On 4/11/22 1:44 AM, gregkh@xxxxxxxxxxxxxxxxxxx wrote: > > The patch below does not apply to the 5.17-stable tree. > If someone wants it applied there, or to any other stable or longterm > tree, then please email the backport, including the original git commit > id to <stable@xxxxxxxxxxxxxxx>. Here's this one and the following ones marked for 5.17-stable. The first two it looks like you, this is the rest. -- Jens Axboe
From ec673f09afabaaad88e86187f70962ab4a456940 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe@xxxxxxxxx> Date: Thu, 31 Mar 2022 12:38:46 -0600 Subject: [PATCH 4/4] io_uring: drop the old style inflight file tracking commit d5361233e9ab920e135819f73dd8466355f1fddd upstream. io_uring tracks requests that are referencing an io_uring descriptor to be able to cancel without worrying about loops in the references. Since we now assign the file at execution time, the easier approach is to drop a potentially problematic reference before we punt the request. This eliminates the need to special case these types of files beyond just marking them as such, and simplifies cancelation quite a bit. This also fixes a recent issue where an async punted tee operation would with the io_uring descriptor as the output file would crash when attempting to get a reference to the file from the io-wq worker. We could have worked around that, but this is the much cleaner fix. Fixes: 6bf9c47a3989 ("io_uring: defer file assignment") Reported-by: syzbot+c4b9303500a21750b250@xxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> --- fs/io_uring.c | 85 ++++++++++++++++----------------------------------- 1 file changed, 27 insertions(+), 58 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 37cc4bb7a657..cc40963998d9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -112,8 +112,7 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -469,7 +468,6 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; @@ -1131,6 +1129,8 @@ static void io_clean_op(struct io_kiocb *req); static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned issue_flags); static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1312,29 +1312,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1344,24 +1324,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1509,14 +1474,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -2382,6 +2339,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); + spin_lock_irqsave(&tctx->task_lock, flags); if (priority) wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); @@ -5550,7 +5509,10 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked) if (!req->result) { struct poll_table_struct pt = { ._key = poll->events }; - req->result = vfs_poll(req->file, &pt) & poll->events; + if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED))) + req->result = -EBADF; + else + req->result = vfs_poll(req->file, &pt) & poll->events; } /* multishot, just fill an CQE and proceed */ @@ -6732,11 +6694,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7025,6 +6982,19 @@ static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, return file; } +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); @@ -7032,8 +7002,8 @@ static struct file *io_file_get_normal(struct io_kiocb *req, int fd) trace_io_uring_file_get(req->ctx, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } @@ -8801,7 +8771,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -9939,7 +9908,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } -- 2.35.1
From 55bfd82cff5095c6cb8b11bd1abf693c025880a9 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe@xxxxxxxxx> Date: Tue, 29 Mar 2022 10:10:08 -0600 Subject: [PATCH 3/4] io_uring: defer file assignment commit 6bf9c47a398911e0ab920e362115153596c80432 upstream. If an application uses direct open or accept, it knows in advance what direct descriptor value it will get as it picks it itself. This allows combined requests such as: sqe = io_uring_get_sqe(ring); io_uring_prep_openat_direct(sqe, ..., file_slot); sqe->flags |= IOSQE_IO_LINK | IOSQE_CQE_SKIP_SUCCESS; sqe = io_uring_get_sqe(ring); io_uring_prep_read(sqe,file_slot, buf, buf_size, 0); sqe->flags |= IOSQE_FIXED_FILE; io_uring_submit(ring); where we prepare both a file open and read, and only get a completion event for the read when both have completed successfully. Currently links are fully prepared before the head is issued, but that fails if the dependent link needs a file assigned that isn't valid until the head has completed. Conversely, if the same chain is performed but the fixed file slot is already valid, then we would be unexpectedly returning data from the old file slot rather than the newly opened one. Make sure we're consistent here. Allow deferral of file setup, which makes this documented case work. Cc: stable@xxxxxxxxxxxxxxx # v5.15+ Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> --- fs/io-wq.h | 1 + fs/io_uring.c | 39 +++++++++++++++++++++++++++++---------- 2 files changed, 30 insertions(+), 10 deletions(-) diff --git a/fs/io-wq.h b/fs/io-wq.h index dbecd27656c7..04d374e65e54 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; + int fd; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index fe5b4d8d9961..37cc4bb7a657 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6746,6 +6746,23 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->work.fd, issue_flags); + else + req->file = io_file_get_normal(req, req->work.fd); + if (req->file) + return true; + + req_set_fail(req); + req->result = -EBADF; + return false; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; @@ -6756,6 +6773,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (!io_op_defs[req->opcode].audit_skip) audit_uring_entry(req->opcode); + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; switch (req->opcode) { case IORING_OP_NOP: @@ -6897,10 +6916,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -6912,14 +6932,18 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + } + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); + io_req_task_queue_fail(req, err); return; } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7250,6 +7274,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->work.fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7259,13 +7285,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - if (req->flags & REQ_F_FIXED_FILE) - req->file = io_file_get_fixed(req, READ_ONCE(sqe->fd), 0); - else - req->file = io_file_get_normal(req, READ_ONCE(sqe->fd)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); -- 2.35.1
From c71eb2ca5276c7f8719d38a5f47b3b309b6cb7f3 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe@xxxxxxxxx> Date: Mon, 4 Apr 2022 17:18:43 -0600 Subject: [PATCH 2/4] io_uring: propagate issue_flags state down to file assignment commit 5106dd6e74ab6c94daac1c357094f11e6934b36f upstream. We'll need this in a future patch, when we could be assigning the file after the prep stage. While at it, get rid of the io_file_get() helper, it just makes the code harder to read. Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> --- fs/io_uring.c | 82 +++++++++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 35 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 9f47b0ebd48d..fe5b4d8d9961 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1128,8 +1128,9 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1258,13 +1259,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(req->fixed_rsrc_refs); + } } } @@ -3124,7 +3132,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3134,7 +3143,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3290,7 +3299,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; @@ -4169,8 +4178,10 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; - in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); if (!in) { ret = -EBADF; goto done; @@ -4209,8 +4220,10 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; - in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); if (!in) { ret = -EBADF; goto done; @@ -5515,7 +5528,7 @@ static void io_poll_remove_entries(struct io_kiocb *req) * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; struct io_poll_iocb *poll = io_poll_get_single(req); @@ -5571,7 +5584,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -5596,7 +5609,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6963,30 +6976,36 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); +out: + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, fd); + trace_io_uring_file_get(req->ctx, fd); /* we don't allow fixed io_uring files */ if (file && unlikely(file->f_op == &io_uring_fops)) @@ -6994,15 +7013,6 @@ static struct file *io_file_get_normal(struct io_ring_ctx *ctx, return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; @@ -7250,8 +7260,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, READ_ONCE(sqe->fd), 0); + else + req->file = io_file_get_normal(req, READ_ONCE(sqe->fd)); if (unlikely(!req->file)) return -EBADF; } -- 2.35.1
From 86a8225b51e14b9fee41ba8c3212a86a4a5c8b8a Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe@xxxxxxxxx> Date: Tue, 29 Mar 2022 10:48:05 -0600 Subject: [PATCH 1/4] io_uring: move read/write file prep state into actual opcode handler commit 584b0180f0f4d67d7145950fe68c625f06c88b10 upstream. In preparation for not necessarily having a file assigned at prep time, defer any initialization associated with the file to when the opcode handler is run. Cc: stable@xxxxxxxxxxxxxxx # v5.15+ Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> --- fs/io_uring.c | 119 ++++++++++++++++++++++++++------------------------ 1 file changed, 62 insertions(+), 57 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 49431646a7e0..9f47b0ebd48d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -560,7 +560,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + u32 flags; }; struct io_connect { @@ -2986,50 +2987,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1) { - if (!(file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = file->f_pos; - } else { - kiocb->ki_pos = 0; - } - } - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3045,6 +3007,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3525,13 +3488,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3619,6 +3575,58 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + if (kiocb->ki_pos == -1) { + if (!(file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = file->f_pos; + } else { + kiocb->ki_pos = 0; + } + } + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3643,6 +3651,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3741,14 +3752,6 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file)); - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3768,6 +3771,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -6502,11 +6508,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: -- 2.35.1