summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/extents.c1
-rw-r--r--fs/ext4/file.c26
-rw-r--r--fs/ext4/ialloc.c2
-rw-r--r--fs/ext4/inode.c48
-rw-r--r--fs/ext4/ioctl.c86
-rw-r--r--fs/ext4/namei.c4
-rw-r--r--fs/ext4/super.c52
7 files changed, 127 insertions, 92 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 07bca11749d4..c941251ac0c0 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4722,6 +4722,7 @@ retry:
EXT4_INODE_EOFBLOCKS);
}
ext4_mark_inode_dirty(handle, inode);
+ ext4_update_inode_fsync_trans(handle, inode, 1);
ret2 = ext4_journal_stop(handle);
if (ret2)
break;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ad204d2724ac..a0ae27b1bc66 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -28,6 +28,7 @@
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
+#include <linux/mman.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -297,6 +298,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
*/
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
+ pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
@@ -304,16 +306,20 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
+ if (IS_ERR(handle)) {
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ sb_end_pagefault(sb);
+ return VM_FAULT_SIGBUS;
+ }
} else {
down_read(&EXT4_I(inode)->i_mmap_sem);
}
- if (!IS_ERR(handle))
- result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
- else
- result = VM_FAULT_SIGBUS;
+ result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
+ ext4_journal_stop(handle);
+ /* Handling synchronous page fault? */
+ if (result & VM_FAULT_NEEDDSYNC)
+ result = dax_finish_sync_fault(vmf, pe_size, pfn);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
} else {
@@ -351,6 +357,13 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
+ /*
+ * We don't support synchronous mappings for non-DAX files. At least
+ * until someone comes with a sensible use case.
+ */
+ if (!IS_DAX(file_inode(file)) && (vma->vm_flags & VM_SYNC))
+ return -EOPNOTSUPP;
+
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
@@ -469,6 +482,7 @@ const struct file_operations ext4_file_operations = {
.compat_ioctl = ext4_compat_ioctl,
#endif
.mmap = ext4_file_mmap,
+ .mmap_supported_flags = MAP_SYNC,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b4267d72f249..b32cf263750d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -816,6 +816,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT);
+ if (IS_ERR(p))
+ return ERR_CAST(p);
if (p) {
int acl_size = p->a_count * sizeof(ext4_acl_entry);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2633150e41b9..534a9130f625 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -149,6 +149,15 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
*/
int ext4_inode_is_fast_symlink(struct inode *inode)
{
+ if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+ int ea_blocks = EXT4_I(inode)->i_file_acl ?
+ EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
+
+ if (ext4_has_inline_data(inode))
+ return 0;
+
+ return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
+ }
return S_ISLNK(inode->i_mode) && inode->i_size &&
(inode->i_size < EXT4_N_BLOCKS * 4);
}
@@ -1719,7 +1728,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
ext4_es_remove_extent(inode, start, last - start + 1);
}
- pagevec_init(&pvec, 0);
+ pagevec_init(&pvec);
while (index <= end) {
nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end);
if (nr_pages == 0)
@@ -2345,7 +2354,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
lblk = start << bpp_bits;
pblock = mpd->map.m_pblk;
- pagevec_init(&pvec, 0);
+ pagevec_init(&pvec);
while (start <= end) {
nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping,
&start, end);
@@ -2616,12 +2625,12 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
else
tag = PAGECACHE_TAG_DIRTY;
- pagevec_init(&pvec, 0);
+ pagevec_init(&pvec);
mpd->map.m_len = 0;
mpd->next_page = index;
while (index <= end) {
- nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+ tag);
if (nr_pages == 0)
goto out;
@@ -2629,16 +2638,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
struct page *page = pvec.pages[i];
/*
- * At this point, the page may be truncated or
- * invalidated (changing page->mapping to NULL), or
- * even swizzled back from swapper_space to tmpfs file
- * mapping. However, page->index will not change
- * because we have a reference on the page.
- */
- if (page->index > end)
- goto out;
-
- /*
* Accumulated enough dirty pages? This doesn't apply
* to WB_SYNC_ALL mode. For integrity sync we have to
* keep going because someone may be concurrently
@@ -2752,7 +2751,7 @@ static int ext4_writepages(struct address_space *mapping,
* If the filesystem has aborted, it is read-only, so return
* right away instead of dumping stack traces later on that
* will obscure the real source of the problem. We test
- * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
+ * EXT4_MF_FS_ABORTED instead of sb->s_flag's SB_RDONLY because
* the latter could be true if the filesystem is mounted
* read-only, and in that case, ext4_writepages should
* *never* be called, so if that ever happens, we would want
@@ -3394,6 +3393,19 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
return try_to_free_buffers(page);
}
+static bool ext4_inode_datasync_dirty(struct inode *inode)
+{
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+ if (journal)
+ return !jbd2_transaction_committed(journal,
+ EXT4_I(inode)->i_datasync_tid);
+ /* Any metadata buffers to write? */
+ if (!list_empty(&inode->i_mapping->private_list))
+ return true;
+ return inode->i_state & I_DIRTY_DATASYNC;
+}
+
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
{
@@ -3507,6 +3519,8 @@ retry:
}
iomap->flags = 0;
+ if (ext4_inode_datasync_dirty(inode))
+ iomap->flags |= IOMAP_F_DIRTY;
iomap->bdev = inode->i_sb->s_bdev;
iomap->dax_dev = sbi->s_daxdev;
iomap->offset = first_block << blkbits;
@@ -5178,7 +5192,7 @@ static int ext4_do_update_inode(handle_t *handle,
ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
- if (inode->i_sb->s_flags & MS_LAZYTIME)
+ if (inode->i_sb->s_flags & SB_LAZYTIME)
ext4_update_other_inodes_time(inode->i_sb, inode->i_ino,
bh->b_data);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index b7558f292420..1eec25014f62 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -592,6 +592,44 @@ static int ext4_ioc_getfsmap(struct super_block *sb,
return 0;
}
+static long ext4_ioctl_group_add(struct file *file,
+ struct ext4_new_group_data *input)
+{
+ struct super_block *sb = file_inode(file)->i_sb;
+ int err, err2=0;
+
+ err = ext4_resize_begin(sb);
+ if (err)
+ return err;
+
+ if (ext4_has_feature_bigalloc(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "Online resizing not supported with bigalloc");
+ err = -EOPNOTSUPP;
+ goto group_add_out;
+ }
+
+ err = mnt_want_write_file(file);
+ if (err)
+ goto group_add_out;
+
+ err = ext4_group_add(sb, input);
+ if (EXT4_SB(sb)->s_journal) {
+ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+ err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ }
+ if (err == 0)
+ err = err2;
+ mnt_drop_write_file(file);
+ if (!err && ext4_has_group_desc_csum(sb) &&
+ test_opt(sb, INIT_INODE_TABLE))
+ err = ext4_register_li_request(sb, input->group);
+group_add_out:
+ ext4_resize_end(sb);
+ return err;
+}
+
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -776,44 +814,12 @@ mext_out:
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
- int err, err2=0;
-
- err = ext4_resize_begin(sb);
- if (err)
- return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
- sizeof(input))) {
- err = -EFAULT;
- goto group_add_out;
- }
-
- if (ext4_has_feature_bigalloc(sb)) {
- ext4_msg(sb, KERN_ERR,
- "Online resizing not supported with bigalloc");
- err = -EOPNOTSUPP;
- goto group_add_out;
- }
-
- err = mnt_want_write_file(filp);
- if (err)
- goto group_add_out;
+ sizeof(input)))
+ return -EFAULT;
- err = ext4_group_add(sb, &input);
- if (EXT4_SB(sb)->s_journal) {
- jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
- err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
- jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
- }
- if (err == 0)
- err = err2;
- mnt_drop_write_file(filp);
- if (!err && ext4_has_group_desc_csum(sb) &&
- test_opt(sb, INIT_INODE_TABLE))
- err = ext4_register_li_request(sb, input.group);
-group_add_out:
- ext4_resize_end(sb);
- return err;
+ return ext4_ioctl_group_add(filp, &input);
}
case EXT4_IOC_MIGRATE:
@@ -1078,8 +1084,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
break;
case EXT4_IOC32_GROUP_ADD: {
struct compat_ext4_new_group_input __user *uinput;
- struct ext4_new_group_input input;
- mm_segment_t old_fs;
+ struct ext4_new_group_data input;
int err;
uinput = compat_ptr(arg);
@@ -1092,12 +1097,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
&uinput->reserved_blocks);
if (err)
return -EFAULT;
- old_fs = get_fs();
- set_fs(KERNEL_DS);
- err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
- (unsigned long) &input);
- set_fs(old_fs);
- return err;
+ return ext4_ioctl_group_add(file, &input);
}
case EXT4_IOC_MOVE_EXT:
case EXT4_IOC_RESIZE_FS:
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 798b3ac680db..e750d68fbcb5 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1399,6 +1399,10 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
"falling back\n"));
}
nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
+ if (!nblocks) {
+ ret = NULL;
+ goto cleanup_and_exit;
+ }
start = EXT4_I(dir)->i_dir_start_lookup;
if (start >= nblocks)
start = 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0556cd036b69..7c46693a14d7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -422,7 +422,7 @@ static void ext4_handle_error(struct super_block *sb)
* before ->s_flags update
*/
smp_wmb();
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
@@ -635,7 +635,7 @@ void __ext4_abort(struct super_block *sb, const char *function,
* before ->s_flags update
*/
smp_wmb();
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
@@ -1682,10 +1682,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
sb->s_flags |= SB_I_VERSION;
return 1;
case Opt_lazytime:
- sb->s_flags |= MS_LAZYTIME;
+ sb->s_flags |= SB_LAZYTIME;
return 1;
case Opt_nolazytime:
- sb->s_flags &= ~MS_LAZYTIME;
+ sb->s_flags &= ~SB_LAZYTIME;
return 1;
}
@@ -2116,7 +2116,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
- res = MS_RDONLY;
+ res = SB_RDONLY;
}
if (read_only)
goto done;
@@ -2429,7 +2429,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
/* don't clear list on RO mount w/ errors */
- if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
+ if (es->s_last_orphan && !(s_flags & SB_RDONLY)) {
ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
"clearing orphan list.\n");
es->s_last_orphan = 0;
@@ -2438,19 +2438,19 @@ static void ext4_orphan_cleanup(struct super_block *sb,
return;
}
- if (s_flags & MS_RDONLY) {
+ if (s_flags & SB_RDONLY) {
ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
- sb->s_flags |= MS_ACTIVE;
+ sb->s_flags |= SB_ACTIVE;
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
- if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) {
+ if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) {
int ret = ext4_enable_quotas(sb);
if (!ret)
@@ -2539,7 +2539,7 @@ static void ext4_orphan_cleanup(struct super_block *sb,
}
}
#endif
- sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+ sb->s_flags = s_flags; /* Restore SB_RDONLY status */
}
/*
@@ -2741,7 +2741,7 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
if (ext4_has_feature_readonly(sb)) {
ext4_msg(sb, KERN_INFO, "filesystem is read-only");
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
return 1;
}
@@ -3623,8 +3623,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sb->s_iflags |= SB_I_CGROUPWB;
}
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(ext4_has_compat_features(sb) ||
@@ -4199,7 +4199,7 @@ no_journal:
}
if (ext4_setup_super(sb, es, sb_rdonly(sb)))
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
@@ -4693,7 +4693,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
* the clock is set in the future, and this will cause e2fsck
* to complain and force a full file system check.
*/
- if (!(sb->s_flags & MS_RDONLY))
+ if (!(sb->s_flags & SB_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
if (sb->s_bdev->bd_part)
es->s_kbytes_written =
@@ -5047,8 +5047,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
- (test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
+ (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
es = sbi->s_es;
@@ -5057,16 +5057,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
- if (*flags & MS_LAZYTIME)
- sb->s_flags |= MS_LAZYTIME;
+ if (*flags & SB_LAZYTIME)
+ sb->s_flags |= SB_LAZYTIME;
- if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) {
+ if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
}
- if (*flags & MS_RDONLY) {
+ if (*flags & SB_RDONLY) {
err = sync_filesystem(sb);
if (err < 0)
goto restore_opts;
@@ -5078,7 +5078,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
*/
- sb->s_flags |= MS_RDONLY;
+ sb->s_flags |= SB_RDONLY;
/*
* OK, test if we are remounting a valid rw partition
@@ -5140,7 +5140,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext4_setup_super(sb, es, 0))
- sb->s_flags &= ~MS_RDONLY;
+ sb->s_flags &= ~SB_RDONLY;
if (ext4_has_feature_mmp(sb))
if (ext4_multi_mount_protect(sb,
le64_to_cpu(es->s_mmp_block))) {
@@ -5164,7 +5164,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
ext4_setup_system_zone(sb);
- if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
+ if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY))
ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
@@ -5182,7 +5182,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
#endif
- *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
+ *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
kfree(orig_data);
return 0;
OpenPOWER on IntegriCloud