diff options
Diffstat (limited to 'io_uring')
| -rw-r--r-- | io_uring/cancel.c | 2 | ||||
| -rw-r--r-- | io_uring/eventfd.c | 1 | ||||
| -rw-r--r-- | io_uring/fdinfo.c | 3 | ||||
| -rw-r--r-- | io_uring/io-wq.c | 3 | ||||
| -rw-r--r-- | io_uring/io_uring.c | 38 | ||||
| -rw-r--r-- | io_uring/napi.c | 27 | ||||
| -rw-r--r-- | io_uring/napi.h | 8 | ||||
| -rw-r--r-- | io_uring/net.c | 29 | ||||
| -rw-r--r-- | io_uring/nop.c | 4 | ||||
| -rw-r--r-- | io_uring/rw.c | 4 | ||||
| -rw-r--r-- | io_uring/tctx.c | 12 | ||||
| -rw-r--r-- | io_uring/timeout.c | 55 | ||||
| -rw-r--r-- | io_uring/wait.c | 6 | ||||
| -rw-r--r-- | io_uring/waitid.c | 1 |
14 files changed, 142 insertions, 51 deletions
diff --git a/io_uring/cancel.c b/io_uring/cancel.c index 5e5eb9cfc7cd..4aa3103ba9c3 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -561,8 +561,8 @@ __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, ret |= io_waitid_remove_all(ctx, tctx, cancel_all); ret |= io_futex_remove_all(ctx, tctx, cancel_all); ret |= io_uring_try_cancel_uring_cmd(ctx, tctx, cancel_all); - mutex_unlock(&ctx->uring_lock); ret |= io_kill_timeouts(ctx, tctx, cancel_all); + mutex_unlock(&ctx->uring_lock); if (tctx) ret |= io_run_task_work() > 0; else diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index 3da028500f76..d656cc2a0b9b 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -43,6 +43,7 @@ static void io_eventfd_do_signal(struct rcu_head *rcu) { struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + atomic_andnot(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops); eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); io_eventfd_put(ev_fd); } diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index c2d3e45544bb..001fb542dc11 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -190,8 +190,9 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) get_task_struct(tsk); rcu_read_unlock(); usec = io_sq_cpu_usec(tsk); + sq_pid = task_pid_nr_ns(tsk, + proc_pid_ns(file_inode(m->file)->i_sb)); put_task_struct(tsk); - sq_pid = sq->task_pid; sq_cpu = sq->sq_cpu; sq_total_time = usec; sq_work_time = sq->work_time; diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 7a9f94a0ce6f..8cc7b47d3089 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1124,7 +1124,8 @@ static inline void io_wq_remove_pending(struct io_wq *wq, if (io_wq_is_hashed(work) && work == wq->hash_tail[hash]) { if (prev) prev_work = container_of(prev, struct io_wq_work, list); - if (prev_work && io_get_work_hash(prev_work) == hash) + if (prev_work && io_wq_is_hashed(prev_work) && + io_get_work_hash(prev_work) == hash) wq->hash_tail[hash] = prev_work; else wq->hash_tail[hash] = NULL; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4ed998d60c09..103b6c88f252 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -687,12 +687,26 @@ static struct io_overflow_cqe *io_alloc_ocqe(struct io_ring_ctx *ctx, } /* + * Compute queued CQEs for free-space calculation, clamped to cq_entries. + */ +static unsigned int io_cqring_queued(struct io_ring_ctx *ctx) +{ + struct io_rings *rings = io_get_rings(ctx); + int diff; + + diff = (int)(ctx->cached_cq_tail - READ_ONCE(rings->cq.head)); + if (diff >= 0) + return min((unsigned int)diff, ctx->cq_entries); + return 0; +} + +/* * Fill an empty dummy CQE, in case alignment is off for posting a 32b CQE * because the ring is a single 16b entry away from wrapping. */ static bool io_fill_nop_cqe(struct io_ring_ctx *ctx, unsigned int off) { - if (__io_cqring_events(ctx) < ctx->cq_entries) { + if (io_cqring_queued(ctx) < ctx->cq_entries) { struct io_uring_cqe *cqe = &ctx->rings->cqes[off]; cqe->user_data = 0; @@ -713,7 +727,7 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32) { struct io_rings *rings = ctx->rings; unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1); - unsigned int free, queued, len; + unsigned int free, len; /* * Posting into the CQ when there are pending overflowed CQEs may break @@ -733,9 +747,7 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32) off = 0; } - /* userspace may cheat modifying the tail, be safe and do min */ - queued = min(__io_cqring_events(ctx), ctx->cq_entries); - free = ctx->cq_entries - queued; + free = ctx->cq_entries - io_cqring_queued(ctx); /* we need a contiguous range, limit based on the current array offset */ len = min(free, ctx->cq_entries - off); if (len < (cqe32 + 1)) @@ -1452,8 +1464,13 @@ struct io_wq_work *io_wq_free_work(struct io_wq_work *work) struct io_kiocb *nxt = NULL; if (req_ref_put_and_test_atomic(req)) { - if (req->flags & IO_REQ_LINK_FLAGS) + if (req->flags & IO_REQ_LINK_FLAGS) { + struct io_ring_ctx *ctx = req->ctx; + + mutex_lock(&ctx->uring_lock); nxt = io_req_find_next(req); + mutex_unlock(&ctx->uring_lock); + } io_free_req(req); } return nxt ? &nxt->work : NULL; @@ -1721,10 +1738,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_issue_def *def; unsigned int sqe_flags; int personality; - u8 opcode; req->ctx = ctx; - req->opcode = opcode = READ_ONCE(sqe->opcode); + req->opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ sqe_flags = READ_ONCE(sqe->flags); req->flags = (__force io_req_flags_t) sqe_flags; @@ -1734,13 +1750,13 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->cancel_seq_set = false; req->async_data = NULL; - if (unlikely(opcode >= IORING_OP_LAST)) { + if (unlikely(req->opcode >= IORING_OP_LAST)) { req->opcode = 0; return io_init_fail_req(req, -EINVAL); } - opcode = array_index_nospec(opcode, IORING_OP_LAST); + req->opcode = array_index_nospec(req->opcode, IORING_OP_LAST); - def = &io_issue_defs[opcode]; + def = &io_issue_defs[req->opcode]; if (def->is_128 && !(ctx->flags & IORING_SETUP_SQE128)) { /* * A 128b op on a non-128b SQ requires mixed SQE support as diff --git a/io_uring/napi.c b/io_uring/napi.c index 8d68366a4b90..bfc771445912 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -38,7 +38,8 @@ static inline ktime_t net_to_ktime(unsigned long t) return ns_to_ktime(t << 10); } -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode) { struct hlist_head *hash_list; struct io_napi_entry *e; @@ -69,6 +70,11 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) * kfree() */ spin_lock(&ctx->napi_lock); + if (unlikely(READ_ONCE(ctx->napi_track_mode) != mode)) { + spin_unlock(&ctx->napi_lock); + kfree(e); + return -EINVAL; + } if (unlikely(io_napi_hash_find(hash_list, napi_id))) { spin_unlock(&ctx->napi_lock); kfree(e); @@ -196,9 +202,14 @@ __io_napi_do_busy_loop(struct io_ring_ctx *ctx, bool (*loop_end)(void *, unsigned long), void *loop_end_arg) { - if (READ_ONCE(ctx->napi_track_mode) == IO_URING_NAPI_TRACKING_STATIC) + switch (READ_ONCE(ctx->napi_track_mode)) { + case IO_URING_NAPI_TRACKING_STATIC: return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); - return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + case IO_URING_NAPI_TRACKING_DYNAMIC: + return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg); + default: + return false; + } } static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx, @@ -273,13 +284,13 @@ static int io_napi_register_napi(struct io_ring_ctx *ctx, default: return -EINVAL; } - /* clean the napi list for new settings */ + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); io_napi_free(ctx); - WRITE_ONCE(ctx->napi_track_mode, napi->op_param); /* cap NAPI at 10 msec of spin time */ napi->busy_poll_to = min(10000, napi->busy_poll_to); WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC); WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll); + WRITE_ONCE(ctx->napi_track_mode, napi->op_param); return 0; } @@ -315,7 +326,8 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) case IO_URING_NAPI_STATIC_ADD_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; - return __io_napi_add_id(ctx, napi.op_param); + return __io_napi_add_id(ctx, napi.op_param, + IO_URING_NAPI_TRACKING_STATIC); case IO_URING_NAPI_STATIC_DEL_ID: if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC) return -EINVAL; @@ -343,9 +355,10 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) if (arg && copy_to_user(arg, &curr, sizeof(curr))) return -EFAULT; + WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); WRITE_ONCE(ctx->napi_busy_poll_dt, 0); WRITE_ONCE(ctx->napi_prefer_busy_poll, false); - WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE); + io_napi_free(ctx); return 0; } diff --git a/io_uring/napi.h b/io_uring/napi.h index fa742f42e09b..e0aecccc5065 100644 --- a/io_uring/napi.h +++ b/io_uring/napi.h @@ -15,7 +15,8 @@ void io_napi_free(struct io_ring_ctx *ctx); int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); -int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id); +int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id, + unsigned int mode); void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq); int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx); @@ -43,13 +44,14 @@ static inline void io_napi_add(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct socket *sock; + unsigned int mode = IO_URING_NAPI_TRACKING_DYNAMIC; - if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC) + if (READ_ONCE(ctx->napi_track_mode) != mode) return; sock = sock_from_file(req->file); if (sock && sock->sk) - __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id)); + __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id), mode); } #else diff --git a/io_uring/net.c b/io_uring/net.c index 30cd22c0b934..ee848eb65ec9 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -4,6 +4,7 @@ #include <linux/file.h> #include <linux/slab.h> #include <linux/net.h> +#include <linux/un.h> #include <linux/compat.h> #include <net/compat.h> #include <linux/io_uring.h> @@ -841,7 +842,8 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) } /* bits to clear in old and inherit in new cflags on bundle retry */ -#define CQE_F_MASK (IORING_CQE_F_SOCK_NONEMPTY|IORING_CQE_F_MORE) +#define CQE_F_MASK (IORING_CQE_F_SOCK_NONEMPTY|IORING_CQE_F_MORE|\ + IORING_CQE_F_BUF_MORE) /* * Finishes io_recv and io_recvmsg. @@ -1799,11 +1801,29 @@ out: return IOU_COMPLETE; } +/* + * Check if bind request would potentially end up with filename_create(), + * which in turn end up in mnt_want_write() which will grab the fs + * percpu start write sem. This can trigger a lockdep warning. + */ +static int io_bind_file_create(const struct io_async_msghdr *io, int addr_len) +{ + const struct sockaddr_un *sun; + + if (io->addr.ss_family != AF_UNIX) + return 0; + if (addr_len <= offsetof(struct sockaddr_un, sun_path)) + return 0; + sun = (const struct sockaddr_un *) &io->addr; + return sun->sun_path[0] != '\0'; +} + int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_bind *bind = io_kiocb_to_cmd(req, struct io_bind); struct sockaddr __user *uaddr; struct io_async_msghdr *io; + int ret; if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; @@ -1814,7 +1834,12 @@ int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) io = io_msg_alloc_async(req); if (unlikely(!io)) return -ENOMEM; - return move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); + ret = move_addr_to_kernel(uaddr, bind->addr_len, &io->addr); + if (unlikely(ret)) + return ret; + if (io_bind_file_create(io, bind->addr_len)) + req->flags |= REQ_F_FORCE_ASYNC; + return 0; } int io_bind(struct io_kiocb *req, unsigned int issue_flags) diff --git a/io_uring/nop.c b/io_uring/nop.c index 3caf07878f8a..f5c9969e7f64 100644 --- a/io_uring/nop.c +++ b/io_uring/nop.c @@ -79,9 +79,9 @@ done: if (ret < 0) req_set_fail(req); if (nop->flags & IORING_NOP_CQE32) - io_req_set_res32(req, nop->result, 0, nop->extra1, nop->extra2); + io_req_set_res32(req, ret, 0, nop->extra1, nop->extra2); else - io_req_set_res(req, nop->result, 0); + io_req_set_res(req, ret, 0); if (nop->flags & IORING_NOP_TW) { req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); diff --git a/io_uring/rw.c b/io_uring/rw.c index e729e0e7657e..0c4834645279 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -230,7 +230,7 @@ static inline void io_meta_restore(struct io_async_rw *io, struct kiocb *kiocb) } static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir, - u64 attr_ptr, u64 attr_type_mask) + u64 attr_ptr) { struct io_uring_attr_pi pi_attr; struct io_async_rw *io; @@ -305,7 +305,7 @@ static int __io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, return -EINVAL; attr_ptr = READ_ONCE(sqe->attr_ptr); - return io_prep_rw_pi(req, rw, ddir, attr_ptr, attr_type_mask); + return io_prep_rw_pi(req, rw, ddir, attr_ptr); } return 0; } diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 6af62ca9baba..42b219b34aa8 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -139,12 +139,14 @@ static int io_tctx_install_node(struct io_ring_ctx *ctx, int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; + bool new_tctx = false; int ret; if (unlikely(!tctx)) { tctx = io_uring_alloc_task_context(current, ctx); if (IS_ERR(tctx)) return PTR_ERR(tctx); + new_tctx = true; if (data_race(ctx->int_flags) & IO_RING_F_IOWQ_LIMITS_SET) { unsigned int limits[2]; @@ -168,13 +170,15 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) if (tctx->io_wq) io_wq_set_exit_on_idle(tctx->io_wq, false); - ret = io_tctx_install_node(ctx, tctx); - if (!ret) { + if (new_tctx) current->io_uring = tctx; + + ret = io_tctx_install_node(ctx, tctx); + if (!ret) return 0; - } - if (!current->io_uring) { err_free: + if (new_tctx) { + current->io_uring = NULL; if (tctx->io_wq) { io_wq_exit_start(tctx->io_wq); io_wq_put_and_exit(tctx->io_wq); diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 4cfdfc519770..c4dd26cf342d 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -3,6 +3,7 @@ #include <linux/errno.h> #include <linux/file.h> #include <linux/io_uring.h> +#include <linux/time_namespace.h> #include <trace/events/io_uring.h> @@ -35,6 +36,22 @@ struct io_timeout_rem { bool ltimeout; }; +static clockid_t io_flags_to_clock(unsigned flags) +{ + switch (flags & IORING_TIMEOUT_CLOCK_MASK) { + case IORING_TIMEOUT_BOOTTIME: + return CLOCK_BOOTTIME; + case IORING_TIMEOUT_REALTIME: + return CLOCK_REALTIME; + default: + /* can't happen, vetted at prep time */ + WARN_ON_ONCE(1); + fallthrough; + case 0: + return CLOCK_MONOTONIC; + } +} + static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) { struct timespec64 ts; @@ -43,7 +60,7 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) *time = ns_to_ktime(arg); if (*time < 0) return -EINVAL; - return 0; + goto out; } if (get_timespec64(&ts, u64_to_user_ptr(arg))) @@ -51,6 +68,9 @@ static int io_parse_user_time(ktime_t *time, u64 arg, unsigned flags) if (ts.tv_sec < 0 || ts.tv_nsec < 0) return -EINVAL; *time = timespec64_to_ktime(ts); +out: + if (flags & IORING_TIMEOUT_ABS) + *time = timens_ktime_to_host(io_flags_to_clock(flags), *time); return 0; } @@ -264,6 +284,10 @@ static struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req, struct io_timeout *timeout = io_kiocb_to_cmd(link, struct io_timeout); io_remove_next_linked(req); + + /* If this is NULL, then timer already claimed it and will complete it */ + if (!timeout->head) + return NULL; timeout->head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&timeout->list); @@ -347,6 +371,14 @@ static void io_req_task_link_timeout(struct io_tw_req tw_req, io_tw_token_t tw) int ret; if (prev) { + /* + * splice the linked timeout out of prev's chain if the regular + * completion path didn't already do it. + */ + if (prev->link == req) + prev->link = req->link; + req->link = NULL; + if (!tw.cancel) { struct io_cancel_data cd = { .ctx = req->ctx, @@ -381,12 +413,14 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) /* * We don't expect the list to be empty, that will only happen if we - * race with the completion of the linked work. + * race with the completion of the linked work. Splice of prev is + * done in io_req_task_link_timeout(), if needed. */ if (prev) { - io_remove_next_linked(prev); - if (!req_ref_inc_not_zero(prev)) + if (!req_ref_inc_not_zero(prev)) { + io_remove_next_linked(prev); prev = NULL; + } } list_del(&timeout->list); timeout->prev = prev; @@ -399,18 +433,7 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) static clockid_t io_timeout_get_clock(struct io_timeout_data *data) { - switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { - case IORING_TIMEOUT_BOOTTIME: - return CLOCK_BOOTTIME; - case IORING_TIMEOUT_REALTIME: - return CLOCK_REALTIME; - default: - /* can't happen, vetted at prep time */ - WARN_ON_ONCE(1); - fallthrough; - case 0: - return CLOCK_MONOTONIC; - } + return io_flags_to_clock(data->flags); } static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, diff --git a/io_uring/wait.c b/io_uring/wait.c index 91df86ce0d18..ec01e78a216d 100644 --- a/io_uring/wait.c +++ b/io_uring/wait.c @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/io_uring.h> +#include <linux/time_namespace.h> #include <trace/events/io_uring.h> @@ -229,7 +230,10 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, if (ext_arg->ts_set) { iowq.timeout = timespec64_to_ktime(ext_arg->ts); - if (!(flags & IORING_ENTER_ABS_TIMER)) + if (flags & IORING_ENTER_ABS_TIMER) + iowq.timeout = timens_ktime_to_host(ctx->clockid, + iowq.timeout); + else iowq.timeout = ktime_add(iowq.timeout, start_time); } diff --git a/io_uring/waitid.c b/io_uring/waitid.c index d25d60aed6af..32f68fd7fcdd 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -275,6 +275,7 @@ int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) iw->options = READ_ONCE(sqe->file_index); iw->head = NULL; iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + memset(&iw->info, 0, sizeof(iw->info)); return 0; } |
