Merge tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block

Pull io_uring xattr support from Jens Axboe:
 "Support for the xattr variants"

* tag 'for-5.19/io_uring-xattr-2022-05-22' of git://git.kernel.dk/linux-block:
  io_uring: cleanup error-handling around io_req_complete
  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

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/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,
-	 const char __user *name, const void __user *value, size_t size,
-	 int flags)
+
+int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
 {
 	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));
-	if (error == 0 || error == sizeof(kname))
-		error = -ERANGE;
+	error = strncpy_from_user(ctx->kname->name, name,
+				sizeof(ctx->kname->name));
+	if (error == 0 || error == sizeof(ctx->kname->name))
+		return  -ERANGE;
 	if (error < 0)
 		return error;
 
-	if (size) {
-		if (size > XATTR_SIZE_MAX)
+	error = 0;
+	if (ctx->size) {
+		if (ctx->size > XATTR_SIZE_MAX)
 			return -E2BIG;
-		kvalue = kvmalloc(size, GFP_KERNEL);
-		if (!kvalue)
-			return -ENOMEM;
-		if (copy_from_user(kvalue, value, size)) {
-			error = -EFAULT;
-			goto out;
+
+		ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size);
+		if (IS_ERR(ctx->kvalue)) {
+			error = PTR_ERR(ctx->kvalue);
+			ctx->kvalue = NULL;
 		}
-		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);
-out:
-	kvfree(kvalue);
+	return error;
+}
+
+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
-getxattr(struct user_namespace *mnt_userns, struct dentry *d,
-	 const char __user *name, void __user *value, size_t size)
+ssize_t
+do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
+	struct xattr_ctx *ctx)
 {
 	ssize_t error;
-	void *kvalue = NULL;
-	char kname[XATTR_NAME_MAX + 1];
-
-	error = strncpy_from_user(kname, name, sizeof(kname));
-	if (error == 0 || error == sizeof(kname))
-		error = -ERANGE;
-	if (error < 0)
-		return error;
+	char *kname = ctx->kname->name;
 
-	if (size) {
-		if (size > XATTR_SIZE_MAX)
-			size = XATTR_SIZE_MAX;
-		kvalue = kvzalloc(size, GFP_KERNEL);
-		if (!kvalue)
+	if (ctx->size) {
+		if (ctx->size > XATTR_SIZE_MAX)
+			ctx->size = XATTR_SIZE_MAX;
+		ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
+		if (!ctx->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);
-		if (size && copy_to_user(value, kvalue, error))
+							ctx->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/trace/events/io_uring.h

@@ -506,7 +506,7 @@ 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		)
 	),
 
@@ -525,14 +525,15 @@ 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, "
 		  "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,
 		  (unsigned long long)__entry->off,
@@ -540,7 +541,7 @@ TRACE_EVENT(io_uring_req_failed,
 		  __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)
 );
 
 

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];
 };
 
 /*
@@ -168,6 +170,10 @@ enum {
 	IORING_OP_SYMLINKAT,
 	IORING_OP_LINKAT,
 	IORING_OP_MSG_RING,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
+	IORING_OP_FGETXATTR,
+	IORING_OP_GETXATTR,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,