aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h15
-rw-r--r--fs/ext4/extents.c90
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/inode.c71
-rw-r--r--fs/ext4/mballoc.c1
-rw-r--r--fs/ext4/page-io.c9
-rw-r--r--fs/ext4/super.c4
-rw-r--r--fs/ext4/truncate.h2
8 files changed, 143 insertions, 51 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9a83f149ac85..8b033f24a6b0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -191,7 +191,7 @@ typedef struct ext4_io_end {
} ext4_io_end_t;
struct ext4_io_submit {
- int io_op;
+ struct writeback_control *io_wbc;
struct bio *io_bio;
ext4_io_end_t *io_end;
sector_t io_next_block;
@@ -873,6 +873,15 @@ struct ext4_inode_info {
* by other means, so we have i_data_sem.
*/
struct rw_semaphore i_data_sem;
+ /*
+ * i_mmap_sem is for serializing page faults with truncate / punch hole
+ * operations. We have to make sure that new page cannot be faulted in
+ * a section of the inode that is being punched. We cannot easily use
+ * i_data_sem for this since we need protection for the whole punch
+ * operation and i_data_sem ranks below transaction start so we have
+ * to occasionally drop it.
+ */
+ struct rw_semaphore i_mmap_sem;
struct inode vfs_inode;
struct jbd2_inode *jinode;
@@ -2287,6 +2296,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
@@ -2632,6 +2642,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
return changed;
}
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+ loff_t len);
+
struct ext4_group_info {
unsigned long bb_state;
struct rb_root bb_free_root;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 87ba10d1d3bc..677955986ad7 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -39,6 +39,7 @@
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/fiemap.h>
+#include <linux/backing-dev.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "xattr.h"
@@ -4741,7 +4742,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
int partial_begin, partial_end;
loff_t start, end;
ext4_lblk_t lblk;
- struct address_space *mapping = inode->i_mapping;
unsigned int blkbits = inode->i_blkbits;
trace_ext4_zero_range(inode, offset, len, mode);
@@ -4757,17 +4757,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
}
/*
- * Write out all dirty pages to avoid race conditions
- * Then release them.
- */
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
- ret = filemap_write_and_wait_range(mapping, offset,
- offset + len - 1);
- if (ret)
- return ret;
- }
-
- /*
* Round up offset. This is not fallocate, we neet to zero out
* blocks, so convert interior block aligned part of the range to
* unwritten and possibly manually zero out unaligned parts of the
@@ -4810,6 +4799,10 @@ static long ext4_zero_range(struct file *file, loff_t offset,
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
/* Preallocate the range including the unaligned edges */
if (partial_begin || partial_end) {
ret = ext4_alloc_file_blocks(file,
@@ -4818,7 +4811,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
round_down(offset, 1 << blkbits)) >> blkbits,
new_size, flags, mode);
if (ret)
- goto out_mutex;
+ goto out_dio;
}
@@ -4827,16 +4820,23 @@ static long ext4_zero_range(struct file *file, loff_t offset,
flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
EXT4_EX_NOCACHE);
- /* Now release the pages and zero block aligned part of pages*/
+ /*
+ * Prevent page faults from reinstantiating pages we have
+ * released from page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ ret = ext4_update_disksize_before_punch(inode, offset, len);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ goto out_dio;
+ }
+ /* Now release the pages and zero block aligned part of pages */
truncate_pagecache_range(inode, start, end - 1);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
-
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags, mode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
if (ret)
goto out_dio;
}
@@ -4964,8 +4964,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
goto out;
}
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags, mode);
+ ext4_inode_resume_unlocked_dio(inode);
if (ret)
goto out;
@@ -5424,21 +5429,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
- /*
- * Need to round down offset to be aligned with page size boundary
- * for page size > block size.
- */
- ioffset = round_down(offset, PAGE_SIZE);
-
- /* Write out all dirty pages */
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
- LLONG_MAX);
- if (ret)
- return ret;
-
- /* Take mutex lock */
mutex_lock(&inode->i_mutex);
-
/*
* There is no need to overlap collapse range with EOF, in which case
* it is effectively a truncate operation
@@ -5454,17 +5445,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
goto out_mutex;
}
- truncate_pagecache(inode, ioffset);
-
/* Wait for existing dio to complete */
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ /*
+ * Need to round down offset to be aligned with page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+ /*
+ * Write tail of the last page before removed range since it will get
+ * removed from the page cache below.
+ */
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+ if (ret)
+ goto out_mmap;
+ /*
+ * Write data that will be shifted to preserve them when discarding
+ * page cache below. We are also protected from pages becoming dirty
+ * by i_mmap_sem.
+ */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+ LLONG_MAX);
+ if (ret)
+ goto out_mmap;
+ truncate_pagecache(inode, ioffset);
+
credits = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- goto out_dio;
+ goto out_mmap;
}
down_write(&EXT4_I(inode)->i_data_sem);
@@ -5503,7 +5520,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
out_stop:
ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0613c256c344..dd65fac5ff2f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -213,7 +213,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
#endif
static const struct vm_operations_struct ext4_file_vm_ops = {
- .fault = filemap_fault,
+ .fault = ext4_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = ext4_page_mkwrite,
};
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2b3a53a51582..3291e1af0e24 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3524,6 +3524,35 @@ int ext4_can_truncate(struct inode *inode)
}
/*
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+ loff_t len)
+{
+ handle_t *handle;
+ loff_t size = i_size_read(inode);
+
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
+ if (offset > size || offset + len < size)
+ return 0;
+
+ if (EXT4_I(inode)->i_disksize >= size)
+ return 0;
+
+ handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ext4_update_i_disksize(inode, size);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+ return 0;
+}
+
+/*
* ext4_punch_hole: punches a hole in a file by releaseing the blocks
* associated with the given offset and length
*
@@ -3588,17 +3617,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
}
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
/* Now release the pages and zero block aligned part of pages*/
- if (last_block_offset > first_block_offset)
+ if (last_block_offset > first_block_offset) {
+ ret = ext4_update_disksize_before_punch(inode, offset, length);
+ if (ret)
+ goto out_dio;
truncate_pagecache_range(inode, first_block_offset,
last_block_offset);
-
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
+ }
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
@@ -3645,16 +3683,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- /* Now release the pages again to reduce race window */
- if (last_block_offset > first_block_offset)
- truncate_pagecache_range(inode, first_block_offset,
- last_block_offset);
-
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
out_stop:
ext4_journal_stop(handle);
out_dio:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
@@ -4775,11 +4809,13 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
} else
ext4_wait_for_tail_page_commit(inode);
}
+ down_write(&EXT4_I(inode)->i_mmap_sem);
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
*/
truncate_pagecache(inode, inode->i_size);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
}
/*
* We want to call ext4_truncate() even if attr->ia_size ==
@@ -5234,6 +5270,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
@@ -5303,6 +5341,19 @@ retry_alloc:
out_ret:
ret = block_page_mkwrite_return(ret);
out:
+ up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
return ret;
}
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ int err;
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ err = filemap_fault(vma, vmf);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+
+ return err;
+}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 41260489d3bc..5b1613a54307 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -26,6 +26,7 @@
#include <linux/log2.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/backing-dev.h>
#include <trace/events/ext4.h>
#ifdef CONFIG_EXT4_DEBUG
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 8082565c59a9..00cda09e4412 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -357,9 +357,10 @@ void ext4_io_submit(struct ext4_io_submit *io)
struct bio *bio = io->io_bio;
if (bio) {
+ int io_op = io->io_wbc->sync_mode == WB_SYNC_ALL ?
+ WRITE_SYNC : WRITE;
bio_get(io->io_bio);
- submit_bio(io->io_op, io->io_bio);
- BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
+ submit_bio(io_op, io->io_bio);
bio_put(io->io_bio);
}
io->io_bio = NULL;
@@ -368,7 +369,7 @@ void ext4_io_submit(struct ext4_io_submit *io)
void ext4_io_submit_init(struct ext4_io_submit *io,
struct writeback_control *wbc)
{
- io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+ io->io_wbc = wbc;
io->io_bio = NULL;
io->io_end = NULL;
}
@@ -382,6 +383,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
if (!bio)
return -ENOMEM;
+ wbc_init_bio(io->io_wbc, bio);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
bio->bi_end_io = ext4_end_bio;
@@ -410,6 +412,7 @@ submit_and_retry:
ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
+ wbc_account_io(io->io_wbc, page, bh->b_size);
io->io_next_block++;
return 0;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8a3b9f14d198..abb7ec3f19b9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
#include <linux/parser.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
@@ -945,6 +946,7 @@ static void init_once(void *foo)
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
+ init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
}
@@ -3649,6 +3651,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (test_opt(sb, DELALLOC))
clear_opt(sb, DELALLOC);
+ } else {
+ sb->s_iflags |= SB_I_CGROUPWB;
}
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 011ba6670d99..c70d06a383e2 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -10,8 +10,10 @@
*/
static inline void ext4_truncate_failed_write(struct inode *inode)
{
+ down_write(&EXT4_I(inode)->i_mmap_sem);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
}
/*
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-28 00:13:35 +0000