- 24 Jul, 2020 36 commits
-
-
Pavel Begunkov authored
As every iopoll request have a task ref, it becomes expensive to put them one by one, instead we can put several at once integrating that into io_req_free_batch(). Signed-off-by:
Pavel Begunkov <asml.silence@gmail.com> Signed-off-by:
Jens Axboe <axboe@kernel.dk>
-
Pavel Begunkov authored
put_task_struct_many() is as put_task_struct() but puts several references at once. Useful to batching it. Signed-off-by:
-
Pavel Begunkov authored
Locked and pinned memory accounting in io_{,un}account_mem() depends on having ->sqo_mm, which is NULL after a recent change for non SQPOLL'ed io_ring. That disables the accounting. Return ->sqo_mm initialisation back, and do __io_sq_thread_acquire_mm() based on IORING_SETUP_SQPOLL flag. Fixes: 8eb06d7e ("io_uring: fix missing ->mm on exit") Signed-off-by: -
Pavel Begunkov authored
io_sqe_buffer_unregister() uses cxt->sqo_mm for memory accounting, but io_ring_ctx_free() drops ->sqo_mm before leaving pinned_vm over-accounted. Postpone mm cleanup for when it's not needed anymore. Fixes: 30975825 ("io_uring: report pinned memory usage") Signed-off-by:
-
Pavel Begunkov authored
Don't implement fast path of kbuf freeing and management inlined into io_recv{,msg}(), that's error prone and duplicates handling. Replace it with a helper io_put_recv_kbuf(), which mimics io_put_rw_kbuf() in the io_read/write(). This also keeps cflags calculation in one place, removing duplication between rw and recv/send. Signed-off-by: -
Pavel Begunkov authored
Extract a common helper for cleaning up a selected buffer, this will be used shortly. By the way, correct cflags types to unsigned and, as kbufs are anyway tracked by a flag, remove useless zeroing req->rw.addr. Signed-off-by:
-
Pavel Begunkov authored
Move REQ_F_BUFFER_SELECT flag check out of io_recv_buffer_select(), and do that in its call sites That saves us from double error checking and possibly an extra function call. Signed-off-by:
-
Pavel Begunkov authored
io_clean_op() may be skipped even if there is a selected io_buffer, that's because *select_buffer() funcions never set REQ_F_NEED_CLEANUP. Trigger io_clean_op() when REQ_F_BUFFER_SELECTED is set as well, and and clear the flag if was freed out of it. Signed-off-by:
-
Pavel Begunkov authored
Instead of returning error from io_recv(), go through generic cleanup path, because it'll retain cflags for userspace. Do the same for io_send() for consistency. Signed-off-by:
-
Pavel Begunkov authored
With the return on a bad socket, kmsg is always non-null by the end of the function, prune left extra checks and initialisations. Signed-off-by:
-
Pavel Begunkov authored
Flip over "if (sock)" condition with return on error, the upper layer will take care. That change will be handy later, but already removes an extra jump from hot path. Signed-off-by:
-
Pavel Begunkov authored
Currently, file refs in struct io_submit_state are tracked with 2 vars: @has_refs -- how many refs were initially taken @used_refs -- number of refs used Replace it with a single variable counting how many refs left at the current moment. Signed-off-by:
-
Pavel Begunkov authored
RLIMIT_SIZE in needed only for execution from an io-wq context, hence move all preparations from hot path to io-wq work setup. Signed-off-by:
-
Pavel Begunkov authored
Every call to io_req_defer_prep() is prepended with allocating ->io, just do that in the function. And while we're at it, mark error paths with unlikey and replace "if (ret < 0)" with "if (ret)". There is only one change in the observable behaviour, that's instead of killing the head request right away on error, it postpones it until the link is assembled, that looks more preferable. Signed-off-by:
-
Pavel Begunkov authored
A switch in __io_clean_op() doesn't have default, it's pointless to list opcodes that doesn't do any cleanup. Remove IORING_OP_OPEN* from there. Signed-off-by:
-
Pavel Begunkov authored
The only caller of io_req_work_grab_env() is io_prep_async_work(), and they are both initialising req->work. Inline grab_env(), it's easier to keep this way, moreover there already were bugs with misplacing io_req_init_async(). Signed-off-by:
-
Pavel Begunkov authored
req->cflags is used only for defer-completion path, just use completion data to store it. With the 4 bytes from the ->sequence patch and compacting io_kiocb, this frees 8 bytes. Signed-off-by:
-
Pavel Begunkov authored
req->sequence is used only for deferred (i.e. DRAIN) requests, but initialised for every request. Remove req->sequence from io_kiocb together with its initialisation in io_init_req(). Replace it with a new field in struct io_defer_entry, that will be calculated only when needed in io_req_defer(), which is a slow path. Signed-off-by:
-
Pavel Begunkov authored
The only left user of req->list is DRAIN, hence instead of keeping a separate per request list for it, do that with old fashion non-intrusive lists allocated on demand. That's a really slow path, so that's OK. This removes req->list and so sheds 16 bytes from io_kiocb. Signed-off-by:
-
Pavel Begunkov authored
poll*() doesn't use req->list, don't init it. Signed-off-by:
-
Pavel Begunkov authored
Instead of using shared req->list, hang timeouts up on their own list entry. struct io_timeout have enough extra space for it, but if that will be a problem ->inflight_entry can reused for that. Signed-off-by:
-
Pavel Begunkov authored
As with the completion path, also use compl.list for overflowed requests. If cleaned up properly, nobody needs per-op data there anymore. Signed-off-by:
-
Pavel Begunkov authored
req->inflight_entry is used to track requests that grabbed files_struct. Let's share it with iopoll list, because the only iopoll'ed ops are reads and writes, which don't need a file table. Signed-off-by:
-
Pavel Begunkov authored
It supports both polling and I/O polling. Rename ctx->poll to clearly show that it's only in I/O poll case. Signed-off-by:
-
Pavel Begunkov authored
Calling io_req_complete(req) means that the request is done, and there is nothing left but to clean it up. That also means that per-op data after that should not be used, so we're free to reuse it in completion path, e.g. to store overflow_list as done in this patch. Signed-off-by:
-
Pavel Begunkov authored
As for import_iovec(), return !=NULL iovec from io_import_iovec() only when it should be freed. That includes returning NULL when iovec is already in req->io, because it should be deallocated by other means, e.g. inside op handler. After io_setup_async_rw() local iovec to ->io, just mark it NULL, to follow the idea in io_{read,write} as well. That's easier to follow, and especially useful if we want to reuse per-op space for completion data. Signed-off-by: -
Pavel Begunkov authored
Preparing reads/writes for async is a bit tricky. Extract a helper to not repeat it twice. Signed-off-by:
-
Pavel Begunkov authored
Don't deref req->io->rw every time, but put it in a local variable. This looks prettier, generates less instructions, and doesn't break alias analysis. Signed-off-by:
-
Pavel Begunkov authored
io_kiocb::task_work was de-unionised, and is not planned to be shared back, because it's too useful and commonly used. Hence, instead of keeping a separate task_work in struct io_async_rw just reuse req->task_work. Signed-off-by:
-
Pavel Begunkov authored
Don't repeat send msg initialisation code, it's error prone. Extract and use a helper function. Signed-off-by:
-
Pavel Begunkov authored
send/recv msghdr initialisation works with struct io_async_msghdr, but pulls the whole struct io_async_ctx for no reason. That complicates it with composite accessing, e.g. io->msg. Use and pass the most specific type, which is struct io_async_msghdr. It is the larget field in union io_async_ctx and doesn't save stack space, but looks clearer. The most of the changes are replacing "io->msg." with "iomsg->" Signed-off-by:
-
Pavel Begunkov authored
Every second field in send/recv is called msg, make it a bit more understandable by renaming ->msg, which is a user provided ptr, to ->umsg. Signed-off-by:
-
Dmitry Vyukov authored
rings_size() sets sq_offset to the total size of the rings (the returned value which is used for memory allocation). This is wrong: sq array should be located within the rings, not after them. Set sq_offset to where it should be. Fixes: 75b28aff ("io_uring: allocate the two rings together") Signed-off-by:
Dmitry Vyukov <dvyukov@google.com> Acked-by:
Hristo Venev <hristo@venev.name> Cc: io-uring@vger.kernel.org Signed-off-by:
-
Jens Axboe authored
Merge in io_uring-5.8 fixes, as changes/cleanups to how we do locked mem accounting require a fixup, and only one of the spots are noticed by git as the other merges cleanly. The flags fix from io_uring-5.8 also causes a merge conflict, the leak fix for recvmsg, the double poll fix, and the link failure locking fix. * io_uring-5.8: io_uring: fix lockup in io_fail_links() io_uring: fix ->work corruption with poll_add io_uring: missed req_init_async() for IOSQE_ASYNC io_uring: always allow drain/link/hardlink/async sqe flags io_uring: ensure double poll additions work with both request types io_uring: fix recvmsg memory leak with buffer selection io_uring: fix not initialised work->flags io_uring: fix missing msg_name assignment io_uring: account user memory freed when exit has been queued io_uring: fix memleak in io_sqe_files_register() io_uring: fix memleak in __io_sqe_files_update() io_uring: export cq overflow status to userspace Signed-off-by: -
Pavel Begunkov authored
io_fail_links() doesn't consider REQ_F_COMP_LOCKED leading to nested spin_lock(completion_lock) and lockup. [ 197.680409] rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: { 6-... } 18239 jiffies s: 1421 root: 0x40/. [ 197.680411] rcu: blocking rcu_node structures: [ 197.680412] Task dump for CPU 6: [ 197.680413] link-timeout R running task 0 1669 1 0x8000008a [ 197.680414] Call Trace: [ 197.680420] ? io_req_find_next+0xa0/0x200 [ 197.680422] ? io_put_req_find_next+0x2a/0x50 [ 197.680423] ? io_poll_task_func+0xcf/0x140 [ 197.680425] ? task_work_run+0x67/0xa0 [ 197.680426] ? do_exit+0x35d/0xb70 [ 197.680429] ? syscall_trace_enter+0x187/0x2c0 [ 197.680430] ? do_group_exit+0x43/0xa0 [ 197.680448] ? __x64_sys_exit_group+0x18/0x20 [ 197.680450] ? do_syscall_64+0x52/0xa0 [ 197.680452] ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 Signed-off-by: -
Pavel Begunkov authored
req->work might be already initialised by the time it gets into __io_arm_poll_handler(), which will corrupt it by using fields that are in an union with req->work. Luckily, the only side effect is missing put_creds(). Clean req->work before going there. Suggested-by:
-
- 23 Jul, 2020 1 commit
-
-
Pavel Begunkov authored
IOSQE_ASYNC branch of io_queue_sqe() is another place where an unitialised req->work can be accessed (i.e. prior io_req_init_async()). Nothing really bad though, it just looses IO_WQ_WORK_CONCURRENT flag. Signed-off-by:
-
- 18 Jul, 2020 2 commits
-
-
Daniele Albano authored
We currently filter these for timeout_remove/async_cancel/files_update, but we only should be filtering for fixed file and buffer select. This also causes a second read of sqe->flags, which isn't needed. Just check req->flags for the relevant bits. This then allows these commands to be used in links, for example, like everything else. Signed-off-by:
Daniele Albano <d.albano@gmail.com> Signed-off-by:
-
Jens Axboe authored
The double poll additions were centered around doing POLL_ADD on file descriptors that use more than one waitqueue (typically one for read, one for write) when being polled. However, it can also end up being triggered for when we use poll triggered retry. For that case, we cannot safely use req->io, as that could be used by the request type itself. Add a second io_poll_iocb pointer in the structure we allocate for poll based retry, and ensure we use the right one from the two paths. Fixes: 18bceab1 ("io_uring: allow POLL_ADD with double poll_wait() users") Signed-off-by:
-
- 15 Jul, 2020 1 commit
-
-
Pavel Begunkov authored
io_recvmsg() doesn't free memory allocated for struct io_buffer. This can causes a leak when used with automatic buffer selection. Signed-off-by:
-
