Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ca8c763..b7f7b31 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -20,18 +20,19 @@
#include "xfs_symlink.h"
#include "xfs_dir2.h"
#include "xfs_iomap.h"
+#include "xfs_error.h"
-#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/iversion.h>
+#include <linux/fiemap.h>
/*
- * Directories have different lock order w.r.t. mmap_sem compared to regular
+ * Directories have different lock order w.r.t. mmap_lock compared to regular
* files. This is due to readdir potentially triggering page faults on a user
* buffer inside filldir(), and this happens with the ilock on the directory
* held. For regular files, the lock order is the other way around - the
- * mmap_sem is taken during the page fault, and then we lock the ilock to do
+ * mmap_lock is taken during the page fault, and then we lock the ilock to do
* block mapping. Hence we need a different class for the directory ilock so
* that lockdep can tell them apart.
*/
@@ -49,8 +50,15 @@
int error = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
- error = xfs_attr_set(ip, xattr->name, xattr->value,
- xattr->value_len, ATTR_SECURE);
+ struct xfs_da_args args = {
+ .dp = ip,
+ .attr_filter = XFS_ATTR_SECURE,
+ .name = xattr->name,
+ .namelen = strlen(xattr->name),
+ .value = xattr->value,
+ .valuelen = xattr->value_len,
+ };
+ error = xfs_attr_set(&args);
if (error < 0)
break;
}
@@ -229,7 +237,7 @@
umode_t mode,
bool flags)
{
- return xfs_vn_mknod(dir, dentry, mode, 0);
+ return xfs_generic_create(dir, dentry, mode, 0, false);
}
STATIC int
@@ -238,7 +246,7 @@
struct dentry *dentry,
umode_t mode)
{
- return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
+ return xfs_generic_create(dir, dentry, mode | S_IFDIR, 0, false);
}
STATIC struct dentry *
@@ -470,20 +478,57 @@
struct inode *inode,
struct delayed_call *done)
{
+ struct xfs_inode *ip = XFS_I(inode);
char *link;
- ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE);
+ ASSERT(ip->i_df.if_flags & XFS_IFINLINE);
/*
* The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
* if_data is junk.
*/
- link = XFS_I(inode)->i_df.if_u1.if_data;
- if (!link)
+ link = ip->i_df.if_u1.if_data;
+ if (XFS_IS_CORRUPT(ip->i_mount, !link))
return ERR_PTR(-EFSCORRUPTED);
return link;
}
+static uint32_t
+xfs_stat_blksize(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ /*
+ * If the file blocks are being allocated from a realtime volume, then
+ * always return the realtime extent size.
+ */
+ if (XFS_IS_REALTIME_INODE(ip))
+ return xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
+
+ /*
+ * Allow large block sizes to be reported to userspace programs if the
+ * "largeio" mount option is used.
+ *
+ * If compatibility mode is specified, simply return the basic unit of
+ * caching so that we don't get inefficient read/modify/write I/O from
+ * user apps. Otherwise....
+ *
+ * If the underlying volume is a stripe, then return the stripe width in
+ * bytes as the recommended I/O size. It is not a stripe and we've set a
+ * default buffered I/O size, return that, otherwise return the compat
+ * default.
+ */
+ if (mp->m_flags & XFS_MOUNT_LARGEIO) {
+ if (mp->m_swidth)
+ return mp->m_swidth << mp->m_sb.sb_blocklog;
+ if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
+ return 1U << mp->m_allocsize_log;
+ }
+
+ return PAGE_SIZE;
+}
+
STATIC int
xfs_vn_getattr(
const struct path *path,
@@ -513,11 +558,10 @@
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
- if (ip->i_d.di_version == 3) {
+ if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
- stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
- stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+ stat->btime = ip->i_d.di_crtime;
}
}
@@ -543,16 +587,7 @@
stat->rdev = inode->i_rdev;
break;
default:
- if (XFS_IS_REALTIME_INODE(ip)) {
- /*
- * If the file blocks are being allocated from a
- * realtime volume, then return the inode's realtime
- * extent size or the realtime volume's extent size.
- */
- stat->blksize =
- xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
- } else
- stat->blksize = xfs_preferred_iosize(mp);
+ stat->blksize = xfs_stat_blksize(ip);
stat->rdev = 0;
break;
}
@@ -662,9 +697,7 @@
*/
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
- error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid),
- xfs_kgid_to_gid(gid),
- xfs_get_projid(ip),
+ error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid,
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
@@ -706,12 +739,7 @@
if (error) /* out of quota */
goto out_cancel;
}
- }
- /*
- * Change file ownership. Must be the owner or privileged.
- */
- if (mask & (ATTR_UID|ATTR_GID)) {
/*
* CAP_FSETID overrides the following restrictions:
*
@@ -733,7 +761,6 @@
olddquot1 = xfs_qm_vop_chown(tp, ip,
&ip->i_udquot, udqp);
}
- ip->i_d.di_uid = xfs_kuid_to_uid(uid);
inode->i_uid = uid;
}
if (!gid_eq(igid, gid)) {
@@ -745,7 +772,6 @@
olddquot2 = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
- ip->i_d.di_gid = xfs_kgid_to_gid(gid);
inode->i_gid = gid;
}
}
@@ -847,7 +873,7 @@
/*
* Short circuit the truncate case for zero length files.
*/
- if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
+ if (newsize == 0 && oldsize == 0 && ip->i_df.if_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
@@ -883,7 +909,7 @@
if (newsize > oldsize) {
trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
error = iomap_zero_range(inode, oldsize, newsize - oldsize,
- &did_zeroing, &xfs_iomap_ops);
+ &did_zeroing, &xfs_buffered_write_iomap_ops);
} else {
/*
* iomap won't detect a dirty page over an unwritten block (or a
@@ -896,7 +922,7 @@
if (error)
return error;
error = iomap_truncate_page(inode, newsize, &did_zeroing,
- &xfs_iomap_ops);
+ &xfs_buffered_write_iomap_ops);
}
if (error)
@@ -1124,7 +1150,7 @@
&xfs_xattr_iomap_ops);
} else {
error = iomap_fiemap(inode, fieinfo, start, length,
- &xfs_iomap_ops);
+ &xfs_read_iomap_ops);
}
xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
@@ -1223,13 +1249,12 @@
{
struct xfs_mount *mp = ip->i_mount;
- /* Only supported on non-reflinked files. */
- if (!S_ISREG(VFS_I(ip)->i_mode) || xfs_is_reflink_inode(ip))
+ /* Only supported on regular files. */
+ if (!S_ISREG(VFS_I(ip)->i_mode))
return false;
- /* DAX mount option or DAX iflag must be set. */
- if (!(mp->m_flags & XFS_MOUNT_DAX) &&
- !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+ /* Only supported on non-reflinked files. */
+ if (xfs_is_reflink_inode(ip))
return false;
/* Block size must match page size */
@@ -1237,29 +1262,54 @@
return false;
/* Device has to support DAX too. */
- return xfs_find_daxdev_for_inode(VFS_I(ip)) != NULL;
+ return xfs_inode_buftarg(ip)->bt_daxdev != NULL;
}
-STATIC void
-xfs_diflags_to_iflags(
- struct inode *inode,
- struct xfs_inode *ip)
+static bool
+xfs_inode_should_enable_dax(
+ struct xfs_inode *ip)
{
- uint16_t flags = ip->i_d.di_flags;
+ if (!IS_ENABLED(CONFIG_FS_DAX))
+ return false;
+ if (ip->i_mount->m_flags & XFS_MOUNT_DAX_NEVER)
+ return false;
+ if (!xfs_inode_supports_dax(ip))
+ return false;
+ if (ip->i_mount->m_flags & XFS_MOUNT_DAX_ALWAYS)
+ return true;
+ if (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+ return true;
+ return false;
+}
- inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC |
- S_NOATIME | S_DAX);
+void
+xfs_diflags_to_iflags(
+ struct xfs_inode *ip,
+ bool init)
+{
+ struct inode *inode = VFS_I(ip);
+ unsigned int xflags = xfs_ip2xflags(ip);
+ unsigned int flags = 0;
- if (flags & XFS_DIFLAG_IMMUTABLE)
- inode->i_flags |= S_IMMUTABLE;
- if (flags & XFS_DIFLAG_APPEND)
- inode->i_flags |= S_APPEND;
- if (flags & XFS_DIFLAG_SYNC)
- inode->i_flags |= S_SYNC;
- if (flags & XFS_DIFLAG_NOATIME)
- inode->i_flags |= S_NOATIME;
- if (xfs_inode_supports_dax(ip))
- inode->i_flags |= S_DAX;
+ ASSERT(!(IS_DAX(inode) && init));
+
+ if (xflags & FS_XFLAG_IMMUTABLE)
+ flags |= S_IMMUTABLE;
+ if (xflags & FS_XFLAG_APPEND)
+ flags |= S_APPEND;
+ if (xflags & FS_XFLAG_SYNC)
+ flags |= S_SYNC;
+ if (xflags & FS_XFLAG_NOATIME)
+ flags |= S_NOATIME;
+ if (init && xfs_inode_should_enable_dax(ip))
+ flags |= S_DAX;
+
+ /*
+ * S_DAX can only be set during inode initialization and is never set by
+ * the VFS, so we cannot mask off S_DAX in i_flags.
+ */
+ inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC | S_NOATIME);
+ inode->i_flags |= flags;
}
/*
@@ -1284,11 +1334,8 @@
/* make the inode look hashed for the writeback code */
inode_fake_hash(inode);
- inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
- inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
-
i_size_write(inode, ip->i_d.di_size);
- xfs_diflags_to_iflags(inode, ip);
+ xfs_diflags_to_iflags(ip, true);
if (S_ISDIR(inode->i_mode)) {
/*
@@ -1300,9 +1347,7 @@
lockdep_set_class(&inode->i_rwsem,
&inode->i_sb->s_type->i_mutex_dir_key);
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
- ip->d_ops = ip->i_mount->m_dir_inode_ops;
} else {
- ip->d_ops = ip->i_mount->m_nondir_inode_ops;
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
}