Pavel Begunkov [Wed, 10 Apr 2024 01:26:54 +0000 (02:26 +0100)]
io_uring: always lock __io_cqring_overflow_flush
Conditional locking is never great, in case of
__io_cqring_overflow_flush(), which is a slow path, it's not justified.
Don't handle IOPOLL separately, always grab uring_lock for overflow
flushing.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/162947df299aa12693ac4b305dacedab32ec7976.1712708261.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Wed, 10 Apr 2024 01:26:53 +0000 (02:26 +0100)]
io_uring: open code io_cqring_overflow_flush()
There is only one caller of io_cqring_overflow_flush(), open code it
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a1fecd56d9dba923ed8d4d159727fa939d3baa2a.1712708261.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Wed, 10 Apr 2024 01:26:52 +0000 (02:26 +0100)]
io_uring: remove extra SQPOLL overflow flush
c1edbf5f081be ("io_uring: flag SQPOLL busy condition to userspace")
added an extra overflowed CQE flush in the SQPOLL submission path due to
backpressure, which was later removed. Remove the flush and let
io_cqring_wait() / iopoll handle it.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/2a83b0724ca6ca9d16c7d79a51b77c81876b2e39.1712708261.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Wed, 10 Apr 2024 01:26:51 +0000 (02:26 +0100)]
io_uring: unexport io_req_cqe_overflow()
There are no users of io_req_cqe_overflow() apart from io_uring.c, make
it static.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f4295eb2f9eb98d5db38c0578f57f0b86bfe0d8c.1712708261.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Tue, 9 Apr 2024 21:05:53 +0000 (14:05 -0700)]
io_uring: separate header for exported net bits
We're exporting some io_uring bits to networking, e.g. for implementing
a net callback for io_uring cmds, but we don't want to expose more than
needed. Add a separate header for networking.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://lore.kernel.org/r/20240409210554.1878789-1-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Sun, 7 Apr 2024 23:54:57 +0000 (00:54 +0100)]
io_uring/net: set MSG_ZEROCOPY for sendzc in advance
We can set MSG_ZEROCOPY at the preparation step, do it so we don't have
to care about it later in the issue callback.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c2c22aaa577624977f045979a6db2b9fb2e5648c.1712534031.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Sun, 7 Apr 2024 23:54:56 +0000 (00:54 +0100)]
io_uring/net: get rid of io_notif_complete_tw_ext
io_notif_complete_tw_ext() can be removed and combined with
io_notif_complete_tw to make it simpler without sacrificing
anything.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/025a124a5e20e2474a57e2f04f16c422eb83063c.1712534031.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Sun, 7 Apr 2024 23:54:55 +0000 (00:54 +0100)]
io_uring/net: merge ubuf sendzc callbacks
Splitting io_tx_ubuf_callback_ext from io_tx_ubuf_callback is a pre
mature optimisation that doesn't give us much. Merge the functions into
one and reclaim some simplicity back.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/d44d68f6f7add33a0dcf0b7fd7b73c2dc543604f.1712534031.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Sun, 7 Apr 2024 13:27:59 +0000 (21:27 +0800)]
io_uring: return void from io_put_kbuf_comp()
The only caller doesn't handle the return value of io_put_kbuf_comp(), so
change its return type into void.
Also follow Jens's suggestion to rename it as io_put_kbuf_drop().
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240407132759.4056167-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Fri, 5 Apr 2024 15:50:05 +0000 (16:50 +0100)]
io_uring: remove io_req_put_rsrc_locked()
io_req_put_rsrc_locked() is a weird shim function around
io_req_put_rsrc(). All calls to io_req_put_rsrc() require holding
->uring_lock, so we can just use it directly.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a195bc78ac3d2c6fbaea72976e982fe51e50ecdd.1712331455.git.asml.silence@gmail.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Fri, 5 Apr 2024 15:50:04 +0000 (16:50 +0100)]
io_uring: remove async request cache
io_req_complete_post() was a sole user of ->locked_free_list, but
since we just gutted the function, the cache is not used anymore and
can be removed.
->locked_free_list served as an asynhronous counterpart of the main
request (i.e. struct io_kiocb) cache for all unlocked cases like io-wq.
Now they're all forced to be completed into the main cache directly,
off of the normal completion path or via io_free_req().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7bffccd213e370abd4de480e739d8b08ab6c1326.1712331455.git.asml.silence@gmail.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Fri, 5 Apr 2024 15:50:03 +0000 (16:50 +0100)]
io_uring: turn implicit assumptions into a warning
io_req_complete_post() is now io-wq only and shouldn't be used outside
of it, i.e. it relies that io-wq holds a ref for the request as
explained in a comment below. Let's add a warning to enforce the
assumption and make sure nobody would try to do anything weird.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/1013b60c35d431d0698cafbc53c06f5917348c20.1712331455.git.asml.silence@gmail.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Ming Lei [Fri, 5 Apr 2024 15:50:02 +0000 (16:50 +0100)]
io_uring: kill dead code in io_req_complete_post
Since commit
8f6c829491fe ("io_uring: remove struct io_tw_state::locked"),
io_req_complete_post() is only called from io-wq submit work, where the
request reference is guaranteed to be grabbed and won't drop to zero
in io_req_complete_post().
Kill the dead code, meantime add req_ref_put() to put the reference.
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/1d8297e2046553153e763a52574f0e0f4d512f86.1712331455.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 29 Mar 2024 23:22:27 +0000 (17:22 -0600)]
io_uring/kbuf: remove dead define
We no longer use IO_BUFFER_LIST_BUF_PER_PAGE, kill it.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Fri, 29 Mar 2024 23:19:45 +0000 (17:19 -0600)]
io_uring: fix warnings on shadow variables
There are a few of those:
io_uring/fdinfo.c:170:16: warning: declaration shadows a local variable [-Wshadow]
170 | struct file *f = io_file_from_index(&ctx->file_table, i);
| ^
io_uring/fdinfo.c:53:67: note: previous declaration is here
53 | __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
| ^
io_uring/cancel.c:187:25: warning: declaration shadows a local variable [-Wshadow]
187 | struct io_uring_task *tctx = node->task->io_uring;
| ^
io_uring/cancel.c:166:31: note: previous declaration is here
166 | struct io_uring_task *tctx,
| ^
io_uring/register.c:371:25: warning: declaration shadows a local variable [-Wshadow]
371 | struct io_uring_task *tctx = node->task->io_uring;
| ^
io_uring/register.c:312:24: note: previous declaration is here
312 | struct io_uring_task *tctx = NULL;
| ^
and a simple cleanup gets rid of them. For the fdinfo case, make a
distinction between the file being passed in (for the ring), and the
registered files we iterate. For the other two cases, just get rid of
shadowed variable, there's no reason to have a new one.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 27 Mar 2024 20:59:09 +0000 (14:59 -0600)]
io_uring: move mapping/allocation helpers to a separate file
Move the related code from io_uring.c into memmap.c. No functional
changes in this patch, just cleaning it up a bit now that the full
transition is done.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 13 Mar 2024 21:01:03 +0000 (15:01 -0600)]
io_uring: use unpin_user_pages() where appropriate
There are a few cases of open-rolled loops around unpin_user_page(), use
the generic helper instead.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 13 Mar 2024 02:24:21 +0000 (20:24 -0600)]
io_uring/kbuf: use vm_insert_pages() for mmap'ed pbuf ring
Rather than use remap_pfn_range() for this and manually free later,
switch to using vm_insert_page() and have it Just Work.
This requires a bit of effort on the mmap lookup side, as the ctx
uring_lock isn't held, which otherwise protects buffer_lists from being
torn down, and it's not safe to grab from mmap context that would
introduce an ABBA deadlock between the mmap lock and the ctx uring_lock.
Instead, lookup the buffer_list under RCU, as the the list is RCU freed
already. Use the existing reference count to determine whether it's
possible to safely grab a reference to it (eg if it's not zero already),
and drop that reference when done with the mapping. If the mmap
reference is the last one, the buffer_list and the associated memory can
go away, since the vma insertion has references to the inserted pages at
that point.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 12 Mar 2024 16:42:27 +0000 (10:42 -0600)]
io_uring/kbuf: vmap pinned buffer ring
This avoids needing to care about HIGHMEM, and it makes the buffer
indexing easier as both ring provided buffer methods are now virtually
mapped in a contigious fashion.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 13 Mar 2024 20:58:14 +0000 (14:58 -0600)]
io_uring: unify io_pin_pages()
Move it into io_uring.c where it belongs, and use it in there as well
rather than have two implementations of this.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 13 Mar 2024 20:10:40 +0000 (14:10 -0600)]
io_uring: use vmap() for ring mapping
This is the last holdout which does odd page checking, convert it to
vmap just like what is done for the non-mmap path.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 13 Mar 2024 15:56:14 +0000 (09:56 -0600)]
io_uring: get rid of remap_pfn_range() for mapping rings/sqes
Rather than use remap_pfn_range() for this and manually free later,
switch to using vm_insert_pages() and have it Just Work.
If possible, allocate a single compound page that covers the range that
is needed. If that works, then we can just use page_address() on that
page. If we fail to get a compound page, allocate single pages and use
vmap() to map them into the kernel virtual address space.
This just covers the rings/sqes, the other remaining user of the mmap
remap_pfn_range() user will be converted separately. Once that is done,
we can kill the old alloc/free code.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Sat, 16 Mar 2024 13:21:43 +0000 (07:21 -0600)]
mm: add nommu variant of vm_insert_pages()
An identical one exists for vm_insert_page(), add one for
vm_insert_pages() to avoid needing to check for CONFIG_MMU in code using
it.
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Gabriel Krisman Bertazi [Thu, 28 Mar 2024 21:09:35 +0000 (17:09 -0400)]
io_uring: Avoid anonymous enums in io_uring uapi
While valid C, anonymous enums confuse Cython (Python to C translator),
as reported by Ritesh (YoSTEALTH) [1] . Since people rely on it when
building against liburing and we want to keep this header in sync with
the library version, let's name the existing enums in the uapi header.
[1] https://github.com/cython/cython/issues/3240
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/20240328210935.25640-1-krisman@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 26 Mar 2024 00:53:33 +0000 (18:53 -0600)]
io_uring: use the right type for work_llist empty check
io_task_work_pending() uses wq_list_empty() on ctx->work_llist, but it's
not an io_wq_work_list, it's a struct llist_head. They both have
->first as head-of-list, and it turns out the checks are identical. But
be proper and use the right helper.
Fixes: dac6a0eae793 ("io_uring: ensure iopoll runs local task work as well")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Joel Granados [Thu, 28 Mar 2024 15:57:53 +0000 (16:57 +0100)]
io_uring: Remove the now superfluous sentinel elements from ctl_table array
This commit comes at the tail end of a greater effort to remove the
empty elements at the end of the ctl_table arrays (sentinels) which will
reduce the overall build time size of the kernel and run time memory
bloat by ~64 bytes per sentinel (further information Link :
https://lore.kernel.org/all/ZO5Yx5JFogGi%2FcBo@bombadil.infradead.org/)
Remove sentinel element from kernel_io_uring_disabled_table
Signed-off-by: Joel Granados <j.granados@samsung.com>
Link: https://lore.kernel.org/r/20240328-jag-sysctl_remset_misc-v1-6-47c1463b3af2@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jiapeng Chong [Thu, 28 Mar 2024 02:23:24 +0000 (10:23 +0800)]
io_uring: Remove unused function
The function are defined in the io_uring.c file, but not called
elsewhere, so delete the unused function.
io_uring/io_uring.c:646:20: warning: unused function '__io_cq_unlock'.
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=8660
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240328022324.78029-1-jiapeng.chong@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Wed, 27 Mar 2024 04:13:41 +0000 (22:13 -0600)]
io_uring: re-arrange Makefile order
The object list is a bit of a mess, with core and opcode files mixed in.
Re-arrange it so that we have the core bits first, and then opcode
specific files after that.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 26 Mar 2024 01:07:22 +0000 (19:07 -0600)]
io_uring: refill request cache in memory order
The allocator will generally return memory in order, but
__io_alloc_req_refill() then adds them to a stack and we'll extract them
in the opposite order. This obviously isn't a huge deal, but:
1) it makes debugging easier when they are in order
2) keeping them in-order is the right thing to do
3) reduces the code for adding them to the stack
Just add them in reverse to the stack.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Thu, 21 Mar 2024 13:53:07 +0000 (07:53 -0600)]
io_uring/poll: shrink alloc cache size to 32
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>
Jens Axboe [Wed, 20 Mar 2024 21:19:44 +0000 (15:19 -0600)]
io_uring/alloc_cache: switch to array based caching
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>
Jens Axboe [Tue, 19 Mar 2024 02:48:38 +0000 (20:48 -0600)]
io_uring: drop ->prep_async()
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>
Jens Axboe [Wed, 20 Mar 2024 21:23:47 +0000 (15:23 -0600)]
io_uring/uring_cmd: defer SQE copying until it's needed
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>
Jens Axboe [Tue, 19 Mar 2024 02:41:58 +0000 (20:41 -0600)]
io_uring/uring_cmd: switch to always allocating async data
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>
Jens Axboe [Tue, 19 Mar 2024 02:37:22 +0000 (20:37 -0600)]
io_uring/net: move connect to always using async data
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>
Jens Axboe [Mon, 18 Mar 2024 22:31:44 +0000 (16:31 -0600)]
io_uring/rw: add iovec recycling
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>
Jens Axboe [Sat, 23 Mar 2024 02:41:18 +0000 (20:41 -0600)]
io_uring/rw: cleanup retry path
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>
Jens Axboe [Mon, 18 Mar 2024 22:25:58 +0000 (16:25 -0600)]
io_uring: get rid of struct io_rw_state
A separate state struct is not needed anymore, just fold it in with
io_async_rw.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 18 Mar 2024 22:13:01 +0000 (16:13 -0600)]
io_uring/rw: always setup io_async_rw for read/write requests
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>
Jens Axboe [Mon, 18 Mar 2024 19:52:42 +0000 (13:52 -0600)]
io_uring/net: drop 'kmsg' parameter from io_req_msg_cleanup()
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>
Jens Axboe [Sat, 16 Mar 2024 21:33:53 +0000 (15:33 -0600)]
io_uring/net: add iovec recycling
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>
Jens Axboe [Thu, 21 Mar 2024 01:09:50 +0000 (19:09 -0600)]
io_uring/net: remove (now) dead code in io_netmsg_recycle()
All net commands have async data at this point, there's no reason to
check if this is the case or not.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Mon, 18 Mar 2024 16:07:37 +0000 (10:07 -0600)]
io_uring: kill io_msg_alloc_async_prep()
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>
Jens Axboe [Mon, 18 Mar 2024 14:09:47 +0000 (08:09 -0600)]
io_uring/net: get rid of ->prep_async() for send side
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>
Jens Axboe [Mon, 18 Mar 2024 13:36:03 +0000 (07:36 -0600)]
io_uring/net: get rid of ->prep_async() for receive side
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>
Jens Axboe [Fri, 12 Apr 2024 18:39:54 +0000 (12:39 -0600)]
io_uring/net: always set kmsg->msg.msg_control_user before issue
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>
Jens Axboe [Sat, 16 Mar 2024 23:26:09 +0000 (17:26 -0600)]
io_uring/net: always setup an io_async_msghdr
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>
Jens Axboe [Tue, 12 Mar 2024 15:38:08 +0000 (09:38 -0600)]
io_uring/net: unify cleanup handling
Now that recv/recvmsg both do the same cleanup, put it in the retry and
finish handlers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 5 Mar 2024 22:39:16 +0000 (15:39 -0700)]
io_uring/net: switch io_recv() to using io_async_msghdr
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>
Jens Axboe [Tue, 5 Mar 2024 16:34:21 +0000 (09:34 -0700)]
io_uring/net: switch io_send() and io_send_zc() to using io_async_msghdr
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>
Jens Axboe [Sun, 17 Mar 2024 00:23:44 +0000 (18:23 -0600)]
io_uring/alloc_cache: shrink default max entries from 512 to 128
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>
Jens Axboe [Sat, 16 Mar 2024 17:10:21 +0000 (11:10 -0600)]
io_uring: remove timeout/poll specific cancelations
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>
Jens Axboe [Mon, 18 Mar 2024 16:41:25 +0000 (10:41 -0600)]
io_uring: flush delayed fallback task_work in cancelation
Just like we run the inline task_work, ensure we also factor in and
run the fallback task_work.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:35 +0000 (22:00 +0000)]
io_uring: clean up io_lockdep_assert_cq_locked
Move CONFIG_PROVE_LOCKING checks inside of io_lockdep_assert_cq_locked()
and kill the else branch.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/bbf33c429c9f6d7207a8fe66d1a5866ec2c99850.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:34 +0000 (22:00 +0000)]
io_uring: refactor io_req_complete_post()
Make io_req_complete_post() to push all IORING_SETUP_IOPOLL requests
to task_work, it's much cleaner and should normally happen. We couldn't
do it before because there was a possibility of looping in
complete_post() -> tw -> complete_post() -> ...
Also, unexport the function and inline __io_req_complete_post().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/ea19c032ace3e0dd96ac4d991a063b0188037014.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:33 +0000 (22:00 +0000)]
io_uring: remove current check from complete_post
task_work execution is now always locked, and we shouldn't get into
io_req_complete_post() from them. That means that complete_post() is
always called out of the original task context and we don't even need to
check current.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/24ec27f27db0d8f58c974d8118dca1d345314ddc.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:32 +0000 (22:00 +0000)]
io_uring: get rid of intermediate aux cqe caches
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>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:31 +0000 (22:00 +0000)]
io_uring: refactor io_fill_cqe_req_aux
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>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:30 +0000 (22:00 +0000)]
io_uring: remove struct io_tw_state::locked
ctx is always locked for task_work now, so get rid of struct
io_tw_state::locked. Note I'm stopping one step before removing
io_tw_state altogether, which is not empty, because it still serves the
purpose of indicating which function is a tw callback and forcing users
not to invoke them carelessly out of a wrong context. The removal can
always be done later.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/e95e1ea116d0bfa54b656076e6a977bc221392a4.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:29 +0000 (22:00 +0000)]
io_uring: force tw ctx locking
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>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:28 +0000 (22:00 +0000)]
io_uring/rw: avoid punting to io-wq directly
kiocb_done() should care to specifically redirecting requests to io-wq.
Remove the hopping to tw to then queue an io-wq, return -EAGAIN and let
the core code io_uring handle offloading.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/413564e550fe23744a970e1783dfa566291b0e6f.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jens Axboe [Tue, 19 Mar 2024 23:10:50 +0000 (17:10 -0600)]
nvme/io_uring: use helper for polled completions
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>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:26 +0000 (22:00 +0000)]
io_uring/cmd: document some uring_cmd related helpers
Add comments warning users that they're only allowed to pass issue_flags
that were given from io_uring.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/82ff8a45f2c3eb5f3a04a33f0692e5e4a1320455.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:25 +0000 (22:00 +0000)]
io_uring/cmd: fix tw <-> issue_flags conversion
!IO_URING_F_UNLOCKED does not translate to availability of the deferred
completion infra, IO_URING_F_COMPLETE_DEFER does, that what we should
pass and look for to use io_req_complete_defer() and other variants.
Luckily, it's not a real problem as two wrongs actually made it right,
at least as far as io_uring_cmd_work() goes.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/aef76d34fe9410df8ecc42a14544fd76cd9d8b9e.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:24 +0000 (22:00 +0000)]
io_uring/cmd: kill one issue_flags to tw conversion
io_uring cmd converts struct io_tw_state to issue_flags and later back
to io_tw_state, it's awfully ill-fated, not to mention that intermediate
issue_flags state is not correct.
Get rid of the last conversion, drag through tw everything that came
with IO_URING_F_UNLOCKED, and replace io_req_complete_defer() with a
direct call to io_req_complete_defer(), at least for the time being.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/c53fa3df749752bd058cf6f824a90704822d6bcc.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pavel Begunkov [Mon, 18 Mar 2024 22:00:23 +0000 (22:00 +0000)]
io_uring/cmd: move io_uring_try_cancel_uring_cmd()
io_uring_try_cancel_uring_cmd() is a part of the cmd handling so let's
move it closer to all cmd bits into uring_cmd.c
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/43a3937af4933655f0fd9362c381802f804f43de.1710799188.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Linus Torvalds [Sun, 14 Apr 2024 20:38:39 +0000 (13:38 -0700)]
Linux 6.9-rc4
Linus Torvalds [Sun, 14 Apr 2024 18:41:51 +0000 (11:41 -0700)]
Merge tag 'pull-sysfs-annotation-fix' of git://git./linux/kernel/git/viro/vfs
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
Linus Torvalds [Sun, 14 Apr 2024 17:48:51 +0000 (10:48 -0700)]
Merge tag 'x86-urgent-2024-04-14' of git://git./linux/kernel/git/tip/tip
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
Linus Torvalds [Sun, 14 Apr 2024 17:32:22 +0000 (10:32 -0700)]
Merge tag 'timers-urgent-2024-04-14' of git://git./linux/kernel/git/tip/tip
Pull timer fixes from Ingo Molnar:
- Address a (valid) W=1 build warning
- Fix timer self-tests
- Annotate a KCSAN warning wrt. accesses to the tick_do_timer_cpu
global variable
- Address a !CONFIG_BUG build warning
* tag 'timers-urgent-2024-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
selftests: kselftest: Fix build failure with NOLIBC
selftests: timers: Fix abs() warning in posix_timers test
selftests: kselftest: Mark functions that unconditionally call exit() as __noreturn
selftests: timers: Fix posix_timers ksft_print_msg() warning
selftests: timers: Fix valid-adjtimex signed left-shift undefined behavior
bug: Fix no-return-statement warning with !CONFIG_BUG
timekeeping: Use READ/WRITE_ONCE() for tick_do_timer_cpu
selftests/timers/posix_timers: Reimplement check_timer_distribution()
irqflags: Explicitly ignore lockdep_hrtimer_exit() argument
Linus Torvalds [Sun, 14 Apr 2024 17:26:27 +0000 (10:26 -0700)]
Merge tag 'perf-urgent-2024-04-14' of git://git./linux/kernel/git/tip/tip
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
Linus Torvalds [Sun, 14 Apr 2024 17:13:56 +0000 (10:13 -0700)]
Merge tag 'locking-urgent-2024-04-14' of git://git./linux/kernel/git/tip/tip
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
Linus Torvalds [Sun, 14 Apr 2024 17:12:34 +0000 (10:12 -0700)]
Merge tag 'irq-urgent-2024-04-14' of git://git./linux/kernel/git/tip/tip
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
Linus Torvalds [Sun, 14 Apr 2024 17:05:59 +0000 (10:05 -0700)]
Merge tag 'for_linus' of git://git./linux/kernel/git/mst/vhost
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()
Linus Torvalds [Sun, 14 Apr 2024 17:02:40 +0000 (10:02 -0700)]
Merge tag 'dma-maping-6.9-2024-04-14' of git://git.infradead.org/users/hch/dma-mapping
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
Amir Goldstein [Fri, 5 Apr 2024 14:56:35 +0000 (17:56 +0300)]
kernfs: annotate different lockdep class for of->mutex of writable files
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: 0fedefd4c4e3 ("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>
Linus Torvalds [Sat, 13 Apr 2024 17:27:58 +0000 (10:27 -0700)]
Merge tag 'ata-6.9-rc4' of git://git./linux/kernel/git/libata/linux
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
Linus Torvalds [Sat, 13 Apr 2024 17:25:32 +0000 (10:25 -0700)]
Merge tag 'zonefs-6.9-rc4' of git://git./linux/kernel/git/dlemoal/zonefs
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
Linus Torvalds [Sat, 13 Apr 2024 17:10:18 +0000 (10:10 -0700)]
Merge tag 'v6.9-rc3-SMB3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6
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()
Igor Pylypiv [Thu, 11 Apr 2024 20:12:24 +0000 (20:12 +0000)]
ata: libata-core: Allow command duration limits detection for ACS-4 drives
Even though the command duration limits (CDL) feature was first added
in ACS-5 (major version 12), there are some ACS-4 (major version 11)
drives that implement CDL as well.
IDENTIFY_DEVICE, SUPPORTED_CAPABILITIES, and CURRENT_SETTINGS log pages
are mandatory in the ACS-4 standard so it should be safe to read these
log pages on older drives implementing the ACS-4 standard.
Fixes: 62e4a60e0cdb ("scsi: ata: libata: Detect support for command duration limits")
Cc: stable@vger.kernel.org
Signed-off-by: Igor Pylypiv <ipylypiv@google.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Damien Le Moal [Thu, 11 Apr 2024 23:41:15 +0000 (08:41 +0900)]
ata: libata-scsi: Fix ata_scsi_dev_rescan() error path
Commit
0c76106cb975 ("scsi: sd: Fix TCG OPAL unlock on system resume")
incorrectly handles failures of scsi_resume_device() in
ata_scsi_dev_rescan(), leading to a double call to
spin_unlock_irqrestore() to unlock a device port. Fix this by redefining
the goto labels used in case of errors and only unlock the port
scsi_scan_mutex when scsi_resume_device() fails.
Bug found with the Smatch static checker warning:
drivers/ata/libata-scsi.c:4774 ata_scsi_dev_rescan()
error: double unlocked 'ap->lock' (orig line 4757)
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: 0c76106cb975 ("scsi: sd: Fix TCG OPAL unlock on system resume")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Linus Torvalds [Fri, 12 Apr 2024 20:08:39 +0000 (13:08 -0700)]
Merge tag 'arm64-fixes' of git://git./linux/kernel/git/arm64/linux
Pull arm64 fix from Catalin Marinas:
"Fix the TLBI RANGE operand calculation causing live migration under
KVM/arm64 to miss dirty pages due to stale TLB entries"
* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
arm64: tlb: Fix TLBI RANGE operand
Linus Torvalds [Fri, 12 Apr 2024 20:02:27 +0000 (13:02 -0700)]
Merge tag 'soc-fixes-6.9-1' of git://git./linux/kernel/git/soc/soc
Pull SoC fixes from Arnd Bergmann:
"The device tree changes this time are all for NXP i.MX platforms,
addressing issues with clocks and regulators on i.MX7 and i.MX8.
The old OMAP2 based Nokia N8x0 tablet get a couple of code fixes for
regressions that came in.
The ARM SCMI and FF-A firmware interfaces get a couple of minor bug
fixes.
A regression fix for RISC-V cache management addresses a problem with
probe order on Sifive cores"
* tag 'soc-fixes-6.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (23 commits)
MAINTAINERS: Change Krzysztof Kozlowski's email address
arm64: dts: imx8qm-ss-dma: fix can lpcg indices
arm64: dts: imx8-ss-dma: fix can lpcg indices
arm64: dts: imx8-ss-dma: fix adc lpcg indices
arm64: dts: imx8-ss-dma: fix pwm lpcg indices
arm64: dts: imx8-ss-dma: fix spi lpcg indices
arm64: dts: imx8-ss-conn: fix usb lpcg indices
arm64: dts: imx8-ss-lsio: fix pwm lpcg indices
ARM: dts: imx7s-warp: Pass OV2680 link-frequencies
ARM: dts: imx7-mba7: Use 'no-mmc' property
arm64: dts: imx8-ss-conn: fix usdhc wrong lpcg clock order
arm64: dts: freescale: imx8mp-venice-gw73xx-2x: fix USB vbus regulator
arm64: dts: freescale: imx8mp-venice-gw72xx-2x: fix USB vbus regulator
cache: sifive_ccache: Partially convert to a platform driver
firmware: arm_scmi: Make raw debugfs entries non-seekable
firmware: arm_scmi: Fix wrong fastchannel initialization
firmware: arm_ffa: Fix the partition ID check in ffa_notification_info_get()
ARM: OMAP2+: fix USB regression on Nokia N8x0
mmc: omap: restore original power up/down steps
mmc: omap: fix deferred probe
...
Linus Torvalds [Fri, 12 Apr 2024 19:56:19 +0000 (12:56 -0700)]
Merge tag 'iommu-fixes-v6.9-rc3' of git://git./linux/kernel/git/joro/iommu
Pull iommu fixes from Joerg Roedel:
- Intel VT-d Fixes:
- Allocate local memory for PRQ page
- Fix WARN_ON in iommu probe path
- Fix wrong use of pasid config
- AMD IOMMU Fixes:
- Lock inversion fix
- Log message severity fix
- Disable SNP when v2 page-tables are used
- Mediatek driver:
- Fix module autoloading
* tag 'iommu-fixes-v6.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/amd: Change log message severity
iommu/vt-d: Fix WARN_ON in iommu probe path
iommu/vt-d: Allocate local memory for page request queue
iommu/vt-d: Fix wrong use of pasid config
iommu: mtk: fix module autoloading
iommu/amd: Do not enable SNP when V2 page table is enabled
iommu/amd: Fix possible irq lock inversion dependency issue
Linus Torvalds [Fri, 12 Apr 2024 19:47:48 +0000 (12:47 -0700)]
Merge tag 'pci-v6.9-fixes-1' of git://git./linux/kernel/git/pci/pci
Pull pci fixes from Bjorn Helgaas:
- Revert a quirk that prevented Secondary Bus Reset for LSI / Agere
FW643.
We thought the device was broken, but the reset does work correctly
on other platforms, and the reset avoids leaking data out of VMs
(Bjorn Helgaas)
- Update MAINTAINERS to reflect that Gustavo Pimentel is no longer
reachable (Manivannan Sadhasivam)
* tag 'pci-v6.9-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci:
Revert "PCI: Mark LSI FW643 to avoid bus reset"
MAINTAINERS: Drop Gustavo Pimentel as PCI DWC Maintainer
Linus Torvalds [Fri, 12 Apr 2024 17:22:33 +0000 (10:22 -0700)]
Merge tag 'block-6.9-
20240412' of git://git.kernel.dk/linux
Pull block fixes from Jens Axboe:
- MD pull request via Song:
- UAF fix (Yu)
- Avoid out-of-bounds shift in blk-iocost (Rik)
- Fix for q->blkg_list corruption (Ming)
- Relax virt boundary mask/size segment checking (Ming)
* tag 'block-6.9-
20240412' of git://git.kernel.dk/linux:
block: fix that blk_time_get_ns() doesn't update time after schedule
block: allow device to have both virt_boundary_mask and max segment size
block: fix q->blkg_list corruption during disk rebind
blk-iocost: avoid out of bounds shift
raid1: fix use-after-free for original bio in raid1_write_request()
Linus Torvalds [Fri, 12 Apr 2024 17:19:36 +0000 (10:19 -0700)]
Merge tag 'io_uring-6.9-
20240412' of git://git.kernel.dk/linux
Pull io_uring fixes from Jens Axboe:
- Fix for sigmask restoring while waiting for events (Alexey)
- Typo fix in comment (Haiyue)
- Fix for a msg_control retstore on SEND_ZC retries (Pavel)
* tag 'io_uring-6.9-
20240412' of git://git.kernel.dk/linux:
io-uring: correct typo in comment for IOU_F_TWQ_LAZY_WAKE
io_uring/net: restore msg_control on sendzc retry
io_uring: Fix io_cqring_wait() not restoring sigmask on get_timespec64() failure
Linus Torvalds [Fri, 12 Apr 2024 17:15:46 +0000 (10:15 -0700)]
Merge tag 'ceph-for-6.9-rc4' of https://github.com/ceph/ceph-client
Pull ceph fixes from Ilya Dryomov:
"Two CephFS fixes marked for stable and a MAINTAINERS update"
* tag 'ceph-for-6.9-rc4' of https://github.com/ceph/ceph-client:
MAINTAINERS: remove myself as a Reviewer for Ceph
ceph: switch to use cap_delay_lock for the unlink delay list
ceph: redirty page before returning AOP_WRITEPAGE_ACTIVATE
Linus Torvalds [Fri, 12 Apr 2024 17:05:10 +0000 (10:05 -0700)]
Kconfig: add some hidden tabs on purpose
Commit
d96c36004e31 ("tracing: Fix FTRACE_RECORD_RECURSION_SIZE Kconfig
entry") removed a hidden tab because it apparently showed breakage in
some third-party kernel config parsing tool.
It wasn't clear what tool it was, but let's make sure it gets fixed.
Because if you can't parse tabs as whitespace, you should not be parsing
the kernel Kconfig files.
In fact, let's make such breakage more obvious than some esoteric ftrace
record size option. If you can't parse tabs, you can't have page sizes.
Yes, tab-vs-space confusion is sadly a traditional Unix thing, and
'make' is famous for being broken in this regard. But no, that does not
mean that it's ok.
I'd add more random tabs to our Kconfig files, but I don't want to make
things uglier than necessary. But it *might* bbe necessary if it turns
out we see more of this kind of silly tooling.
Fixes: d96c36004e31 ("tracing: Fix FTRACE_RECORD_RECURSION_SIZE Kconfig entry")
Link: https://lore.kernel.org/lkml/CAHk-=wj-hLLN_t_m5OL4dXLaxvXKy_axuoJYXif7iczbfgAevQ@mail.gmail.com/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds [Fri, 12 Apr 2024 16:02:24 +0000 (09:02 -0700)]
Merge tag 'trace-v6.9-rc3' of git://git./linux/kernel/git/trace/linux-trace
Pull tracing fixes from Steven Rostedt:
- Fix the buffer_percent accounting as it is dependent on three
variables:
1) pages_read - number of subbuffers read
2) pages_lost - number of subbuffers lost due to overwrite
3) pages_touched - number of pages that a writer entered
These three counters only increment, and to know how many active
pages there are on the buffer at any given time, the pages_read and
pages_lost are subtracted from pages_touched.
But the pages touched was incremented whenever any writer went to the
next subbuffer even if it wasn't the only one, so it was incremented
more than it should be causing the counter for how many subbuffers
currently have content incorrect, which caused the buffer_percent
that holds waiters until the ring buffer is filled to a given
percentage to wake up early.
- Fix warning of unused functions when PERF_EVENTS is not configured in
- Replace bad tab with space in Kconfig for FTRACE_RECORD_RECURSION_SIZE
- Fix to some kerneldoc function comments in eventfs code.
* tag 'trace-v6.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
ring-buffer: Only update pages_touched when a new page is touched
tracing: hide unused ftrace_event_id_fops
tracing: Fix FTRACE_RECORD_RECURSION_SIZE Kconfig entry
eventfs: Fix kernel-doc comments to functions
Linus Torvalds [Fri, 12 Apr 2024 15:46:58 +0000 (08:46 -0700)]
Merge tag 'mips-fixes_6.9_1' of git://git./linux/kernel/git/mips/linux
Pull MIPS fix from Thomas Bogendoerfer:
"Fix for syscall_get_nr() to make it work even if tracing is disabled"
* tag 'mips-fixes_6.9_1' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
MIPS: scall: Save thread_info.syscall unconditionally on entry
Linus Torvalds [Fri, 12 Apr 2024 15:27:09 +0000 (08:27 -0700)]
Merge tag 'drm-fixes-2024-04-12' of https://gitlab.freedesktop.org/drm/kernel
Pull drm fixes from Dave Airlie:
"Looks like everyone woke up after holidays, this weeks pull has a
bunch of stuff all over, 2 weeks worth of amdgpu is a lot of it, then
i915/xe have a few, a bunch of msm fixes, then some scattered driver
fixes.
I expect things will settle down for rc5.
client:
- Protect connector modes with mode_config mutex
ast:
- Fix soft lockup
host1x:
- Do not setup DMA for virtual addresses
ivpu:
- Fix deadlock in context_xa
- PCI fixes
- Fixes to error handling
nouveau:
- gsp: Fix OOB access
- Fix casting
panfrost:
- Fix error path in MMU code
qxl:
- Revert "drm/qxl: simplify qxl_fence_wait"
vmwgfx:
- Enable DMA for SEV mappings
i915:
- Couple CDCLK programming fixes
- HDCP related fix
- 4 Bigjoiner related fixes
- Fix for a circular locking around GuC on reset+wedged case
xe:
- Fix double display mutex initializations
- Fix u32 -> u64 implicit conversions
- Fix RING_CONTEXT_CONTROL not marked as masked
msm:
- DP refcount leak fix on disconnect
- Add missing newlines to prints in msm_fb and msm_kms
- fix dpu debugfs entry permissions
- Fix the interface table for the catalog of X1E80100
- fix irq message printing
- Bindings fix to add DP node as child of mdss for mdss node
- Minor typo fix in DP driver API which handles port status change
- fix CHRASHDUMP_READ()
- fix HHB (highest bank bit) for a619 to fix UBWC corruption
amdgpu:
- GPU reset fixes
- Fix some confusing logging
- UMSCH fix
- Aborted suspend fix
- DCN 3.5 fixes
- S4 fix
- MES logging fixes
- SMU 14 fixes
- SDMA 4.4.2 fix
- KASAN fix
- SMU 13.0.10 fix
- VCN partition fix
- GFX11 fixes
- DWB fixes
- Plane handling fix
- FAMS fix
- DCN 3.1.6 fix
- VSC SDP fixes
- OLED panel fix
- GFX 11.5 fix
amdkfd:
- GPU reset fixes
- fix ioctl integer overflow"
* tag 'drm-fixes-2024-04-12' of https://gitlab.freedesktop.org/drm/kernel: (65 commits)
amdkfd: use calloc instead of kzalloc to avoid integer overflow
drm/xe: Label RING_CONTEXT_CONTROL as masked
drm/xe/xe_migrate: Cast to output precision before multiplying operands
drm/xe/hwmon: Cast result to output precision on left shift of operand
drm/xe/display: Fix double mutex initialization
drm/amdgpu: differentiate external rev id for gfx 11.5.0
drm/amd/display: Adjust dprefclk by down spread percentage.
drm/amd/display: Set VSC SDP Colorimetry same way for MST and SST
drm/amd/display: Program VSC SDP colorimetry for all DP sinks >= 1.4
drm/amd/display: fix disable otg wa logic in DCN316
drm/amd/display: Do not recursively call manual trigger programming
drm/amd/display: always reset ODM mode in context when adding first plane
drm/amdgpu: fix incorrect number of active RBs for gfx11
drm/amd/display: Return max resolution supported by DWB
amd/amdkfd: sync all devices to wait all processes being evicted
drm/amdgpu: clear set_q_mode_offs when VM changed
drm/amdgpu: Fix VCN allocation in CPX partition
drm/amd/pm: fix the high voltage issue after unload
drm/amd/display: Skip on writeback when it's not applicable
drm/amdgpu: implement IRQ_STATE_ENABLE for SDMA v4.4.2
...
Oleg Nesterov [Fri, 12 Apr 2024 12:35:36 +0000 (14:35 +0200)]
selftests: kselftest: Fix build failure with NOLIBC
As Mark explains ksft_min_kernel_version() can't be compiled with nolibc,
it doesn't implement uname().
Fixes: 6d029c25b71f ("selftests/timers/posix_timers: Reimplement check_timer_distribution()")
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240412123536.GA32444@redhat.com
Closes: https://lore.kernel.org/all/f0523b3a-ea08-4615-b0fb-5b504a2d39df@sirena.org.uk/
Yu Kuai [Thu, 11 Apr 2024 03:23:48 +0000 (11:23 +0800)]
block: fix that blk_time_get_ns() doesn't update time after schedule
While monitoring the throttle time of IO from iocost, it's found that
such time is always zero after the io_schedule() from ioc_rqos_throttle,
for example, with the following debug patch:
+ printk("%s-%d: %s enter %llu\n", current->comm, current->pid, __func__, blk_time_get_ns());
while (true) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (wait.committed)
break;
io_schedule();
}
+ printk("%s-%d: %s exit %llu\n", current->comm, current->pid, __func__, blk_time_get_ns());
It can be observerd that blk_time_get_ns() always return the same time:
[ 1068.096579] fio-1268: ioc_rqos_throttle enter
1067901962288
[ 1068.272587] fio-1268: ioc_rqos_throttle exit
1067901962288
[ 1068.274389] fio-1268: ioc_rqos_throttle enter
1067901962288
[ 1068.472690] fio-1268: ioc_rqos_throttle exit
1067901962288
[ 1068.474485] fio-1268: ioc_rqos_throttle enter
1067901962288
[ 1068.672656] fio-1268: ioc_rqos_throttle exit
1067901962288
[ 1068.674451] fio-1268: ioc_rqos_throttle enter
1067901962288
[ 1068.872655] fio-1268: ioc_rqos_throttle exit
1067901962288
And I think the root cause is that 'PF_BLOCK_TS' is always cleared
by blk_flush_plug() before scheduel(), hence blk_plug_invalidate_ts()
will never be called:
blk_time_get_ns
plug->cur_ktime = ktime_get_ns();
current->flags |= PF_BLOCK_TS;
io_schedule:
io_schedule_prepare
blk_flush_plug
__blk_flush_plug
/* the flag is cleared, while time is not */
current->flags &= ~PF_BLOCK_TS;
schedule
sched_update_worker
/* the flag is not set, hence plug->cur_ktime is not cleared */
if (tsk->flags & PF_BLOCK_TS)
blk_plug_invalidate_ts()
blk_time_get_ns
/* got the time stashed before schedule */
return plug->cur_ktime;
Fix the problem by clearing cached time in __blk_flush_plug().
Fixes: 06b23f92af87 ("block: update cached timestamp post schedule/preemption")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240411032349.3051233-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
John Stultz [Wed, 10 Apr 2024 23:26:30 +0000 (16:26 -0700)]
selftests: timers: Fix abs() warning in posix_timers test
Building with clang results in the following warning:
posix_timers.c:69:6: warning: absolute value function 'abs' given an
argument of type 'long long' but has parameter of type 'int' which may
cause truncation of value [-Wabsolute-value]
if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
^
So switch to using llabs() instead.
Fixes: 0bc4b0cf1570 ("selftests: add basic posix timers selftests")
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240410232637.4135564-3-jstultz@google.com
Nathan Chancellor [Thu, 11 Apr 2024 18:45:40 +0000 (11:45 -0700)]
selftests: kselftest: Mark functions that unconditionally call exit() as __noreturn
After commit
6d029c25b71f ("selftests/timers/posix_timers: Reimplement
check_timer_distribution()"), clang warns:
tools/testing/selftests/timers/../kselftest.h:398:6: warning: variable 'major' is used uninitialized whenever '||' condition is true [-Wsometimes-uninitialized]
398 | if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
| ^~~~~~~~~~~~
tools/testing/selftests/timers/../kselftest.h:401:9: note: uninitialized use occurs here
401 | return major > min_major || (major == min_major && minor >= min_minor);
| ^~~~~
tools/testing/selftests/timers/../kselftest.h:398:6: note: remove the '||' if its condition is always false
398 | if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
| ^~~~~~~~~~~~~~~
tools/testing/selftests/timers/../kselftest.h:395:20: note: initialize the variable 'major' to silence this warning
395 | unsigned int major, minor;
| ^
| = 0
This is a false positive because if uname() fails, ksft_exit_fail_msg()
will be called, which unconditionally calls exit(), a noreturn function.
However, clang does not know that ksft_exit_fail_msg() will call exit() at
the point in the pipeline that the warning is emitted because inlining has
not occurred, so it assumes control flow will resume normally after
ksft_exit_fail_msg() is called.
Make it clear to clang that all of the functions that call exit()
unconditionally in kselftest.h are noreturn transitively by marking them
explicitly with '__attribute__((__noreturn__))', which clears up the
warning above and any future warnings that may appear for the same reason.
Fixes: 6d029c25b71f ("selftests/timers/posix_timers: Reimplement check_timer_distribution()")
Reported-by: John Stultz <jstultz@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240411-mark-kselftest-exit-funcs-noreturn-v1-1-b027c948f586@kernel.org
Closes: https://lore.kernel.org/all/20240410232637.4135564-2-jstultz@google.com/
John Stultz [Wed, 10 Apr 2024 23:26:28 +0000 (16:26 -0700)]
selftests: timers: Fix posix_timers ksft_print_msg() warning
After commit
6d029c25b71f ("selftests/timers/posix_timers: Reimplement
check_timer_distribution()") the following warning occurs when building
with an older gcc:
posix_timers.c:250:2: warning: format not a string literal and no format arguments [-Wformat-security]
250 | ksft_print_msg(errmsg);
| ^~~~~~~~~~~~~~
Fix this up by changing it to ksft_print_msg("%s", errmsg)
Fixes: 6d029c25b71f ("selftests/timers/posix_timers: Reimplement check_timer_distribution()")
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Justin Stitt <justinstitt@google.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240410232637.4135564-1-jstultz@google.com
Vasant Hegde [Wed, 10 Apr 2024 10:16:43 +0000 (10:16 +0000)]
iommu/amd: Change log message severity
Use consistent log severity (pr_warn) to log all messages in SNP
enable path.
Suggested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20240410101643.32309-1-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Lu Baolu [Thu, 11 Apr 2024 03:07:44 +0000 (11:07 +0800)]
iommu/vt-d: Fix WARN_ON in iommu probe path
Commit
1a75cc710b95 ("iommu/vt-d: Use rbtree to track iommu probed
devices") adds all devices probed by the iommu driver in a rbtree
indexed by the source ID of each device. It assumes that each device
has a unique source ID. This assumption is incorrect and the VT-d
spec doesn't state this requirement either.
The reason for using a rbtree to track devices is to look up the device
with PCI bus and devfunc in the paths of handling ATS invalidation time
out error and the PRI I/O page faults. Both are PCI ATS feature related.
Only track the devices that have PCI ATS capabilities in the rbtree to
avoid unnecessary WARN_ON in the iommu probe path. Otherwise, on some
platforms below kernel splat will be displayed and the iommu probe results
in failure.
WARNING: CPU: 3 PID: 166 at drivers/iommu/intel/iommu.c:158 intel_iommu_probe_device+0x319/0xd90
Call Trace:
<TASK>
? __warn+0x7e/0x180
? intel_iommu_probe_device+0x319/0xd90
? report_bug+0x1f8/0x200
? handle_bug+0x3c/0x70
? exc_invalid_op+0x18/0x70
? asm_exc_invalid_op+0x1a/0x20
? intel_iommu_probe_device+0x319/0xd90
? debug_mutex_init+0x37/0x50
__iommu_probe_device+0xf2/0x4f0
iommu_probe_device+0x22/0x70
iommu_bus_notifier+0x1e/0x40
notifier_call_chain+0x46/0x150
blocking_notifier_call_chain+0x42/0x60
bus_notify+0x2f/0x50
device_add+0x5ed/0x7e0
platform_device_add+0xf5/0x240
mfd_add_devices+0x3f9/0x500
? preempt_count_add+0x4c/0xa0
? up_write+0xa2/0x1b0
? __debugfs_create_file+0xe3/0x150
intel_lpss_probe+0x49f/0x5b0
? pci_conf1_write+0xa3/0xf0
intel_lpss_pci_probe+0xcf/0x110 [intel_lpss_pci]
pci_device_probe+0x95/0x120
really_probe+0xd9/0x370
? __pfx___driver_attach+0x10/0x10
__driver_probe_device+0x73/0x150
driver_probe_device+0x19/0xa0
__driver_attach+0xb6/0x180
? __pfx___driver_attach+0x10/0x10
bus_for_each_dev+0x77/0xd0
bus_add_driver+0x114/0x210
driver_register+0x5b/0x110
? __pfx_intel_lpss_pci_driver_init+0x10/0x10 [intel_lpss_pci]
do_one_initcall+0x57/0x2b0
? kmalloc_trace+0x21e/0x280
? do_init_module+0x1e/0x210
do_init_module+0x5f/0x210
load_module+0x1d37/0x1fc0
? init_module_from_file+0x86/0xd0
init_module_from_file+0x86/0xd0
idempotent_init_module+0x17c/0x230
__x64_sys_finit_module+0x56/0xb0
do_syscall_64+0x6e/0x140
entry_SYSCALL_64_after_hwframe+0x71/0x79
Fixes: 1a75cc710b95 ("iommu/vt-d: Use rbtree to track iommu probed devices")
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/10689
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20240407011429.136282-1-baolu.lu@linux.intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Jacob Pan [Thu, 11 Apr 2024 03:07:43 +0000 (11:07 +0800)]
iommu/vt-d: Allocate local memory for page request queue
The page request queue is per IOMMU, its allocation should be made
NUMA-aware for performance reasons.
Fixes: a222a7f0bb6c ("iommu/vt-d: Implement page request handling")
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20240403214007.985600-1-jacob.jun.pan@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>