1 files changed, 144 insertions, 67 deletions

diff --git a/fs/stat.c b/fs/stat.c
index 030008796479..ef50573c72a2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -5,6 +5,7 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
+#include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
@@ -22,24 +23,33 @@
 #include <asm/unistd.h>
 
 #include "internal.h"
+#include "mount.h"
 
 /**
  * generic_fillattr - Fill in the basic attributes from the inode struct
- * @inode: Inode to use as the source
- * @stat: Where to fill in the attributes
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ * @inode:	Inode to use as the source
+ * @stat:	Where to fill in the attributes
  *
  * Fill in the basic attributes in the kstat structure from data that's to be
  * found on the VFS inode structure.  This is the default if no getattr inode
  * operation is supplied.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before filling in the
+ * uid and gid filds. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
  */
-void generic_fillattr(struct inode *inode, struct kstat *stat)
+void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode,
+		      struct kstat *stat)
 {
 	stat->dev = inode->i_sb->s_dev;
 	stat->ino = inode->i_ino;
 	stat->mode = inode->i_mode;
 	stat->nlink = inode->i_nlink;
-	stat->uid = inode->i_uid;
-	stat->gid = inode->i_gid;
+	stat->uid = i_uid_into_mnt(mnt_userns, inode);
+	stat->gid = i_gid_into_mnt(mnt_userns, inode);
 	stat->rdev = inode->i_rdev;
 	stat->size = i_size_read(inode);
 	stat->atime = inode->i_atime;
@@ -51,11 +61,29 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 EXPORT_SYMBOL(generic_fillattr);
 
 /**
+ * generic_fill_statx_attr - Fill in the statx attributes from the inode flags
+ * @inode:	Inode to use as the source
+ * @stat:	Where to fill in the attribute flags
+ *
+ * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the
+ * inode that are published on i_flags and enforced by the VFS.
+ */
+void generic_fill_statx_attr(struct inode *inode, struct kstat *stat)
+{
+	if (inode->i_flags & S_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (inode->i_flags & S_APPEND)
+		stat->attributes |= STATX_ATTR_APPEND;
+	stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS;
+}
+EXPORT_SYMBOL(generic_fill_statx_attr);
+
+/**
  * vfs_getattr_nosec - getattr without security checks
  * @path: file to get attributes from
  * @stat: structure to return attributes in
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Get attributes without calling security_inode_getattr.
  *
@@ -66,24 +94,37 @@ EXPORT_SYMBOL(generic_fillattr);
 int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 		      u32 request_mask, unsigned int query_flags)
 {
+	struct user_namespace *mnt_userns;
 	struct inode *inode = d_backing_inode(path->dentry);
 
 	memset(stat, 0, sizeof(*stat));
 	stat->result_mask |= STATX_BASIC_STATS;
-	request_mask &= STATX_ALL;
-	query_flags &= KSTAT_QUERY_FLAGS;
+	query_flags &= AT_STATX_SYNC_TYPE;
 
 	/* allow the fs to override these if it really wants to */
-	if (IS_NOATIME(inode))
+	/* SB_NOATIME means filesystem supplies dummy atime value */
+	if (inode->i_sb->s_flags & SB_NOATIME)
 		stat->result_mask &= ~STATX_ATIME;
+
+	/*
+	 * Note: If you add another clause to set an attribute flag, please
+	 * update attributes_mask below.
+	 */
 	if (IS_AUTOMOUNT(inode))
 		stat->attributes |= STATX_ATTR_AUTOMOUNT;
 
+	if (IS_DAX(inode))
+		stat->attributes |= STATX_ATTR_DAX;
+
+	stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT |
+				  STATX_ATTR_DAX);
+
+	mnt_userns = mnt_user_ns(path->mnt);
 	if (inode->i_op->getattr)
-		return inode->i_op->getattr(path, stat, request_mask,
-					    query_flags);
+		return inode->i_op->getattr(mnt_userns, path, stat,
+					    request_mask, query_flags);
 
-	generic_fillattr(inode, stat);
+	generic_fillattr(mnt_userns, inode, stat);
 	return 0;
 }
 EXPORT_SYMBOL(vfs_getattr_nosec);
@@ -93,7 +134,7 @@ EXPORT_SYMBOL(vfs_getattr_nosec);
  * @path: The file of interest
  * @stat: Where to return the statistics
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Ask the filesystem for a file's attributes.  The caller must indicate in
  * request_mask and query_flags to indicate what they want.
@@ -122,51 +163,40 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
 EXPORT_SYMBOL(vfs_getattr);
 
 /**
- * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * vfs_fstat - Get the basic attributes by file descriptor
  * @fd: The file descriptor referring to the file of interest
  * @stat: The result structure to fill in.
- * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * This function is a wrapper around vfs_getattr().  The main difference is
  * that it uses a file descriptor to determine the file location.
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx_fd(unsigned int fd, struct kstat *stat,
-		 u32 request_mask, unsigned int query_flags)
+int vfs_fstat(int fd, struct kstat *stat)
 {
 	struct fd f;
-	int error = -EBADF;
-
-	if (query_flags & ~KSTAT_QUERY_FLAGS)
-		return -EINVAL;
+	int error;
 
 	f = fdget_raw(fd);
-	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat,
-				    request_mask, query_flags);
-		fdput(f);
-	}
+	if (!f.file)
+		return -EBADF;
+	error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0);
+	fdput(f);
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx_fd);
 
-inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags)
+int getname_statx_lookup_flags(int flags)
 {
-	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
-		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
-		return -EINVAL;
+	int lookup_flags = 0;
 
-	*lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
-	if (flags & AT_SYMLINK_NOFOLLOW)
-		*lookup_flags &= ~LOOKUP_FOLLOW;
-	if (flags & AT_NO_AUTOMOUNT)
-		*lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (!(flags & AT_SYMLINK_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+	if (!(flags & AT_NO_AUTOMOUNT))
+		lookup_flags |= LOOKUP_AUTOMOUNT;
 	if (flags & AT_EMPTY_PATH)
-		*lookup_flags |= LOOKUP_EMPTY;
+		lookup_flags |= LOOKUP_EMPTY;
 
-	return 0;
+	return lookup_flags;
 }
 
 /**
@@ -184,21 +214,39 @@ inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags)
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx(int dfd, const char __user *filename, int flags,
+static int vfs_statx(int dfd, struct filename *filename, int flags,
 	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
-	int error = -EINVAL;
-	unsigned lookup_flags;
+	unsigned int lookup_flags = getname_statx_lookup_flags(flags);
+	int error;
 
-	if (vfs_stat_set_lookup_flags(&lookup_flags, flags))
+	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
+		      AT_STATX_SYNC_TYPE))
 		return -EINVAL;
+
 retry:
-	error = user_path_at(dfd, filename, lookup_flags, &path);
+	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
 	if (error)
 		goto out;
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
+
+	stat->mnt_id = real_mount(path.mnt)->mnt_id;
+	stat->result_mask |= STATX_MNT_ID;
+
+	if (path.mnt->mnt_root == path.dentry)
+		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
+	stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
+
+	/* Handle STATX_DIOALIGN for block devices. */
+	if (request_mask & STATX_DIOALIGN) {
+		struct inode *inode = d_backing_inode(path.dentry);
+
+		if (S_ISBLK(inode->i_mode))
+			bdev_statx_dioalign(inode, stat);
+	}
+
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -207,8 +255,20 @@ retry:
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx);
 
+int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
+{
+	int ret;
+	int statx_flags = flags | AT_NO_AUTOMOUNT;
+	struct filename *name;
+
+	name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL);
+	ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
+	putname(name);
+
+	return ret;
+}
 
 #ifdef __ARCH_WANT_OLD_STAT
 
@@ -300,9 +360,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat
 #  define choose_32_64(a,b) b
 #endif
 
-#define valid_dev(x)  choose_32_64(old_valid_dev(x),true)
-#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x)
-
 #ifndef INIT_STRUCT_STAT_PADDING
 #  define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
 #endif
@@ -311,7 +368,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 {
 	struct stat tmp;
 
-	if (!valid_dev(stat->dev) || !valid_dev(stat->rdev))
+	if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
+		return -EOVERFLOW;
+	if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
 		return -EOVERFLOW;
 #if BITS_PER_LONG == 32
 	if (stat->size > MAX_NON_LFS)
@@ -319,7 +378,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 #endif
 
 	INIT_STRUCT_STAT_PADDING(tmp);
-	tmp.st_dev = encode_dev(stat->dev);
+	tmp.st_dev = new_encode_dev(stat->dev);
 	tmp.st_ino = stat->ino;
 	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
 		return -EOVERFLOW;
@@ -329,7 +388,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 		return -EOVERFLOW;
 	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
 	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
-	tmp.st_rdev = encode_dev(stat->rdev);
+	tmp.st_rdev = new_encode_dev(stat->rdev);
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;
 	tmp.st_mtime = stat->mtime.tv_sec;
@@ -533,7 +592,7 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
-noinline_for_stack int
+static noinline_for_stack int
 cp_statx(const struct kstat *stat, struct statx __user *buffer)
 {
 	struct statx tmp;
@@ -563,10 +622,31 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	tmp.stx_rdev_minor = MINOR(stat->rdev);
 	tmp.stx_dev_major = MAJOR(stat->dev);
 	tmp.stx_dev_minor = MINOR(stat->dev);
+	tmp.stx_mnt_id = stat->mnt_id;
+	tmp.stx_dio_mem_align = stat->dio_mem_align;
+	tmp.stx_dio_offset_align = stat->dio_offset_align;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }
 
+int do_statx(int dfd, struct filename *filename, unsigned int flags,
+	     unsigned int mask, struct statx __user *buffer)
+{
+	struct kstat stat;
+	int error;
+
+	if (mask & STATX__RESERVED)
+		return -EINVAL;
+	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+		return -EINVAL;
+
+	error = vfs_statx(dfd, filename, flags, &stat, mask);
+	if (error)
+		return error;
+
+	return cp_statx(&stat, buffer);
+}
+
 /**
  * sys_statx - System call to get enhanced stats
  * @dfd: Base directory to pathwalk from *or* fd to stat.
@@ -583,31 +663,28 @@ SYSCALL_DEFINE5(statx,
 		unsigned int, mask,
 		struct statx __user *, buffer)
 {
-	struct kstat stat;
-	int error;
+	int ret;
+	struct filename *name;
 
-	if (mask & STATX__RESERVED)
-		return -EINVAL;
-	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
-		return -EINVAL;
+	name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL);
+	ret = do_statx(dfd, name, flags, mask, buffer);
+	putname(name);
 
-	error = vfs_statx(dfd, filename, flags, &stat, mask);
-	if (error)
-		return error;
-
-	return cp_statx(&stat, buffer);
+	return ret;
 }
 
-#ifdef CONFIG_COMPAT
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT)
 static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
 {
 	struct compat_stat tmp;
 
-	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+	if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev))
+		return -EOVERFLOW;
+	if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev))
 		return -EOVERFLOW;
 
 	memset(&tmp, 0, sizeof(tmp));
-	tmp.st_dev = old_encode_dev(stat->dev);
+	tmp.st_dev = new_encode_dev(stat->dev);
 	tmp.st_ino = stat->ino;
 	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
 		return -EOVERFLOW;
@@ -617,7 +694,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
 		return -EOVERFLOW;
 	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
 	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
-	tmp.st_rdev = old_encode_dev(stat->rdev);
+	tmp.st_rdev = new_encode_dev(stat->rdev);
 	if ((u64) stat->size > MAX_NON_LFS)
 		return -EOVERFLOW;
 	tmp.st_size = stat->size;