Merge tag 'for-6.10/io_uring-20240511' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - Greatly improve send zerocopy performance, by enabling coalescing of
   sent buffers.

   MSG_ZEROCOPY already does this with send(2) and sendmsg(2), but the
   io_uring side did not. In local testing, the crossover point for send
   zerocopy being faster is now around 3000 byte packets, and it
   performs better than the sync syscall variants as well.

   This feature relies on a shared branch with net-next, which was
   pulled into both branches.

 - Unification of how async preparation is done across opcodes.

   Previously, opcodes that required extra memory for async retry would
   allocate that as needed, using on-stack state until that was the
   case. If async retry was needed, the on-stack state was adjusted
   appropriately for a retry and then copied to the allocated memory.

   This led to some fragile and ugly code, particularly for read/write
   handling, and made storage retries more difficult than they needed to
   be. Allocate the memory upfront, as it's cheap from our pools, and
   use that state consistently both initially and also from the retry
   side.

 - Move away from using remap_pfn_range() for mapping the rings.

   This is really not the right interface to use and can cause lifetime
   issues or leaks. Additionally, it means the ring sq/cq arrays need to
   be physically contigious, which can cause problems in production with
   larger rings when services are restarted, as memory can be very
   fragmented at that point.

   Move to using vm_insert_page(s) for the ring sq/cq arrays, and apply
   the same treatment to mapped ring provided buffers. This also helps
   unify the code we have dealing with allocating and mapping memory.

   Hard to see in the diffstat as we're adding a few features as well,
   but this kills about ~400 lines of code from the codebase as well.

 - Add support for bundles for send/recv.

   When used with provided buffers, bundles support sending or receiving
   more than one buffer at the time, improving the efficiency by only
   needing to call into the networking stack once for multiple sends or
   receives.

 - Tweaks for our accept operations, supporting both a DONTWAIT flag for
   skipping poll arm and retry if we can, and a POLLFIRST flag that the
   application can use to skip the initial accept attempt and rely
   purely on poll for triggering the operation. Both of these have
   identical flags on the receive side already.

 - Make the task_work ctx locking unconditional.

   We had various code paths here that would do a mix of lock/trylock
   and set the task_work state to whether or not it was locked. All of
   that goes away, we lock it unconditionally and get rid of the state
   flag indicating whether it's locked or not.

   The state struct still exists as an empty type, can go away in the
   future.

 - Add support for specifying NOP completion values, allowing it to be
   used for error handling testing.

 - Use set/test bit for io-wq worker flags. Not strictly needed, but
   also doesn't hurt and helps silence a KCSAN warning.

 - Cleanups for io-wq locking and work assignments, closing a tiny race
   where cancelations would not be able to find the work item reliably.

 - Misc fixes, cleanups, and improvements

* tag 'for-6.10/io_uring-20240511' of git://git.kernel.dk/linux: (97 commits)
  io_uring: support to inject result for NOP
  io_uring: fail NOP if non-zero op flags is passed in
  io_uring/net: add IORING_ACCEPT_POLL_FIRST flag
  io_uring/net: add IORING_ACCEPT_DONTWAIT flag
  io_uring/filetable: don't unnecessarily clear/reset bitmap
  io_uring/io-wq: Use set_bit() and test_bit() at worker->flags
  io_uring/msg_ring: cleanup posting to IOPOLL vs !IOPOLL ring
  io_uring: Require zeroed sqe->len on provided-buffers send
  io_uring/notif: disable LAZY_WAKE for linked notifs
  io_uring/net: fix sendzc lazy wake polling
  io_uring/msg_ring: reuse ctx->submitter_task read using READ_ONCE instead of re-reading it
  io_uring/rw: reinstate thread check for retries
  io_uring/notif: implement notification stacking
  io_uring/notif: simplify io_notif_flush()
  net: add callback for setting a ubuf_info to skb
  net: extend ubuf_info callback to ops structure
  io_uring/net: support bundles for recv
  io_uring/net: support bundles for send
  io_uring/kbuf: add helpers for getting/peeking multiple buffers
  io_uring/net: add provided buffer support for IORING_OP_SEND
  ...

Author: torvalds

drivers/net/tap.c

@@ -754,7 +754,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 		skb_zcopy_init(skb, msg_control);
 	} else if (msg_control) {
 		struct ubuf_info *uarg = msg_control;
-		uarg->callback(NULL, uarg, false);
+		uarg->ops->complete(NULL, uarg, false);
 	}
 
 	dev_queue_xmit(skb);

drivers/net/tun.c

@@ -1906,7 +1906,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb_zcopy_init(skb, msg_control);
 	} else if (msg_control) {
 		struct ubuf_info *uarg = msg_control;
-		uarg->callback(NULL, uarg, false);
+		uarg->ops->complete(NULL, uarg, false);
 	}
 
 	skb_reset_network_header(skb);

drivers/net/xen-netback/common.h

@@ -390,9 +390,8 @@ bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb);
 
 void xenvif_carrier_on(struct xenvif *vif);
 
-/* Callback from stack when TX packet can be released */
-void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf,
-			      bool zerocopy_success);
+/* Callbacks from stack when TX packet can be released */
+extern const struct ubuf_info_ops xenvif_ubuf_ops;
 
 static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
 {

drivers/net/xen-netback/interface.c

@@ -593,7 +593,7 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 
 	for (i = 0; i < MAX_PENDING_REQS; i++) {
 		queue->pending_tx_info[i].callback_struct = (struct ubuf_info_msgzc)
-			{ { .callback = xenvif_zerocopy_callback },
+			{ { .ops = &xenvif_ubuf_ops },
 			  { { .ctx = NULL,
 			      .desc = i } } };
 		queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;

drivers/net/xen-netback/netback.c

@@ -1156,7 +1156,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s
 	uarg = skb_shinfo(skb)->destructor_arg;
 	/* increase inflight counter to offset decrement in callback */
 	atomic_inc(&queue->inflight_packets);
-	uarg->callback(NULL, uarg, true);
+	uarg->ops->complete(NULL, uarg, true);
 	skb_shinfo(skb)->destructor_arg = NULL;
 
 	/* Fill the skb with the new (local) frags. */
@@ -1278,8 +1278,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
 	return work_done;
 }
 
-void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base,
-			      bool zerocopy_success)
+static void xenvif_zerocopy_callback(struct sk_buff *skb,
+				     struct ubuf_info *ubuf_base,
+				     bool zerocopy_success)
 {
 	unsigned long flags;
 	pending_ring_idx_t index;
@@ -1312,6 +1313,10 @@ void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf_base,
 	xenvif_skb_zerocopy_complete(queue);
 }
 
+const struct ubuf_info_ops xenvif_ubuf_ops = {
+	.complete = xenvif_zerocopy_callback,
+};
+
 static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
 {
 	struct gnttab_unmap_grant_ref *gop;

drivers/nvme/host/ioctl.c

@@ -423,13 +423,20 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly.
+	 * For iopoll, complete it directly. Note that using the uring_cmd
+	 * helper for this is safe only because we check blk_rq_is_poll().
+	 * As that returns false if we're NOT on a polled queue, then it's
+	 * safe to use the polled completion helper.
+	 *
 	 * Otherwise, move the completion to task work.
 	 */
-	if (blk_rq_is_poll(req))
-		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
-	else
+	if (blk_rq_is_poll(req)) {
+		if (pdu->bio)
+			blk_rq_unmap_user(pdu->bio);
+		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
+	} else {
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
+	}
 
 	return RQ_END_IO_FREE;
 }

drivers/vhost/net.c

@@ -380,7 +380,7 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
 	}
 }
 
-static void vhost_zerocopy_callback(struct sk_buff *skb,
+static void vhost_zerocopy_complete(struct sk_buff *skb,
 				    struct ubuf_info *ubuf_base, bool success)
 {
 	struct ubuf_info_msgzc *ubuf = uarg_to_msgzc(ubuf_base);
@@ -408,6 +408,10 @@ static void vhost_zerocopy_callback(struct sk_buff *skb,
 	rcu_read_unlock_bh();
 }
 
+static const struct ubuf_info_ops vhost_ubuf_ops = {
+	.complete = vhost_zerocopy_complete,
+};
+
 static inline unsigned long busy_clock(void)
 {
 	return local_clock() >> 10;
@@ -879,7 +883,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 			vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
 			ubuf->ctx = nvq->ubufs;
 			ubuf->desc = nvq->upend_idx;
-			ubuf->ubuf.callback = vhost_zerocopy_callback;
+			ubuf->ubuf.ops = &vhost_ubuf_ops;
 			ubuf->ubuf.flags = SKBFL_ZEROCOPY_FRAG;
 			refcount_set(&ubuf->ubuf.refcnt, 1);
 			msg.msg_control = &ctl;

include/linux/io_uring.h

@@ -11,7 +11,6 @@ void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
 bool io_is_uring_fops(struct file *file);
 
 static inline void io_uring_files_cancel(void)
@@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode)
 {
 	return "";
 }
-static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
-				    unsigned int issue_flags)
-{
-	return -EOPNOTSUPP;
-}
 static inline bool io_is_uring_fops(struct file *file)
 {
 	return false;

include/linux/io_uring/cmd.h

@@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
 #if defined(CONFIG_IO_URING)
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 			      struct iov_iter *iter, void *ioucmd);
+
+/*
+ * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd
+ * and the corresponding io_uring request.
+ *
+ * Note: the caller should never hard code @issue_flags and is only allowed
+ * to pass the mask provided by the core io_uring code.
+ */
 void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
 			unsigned issue_flags);
+
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
 			    unsigned flags);
 
+/*
+ * Note: the caller should never hard code @issue_flags and only use the
+ * mask provided by the core io_uring code.
+ */
 void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 		unsigned int issue_flags);
 
@@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 }
 #endif
 
+/*
+ * Polled completions must ensure they are coming from a poll queue, and
+ * hence are completed inside the usual poll handling loops.
+ */
+static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd,
+					    ssize_t ret, ssize_t res2)
+{
+	lockdep_assert(in_task());
+	io_uring_cmd_done(ioucmd, ret, res2, 0);
+}
+
 /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
 static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
 			void (*task_work_cb)(struct io_uring_cmd *, unsigned))

include/linux/io_uring/net.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_NET_H
+#define _LINUX_IO_URING_NET_H
+
+struct io_uring_cmd;
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+
+#else
+static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
+				    unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif