This should be plenty, rather than the default of 128, and matches what
we have on the rsrc and futex side as well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently lists are being used to manage this, but best practice is
usually to have these in an array instead as that it cheaper to manage.
Outside of that detail, games are also played with KASAN as the list
is inside the cached entry itself.
Finally, all users of this need a struct io_cache_entry embedded in
their struct, which is union'ized with something else in there that
isn't used across the free -> realloc cycle.
Get rid of all of that, and simply have it be an array. This will not
change the memory used, as we're just trading an 8-byte member entry
for the per-elem array size.
This reduces the overhead of the recycled allocations, and it reduces
the amount of code code needed to support recycling to about half of
what it currently is.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It's now unused, drop the code related to it. This includes the
io_issue_defs->manual alloc field.
While in there, and since ->async_size is now being used a bit more
frequently and in the issue path, move it to io_issue_defs[].
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The previous commit turned on async data for uring_cmd, and did the
basic conversion of setting everything up on the prep side. However, for
a lot of use cases, -EIOCBQUEUED will get returned on issue, as the
operation got successfully queued. For that case, a persistent SQE isn't
needed, as it's just used for issue.
Unless execution goes async immediately, defer copying the double SQE
until it's necessary.
This greatly reduces the overhead of such commands, as evidenced by
a perf diff from before and after this change:
10.60% -8.58% [kernel.vmlinux] [k] io_uring_cmd_prep
where the prep side drops from 10.60% to ~2%, which is more expected.
Performance also rises from ~113M IOPS to ~122M IOPS, bringing us back
to where it was before the async command prep.
Tested-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Basic conversion ensuring async_data is allocated off the prep path. Adds
a basic alloc cache as well, as passthrough IO can be quite high in rate.
Tested-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
While doing that, get rid of io_async_connect and just use the generic
io_async_msghdr. Both of them have a struct sockaddr_storage in there,
and while io_async_msghdr is bigger, if the same type can be used then
the netmsg_cache can get reused for connect as well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Let the io_async_rw hold on to the iovec and reuse it, rather than always
allocate and free them.
Also enables KASAN for the iovec entries, so that reuse can be detected
even while they are in the cache.
While doing so, shrink io_async_rw by getting rid of the bigger embedded
fast iovec. Since iovecs are being recycled now, shrink it from 8 to 1.
This reduces the io_async_rw size from 264 to 160 bytes, a 40% reduction.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We no longer need to gate a potential retry on whether or not the
context matches our original task, as all read/write operations have
been fully prepared upfront. This means there's never any re-import
needed, and hence we can always retry requests.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
read/write requests try to put everything on the stack, and then alloc
and copy if a retry is needed. This necessitates a bunch of nasty code
that deals with intermediate state.
Get rid of this, and have the prep side setup everything that is needed
upfront, which greatly simplifies the opcode handlers.
This includes adding an alloc cache for io_async_rw, to make it cheap
to handle.
In terms of cost, this should be basically free and transparent. For
the worst case of {READ,WRITE}_FIXED which didn't need it before,
performance is unaffected in the normal peak workload that is being
used to test that. Still runs at 122M IOPS.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now that iovec recycling is being done, the iovec is no longer being
freed in there. Hence the kmsg parameter is now useless.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Right now the io_async_msghdr is recycled to avoid the overhead of
allocating+freeing it for every request. But the iovec is not included,
hence that will be allocated and freed for each transfer regardless.
This commit enables recyling of the iovec between io_async_msghdr
recycles. This avoids alloc+free for each one if an iovec is used, and
on top of that, it extends the cache hot nature of msg to the iovec as
well.
Also enables KASAN for the iovec entries, so that reuse can be detected
even while they are in the cache.
The io_async_msghdr also shrinks from 376 -> 288 bytes, an 88 byte
saving (or ~23% smaller), as the fast_iovec entry is dropped from 8
entries to a single entry. There's no point keeping a big fast iovec
entry, if iovecs aren't being allocated and freed continually.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We now ONLY call io_msg_alloc_async() from inside prep handling, which
is always locked. No need for this helper anymore, or the check in
io_msg_alloc_async() on whether the ring is locked or not.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Move the io_async_msghdr out of the issue path and into prep handling,
e it's now done unconditionally and hence does not need to be part
of the issue path. This means any usage of io_sendrecv_prep_async() and
io_sendmsg_prep_async(), and hence the forced async setup path is now
unified with the normal prep setup.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Move the io_async_msghdr out of the issue path and into prep handling,
since it's now done unconditionally and hence does not need to be part
of the issue path. This reduces the footprint of the multishot fast
path of multiple invocations of ->issue() per prep, and also means that
using ->prep_async() can be dropped for recvmsg asthis is now done via
setup on the prep side.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently set this separately for async/sync entry, but let's just
move it to a generic pre-issue spot and eliminate the difference
between the two.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Rather than use an on-stack one and then need to allocate and copy if
async execution is required, always grab one upfront. This should be
very cheap, and potentially even have cache hotness benefits for
back-to-back send/recv requests.
For any recv type of request, this is probably a good choice in general,
as it's expected that no data is available initially. For send this is
not necessarily the case, as space in the socket buffer is expected to
be available. However, getting a cached io_async_msghdr is very cheap,
and as it should be cache hot, probably the difference here is neglible,
if any.
A nice side benefit is that io_setup_async_msg can get killed
completely, which has some nasty iovec manipulation code.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No functional changes in this patch, just in preparation for carrying
more state than what is available now, if necessary.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No functional changes in this patch, just in preparation for carrying
more state then what is being done now, if necessary. While unifying
some of this code, add a generic send setup prep handler that they can
both use.
This gets rid of some manual msghdr and sockaddr on the stack, and makes
it look a bit more like the sendmsg/recvmsg variants. Going forward, more
can get unified on top.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In practice, we just need to recycle a few elements for (by far) most
use cases. Shrink the total size down from 512 to 128, which should be
more than plenty.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For historical reasons these were special cased, as they were the only
ones that needed cancelation. But now we handle cancelations generally,
and hence there's no need to check for these in
io_ring_ctx_wait_and_kill() when io_uring_try_cancel_requests() handles
both these and the rest as well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_post_aux_cqe(), which is used for multishot requests, delays
completions by putting CQEs into a temporary array for the purpose
completion lock/flush batching.
DEFER_TASKRUN doesn't need any locking, so for it we can put completions
directly into the CQ and defer post completion handling with a flag.
That leaves !DEFER_TASKRUN, which is not that interesting / hot for
multishot requests, so have conditional locking with deferred flush
for them.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/b1d05a81fd27aaa2a07f9860af13059e7ad7a890.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The restriction on multishot execution context disallowing io-wq is
driven by rules of io_fill_cqe_req_aux(), it should only be called in
the master task context, either from the syscall path or in task_work.
Since task_work now always takes the ctx lock implying
IO_URING_F_COMPLETE_DEFER, we can just assume that the function is
always called with its defer argument set to true.
Kill the argument. Also rename the function for more consistency as
"fill" in CQE related functions was usually meant for raw interfaces
only copying data into the CQ without any locking, waking the user
and other accounting "post" functions take care of.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/93423d106c33116c7d06bf277f651aa68b427328.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can run normal task_work without locking the ctx, however we try to
lock anyway and most handlers prefer or require it locked. It might have
been interesting to multi-submitter ring with high contention completing
async read/write requests via task_work, however that will still need to
go through io_req_complete_post() and potentially take the lock for
rsrc node putting or some other case.
In other words, it's hard to care about it, so alawys force the locking.
The case described would also because of various io_uring caches.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/6ae858f2ef562e6ed9f13c60978c0d48926954ba.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
NVMe is making up issue_flags, which is a no-no in general, and to make
matters worse, they are completely the wrong ones. For a pure polled
request, which it does check for, we're already inside the
ctx->uring_lock when the completions are run off io_do_iopoll(). Hence
the correct flag would be '0' rather than IO_URING_F_UNLOCKED.
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull sysfs fix from Al Viro:
"Get rid of lockdep false positives around sysfs/overlayfs
syzbot has uncovered a class of lockdep false positives for setups
with sysfs being one of the backing layers in overlayfs. The root
cause is that of->mutex allocated when opening a sysfs file read-only
(which overlayfs might do) is confused with of->mutex of a file opened
writable (held in write to sysfs file, which overlayfs won't do).
Assigning them separate lockdep classes fixes that bunch and it's
obviously safe"
* tag 'pull-sysfs-annotation-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
kernfs: annotate different lockdep class for of->mutex of writable files
Pull misc x86 fixes from Ingo Molnar:
- Follow up fixes for the BHI mitigations code
- Fix !SPECULATION_MITIGATIONS bug not turning off mitigations as
expected
- Work around an APIC emulation bug when the kernel is built with Clang
and run as a SEV guest
- Follow up x86 topology fixes
* tag 'x86-urgent-2024-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu/amd: Move TOPOEXT enablement into the topology parser
x86/cpu/amd: Make the NODEID_MSR union actually work
x86/cpu/amd: Make the CPUID 0x80000008 parser correct
x86/bugs: Replace CONFIG_SPECTRE_BHI_{ON,OFF} with CONFIG_MITIGATION_SPECTRE_BHI
x86/bugs: Remove CONFIG_BHI_MITIGATION_AUTO and spectre_bhi=auto
x86/bugs: Clarify that syscall hardening isn't a BHI mitigation
x86/bugs: Fix BHI handling of RRSBA
x86/bugs: Rename various 'ia32_cap' variables to 'x86_arch_cap_msr'
x86/bugs: Cache the value of MSR_IA32_ARCH_CAPABILITIES
x86/bugs: Fix BHI documentation
x86/cpu: Actually turn off mitigations by default for SPECULATION_MITIGATIONS=n
x86/topology: Don't update cpu_possible_map in topo_set_cpuids()
x86/bugs: Fix return type of spectre_bhi_state()
x86/apic: Force native_apic_mem_read() to use the MOV instruction
Pull perf event fix from Ingo Molnar:
"Fix the x86 PMU multi-counter code returning invalid data in certain
circumstances"
* tag 'perf-urgent-2024-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Fix out of range data
Pull locking fix from Ingo Molnar:
"Fix a PREEMPT_RT build bug"
* tag 'locking-urgent-2024-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking: Make rwsem_assert_held_write_nolockdep() build with PREEMPT_RT=y
Pull irq fix from Ingo Molnar:
"Fix a bug in the GIC irqchip driver"
* tag 'irq-urgent-2024-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/gic-v3-its: Fix VSYNC referencing an unmapped VPE on GIC v4.1
Pull virtio bugfixes from Michael Tsirkin:
"Some small, obvious (in hindsight) bugfixes:
- new ioctl in vhost-vdpa has a wrong # - not too late to fix
- vhost has apparently been lacking an smp_rmb() - due to code
duplication :( The duplication will be fixed in the next merge
cycle, this is a minimal fix
- an error message in vhost talks about guest moving used index -
which of course never happens, guest only ever moves the available
index
- i2c-virtio didn't set the driver owner so it did not get refcounted
correctly"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vhost: correct misleading printing information
vhost-vdpa: change ioctl # for VDPA_GET_VRING_SIZE
virtio: store owner from modules with register_virtio_driver()
vhost: Add smp_rmb() in vhost_enable_notify()
vhost: Add smp_rmb() in vhost_vq_avail_empty()
Pull dma-mapping fixes from Christoph Hellwig:
- fix up swiotlb buffer padding even more (Petr Tesarik)
- fix for partial dma_sync on swiotlb (Michael Kelley)
- swiotlb debugfs fix (Dexuan Cui)
* tag 'dma-maping-6.9-2024-04-14' of git://git.infradead.org/users/hch/dma-mapping:
swiotlb: do not set total_used to 0 in swiotlb_create_debugfs_files()
swiotlb: fix swiotlb_bounce() to do partial sync's correctly
swiotlb: extend buffer pre-padding to alloc_align_mask if necessary
The writable file /sys/power/resume may call vfs lookup helpers for
arbitrary paths and readonly files can be read by overlayfs from vfs
helpers when sysfs is a lower layer of overalyfs.
To avoid a lockdep warning of circular dependency between overlayfs
inode lock and kernfs of->mutex, use a different lockdep class for
writable and readonly kernfs files.
Reported-by: syzbot+9a5b0ced8b1bfb238b56@syzkaller.appspotmail.com
Fixes: 0fedefd4c4 ("kernfs: sysfs: support custom llseek method for sysfs entries")
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull ata fixes from Damien Le Moal:
- Add the mask_port_map parameter to the ahci driver. This is a
follow-up to the recent snafu with the ASMedia controller and its
virtual port hidding port-multiplier devices. As ASMedia confirmed
that there is no way to determine if these slow-to-probe virtual
ports are actually representing the ports of a port-multiplier
devices, this new parameter allow masking ports to significantly
speed up probing during system boot, resulting in shorter boot times.
- A fix for an incorrect handling of a port unlock in
ata_scsi_dev_rescan().
- Allow command duration limits to be detected for ACS-4 devices are
there are such devices out in the field.
* tag 'ata-6.9-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/libata/linux:
ata: libata-core: Allow command duration limits detection for ACS-4 drives
ata: libata-scsi: Fix ata_scsi_dev_rescan() error path
ata: ahci: Add mask_port_map module parameter
Pull zonefs fix from Damien Le Moal:
- Suppress a coccicheck warning using str_plural()
* tag 'zonefs-6.9-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
zonefs: Use str_plural() to fix Coccinelle warning
Pull smb client fixes from Steve French:
- fix for oops in cifs_get_fattr of deleted files
- fix for the remote open counter going negative in some directory
lease cases
- fix for mkfifo to instantiate dentry to avoid possible crash
- important fix to allow handling key rotation for mount and remount
(ie cases that are becoming more common when password that was used
for the mount will expire soon but will be replaced by new password)
* tag 'v6.9-rc3-SMB3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6:
smb3: fix broken reconnect when password changing on the server by allowing password rotation
smb: client: instantiate when creating SFU files
smb3: fix Open files on server counter going negative
smb: client: fix NULL ptr deref in cifs_mark_open_handles_for_deleted_file()
