diff options
Diffstat (limited to 'io_uring')
| -rw-r--r-- | io_uring/eventfd.c | 10 | ||||
| -rw-r--r-- | io_uring/io_uring.c | 26 | ||||
| -rw-r--r-- | io_uring/kbuf.c | 13 | ||||
| -rw-r--r-- | io_uring/net.c | 2 | ||||
| -rw-r--r-- | io_uring/register.c | 12 | ||||
| -rw-r--r-- | io_uring/zcrx.c | 5 |
6 files changed, 58 insertions, 10 deletions
diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index 78f8ab7db104..ab789e1ebe91 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -76,11 +76,15 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event) { bool skip = false; struct io_ev_fd *ev_fd; - - if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) - return; + struct io_rings *rings; guard(rcu)(); + + rings = rcu_dereference(ctx->rings_rcu); + if (!rings) + return; + if (READ_ONCE(rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) + return; ev_fd = rcu_dereference(ctx->io_ev_fd); /* * Check again if ev_fd exists in case an io_eventfd_unregister call diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 63efd60829f3..ac1a5cf10287 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1202,6 +1202,21 @@ void tctx_task_work(struct callback_head *cb) WARN_ON_ONCE(ret); } +/* + * Sets IORING_SQ_TASKRUN in the sq_flags shared with userspace, using the + * RCU protected rings pointer to be safe against concurrent ring resizing. + */ +static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx) +{ + lockdep_assert_in_rcu_read_lock(); + + if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) { + struct io_rings *rings = rcu_dereference(ctx->rings_rcu); + + atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags); + } +} + static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; @@ -1256,8 +1271,7 @@ static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) */ if (!head) { - if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) - atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); + io_ctx_mark_taskrun(ctx); if (ctx->has_evfd) io_eventfd_signal(ctx, false); } @@ -1281,6 +1295,10 @@ static void io_req_normal_work_add(struct io_kiocb *req) if (!llist_add(&req->io_task_work.node, &tctx->task_list)) return; + /* + * Doesn't need to use ->rings_rcu, as resizing isn't supported for + * !DEFER_TASKRUN. + */ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); @@ -2152,7 +2170,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, * well as 2 contiguous entries. */ if (!(ctx->flags & IORING_SETUP_SQE_MIXED) || *left < 2 || - !(ctx->cached_sq_head & (ctx->sq_entries - 1))) + (unsigned)(sqe - ctx->sq_sqes) >= ctx->sq_entries - 1) return io_init_fail_req(req, -EINVAL); /* * A 128b operation on a mixed SQ uses two entries, so we have @@ -2760,6 +2778,7 @@ static void io_rings_free(struct io_ring_ctx *ctx) io_free_region(ctx->user, &ctx->sq_region); io_free_region(ctx->user, &ctx->ring_region); ctx->rings = NULL; + RCU_INIT_POINTER(ctx->rings_rcu, NULL); ctx->sq_sqes = NULL; } @@ -3389,6 +3408,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (ret) return ret; ctx->rings = rings = io_region_get_ptr(&ctx->ring_region); + rcu_assign_pointer(ctx->rings_rcu, rings); if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) ctx->sq_array = (u32 *)((char *)rings + rl->sq_array_offset); diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index dae5b4ab3819..e7f444953dfb 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -111,9 +111,18 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); - list_add(&buf->list, &bl->buf_list); - bl->nbufs++; + /* + * If the buffer list was upgraded to a ring-based one, or removed, + * while the request was in-flight in io-wq, drop it. + */ + if (bl && !(bl->flags & IOBL_BUF_RING)) { + list_add(&buf->list, &bl->buf_list); + bl->nbufs++; + } else { + kfree(buf); + } req->flags &= ~REQ_F_BUFFER_SELECTED; + req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true; diff --git a/io_uring/net.c b/io_uring/net.c index d9a4b83804a2..cfcd49f0cecf 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -375,6 +375,8 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) kmsg->msg.msg_namelen = addr_len; } if (sr->flags & IORING_RECVSEND_FIXED_BUF) { + if (sr->flags & IORING_SEND_VECTORIZED) + return -EINVAL; req->flags |= REQ_F_IMPORT_BUFFER; return 0; } diff --git a/io_uring/register.c b/io_uring/register.c index 12318c276068..ff9d75ffbd15 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -545,7 +545,15 @@ overflow: ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; + /* + * Just mark any flag we may have missed and that the application + * should act on unconditionally. Worst case it'll be an extra + * syscall. + */ + atomic_or(IORING_SQ_TASKRUN | IORING_SQ_NEED_WAKEUP, &n.rings->sq_flags); ctx->rings = n.rings; + rcu_assign_pointer(ctx->rings_rcu, n.rings); + ctx->sq_sqes = n.sq_sqes; swap_old(ctx, o, n, ring_region); swap_old(ctx, o, n, sq_region); @@ -554,6 +562,10 @@ overflow: out: spin_unlock(&ctx->completion_lock); mutex_unlock(&ctx->mmap_lock); + + /* Wait for concurrent io_ctx_mark_taskrun() */ + if (to_free == &o) + synchronize_rcu_expedited(); io_register_free_rings(ctx, to_free); if (ctx->sq_data) diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 93da8933a91f..262ac732cf96 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -898,11 +898,12 @@ static inline bool io_parse_rqe(struct io_uring_zcrx_rqe *rqe, struct io_zcrx_ifq *ifq, struct net_iov **ret_niov) { + __u64 off = READ_ONCE(rqe->off); unsigned niov_idx, area_idx; struct io_zcrx_area *area; - area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT; - niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift; + area_idx = off >> IORING_ZCRX_AREA_SHIFT; + niov_idx = (off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift; if (unlikely(rqe->__pad || area_idx)) return false; |