Merge branch 'for-5.19/io_uring-socket' into for-5.19/io_uring-net

* for-5.19/io_uring-socket: (73 commits)
  io_uring: use the text representation of ops in trace
  io_uring: rename op -> opcode
  io_uring: add io_uring_get_opcode
  io_uring: add type to op enum
  io_uring: add socket(2) support
  net: add __sys_socket_file()
  io_uring: fix trace for reduced sqe padding
  io_uring: add fgetxattr and getxattr support
  io_uring: add fsetxattr and setxattr support
  fs: split off do_getxattr from getxattr
  fs: split off setxattr_copy and do_setxattr function from setxattr
  io_uring: return an error when cqe is dropped
  io_uring: use constants for cq_overflow bitfield
  io_uring: rework io_uring_enter to simplify return value
  io_uring: trace cqe overflows
  io_uring: add trace support for CQE overflow
  io_uring: allow re-poll if we made progress
  io_uring: support MSG_WAITALL for IORING_OP_SEND(MSG)
  io_uring: add support for IORING_ASYNC_CANCEL_ANY
  io_uring: allow IORING_OP_ASYNC_CANCEL with 'fd' key
  ...

fs/internal.h

@@ -191,3 +191,32 @@ long splice_file_to_pipe(struct file *in,
 			 struct pipe_inode_info *opipe,
 			 loff_t *offset,
 			 size_t len, unsigned int flags);
+
+/*
+ * fs/xattr.c:
+ */
+struct xattr_name {
+	char name[XATTR_NAME_MAX + 1];
+};
+
+struct xattr_ctx {
+	/* Value of attribute */
+	union {
+		const void __user *cvalue;
+		void __user *value;
+	};
+	void *kvalue;
+	size_t size;
+	/* Attribute name */
+	struct xattr_name *kname;
+	unsigned int flags;
+};
+
+
+ssize_t do_getxattr(struct user_namespace *mnt_userns,
+		    struct dentry *d,
+		    struct xattr_ctx *ctx);
+
+int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
+int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		struct xattr_ctx *ctx);

fs/io-wq.h

@@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
 struct io_wq_work {
 	struct io_wq_work_node list;
 	unsigned flags;
+	int cancel_seq;
 };
 
 static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)

fs/xattr.c

@@ -25,6 +25,8 @@
 
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 static const char *
 strcmp_prefix(const char *a, const char *a_prefix)
 {
@@ -539,44 +541,76 @@ EXPORT_SYMBOL_GPL(vfs_removexattr);
 /*
  * Extended attribute SET operations
  */
-static long
+
-setxattr(struct user_namespace *mnt_userns, struct dentry *d,
+int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
-	 const char __user *name, const void __user *value, size_t size,
-	 int flags)
 {
 	int error;
-	void *kvalue = NULL;
-	char kname[XATTR_NAME_MAX + 1];
 
-	if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
+	if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
 		return -EINVAL;
 
-	error = strncpy_from_user(kname, name, sizeof(kname));
+	error = strncpy_from_user(ctx->kname->name, name,
-	if (error == 0 || error == sizeof(kname))
+				sizeof(ctx->kname->name));
-		error = -ERANGE;
+	if (error == 0 || error == sizeof(ctx->kname->name))
+		return  -ERANGE;
 	if (error < 0)
 		return error;
 
-	if (size) {
+	error = 0;
-		if (size > XATTR_SIZE_MAX)
+	if (ctx->size) {
+		if (ctx->size > XATTR_SIZE_MAX)
 			return -E2BIG;
-		kvalue = kvmalloc(size, GFP_KERNEL);
+
-		if (!kvalue)
+		ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size);
-			return -ENOMEM;
+		if (IS_ERR(ctx->kvalue)) {
-		if (copy_from_user(kvalue, value, size)) {
+			error = PTR_ERR(ctx->kvalue);
-			error = -EFAULT;
+			ctx->kvalue = NULL;
-			goto out;
 		}
-		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
-		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
-			posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d),
-						      kvalue, size);
 	}
 
-	error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags);
+	return error;
-out:
+}
-	kvfree(kvalue);
 
+static void setxattr_convert(struct user_namespace *mnt_userns,
+			     struct dentry *d, struct xattr_ctx *ctx)
+{
+	if (ctx->size &&
+		((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
+		(strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)))
+		posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d),
+						ctx->kvalue, ctx->size);
+}
+
+int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+		struct xattr_ctx *ctx)
+{
+	setxattr_convert(mnt_userns, dentry, ctx);
+	return vfs_setxattr(mnt_userns, dentry, ctx->kname->name,
+			ctx->kvalue, ctx->size, ctx->flags);
+}
+
+static long
+setxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	const char __user *name, const void __user *value, size_t size,
+	int flags)
+{
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.cvalue   = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = flags,
+	};
+	int error;
+
+	error = setxattr_copy(name, &ctx);
+	if (error)
+		return error;
+
+	error = do_setxattr(mnt_userns, d, &ctx);
+
+	kvfree(ctx.kvalue);
 	return error;
 }
 
@@ -642,44 +676,61 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 /*
  * Extended attribute GET operations
  */
-static ssize_t
+ssize_t
-getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
-	 const char __user *name, void __user *value, size_t size)
+	struct xattr_ctx *ctx)
 {
 	ssize_t error;
-	void *kvalue = NULL;
+	char *kname = ctx->kname->name;
-	char kname[XATTR_NAME_MAX + 1];
 
-	error = strncpy_from_user(kname, name, sizeof(kname));
+	if (ctx->size) {
-	if (error == 0 || error == sizeof(kname))
+		if (ctx->size > XATTR_SIZE_MAX)
-		error = -ERANGE;
+			ctx->size = XATTR_SIZE_MAX;
-	if (error < 0)
+		ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
-		return error;
+		if (!ctx->kvalue)
-
-	if (size) {
-		if (size > XATTR_SIZE_MAX)
-			size = XATTR_SIZE_MAX;
-		kvalue = kvzalloc(size, GFP_KERNEL);
-		if (!kvalue)
 			return -ENOMEM;
 	}
 
-	error = vfs_getxattr(mnt_userns, d, kname, kvalue, size);
+	error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size);
 	if (error > 0) {
 		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
 		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
 			posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d),
-						    kvalue, error);
+							ctx->kvalue, error);
-		if (size && copy_to_user(value, kvalue, error))
+		if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error))
 			error = -EFAULT;
-	} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
+	} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
 		/* The file system tried to returned a value bigger
 		   than XATTR_SIZE_MAX bytes. Not possible. */
 		error = -E2BIG;
 	}
 
-	kvfree(kvalue);
+	return error;
+}
 
+static ssize_t
+getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	 const char __user *name, void __user *value, size_t size)
+{
+	ssize_t error;
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.value    = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = 0,
+	};
+
+	error = strncpy_from_user(kname.name, name, sizeof(kname.name));
+	if (error == 0 || error == sizeof(kname.name))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
+	error =  do_getxattr(mnt_userns, d, &ctx);
+
+	kvfree(ctx.kvalue);
 	return error;
 }
 

include/linux/io_uring.h

@@ -10,6 +10,7 @@ struct sock *io_uring_get_socket(struct file *file);
 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);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -42,6 +43,10 @@ static inline void io_uring_files_cancel(void)
 static inline void io_uring_free(struct task_struct *tsk)
 {
 }
+static inline const char *io_uring_get_opcode(u8 opcode)
+{
+	return "";
+}
 #endif
 
 #endif

include/linux/socket.h

@@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags,
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 			 int __user *upeer_addrlen, int flags);
 extern int __sys_socket(int family, int type, int protocol);
+extern struct file *__sys_socket_file(int family, int type, int protocol);
 extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
 extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
 			      int addrlen, int file_flags);

include/trace/events/io_uring.h

@@ -7,6 +7,7 @@
 
 #include <linux/tracepoint.h>
 #include <uapi/linux/io_uring.h>
+#include <linux/io_uring.h>
 
 struct io_wq_work;
 
@@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work,
 		__entry->rw		= rw;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+		__entry->ctx, __entry->req, __entry->user_data,
+		io_uring_get_opcode(__entry->opcode),
 		__entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
 );
 
@@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer,
 		__entry->opcode	= opcode;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s",
-		__entry->ctx, __entry->req, __entry->data, __entry->opcode)
+		__entry->ctx, __entry->req, __entry->data,
+		io_uring_get_opcode(__entry->opcode))
 );
 
 /**
@@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link,
 		__entry->link		= link;
 	),
 
-	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p",
+	TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+		__entry->ctx, __entry->req, __entry->user_data,
-		__entry->link)
+		io_uring_get_opcode(__entry->opcode), __entry->link)
 );
 
 /**
@@ -389,9 +392,9 @@ TRACE_EVENT(io_uring_submit_sqe,
 		__entry->sq_thread	= sq_thread;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, "
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
 		  "non block %d, sq_thread %d", __entry->ctx, __entry->req,
-		  __entry->user_data, __entry->opcode,
+		  __entry->user_data, io_uring_get_opcode(__entry->opcode),
 		  __entry->flags, __entry->force_nonblock, __entry->sq_thread)
 );
 
@@ -433,8 +436,9 @@ TRACE_EVENT(io_uring_poll_arm,
 		__entry->events		= events;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x",
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x",
-		  __entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+		  __entry->ctx, __entry->req, __entry->user_data,
+		  io_uring_get_opcode(__entry->opcode),
 		  __entry->mask, __entry->events)
 );
 
@@ -470,8 +474,9 @@ TRACE_EVENT(io_uring_task_add,
 		__entry->mask		= mask;
 	),
 
-	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x",
+	TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x",
-		__entry->ctx, __entry->req, __entry->user_data, __entry->opcode,
+		__entry->ctx, __entry->req, __entry->user_data,
+		io_uring_get_opcode(__entry->opcode),
 		__entry->mask)
 );
 
@@ -506,7 +511,7 @@ TRACE_EVENT(io_uring_req_failed,
 		__field( u16,			personality	)
 		__field( u32,			file_index	)
 		__field( u64,			pad1		)
-		__field( u64,			pad2		)
+		__field( u64,			addr3		)
 		__field( int,			error		)
 	),
 
@@ -525,22 +530,64 @@ TRACE_EVENT(io_uring_req_failed,
 		__entry->personality	= sqe->personality;
 		__entry->file_index	= sqe->file_index;
 		__entry->pad1		= sqe->__pad2[0];
-		__entry->pad2		= sqe->__pad2[1];
+		__entry->addr3		= sqe->addr3;
 		__entry->error		= error;
 	),
 
 	TP_printk("ring %p, req %p, user_data 0x%llx, "
-		"op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, "
+		  "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, "
 		  "len=%u, rw_flags=0x%x, buf_index=%d, "
-		  "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d",
+		  "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, "
+		  "error=%d",
 		  __entry->ctx, __entry->req, __entry->user_data,
-		  __entry->opcode, __entry->flags, __entry->ioprio,
+		  io_uring_get_opcode(__entry->opcode),
+		  __entry->flags, __entry->ioprio,
 		  (unsigned long long)__entry->off,
 		  (unsigned long long) __entry->addr, __entry->len,
 		  __entry->op_flags,
 		  __entry->buf_index, __entry->personality, __entry->file_index,
 		  (unsigned long long) __entry->pad1,
-		  (unsigned long long) __entry->pad2, __entry->error)
+		  (unsigned long long) __entry->addr3, __entry->error)
+);
+
+
+/*
+ * io_uring_cqe_overflow - a CQE overflowed
+ *
+ * @ctx:		pointer to a ring context structure
+ * @user_data:		user data associated with the request
+ * @res:		CQE result
+ * @cflags:		CQE flags
+ * @ocqe:		pointer to the overflow cqe (if available)
+ *
+ */
+TRACE_EVENT(io_uring_cqe_overflow,
+
+	TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags,
+		 void *ocqe),
+
+	TP_ARGS(ctx, user_data, res, cflags, ocqe),
+
+	TP_STRUCT__entry (
+		__field(  void *,		ctx		)
+		__field(  unsigned long long,	user_data	)
+		__field(  s32,			res		)
+		__field(  u32,			cflags		)
+		__field(  void *,		ocqe		)
+	),
+
+	TP_fast_assign(
+		__entry->ctx		= ctx;
+		__entry->user_data	= user_data;
+		__entry->res		= res;
+		__entry->cflags		= cflags;
+		__entry->ocqe		= ocqe;
+	),
+
+	TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, "
+		  "overflow_cqe %p",
+		  __entry->ctx, __entry->user_data, __entry->res,
+		  __entry->cflags, __entry->ocqe)
 );
 
 #endif /* _TRACE_IO_URING_H */

include/uapi/linux/io_uring.h

@@ -45,6 +45,7 @@ struct io_uring_sqe {
 		__u32		rename_flags;
 		__u32		unlink_flags;
 		__u32		hardlink_flags;
+		__u32		xattr_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -60,7 +61,8 @@ struct io_uring_sqe {
 		__s32	splice_fd_in;
 		__u32	file_index;
 	};
-	__u64	__pad2[2];
+	__u64	addr3;
+	__u64	__pad2[1];
 };
 
 enum {
@@ -103,7 +105,7 @@ enum {
 #define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
 #define IORING_SETUP_SUBMIT_ALL	(1U << 7)	/* continue submit on error */
 
-enum {
+enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
 	IORING_OP_WRITEV,
@@ -145,6 +147,11 @@ enum {
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
 	IORING_OP_MSG_RING,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
+	IORING_OP_FGETXATTR,
+	IORING_OP_GETXATTR,
+	IORING_OP_SOCKET,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -187,6 +194,18 @@ enum {
 #define IORING_POLL_UPDATE_EVENTS	(1U << 1)
 #define IORING_POLL_UPDATE_USER_DATA	(1U << 2)
 
+/*
+ * ASYNC_CANCEL flags.
+ *
+ * IORING_ASYNC_CANCEL_ALL	Cancel all requests that match the given key
+ * IORING_ASYNC_CANCEL_FD	Key off 'fd' for cancelation rather than the
+ *				request 'user_data'
+ * IORING_ASYNC_CANCEL_ANY	Match any request
+ */
+#define IORING_ASYNC_CANCEL_ALL	(1U << 0)
+#define IORING_ASYNC_CANCEL_FD	(1U << 1)
+#define IORING_ASYNC_CANCEL_ANY	(1U << 2)
+
 /*
  * IO completion data structure (Completion Queue Entry)
  */

net/socket.c

@@ -504,7 +504,7 @@ static int sock_map_fd(struct socket *sock, int flags)
 struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
-		return file->private_data;	/* set in sock_map_fd */
+		return file->private_data;	/* set in sock_alloc_file */
 
 	return NULL;
 }
@@ -1538,11 +1538,10 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
 }
 EXPORT_SYMBOL(sock_create_kern);
 
-int __sys_socket(int family, int type, int protocol)
+static struct socket *__sys_socket_create(int family, int type, int protocol)
 {
-	int retval;
 	struct socket *sock;
-	int flags;
+	int retval;
 
 	/* Check the SOCK_* constants for consistency.  */
 	BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC);
@@ -1550,17 +1549,50 @@ int __sys_socket(int family, int type, int protocol)
 	BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK);
 	BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK);
 
-	flags = type & ~SOCK_TYPE_MASK;
+	if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
-	if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+		return ERR_PTR(-EINVAL);
-		return -EINVAL;
 	type &= SOCK_TYPE_MASK;
 
-	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
-		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
-
 	retval = sock_create(family, type, protocol, &sock);
 	if (retval < 0)
-		return retval;
+		return ERR_PTR(retval);
+
+	return sock;
+}
+
+struct file *__sys_socket_file(int family, int type, int protocol)
+{
+	struct socket *sock;
+	struct file *file;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return ERR_CAST(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
+
+	file = sock_alloc_file(sock, flags, NULL);
+	if (IS_ERR(file))
+		sock_release(sock);
+
+	return file;
+}
+
+int __sys_socket(int family, int type, int protocol)
+{
+	struct socket *sock;
+	int flags;
+
+	sock = __sys_socket_create(family, type, protocol);
+	if (IS_ERR(sock))
+		return PTR_ERR(sock);
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
+		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
 	return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
 }