@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
On at least arm32, but presumably any arch with highmem, if the
application passes in memory that resides in highmem for the rings,
then we should fail that ring creation. We fail it with -EINVAL, which
is what kernels that don't support IORING_SETUP_NO_MMAP will do as well.
Cc: stable@vger.kernel.org
Fixes: 03d89a2de25b ("io_uring: support for user allocated memory for rings/sqes")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Add support for FUTEX_WAKE/WAIT primitives.
IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as
it does support passing in a bitset.
Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and
FUTEX_WAIT_BITSET.
For both of them, they are using the futex2 interface.
FUTEX_WAKE is straight forward, as those can always be done directly from
the io_uring submission without needing async handling. For FUTEX_WAIT,
things are a bit more complicated. If the futex isn't ready, then we
rely on a callback via futex_queue->wake() when someone wakes up the
futex. From that calback, we queue up task_work with the original task,
which will post a CQE and wake it, if necessary.
Cancelations are supported, both from the application point-of-view,
but also to be able to cancel pending waits if the ring exits before
all events have occurred. The return value of futex_unqueue() is used
to gate who wins the potential race between cancelation and futex
wakeups. Whomever gets a 'ret == 1' return from that claims ownership
of the io_uring futex request.
This is just the barebones wait/wake support. PI or REQUEUE support is
not added at this point, unclear if we might look into that later.
Likewise, explicit timeouts are not supported either. It is expected
that users that need timeouts would do so via the usual io_uring
mechanism to do that using linked timeouts.
The SQE format is as follows:
`addr` Address of futex
`fd` futex2(2) FUTEX2_* flags
`futex_flags` io_uring specific command flags. None valid now.
`addr2` Value of futex
`addr3` Mask to wake/wait
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
uring_cmd may never complete, such as ublk, in which uring cmd isn't
completed until one new block request is coming from ublk block device.
Add cancelable uring_cmd to provide mechanism to driver for cancelling
pending commands in its own way.
Add API of io_uring_cmd_mark_cancelable() for driver to mark one command as
cancelable, then io_uring will cancel this command in
io_uring_cancel_generic(). ->uring_cmd() callback is reused for canceling
command in driver's way, then driver gets notified with the cancelling
from io_uring.
Add API of io_uring_cmd_get_task() to help driver cancel handler
deal with the canceling.
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Suggested-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Retain top 8bits of uring_cmd flags for kernel internal use, so that we
can move IORING_URING_CMD_POLLED out of uapi header.
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
This adds support for an async version of waitid(2), in a fully async
version. If an event isn't immediately available, wait for a callback
to trigger a retry.
The format of the sqe is as follows:
sqe->len The 'which', the idtype being queried/waited for.
sqe->fd The 'pid' (or id) being waited for.
sqe->file_index The 'options' being set.
sqe->addr2 A pointer to siginfo_t, if any, being filled in.
buf_index, add3, and waitid_flags are reserved/unused for now.
waitid_flags will be used for options for this request type. One
interesting use case may be to add multi-shot support, so that the
request stays armed and posts a notification every time a monitored
process state change occurs.
Note that this does not support rusage, on Arnd's recommendation.
See the waitid(2) man page for details on the arguments.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
This reverts commit b484a40dc1f16edb58e5430105a021e1916e6f27.
This commit cancels all requests with io-wq, not just the ones from the
originating task. This breaks use cases that have thread pools, or just
multiple tasks issuing requests on the same ring. The liburing
regression test for this also shows that problem:
$ test/thread-exit.t
cqe->res=-125, Expected 512
where an IO thread gets its request canceled rather than complete
successfully.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
[ 71.490669] WARNING: CPU: 3 PID: 17070 at io_uring/io_uring.c:769
io_cqring_event_overflow+0x47b/0x6b0
[ 71.498381] Call Trace:
[ 71.498590] <TASK>
[ 71.501858] io_req_cqe_overflow+0x105/0x1e0
[ 71.502194] __io_submit_flush_completions+0x9f9/0x1090
[ 71.503537] io_submit_sqes+0xebd/0x1f00
[ 71.503879] __do_sys_io_uring_enter+0x8c5/0x2380
[ 71.507360] do_syscall_64+0x39/0x80
We decoupled CQ locking from ->task_complete but haven't fixed up places
forcing locking for CQ overflows.
Fixes: ec26c225f06f5 ("io_uring: merge iopoll and normal completion paths")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io-wq will retry iopoll even when it failed with -EAGAIN. If that
races with task exit, which sets TIF_NOTIFY_SIGNAL for all its workers,
such workers might potentially infinitely spin retrying iopoll again and
again and each time failing on some allocation / waiting / etc. Don't
keep spinning if io-wq is dying.
Fixes: 561fb04a6a225 ("io_uring: replace workqueue usage with io-wq")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Introduce a new sysctl (io_uring_disabled) which can be either 0, 1, or
2. When 0 (the default), all processes are allowed to create io_uring
instances, which is the current behavior. When 1, io_uring creation is
disabled (io_uring_setup() will fail with -EPERM) for unprivileged
processes not in the kernel.io_uring_group group. When 2, calls to
io_uring_setup() fail with -EPERM regardless of privilege.
Signed-off-by: Matteo Rizzo <matteorizzo@google.com>
[JEM: modified to add io_uring_group]
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Link: https://lore.kernel.org/r/x49y1i42j1z.fsf@segfault.boston.devel.redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_wq_put_and_exit() is called from do_exit(), but all FIXED_FILE requests
in io_wq aren't canceled in io_uring_cancel_generic() called from do_exit().
Meantime io_wq IO code path may share resource with normal iopoll code
path.
So if any HIPRI request is submittd via io_wq, this request may not get resouce
for moving on, given iopoll isn't possible in io_wq_put_and_exit().
The issue can be triggered when terminating 't/io_uring -n4 /dev/nullb0'
with default null_blk parameters.
Fix it by always cancelling all requests in io_wq by adding helper of
io_uring_cancel_wq(), and this way is reasonable because io_wq destroying
follows canceling requests immediately.
Closes: https://lore.kernel.org/linux-block/3893581.1691785261@warthog.procyon.org.uk/
Reported-by: David Howells <dhowells@redhat.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230901134916.2415386-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Pull io_uring updates from Jens Axboe:
"Fairly quiet round in terms of features, mostly just improvements all
over the map for existing code. In detail:
- Initial support for socket operations through io_uring. Latter half
of this will likely land with the 6.7 kernel, then allowing things
like get/setsockopt (Breno)
- Cleanup of the cancel code, and then adding support for canceling
requests with the opcode as the key (me)
- Improvements for the io-wq locking (me)
- Fix affinity setting for SQPOLL based io-wq (me)
- Remove the io_uring userspace code. These were added initially as
copies from liburing, but all of them have since bitrotted and are
way out of date at this point. Rather than attempt to keep them in
sync, just get rid of them. People will have liburing available
anyway for these examples. (Pavel)
- Series improving the CQ/SQ ring caching (Pavel)
- Misc fixes and cleanups (Pavel, Yue, me)"
* tag 'for-6.6/io_uring-2023-08-28' of git://git.kernel.dk/linux: (47 commits)
io_uring: move iopoll ctx fields around
io_uring: move multishot cqe cache in ctx
io_uring: separate task_work/waiting cache line
io_uring: banish non-hot data to end of io_ring_ctx
io_uring: move non aligned field to the end
io_uring: add option to remove SQ indirection
io_uring: compact SQ/CQ heads/tails
io_uring: force inline io_fill_cqe_req
io_uring: merge iopoll and normal completion paths
io_uring: reorder cqring_flush and wakeups
io_uring: optimise extra io_get_cqe null check
io_uring: refactor __io_get_cqe()
io_uring: simplify big_cqe handling
io_uring: cqe init hardening
io_uring: improve cqe !tracing hot path
io_uring/rsrc: Annotate struct io_mapped_ubuf with __counted_by
io_uring/sqpoll: fix io-wq affinity when IORING_SETUP_SQPOLL is used
io_uring: simplify io_run_task_work_sig return
io_uring/rsrc: keep one global dummy_ubuf
io_uring: never overflow io_aux_cqe
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Some swap cleanups from Ma Wupeng ("fix WARN_ON in
add_to_avail_list")
- Peter Xu has a series (mm/gup: Unify hugetlb, speed up thp") which
reduces the special-case code for handling hugetlb pages in GUP. It
also speeds up GUP handling of transparent hugepages.
- Peng Zhang provides some maple tree speedups ("Optimize the fast path
of mas_store()").
- Sergey Senozhatsky has improved te performance of zsmalloc during
compaction (zsmalloc: small compaction improvements").
- Domenico Cerasuolo has developed additional selftest code for zswap
("selftests: cgroup: add zswap test program").
- xu xin has doe some work on KSM's handling of zero pages. These
changes are mainly to enable the user to better understand the
effectiveness of KSM's treatment of zero pages ("ksm: support
tracking KSM-placed zero-pages").
- Jeff Xu has fixes the behaviour of memfd's
MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED sysctl ("mm/memfd: fix sysctl
MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED").
- David Howells has fixed an fscache optimization ("mm, netfs, fscache:
Stop read optimisation when folio removed from pagecache").
- Axel Rasmussen has given userfaultfd the ability to simulate memory
poisoning ("add UFFDIO_POISON to simulate memory poisoning with
UFFD").
- Miaohe Lin has contributed some routine maintenance work on the
memory-failure code ("mm: memory-failure: remove unneeded PageHuge()
check").
- Peng Zhang has contributed some maintenance work on the maple tree
code ("Improve the validation for maple tree and some cleanup").
- Hugh Dickins has optimized the collapsing of shmem or file pages into
THPs ("mm: free retracted page table by RCU").
- Jiaqi Yan has a patch series which permits us to use the healthy
subpages within a hardware poisoned huge page for general purposes
("Improve hugetlbfs read on HWPOISON hugepages").
- Kemeng Shi has done some maintenance work on the pagetable-check code
("Remove unused parameters in page_table_check").
- More folioification work from Matthew Wilcox ("More filesystem folio
conversions for 6.6"), ("Followup folio conversions for zswap"). And
from ZhangPeng ("Convert several functions in page_io.c to use a
folio").
- page_ext cleanups from Kemeng Shi ("minor cleanups for page_ext").
- Baoquan He has converted some architectures to use the
GENERIC_IOREMAP ioremap()/iounmap() code ("mm: ioremap: Convert
architectures to take GENERIC_IOREMAP way").
- Anshuman Khandual has optimized arm64 tlb shootdown ("arm64: support
batched/deferred tlb shootdown during page reclamation/migration").
- Better maple tree lockdep checking from Liam Howlett ("More strict
maple tree lockdep"). Liam also developed some efficiency
improvements ("Reduce preallocations for maple tree").
- Cleanup and optimization to the secondary IOMMU TLB invalidation,
from Alistair Popple ("Invalidate secondary IOMMU TLB on permission
upgrade").
- Ryan Roberts fixes some arm64 MM selftest issues ("selftests/mm fixes
for arm64").
- Kemeng Shi provides some maintenance work on the compaction code
("Two minor cleanups for compaction").
- Some reduction in mmap_lock pressure from Matthew Wilcox ("Handle
most file-backed faults under the VMA lock").
- Aneesh Kumar contributes code to use the vmemmap optimization for DAX
on ppc64, under some circumstances ("Add support for DAX vmemmap
optimization for ppc64").
- page-ext cleanups from Kemeng Shi ("add page_ext_data to get client
data in page_ext"), ("minor cleanups to page_ext header").
- Some zswap cleanups from Johannes Weiner ("mm: zswap: three
cleanups").
- kmsan cleanups from ZhangPeng ("minor cleanups for kmsan").
- VMA handling cleanups from Kefeng Wang ("mm: convert to
vma_is_initial_heap/stack()").
- DAMON feature work from SeongJae Park ("mm/damon/sysfs-schemes:
implement DAMOS tried total bytes file"), ("Extend DAMOS filters for
address ranges and DAMON monitoring targets").
- Compaction work from Kemeng Shi ("Fixes and cleanups to compaction").
- Liam Howlett has improved the maple tree node replacement code
("maple_tree: Change replacement strategy").
- ZhangPeng has a general code cleanup - use the K() macro more widely
("cleanup with helper macro K()").
- Aneesh Kumar brings memmap-on-memory to ppc64 ("Add support for
memmap on memory feature on ppc64").
- pagealloc cleanups from Kemeng Shi ("Two minor cleanups for pcp list
in page_alloc"), ("Two minor cleanups for get pageblock
migratetype").
- Vishal Moola introduces a memory descriptor for page table tracking,
"struct ptdesc" ("Split ptdesc from struct page").
- memfd selftest maintenance work from Aleksa Sarai ("memfd: cleanups
for vm.memfd_noexec").
- MM include file rationalization from Hugh Dickins ("arch: include
asm/cacheflush.h in asm/hugetlb.h").
- THP debug output fixes from Hugh Dickins ("mm,thp: fix sloppy text
output").
- kmemleak improvements from Xiaolei Wang ("mm/kmemleak: use
object_cache instead of kmemleak_initialized").
- More folio-related cleanups from Matthew Wilcox ("Remove _folio_dtor
and _folio_order").
- A VMA locking scalability improvement from Suren Baghdasaryan
("Per-VMA lock support for swap and userfaults").
- pagetable handling cleanups from Matthew Wilcox ("New page table
range API").
- A batch of swap/thp cleanups from David Hildenbrand ("mm/swap: stop
using page->private on tail pages for THP_SWAP + cleanups").
- Cleanups and speedups to the hugetlb fault handling from Matthew
Wilcox ("Change calling convention for ->huge_fault").
- Matthew Wilcox has also done some maintenance work on the MM
subsystem documentation ("Improve mm documentation").
* tag 'mm-stable-2023-08-28-18-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (489 commits)
maple_tree: shrink struct maple_tree
maple_tree: clean up mas_wr_append()
secretmem: convert page_is_secretmem() to folio_is_secretmem()
nios2: fix flush_dcache_page() for usage from irq context
hugetlb: add documentation for vma_kernel_pagesize()
mm: add orphaned kernel-doc to the rst files.
mm: fix clean_record_shared_mapping_range kernel-doc
mm: fix get_mctgt_type() kernel-doc
mm: fix kernel-doc warning from tlb_flush_rmaps()
mm: remove enum page_entry_size
mm: allow ->huge_fault() to be called without the mmap_lock held
mm: move PMD_ORDER to pgtable.h
mm: remove checks for pte_index
memcg: remove duplication detection for mem_cgroup_uncharge_swap
mm/huge_memory: work on folio->swap instead of page->private when splitting folio
mm/swap: inline folio_set_swap_entry() and folio_swap_entry()
mm/swap: use dedicated entry for swap in folio
mm/swap: stop using page->private on tail pages for THP_SWAP
selftests/mm: fix WARNING comparing pointer to 0
selftests: cgroup: fix test_kmem_memcg_deletion kernel mem check
...
|
|
We cache multishot CQEs before flushing them to the CQ in
submit_state.cqe. It's a 16 entry cache totalling 256 bytes in the
middle of the io_submit_state structure. Move it out of there, it
should help with CPU caches for the submission state, and shouldn't
affect cached CQEs.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/dbe1f39c043ee23da918836be44fcec252ce6711.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Not many aware, but io_uring submission queue has two levels. The first
level usually appears as sq_array and stores indexes into the actual SQ.
To my knowledge, no one has ever seriously used it, nor liburing exposes
it to users. Add IORING_SETUP_NO_SQARRAY, when set we don't bother
creating and using the sq_array and SQ heads/tails will be pointing
directly into the SQ. Improves memory footprint, in term of both
allocations as well as cache usage, and also should make io_get_sqe()
less branchy in the end.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0ffa3268a5ef61d326201ff43a233315c96312e0.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_do_iopoll() and io_submit_flush_completions() are pretty similar,
both filling CQEs and then free a list of requests. Don't duplicate it
and make iopoll use __io_submit_flush_completions(), which also helps
with inlining and other optimisations.
For that, we need to first find all completed iopoll requests and splice
them from the iopoll list and then pass it down. This adds one extra
list traversal, which should be fine as requests will stay hot in cache.
CQ locking is already conditional, introduce ->lockless_cq and skip
locking for IOPOLL as it's protected by ->uring_lock.
We also add a wakeup optimisation for IOPOLL to __io_cq_unlock_post(),
so it works just like io_cqring_ev_posted_iopoll().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3840473f5e8a960de35b77292026691880f6bdbc.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Unlike in the past, io_commit_cqring_flush() doesn't do anything that
may need io_cqring_wake() to be issued after, all requests it completes
will go via task_work. Do io_commit_cqring_flush() after
io_cqring_wake() to clean up __io_cq_unlock_post().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/ed32dcfeec47e6c97bd6b18c152ddce5b218403f.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
If the cached cqe check passes in io_get_cqe*() it already means that
the cqe we return is valid and non-zero, however the compiler is unable
to optimise null checks like in io_fill_cqe_req().
Do a bit of trickery, return success/fail boolean from io_get_cqe*()
and store cqe in the cqe parameter. That makes it do the right thing,
erasing the check together with the introduced indirection.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/322ea4d3377d3d4efd8ae90ab8ed28a99f518210.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Make __io_get_cqe simpler by not grabbing the cqe from refilled cached,
but letting io_get_cqe() do it for us. That's cleaner and removes some
duplication.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/74dc8fdf2657e438b2e05e1d478a3596924604e9.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Don't keep big_cqe bits of req in a union with hash_node, find a
separate space for it. It's bit safer, but also if we keep it always
initialised, we can get rid of ugly REQ_F_CQE32_INIT handling.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/447aa1b2968978c99e655ba88db536e903df0fe9.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_kiocb::cqe stores the completion info which we'll memcpy to
userspace, and we rely on callbacks and other later steps to populate
it with right values. We have never had problems with that, but it would
still be safer to zero it on allocation.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b16a3b64dde678686460d3c3792c3ba6d3d1bc7a.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Patch series "Remove _folio_dtor and _folio_order", v2.
This patch (of 13):
folio_put() is the standard way to write this, and it's not appreciably
slower. This is an enabling patch for removing free_compound_page()
entirely.
Link: https://lkml.kernel.org/r/20230816151201.3655946-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20230816151201.3655946-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Yanteng Si <siyanteng@loongson.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
If we setup the ring with SQPOLL, then that polling thread has its
own io-wq setup. This means that if the application uses
IORING_REGISTER_IOWQ_AFF to set the io-wq affinity, we should not be
setting it for the invoking task, but rather the sqpoll task.
Add an sqpoll helper that parks the thread and updates the affinity,
and use that one if we're using SQPOLL.
Fixes: fe76421d1da1 ("io_uring: allow user configurable IO thread CPU affinity")
Cc: stable@vger.kernel.org # 5.10+
Link: https://github.com/axboe/liburing/discussions/884
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Nobody cares about io_run_task_work_sig returning 1, we only check for
negative errors. Simplify by keeping to 0/-error returns.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3aec8a532c003d6e50739b969a82989402696170.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
We set empty registered buffers to dummy_ubuf as an optimisation.
Currently, we allocate the dummy entry for each ring, whenever we can
simply have one global instance.
We're casting out const on assignment, it's fine as we're not going to
change the content of the dummy, the constness gives us an extra layer
of protection if sth ever goes wrong.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e4a96dda35ab755914bc43f6781bba0df97ac489.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Now all callers of io_aux_cqe() set allow_overflow to false, remove the
parameter and not allow overflowing auxilary multishot cqes.
When CQ is full the function callers and all multishot requests in
general are expected to complete the request. That prevents indefinite
in-background grows of the overflow list and let's the userspace to
handle the backlog at its own pace.
Resubmitting a request should also be faster than accounting a bunch of
overflows, so it should be better for perf when it happens, but a well
behaving userspace should be trying to avoid overflows in any case.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/bb20d14d708ea174721e58bb53786b0521e4dd6d.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Nobody checks io_req_cqe_overflow()'s return, make it return void.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/8f2029ad0c22f73451664172d834372608ee0a77.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_fill_cqe_req() is only called from one place, open code it, and
rename __io_fill_cqe_req().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f432ce75bb1c94cadf0bd2add4d6aa510bd1fb36.1691757663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
We never use io_move_task_work_from_local() before it's defined in the
file anyway, so kill the forward declaration.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
No functional changes in this patch, just a prep patch for needing the
request in io_file_put().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
We return 0 for success, or -error when there's an error. Move the 'ret'
variable into the loop where we are actually using it, to make it
clearer that we don't carry this variable forward for return outside of
the loop.
While at it, also move the need_resched() break condition out of the
while check itself, keeping it with the signal pending check.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Don't keep spinning iopoll with a signal set. It'll eventually return
back, e.g. by virtue of need_resched(), but it's not a nice user
experience.
Cc: stable@vger.kernel.org
Fixes: def596e9557c9 ("io_uring: support for IO polling")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/eeba551e82cad12af30c3220125eb6cb244cc94c.1691594339.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_req_local_work_add() peeks into the work list, which can be executed
in the meanwhile. It's completely fine without KASAN as we're in an RCU
read section and it's SLAB_TYPESAFE_BY_RCU. With KASAN though it may
trigger a false positive warning because internal io_uring caches are
sanitised.
Remove sanitisation from the io_uring request cache for now.
Cc: stable@vger.kernel.org
Fixes: 8751d15426a31 ("io_uring: reduce scheduling due to tw")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c6fbf7a82a341e66a0007c76eefd9d57f2d3ba51.1691541473.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
cq_extra is protected by ->completion_lock, which io_get_sqe() misses.
The bug is harmless as it doesn't happen in real life, requires invalid
SQ index array and racing with submission, and only messes up the
userspace, i.e. stall requests execution but will be cleaned up on
ring destruction.
Fixes: 15641e427070f ("io_uring: don't cache number of dropped SQEs")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/66096d54651b1a60534bb2023f2947f09f50ef73.1691538547.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
When compiling the kernel with clang and having HARDENED_USERCOPY
enabled, the liburing openat2.t test case fails during request setup:
usercopy: Kernel memory overwrite attempt detected to SLUB object 'io_kiocb' (offset 24, size 24)!
------------[ cut here ]------------
kernel BUG at mm/usercopy.c:102!
invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
CPU: 3 PID: 413 Comm: openat2.t Tainted: G N 6.4.3-g6995e2de6891-dirty #19
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
RIP: 0010:usercopy_abort+0x84/0x90
Code: ce 49 89 ce 48 c7 c3 68 48 98 82 48 0f 44 de 48 c7 c7 56 c6 94 82 4c 89 de 48 89 c1 41 52 41 56 53 e8 e0 51 c5 00 48 83 c4 18 <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 41 57 41 56
RSP: 0018:ffffc900016b3da0 EFLAGS: 00010296
RAX: 0000000000000062 RBX: ffffffff82984868 RCX: 4e9b661ac6275b00
RDX: ffff8881b90ec580 RSI: ffffffff82949a64 RDI: 00000000ffffffff
RBP: 0000000000000018 R08: 0000000000000000 R09: 0000000000000000
R10: ffffc900016b3c88 R11: ffffc900016b3c30 R12: 00007ffe549659e0
R13: ffff888119014000 R14: 0000000000000018 R15: 0000000000000018
FS: 00007f862e3ca680(0000) GS:ffff8881b90c0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005571483542a8 CR3: 0000000118c11000 CR4: 00000000003506e0
Call Trace:
<TASK>
? __die_body+0x63/0xb0
? die+0x9d/0xc0
? do_trap+0xa7/0x180
? usercopy_abort+0x84/0x90
? do_error_trap+0xc6/0x110
? usercopy_abort+0x84/0x90
? handle_invalid_op+0x2c/0x40
? usercopy_abort+0x84/0x90
? exc_invalid_op+0x2f/0x40
? asm_exc_invalid_op+0x16/0x20
? usercopy_abort+0x84/0x90
__check_heap_object+0xe2/0x110
__check_object_size+0x142/0x3d0
io_openat2_prep+0x68/0x140
io_submit_sqes+0x28a/0x680
__se_sys_io_uring_enter+0x120/0x580
do_syscall_64+0x3d/0x80
entry_SYSCALL_64_after_hwframe+0x46/0xb0
RIP: 0033:0x55714834de26
Code: ca 01 0f b6 82 d0 00 00 00 8b ba cc 00 00 00 45 31 c0 31 d2 41 b9 08 00 00 00 83 e0 01 c1 e0 04 41 09 c2 b8 aa 01 00 00 0f 05 <c3> 66 0f 1f 84 00 00 00 00 00 89 30 eb 89 0f 1f 40 00 8b 00 a8 06
RSP: 002b:00007ffe549659c8 EFLAGS: 00000246 ORIG_RAX: 00000000000001aa
RAX: ffffffffffffffda RBX: 00007ffe54965a50 RCX: 000055714834de26
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000003
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000008
R10: 0000000000000000 R11: 0000000000000246 R12: 000055714834f057
R13: 00007ffe54965a50 R14: 0000000000000001 R15: 0000557148351dd8
</TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
when it tries to copy struct open_how from userspace into the per-command
space in the io_kiocb. There's nothing wrong with the copy, but we're
missing the appropriate annotations for allowing user copies to/from the
io_kiocb slab.
Allow copies in the per-command area, which is from the 'file' pointer to
when 'opcode' starts. We do have existing user copies there, but they are
not all annotated like the one that openat2_prep() uses,
copy_struct_from_user(). But in practice opcodes should be allowed to
copy data into their per-command area in the io_kiocb.
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
The changes from commit 32832a407a71 ("io_uring: Fix io_uring mmap() by
using architecture-provided get_unmapped_area()") to the parisc
implementation of get_unmapped_area() broke glibc's locale-gen
executable when running on parisc.
This patch reverts those architecture-specific changes, and instead
adjusts in io_uring_mmu_get_unmapped_area() the pgoff offset which is
then given to parisc's get_unmapped_area() function. This is much
cleaner than the previous approach, and we still will get a coherent
addresss.
This patch has no effect on other architectures (SHM_COLOUR is only
defined on parisc), and the liburing testcase stil passes on parisc.
Cc: stable@vger.kernel.org # 6.4
Signed-off-by: Helge Deller <deller@gmx.de>
Reported-by: Christoph Biedl <linux-kernel.bfrz@manchmal.in-ulm.de>
Fixes: 32832a407a71 ("io_uring: Fix io_uring mmap() by using architecture-provided get_unmapped_area()")
Fixes: d808459b2e31 ("io_uring: Adjust mapping wrt architecture aliasing requirements")
Link: https://lore.kernel.org/r/ZNEyGV0jyI8kOOfz@p100
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
A previous commit made all cqring waits marked as iowait, as a way to
improve performance for short schedules with pending IO. However, for
use cases that have a special reaper thread that does nothing but
wait on events on the ring, this causes a cosmetic issue where we
know have one core marked as being "busy" with 100% iowait.
While this isn't a grave issue, it is confusing to users. Rather than
always mark us as being in iowait, gate setting of current->in_iowait
to 1 by whether or not the waiting task has pending requests.
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/io-uring/CAMEGJJ2RxopfNQ7GNLhr7X9=bHXKo+G5OOe0LUq=+UgLXsv1Xg@mail.gmail.com/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217699
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217700
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Reported-by: Phil Elwell <phil@raspberrypi.com>
Tested-by: Andres Freund <andres@anarazel.de>
Fixes: 8a796565cec3 ("io_uring: Use io_schedule* in cqring wait")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
The io_uring testcase is broken on IA-64 since commit d808459b2e31
("io_uring: Adjust mapping wrt architecture aliasing requirements").
The reason is, that this commit introduced an own architecture
independend get_unmapped_area() search algorithm which finds on IA-64 a
memory region which is outside of the regular memory region used for
shared userspace mappings and which can't be used on that platform
due to aliasing.
To avoid similar problems on IA-64 and other platforms in the future,
it's better to switch back to the architecture-provided
get_unmapped_area() function and adjust the needed input parameters
before the call. Beside fixing the issue, the function now becomes
easier to understand and maintain.
This patch has been successfully tested with the io_uring testcase on
physical x86-64, ppc64le, IA-64 and PA-RISC machines. On PA-RISC the LTP
mmmap testcases did not report any regressions.
Cc: stable@vger.kernel.org # 6.4
Signed-off-by: Helge Deller <deller@gmx.de>
Reported-by: matoro <matoro_mailinglist_kernel@matoro.tk>
Fixes: d808459b2e31 ("io_uring: Adjust mapping wrt architecture aliasing requirements")
Link: https://lore.kernel.org/r/20230721152432.196382-2-deller@gmx.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io-wq assumes that an issue is blocking, but it may not be if the
request type has asked for a non-blocking attempt. If we get
-EAGAIN for that case, then we need to treat it as a final result
and not retry or arm poll for it.
Cc: stable@vger.kernel.org # 5.10+
Link: https://github.com/axboe/liburing/issues/897
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
The check being unconditional may lead to unwanted denials reported by
LSMs when a process has the capability granted by DAC, but denied by an
LSM. In the case of SELinux such denials are a problem, since they can't
be effectively filtered out via the policy and when not silenced, they
produce noise that may hide a true problem or an attack.
Since not having the capability merely means that the created io_uring
context will be accounted against the current user's RLIMIT_MEMLOCK
limit, we can disable auditing of denials for this check by using
ns_capable_noaudit() instead of capable().
Fixes: 2b188cc1bb85 ("Add io_uring IO interface")
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2193317
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Link: https://lore.kernel.org/r/20230718115607.65652-1-omosnace@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
I observed poor performance of io_uring compared to synchronous IO. That
turns out to be caused by deeper CPU idle states entered with io_uring,
due to io_uring using plain schedule(), whereas synchronous IO uses
io_schedule().
The losses due to this are substantial. On my cascade lake workstation,
t/io_uring from the fio repository e.g. yields regressions between 20%
and 40% with the following command:
./t/io_uring -r 5 -X0 -d 1 -s 1 -c 1 -p 0 -S$use_sync -R 0 /mnt/t2/fio/write.0.0
This is repeatable with different filesystems, using raw block devices
and using different block devices.
Use io_schedule_prepare() / io_schedule_finish() in
io_cqring_wait_schedule() to address the difference.
After that using io_uring is on par or surpassing synchronous IO (using
registered files etc makes it reliably win, but arguably is a less fair
comparison).
There are other calls to schedule() in io_uring/, but none immediately
jump out to be similarly situated, so I did not touch them. Similarly,
it's possible that mutex_lock_io() should be used, but it's not clear if
there are cases where that matters.
Cc: stable@vger.kernel.org # 5.10+
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: io-uring@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Andres Freund <andres@anarazel.de>
Link: https://lore.kernel.org/r/20230707162007.194068-1-andres@anarazel.de
[axboe: minor style fixup]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_uring offloads task_work for cancelation purposes when the task is
exiting. This is conceptually fine, but we should be nicer and actually
wait for that work to complete before returning.
Add an argument to io_fallback_tw() telling it to flush the deferred
work when it's all queued up, and have it flush a ctx behind whenever
the ctx changes.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
It's used just one function higher up, get rid of the declaration and
just move it up a bit.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
There is no reason not to use __io_cq_unlock_post_flush for intermediate
aux CQE flushing, all ->task_complete should apply there, i.e. if set it
should be the submitter task. Combine them, get rid of of
__io_cq_unlock_post() and rename the left function.
This place was also taking a couple percents of CPU according to
profiles for max throughput net benchmarks due to multishot recv
flooding it with completions.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/bbed60734cbec2e833d9c7bdcf9741aada5d8aab.1687518903.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
io_cq_unlock_post() is exclusively used in io_uring/io_uring.c, mark it
static and don't expose to other files.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/3dc8127dda4514e1dd24bb32035faac887c5fa37.1687518903.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
