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
  ...

6 files changed, 90 insertions, 36 deletions

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 68ed6697fece..e123d5e17b52 100644
--- a/include/linux/io_uring.h
+++ b/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;
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index e453a997c060..447fbfd32215 100644
--- a/include/linux/io_uring/cmd.h
+++ b/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))
diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h
new file mode 100644
index 000000000000..b58f39fed4d5
--- /dev/null
+++ b/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
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index ac333ea81d31..7a6b190c7da7 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -205,6 +205,7 @@ struct io_submit_state {
 
 	bool			plug_started;
 	bool			need_plug;
+	bool			cq_flush;
 	unsigned short		submit_nr;
 	unsigned int		cqes_count;
 	struct blk_plug		plug;
@@ -219,7 +220,7 @@ struct io_ev_fd {
 };
 
 struct io_alloc_cache {
-	struct io_wq_work_node	list;
+	void			**entries;
 	unsigned int		nr_cached;
 	unsigned int		max_cached;
 	size_t			elem_size;
@@ -299,6 +300,8 @@ struct io_ring_ctx {
 		struct io_hash_table	cancel_table_locked;
 		struct io_alloc_cache	apoll_cache;
 		struct io_alloc_cache	netmsg_cache;
+		struct io_alloc_cache	rw_cache;
+		struct io_alloc_cache	uring_cache;
 
 		/*
 		 * Any cancelable uring_cmd is added to this list in
@@ -341,14 +344,8 @@ struct io_ring_ctx {
 		unsigned		cq_last_tm_flush;
 	} ____cacheline_aligned_in_smp;
 
-	struct io_uring_cqe	completion_cqes[16];
-
 	spinlock_t		completion_lock;
 
-	/* IRQ completion list, under ->completion_lock */
-	unsigned int		locked_free_nr;
-	struct io_wq_work_list	locked_free_list;
-
 	struct list_head	io_buffers_comp;
 	struct list_head	cq_overflow_list;
 	struct io_hash_table	cancel_table;
@@ -371,9 +368,6 @@ struct io_ring_ctx {
 
 	struct list_head	io_buffers_cache;
 
-	/* deferred free list, protected by ->uring_lock */
-	struct hlist_head	io_buf_list;
-
 	/* Keep this last, we don't need it for the fast path */
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
@@ -438,8 +432,6 @@ struct io_ring_ctx {
 };
 
 struct io_tw_state {
-	/* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */
-	bool locked;
 };
 
 enum {
@@ -480,6 +472,7 @@ enum {
 	REQ_F_CAN_POLL_BIT,
 	REQ_F_BL_EMPTY_BIT,
 	REQ_F_BL_NO_RECYCLE_BIT,
+	REQ_F_BUFFERS_COMMIT_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -558,6 +551,8 @@ enum {
 	REQ_F_BL_EMPTY		= IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
 	/* don't recycle provided buffers for this request */
 	REQ_F_BL_NO_RECYCLE	= IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
+	/* buffer ring head needs incrementing on put */
+	REQ_F_BUFFERS_COMMIT	= IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4ff48eda3f64..1cc72c370190 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -527,6 +527,13 @@ enum {
 #define SKBFL_ALL_ZEROCOPY	(SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \
 				 SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS)
 
+struct ubuf_info_ops {
+	void (*complete)(struct sk_buff *, struct ubuf_info *,
+			 bool zerocopy_success);
+	/* has to be compatible with skb_zcopy_set() */
+	int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg);
+};
+
 /*
  * The callback notifies userspace to release buffers when skb DMA is done in
  * lower device, the skb last reference should be 0 when calling this.
@@ -536,8 +543,7 @@ enum {
  * The desc field is used to track userspace buffer index.
  */
 struct ubuf_info {
-	void (*callback)(struct sk_buff *, struct ubuf_info *,
-			 bool zerocopy_success);
+	const struct ubuf_info_ops *ops;
 	refcount_t refcnt;
 	u8 flags;
 };
@@ -1662,14 +1668,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
 }
 #endif
 
+extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops;
+
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 				       struct ubuf_info *uarg);
 
 void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
 
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
-			   bool success);
-
 int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
 			    struct sk_buff *skb, struct iov_iter *from,
 			    size_t length);
@@ -1757,13 +1762,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
 static inline void net_zcopy_put(struct ubuf_info *uarg)
 {
 	if (uarg)
-		uarg->callback(NULL, uarg, true);
+		uarg->ops->complete(NULL, uarg, true);
 }
 
 static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref)
 {
 	if (uarg) {
-		if (uarg->callback == msg_zerocopy_callback)
+		if (uarg->ops == &msg_zerocopy_ubuf_ops)
 			msg_zerocopy_put_abort(uarg, have_uref);
 		else if (have_uref)
 			net_zcopy_put(uarg);
@@ -1777,7 +1782,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
 
 	if (uarg) {
 		if (!skb_zcopy_is_nouarg(skb))
-			uarg->callback(skb, uarg, zerocopy_success);
+			uarg->ops->complete(skb, uarg, zerocopy_success);
 
 		skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
 	}
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 7bd10201a02b..994bf7af0efe 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -72,6 +72,7 @@ struct io_uring_sqe {
 		__u32		waitid_flags;
 		__u32		futex_flags;
 		__u32		install_fd_flags;
+		__u32		nop_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -115,7 +116,7 @@ struct io_uring_sqe {
  */
 #define IORING_FILE_INDEX_ALLOC		(~0U)
 
-enum {
+enum io_uring_sqe_flags_bit {
 	IOSQE_FIXED_FILE_BIT,
 	IOSQE_IO_DRAIN_BIT,
 	IOSQE_IO_LINK_BIT,
@@ -351,11 +352,20 @@ enum io_uring_op {
  *				0 is reported if zerocopy was actually possible.
  *				IORING_NOTIF_USAGE_ZC_COPIED if data was copied
  *				(at least partially).
+ *
+ * IORING_RECVSEND_BUNDLE	Used with IOSQE_BUFFER_SELECT. If set, send or
+ *				recv will grab as many buffers from the buffer
+ *				group ID given and send them all. The completion
+ *				result 	will be the number of buffers send, with
+ *				the starting buffer ID in cqe->flags as per
+ *				usual for provided buffer usage. The buffers
+ *				will be	contigious from the starting buffer ID.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)
 #define IORING_RECVSEND_FIXED_BUF	(1U << 2)
 #define IORING_SEND_ZC_REPORT_USAGE	(1U << 3)
+#define IORING_RECVSEND_BUNDLE		(1U << 4)
 
 /*
  * cqe.res for IORING_CQE_F_NOTIF if
@@ -370,11 +380,13 @@ enum io_uring_op {
  * accept flags stored in sqe->ioprio
  */
 #define IORING_ACCEPT_MULTISHOT	(1U << 0)
+#define IORING_ACCEPT_DONTWAIT	(1U << 1)
+#define IORING_ACCEPT_POLL_FIRST	(1U << 2)
 
 /*
  * IORING_OP_MSG_RING command types, stored in sqe->addr
  */
-enum {
+enum io_uring_msg_ring_flags {
 	IORING_MSG_DATA,	/* pass sqe->len as 'res' and off as user_data */
 	IORING_MSG_SEND_FD,	/* send a registered fd to another ring */
 };
@@ -397,6 +409,13 @@ enum {
 #define IORING_FIXED_FD_NO_CLOEXEC	(1U << 0)
 
 /*
+ * IORING_OP_NOP flags (sqe->nop_flags)
+ *
+ * IORING_NOP_INJECT_RESULT	Inject result from sqe->result
+ */
+#define IORING_NOP_INJECT_RESULT	(1U << 0)
+
+/*
  * IO completion data structure (Completion Queue Entry)
  */
 struct io_uring_cqe {
@@ -425,9 +444,7 @@ struct io_uring_cqe {
 #define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
 #define IORING_CQE_F_NOTIF		(1U << 3)
 
-enum {
-	IORING_CQE_BUFFER_SHIFT		= 16,
-};
+#define IORING_CQE_BUFFER_SHIFT		16
 
 /*
  * Magic offsets for the application to mmap the data it needs
@@ -522,11 +539,12 @@ struct io_uring_params {
 #define IORING_FEAT_CQE_SKIP		(1U << 11)
 #define IORING_FEAT_LINKED_FILE		(1U << 12)
 #define IORING_FEAT_REG_REG_RING	(1U << 13)
+#define IORING_FEAT_RECVSEND_BUNDLE	(1U << 14)
 
 /*
  * io_uring_register(2) opcodes and arguments
  */
-enum {
+enum io_uring_register_op {
 	IORING_REGISTER_BUFFERS			= 0,
 	IORING_UNREGISTER_BUFFERS		= 1,
 	IORING_REGISTER_FILES			= 2,
@@ -583,7 +601,7 @@ enum {
 };
 
 /* io-wq worker categories */
-enum {
+enum io_wq_type {
 	IO_WQ_BOUND,
 	IO_WQ_UNBOUND,
 };
@@ -688,7 +706,7 @@ struct io_uring_buf_ring {
  *			IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT)
  *			to get a virtual mapping for the ring.
  */
-enum {
+enum io_uring_register_pbuf_ring_flags {
 	IOU_PBUF_RING_MMAP	= 1,
 };
 
@@ -719,7 +737,7 @@ struct io_uring_napi {
 /*
  * io_uring_restriction->opcode values
  */
-enum {
+enum io_uring_register_restriction_op {
 	/* Allow an io_uring_register(2) opcode */
 	IORING_RESTRICTION_REGISTER_OP		= 0,
 
@@ -775,7 +793,7 @@ struct io_uring_recvmsg_out {
 /*
  * Argument for IORING_OP_URING_CMD when file is a socket
  */
-enum {
+enum io_uring_socket_op {
 	SOCKET_URING_OP_SIOCINQ		= 0,
 	SOCKET_URING_OP_SIOCOUTQ,
 	SOCKET_URING_OP_GETSOCKOPT,