Merge tag 'for-6.9/io_uring-20240310' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - Make running of task_work internal loops more fair, and unify how the
   different methods deal with them (me)

 - Support for per-ring NAPI. The two minor networking patches are in a
   shared branch with netdev (Stefan)

 - Add support for truncate (Tony)

 - Export SQPOLL utilization stats (Xiaobing)

 - Multishot fixes (Pavel)

 - Fix for a race in manipulating the request flags via poll (Pavel)

 - Cleanup the multishot checking by making it generic, moving it out of
   opcode handlers (Pavel)

 - Various tweaks and cleanups (me, Kunwu, Alexander)

* tag 'for-6.9/io_uring-20240310' of git://git.kernel.dk/linux: (53 commits)
  io_uring: Fix sqpoll utilization check racing with dying sqpoll
  io_uring/net: dedup io_recv_finish req completion
  io_uring: refactor DEFER_TASKRUN multishot checks
  io_uring: fix mshot io-wq checks
  io_uring/net: add io_req_msg_cleanup() helper
  io_uring/net: simplify msghd->msg_inq checking
  io_uring/kbuf: rename REQ_F_PARTIAL_IO to REQ_F_BL_NO_RECYCLE
  io_uring/net: remove dependency on REQ_F_PARTIAL_IO for sr->done_io
  io_uring/net: correctly handle multishot recvmsg retry setup
  io_uring/net: clear REQ_F_BL_EMPTY in the multishot retry handler
  io_uring: fix io_queue_proc modifying req->flags
  io_uring: fix mshot read defer taskrun cqe posting
  io_uring/net: fix overflow check in io_recvmsg_mshot_prep()
  io_uring/net: correct the type of variable
  io_uring/sqpoll: statistics of the true utilization of sq threads
  io_uring/net: move recv/recvmsg flags out of retry loop
  io_uring/kbuf: flag request if buffer pool is empty after buffer pick
  io_uring/net: improve the usercopy for sendmsg/recvmsg
  io_uring/net: move receive multishot out of the generic msghdr path
  io_uring/net: unify how recvmsg and sendmsg copy in the msghdr
  ...

fs/internal.h

@@ -183,6 +183,7 @@ extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 struct file *file_close_fd_locked(struct files_struct *files, unsigned fd);
 
+long do_ftruncate(struct file *file, loff_t length, int small);
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,

fs/open.c

@@ -154,49 +154,52 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length
 }
 #endif
 
-long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+long do_ftruncate(struct file *file, loff_t length, int small)
 {
 	struct inode *inode;
 	struct dentry *dentry;
-	struct fd f;
 	int error;
 
-	error = -EINVAL;
-	if (length < 0)
-		goto out;
-	error = -EBADF;
-	f = fdget(fd);
-	if (!f.file)
-		goto out;
-
 	/* explicitly opened as large or we are on 64-bit box */
-	if (f.file->f_flags & O_LARGEFILE)
+	if (file->f_flags & O_LARGEFILE)
 		small = 0;
 
-	dentry = f.file->f_path.dentry;
+	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
-	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
-		goto out_putf;
+	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
+		return -EINVAL;
 
-	error = -EINVAL;
 	/* Cannot ftruncate over 2^31 bytes without large file support */
 	if (small && length > MAX_NON_LFS)
-		goto out_putf;
+		return -EINVAL;
 
-	error = -EPERM;
 	/* Check IS_APPEND on real upper inode */
-	if (IS_APPEND(file_inode(f.file)))
-		goto out_putf;
+	if (IS_APPEND(file_inode(file)))
+		return -EPERM;
 	sb_start_write(inode->i_sb);
-	error = security_file_truncate(f.file);
+	error = security_file_truncate(file);
 	if (!error)
-		error = do_truncate(file_mnt_idmap(f.file), dentry, length,
-				    ATTR_MTIME | ATTR_CTIME, f.file);
+		error = do_truncate(file_mnt_idmap(file), dentry, length,
+				    ATTR_MTIME | ATTR_CTIME, file);
 	sb_end_write(inode->i_sb);
-out_putf:
+
+	return error;
+}
+
+long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+{
+	struct fd f;
+	int error;
+
+	if (length < 0)
+		return -EINVAL;
+	f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = do_ftruncate(f.file, length, small);
+
 	fdput(f);
-out:
 	return error;
 }
 

include/linux/io_uring_types.h

@@ -2,6 +2,7 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
 #include <linux/llist.h>
@@ -240,12 +241,14 @@ struct io_ring_ctx {
 		unsigned int		poll_activated: 1;
 		unsigned int		drain_disabled: 1;
 		unsigned int		compat: 1;
+		unsigned int		iowq_limits_set : 1;
 
 		struct task_struct	*submitter_task;
 		struct io_rings		*rings;
 		struct percpu_ref	refs;
 
 		enum task_work_notify_mode	notify_method;
+		unsigned			sq_thread_idle;
 	} ____cacheline_aligned_in_smp;
 
 	/* submission data */
@@ -274,10 +277,20 @@ struct io_ring_ctx {
 		 */
 		struct io_rsrc_node	*rsrc_node;
 		atomic_t		cancel_seq;
+
+		/*
+		 * ->iopoll_list is protected by the ctx->uring_lock for
+		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
+		 * For SQPOLL, only the single threaded io_sq_thread() will
+		 * manipulate the list, hence no extra locking is needed there.
+		 */
+		bool			poll_multi_queue;
+		struct io_wq_work_list	iopoll_list;
+
 		struct io_file_table	file_table;
+		struct io_mapped_ubuf	**user_bufs;
 		unsigned		nr_user_files;
 		unsigned		nr_user_bufs;
-		struct io_mapped_ubuf	**user_bufs;
 
 		struct io_submit_state	submit_state;
 
@@ -288,15 +301,6 @@ struct io_ring_ctx {
 		struct io_alloc_cache	apoll_cache;
 		struct io_alloc_cache	netmsg_cache;
 
-		/*
-		 * ->iopoll_list is protected by the ctx->uring_lock for
-		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
-		 * For SQPOLL, only the single threaded io_sq_thread() will
-		 * manipulate the list, hence no extra locking is needed there.
-		 */
-		struct io_wq_work_list	iopoll_list;
-		bool			poll_multi_queue;
-
 		/*
 		 * Any cancelable uring_cmd is added to this list in
 		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()
@@ -343,8 +347,8 @@ struct io_ring_ctx {
 	spinlock_t		completion_lock;
 
 	/* IRQ completion list, under ->completion_lock */
-	struct io_wq_work_list	locked_free_list;
 	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;
@@ -366,9 +370,6 @@ struct io_ring_ctx {
 	unsigned int		file_alloc_start;
 	unsigned int		file_alloc_end;
 
-	struct xarray		personalities;
-	u32			pers_next;
-
 	struct list_head	io_buffers_cache;
 
 	/* deferred free list, protected by ->uring_lock */
@@ -389,6 +390,9 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
+	u32			pers_next;
+	struct xarray		personalities;
+
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
@@ -405,11 +409,22 @@ struct io_ring_ctx {
 
 	/* io-wq management, e.g. thread count */
 	u32				iowq_limits[2];
-	bool				iowq_limits_set;
 
 	struct callback_head		poll_wq_task_work;
 	struct list_head		defer_list;
-	unsigned			sq_thread_idle;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct list_head	napi_list;	/* track busy poll napi_id */
+	spinlock_t		napi_lock;	/* napi_list lock */
+
+	/* napi busy poll default timeout */
+	unsigned int		napi_busy_poll_to;
+	bool			napi_prefer_busy_poll;
+	bool			napi_enabled;
+
+	DECLARE_HASHTABLE(napi_ht, 4);
+#endif
+
 	/* protected by ->completion_lock */
 	unsigned			evfd_last_cq_tail;
 
@@ -455,7 +470,6 @@ enum {
 	REQ_F_SKIP_LINK_CQES_BIT,
 	REQ_F_SINGLE_POLL_BIT,
 	REQ_F_DOUBLE_POLL_BIT,
-	REQ_F_PARTIAL_IO_BIT,
 	REQ_F_APOLL_MULTISHOT_BIT,
 	REQ_F_CLEAR_POLLIN_BIT,
 	REQ_F_HASH_LOCKED_BIT,
@@ -463,75 +477,88 @@ enum {
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
 	REQ_F_POLL_NO_LAZY_BIT,
+	REQ_F_CANCEL_SEQ_BIT,
+	REQ_F_CAN_POLL_BIT,
+	REQ_F_BL_EMPTY_BIT,
+	REQ_F_BL_NO_RECYCLE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
 };
 
+typedef u64 __bitwise io_req_flags_t;
+#define IO_REQ_FLAG(bitno)	((__force io_req_flags_t) BIT_ULL((bitno)))
+
 enum {
 	/* ctx owns file */
-	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	REQ_F_FIXED_FILE	= IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT),
 	/* drain existing IO first */
-	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	REQ_F_IO_DRAIN		= IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT),
 	/* linked sqes */
-	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	REQ_F_LINK		= IO_REQ_FLAG(REQ_F_LINK_BIT),
 	/* doesn't sever on completion < 0 */
-	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	REQ_F_HARDLINK		= IO_REQ_FLAG(REQ_F_HARDLINK_BIT),
 	/* IOSQE_ASYNC */
-	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+	REQ_F_FORCE_ASYNC	= IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT),
 	/* IOSQE_BUFFER_SELECT */
-	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
+	REQ_F_BUFFER_SELECT	= IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT),
 	/* IOSQE_CQE_SKIP_SUCCESS */
-	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),
+	REQ_F_CQE_SKIP		= IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT),
 
 	/* fail rest of links */
-	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
+	REQ_F_FAIL		= IO_REQ_FLAG(REQ_F_FAIL_BIT),
 	/* on inflight list, should be cancelled and waited on exit reliably */
-	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	REQ_F_INFLIGHT		= IO_REQ_FLAG(REQ_F_INFLIGHT_BIT),
 	/* read/write uses file position */
-	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	REQ_F_CUR_POS		= IO_REQ_FLAG(REQ_F_CUR_POS_BIT),
 	/* must not punt to workers */
-	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	REQ_F_NOWAIT		= IO_REQ_FLAG(REQ_F_NOWAIT_BIT),
 	/* has or had linked timeout */
-	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	REQ_F_LINK_TIMEOUT	= IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT),
 	/* needs cleanup */
-	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
+	REQ_F_NEED_CLEANUP	= IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT),
 	/* already went through poll handler */
-	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
+	REQ_F_POLLED		= IO_REQ_FLAG(REQ_F_POLLED_BIT),
 	/* buffer already selected */
-	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	REQ_F_BUFFER_SELECTED	= IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT),
 	/* buffer selected from ring, needs commit */
-	REQ_F_BUFFER_RING	= BIT(REQ_F_BUFFER_RING_BIT),
+	REQ_F_BUFFER_RING	= IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT),
 	/* caller should reissue async */
-	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
+	REQ_F_REISSUE		= IO_REQ_FLAG(REQ_F_REISSUE_BIT),
 	/* supports async reads/writes */
-	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
+	REQ_F_SUPPORT_NOWAIT	= IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT),
 	/* regular file */
-	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	REQ_F_ISREG		= IO_REQ_FLAG(REQ_F_ISREG_BIT),
 	/* has creds assigned */
-	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
+	REQ_F_CREDS		= IO_REQ_FLAG(REQ_F_CREDS_BIT),
 	/* skip refcounting if not set */
-	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
+	REQ_F_REFCOUNT		= IO_REQ_FLAG(REQ_F_REFCOUNT_BIT),
 	/* there is a linked timeout that has to be armed */
-	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
+	REQ_F_ARM_LTIMEOUT	= IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT),
 	/* ->async_data allocated */
-	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
+	REQ_F_ASYNC_DATA	= IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT),
 	/* don't post CQEs while failing linked requests */
-	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
+	REQ_F_SKIP_LINK_CQES	= IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT),
 	/* single poll may be active */
-	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
+	REQ_F_SINGLE_POLL	= IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT),
 	/* double poll may active */
-	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
-	/* request has already done partial IO */
-	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
+	REQ_F_DOUBLE_POLL	= IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT),
 	/* fast poll multishot mode */
-	REQ_F_APOLL_MULTISHOT	= BIT(REQ_F_APOLL_MULTISHOT_BIT),
+	REQ_F_APOLL_MULTISHOT	= IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT),
 	/* recvmsg special flag, clear EPOLLIN */
-	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
+	REQ_F_CLEAR_POLLIN	= IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
-	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	REQ_F_HASH_LOCKED	= IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
 	/* don't use lazy poll wake for this request */
-	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
+	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
+	/* cancel sequence is set and valid */
+	REQ_F_CANCEL_SEQ	= IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
+	/* file is pollable */
+	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
+	/* buffer list was empty after selection of buffer */
+	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),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -592,15 +619,17 @@ struct io_kiocb {
 	 * and after selection it points to the buffer ID itself.
 	 */
 	u16				buf_index;
-	unsigned int			flags;
+
+	unsigned			nr_tw;
+
+	/* REQ_F_* flags */
+	io_req_flags_t			flags;
 
 	struct io_cqe			cqe;
 
 	struct io_ring_ctx		*ctx;
 	struct task_struct		*task;
 
-	struct io_rsrc_node		*rsrc_node;
-
 	union {
 		/* store used ubuf, so we can prevent reloading */
 		struct io_mapped_ubuf	*imu;
@@ -621,10 +650,12 @@ struct io_kiocb {
 		/* cache ->apoll->events */
 		__poll_t apoll_events;
 	};
+
+	struct io_rsrc_node		*rsrc_node;
+
 	atomic_t			refs;
 	atomic_t			poll_refs;
 	struct io_task_work		io_task_work;
-	unsigned			nr_tw;
 	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
 	struct hlist_node		hash_node;
 	/* internal polling, see IORING_FEAT_FAST_POLL */

include/net/busy_poll.h

@@ -48,6 +48,10 @@ void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
 		    void *loop_end_arg, bool prefer_busy_poll, u16 budget);
 
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
 #else /* CONFIG_NET_RX_BUSY_POLL */
 static inline unsigned long net_busy_loop_on(void)
 {

include/trace/events/io_uring.h

@@ -148,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__field(  void *,			req		)
 		__field(  u64,				user_data	)
 		__field(  u8,				opcode		)
-		__field(  unsigned int,			flags		)
+		__field(  unsigned long long,		flags		)
 		__field(  struct io_wq_work *,		work		)
 		__field(  int,				rw		)
 
@@ -159,7 +159,7 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__entry->ctx		= req->ctx;
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->opcode		= req->opcode;
 		__entry->work		= &req->work;
 		__entry->rw		= rw;
@@ -167,10 +167,10 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%llx, %s queue, work %p",
 		__entry->ctx, __entry->req, __entry->user_data,
-		__get_str(op_str),
-		__entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
+		__get_str(op_str), __entry->flags,
+		__entry->rw ? "hashed" : "normal", __entry->work)
 );
 
 /**
@@ -378,7 +378,7 @@ TRACE_EVENT(io_uring_submit_req,
 		__field(  void *,		req		)
 		__field(  unsigned long long,	user_data	)
 		__field(  u8,			opcode		)
-		__field(  u32,			flags		)
+		__field(  unsigned long long,	flags		)
 		__field(  bool,			sq_thread	)
 
 		__string( op_str, io_uring_get_opcode(req->opcode) )
@@ -389,16 +389,16 @@ TRACE_EVENT(io_uring_submit_req,
 		__entry->req		= req;
 		__entry->user_data	= req->cqe.user_data;
 		__entry->opcode		= req->opcode;
-		__entry->flags		= req->flags;
+		__entry->flags		= (__force unsigned long long) req->flags;
 		__entry->sq_thread	= req->ctx->flags & IORING_SETUP_SQPOLL;
 
 		__assign_str(op_str, io_uring_get_opcode(req->opcode));
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%llx, "
 		  "sq_thread %d", __entry->ctx, __entry->req,
-		  __entry->user_data, __get_str(op_str),
-		  __entry->flags, __entry->sq_thread)
+		  __entry->user_data, __get_str(op_str), __entry->flags,
+		  __entry->sq_thread)
 );
 
 /*
@@ -602,29 +602,25 @@ TRACE_EVENT(io_uring_cqe_overflow,
  *
  * @tctx:		pointer to a io_uring_task
  * @count:		how many functions it ran
- * @loops:		how many loops it ran
  *
  */
 TRACE_EVENT(io_uring_task_work_run,
 
-	TP_PROTO(void *tctx, unsigned int count, unsigned int loops),
+	TP_PROTO(void *tctx, unsigned int count),
 
-	TP_ARGS(tctx, count, loops),
+	TP_ARGS(tctx, count),
 
 	TP_STRUCT__entry (
 		__field(  void *,		tctx		)
 		__field(  unsigned int,		count		)
-		__field(  unsigned int,		loops		)
 	),
 
 	TP_fast_assign(
 		__entry->tctx		= tctx;
 		__entry->count		= count;
-		__entry->loops		= loops;
 	),
 
-	TP_printk("tctx %p, count %u, loops %u",
-		 __entry->tctx, __entry->count, __entry->loops)
+	TP_printk("tctx %p, count %u", __entry->tctx, __entry->count)
 );
 
 TRACE_EVENT(io_uring_short_write,

include/uapi/linux/io_uring.h

@@ -255,6 +255,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
 	IORING_OP_FIXED_FD_INSTALL,
+	IORING_OP_FTRUNCATE,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -570,6 +571,10 @@ enum {
 	/* return status information for a buffer group */
 	IORING_REGISTER_PBUF_STATUS		= 26,
 
+	/* set/clear busy poll settings */
+	IORING_REGISTER_NAPI			= 27,
+	IORING_UNREGISTER_NAPI			= 28,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -703,6 +708,14 @@ struct io_uring_buf_status {
 	__u32	resv[8];
 };
 
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+	__u32	busy_poll_to;
+	__u8	prefer_busy_poll;
+	__u8	pad[3];
+	__u64	resv;
+};
+
 /*
  * io_uring_restriction->opcode values
  */

io_uring/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
 					cancel.o kbuf.o rsrc.o rw.o opdef.o \
-					notif.o waitid.o register.o
+					notif.o waitid.o register.o truncate.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
+obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o

io_uring/cancel.c

@@ -58,9 +58,8 @@ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd)
 		return false;
 	if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
 check_seq:
-		if (cd->seq == req->work.cancel_seq)
+		if (io_cancel_match_sequence(req, cd->seq))
 			return false;
-		req->work.cancel_seq = cd->seq;
 	}
 
 	return true;

io_uring/cancel.h

@@ -25,4 +25,14 @@ void init_hash_table(struct io_hash_table *table, unsigned size);
 int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg);
 bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd);
 
+static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence)
+{
+	if ((req->flags & REQ_F_CANCEL_SEQ) && sequence == req->work.cancel_seq)
+		return true;
+
+	req->flags |= REQ_F_CANCEL_SEQ;
+	req->work.cancel_seq = sequence;
+	return false;
+}
+
 #endif

io_uring/fdinfo.c

@@ -55,6 +55,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	struct io_ring_ctx *ctx = f->private_data;
 	struct io_overflow_cqe *ocqe;
 	struct io_rings *r = ctx->rings;
+	struct rusage sq_usage;
 	unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
 	unsigned int sq_head = READ_ONCE(r->sq.head);
 	unsigned int sq_tail = READ_ONCE(r->sq.tail);
@@ -64,6 +65,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	unsigned int sq_shift = 0;
 	unsigned int sq_entries, cq_entries;
 	int sq_pid = -1, sq_cpu = -1;
+	u64 sq_total_time = 0, sq_work_time = 0;
 	bool has_lock;
 	unsigned int i;
 
@@ -145,12 +147,24 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
 		struct io_sq_data *sq = ctx->sq_data;
 
-		sq_pid = sq->task_pid;
-		sq_cpu = sq->sq_cpu;
+		/*
+		 * sq->thread might be NULL if we raced with the sqpoll
+		 * thread termination.
+		 */
+		if (sq->thread) {
+			sq_pid = sq->task_pid;
+			sq_cpu = sq->sq_cpu;
+			getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
+			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
+					 + sq_usage.ru_stime.tv_usec);
+			sq_work_time = sq->work_time;
+		}
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
 	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time);
+	seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time);
 	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
 	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
 		struct file *f = io_file_from_index(&ctx->file_table, i);

io_uring/filetable.h

@@ -17,7 +17,7 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
 int io_register_file_alloc_range(struct io_ring_ctx *ctx,
 				 struct io_uring_file_index_range __user *arg);
 
-unsigned int io_file_get_flags(struct file *file);
+io_req_flags_t io_file_get_flags(struct file *file);
 
 static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
 {

io_uring/io_uring.h

@@ -5,6 +5,7 @@
 #include <linux/lockdep.h>
 #include <linux/resume_user_mode.h>
 #include <linux/kasan.h>
+#include <linux/poll.h>
 #include <linux/io_uring_types.h>
 #include <uapi/linux/eventpoll.h>
 #include "io-wq.h"
@@ -34,6 +35,32 @@ enum {
 	IOU_STOP_MULTISHOT	= -ECANCELED,
 };
 
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	unsigned cq_tail;
+	unsigned nr_timeouts;
+	ktime_t timeout;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_busy_poll_to;
+	bool napi_prefer_busy_poll;
+#endif
+};
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+	struct io_ring_ctx *ctx = iowq->ctx;
+	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
+
+	/*
+	 * Wake up if we have enough events, or if a timeout occurred since we
+	 * started waiting. For timeouts, we always want to return to userspace,
+	 * regardless of event count.
+	 */
+	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
 bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
 void io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
@@ -56,6 +83,8 @@ void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
 void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts);
 void io_req_task_queue_fail(struct io_kiocb *req, int ret);
 void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts);
+struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *count, unsigned int max_entries);
+struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
 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,
@@ -207,7 +236,7 @@ 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)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_unlock(&ctx->uring_lock);
 }
 
@@ -220,7 +249,7 @@ static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
 	 * 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)
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		mutex_lock(&ctx->uring_lock);
 	lockdep_assert_held(&ctx->uring_lock);
 }
@@ -274,6 +303,8 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 
 static inline int io_run_task_work(void)
 {
+	bool ret = false;
+
 	/*
 	 * Always check-and-clear the task_work notification signal. With how
 	 * signaling works for task_work, we can find it set with nothing to
@@ -285,18 +316,26 @@ static inline int io_run_task_work(void)
 	 * PF_IO_WORKER never returns to userspace, so check here if we have
 	 * notify work that needs processing.
 	 */
-	if (current->flags & PF_IO_WORKER &&
-	    test_thread_flag(TIF_NOTIFY_RESUME)) {
-		__set_current_state(TASK_RUNNING);
-		resume_user_mode_work(NULL);
+	if (current->flags & PF_IO_WORKER) {
+		if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+			__set_current_state(TASK_RUNNING);
+			resume_user_mode_work(NULL);
+		}
+		if (current->io_uring) {
+			unsigned int count = 0;
+
+			tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+			if (count)
+				ret = true;
+		}
 	}
 	if (task_work_pending(current)) {
 		__set_current_state(TASK_RUNNING);
 		task_work_run();
-		return 1;
+		ret = true;
 	}
 
-	return 0;
+	return ret;
 }
 
 static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
@@ -398,4 +437,26 @@ static inline size_t uring_sqe_size(struct io_ring_ctx *ctx)
 		return 2 * sizeof(struct io_uring_sqe);
 	return sizeof(struct io_uring_sqe);
 }
+
+static inline bool io_file_can_poll(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_CAN_POLL)
+		return true;
+	if (file_can_poll(req->file)) {
+		req->flags |= REQ_F_CAN_POLL;
+		return true;
+	}
+	return false;
+}
+
+enum {
+	IO_CHECK_CQ_OVERFLOW_BIT,
+	IO_CHECK_CQ_DROPPED_BIT,
+};
+
+static inline bool io_has_work(struct io_ring_ctx *ctx)
+{
+	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
+	       !llist_empty(&ctx->work_llist);
+}
 #endif

io_uring/kbuf.c

@@ -81,15 +81,6 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	struct io_buffer_list *bl;
 	struct io_buffer *buf;
 
-	/*
-	 * For legacy provided buffer mode, don't recycle if we already did
-	 * IO to this buffer. For ring-mapped provided buffer mode, we should
-	 * increment ring->head to explicitly monopolize the buffer to avoid
-	 * multiple use.
-	 */
-	if (req->flags & REQ_F_PARTIAL_IO)
-		return false;
-
 	io_ring_submit_lock(ctx, issue_flags);
 
 	buf = req->kbuf;
@@ -102,10 +93,8 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 	return true;
 }
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 {
-	unsigned int cflags;
-
 	/*
 	 * We can add this buffer back to two lists:
 	 *
@@ -118,21 +107,17 @@ unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags)
 	 * We migrate buffers from the comp_list to the issue cache list
 	 * when we need one.
 	 */
-	if (req->flags & REQ_F_BUFFER_RING) {
-		/* no buffers to recycle for this case */
-		cflags = __io_put_kbuf_list(req, NULL);
-	} else if (issue_flags & IO_URING_F_UNLOCKED) {
+	if (issue_flags & IO_URING_F_UNLOCKED) {
 		struct io_ring_ctx *ctx = req->ctx;
 
 		spin_lock(&ctx->completion_lock);
-		cflags = __io_put_kbuf_list(req, &ctx->io_buffers_comp);
+		__io_put_kbuf_list(req, &ctx->io_buffers_comp);
 		spin_unlock(&ctx->completion_lock);
 	} else {
 		lockdep_assert_held(&req->ctx->uring_lock);
 
-		cflags = __io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
+		__io_put_kbuf_list(req, &req->ctx->io_buffers_cache);
 	}
-	return cflags;
 }
 
 static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
@@ -145,6 +130,8 @@ static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
 		list_del(&kbuf->list);
 		if (*len == 0 || *len > kbuf->len)
 			*len = kbuf->len;
+		if (list_empty(&bl->buf_list))
+			req->flags |= REQ_F_BL_EMPTY;
 		req->flags |= REQ_F_BUFFER_SELECTED;
 		req->kbuf = kbuf;
 		req->buf_index = kbuf->bid;
@@ -158,12 +145,16 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 					  unsigned int issue_flags)
 {
 	struct io_uring_buf_ring *br = bl->buf_ring;
+	__u16 tail, head = bl->head;
 	struct io_uring_buf *buf;
-	__u16 head = bl->head;
 
-	if (unlikely(smp_load_acquire(&br->tail) == head))
+	tail = smp_load_acquire(&br->tail);
+	if (unlikely(tail == head))
 		return NULL;
 
+	if (head + 1 == tail)
+		req->flags |= REQ_F_BL_EMPTY;
+
 	head &= bl->mask;
 	/* mmaped buffers are always contig */
 	if (bl->is_mmap || head < IO_BUFFER_LIST_BUF_PER_PAGE) {
@@ -180,7 +171,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
 
-	if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
+	if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) {
 		/*
 		 * If we came in unlocked, we have no choice but to consume the
 		 * buffer here, otherwise nothing ensures that the buffer won't

io_uring/kbuf.h

@@ -57,7 +57,7 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
 
 void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
 
-unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
+void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
 bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
 
@@ -73,21 +73,9 @@ static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
 	 * to monopolize the buffer.
 	 */
 	if (req->buf_list) {
-		if (req->flags & REQ_F_PARTIAL_IO) {
-			/*
-			 * If we end up here, then the io_uring_lock has
-			 * been kept held since we retrieved the buffer.
-			 * For the io-wq case, we already cleared
-			 * req->buf_list when the buffer was retrieved,
-			 * hence it cannot be set here for that case.
-			 */
-			req->buf_list->head++;
-			req->buf_list = NULL;
-		} else {
-			req->buf_index = req->buf_list->bgid;
-			req->flags &= ~REQ_F_BUFFER_RING;
-			return true;
-		}
+		req->buf_index = req->buf_list->bgid;
+		req->flags &= ~REQ_F_BUFFER_RING;
+		return true;
 	}
 	return false;
 }
@@ -101,6 +89,8 @@ static inline bool io_do_buffer_select(struct io_kiocb *req)
 
 static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 {
+	if (req->flags & REQ_F_BL_NO_RECYCLE)
+		return false;
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		return io_kbuf_recycle_legacy(req, issue_flags);
 	if (req->flags & REQ_F_BUFFER_RING)
@@ -108,41 +98,54 @@ static inline bool io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
 	return false;
 }
 
-static inline unsigned int __io_put_kbuf_list(struct io_kiocb *req,
-					      struct list_head *list)
+static inline void __io_put_kbuf_ring(struct io_kiocb *req)
 {
-	unsigned int ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->buf_list) {
+		req->buf_index = req->buf_list->bgid;
+		req->buf_list->head++;
+	}
+	req->flags &= ~REQ_F_BUFFER_RING;
+}
 
+static inline void __io_put_kbuf_list(struct io_kiocb *req,
+				      struct list_head *list)
+{
 	if (req->flags & REQ_F_BUFFER_RING) {
-		if (req->buf_list) {
-			req->buf_index = req->buf_list->bgid;
-			req->buf_list->head++;
-		}
-		req->flags &= ~REQ_F_BUFFER_RING;
+		__io_put_kbuf_ring(req);
 	} else {
 		req->buf_index = req->kbuf->bgid;
 		list_add(&req->kbuf->list, list);
 		req->flags &= ~REQ_F_BUFFER_SELECTED;
 	}
-
-	return ret;
 }
 
 static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
 {
+	unsigned int ret;
+
 	lockdep_assert_held(&req->ctx->completion_lock);
 
 	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
 		return 0;
-	return __io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	__io_put_kbuf_list(req, &req->ctx->io_buffers_comp);
+	return ret;
 }
 
 static inline unsigned int io_put_kbuf(struct io_kiocb *req,
 				       unsigned issue_flags)
 {
+	unsigned int ret;
 
-	if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
+	if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
 		return 0;
-	return __io_put_kbuf(req, issue_flags);
+
+	ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
+	if (req->flags & REQ_F_BUFFER_RING)
+		__io_put_kbuf_ring(req);
+	else
+		__io_put_kbuf(req, issue_flags);
+	return ret;
 }
 #endif

io_uring/napi.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include "io_uring.h"
+#include "napi.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+/* Timeout for cleanout of stale entries. */
+#define NAPI_TIMEOUT		(60 * SEC_CONVERSION)
+
+struct io_napi_entry {
+	unsigned int		napi_id;
+	struct list_head	list;
+
+	unsigned long		timeout;
+	struct hlist_node	node;
+
+	struct rcu_head		rcu;
+};
+
+static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
+					       unsigned int napi_id)
+{
+	struct io_napi_entry *e;
+
+	hlist_for_each_entry_rcu(e, hash_list, node) {
+		if (e->napi_id != napi_id)
+			continue;
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		return e;
+	}
+
+	return NULL;
+}
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+{
+	struct hlist_head *hash_list;
+	unsigned int napi_id;
+	struct sock *sk;
+	struct io_napi_entry *e;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+
+	/* Non-NAPI IDs can be rejected. */
+	if (napi_id < MIN_NAPI_ID)
+		return;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+
+	rcu_read_lock();
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (e) {
+		e->timeout = jiffies + NAPI_TIMEOUT;
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	e = kmalloc(sizeof(*e), GFP_NOWAIT);
+	if (!e)
+		return;
+
+	e->napi_id = napi_id;
+	e->timeout = jiffies + NAPI_TIMEOUT;
+
+	spin_lock(&ctx->napi_lock);
+	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
+		spin_unlock(&ctx->napi_lock);
+		kfree(e);
+		return;
+	}
+
+	hlist_add_tail_rcu(&e->node, hash_list);
+	list_add_tail(&e->list, &ctx->napi_list);
+	spin_unlock(&ctx->napi_lock);
+}
+
+static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		if (time_after(jiffies, e->timeout)) {
+			list_del(&e->list);
+			hash_del_rcu(&e->node);
+			kfree_rcu(e, rcu);
+		}
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
+{
+	if (is_stale)
+		__io_napi_remove_stale(ctx);
+}
+
+static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
+					     unsigned long bp_usec)
+{
+	if (bp_usec) {
+		unsigned long end_time = start_time + bp_usec;
+		unsigned long now = busy_loop_current_time();
+
+		return time_after(now, end_time);
+	}
+
+	return true;
+}
+
+static bool io_napi_busy_loop_should_end(void *data,
+					 unsigned long start_time)
+{
+	struct io_wait_queue *iowq = data;
+
+	if (signal_pending(current))
+		return true;
+	if (io_should_wake(iowq) || io_has_work(iowq->ctx))
+		return true;
+	if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to))
+		return true;
+
+	return false;
+}
+
+static bool __io_napi_do_busy_loop(struct io_ring_ctx *ctx,
+				   void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool (*loop_end)(void *, unsigned long) = NULL;
+	bool is_stale = false;
+
+	if (loop_end_arg)
+		loop_end = io_napi_busy_loop_should_end;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list) {
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+
+		if (time_after(jiffies, e->timeout))
+			is_stale = true;
+	}
+
+	return is_stale;
+}
+
+static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
+				       struct io_wait_queue *iowq)
+{
+	unsigned long start_time = busy_loop_current_time();
+	void *loop_end_arg = NULL;
+	bool is_stale = false;
+
+	/* Singular lists use a different napi loop end check function and are
+	 * only executed once.
+	 */
+	if (list_is_singular(&ctx->napi_list))
+		loop_end_arg = iowq;
+
+	rcu_read_lock();
+	do {
+		is_stale = __io_napi_do_busy_loop(ctx, loop_end_arg);
+	} while (!io_napi_busy_loop_should_end(iowq, start_time) && !loop_end_arg);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+}
+
+/*
+ * io_napi_init() - Init napi settings
+ * @ctx: pointer to io-uring context structure
+ *
+ * Init napi settings in the io-uring context.
+ */
+void io_napi_init(struct io_ring_ctx *ctx)
+{
+	INIT_LIST_HEAD(&ctx->napi_list);
+	spin_lock_init(&ctx->napi_lock);
+	ctx->napi_prefer_busy_poll = false;
+	ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
+}
+
+/*
+ * io_napi_free() - Deallocate napi
+ * @ctx: pointer to io-uring context structure
+ *
+ * Free the napi list and the hash table in the io-uring context.
+ */
+void io_napi_free(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+	LIST_HEAD(napi_list);
+	unsigned int i;
+
+	spin_lock(&ctx->napi_lock);
+	hash_for_each(ctx->napi_ht, i, e, node) {
+		hash_del_rcu(&e->node);
+		kfree_rcu(e, rcu);
+	}
+	spin_unlock(&ctx->napi_lock);
+}
+
+/*
+ * io_napi_register() - Register napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Register napi in the io-uring context.
+ */
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+	struct io_uring_napi napi;
+
+	if (copy_from_user(&napi, arg, sizeof(napi)))
+		return -EFAULT;
+	if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+		return -EINVAL;
+
+	if (copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
+	WRITE_ONCE(ctx->napi_enabled, true);
+	return 0;
+}
+
+/*
+ * io_napi_unregister() - Unregister napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Unregister napi. If arg has been specified copy the busy poll timeout and
+ * prefer busy poll setting to the passed in structure.
+ */
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ctx->napi_busy_poll_to,
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+
+	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_busy_poll_to, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+	WRITE_ONCE(ctx->napi_enabled, false);
+	return 0;
+}
+
+/*
+ * __io_napi_adjust_timeout() - Add napi id to the busy poll list
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ * @ts: pointer to timespec or NULL
+ *
+ * Adjust the busy loop timeout according to timespec and busy poll timeout.
+ */
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+			      struct timespec64 *ts)
+{
+	unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
+
+	if (ts) {
+		struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
+
+		if (timespec64_compare(ts, &poll_to_ts) > 0) {
+			*ts = timespec64_sub(*ts, poll_to_ts);
+		} else {
+			u64 to = timespec64_to_ns(ts);
+
+			do_div(to, 1000);
+			ts->tv_sec = 0;
+			ts->tv_nsec = 0;
+		}
+	}
+
+	iowq->napi_busy_poll_to = poll_to;
+}
+
+/*
+ * __io_napi_busy_loop() - execute busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ *
+ * Execute the busy poll loop and merge the spliced off list.
+ */
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
+{
+	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled)
+		io_napi_blocking_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	LIST_HEAD(napi_list);
+	bool is_stale = false;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return 0;
+	if (list_empty_careful(&ctx->napi_list))
+		return 0;
+
+	rcu_read_lock();
+	is_stale = __io_napi_do_busy_loop(ctx, NULL);
+	rcu_read_unlock();
+
+	io_napi_remove_stale(ctx, is_stale);
+	return 1;
+}
+
+#endif

io_uring/napi.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef IOU_NAPI_H
+#define IOU_NAPI_H
+
+#include <linux/kernel.h>
+#include <linux/io_uring.h>
+#include <net/busy_poll.h>
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+void io_napi_init(struct io_ring_ctx *ctx);
+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);
+
+void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock);
+
+void __io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+		struct io_wait_queue *iowq, struct timespec64 *ts);
+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);
+
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return !list_empty(&ctx->napi_list);
+}
+
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_adjust_timeout(ctx, iowq, ts);
+}
+
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+	if (!io_napi(ctx))
+		return;
+	__io_napi_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_add() - Add napi id to the busy poll list
+ * @req: pointer to io_kiocb request
+ *
+ * Add the napi id of the socket to the napi busy poll list and hash table.
+ */
+static inline void io_napi_add(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct socket *sock;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_to))
+		return;
+
+	sock = sock_from_file(req->file);
+	if (sock)
+		__io_napi_add(ctx, sock);
+}
+
+#else
+
+static inline void io_napi_init(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_napi_free(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool io_napi(struct io_ring_ctx *ctx)
+{
+	return false;
+}
+static inline void io_napi_add(struct io_kiocb *req)
+{
+}
+static inline void io_napi_adjust_timeout(struct io_ring_ctx *ctx,
+					  struct io_wait_queue *iowq,
+					  struct timespec64 *ts)
+{
+}
+static inline void io_napi_busy_loop(struct io_ring_ctx *ctx,
+				     struct io_wait_queue *iowq)
+{
+}
+static inline int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	return 0;
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+#endif

io_uring/opdef.c

@@ -35,6 +35,7 @@
 #include "rw.h"
 #include "waitid.h"
 #include "futex.h"
+#include "truncate.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -474,6 +475,12 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_install_fixed_fd_prep,
 		.issue			= io_install_fixed_fd,
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.prep			= io_ftruncate_prep,
+		.issue			= io_ftruncate,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -712,6 +719,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FIXED_FD_INSTALL] = {
 		.name			= "FIXED_FD_INSTALL",
 	},
+	[IORING_OP_FTRUNCATE] = {
+		.name			= "FTRUNCATE",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)

io_uring/poll.c

@@ -15,6 +15,7 @@
 
 #include "io_uring.h"
 #include "refs.h"
+#include "napi.h"
 #include "opdef.h"
 #include "kbuf.h"
 #include "poll.h"
@@ -343,8 +344,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 		 * Release all references, retry if someone tried to restart
 		 * task_work while we were executing it.
 		 */
-	} while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) &
-					IO_POLL_REF_MASK);
+		v &= IO_POLL_REF_MASK;
+	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
 
 	return IOU_POLL_NO_ACTION;
 }
@@ -539,14 +540,6 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->wait.private = (void *) wqe_private;
 
 	if (poll->events & EPOLLEXCLUSIVE) {
-		/*
-		 * Exclusive waits may only wake a limited amount of entries
-		 * rather than all of them, this may interfere with lazy
-		 * wake if someone does wait(events > 1). Ensure we don't do
-		 * lazy wake for those, as we need to process each one as they
-		 * come in.
-		 */
-		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
 	} else {
 		add_wait_queue(head, &poll->wait);
@@ -588,10 +581,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 				 struct io_poll_table *ipt, __poll_t mask,
 				 unsigned issue_flags)
 {
-	struct io_ring_ctx *ctx = req->ctx;
-
 	INIT_HLIST_NODE(&req->hash_node);
-	req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
 	io_init_poll_iocb(poll, mask);
 	poll->file = req->file;
 	req->apoll_events = poll->events;
@@ -618,6 +608,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		req->flags &= ~REQ_F_HASH_LOCKED;
 
+
+	/*
+	 * Exclusive waits may only wake a limited amount of entries
+	 * rather than all of them, this may interfere with lazy
+	 * wake if someone does wait(events > 1). Ensure we don't do
+	 * lazy wake for those, as we need to process each one as they
+	 * come in.
+	 */
+	if (poll->events & EPOLLEXCLUSIVE)
+		req->flags |= REQ_F_POLL_NO_LAZY;
+
 	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
 
 	if (unlikely(ipt->error || !ipt->nr_entries)) {
@@ -652,6 +653,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
 		__io_poll_execute(req, mask);
 		return 0;
 	}
+	io_napi_add(req);
 
 	if (ipt->owning) {
 		/*
@@ -727,7 +729,7 @@ int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
 
 	if (!def->pollin && !def->pollout)
 		return IO_APOLL_ABORTED;
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return IO_APOLL_ABORTED;
 	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
 		mask |= EPOLLONESHOT;
@@ -818,9 +820,8 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
 		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
 			continue;
 		if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
-			if (cd->seq == req->work.cancel_seq)
+			if (io_cancel_match_sequence(req, cd->seq))
 				continue;
-			req->work.cancel_seq = cd->seq;
 		}
 		*out_bucket = hb;
 		return req;

io_uring/register.c

@@ -26,6 +26,7 @@
 #include "register.h"
 #include "cancel.h"
 #include "kbuf.h"
+#include "napi.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -550,6 +551,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_pbuf_status(ctx, arg);
 		break;
+	case IORING_REGISTER_NAPI:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_napi(ctx, arg);
+		break;
+	case IORING_UNREGISTER_NAPI:
+		ret = -EINVAL;
+		if (nr_args != 1)
+			break;
+		ret = io_unregister_napi(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

io_uring/rsrc.h

@@ -2,8 +2,6 @@
 #ifndef IOU_RSRC_H
 #define IOU_RSRC_H
 
-#include <net/af_unix.h>
-
 #include "alloc_cache.h"
 
 #define IO_NODE_ALLOC_CACHE_MAX 32

io_uring/rw.c

@@ -11,6 +11,7 @@
 #include <linux/nospec.h>
 #include <linux/compat.h>
 #include <linux/io_uring/cmd.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include <uapi/linux/io_uring.h>
 
@@ -274,7 +275,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
 			 * current cycle.
 			 */
 			io_req_io_end(req);
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return true;
 		}
 		req_set_fail(req);
@@ -341,7 +342,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 		io_req_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
 		if (res == -EAGAIN && io_rw_should_reissue(req)) {
-			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
+			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
 			return;
 		}
 		req->cqe.res = res;
@@ -682,7 +683,7 @@ static bool io_rw_should_retry(struct io_kiocb *req)
 	 * just use poll if we can, and don't attempt if the fs doesn't
 	 * support callback based unlocks
 	 */
-	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+	if (io_file_can_poll(req) || !(req->file->f_mode & FMODE_BUF_RASYNC))
 		return false;
 
 	wait->wait.func = io_async_buf_func;
@@ -721,7 +722,7 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
 	struct file *file = req->file;
 	int ret;
 
-	if (unlikely(!file || !(file->f_mode & mode)))
+	if (unlikely(!(file->f_mode & mode)))
 		return -EBADF;
 
 	if (!(req->flags & REQ_F_FIXED_FILE))
@@ -831,7 +832,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 		 * If we can poll, just do that. For a vectored read, we'll
 		 * need to copy state first.
 		 */
-		if (file_can_poll(req->file) && !io_issue_defs[req->opcode].vectored)
+		if (io_file_can_poll(req) && !io_issue_defs[req->opcode].vectored)
 			return -EAGAIN;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
@@ -930,7 +931,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	/*
 	 * Multishot MUST be used on a pollable file
 	 */
-	if (!file_can_poll(req->file))
+	if (!io_file_can_poll(req))
 		return -EBADFD;
 
 	ret = __io_read(req, issue_flags);

io_uring/sqpoll.c

@@ -15,9 +15,11 @@
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "napi.h"
 #include "sqpoll.h"
 
 #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+#define IORING_TW_CAP_ENTRIES_VALUE	8
 
 enum {
 	IO_SQ_THREAD_SHOULD_STOP = 0,
@@ -193,6 +195,9 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
+		if (io_napi(ctx))
+			ret += io_napi_sqpoll_busy_poll(ctx);
+
 		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
 			wake_up(&ctx->sqo_sq_wait);
 		if (creds)
@@ -219,10 +224,52 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd)
 	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 }
 
+/*
+ * Run task_work, processing the retry_list first. The retry_list holds
+ * entries that we passed on in the previous run, if we had more task_work
+ * than we were asked to process. Newly queued task_work isn't run until the
+ * retry list has been fully processed.
+ */
+static unsigned int io_sq_tw(struct llist_node **retry_list, int max_entries)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	unsigned int count = 0;
+
+	if (*retry_list) {
+		*retry_list = io_handle_tw_list(*retry_list, &count, max_entries);
+		if (count >= max_entries)
+			return count;
+		max_entries -= count;
+	}
+
+	*retry_list = tctx_task_work_run(tctx, max_entries, &count);
+	return count;
+}
+
+static bool io_sq_tw_pending(struct llist_node *retry_list)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	return retry_list || !llist_empty(&tctx->task_list);
+}
+
+static void io_sq_update_worktime(struct io_sq_data *sqd, struct rusage *start)
+{
+	struct rusage end;
+
+	getrusage(current, RUSAGE_SELF, &end);
+	end.ru_stime.tv_sec -= start->ru_stime.tv_sec;
+	end.ru_stime.tv_usec -= start->ru_stime.tv_usec;
+
+	sqd->work_time += end.ru_stime.tv_usec + end.ru_stime.tv_sec * 1000000;
+}
+
 static int io_sq_thread(void *data)
 {
+	struct llist_node *retry_list = NULL;
 	struct io_sq_data *sqd = data;
 	struct io_ring_ctx *ctx;
+	struct rusage start;
 	unsigned long timeout = 0;
 	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
@@ -251,18 +298,21 @@ static int io_sq_thread(void *data)
 		}
 
 		cap_entries = !list_is_singular(&sqd->ctx_list);
+		getrusage(current, RUSAGE_SELF, &start);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
 			int ret = __io_sq_thread(ctx, cap_entries);
 
 			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
 				sqt_spin = true;
 		}
-		if (io_run_task_work())
+		if (io_sq_tw(&retry_list, IORING_TW_CAP_ENTRIES_VALUE))
 			sqt_spin = true;
 
 		if (sqt_spin || !time_after(jiffies, timeout)) {
-			if (sqt_spin)
+			if (sqt_spin) {
+				io_sq_update_worktime(sqd, &start);
 				timeout = jiffies + sqd->sq_thread_idle;
+			}
 			if (unlikely(need_resched())) {
 				mutex_unlock(&sqd->lock);
 				cond_resched();
@@ -273,7 +323,7 @@ static int io_sq_thread(void *data)
 		}
 
 		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
-		if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
+		if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending(retry_list)) {
 			bool needs_sched = true;
 
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -312,6 +362,9 @@ static int io_sq_thread(void *data)
 		timeout = jiffies + sqd->sq_thread_idle;
 	}
 
+	if (retry_list)
+		io_sq_tw(&retry_list, UINT_MAX);
+
 	io_uring_cancel_generic(true, sqd);
 	sqd->thread = NULL;
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)

io_uring/sqpoll.h

@@ -16,6 +16,7 @@ struct io_sq_data {
 	pid_t			task_pid;
 	pid_t			task_tgid;
 
+	u64			work_time;
 	unsigned long		state;
 	struct completion	exited;
 };

io_uring/truncate.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../fs/internal.h"
+
+#include "io_uring.h"
+#include "truncate.h"
+
+struct io_ftrunc {
+	struct file			*file;
+	loff_t				len;
+};
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+
+	if (sqe->rw_flags || sqe->addr || sqe->len || sqe->buf_index ||
+	    sqe->splice_fd_in || sqe->addr3)
+		return -EINVAL;
+
+	ft->len = READ_ONCE(sqe->off);
+
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ftrunc *ft = io_kiocb_to_cmd(req, struct io_ftrunc);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_ftruncate(req->file, ft->len, 1);
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}

io_uring/truncate.h

+// SPDX-License-Identifier: GPL-2.0
+
+int io_ftruncate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_ftruncate(struct io_kiocb *req, unsigned int issue_flags);

io_uring/uring_cmd.c

@@ -5,6 +5,7 @@
 #include <linux/io_uring/cmd.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
+#include <net/sock.h>
 
 #include <uapi/linux/io_uring.h>
 #include <asm/ioctls.h>

io_uring/xattr.c

@@ -112,7 +112,7 @@ int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-	ret = do_getxattr(mnt_idmap(req->file->f_path.mnt),
+	ret = do_getxattr(file_mnt_idmap(req->file),
 			req->file->f_path.dentry,
 			&ix->ctx);
 

net/core/dev.c

@@ -6177,8 +6177,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
-			   u16 budget)
+enum {
+	NAPI_F_PREFER_BUSY_POLL	= 1,
+	NAPI_F_END_ON_RESCHED	= 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+			   unsigned flags, u16 budget)
 {
 	bool skip_schedule = false;
 	unsigned long timeout;
@@ -6198,7 +6203,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 
 	local_bh_disable();
 
-	if (prefer_busy_poll) {
+	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
 		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
 		if (napi->defer_hard_irqs_count && timeout) {
@@ -6222,23 +6227,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
 	local_bh_enable();
 }
 
-void napi_busy_loop(unsigned int napi_id,
-		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+		      bool (*loop_end)(void *, unsigned long),
+		      void *loop_end_arg, unsigned flags, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 restart:
 	napi_poll = NULL;
 
-	rcu_read_lock();
-
 	napi = napi_by_id(napi_id);
 	if (!napi)
-		goto out;
+		return;
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_disable();
@@ -6254,14 +6259,14 @@ void napi_busy_loop(unsigned int napi_id,
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
 				   NAPIF_STATE_IN_BUSY_POLL)) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
 					  NAPIF_STATE_SCHED) != val) {
-				if (prefer_busy_poll)
+				if (flags & NAPI_F_PREFER_BUSY_POLL)
 					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
 			}
@@ -6281,12 +6286,15 @@ void napi_busy_loop(unsigned int napi_id,
 			break;
 
 		if (unlikely(need_resched())) {
+			if (flags & NAPI_F_END_ON_RESCHED)
+				break;
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+				busy_poll_stop(napi, have_poll_lock, flags, budget);
 			if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 				preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
+			rcu_read_lock();
 			if (loop_end(loop_end_arg, start_time))
 				return;
 			goto restart;
@@ -6294,10 +6302,31 @@ void napi_busy_loop(unsigned int napi_id,
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+		busy_poll_stop(napi, have_poll_lock, flags, budget);
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+			bool (*loop_end)(void *, unsigned long),
+			void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = NAPI_F_END_ON_RESCHED;
+
+	if (prefer_busy_poll)
+		flags |= NAPI_F_PREFER_BUSY_POLL;
+
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+		    bool (*loop_end)(void *, unsigned long),
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+	unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+	rcu_read_lock();
+	__napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(napi_busy_loop);