diff options
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r-- | fs/io_uring.c | 3416 |
1 files changed, 2579 insertions, 837 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 405be10da73d..1806afddfea5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -46,6 +46,7 @@ #include <linux/compat.h> #include <linux/refcount.h> #include <linux/uio.h> +#include <linux/bits.h> #include <linux/sched/signal.h> #include <linux/fs.h> @@ -70,6 +71,10 @@ #include <linux/sizes.h> #include <linux/hugetlb.h> #include <linux/highmem.h> +#include <linux/namei.h> +#include <linux/fsnotify.h> +#include <linux/fadvise.h> +#include <linux/eventpoll.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -177,6 +182,21 @@ struct fixed_file_table { struct file **files; }; +enum { + FFD_F_ATOMIC, +}; + +struct fixed_file_data { + struct fixed_file_table *table; + struct io_ring_ctx *ctx; + + struct percpu_ref refs; + struct llist_head put_llist; + unsigned long state; + struct work_struct ref_work; + struct completion done; +}; + struct io_ring_ctx { struct { struct percpu_ref refs; @@ -184,10 +204,11 @@ struct io_ring_ctx { struct { unsigned int flags; - bool compat; - bool account_mem; - bool cq_overflow_flushed; - bool drain_next; + int compat: 1; + int account_mem: 1; + int cq_overflow_flushed: 1; + int drain_next: 1; + int eventfd_async: 1; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -207,13 +228,14 @@ struct io_ring_ctx { unsigned sq_thread_idle; unsigned cached_sq_dropped; atomic_t cached_cq_overflow; - struct io_uring_sqe *sq_sqes; + unsigned long sq_check_overflow; struct list_head defer_list; struct list_head timeout_list; struct list_head cq_overflow_list; wait_queue_head_t inflight_wait; + struct io_uring_sqe *sq_sqes; } ____cacheline_aligned_in_smp; struct io_rings *rings; @@ -229,8 +251,10 @@ struct io_ring_ctx { * readers must ensure that ->refs is alive as long as the file* is * used. Only updated through io_uring_register(2). */ - struct fixed_file_table *file_table; + struct fixed_file_data *file_data; unsigned nr_user_files; + int ring_fd; + struct file *ring_file; /* if used, fixed mapped user buffers */ unsigned nr_user_bufs; @@ -250,11 +274,14 @@ struct io_ring_ctx { struct socket *ring_sock; #endif + struct idr personality_idr; + struct { unsigned cached_cq_tail; unsigned cq_entries; unsigned cq_mask; atomic_t cq_timeouts; + unsigned long cq_check_overflow; struct wait_queue_head cq_wait; struct fasync_struct *cq_fasync; struct eventfd_ctx *cq_ev_fd; @@ -267,7 +294,8 @@ struct io_ring_ctx { struct { spinlock_t completion_lock; - bool poll_multi_file; + struct llist_head poll_llist; + /* * ->poll_list is protected by the ctx->uring_lock for * io_uring instances that don't use IORING_SETUP_SQPOLL. @@ -277,6 +305,7 @@ struct io_ring_ctx { struct list_head poll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; + bool poll_multi_file; spinlock_t inflight_lock; struct list_head inflight_list; @@ -289,11 +318,20 @@ struct io_ring_ctx { */ struct io_poll_iocb { struct file *file; - struct wait_queue_head *head; + union { + struct wait_queue_head *head; + u64 addr; + }; __poll_t events; bool done; bool canceled; - struct wait_queue_entry *wait; + struct wait_queue_entry wait; +}; + +struct io_close { + struct file *file; + struct file *put_file; + int fd; }; struct io_timeout_data { @@ -304,6 +342,96 @@ struct io_timeout_data { u32 seq_offset; }; +struct io_accept { + struct file *file; + struct sockaddr __user *addr; + int __user *addr_len; + int flags; +}; + +struct io_sync { + struct file *file; + loff_t len; + loff_t off; + int flags; + int mode; +}; + +struct io_cancel { + struct file *file; + u64 addr; +}; + +struct io_timeout { + struct file *file; + u64 addr; + int flags; + unsigned count; +}; + +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; +}; + +struct io_connect { + struct file *file; + struct sockaddr __user *addr; + int addr_len; +}; + +struct io_sr_msg { + struct file *file; + union { + struct user_msghdr __user *msg; + void __user *buf; + }; + int msg_flags; + size_t len; +}; + +struct io_open { + struct file *file; + int dfd; + union { + unsigned mask; + }; + struct filename *filename; + struct statx __user *buffer; + struct open_how how; +}; + +struct io_files_update { + struct file *file; + u64 arg; + u32 nr_args; + u32 offset; +}; + +struct io_fadvise { + struct file *file; + u64 offset; + u32 len; + u32 advice; +}; + +struct io_madvise { + struct file *file; + u64 addr; + u32 len; + u32 advice; +}; + +struct io_epoll { + struct file *file; + int epfd; + int op; + int fd; + struct epoll_event event; +}; + struct io_async_connect { struct sockaddr_storage address; }; @@ -322,16 +450,79 @@ struct io_async_rw { ssize_t size; }; +struct io_async_open { + struct filename *filename; +}; + struct io_async_ctx { - struct io_uring_sqe sqe; union { struct io_async_rw rw; struct io_async_msghdr msg; struct io_async_connect connect; struct io_timeout_data timeout; + struct io_async_open open; }; }; +enum { + REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, + REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, + REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, + REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, + REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, + + REQ_F_LINK_NEXT_BIT, + REQ_F_FAIL_LINK_BIT, + REQ_F_INFLIGHT_BIT, + REQ_F_CUR_POS_BIT, + REQ_F_NOWAIT_BIT, + REQ_F_IOPOLL_COMPLETED_BIT, + REQ_F_LINK_TIMEOUT_BIT, + REQ_F_TIMEOUT_BIT, + REQ_F_ISREG_BIT, + REQ_F_MUST_PUNT_BIT, + REQ_F_TIMEOUT_NOSEQ_BIT, + REQ_F_COMP_LOCKED_BIT, +}; + +enum { + /* ctx owns file */ + REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), + /* drain existing IO first */ + REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), + /* linked sqes */ + REQ_F_LINK = BIT(REQ_F_LINK_BIT), + /* doesn't sever on completion < 0 */ + REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), + /* IOSQE_ASYNC */ + REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), + + /* already grabbed next link */ + REQ_F_LINK_NEXT = BIT(REQ_F_LINK_NEXT_BIT), + /* fail rest of links */ + REQ_F_FAIL_LINK = BIT(REQ_F_FAIL_LINK_BIT), + /* on inflight list */ + REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), + /* read/write uses file position */ + REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), + /* must not punt to workers */ + REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), + /* polled IO has completed */ + REQ_F_IOPOLL_COMPLETED = BIT(REQ_F_IOPOLL_COMPLETED_BIT), + /* has linked timeout */ + REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), + /* timeout request */ + REQ_F_TIMEOUT = BIT(REQ_F_TIMEOUT_BIT), + /* regular file */ + REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* must be punted even for NONBLOCK */ + REQ_F_MUST_PUNT = BIT(REQ_F_MUST_PUNT_BIT), + /* no timeout sequence */ + REQ_F_TIMEOUT_NOSEQ = BIT(REQ_F_TIMEOUT_NOSEQ_BIT), + /* completion under lock */ + REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), +}; + /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can @@ -341,17 +532,31 @@ struct io_async_ctx { struct io_kiocb { union { struct file *file; - struct kiocb rw; + struct io_rw rw; struct io_poll_iocb poll; + struct io_accept accept; + struct io_sync sync; + struct io_cancel cancel; + struct io_timeout timeout; + struct io_connect connect; + struct io_sr_msg sr_msg; + struct io_open open; + struct io_close close; + struct io_files_update files_update; + struct io_fadvise fadvise; + struct io_madvise madvise; + struct io_epoll epoll; }; - const struct io_uring_sqe *sqe; struct io_async_ctx *io; - struct file *ring_file; - int ring_fd; + /* + * llist_node is only used for poll deferred completions + */ + struct llist_node llist_node; bool has_user; bool in_async; bool needs_fixed_file; + u8 opcode; struct io_ring_ctx *ctx; union { @@ -361,22 +566,6 @@ struct io_kiocb { struct list_head link_list; unsigned int flags; refcount_t refs; -#define REQ_F_NOWAIT 1 /* must not punt to workers */ -#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ -#define REQ_F_FIXED_FILE 4 /* ctx owns file */ -#define REQ_F_LINK_NEXT 8 /* already grabbed next link */ -#define REQ_F_IO_DRAIN 16 /* drain existing IO first */ -#define REQ_F_IO_DRAINED 32 /* drain done */ -#define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_LINK_TIMEOUT 128 /* has linked timeout */ -#define REQ_F_FAIL_LINK 256 /* fail rest of links */ -#define REQ_F_DRAIN_LINK 512 /* link should be fully drained */ -#define REQ_F_TIMEOUT 1024 /* timeout request */ -#define REQ_F_ISREG 2048 /* regular file */ -#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */ -#define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */ -#define REQ_F_INFLIGHT 16384 /* on inflight list */ -#define REQ_F_COMP_LOCKED 32768 /* completion under lock */ u64 user_data; u32 result; u32 sequence; @@ -409,14 +598,162 @@ struct io_submit_state { unsigned int ios_left; }; +struct io_op_def { + /* needs req->io allocated for deferral/async */ + unsigned async_ctx : 1; + /* needs current->mm setup, does mm access */ + unsigned needs_mm : 1; + /* needs req->file assigned */ + unsigned needs_file : 1; + /* needs req->file assigned IFF fd is >= 0 */ + unsigned fd_non_neg : 1; + /* hash wq insertion if file is a regular file */ + unsigned hash_reg_file : 1; + /* unbound wq insertion if file is a non-regular file */ + unsigned unbound_nonreg_file : 1; + /* opcode is not supported by this kernel */ + unsigned not_supported : 1; + /* needs file table */ + unsigned file_table : 1; +}; + +static const struct io_op_def io_op_defs[] = { + [IORING_OP_NOP] = {}, + [IORING_OP_READV] = { + .async_ctx = 1, + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_WRITEV] = { + .async_ctx = 1, + .needs_mm = 1, + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_FSYNC] = { + .needs_file = 1, + }, + [IORING_OP_READ_FIXED] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_WRITE_FIXED] = { + .needs_file = 1, + .hash_reg_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_POLL_ADD] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_POLL_REMOVE] = {}, + [IORING_OP_SYNC_FILE_RANGE] = { + .needs_file = 1, + }, + [IORING_OP_SENDMSG] = { + .async_ctx = 1, + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_RECVMSG] = { + .async_ctx = 1, + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_TIMEOUT] = { + .async_ctx = 1, + .needs_mm = 1, + }, + [IORING_OP_TIMEOUT_REMOVE] = {}, + [IORING_OP_ACCEPT] = { + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + .file_table = 1, + }, + [IORING_OP_ASYNC_CANCEL] = {}, + [IORING_OP_LINK_TIMEOUT] = { + .async_ctx = 1, + .needs_mm = 1, + }, + [IORING_OP_CONNECT] = { + .async_ctx = 1, + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_FALLOCATE] = { + .needs_file = 1, + }, + [IORING_OP_OPENAT] = { + .needs_file = 1, + .fd_non_neg = 1, + .file_table = 1, + }, + [IORING_OP_CLOSE] = { + .needs_file = 1, + .file_table = 1, + }, + [IORING_OP_FILES_UPDATE] = { + .needs_mm = 1, + .file_table = 1, + }, + [IORING_OP_STATX] = { + .needs_mm = 1, + .needs_file = 1, + .fd_non_neg = 1, + }, + [IORING_OP_READ] = { + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_WRITE] = { + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_FADVISE] = { + .needs_file = 1, + }, + [IORING_OP_MADVISE] = { + .needs_mm = 1, + }, + [IORING_OP_SEND] = { + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_RECV] = { + .needs_mm = 1, + .needs_file = 1, + .unbound_nonreg_file = 1, + }, + [IORING_OP_OPENAT2] = { + .needs_file = 1, + .fd_non_neg = 1, + .file_table = 1, + }, + [IORING_OP_EPOLL_CTL] = { + .unbound_nonreg_file = 1, + .file_table = 1, + }, +}; + static void io_wq_submit_work(struct io_wq_work **workptr); static void io_cqring_fill_event(struct io_kiocb *req, long res); -static void __io_free_req(struct io_kiocb *req); static void io_put_req(struct io_kiocb *req); -static void io_double_put_req(struct io_kiocb *req); static void __io_double_put_req(struct io_kiocb *req); static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); +static int __io_sqe_files_update(struct io_ring_ctx *ctx, + struct io_uring_files_update *ip, + unsigned nr_args); +static int io_grab_files(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -483,9 +820,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->completions[0]); init_completion(&ctx->completions[1]); + idr_init(&ctx->personality_idr); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); spin_lock_init(&ctx->completion_lock); + init_llist_head(&ctx->poll_llist); INIT_LIST_HEAD(&ctx->poll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); @@ -512,7 +851,7 @@ static inline bool __req_need_defer(struct io_kiocb *req) static inline bool req_need_defer(struct io_kiocb *req) { - if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN) + if (unlikely(req->flags & REQ_F_IO_DRAIN)) return __req_need_defer(req); return false; @@ -552,56 +891,54 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - if (ctx->cached_cq_tail != READ_ONCE(rings->cq.tail)) { - /* order cqe stores with ring update */ - smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); + /* order cqe stores with ring update */ + smp_store_release(&rings->cq.tail, ctx->cached_cq_tail); - if (wq_has_sleeper(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } + if (wq_has_sleeper(&ctx->cq_wait)) { + wake_up_interruptible(&ctx->cq_wait); + kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); } } -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +static inline void io_req_work_grab_env(struct io_kiocb *req, + const struct io_op_def *def) { - u8 opcode = READ_ONCE(sqe->opcode); + if (!req->work.mm && def->needs_mm) { + mmgrab(current->mm); + req->work.mm = current->mm; + } + if (!req->work.creds) + req->work.creds = get_current_cred(); +} - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); +static inline void io_req_work_drop_env(struct io_kiocb *req) +{ + if (req->work.mm) { + mmdrop(req->work.mm); + req->work.mm = NULL; + } + if (req->work.creds) { + put_cred(req->work.creds); + req->work.creds = NULL; + } } static inline bool io_prep_async_work(struct io_kiocb *req, struct io_kiocb **link) { + const struct io_op_def *def = &io_op_defs[req->opcode]; bool do_hashed = false; - if (req->sqe) { - switch (req->sqe->opcode) { - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: + if (req->flags & REQ_F_ISREG) { + if (def->hash_reg_file) do_hashed = true; - /* fall-through */ - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_SENDMSG: - case IORING_OP_RECVMSG: - case IORING_OP_ACCEPT: - case IORING_OP_POLL_ADD: - case IORING_OP_CONNECT: - /* - * We know REQ_F_ISREG is not set on some of these - * opcodes, but this enables us to keep the check in - * just one place. - */ - if (!(req->flags & REQ_F_ISREG)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } - if (io_sqe_needs_user(req->sqe)) - req->work.flags |= IO_WQ_WORK_NEEDS_USER; + } else { + if (def->unbound_nonreg_file) + req->work.flags |= IO_WQ_WORK_UNBOUND; } + io_req_work_grab_env(req, def); + *link = io_prep_linked_timeout(req); return do_hashed; } @@ -659,10 +996,8 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) __io_commit_cqring(ctx); - while ((req = io_get_deferred_req(ctx)) != NULL) { - req->flags |= REQ_F_IO_DRAINED; + while ((req = io_get_deferred_req(ctx)) != NULL) io_queue_async_work(req); - } } static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) @@ -683,13 +1018,20 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) return &rings->cqes[tail & ctx->cq_mask]; } +static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) +{ + if (!ctx->eventfd_async) + return true; + return io_wq_current_is_worker() || in_interrupt(); +} + static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); if (waitqueue_active(&ctx->sqo_wait)) wake_up(&ctx->sqo_wait); - if (ctx->cq_ev_fd) + if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); } @@ -714,7 +1056,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) /* if force is set, the ring is going away. always drop after that */ if (force) - ctx->cq_overflow_flushed = true; + ctx->cq_overflow_flushed = 1; cqe = NULL; while (!list_empty(&ctx->cq_overflow_list)) { @@ -736,6 +1078,10 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) } io_commit_cqring(ctx); + if (cqe) { + clear_bit(0, &ctx->sq_check_overflow); + clear_bit(0, &ctx->cq_check_overflow); + } spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); @@ -769,6 +1115,10 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res) WRITE_ONCE(ctx->rings->cq_overflow, atomic_inc_return(&ctx->cached_cq_overflow)); } else { + if (list_empty(&ctx->cq_overflow_list)) { + set_bit(0, &ctx->sq_check_overflow); + set_bit(0, &ctx->cq_check_overflow); + } refcount_inc(&req->refs); req->result = res; list_add_tail(&req->list, &ctx->cq_overflow_list); @@ -811,9 +1161,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct io_kiocb *req; - if (!percpu_ref_tryget(&ctx->refs)) - return NULL; - if (!state) { req = kmem_cache_alloc(req_cachep, gfp); if (unlikely(!req)) @@ -846,7 +1193,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, got_it: req->io = NULL; - req->ring_file = NULL; req->file = NULL; req->ctx = ctx; req->flags = 0; @@ -863,24 +1209,35 @@ fallback: return NULL; } -static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) +static void __io_req_do_free(struct io_kiocb *req) +{ + if (likely(!io_is_fallback_req(req))) + kmem_cache_free(req_cachep, req); + else + clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req); +} + +static void __io_req_aux_free(struct io_kiocb *req) { - if (*nr) { - kmem_cache_free_bulk(req_cachep, *nr, reqs); - percpu_ref_put_many(&ctx->refs, *nr); - *nr = 0; + struct io_ring_ctx *ctx = req->ctx; + + kfree(req->io); + if (req->file) { + if (req->flags & REQ_F_FIXED_FILE) + percpu_ref_put(&ctx->file_data->refs); + else + fput(req->file); } + + io_req_work_drop_env(req); } static void __io_free_req(struct io_kiocb *req) { - struct io_ring_ctx *ctx = req->ctx; + __io_req_aux_free(req); - if (req->io) - kfree(req->io); - if (req->file && !(req->flags & REQ_F_FIXED_FILE)) - fput(req->file); if (req->flags & REQ_F_INFLIGHT) { + struct io_ring_ctx *ctx = req->ctx; unsigned long flags; spin_lock_irqsave(&ctx->inflight_lock, flags); @@ -889,11 +1246,63 @@ static void __io_free_req(struct io_kiocb *req) wake_up(&ctx->inflight_wait); spin_unlock_irqrestore(&ctx->inflight_lock, flags); } - percpu_ref_put(&ctx->refs); - if (likely(!io_is_fallback_req(req))) - kmem_cache_free(req_cachep, req); - else - clear_bit_unlock(0, (unsigned long *) ctx->fallback_req); + + percpu_ref_put(&req->ctx->refs); + __io_req_do_free(req); +} + +struct req_batch { + void *reqs[IO_IOPOLL_BATCH]; + int to_free; + int need_iter; +}; + +static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb) +{ + int fixed_refs = rb->to_free; + + if (!rb->to_free) + return; + if (rb->need_iter) { + int i, inflight = 0; + unsigned long flags; + + fixed_refs = 0; + for (i = 0; i < rb->to_free; i++) { + struct io_kiocb *req = rb->reqs[i]; + + if (req->flags & REQ_F_FIXED_FILE) { + req->file = NULL; + fixed_refs++; + } + if (req->flags & REQ_F_INFLIGHT) + inflight++; + __io_req_aux_free(req); + } + if (!inflight) + goto do_free; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + for (i = 0; i < rb->to_free; i++) { + struct io_kiocb *req = rb->reqs[i]; + + if (req->flags & REQ_F_INFLIGHT) { + list_del(&req->inflight_entry); + if (!--inflight) + break; + } + } + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + } +do_free: + kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs); + if (fixed_refs) + percpu_ref_put_many(&ctx->file_data->refs, fixed_refs); + percpu_ref_put_many(&ctx->refs, rb->to_free); + rb->to_free = rb->need_iter = 0; } static bool io_link_cancel_timeout(struct io_kiocb *req) @@ -969,7 +1378,7 @@ static void io_fail_links(struct io_kiocb *req) trace_io_uring_fail_link(req, link); if ((req->flags & REQ_F_LINK_TIMEOUT) && - link->sqe->opcode == IORING_OP_LINK_TIMEOUT) { + link->opcode == IORING_OP_LINK_TIMEOUT) { io_link_cancel_timeout(link); } else { io_cqring_fill_event(link, -ECANCELED); @@ -1066,19 +1475,21 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush) { struct io_rings *rings = ctx->rings; - /* - * noflush == true is from the waitqueue handler, just ensure we wake - * up the task, and the next invocation will flush the entries. We - * cannot safely to it from here. - */ - if (noflush && !list_empty(&ctx->cq_overflow_list)) - return -1U; + if (test_bit(0, &ctx->cq_check_overflow)) { + /* + * noflush == true is from the waitqueue handler, just ensure + * we wake up the task, and the next invocation will flush the + * entries. We cannot safely to it from here. + */ + if (noflush && !list_empty(&ctx->cq_overflow_list)) + return -1U; - io_cqring_overflow_flush(ctx, false); + io_cqring_overflow_flush(ctx, false); + } /* See comment at the top of this file */ smp_rmb(); - return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head); + return ctx->cached_cq_tail - READ_ONCE(rings->cq.head); } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) @@ -1089,17 +1500,30 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; } +static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req) +{ + if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req)) + return false; + + if (!(req->flags & REQ_F_FIXED_FILE) || req->io) + rb->need_iter++; + + rb->reqs[rb->to_free++] = req; + if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs))) + io_free_req_many(req->ctx, rb); + return true; +} + /* * Find and free completed poll iocbs */ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, struct list_head *done) { - void *reqs[IO_IOPOLL_BATCH]; + struct req_batch rb; struct io_kiocb *req; - int to_free; - to_free = 0; + rb.to_free = rb.need_iter = 0; while (!list_empty(done)) { req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); @@ -1107,26 +1531,13 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_cqring_fill_event(req, req->result); (*nr_events)++; - if (refcount_dec_and_test(&req->refs)) { - /* If we're not using fixed files, we have to pair the - * completion part with the file put. Use regular - * completions for those, only batch free for fixed - * file and non-linked commands. - */ - if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == - REQ_F_FIXED_FILE) && !io_is_fallback_req(req) && - !req->io) { - reqs[to_free++] = req; - if (to_free == ARRAY_SIZE(reqs)) - io_free_req_many(ctx, reqs, &to_free); - } else { - io_free_req(req); - } - } + if (refcount_dec_and_test(&req->refs) && + !io_req_multi_free(&rb, req)) + io_free_req(req); } io_commit_cqring(ctx); - io_free_req_many(ctx, reqs, &to_free); + io_free_req_many(ctx, &rb); } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, @@ -1145,7 +1556,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, ret = 0; list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) { - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; /* * Move completed entries to our local list. If we find a @@ -1175,7 +1586,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, } /* - * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a + * Poll for a minimum of 'min' events. Note that if min == 0 we consider that a * non-spinning poll check - we'll still enter the driver poll loop, but only * as a non-spinning completion check. */ @@ -1292,21 +1703,27 @@ static void kiocb_end_write(struct io_kiocb *req) file_end_write(req->file); } +static inline void req_set_fail_links(struct io_kiocb *req) +{ + if ((req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) == REQ_F_LINK) + req->flags |= REQ_F_FAIL_LINK; +} + static void io_complete_rw_common(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - if ((req->flags & REQ_F_LINK) && res != req->result) - req->flags |= REQ_F_FAIL_LINK; + if (res != req->result) + req_set_fail_links(req); io_cqring_add_event(req, res); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); io_complete_rw_common(kiocb, res); io_put_req(req); @@ -1314,7 +1731,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_kiocb *nxt = NULL; io_complete_rw_common(kiocb, res); @@ -1325,13 +1742,13 @@ static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); - if ((req->flags & REQ_F_LINK) && res != req->result) - req->flags |= REQ_F_FAIL_LINK; + if (res != req->result) + req_set_fail_links(req); req->result = res; if (res != -EAGAIN) req->flags |= REQ_F_IOPOLL_COMPLETED; @@ -1359,7 +1776,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_req = list_first_entry(&ctx->poll_list, struct io_kiocb, list); - if (list_req->rw.ki_filp != req->rw.ki_filp) + if (list_req->file != req->file) ctx->poll_multi_file = true; } @@ -1422,7 +1839,7 @@ static bool io_file_supports_async(struct file *file) { umode_t mode = file_inode(file)->i_mode; - if (S_ISBLK(mode) || S_ISCHR(mode)) + if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISSOCK(mode)) return true; if (S_ISREG(mode) && file->f_op != &io_uring_fops) return true; @@ -1430,11 +1847,11 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; unsigned ioprio; int ret; @@ -1445,6 +1862,10 @@ static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); + if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + } kiocb->ki_flags = iocb_flags(kiocb->ki_filp); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); @@ -1483,6 +1904,12 @@ static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) return -EINVAL; kiocb->ki_complete = io_complete_rw; } + + req->rw.addr = READ_ONCE(sqe->addr); + req->rw.len = READ_ONCE(sqe->len); + /* we own ->private, reuse it for the buffer index */ + req->rw.kiocb.private = (void *) (unsigned long) + READ_ONCE(sqe->buf_index); return 0; } @@ -1510,17 +1937,21 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt, bool in_async) { + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); + + if (req->flags & REQ_F_CUR_POS) + req->file->f_pos = kiocb->ki_pos; if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw) *nxt = __io_complete_rw(kiocb, ret); else io_rw_done(kiocb, ret); } -static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, - const struct io_uring_sqe *sqe, +static ssize_t io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { - size_t len = READ_ONCE(sqe->len); + struct io_ring_ctx *ctx = req->ctx; + size_t len = req->rw.len; struct io_mapped_ubuf *imu; unsigned index, buf_index; size_t offset; @@ -1530,13 +1961,13 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, if (unlikely(!ctx->user_bufs)) return -EFAULT; - buf_index = READ_ONCE(sqe->buf_index); + buf_index = (unsigned long) req->rw.kiocb.private; if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = &ctx->user_bufs[index]; - buf_addr = READ_ONCE(sqe->addr); + buf_addr = req->rw.addr; /* overflow */ if (buf_addr + len < buf_addr) @@ -1593,23 +2024,25 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, static ssize_t io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter) { - const struct io_uring_sqe *sqe = req->sqe; - void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); - size_t sqe_len = READ_ONCE(sqe->len); + void __user *buf = u64_to_user_ptr(req->rw.addr); + size_t sqe_len = req->rw.len; u8 opcode; - /* - * We're reading ->opcode for the second time, but the first read - * doesn't care whether it's _FIXED or not, so it doesn't matter - * whether ->opcode changes concurrently. The first read does care - * about whether it is a READ or a WRITE, so we don't trust this read - * for that purpose and instead let the caller pass in the read/write - * flag. - */ - opcode = READ_ONCE(sqe->opcode); + opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; - return io_import_fixed(req->ctx, rw, sqe, iter); + return io_import_fixed(req, rw, iter); + } + + /* buffer index only valid with fixed read/write */ + if (req->rw.kiocb.private) + return -EINVAL; + + if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { + ssize_t ret; + ret = import_single_range(rw, buf, sqe_len, *iovec, iter); + *iovec = NULL; + return ret; } if (req->io) { @@ -1692,7 +2125,7 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, return ret; } -static void io_req_map_io(struct io_kiocb *req, ssize_t io_size, +static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, struct iovec *iovec, struct iovec *fast_iov, struct iov_iter *iter) { @@ -1706,57 +2139,86 @@ static void io_req_map_io(struct io_kiocb *req, ssize_t io_size, } } -static int io_setup_async_io(struct io_kiocb *req, ssize_t io_size, +static int io_alloc_async_ctx(struct io_kiocb *req) +{ + if (!io_op_defs[req->opcode].async_ctx) + return 0; + req->io = kmalloc(sizeof(*req->io), GFP_KERNEL); + return req->io == NULL; +} + +static void io_rw_async(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct iovec *iov = NULL; + + if (req->io->rw.iov != req->io->rw.fast_iov) + iov = req->io->rw.iov; + io_wq_submit_work(workptr); + kfree(iov); +} + +static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, struct iovec *iovec, struct iovec *fast_iov, struct iov_iter *iter) { - req->io = kmalloc(sizeof(*req->io), GFP_KERNEL); - if (req->io) { - io_req_map_io(req, io_size, iovec, fast_iov, iter); - memcpy(&req->io->sqe, req->sqe, sizeof(req->io->sqe)); - req->sqe = &req->io->sqe; + if (!io_op_defs[req->opcode].async_ctx) return 0; - } + if (!req->io && io_alloc_async_ctx(req)) + return -ENOMEM; - return -ENOMEM; + io_req_map_rw(req, io_size, iovec, fast_iov, iter); + req->work.func = io_rw_async; + return 0; } -static int io_read_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_import_iovec(READ, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(READ, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t io_size, ret; - if (!req->io) { - ret = io_read_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(READ, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(READ, req, &iovec, &iter); + if (ret < 0) + return ret; - file = req->file; + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; + + req->result = 0; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1765,39 +2227,27 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so * we know to async punt it even if it was opened O_NONBLOCK */ - if (force_nonblock && !io_file_supports_async(file)) { + if (force_nonblock && !io_file_supports_async(req->file)) { req->flags |= REQ_F_MUST_PUNT; goto copy_iov; } iov_count = iov_iter_count(&iter); - ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; - if (file->f_op->read_iter) - ret2 = call_read_iter(file, kiocb, &iter); + if (req->file->f_op->read_iter) + ret2 = call_read_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(READ, file, kiocb, &iter); + ret2 = loop_rw_iter(READ, req->file, kiocb, &iter); - /* - * In case of a short read, punt to async. This can happen - * if we have data partially cached. Alternatively we can - * return the short read, in which case the application will - * need to issue another SQE and wait for it. That SQE will - * need async punt anyway, so it's more efficient to do it - * here. - */ - if (force_nonblock && !(req->flags & REQ_F_NOWAIT) && - (req->flags & REQ_F_ISREG) && - ret2 > 0 && ret2 < io_size) - ret2 = -EAGAIN; /* Catch -EAGAIN return for forced non-blocking submission */ if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, nxt, req->in_async); } else { copy_iov: - ret = io_setup_async_io(req, io_size, iovec, + ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, &iter); if (ret) goto out_free; @@ -1805,46 +2255,58 @@ copy_iov: } } out_free: - kfree(iovec); + if (!io_wq_current_is_worker()) + kfree(iovec); return ret; } -static int io_write_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_import_iovec(WRITE, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t ret, io_size; - if (!req->io) { - ret = io_write_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(WRITE, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(WRITE, req, &iovec, &iter); + if (ret < 0) + return ret; + + /* Ensure we clear previously set non-block flag */ + if (!force_nonblock) + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; - file = kiocb->ki_filp; + req->result = 0; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1858,11 +2320,13 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, goto copy_iov; } - if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT)) + /* file path doesn't support NOWAIT for non-direct_IO */ + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && + (req->flags & REQ_F_ISREG)) goto copy_iov; iov_count = iov_iter_count(&iter); - ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; @@ -1874,22 +2338,22 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(file)->i_sb, + __sb_start_write(file_inode(req->file)->i_sb, SB_FREEZE_WRITE, true); - __sb_writers_release(file_inode(file)->i_sb, + __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - if (file->f_op->write_iter) - ret2 = call_write_iter(file, kiocb, &iter); + if (req->file->f_op->write_iter) + ret2 = call_write_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); + ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter); if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, nxt, req->in_async); } else { copy_iov: - ret = io_setup_async_io(req, io_size, iovec, + ret = io_setup_async_rw(req, io_size, iovec, inline_vecs, &iter); if (ret) goto out_free; @@ -1897,7 +2361,8 @@ copy_iov: } } out_free: - kfree(iovec); + if (!io_wq_current_is_worker()) + kfree(iovec); return ret; } @@ -1928,45 +2393,507 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; + req->sync.flags = READ_ONCE(sqe->fsync_flags); + if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC)) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); return 0; } -static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static bool io_req_cancelled(struct io_kiocb *req) { - loff_t sqe_off = READ_ONCE(sqe->off); - loff_t sqe_len = READ_ONCE(sqe->len); - loff_t end = sqe_off + sqe_len; - unsigned fsync_flags; + if (req->work.flags & IO_WQ_WORK_CANCEL) { + req_set_fail_links(req); + io_cqring_add_event(req, -ECANCELED); + io_put_req(req); + return true; + } + + return false; +} + +static void io_link_work_cb(struct io_wq_work **workptr) +{ + struct io_wq_work *work = *workptr; + struct io_kiocb *link = work->data; + + io_queue_linked_timeout(link); + work->func = io_wq_submit_work; +} + +static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt) +{ + struct io_kiocb *link; + + io_prep_async_work(nxt, &link); + *workptr = &nxt->work; + if (link) { + nxt->work.flags |= IO_WQ_WORK_CB; + nxt->work.func = io_link_work_cb; + nxt->work.data = link; + } +} + +static void io_fsync_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + loff_t end = req->sync.off + req->sync.len; + struct io_kiocb *nxt = NULL; int ret; - fsync_flags = READ_ONCE(sqe->fsync_flags); - if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC)) + if (io_req_cancelled(req)) + return; + + ret = vfs_fsync_range(req->file, req->sync.off, + end > 0 ? end : LLONG_MAX, + req->sync.flags & IORING_FSYNC_DATASYNC); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, &nxt); + if (nxt) + io_wq_assign_next(workptr, nxt); +} + +static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_wq_work *work, *old_work; + + /* fsync always requires a blocking context */ + if (force_nonblock) { + io_put_req(req); + req->work.func = io_fsync_finish; + return -EAGAIN; + } + + work = old_work = &req->work; + io_fsync_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); + return 0; +} + +static void io_fallocate_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; + int ret; + + ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, + req->sync.len); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, &nxt); + if (nxt) + io_wq_assign_next(workptr, nxt); +} + +static int io_fallocate_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (sqe->ioprio || sqe->buf_index || sqe->rw_flags) + return -EINVAL; + + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->addr); + req->sync.mode = READ_ONCE(sqe->len); + return 0; +} + +static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_wq_work *work, *old_work; + + /* fallocate always requiring blocking context */ + if (force_nonblock) { + io_put_req(req); + req->work.func = io_fallocate_finish; + return -EAGAIN; + } + + work = old_work = &req->work; + io_fallocate_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); + + return 0; +} + +static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + const char __user *fname; + int ret; + + if (sqe->ioprio || sqe->buf_index) return -EINVAL; - ret = io_prep_fsync(req, sqe); + req->open.dfd = READ_ONCE(sqe->fd); + req->open.how.mode = READ_ONCE(sqe->len); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + req->open.how.flags = READ_ONCE(sqe->open_flags); + + req->open.filename = getname(fname); + if (IS_ERR(req->open.filename)) { + ret = PTR_ERR(req->open.filename); + req->open.filename = NULL; + return ret; + } + + return 0; +} + +static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct open_how __user *how; + const char __user *fname; + size_t len; + int ret; + + if (sqe->ioprio || sqe->buf_index) + return -EINVAL; + + req->open.dfd = READ_ONCE(sqe->fd); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + len = READ_ONCE(sqe->len); + + if (len < OPEN_HOW_SIZE_VER0) + return -EINVAL; + + ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how, + len); if (ret) return ret; - /* fsync always requires a blocking context */ + if (!(req->open.how.flags & O_PATH) && force_o_largefile()) + req->open.how.flags |= O_LARGEFILE; + + req->open.filename = getname(fname); + if (IS_ERR(req->open.filename)) { + ret = PTR_ERR(req->open.filename); + req->open.filename = NULL; + return ret; + } + + return 0; +} + +static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct open_flags op; + struct file *file; + int ret; + if (force_nonblock) return -EAGAIN; - ret = vfs_fsync_range(req->rw.ki_filp, sqe_off, - end > 0 ? end : LLONG_MAX, - fsync_flags & IORING_FSYNC_DATASYNC); + ret = build_open_flags(&req->open.how, &op); + if (ret) + goto err; - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + ret = get_unused_fd_flags(req->open.how.flags); + if (ret < 0) + goto err; + + file = do_filp_open(req->open.dfd, req->open.filename, &op); + if (IS_ERR(file)) { + put_unused_fd(ret); + ret = PTR_ERR(file); + } else { + fsnotify_open(file); + fd_install(ret, file); + } +err: + putname(req->open.filename); + if (ret < 0) + req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req_find_next(req, nxt); return 0; } +static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + req->open.how = build_open_how(req->open.how.flags, req->open.how.mode); + return io_openat2(req, nxt, force_nonblock); +} + +static int io_epoll_ctl_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_EPOLL) + if (sqe->ioprio || sqe->buf_index) + return -EINVAL; + + req->epoll.epfd = READ_ONCE(sqe->fd); + req->epoll.op = READ_ONCE(sqe->len); + req->epoll.fd = READ_ONCE(sqe->off); + + if (ep_op_has_event(req->epoll.op)) { + struct epoll_event __user *ev; + + ev = u64_to_user_ptr(READ_ONCE(sqe->addr)); + if (copy_from_user(&req->epoll.event, ev, sizeof(*ev))) + return -EFAULT; + } + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ +#if defined(CONFIG_EPOLL) + struct io_epoll *ie = &req->epoll; + int ret; + + ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + if (sqe->ioprio || sqe->buf_index || sqe->off) + return -EINVAL; + + req->madvise.addr = READ_ONCE(sqe->addr); + req->madvise.len = READ_ONCE(sqe->len); + req->madvise.advice = READ_ONCE(sqe->fadvise_advice); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ +#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) + struct io_madvise *ma = &req->madvise; + int ret; + + if (force_nonblock) + return -EAGAIN; + + ret = do_madvise(ma->addr, ma->len, ma->advice); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + if (sqe->ioprio || sqe->buf_index || sqe->addr) + return -EINVAL; + + req->fadvise.offset = READ_ONCE(sqe->off); + req->fadvise.len = READ_ONCE(sqe->len); + req->fadvise.advice = READ_ONCE(sqe->fadvise_advice); + return 0; +} + +static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_fadvise *fa = &req->fadvise; + int ret; + + /* DONTNEED may block, others _should_ not */ + if (fa->advice == POSIX_FADV_DONTNEED && force_nonblock) + return -EAGAIN; + + ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; +} + +static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + const char __user *fname; + unsigned lookup_flags; + int ret; + + if (sqe->ioprio || sqe->buf_index) + return -EINVAL; + + req->open.dfd = READ_ONCE(sqe->fd); + req->open.mask = READ_ONCE(sqe->len); + fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); + req->open.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + req->open.how.flags = READ_ONCE(sqe->statx_flags); + + if (vfs_stat_set_lookup_flags(&lookup_flags, req->open.how.flags)) + return -EINVAL; + + req->open.filename = getname_flags(fname, lookup_flags, NULL); + if (IS_ERR(req->open.filename)) { + ret = PTR_ERR(req->open.filename); + req->open.filename = NULL; + return ret; + } + + return 0; +} + +static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_open *ctx = &req->open; + unsigned lookup_flags; + struct path path; + struct kstat stat; + int ret; + + if (force_nonblock) + return -EAGAIN; + + if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags)) + return -EINVAL; + +retry: + /* filename_lookup() drops it, keep a reference */ + ctx->filename->refcnt++; + + ret = filename_lookup(ctx->dfd, ctx->filename, lookup_flags, &path, + NULL); + if (ret) + goto err; + + ret = vfs_getattr(&path, &stat, ctx->mask, ctx->how.flags); + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + if (!ret) + ret = cp_statx(&stat, ctx->buffer); +err: + putname(ctx->filename); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, nxt); + return 0; +} + +static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + /* + * If we queue this for async, it must not be cancellable. That would + * leave the 'file' in an undeterminate state. + */ + req->work.flags |= IO_WQ_WORK_NO_CANCEL; + + if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || + sqe->rw_flags || sqe->buf_index) + return -EINVAL; + if (sqe->flags & IOSQE_FIXED_FILE) + return -EINVAL; + + req->close.fd = READ_ONCE(sqe->fd); + if (req->file->f_op == &io_uring_fops || + req->close.fd == req->ctx->ring_fd) + return -EBADF; + + return 0; +} + +static void io_close_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; + + /* Invoked with files, we need to do the close */ + if (req->work.files) { + int ret; + + ret = filp_close(req->close.put_file, req->work.files); + if (ret < 0) { + req_set_fail_links(req); + } + io_cqring_add_event(req, ret); + } + + fput(req->close.put_file); + + /* we bypassed the re-issue, drop the submission reference */ + io_put_req(req); + io_put_req_find_next(req, &nxt); + if (nxt) + io_wq_assign_next(workptr, nxt); +} + +static int io_close(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + int ret; + + req->close.put_file = NULL; + ret = __close_fd_get_file(req->close.fd, &req->close.put_file); + if (ret < 0) + return ret; + + /* if the file has a flush method, be safe and punt to async */ + if (req->close.put_file->f_op->flush && !io_wq_current_is_worker()) + goto eagain; + + /* + * No ->flush(), safely close from here and just punt the + * fput() to async context. + */ + ret = filp_close(req->close.put_file, current->files); + + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + + if (io_wq_current_is_worker()) { + struct io_wq_work *old_work, *work; + + old_work = work = &req->work; + io_close_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); + return 0; + } + +eagain: + req->work.func = io_close_finish; + return -EAGAIN; +} + static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - int ret = 0; if (!req->file) return -EBADF; @@ -1976,59 +2903,89 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - return ret; + req->sync.off = READ_ONCE(sqe->off); + req->sync.len = READ_ONCE(sqe->len); + req->sync.flags = READ_ONCE(sqe->sync_range_flags); + return 0; } -static int io_sync_file_range(struct io_kiocb *req, - const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, - bool force_nonblock) +static void io_sync_file_range_finish(struct io_wq_work **workptr) { - loff_t sqe_off; - loff_t sqe_len; - unsigned flags; + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; int ret; - ret = io_prep_sfr(req, sqe); - if (ret) - return ret; + if (io_req_cancelled(req)) + return; + + ret = sync_file_range(req->file, req->sync.off, req->sync.len, + req->sync.flags); + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req_find_next(req, &nxt); + if (nxt) + io_wq_assign_next(workptr, nxt); +} + +static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_wq_work *work, *old_work; /* sync_file_range always requires a blocking context */ - if (force_nonblock) + if (force_nonblock) { + io_put_req(req); + req->work.func = io_sync_file_range_finish; return -EAGAIN; + } - sqe_off = READ_ONCE(sqe->off); - sqe_len = READ_ONCE(sqe->len); - flags = READ_ONCE(sqe->sync_range_flags); + work = old_work = &req->work; + io_sync_file_range_finish(&work); + if (work && work != old_work) + *nxt = container_of(work, struct io_kiocb, work); + return 0; +} - ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags); +#if defined(CONFIG_NET) +static void io_sendrecv_async(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct iovec *iov = NULL; - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; - io_cqring_add_event(req, ret); - io_put_req_find_next(req, nxt); - return 0; + if (req->io->rw.iov != req->io->rw.fast_iov) + iov = req->io->msg.iov; + io_wq_submit_work(workptr); + kfree(iov); } +#endif -static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + sr->len = READ_ONCE(sqe->len); + + if (!io || req->opcode == IORING_OP_SEND) + return 0; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); - return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov); + io->msg.iov = io->msg.fast_iov; + return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.iov); #else - return 0; + return -EOPNOTSUPP; #endif } -static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) + struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2037,50 +2994,55 @@ static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { - struct io_async_ctx io, *copy; + struct io_async_ctx io; struct sockaddr_storage addr; - struct msghdr *kmsg; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - if (req->io) { - kmsg = &req->io->msg.msg; - kmsg->msg_name = &addr; + kmsg = &req->io->msg; + kmsg->msg.msg_name = &addr; + /* if iov is set, it's allocated already */ + if (!kmsg->iov) + kmsg->iov = kmsg->fast_iov; + kmsg->msg.msg_iter.iov = kmsg->iov; } else { - kmsg = &io.msg.msg; - kmsg->msg_name = &addr; + struct io_sr_msg *sr = &req->sr_msg; + + kmsg = &io.msg; + kmsg->msg.msg_name = &addr; + io.msg.iov = io.msg.fast_iov; - ret = io_sendmsg_prep(req, &io); + ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.iov); if (ret) - goto out; + return ret; } - ret = __sys_sendmsg_sock(sock, kmsg, flags); + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if (force_nonblock && ret == -EAGAIN) { - copy = kmalloc(sizeof(*copy), GFP_KERNEL); - if (!copy) { - ret = -ENOMEM; - goto out; - } - memcpy(©->msg, &io.msg, sizeof(copy->msg)); - req->io = copy; - memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &req->io->sqe; - return ret; + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) + return -ENOMEM; + memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); + req->work.func = io_sendrecv_async; + return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } -out: + if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); io_cqring_add_event(req, ret); - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req_find_next(req, nxt); return 0; #else @@ -2088,26 +3050,82 @@ out: #endif } -static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_send(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct socket *sock; + int ret; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); - return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr, - &io->msg.iov); -#else + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + sock = sock_from_file(req->file, &ret); + if (sock) { + struct io_sr_msg *sr = &req->sr_msg; + struct msghdr msg; + struct iovec iov; + unsigned flags; + + ret = import_single_range(WRITE, sr->buf, sr->len, &iov, + &msg.msg_iter); + if (ret) + return ret; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_sendmsg_sock(sock, &msg, flags); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + } + + io_cqring_add_event(req, ret); + if (ret < 0) + req_set_fail_links(req); + io_put_req_find_next(req, nxt); return 0; +#else + return -EOPNOTSUPP; +#endif +} + +static int io_recvmsg_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_NET) + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + + if (!io || req->opcode == IORING_OP_RECV) + return 0; + + io->msg.iov = io->msg.fast_iov; + return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.uaddr, &io->msg.iov); +#else + return -EOPNOTSUPP; #endif } -static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) + struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2116,53 +3134,57 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { - struct user_msghdr __user *msg; - struct io_async_ctx io, *copy; + struct io_async_ctx io; struct sockaddr_storage addr; - struct msghdr *kmsg; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - - msg = (struct user_msghdr __user *) (unsigned long) - READ_ONCE(sqe->addr); if (req->io) { - kmsg = &req->io->msg.msg; - kmsg->msg_name = &addr; + kmsg = &req->io->msg; + kmsg->msg.msg_name = &addr; + /* if iov is set, it's allocated already */ + if (!kmsg->iov) + kmsg->iov = kmsg->fast_iov; + kmsg->msg.msg_iter.iov = kmsg->iov; } else { - kmsg = &io.msg.msg; - kmsg->msg_name = &addr; + struct io_sr_msg *sr = &req->sr_msg; + + kmsg = &io.msg; + kmsg->msg.msg_name = &addr; + io.msg.iov = io.msg.fast_iov; - ret = io_recvmsg_prep(req, &io); + ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.uaddr, + &io.msg.iov); if (ret) - goto out; + return ret; } - ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags); + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg, + kmsg->uaddr, flags); if (force_nonblock && ret == -EAGAIN) { - copy = kmalloc(sizeof(*copy), GFP_KERNEL); - if (!copy) { - ret = -ENOMEM; - goto out; - } - memcpy(copy, &io, sizeof(*copy)); - req->io = copy; - memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &req->io->sqe; - return ret; + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) + return -ENOMEM; + memcpy(&req->io->msg, &io.msg, sizeof(io.msg)); + req->work.func = io_sendrecv_async; + return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; } -out: + if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) + kfree(kmsg->iov); io_cqring_add_event(req, ret); - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req_find_next(req, nxt); return 0; #else @@ -2170,101 +3192,193 @@ out: #endif } -static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) - struct sockaddr __user *addr; - int __user *addr_len; - unsigned file_flags; - int flags, ret; + struct socket *sock; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + sock = sock_from_file(req->file, &ret); + if (sock) { + struct io_sr_msg *sr = &req->sr_msg; + struct msghdr msg; + struct iovec iov; + unsigned flags; + + ret = import_single_range(READ, sr->buf, sr->len, &iov, + &msg.msg_iter); + if (ret) + return ret; + + msg.msg_name = NULL; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; + msg.msg_iocb = NULL; + msg.msg_flags = 0; + + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_recvmsg_sock(sock, &msg, NULL, NULL, flags); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + } + + io_cqring_add_event(req, ret); + if (ret < 0) + req_set_fail_links(req); + io_put_req_find_next(req, nxt); + return 0; +#else + return -EOPNOTSUPP; +#endif +} + + +static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ +#if defined(CONFIG_NET) + struct io_accept *accept = &req->accept; if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); - addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); - flags = READ_ONCE(sqe->accept_flags); - file_flags = force_nonblock ? O_NONBLOCK : 0; + accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + accept->flags = READ_ONCE(sqe->accept_flags); + return 0; +#else + return -EOPNOTSUPP; +#endif +} - ret = __sys_accept4_file(req->file, file_flags, addr, addr_len, flags); - if (ret == -EAGAIN && force_nonblock) { - req->work.flags |= IO_WQ_WORK_NEEDS_FILES; +#if defined(CONFIG_NET) +static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ + struct io_accept *accept = &req->accept; + unsigned file_flags; + int ret; + + file_flags = force_nonblock ? O_NONBLOCK : 0; + ret = __sys_accept4_file(req->file, file_flags, accept->addr, + accept->addr_len, accept->flags); + if (ret == -EAGAIN && force_nonblock) return -EAGAIN; - } if (ret == -ERESTARTSYS) ret = -EINTR; - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req_find_next(req, nxt); return 0; -#else - return -EOPNOTSUPP; -#endif } -static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) +static void io_accept_finish(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; + + if (io_req_cancelled(req)) + return; + __io_accept(req, &nxt, false); + if (nxt) + io_wq_assign_next(workptr, nxt); +} +#endif + +static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct sockaddr __user *addr; - int addr_len; + int ret; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); - addr_len = READ_ONCE(sqe->addr2); - return move_addr_to_kernel(addr, addr_len, &io->connect.address); -#else + ret = __io_accept(req, nxt, force_nonblock); + if (ret == -EAGAIN && force_nonblock) { + req->work.func = io_accept_finish; + io_put_req(req); + return -EAGAIN; + } return 0; +#else + return -EOPNOTSUPP; #endif } -static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - struct io_async_ctx __io, *io; - unsigned file_flags; - int addr_len, ret; + struct io_connect *conn = &req->connect; + struct io_async_ctx *io = req->io; if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) return -EINVAL; - addr_len = READ_ONCE(sqe->addr2); - file_flags = force_nonblock ? O_NONBLOCK : 0; + conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + conn->addr_len = READ_ONCE(sqe->addr2); + + if (!io) + return 0; + + return move_addr_to_kernel(conn->addr, conn->addr_len, + &io->connect.address); +#else + return -EOPNOTSUPP; +#endif +} + +static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt, + bool force_nonblock) +{ +#if defined(CONFIG_NET) + struct io_async_ctx __io, *io; + unsigned file_flags; + int ret; if (req->io) { io = req->io; } else { - ret = io_connect_prep(req, &__io); + ret = move_addr_to_kernel(req->connect.addr, + req->connect.addr_len, + &__io.connect.address); if (ret) goto out; io = &__io; } - ret = __sys_connect_file(req->file, &io->connect.address, addr_len, - file_flags); + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_connect_file(req->file, &io->connect.address, + req->connect.addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) { + if (req->io) + return -EAGAIN; + if (io_alloc_async_ctx(req)) { ret = -ENOMEM; goto out; } - memcpy(&io->connect, &__io.connect, sizeof(io->connect)); - req->io = io; - memcpy(&io->sqe, req->sqe, sizeof(*req->sqe)); - req->sqe = &io->sqe; + memcpy(&req->io->connect, &__io.connect, sizeof(__io.connect)); return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; out: - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req_find_next(req, nxt); return 0; @@ -2279,8 +3393,8 @@ static void io_poll_remove_one(struct io_kiocb *req) spin_lock(&poll->head->lock); WRITE_ONCE(poll->canceled, true); - if (!list_empty(&poll->wait->entry)) { - list_del_init(&poll->wait->entry); + if (!list_empty(&poll->wait.entry)) { + list_del_init(&poll->wait.entry); io_queue_async_work(req); } spin_unlock(&poll->head->lock); @@ -2320,28 +3434,37 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) return -ENOENT; } +static int io_poll_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || + sqe->poll_events) + return -EINVAL; + + req->poll.addr = READ_ONCE(sqe->addr); + return 0; +} + /* * Find a running poll command that matches one specified in sqe->addr, * and remove it if found. */ -static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_poll_remove(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + u64 addr; int ret; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || - sqe->poll_events) - return -EINVAL; - + addr = req->poll.addr; spin_lock_irq(&ctx->completion_lock); - ret = io_poll_cancel(ctx, READ_ONCE(sqe->addr)); + ret = io_poll_cancel(ctx, addr); spin_unlock_irq(&ctx->completion_lock); io_cqring_add_event(req, ret); - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req(req); return 0; } @@ -2351,7 +3474,6 @@ static void io_poll_complete(struct io_kiocb *req, __poll_t mask, int error) struct io_ring_ctx *ctx = req->ctx; req->poll.done = true; - kfree(req->poll.wait); if (error) io_cqring_fill_event(req, error); else @@ -2389,7 +3511,7 @@ static void io_poll_complete_work(struct io_wq_work **workptr) */ spin_lock_irq(&ctx->completion_lock); if (!mask && ret != -ECANCELED) { - add_wait_queue(poll->head, poll->wait); + add_wait_queue(poll->head, &poll->wait); spin_unlock_irq(&ctx->completion_lock); return; } @@ -2399,11 +3521,44 @@ static void io_poll_complete_work(struct io_wq_work **workptr) io_cqring_ev_posted(ctx); - if (ret < 0 && req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req_find_next(req, &nxt); if (nxt) - *workptr = &nxt->work; + io_wq_assign_next(workptr, nxt); +} + +static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes) +{ + struct io_kiocb *req, *tmp; + struct req_batch rb; + + rb.to_free = rb.need_iter = 0; + spin_lock_irq(&ctx->completion_lock); + llist_for_each_entry_safe(req, tmp, nodes, llist_node) { + hash_del(&req->hash_node); + io_poll_complete(req, req->result, 0); + + if (refcount_dec_and_test(&req->refs) && + !io_req_multi_free(&rb, req)) { + req->flags |= REQ_F_COMP_LOCKED; + io_free_req(req); + } + } + spin_unlock_irq(&ctx->completion_lock); + + io_cqring_ev_posted(ctx); + io_free_req_many(ctx, &rb); +} + +static void io_poll_flush(struct io_wq_work **workptr) +{ + struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work); + struct llist_node *nodes; + + nodes = llist_del_all(&req->ctx->poll_llist); + if (nodes) + __io_poll_flush(req->ctx, nodes); } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, @@ -2413,13 +3568,12 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct io_kiocb *req = container_of(poll, struct io_kiocb, poll); struct io_ring_ctx *ctx = req->ctx; __poll_t mask = key_to_poll(key); - unsigned long flags; /* for instances that support it check for an event match first: */ if (mask && !(mask & poll->events)) return 0; - list_del_init(&poll->wait->entry); + list_del_init(&poll->wait.entry); /* * Run completion inline if we can. We're using trylock here because @@ -2427,17 +3581,31 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, * If we have a link timeout we're going to need the completion_lock * for finalizing the request, mark us as having grabbed that already. */ - if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) { - hash_del(&req->hash_node); - io_poll_complete(req, mask, 0); - req->flags |= REQ_F_COMP_LOCKED; - io_put_req(req); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + if (mask) { + unsigned long flags; - io_cqring_ev_posted(ctx); - } else { - io_queue_async_work(req); + if (llist_empty(&ctx->poll_llist) && + spin_trylock_irqsave(&ctx->completion_lock, flags)) { + hash_del(&req->hash_node); + io_poll_complete(req, mask, 0); + req->flags |= REQ_F_COMP_LOCKED; + io_put_req(req); + spin_unlock_irqrestore(&ctx->completion_lock, flags); + + io_cqring_ev_posted(ctx); + req = NULL; + } else { + req->result = mask; + req->llist_node.next = NULL; + /* if the list wasn't empty, we're done */ + if (!llist_add(&req->llist_node, &ctx->poll_llist)) + req = NULL; + else + req->work.func = io_poll_flush; + } } + if (req) + io_queue_async_work(req); return 1; } @@ -2460,7 +3628,7 @@ static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, pt->error = 0; pt->req->poll.head = head; - add_wait_queue(head, pt->req->poll.wait); + add_wait_queue(head, &pt->req->poll.wait); } static void io_poll_req_insert(struct io_kiocb *req) @@ -2472,14 +3640,9 @@ static void io_poll_req_insert(struct io_kiocb *req) hlist_add_head(&req->hash_node, list); } -static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt) +static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_poll_iocb *poll = &req->poll; - struct io_ring_ctx *ctx = req->ctx; - struct io_poll_table ipt; - bool cancel = false; - __poll_t mask; u16 events; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) @@ -2489,14 +3652,20 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (!poll->file) return -EBADF; - poll->wait = kmalloc(sizeof(*poll->wait), GFP_KERNEL); - if (!poll->wait) - return -ENOMEM; - - req->io = NULL; - INIT_IO_WORK(&req->work, io_poll_complete_work); events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; + return 0; +} + +static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt) +{ + struct io_poll_iocb *poll = &req->poll; + struct io_ring_ctx *ctx = req->ctx; + struct io_poll_table ipt; + bool cancel = false; + __poll_t mask; + + INIT_IO_WORK(&req->work, io_poll_complete_work); INIT_HLIST_NODE(&req->hash_node); poll->head = NULL; @@ -2509,9 +3678,9 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ - INIT_LIST_HEAD(&poll->wait->entry); - init_waitqueue_func_entry(poll->wait, io_poll_wake); - poll->wait->private = poll; + INIT_LIST_HEAD(&poll->wait.entry); + init_waitqueue_func_entry(&poll->wait, io_poll_wake); + poll->wait.private = poll; INIT_LIST_HEAD(&req->list); @@ -2520,14 +3689,14 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe, spin_lock_irq(&ctx->completion_lock); if (likely(poll->head)) { spin_lock(&poll->head->lock); - if (unlikely(list_empty(&poll->wait->entry))) { + if (unlikely(list_empty(&poll->wait.entry))) { if (ipt.error) cancel = true; ipt.error = 0; mask = 0; } if (mask || ipt.error) - list_del_init(&poll->wait->entry); + list_del_init(&poll->wait.entry); else if (cancel) WRITE_ONCE(poll->canceled, true); else if (!poll->done) /* actually waiting for an event */ @@ -2567,7 +3736,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) /* * Adjust the reqs sequence before the current one because it - * will consume a slot in the cq_ring and the the cq_tail + * will consume a slot in the cq_ring and the cq_tail * pointer will be increased, otherwise other timeout reqs may * return in advance without waiting for enough wait_nr. */ @@ -2582,8 +3751,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(req); io_put_req(req); return HRTIMER_NORESTART; } @@ -2608,48 +3776,52 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) if (ret == -1) return -EALREADY; - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(req); io_cqring_fill_event(req, -ECANCELED); io_put_req(req); return 0; } +static int io_timeout_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) + return -EINVAL; + + req->timeout.addr = READ_ONCE(sqe->addr); + req->timeout.flags = READ_ONCE(sqe->timeout_flags); + if (req->timeout.flags) + return -EINVAL; + + return 0; +} + /* * Remove or update an existing timeout command */ -static int io_timeout_remove(struct io_kiocb *req, - const struct io_uring_sqe *sqe) +static int io_timeout_remove(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - unsigned flags; int ret; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) - return -EINVAL; - if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) - return -EINVAL; - flags = READ_ONCE(sqe->timeout_flags); - if (flags) - return -EINVAL; - spin_lock_irq(&ctx->completion_lock); - ret = io_timeout_cancel(ctx, READ_ONCE(sqe->addr)); + ret = io_timeout_cancel(ctx, req->timeout.addr); io_cqring_fill_event(req, ret); io_commit_cqring(ctx); spin_unlock_irq(&ctx->completion_lock); io_cqring_ev_posted(ctx); - if (ret < 0 && req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req(req); return 0; } -static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, +static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, bool is_timeout_link) { - const struct io_uring_sqe *sqe = req->sqe; struct io_timeout_data *data; unsigned flags; @@ -2663,7 +3835,12 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, if (flags & ~IORING_TIMEOUT_ABS) return -EINVAL; - data = &io->timeout; + req->timeout.count = READ_ONCE(sqe->off); + + if (!req->io && io_alloc_async_ctx(req)) + return -ENOMEM; + + data = &req->io->timeout; data->req = req; req->flags |= REQ_F_TIMEOUT; @@ -2676,32 +3853,17 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, data->mode = HRTIMER_MODE_REL; hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); - req->io = io; return 0; } -static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_timeout(struct io_kiocb *req) { unsigned count; struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data; - struct io_async_ctx *io; struct list_head *entry; unsigned span = 0; - io = req->io; - if (!io) { - int ret; - - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) - return -ENOMEM; - ret = io_timeout_prep(req, io, false); - if (ret) { - kfree(io); - return ret; - } - } data = &req->io->timeout; /* @@ -2709,7 +3871,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe) * timeout event to be satisfied. If it isn't set, then this is * a pure timeout request, sequence isn't used. */ - count = READ_ONCE(sqe->off); + count = req->timeout.count; if (!count) { req->flags |= REQ_F_TIMEOUT_NOSEQ; spin_lock_irq(&ctx->completion_lock); @@ -2822,89 +3984,185 @@ done: spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - if (ret < 0 && (req->flags & REQ_F_LINK)) - req->flags |= REQ_F_FAIL_LINK; + if (ret < 0) + req_set_fail_links(req); io_put_req_find_next(req, nxt); } -static int io_async_cancel(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt) +static int io_async_cancel_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; - - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags) return -EINVAL; - io_async_find_and_cancel(ctx, req, READ_ONCE(sqe->addr), nxt, 0); + req->cancel.addr = READ_ONCE(sqe->addr); return 0; } -static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt) { - struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct iov_iter iter; - ssize_t ret; + struct io_ring_ctx *ctx = req->ctx; - memcpy(&io->sqe, req->sqe, sizeof(io->sqe)); - req->sqe = &io->sqe; + io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0); + return 0; +} - switch (io->sqe.opcode) { +static int io_files_update_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + if (sqe->flags || sqe->ioprio || sqe->rw_flags) + return -EINVAL; + + req->files_update.offset = READ_ONCE(sqe->off); + req->files_update.nr_args = READ_ONCE(sqe->len); + if (!req->files_update.nr_args) + return -EINVAL; + req->files_update.arg = READ_ONCE(sqe->addr); + return 0; +} + +static int io_files_update(struct io_kiocb *req, bool force_nonblock) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_uring_files_update up; + int ret; + + if (force_nonblock) + return -EAGAIN; + + up.offset = req->files_update.offset; + up.fds = req->files_update.arg; + + mutex_lock(&ctx->uring_lock); + ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args); + mutex_unlock(&ctx->uring_lock); + + if (ret < 0) + req_set_fail_links(req); + io_cqring_add_event(req, ret); + io_put_req(req); + return 0; +} + +static int io_req_defer_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + ssize_t ret = 0; + + if (io_op_defs[req->opcode].file_table) { + ret = io_grab_files(req); + if (unlikely(ret)) + return ret; + } + + io_req_work_grab_env(req, &io_op_defs[req->opcode]); + + switch (req->opcode) { + case IORING_OP_NOP: + break; case IORING_OP_READV: case IORING_OP_READ_FIXED: - ret = io_read_prep(req, &iovec, &iter, true); + case IORING_OP_READ: + ret = io_read_prep(req, sqe, true); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: - ret = io_write_prep(req, &iovec, &iter, true); + case IORING_OP_WRITE: + ret = io_write_prep(req, sqe, true); + break; + case IORING_OP_POLL_ADD: + ret = io_poll_add_prep(req, sqe); + break; + case IORING_OP_POLL_REMOVE: + ret = io_poll_remove_prep(req, sqe); + break; + case IORING_OP_FSYNC: + ret = io_prep_fsync(req, sqe); + break; + case IORING_OP_SYNC_FILE_RANGE: + ret = io_prep_sfr(req, sqe); break; case IORING_OP_SENDMSG: - ret = io_sendmsg_prep(req, io); + case IORING_OP_SEND: + ret = io_sendmsg_prep(req, sqe); break; case IORING_OP_RECVMSG: - ret = io_recvmsg_prep(req, io); + case IORING_OP_RECV: + ret = io_recvmsg_prep(req, sqe); break; case IORING_OP_CONNECT: - ret = io_connect_prep(req, io); + ret = io_connect_prep(req, sqe); break; case IORING_OP_TIMEOUT: - return io_timeout_prep(req, io, false); + ret = io_timeout_prep(req, sqe, false); + break; + case IORING_OP_TIMEOUT_REMOVE: + ret = io_timeout_remove_prep(req, sqe); + break; + case IORING_OP_ASYNC_CANCEL: + ret = io_async_cancel_prep(req, sqe); + break; case IORING_OP_LINK_TIMEOUT: - return io_timeout_prep(req, io, true); + ret = io_timeout_prep(req, sqe, true); + break; + case IORING_OP_ACCEPT: + ret = io_accept_prep(req, sqe); + break; + case IORING_OP_FALLOCATE: + ret = io_fallocate_prep(req, sqe); + break; + case IORING_OP_OPENAT: + ret = io_openat_prep(req, sqe); + break; + case IORING_OP_CLOSE: + ret = io_close_prep(req, sqe); + break; + case IORING_OP_FILES_UPDATE: + ret = io_files_update_prep(req, sqe); + break; + case IORING_OP_STATX: + ret = io_statx_prep(req, sqe); + break; + case IORING_OP_FADVISE: + ret = io_fadvise_prep(req, sqe); + break; + case IORING_OP_MADVISE: + ret = io_madvise_prep(req, sqe); + break; + case IORING_OP_OPENAT2: + ret = io_openat2_prep(req, sqe); + break; + case IORING_OP_EPOLL_CTL: + ret = io_epoll_ctl_prep(req, sqe); + break; default: - req->io = io; - return 0; + printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", + req->opcode); + ret = -EINVAL; + break; } - if (ret < 0) - return ret; - - req->io = io; - io_req_map_io(req, ret, iovec, inline_vecs, &iter); - return 0; + return ret; } -static int io_req_defer(struct io_kiocb *req) +static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - struct io_async_ctx *io; int ret; /* Still need defer if there is pending req in defer list. */ if (!req_need_defer(req) && list_empty(&ctx->defer_list)) return 0; - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) + if (!req->io && io_alloc_async_ctx(req)) return -EAGAIN; - ret = io_req_defer_prep(req, io); - if (ret < 0) { - kfree(io); + ret = io_req_defer_prep(req, sqe); + if (ret < 0) return ret; - } spin_lock_irq(&ctx->completion_lock); if (!req_need_defer(req) && list_empty(&ctx->defer_list)) { @@ -2918,66 +4176,203 @@ static int io_req_defer(struct io_kiocb *req) return -EIOCBQUEUED; } -__attribute__((nonnull)) -static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, - bool force_nonblock) +static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { - int ret, opcode; struct io_ring_ctx *ctx = req->ctx; + int ret; - opcode = READ_ONCE(req->sqe->opcode); - switch (opcode) { + switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req); break; case IORING_OP_READV: - if (unlikely(req->sqe->buf_index)) - return -EINVAL; - ret = io_read(req, nxt, force_nonblock); - break; - case IORING_OP_WRITEV: - if (unlikely(req->sqe->buf_index)) - return -EINVAL; - ret = io_write(req, nxt, force_nonblock); - break; case IORING_OP_READ_FIXED: + case IORING_OP_READ: + if (sqe) { + ret = io_read_prep(req, sqe, force_nonblock); + if (ret < 0) + break; + } ret = io_read(req, nxt, force_nonblock); break; + case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: + case IORING_OP_WRITE: + if (sqe) { + ret = io_write_prep(req, sqe, force_nonblock); + if (ret < 0) + break; + } ret = io_write(req, nxt, force_nonblock); break; case IORING_OP_FSYNC: - ret = io_fsync(req, req->sqe, nxt, force_nonblock); + if (sqe) { + ret = io_prep_fsync(req, sqe); + if (ret < 0) + break; + } + ret = io_fsync(req, nxt, force_nonblock); break; case IORING_OP_POLL_ADD: - ret = io_poll_add(req, req->sqe, nxt); + if (sqe) { + ret = io_poll_add_prep(req, sqe); + if (ret) + break; + } + ret = io_poll_add(req, nxt); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove(req, req->sqe); + if (sqe) { + ret = io_poll_remove_prep(req, sqe); + if (ret < 0) + break; + } + ret = io_poll_remove(req); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_sync_file_range(req, req->sqe, nxt, force_nonblock); + if (sqe) { + ret = io_prep_sfr(req, sqe); + if (ret < 0) + break; + } + ret = io_sync_file_range(req, nxt, force_nonblock); break; case IORING_OP_SENDMSG: - ret = io_sendmsg(req, req->sqe, nxt, force_nonblock); + case IORING_OP_SEND: + if (sqe) { + ret = io_sendmsg_prep(req, sqe); + if (ret < 0) + break; + } + if (req->opcode == IORING_OP_SENDMSG) + ret = io_sendmsg(req, nxt, force_nonblock); + else + ret = io_send(req, nxt, force_nonblock); break; case IORING_OP_RECVMSG: - ret = io_recvmsg(req, req->sqe, nxt, force_nonblock); + case IORING_OP_RECV: + if (sqe) { + ret = io_recvmsg_prep(req, sqe); + if (ret) + break; + } + if (req->opcode == IORING_OP_RECVMSG) + ret = io_recvmsg(req, nxt, force_nonblock); + else + ret = io_recv(req, nxt, force_nonblock); break; case IORING_OP_TIMEOUT: - ret = io_timeout(req, req->sqe); + if (sqe) { + ret = io_timeout_prep(req, sqe, false); + if (ret) + break; + } + ret = io_timeout(req); break; case IORING_OP_TIMEOUT_REMOVE: - ret = io_timeout_remove(req, req->sqe); + if (sqe) { + ret = io_timeout_remove_prep(req, sqe); + if (ret) + break; + } + ret = io_timeout_remove(req); break; case IORING_OP_ACCEPT: - ret = io_accept(req, req->sqe, nxt, force_nonblock); + if (sqe) { + ret = io_accept_prep(req, sqe); + if (ret) + break; + } + ret = io_accept(req, nxt, force_nonblock); break; case IORING_OP_CONNECT: - ret = io_connect(req, req->sqe, nxt, force_nonblock); + if (sqe) { + ret = io_connect_prep(req, sqe); + if (ret) + break; + } + ret = io_connect(req, nxt, force_nonblock); break; case IORING_OP_ASYNC_CANCEL: - ret = io_async_cancel(req, req->sqe, nxt); + if (sqe) { + ret = io_async_cancel_prep(req, sqe); + if (ret) + break; + } + ret = io_async_cancel(req, nxt); + break; + case IORING_OP_FALLOCATE: + if (sqe) { + ret = io_fallocate_prep(req, sqe); + if (ret) + break; + } + ret = io_fallocate(req, nxt, force_nonblock); + break; + case IORING_OP_OPENAT: + if (sqe) { + ret = io_openat_prep(req, sqe); + if (ret) + break; + } + ret = io_openat(req, nxt, force_nonblock); + break; + case IORING_OP_CLOSE: + if (sqe) { + ret = io_close_prep(req, sqe); + if (ret) + break; + } + ret = io_close(req, nxt, force_nonblock); + break; + case IORING_OP_FILES_UPDATE: + if (sqe) { + ret = io_files_update_prep(req, sqe); + if (ret) + break; + } + ret = io_files_update(req, force_nonblock); + break; + case IORING_OP_STATX: + if (sqe) { + ret = io_statx_prep(req, sqe); + if (ret) + break; + } + ret = io_statx(req, nxt, force_nonblock); + break; + case IORING_OP_FADVISE: + if (sqe) { + ret = io_fadvise_prep(req, sqe); + if (ret) + break; + } + ret = io_fadvise(req, nxt, force_nonblock); + break; + case IORING_OP_MADVISE: + if (sqe) { + ret = io_madvise_prep(req, sqe); + if (ret) + break; + } + ret = io_madvise(req, nxt, force_nonblock); + break; + case IORING_OP_OPENAT2: + if (sqe) { + ret = io_openat2_prep(req, sqe); + if (ret) + break; + } + ret = io_openat2(req, nxt, force_nonblock); + break; + case IORING_OP_EPOLL_CTL: + if (sqe) { + ret = io_epoll_ctl_prep(req, sqe); + if (ret) + break; + } + ret = io_epoll_ctl(req, nxt, force_nonblock); break; default: ret = -EINVAL; @@ -2988,29 +4383,24 @@ static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt, return ret; if (ctx->flags & IORING_SETUP_IOPOLL) { + const bool in_async = io_wq_current_is_worker(); + if (req->result == -EAGAIN) return -EAGAIN; /* workqueue context doesn't hold uring_lock, grab it now */ - if (req->in_async) + if (in_async) mutex_lock(&ctx->uring_lock); + io_iopoll_req_issued(req); - if (req->in_async) + + if (in_async) mutex_unlock(&ctx->uring_lock); } return 0; } -static void io_link_work_cb(struct io_wq_work **workptr) -{ - struct io_wq_work *work = *workptr; - struct io_kiocb *link = work->data; - - io_queue_linked_timeout(link); - work->func = io_wq_submit_work; -} - static void io_wq_submit_work(struct io_wq_work **workptr) { struct io_wq_work *work = *workptr; @@ -3018,17 +4408,17 @@ static void io_wq_submit_work(struct io_wq_work **workptr) struct io_kiocb *nxt = NULL; int ret = 0; - /* Ensure we clear previously set non-block flag */ - req->rw.ki_flags &= ~IOCB_NOWAIT; - - if (work->flags & IO_WQ_WORK_CANCEL) + /* if NO_CANCEL is set, we must still run the work */ + if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) == + IO_WQ_WORK_CANCEL) { ret = -ECANCELED; + } if (!ret) { req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0; req->in_async = true; do { - ret = io_issue_sqe(req, &nxt, false); + ret = io_issue_sqe(req, NULL, &nxt, false); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't @@ -3044,41 +4434,23 @@ static void io_wq_submit_work(struct io_wq_work **workptr) io_put_req(req); if (ret) { - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(req); io_cqring_add_event(req, ret); io_put_req(req); } /* if a dependent link is ready, pass it back */ - if (!ret && nxt) { - struct io_kiocb *link; - - io_prep_async_work(nxt, &link); - *workptr = &nxt->work; - if (link) { - nxt->work.flags |= IO_WQ_WORK_CB; - nxt->work.func = io_link_work_cb; - nxt->work.data = link; - } - } + if (!ret && nxt) + io_wq_assign_next(workptr, nxt); } -static bool io_op_needs_file(const struct io_uring_sqe *sqe) +static int io_req_needs_file(struct io_kiocb *req, int fd) { - int op = READ_ONCE(sqe->opcode); - - switch (op) { - case IORING_OP_NOP: - case IORING_OP_POLL_REMOVE: - case IORING_OP_TIMEOUT: - case IORING_OP_TIMEOUT_REMOVE: - case IORING_OP_ASYNC_CANCEL: - case IORING_OP_LINK_TIMEOUT: - return false; - default: - return true; - } + if (!io_op_defs[req->opcode].needs_file) + return 0; + if (fd == -1 && io_op_defs[req->opcode].fd_non_neg) + return 0; + return 1; } static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, @@ -3086,27 +4458,25 @@ static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, { struct fixed_file_table *table; - table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT]; - return table->files[index & IORING_FILE_TABLE_MASK]; + table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT]; + return table->files[index & IORING_FILE_TABLE_MASK];; } -static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) +static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, + const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; unsigned flags; int fd; - flags = READ_ONCE(req->sqe->flags); - fd = READ_ONCE(req->sqe->fd); + flags = READ_ONCE(sqe->flags); + fd = READ_ONCE(sqe->fd); - if (flags & IOSQE_IO_DRAIN) - req->flags |= REQ_F_IO_DRAIN; - - if (!io_op_needs_file(req->sqe)) + if (!io_req_needs_file(req, fd)) return 0; if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->file_table || + if (unlikely(!ctx->file_data || (unsigned) fd >= ctx->nr_user_files)) return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); @@ -3114,6 +4484,7 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req) if (!req->file) return -EBADF; req->flags |= REQ_F_FIXED_FILE; + percpu_ref_get(&ctx->file_data->refs); } else { if (req->needs_fixed_file) return -EBADF; @@ -3131,6 +4502,11 @@ static int io_grab_files(struct io_kiocb *req) int ret = -EBADF; struct io_ring_ctx *ctx = req->ctx; + if (req->work.files) + return 0; + if (!ctx->ring_file) + return -EBADF; + rcu_read_lock(); spin_lock_irq(&ctx->inflight_lock); /* @@ -3139,7 +4515,7 @@ static int io_grab_files(struct io_kiocb *req) * the fd has changed since we started down this path, and disallow * this operation if it has. */ - if (fcheck(req->ring_fd) == req->ring_file) { + if (fcheck(ctx->ring_fd) == ctx->ring_file) { list_add(&req->inflight_entry, &ctx->inflight_list); req->flags |= REQ_F_INFLIGHT; req->work.files = current->files; @@ -3179,8 +4555,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->completion_lock, flags); if (prev) { - if (prev->flags & REQ_F_LINK) - prev->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(prev); io_async_find_and_cancel(ctx, req, prev->user_data, NULL, -ETIME); io_put_req(prev); @@ -3222,22 +4597,23 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb, link_list); - if (!nxt || nxt->sqe->opcode != IORING_OP_LINK_TIMEOUT) + if (!nxt || nxt->opcode != IORING_OP_LINK_TIMEOUT) return NULL; req->flags |= REQ_F_LINK_TIMEOUT; return nxt; } -static void __io_queue_sqe(struct io_kiocb *req) +static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); + struct io_kiocb *linked_timeout; struct io_kiocb *nxt = NULL; int ret; - ret = io_issue_sqe(req, &nxt, true); - if (nxt) - io_queue_async_work(nxt); +again: + linked_timeout = io_prep_linked_timeout(req); + + ret = io_issue_sqe(req, sqe, &nxt, true); /* * We async punt it if the file wasn't marked NOWAIT, or if the file @@ -3245,7 +4621,8 @@ static void __io_queue_sqe(struct io_kiocb *req) */ if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) || (req->flags & REQ_F_MUST_PUNT))) { - if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) { +punt: + if (io_op_defs[req->opcode].file_table) { ret = io_grab_files(req); if (ret) goto err; @@ -3256,7 +4633,7 @@ static void __io_queue_sqe(struct io_kiocb *req) * submit reference when the iocb is actually submitted. */ io_queue_async_work(req); - return; + goto done_req; } err: @@ -3273,32 +4650,45 @@ err: /* and drop final reference, if we failed */ if (ret) { io_cqring_add_event(req, ret); - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(req); io_put_req(req); } +done_req: + if (nxt) { + req = nxt; + nxt = NULL; + + if (req->flags & REQ_F_FORCE_ASYNC) + goto punt; + goto again; + } } -static void io_queue_sqe(struct io_kiocb *req) +static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { int ret; - if (unlikely(req->ctx->drain_next)) { - req->flags |= REQ_F_IO_DRAIN; - req->ctx->drain_next = false; - } - req->ctx->drain_next = (req->flags & REQ_F_DRAIN_LINK); - - ret = io_req_defer(req); + ret = io_req_defer(req, sqe); if (ret) { if (ret != -EIOCBQUEUED) { +fail_req: io_cqring_add_event(req, ret); - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req_set_fail_links(req); io_double_put_req(req); } - } else - __io_queue_sqe(req); + } else if (req->flags & REQ_F_FORCE_ASYNC) { + ret = io_req_defer_prep(req, sqe); + if (unlikely(ret < 0)) + goto fail_req; + /* + * Never try inline submit of IOSQE_ASYNC is set, go straight + * to async execution. + */ + req->work.flags |= IO_WQ_WORK_CONCURRENT; + io_queue_async_work(req); + } else { + __io_queue_sqe(req, sqe); + } } static inline void io_queue_link_head(struct io_kiocb *req) @@ -3307,31 +4697,51 @@ static inline void io_queue_link_head(struct io_kiocb *req) io_cqring_add_event(req, -ECANCELED); io_double_put_req(req); } else - io_queue_sqe(req); + io_queue_sqe(req, NULL); } +#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC) -#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK) - -static bool io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state, - struct io_kiocb **link) +static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_submit_state *state, struct io_kiocb **link) { + const struct cred *old_creds = NULL; struct io_ring_ctx *ctx = req->ctx; - int ret; + unsigned int sqe_flags; + int ret, id; - req->user_data = req->sqe->user_data; + sqe_flags = READ_ONCE(sqe->flags); /* enforce forwards compatibility on users */ - if (unlikely(req->sqe->flags & ~SQE_VALID_FLAGS)) { + if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) { ret = -EINVAL; goto err_req; } - ret = io_req_set_file(state, req); + id = READ_ONCE(sqe->personality); + if (id) { + const struct cred *personality_creds; + + personality_creds = idr_find(&ctx->personality_idr, id); + if (unlikely(!personality_creds)) { + ret = -EINVAL; + goto err_req; + } + old_creds = override_creds(personality_creds); + } + + /* same numerical values with corresponding REQ_F_*, safe to copy */ + req->flags |= sqe_flags & (IOSQE_IO_DRAIN|IOSQE_IO_HARDLINK| + IOSQE_ASYNC); + + ret = io_req_set_file(state, req, sqe); if (unlikely(ret)) { err_req: io_cqring_add_event(req, ret); io_double_put_req(req); + if (old_creds) + revert_creds(old_creds); return false; } @@ -3343,35 +4753,57 @@ err_req: * conditions are true (normal request), then just queue it. */ if (*link) { - struct io_kiocb *prev = *link; - struct io_async_ctx *io; - - if (req->sqe->flags & IOSQE_IO_DRAIN) - (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN; + struct io_kiocb *head = *link; - io = kmalloc(sizeof(*io), GFP_KERNEL); - if (!io) { + /* + * Taking sequential execution of a link, draining both sides + * of the link also fullfils IOSQE_IO_DRAIN semantics for all + * requests in the link. So, it drains the head and the + * next after the link request. The last one is done via + * drain_next flag to persist the effect across calls. + */ + if (sqe_flags & IOSQE_IO_DRAIN) { + head->flags |= REQ_F_IO_DRAIN; + ctx->drain_next = 1; + } + if (io_alloc_async_ctx(req)) { ret = -EAGAIN; goto err_req; } - ret = io_req_defer_prep(req, io); + ret = io_req_defer_prep(req, sqe); if (ret) { - kfree(io); - prev->flags |= REQ_F_FAIL_LINK; + /* fail even hard links since we don't submit */ + head->flags |= REQ_F_FAIL_LINK; goto err_req; } - trace_io_uring_link(ctx, req, prev); - list_add_tail(&req->link_list, &prev->link_list); - } else if (req->sqe->flags & IOSQE_IO_LINK) { - req->flags |= REQ_F_LINK; + trace_io_uring_link(ctx, req, head); + list_add_tail(&req->link_list, &head->link_list); - INIT_LIST_HEAD(&req->link_list); - *link = req; + /* last request of a link, enqueue the link */ + if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) { + io_queue_link_head(head); + *link = NULL; + } } else { - io_queue_sqe(req); + if (unlikely(ctx->drain_next)) { + req->flags |= REQ_F_IO_DRAIN; + req->ctx->drain_next = 0; + } + if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) { + req->flags |= REQ_F_LINK; + INIT_LIST_HEAD(&req->link_list); + ret = io_req_defer_prep(req, sqe); + if (ret) + req->flags |= REQ_F_FAIL_LINK; + *link = req; + } else { + io_queue_sqe(req, sqe); + } } + if (old_creds) + revert_creds(old_creds); return true; } @@ -3403,27 +4835,25 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - if (ctx->cached_sq_head != READ_ONCE(rings->sq.head)) { - /* - * Ensure any loads from the SQEs are done at this point, - * since once we write the new head, the application could - * write new data to them. - */ - smp_store_release(&rings->sq.head, ctx->cached_sq_head); - } + /* + * Ensure any loads from the SQEs are done at this point, + * since once we write the new head, the application could + * write new data to them. + */ + smp_store_release(&rings->sq.head, ctx->cached_sq_head); } /* - * Fetch an sqe, if one is available. Note that s->sqe will point to memory + * Fetch an sqe, if one is available. Note that sqe_ptr will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later * used, it's important that those reads are done through READ_ONCE() to * prevent a re-load down the line. */ -static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) +static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req, + const struct io_uring_sqe **sqe_ptr) { - struct io_rings *rings = ctx->rings; u32 *sq_array = ctx->sq_array; unsigned head; @@ -3435,12 +4865,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ - head = ctx->cached_sq_head; - /* make sure SQ entry isn't read before tail */ - if (unlikely(head == smp_load_acquire(&rings->sq.tail))) - return false; - - head = READ_ONCE(sq_array[head & ctx->sq_mask]); + head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]); if (likely(head < ctx->sq_entries)) { /* * All io need record the previous position, if LINK vs DARIN, @@ -3448,7 +4873,9 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) * link list. */ req->sequence = ctx->cached_sq_head; - req->sqe = &ctx->sq_sqes[head]; + *sqe_ptr = &ctx->sq_sqes[head]; + req->opcode = READ_ONCE((*sqe_ptr)->opcode); + req->user_data = READ_ONCE((*sqe_ptr)->user_data); ctx->cached_sq_head++; return true; } @@ -3456,7 +4883,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req) /* drop invalid entries */ ctx->cached_sq_head++; ctx->cached_sq_dropped++; - WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped); + WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped); return false; } @@ -3470,18 +4897,29 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, bool mm_fault = false; /* if we have a backlog and couldn't flush it all, return BUSY */ - if (!list_empty(&ctx->cq_overflow_list) && - !io_cqring_overflow_flush(ctx, false)) - return -EBUSY; + if (test_bit(0, &ctx->sq_check_overflow)) { + if (!list_empty(&ctx->cq_overflow_list) && + !io_cqring_overflow_flush(ctx, false)) + return -EBUSY; + } + + /* make sure SQ entry isn't read before tail */ + nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); + + if (!percpu_ref_tryget_many(&ctx->refs, nr)) + return -EAGAIN; if (nr > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, nr); statep = &state; } + ctx->ring_fd = ring_fd; + ctx->ring_file = ring_file; + for (i = 0; i < nr; i++) { + const struct io_uring_sqe *sqe; struct io_kiocb *req; - unsigned int sqe_flags; req = io_get_req(ctx, statep); if (unlikely(!req)) { @@ -3489,12 +4927,21 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, submitted = -EAGAIN; break; } - if (!io_get_sqring(ctx, req)) { - __io_free_req(req); + if (!io_get_sqring(ctx, req, &sqe)) { + __io_req_do_free(req); break; } - if (io_sqe_needs_user(req->sqe) && !*mm) { + /* will complete beyond this point, count as submitted */ + submitted++; + + if (unlikely(req->opcode >= IORING_OP_LAST)) { + io_cqring_add_event(req, -EINVAL); + io_double_put_req(req); + break; + } + + if (io_op_defs[req->opcode].needs_mm && !*mm) { mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm); if (!mm_fault) { use_mm(ctx->sqo_mm); @@ -3502,28 +4949,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, } } - submitted++; - sqe_flags = req->sqe->flags; - - req->ring_file = ring_file; - req->ring_fd = ring_fd; req->has_user = *mm != NULL; req->in_async = async; req->needs_fixed_file = async; - trace_io_uring_submit_sqe(ctx, req->sqe->user_data, - true, async); - if (!io_submit_sqe(req, statep, &link)) + trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, + true, async); + if (!io_submit_sqe(req, sqe, statep, &link)) break; - /* - * If previous wasn't linked and we have a linked command, - * that's the end of the chain. Submit the previous link. - */ - if (!(sqe_flags & IOSQE_IO_LINK) && link) { - io_queue_link_head(link); - link = NULL; - } } + if (unlikely(submitted != nr)) { + int ref_used = (submitted == -EAGAIN) ? 0 : submitted; + + percpu_ref_put_many(&ctx->refs, nr - ref_used); + } if (link) io_queue_link_head(link); if (statep) @@ -3646,8 +5085,9 @@ static int io_sq_thread(void *data) ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; } - to_submit = min(to_submit, ctx->sq_entries); + mutex_lock(&ctx->uring_lock); ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); + mutex_unlock(&ctx->uring_lock); if (ret > 0) inflight += ret; } @@ -3676,7 +5116,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush) struct io_ring_ctx *ctx = iowq->ctx; /* - * Wake up if we have enough events, or if a timeout occured since we + * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ @@ -3775,19 +5215,40 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) #endif } +static void io_file_ref_kill(struct percpu_ref *ref) +{ + struct fixed_file_data *data; + + data = container_of(ref, struct fixed_file_data, refs); + complete(&data->done); +} + static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { + struct fixed_file_data *data = ctx->file_data; unsigned nr_tables, i; - if (!ctx->file_table) + if (!data) return -ENXIO; + /* protect against inflight atomic switch, which drops the ref */ + percpu_ref_get(&data->refs); + /* wait for existing switches */ + flush_work(&data->ref_work); + percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill); + wait_for_completion(&data->done); + percpu_ref_put(&data->refs); + /* flush potential new switch */ + flush_work(&data->ref_work); + percpu_ref_exit(&data->refs); + __io_sqe_files_unregister(ctx); nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE); for (i = 0; i < nr_tables; i++) - kfree(ctx->file_table[i].files); - kfree(ctx->file_table); - ctx->file_table = NULL; + kfree(data->table[i].files); + kfree(data->table); + kfree(data); + ctx->file_data = NULL; ctx->nr_user_files = 0; return 0; } @@ -3818,16 +5279,6 @@ static void io_finish_async(struct io_ring_ctx *ctx) } #if defined(CONFIG_UNIX) -static void io_destruct_skb(struct sk_buff *skb) -{ - struct io_ring_ctx *ctx = skb->sk->sk_user_data; - - if (ctx->io_wq) - io_wq_flush(ctx->io_wq); - - unix_destruct_scm(skb); -} - /* * Ensure the UNIX gc is aware of our file set, so we are certain that * the io_uring can be safely unregistered on process exit, even if we have @@ -3875,7 +5326,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) fpl->max = SCM_MAX_FD; fpl->count = nr_files; UNIXCB(skb).fp = fpl; - skb->destructor = io_destruct_skb; + skb->destructor = unix_destruct_scm; refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_queue_head(&sk->sk_receive_queue, skb); @@ -3937,7 +5388,7 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables, int i; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &ctx->file_table[i]; + struct fixed_file_table *table = &ctx->file_data->table[i]; unsigned this_files; this_files = min(nr_files, IORING_MAX_FILES_TABLE); @@ -3952,36 +5403,159 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables, return 0; for (i = 0; i < nr_tables; i++) { - struct fixed_file_table *table = &ctx->file_table[i]; + struct fixed_file_table *table = &ctx->file_data->table[i]; kfree(table->files); } return 1; } +static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file) +{ +#if defined(CONFIG_UNIX) + struct sock *sock = ctx->ring_sock->sk; + struct sk_buff_head list, *head = &sock->sk_receive_queue; + struct sk_buff *skb; + int i; + + __skb_queue_head_init(&list); + + /* + * Find the skb that holds this file in its SCM_RIGHTS. When found, + * remove this entry and rearrange the file array. + */ + skb = skb_dequeue(head); + while (skb) { + struct scm_fp_list *fp; + + fp = UNIXCB(skb).fp; + for (i = 0; i < fp->count; i++) { + int left; + + if (fp->fp[i] != file) + continue; + + unix_notinflight(fp->user, fp->fp[i]); + left = fp->count - 1 - i; + if (left) { + memmove(&fp->fp[i], &fp->fp[i + 1], + left * sizeof(struct file *)); + } + fp->count--; + if (!fp->count) { + kfree_skb(skb); + skb = NULL; + } else { + __skb_queue_tail(&list, skb); + } + fput(file); + file = NULL; + break; + } + + if (!file) + break; + + __skb_queue_tail(&list, skb); + + skb = skb_dequeue(head); + } + + if (skb_peek(&list)) { + spin_lock_irq(&head->lock); + while ((skb = __skb_dequeue(&list)) != NULL) + __skb_queue_tail(head, skb); + spin_unlock_irq(&head->lock); + } +#else + fput(file); +#endif +} + +struct io_file_put { + struct llist_node llist; + struct file *file; + struct completion *done; +}; + +static void io_ring_file_ref_switch(struct work_struct *work) +{ + struct io_file_put *pfile, *tmp; + struct fixed_file_data *data; + struct llist_node *node; + + data = container_of(work, struct fixed_file_data, ref_work); + + while ((node = llist_del_all(&data->put_llist)) != NULL) { + llist_for_each_entry_safe(pfile, tmp, node, llist) { + io_ring_file_put(data->ctx, pfile->file); + if (pfile->done) + complete(pfile->done); + else + kfree(pfile); + } + } + + percpu_ref_get(&data->refs); + percpu_ref_switch_to_percpu(&data->refs); +} + +static void io_file_data_ref_zero(struct percpu_ref *ref) +{ + struct fixed_file_data *data; + + data = container_of(ref, struct fixed_file_data, refs); + + /* we can't safely switch from inside this context, punt to wq */ + queue_work(system_wq, &data->ref_work); +} + static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { __s32 __user *fds = (__s32 __user *) arg; unsigned nr_tables; + struct file *file; int fd, ret = 0; unsigned i; - if (ctx->file_table) + if (ctx->file_data) return -EBUSY; if (!nr_args) return -EINVAL; if (nr_args > IORING_MAX_FIXED_FILES) return -EMFILE; + ctx->file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL); + if (!ctx->file_data) + return -ENOMEM; + ctx->file_data->ctx = ctx; + init_completion(&ctx->file_data->done); + nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE); - ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table), + ctx->file_data->table = kcalloc(nr_tables, + sizeof(struct fixed_file_table), GFP_KERNEL); - if (!ctx->file_table) + if (!ctx->file_data->table) { + kfree(ctx->file_data); + ctx->file_data = NULL; return -ENOMEM; + } + + if (percpu_ref_init(&ctx->file_data->refs, io_file_data_ref_zero, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { + kfree(ctx->file_data->table); + kfree(ctx->file_data); + ctx->file_data = NULL; + return -ENOMEM; + } + ctx->file_data->put_llist.first = NULL; + INIT_WORK(&ctx->file_data->ref_work, io_ring_file_ref_switch); if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) { - kfree(ctx->file_table); - ctx->file_table = NULL; + percpu_ref_exit(&ctx->file_data->refs); + kfree(ctx->file_data->table); + kfree(ctx->file_data); + ctx->file_data = NULL; return -ENOMEM; } @@ -3998,13 +5572,14 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, continue; } - table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; index = i & IORING_FILE_TABLE_MASK; - table->files[index] = fget(fd); + file = fget(fd); ret = -EBADF; - if (!table->files[index]) + if (!file) break; + /* * Don't allow io_uring instances to be registered. If UNIX * isn't enabled, then this causes a reference cycle and this @@ -4012,26 +5587,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, * handle it just fine, but there's still no point in allowing * a ring fd as it doesn't support regular read/write anyway. */ - if (table->files[index]->f_op == &io_uring_fops) { - fput(table->files[index]); + if (file->f_op == &io_uring_fops) { + fput(file); break; } ret = 0; + table->files[index] = file; } if (ret) { for (i = 0; i < ctx->nr_user_files; i++) { - struct file *file; - file = io_file_from_index(ctx, i); if (file) fput(file); } for (i = 0; i < nr_tables; i++) - kfree(ctx->file_table[i].files); + kfree(ctx->file_data->table[i].files); - kfree(ctx->file_table); - ctx->file_table = NULL; + kfree(ctx->file_data->table); + kfree(ctx->file_data); + ctx->file_data = NULL; ctx->nr_user_files = 0; return ret; } @@ -4043,69 +5618,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, return ret; } -static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index) -{ -#if defined(CONFIG_UNIX) - struct file *file = io_file_from_index(ctx, index); - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head list, *head = &sock->sk_receive_queue; - struct sk_buff *skb; - int i; - - __skb_queue_head_init(&list); - - /* - * Find the skb that holds this file in its SCM_RIGHTS. When found, - * remove this entry and rearrange the file array. - */ - skb = skb_dequeue(head); - while (skb) { - struct scm_fp_list *fp; - - fp = UNIXCB(skb).fp; - for (i = 0; i < fp->count; i++) { - int left; - - if (fp->fp[i] != file) - continue; - - unix_notinflight(fp->user, fp->fp[i]); - left = fp->count - 1 - i; - if (left) { - memmove(&fp->fp[i], &fp->fp[i + 1], - left * sizeof(struct file *)); - } - fp->count--; - if (!fp->count) { - kfree_skb(skb); - skb = NULL; - } else { - __skb_queue_tail(&list, skb); - } - fput(file); - file = NULL; - break; - } - - if (!file) - break; - - __skb_queue_tail(&list, skb); - - skb = skb_dequeue(head); - } - - if (skb_peek(&list)) { - spin_lock_irq(&head->lock); - while ((skb = __skb_dequeue(&list)) != NULL) - __skb_queue_tail(head, skb); - spin_unlock_irq(&head->lock); - } -#else - fput(io_file_from_index(ctx, index)); -#endif -} - static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, int index) { @@ -4149,27 +5661,65 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } -static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, - unsigned nr_args) +static void io_atomic_switch(struct percpu_ref *ref) { - struct io_uring_files_update up; + struct fixed_file_data *data; + + data = container_of(ref, struct fixed_file_data, refs); + clear_bit(FFD_F_ATOMIC, &data->state); +} + +static bool io_queue_file_removal(struct fixed_file_data *data, + struct file *file) +{ + struct io_file_put *pfile, pfile_stack; + DECLARE_COMPLETION_ONSTACK(done); + + /* + * If we fail allocating the struct we need for doing async reomval + * of this file, just punt to sync and wait for it. + */ + pfile = kzalloc(sizeof(*pfile), GFP_KERNEL); + if (!pfile) { + pfile = &pfile_stack; + pfile->done = &done; + } + + pfile->file = file; + llist_add(&pfile->llist, &data->put_llist); + + if (pfile == &pfile_stack) { + if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) { + percpu_ref_put(&data->refs); + percpu_ref_switch_to_atomic(&data->refs, + io_atomic_switch); + } + wait_for_completion(&done); + flush_work(&data->ref_work); + return false; + } + + return true; +} + +static int __io_sqe_files_update(struct io_ring_ctx *ctx, + struct io_uring_files_update *up, + unsigned nr_args) +{ + struct fixed_file_data *data = ctx->file_data; + bool ref_switch = false; + struct file *file; __s32 __user *fds; int fd, i, err; __u32 done; - if (!ctx->file_table) - return -ENXIO; - if (!nr_args) - return -EINVAL; - if (copy_from_user(&up, arg, sizeof(up))) - return -EFAULT; - if (check_add_overflow(up.offset, nr_args, &done)) + if (check_add_overflow(up->offset, nr_args, &done)) return -EOVERFLOW; if (done > ctx->nr_user_files) return -EINVAL; done = 0; - fds = (__s32 __user *) up.fds; + fds = u64_to_user_ptr(up->fds); while (nr_args) { struct fixed_file_table *table; unsigned index; @@ -4179,16 +5729,16 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, err = -EFAULT; break; } - i = array_index_nospec(up.offset, ctx->nr_user_files); - table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT]; + i = array_index_nospec(up->offset, ctx->nr_user_files); + table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT]; index = i & IORING_FILE_TABLE_MASK; if (table->files[index]) { - io_sqe_file_unregister(ctx, i); + file = io_file_from_index(ctx, index); table->files[index] = NULL; + if (io_queue_file_removal(data, file)) + ref_switch = true; } if (fd != -1) { - struct file *file; - file = fget(fd); if (!file) { err = -EBADF; @@ -4214,11 +5764,32 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, } nr_args--; done++; - up.offset++; + up->offset++; + } + + if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) { + percpu_ref_put(&data->refs); + percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); } return done ? done : err; } +static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) +{ + struct io_uring_files_update up; + + if (!ctx->file_data) + return -ENXIO; + if (!nr_args) + return -EINVAL; + if (copy_from_user(&up, arg, sizeof(up))) + return -EFAULT; + if (up.resv) + return -EINVAL; + + return __io_sqe_files_update(ctx, &up, nr_args); +} static void io_put_work(struct io_wq_work *work) { @@ -4234,11 +5805,56 @@ static void io_get_work(struct io_wq_work *work) refcount_inc(&req->refs); } +static int io_init_wq_offload(struct io_ring_ctx *ctx, + struct io_uring_params *p) +{ + struct io_wq_data data; + struct fd f; + struct io_ring_ctx *ctx_attach; + unsigned int concurrency; + int ret = 0; + + data.user = ctx->user; + data.get_work = io_get_work; + data.put_work = io_put_work; + + if (!(p->flags & IORING_SETUP_ATTACH_WQ)) { + /* Do QD, or 4 * CPUS, whatever is smallest */ + concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); + + ctx->io_wq = io_wq_create(concurrency, &data); + if (IS_ERR(ctx->io_wq)) { + ret = PTR_ERR(ctx->io_wq); + ctx->io_wq = NULL; + } + return ret; + } + + f = fdget(p->wq_fd); + if (!f.file) + return -EBADF; + + if (f.file->f_op != &io_uring_fops) { + ret = -EINVAL; + goto out_fput; + } + + ctx_attach = f.file->private_data; + /* @io_wq is protected by holding the fd */ + if (!io_wq_get(ctx_attach->io_wq, &data)) { + ret = -EINVAL; + goto out_fput; + } + + ctx->io_wq = ctx_attach->io_wq; +out_fput: + fdput(f); + return ret; +} + static int io_sq_offload_start(struct io_ring_ctx *ctx, struct io_uring_params *p) { - struct io_wq_data data; - unsigned concurrency; int ret; init_waitqueue_head(&ctx->sqo_wait); @@ -4282,20 +5898,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, goto err; } - data.mm = ctx->sqo_mm; - data.user = ctx->user; - data.creds = ctx->creds; - data.get_work = io_get_work; - data.put_work = io_put_work; - - /* Do QD, or 4 * CPUS, whatever is smallest */ - concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); - ctx->io_wq = io_wq_create(concurrency, &data); - if (IS_ERR(ctx->io_wq)) { - ret = PTR_ERR(ctx->io_wq); - ctx->io_wq = NULL; + ret = io_init_wq_offload(ctx, p); + if (ret) goto err; - } return 0; err: @@ -4400,7 +6005,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) struct io_mapped_ubuf *imu = &ctx->user_bufs[i]; for (j = 0; j < imu->nr_bvecs; j++) - put_user_page(imu->bvec[j].bv_page); + unpin_user_page(imu->bvec[j].bv_page); if (ctx->account_mem) io_unaccount_mem(ctx->user, imu->nr_bvecs); @@ -4428,7 +6033,7 @@ static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) return -EFAULT; - dst->iov_base = (void __user *) (unsigned long) ciov.iov_base; + dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); dst->iov_len = ciov.iov_len; return 0; } @@ -4521,7 +6126,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ret = 0; down_read(¤t->mm->mmap_sem); - pret = get_user_pages(ubuf, nr_pages, + pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, pages, vmas); if (pret == nr_pages) { @@ -4545,7 +6150,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, * release any pages we did get */ if (pret > 0) - put_user_pages(pages, pret); + unpin_user_pages(pages, pret); if (ctx->account_mem) io_unaccount_mem(ctx->user, nr_pages); kvfree(imu->bvec); @@ -4673,6 +6278,17 @@ static int io_uring_fasync(int fd, struct file *file, int on) return fasync_helper(fd, file, on, &ctx->cq_fasync); } +static int io_remove_personalities(int id, void *p, void *data) +{ + struct io_ring_ctx *ctx = data; + const struct cred *cred; + + cred = idr_remove(&ctx->personality_idr, id); + if (cred) + put_cred(cred); + return 0; +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { mutex_lock(&ctx->uring_lock); @@ -4689,6 +6305,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) /* if we failed setting up the ctx, we might not have any rings */ if (ctx->rings) io_cqring_overflow_flush(ctx, true); + idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); wait_for_completion(&ctx->completions[0]); io_ring_ctx_free(ctx); } @@ -4742,10 +6359,6 @@ static int io_uring_flush(struct file *file, void *data) struct io_ring_ctx *ctx = file->private_data; io_uring_cancel_files(ctx, data); - if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { - io_cqring_overflow_flush(ctx, true); - io_wq_cancel_all(ctx->io_wq); - } return 0; } @@ -4859,13 +6472,15 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } else if (to_submit) { struct mm_struct *cur_mm; - to_submit = min(to_submit, ctx->sq_entries); mutex_lock(&ctx->uring_lock); /* already have mm, so io_submit_sqes() won't try to grab it */ cur_mm = ctx->sqo_mm; submitted = io_submit_sqes(ctx, to_submit, f.file, fd, &cur_mm, false); mutex_unlock(&ctx->uring_lock); + + if (submitted != to_submit) + goto out; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; @@ -4879,6 +6494,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } } +out: percpu_ref_put(&ctx->refs); out_fput: fdput(f); @@ -4971,7 +6587,6 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx) #if defined(CONFIG_UNIX) ctx->ring_sock->file = file; - ctx->ring_sock->sk->sk_user_data = ctx; #endif fd_install(ret, file); return ret; @@ -4990,8 +6605,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) bool account_mem; int ret; - if (!entries || entries > IORING_MAX_ENTRIES) + if (!entries) return -EINVAL; + if (entries > IORING_MAX_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + entries = IORING_MAX_ENTRIES; + } /* * Use twice as many entries for the CQ ring. It's possible for the @@ -5008,8 +6628,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ - if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES) + if (p->cq_entries < p->sq_entries) return -EINVAL; + if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { + if (!(p->flags & IORING_SETUP_CLAMP)) + return -EINVAL; + p->cq_entries = IORING_MAX_CQ_ENTRIES; + } p->cq_entries = roundup_pow_of_two(p->cq_entries); } else { p->cq_entries = 2 * p->sq_entries; @@ -5074,7 +6699,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) goto err; p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE; + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: @@ -5101,7 +6727,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) } if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | - IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE)) + IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | + IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) return -EINVAL; ret = io_uring_create(entries, &p); @@ -5120,6 +6747,84 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, return io_uring_setup(entries, params); } +static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) +{ + struct io_uring_probe *p; + size_t size; + int i, ret; + + size = struct_size(p, ops, nr_args); + if (size == SIZE_MAX) + return -EOVERFLOW; + p = kzalloc(size, GFP_KERNEL); + if (!p) + return -ENOMEM; + + ret = -EFAULT; + if (copy_from_user(p, arg, size)) + goto out; + ret = -EINVAL; + if (memchr_inv(p, 0, size)) + goto out; + + p->last_op = IORING_OP_LAST - 1; + if (nr_args > IORING_OP_LAST) + nr_args = IORING_OP_LAST; + + for (i = 0; i < nr_args; i++) { + p->ops[i].op = i; + if (!io_op_defs[i].not_supported) + p->ops[i].flags = IO_URING_OP_SUPPORTED; + } + p->ops_len = i; + + ret = 0; + if (copy_to_user(arg, p, size)) + ret = -EFAULT; +out: + kfree(p); + return ret; +} + +static int io_register_personality(struct io_ring_ctx *ctx) +{ + const struct cred *creds = get_current_cred(); + int id; + + id = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1, + USHRT_MAX, GFP_KERNEL); + if (id < 0) + put_cred(creds); + return id; +} + +static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) +{ + const struct cred *old_creds; + + old_creds = idr_remove(&ctx->personality_idr, id); + if (old_creds) { + put_cred(old_creds); + return 0; + } + + return -EINVAL; +} + +static bool io_register_op_must_quiesce(int op) +{ + switch (op) { + case IORING_UNREGISTER_FILES: + case IORING_REGISTER_FILES_UPDATE: + case IORING_REGISTER_PROBE: + case IORING_REGISTER_PERSONALITY: + case IORING_UNREGISTER_PERSONALITY: + return false; + default: + return true; + } +} + static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) @@ -5135,18 +6840,26 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (percpu_ref_is_dying(&ctx->refs)) return -ENXIO; - percpu_ref_kill(&ctx->refs); + if (io_register_op_must_quiesce(opcode)) { + percpu_ref_kill(&ctx->refs); - /* - * Drop uring mutex before waiting for references to exit. If another - * thread is currently inside io_uring_enter() it might need to grab - * the uring_lock to make progress. If we hold it here across the drain - * wait, then we can deadlock. It's safe to drop the mutex here, since - * no new references will come in after we've killed the percpu ref. - */ - mutex_unlock(&ctx->uring_lock); - wait_for_completion(&ctx->completions[0]); - mutex_lock(&ctx->uring_lock); + /* + * Drop uring mutex before waiting for references to exit. If + * another thread is currently inside io_uring_enter() it might + * need to grab the uring_lock to make progress. If we hold it + * here across the drain wait, then we can deadlock. It's safe + * to drop the mutex here, since no new references will come in + * after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); + ret = wait_for_completion_interruptible(&ctx->completions[0]); + mutex_lock(&ctx->uring_lock); + if (ret) { + percpu_ref_resurrect(&ctx->refs); + ret = -EINTR; + goto out; + } + } switch (opcode) { case IORING_REGISTER_BUFFERS: @@ -5171,10 +6884,17 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_sqe_files_update(ctx, arg, nr_args); break; case IORING_REGISTER_EVENTFD: + case IORING_REGISTER_EVENTFD_ASYNC: ret = -EINVAL; if (nr_args != 1) break; ret = io_eventfd_register(ctx, arg); + if (ret) + break; + if (opcode == IORING_REGISTER_EVENTFD_ASYNC) + ctx->eventfd_async = 1; + else + ctx->eventfd_async = 0; break; case IORING_UNREGISTER_EVENTFD: ret = -EINVAL; @@ -5182,14 +6902,35 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, break; ret = io_eventfd_unregister(ctx); break; + case IORING_REGISTER_PROBE: + ret = -EINVAL; + if (!arg || nr_args > 256) + break; + ret = io_probe(ctx, arg, nr_args); + break; + case IORING_REGISTER_PERSONALITY: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_register_personality(ctx); + break; + case IORING_UNREGISTER_PERSONALITY: + ret = -EINVAL; + if (arg) + break; + ret = io_unregister_personality(ctx, nr_args); + break; default: ret = -EINVAL; break; } - /* bring the ctx back to life */ - reinit_completion(&ctx->completions[0]); - percpu_ref_reinit(&ctx->refs); + if (io_register_op_must_quiesce(opcode)) { + /* bring the ctx back to life */ + percpu_ref_reinit(&ctx->refs); +out: + reinit_completion(&ctx->completions[0]); + } return ret; } @@ -5222,6 +6963,7 @@ out_fput: static int __init io_uring_init(void) { + BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC); return 0; }; |