diff options
Diffstat (limited to 'io_uring')
-rw-r--r-- | io_uring/fdinfo.c | 18 | ||||
-rw-r--r-- | io_uring/fs.c | 2 | ||||
-rw-r--r-- | io_uring/io-wq.c | 10 | ||||
-rw-r--r-- | io_uring/io_uring.c | 22 | ||||
-rw-r--r-- | io_uring/io_uring.h | 41 | ||||
-rw-r--r-- | io_uring/kbuf.c | 27 | ||||
-rw-r--r-- | io_uring/openclose.c | 9 | ||||
-rw-r--r-- | io_uring/rw.c | 11 |
8 files changed, 86 insertions, 54 deletions
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index c53678875416..f04a43044d91 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -53,7 +53,6 @@ static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) { struct io_ring_ctx *ctx = f->private_data; - struct io_sq_data *sq = NULL; struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; @@ -64,6 +63,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) unsigned int cq_shift = 0; unsigned int sq_shift = 0; unsigned int sq_entries, cq_entries; + int sq_pid = -1, sq_cpu = -1; bool has_lock; unsigned int i; @@ -143,13 +143,19 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) has_lock = mutex_trylock(&ctx->uring_lock); if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { - sq = ctx->sq_data; - if (!sq->thread) - sq = NULL; + struct io_sq_data *sq = ctx->sq_data; + + if (mutex_trylock(&sq->lock)) { + if (sq->thread) { + sq_pid = task_pid_nr(sq->thread); + sq_cpu = task_cpu(sq->thread); + } + mutex_unlock(&sq->lock); + } } - seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1); - seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1); + seq_printf(m, "SqThread:\t%d\n", sq_pid); + seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { struct file *f = io_file_from_index(&ctx->file_table, i); diff --git a/io_uring/fs.c b/io_uring/fs.c index f6a69a549fd4..08e3b175469c 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -243,7 +243,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); const char __user *oldf, *newf; - if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 1ecc8c748768..522196dfb0ff 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1151,9 +1151,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) wq = kzalloc(sizeof(struct io_wq), GFP_KERNEL); if (!wq) return ERR_PTR(-ENOMEM); - ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); - if (ret) - goto err_wq; refcount_inc(&data->hash->refs); wq->hash = data->hash; @@ -1186,13 +1183,14 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) wq->task = get_task_struct(data->task); atomic_set(&wq->worker_refs, 1); init_completion(&wq->worker_done); + ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); + if (ret) + goto err; + return wq; err: io_wq_put_hash(data->hash); - cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - free_cpumask_var(wq->cpu_mask); -err_wq: kfree(wq); return ERR_PTR(ret); } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b9e1af5772f3..36ae5ac2b070 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2676,7 +2676,11 @@ static void io_pages_free(struct page ***pages, int npages) if (!pages) return; + page_array = *pages; + if (!page_array) + return; + for (i = 0; i < npages; i++) unpin_user_page(page_array[i]); kvfree(page_array); @@ -2688,7 +2692,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, { struct page **page_array; unsigned int nr_pages; - int ret; + int ret, i; *npages = 0; @@ -2718,6 +2722,20 @@ err: */ if (page_array[0] != page_array[ret - 1]) goto err; + + /* + * Can't support mapping user allocated ring memory on 32-bit archs + * where it could potentially reside in highmem. Just fail those with + * -EINVAL, just like we did on kernels that didn't support this + * feature. + */ + for (i = 0; i < nr_pages; i++) { + if (PageHighMem(page_array[i])) { + ret = -EINVAL; + goto err; + } + } + *pages = page_array; *npages = nr_pages; return page_to_virt(page_array[0]); @@ -2746,7 +2764,9 @@ static void io_rings_free(struct io_ring_ctx *ctx) ctx->sq_sqes = NULL; } else { io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); + ctx->n_ring_pages = 0; io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); + ctx->n_sqe_pages = 0; } } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 2ff719ae1b57..dc6d779b452b 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -86,20 +86,33 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); -#define io_lockdep_assert_cq_locked(ctx) \ - do { \ - lockdep_assert(in_task()); \ - \ - if (ctx->flags & IORING_SETUP_IOPOLL) { \ - lockdep_assert_held(&ctx->uring_lock); \ - } else if (!ctx->task_complete) { \ - lockdep_assert_held(&ctx->completion_lock); \ - } else if (ctx->submitter_task->flags & PF_EXITING) { \ - lockdep_assert(current_work()); \ - } else { \ - lockdep_assert(current == ctx->submitter_task); \ - } \ - } while (0) +#if defined(CONFIG_PROVE_LOCKING) +static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) +{ + lockdep_assert(in_task()); + + if (ctx->flags & IORING_SETUP_IOPOLL) { + lockdep_assert_held(&ctx->uring_lock); + } else if (!ctx->task_complete) { + lockdep_assert_held(&ctx->completion_lock); + } else if (ctx->submitter_task) { + /* + * ->submitter_task may be NULL and we can still post a CQE, + * if the ring has been setup with IORING_SETUP_R_DISABLED. + * Not from an SQE, as those cannot be submitted, but via + * updating tagged resources. + */ + if (ctx->submitter_task->flags & PF_EXITING) + lockdep_assert(current_work()); + else + lockdep_assert(current == ctx->submitter_task); + } +} +#else +static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) +{ +} +#endif static inline void io_req_task_work_add(struct io_kiocb *req) { diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index d5a04467666f..fea06810b43d 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -485,7 +485,7 @@ static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, { struct io_uring_buf_ring *br; struct page **pages; - int nr_pages; + int i, nr_pages; pages = io_pin_pages(reg->ring_addr, flex_array_size(br, bufs, reg->ring_entries), @@ -493,6 +493,17 @@ static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, if (IS_ERR(pages)) return PTR_ERR(pages); + /* + * Apparently some 32-bit boxes (ARM) will return highmem pages, + * which then need to be mapped. We could support that, but it'd + * complicate the code and slowdown the common cases quite a bit. + * So just error out, returning -EINVAL just like we did on kernels + * that didn't support mapped buffer rings. + */ + for (i = 0; i < nr_pages; i++) + if (PageHighMem(pages[i])) + goto error_unpin; + br = page_address(pages[0]); #ifdef SHM_COLOUR /* @@ -504,13 +515,8 @@ static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, * should use IOU_PBUF_RING_MMAP instead, and liburing will handle * this transparently. */ - if ((reg->ring_addr | (unsigned long) br) & (SHM_COLOUR - 1)) { - int i; - - for (i = 0; i < nr_pages; i++) - unpin_user_page(pages[i]); - return -EINVAL; - } + if ((reg->ring_addr | (unsigned long) br) & (SHM_COLOUR - 1)) + goto error_unpin; #endif bl->buf_pages = pages; bl->buf_nr_pages = nr_pages; @@ -518,6 +524,11 @@ static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, bl->is_mapped = 1; bl->is_mmap = 0; return 0; +error_unpin: + for (i = 0; i < nr_pages; i++) + unpin_user_page(pages[i]); + kvfree(pages); + return -EINVAL; } static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg, diff --git a/io_uring/openclose.c b/io_uring/openclose.c index e3fae26e025d..fb73adb89067 100644 --- a/io_uring/openclose.c +++ b/io_uring/openclose.c @@ -220,7 +220,6 @@ int io_close(struct io_kiocb *req, unsigned int issue_flags) { struct files_struct *files = current->files; struct io_close *close = io_kiocb_to_cmd(req, struct io_close); - struct fdtable *fdt; struct file *file; int ret = -EBADF; @@ -230,13 +229,7 @@ int io_close(struct io_kiocb *req, unsigned int issue_flags) } spin_lock(&files->file_lock); - fdt = files_fdtable(files); - if (close->fd >= fdt->max_fds) { - spin_unlock(&files->file_lock); - goto err; - } - file = rcu_dereference_protected(fdt->fd[close->fd], - lockdep_is_held(&files->file_lock)); + file = files_lookup_fd_locked(files, close->fd); if (!file || io_is_uring_fops(file)) { spin_unlock(&files->file_lock); goto err; diff --git a/io_uring/rw.c b/io_uring/rw.c index ec0cc38ea682..3398e1d944c2 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -355,7 +355,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret, struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); unsigned final_ret = io_fixup_rw_res(req, ret); - if (req->flags & REQ_F_CUR_POS) + if (ret >= 0 && req->flags & REQ_F_CUR_POS) req->file->f_pos = rw->kiocb.ki_pos; if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) { if (!__io_complete_rw_common(req, ret)) { @@ -993,15 +993,6 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) kiocb_start_write(kiocb); kiocb->ki_flags |= IOCB_WRITE; - /* - * For non-polled IO, set IOCB_DIO_CALLER_COMP, stating that our handler - * groks deferring the completion to task context. This isn't - * necessary and useful for polled IO as that can always complete - * directly. - */ - if (!(kiocb->ki_flags & IOCB_HIPRI)) - kiocb->ki_flags |= IOCB_DIO_CALLER_COMP; - if (likely(req->file->f_op->write_iter)) ret2 = call_write_iter(req->file, kiocb, &s->iter); else if (req->file->f_op->write) |