Merge tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:

 - As per (valid) complaint in the last merge window, fs/io_uring.c has
   grown quite large these days. io_uring isn't really tied to fs
   either, as it supports a wide variety of functionality outside of
   that.

   Move the code to io_uring/ and split it into files that either
   implement a specific request type, and split some code into helpers
   as well. The code is organized a lot better like this, and io_uring.c
   is now < 4K LOC (me).

 - Deprecate the epoll_ctl opcode. It'll still work, just trigger a
   warning once if used. If we don't get any complaints on this, and I
   don't expect any, then we can fully remove it in a future release
   (me).

 - Improve the cancel hash locking (Hao)

 - kbuf cleanups (Hao)

 - Efficiency improvements to the task_work handling (Dylan, Pavel)

 - Provided buffer improvements (Dylan)

 - Add support for recv/recvmsg multishot support. This is similar to
   the accept (or poll) support for have for multishot, where a single
   SQE can trigger everytime data is received. For applications that
   expect to do more than a few receives on an instantiated socket, this
   greatly improves efficiency (Dylan).

 - Efficiency improvements for poll handling (Pavel)

 - Poll cancelation improvements (Pavel)

 - Allow specifiying a range for direct descriptor allocations (Pavel)

 - Cleanup the cqe32 handling (Pavel)

 - Move io_uring types to greatly cleanup the tracing (Pavel)

 - Tons of great code cleanups and improvements (Pavel)

 - Add a way to do sync cancelations rather than through the sqe -> cqe
   interface, as that's a lot easier to use for some use cases (me).

 - Add support to IORING_OP_MSG_RING for sending direct descriptors to a
   different ring. This avoids the usually problematic SCM case, as we
   disallow those. (me)

 - Make the per-command alloc cache we use for apoll generic, place
   limits on it, and use it for netmsg as well (me).

 - Various cleanups (me, Michal, Gustavo, Uros)

* tag 'for-5.20/io_uring-2022-07-29' of git://git.kernel.dk/linux-block: (172 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

1 files changed, 261 insertions, 0 deletions

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
new file mode 100644
index 000000000000..5db0a60dc04e
--- /dev/null
+++ b/io_uring/io_uring.h
@@ -0,0 +1,261 @@
+#ifndef IOU_CORE_H
+#define IOU_CORE_H
+
+#include <linux/errno.h>
+#include <linux/lockdep.h>
+#include <linux/io_uring_types.h>
+#include "io-wq.h"
+#include "slist.h"
+#include "filetable.h"
+
+#ifndef CREATE_TRACE_POINTS
+#include <trace/events/io_uring.h>
+#endif
+
+enum {
+	IOU_OK			= 0,
+	IOU_ISSUE_SKIP_COMPLETE	= -EIOCBQUEUED,
+
+	/*
+	 * Intended only when both REQ_F_POLLED and REQ_F_APOLL_MULTISHOT
+	 * are set to indicate to the poll runner that multishot should be
+	 * removed and the result is set on req->cqe.res.
+	 */
+	IOU_STOP_MULTISHOT	= -ECANCELED,
+};
+
+struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx);
+bool io_req_cqe_overflow(struct io_kiocb *req);
+int io_run_task_work_sig(void);
+void io_req_complete_failed(struct io_kiocb *req, s32 res);
+void __io_req_complete(struct io_kiocb *req, unsigned issue_flags);
+void io_req_complete_post(struct io_kiocb *req);
+void __io_req_complete_post(struct io_kiocb *req);
+bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags,
+		     bool allow_overflow);
+void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
+
+struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
+
+struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+			       unsigned issue_flags);
+
+static inline bool io_req_ffs_set(struct io_kiocb *req)
+{
+	return req->flags & REQ_F_FIXED_FILE;
+}
+
+bool io_is_uring_fops(struct file *file);
+bool io_alloc_async_data(struct io_kiocb *req);
+void io_req_task_work_add(struct io_kiocb *req);
+void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);
+void io_req_task_queue(struct io_kiocb *req);
+void io_queue_iowq(struct io_kiocb *req, bool *dont_use);
+void io_req_task_complete(struct io_kiocb *req, bool *locked);
+void io_req_task_queue_fail(struct io_kiocb *req, int ret);
+void io_req_task_submit(struct io_kiocb *req, bool *locked);
+void tctx_task_work(struct callback_head *cb);
+__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
+int io_uring_alloc_task_context(struct task_struct *task,
+				struct io_ring_ctx *ctx);
+
+int io_poll_issue(struct io_kiocb *req, bool *locked);
+int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
+int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin);
+void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node);
+int io_req_prep_async(struct io_kiocb *req);
+
+struct io_wq_work *io_wq_free_work(struct io_wq_work *work);
+void io_wq_submit_work(struct io_wq_work *work);
+
+void io_free_req(struct io_kiocb *req);
+void io_queue_next(struct io_kiocb *req);
+
+bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
+			bool cancel_all);
+
+#define io_for_each_link(pos, head) \
+	for (pos = (head); pos; pos = pos->link)
+
+static inline void io_cq_lock(struct io_ring_ctx *ctx)
+	__acquires(ctx->completion_lock)
+{
+	spin_lock(&ctx->completion_lock);
+}
+
+void io_cq_unlock_post(struct io_ring_ctx *ctx);
+
+static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
+{
+	if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
+		struct io_uring_cqe *cqe = ctx->cqe_cached;
+
+		ctx->cached_cq_tail++;
+		ctx->cqe_cached++;
+		if (ctx->flags & IORING_SETUP_CQE32)
+			ctx->cqe_cached++;
+		return cqe;
+	}
+
+	return __io_get_cqe(ctx);
+}
+
+static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
+				     struct io_kiocb *req)
+{
+	struct io_uring_cqe *cqe;
+
+	/*
+	 * If we can't get a cq entry, userspace overflowed the
+	 * submission (by quite a lot). Increment the overflow count in
+	 * the ring.
+	 */
+	cqe = io_get_cqe(ctx);
+	if (unlikely(!cqe))
+		return io_req_cqe_overflow(req);
+
+	trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+				req->cqe.res, req->cqe.flags,
+				(req->flags & REQ_F_CQE32_INIT) ? req->extra1 : 0,
+				(req->flags & REQ_F_CQE32_INIT) ? req->extra2 : 0);
+
+	memcpy(cqe, &req->cqe, sizeof(*cqe));
+
+	if (ctx->flags & IORING_SETUP_CQE32) {
+		u64 extra1 = 0, extra2 = 0;
+
+		if (req->flags & REQ_F_CQE32_INIT) {
+			extra1 = req->extra1;
+			extra2 = req->extra2;
+		}
+
+		WRITE_ONCE(cqe->big_cqe[0], extra1);
+		WRITE_ONCE(cqe->big_cqe[1], extra2);
+	}
+	return true;
+}
+
+static inline void req_set_fail(struct io_kiocb *req)
+{
+	req->flags |= REQ_F_FAIL;
+	if (req->flags & REQ_F_CQE_SKIP) {
+		req->flags &= ~REQ_F_CQE_SKIP;
+		req->flags |= REQ_F_SKIP_LINK_CQES;
+	}
+}
+
+static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags;
+}
+
+static inline bool req_has_async_data(struct io_kiocb *req)
+{
+	return req->flags & REQ_F_ASYNC_DATA;
+}
+
+static inline void io_put_file(struct file *file)
+{
+	if (file)
+		fput(file);
+}
+
+static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx,
+					 unsigned issue_flags)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_unlock(&ctx->uring_lock);
+}
+
+static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
+				       unsigned issue_flags)
+{
+	/*
+	 * "Normal" inline submissions always hold the uring_lock, since we
+	 * grab it from the system call. Same is true for the SQPOLL offload.
+	 * The only exception is when we've detached the request and issue it
+	 * from an async worker thread, grab the lock for that case.
+	 */
+	if (issue_flags & IO_URING_F_UNLOCKED)
+		mutex_lock(&ctx->uring_lock);
+	lockdep_assert_held(&ctx->uring_lock);
+}
+
+static inline void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+	/* order cqe stores with ring update */
+	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
+}
+
+static inline void io_cqring_wake(struct io_ring_ctx *ctx)
+{
+	/*
+	 * wake_up_all() may seem excessive, but io_wake_function() and
+	 * io_should_wake() handle the termination of the loop and only
+	 * wake as many waiters as we need to.
+	 */
+	if (wq_has_sleeper(&ctx->cq_wait))
+		wake_up_all(&ctx->cq_wait);
+}
+
+static inline bool io_sqring_full(struct io_ring_ctx *ctx)
+{
+	struct io_rings *r = ctx->rings;
+
+	return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries;
+}
+
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	struct io_rings *rings = ctx->rings;
+
+	/* make sure SQ entry isn't read before tail */
+	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
+}
+
+static inline bool io_run_task_work(void)
+{
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL)) {
+		__set_current_state(TASK_RUNNING);
+		clear_notify_signal();
+		if (task_work_pending(current))
+			task_work_run();
+		return true;
+	}
+
+	return false;
+}
+
+static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
+{
+	if (!*locked) {
+		mutex_lock(&ctx->uring_lock);
+		*locked = true;
+	}
+}
+
+/*
+ * Don't complete immediately but use deferred completion infrastructure.
+ * Protected by ->uring_lock and can only be used either with
+ * IO_URING_F_COMPLETE_DEFER or inside a tw handler holding the mutex.
+ */
+static inline void io_req_complete_defer(struct io_kiocb *req)
+	__must_hold(&req->ctx->uring_lock)
+{
+	struct io_submit_state *state = &req->ctx->submit_state;
+
+	lockdep_assert_held(&req->ctx->uring_lock);
+
+	wq_list_add_tail(&req->comp_list, &state->compl_reqs);
+}
+
+static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx)
+{
+	if (unlikely(ctx->off_timeout_used || ctx->drain_active || ctx->has_evfd))
+		__io_commit_cqring_flush(ctx);
+}
+
+#endif