summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/file.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/file.c')
-rw-r--r--fs/btrfs/file.c243
1 files changed, 204 insertions, 39 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66836d85763..f447b783bb8 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,6 +24,7 @@
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
+#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
@@ -69,6 +70,19 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
/* Flush processor's dcache for this page */
flush_dcache_page(page);
+
+ /*
+ * if we get a partial write, we can end up with
+ * partially up to date pages. These add
+ * a lot of complexity, so make sure they don't
+ * happen by forcing this copy to be retried.
+ *
+ * The rest of the btrfs_file_write code will fall
+ * back to page at a time copies after we return 0.
+ */
+ if (!PageUptodate(page) && copied < count)
+ copied = 0;
+
iov_iter_advance(i, copied);
write_bytes -= copied;
total_copied += copied;
@@ -185,6 +199,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split = alloc_extent_map(GFP_NOFS);
if (!split2)
split2 = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!split || !split2);
write_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
@@ -224,6 +239,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split->bdev = em->bdev;
split->flags = flags;
+ split->compress_type = em->compress_type;
ret = add_extent_mapping(em_tree, split);
BUG_ON(ret);
free_extent_map(split);
@@ -238,6 +254,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split->len = em->start + em->len - (start + len);
split->bdev = em->bdev;
split->flags = flags;
+ split->compress_type = em->compress_type;
if (compressed) {
split->block_len = em->block_len;
@@ -759,6 +776,27 @@ out:
}
/*
+ * on error we return an unlocked page and the error value
+ * on success we return a locked page and 0
+ */
+static int prepare_uptodate_page(struct page *page, u64 pos)
+{
+ int ret = 0;
+
+ if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+ ret = btrfs_readpage(NULL, page);
+ if (ret)
+ return ret;
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ unlock_page(page);
+ return -EIO;
+ }
+ }
+ return 0;
+}
+
+/*
* this gets pages into the page cache and locks them down, it also properly
* waits for data=ordered extents to finish before allowing the pages to be
* modified.
@@ -773,6 +811,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
unsigned long index = pos >> PAGE_CACHE_SHIFT;
struct inode *inode = fdentry(file)->d_inode;
int err = 0;
+ int faili = 0;
u64 start_pos;
u64 last_pos;
@@ -790,11 +829,24 @@ again:
for (i = 0; i < num_pages; i++) {
pages[i] = grab_cache_page(inode->i_mapping, index + i);
if (!pages[i]) {
+ faili = i - 1;
err = -ENOMEM;
- BUG_ON(1);
+ goto fail;
+ }
+
+ if (i == 0)
+ err = prepare_uptodate_page(pages[i], pos);
+ if (i == num_pages - 1)
+ err = prepare_uptodate_page(pages[i],
+ pos + write_bytes);
+ if (err) {
+ page_cache_release(pages[i]);
+ faili = i - 1;
+ goto fail;
}
wait_on_page_writeback(pages[i]);
}
+ err = 0;
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
lock_extent_bits(&BTRFS_I(inode)->io_tree,
@@ -834,6 +886,14 @@ again:
WARN_ON(!PageLocked(pages[i]));
}
return 0;
+fail:
+ while (faili >= 0) {
+ unlock_page(pages[faili]);
+ page_cache_release(pages[faili]);
+ faili--;
+ }
+ return err;
+
}
static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
@@ -843,7 +903,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
struct file *file = iocb->ki_filp;
struct inode *inode = fdentry(file)->d_inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct page *pinned[2];
struct page **pages = NULL;
struct iov_iter i;
loff_t *ppos = &iocb->ki_pos;
@@ -864,9 +923,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
(file->f_flags & O_DIRECT));
- pinned[0] = NULL;
- pinned[1] = NULL;
-
start_pos = pos;
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
@@ -890,6 +946,17 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
if (err)
goto out;
+ /*
+ * If BTRFS flips readonly due to some impossible error
+ * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
+ * although we have opened a file as writable, we have
+ * to stop this write operation to ensure FS consistency.
+ */
+ if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ err = -EROFS;
+ goto out;
+ }
+
file_update_time(file);
BTRFS_I(inode)->sequence++;
@@ -932,6 +999,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
+ if (!pages) {
+ ret = -ENOMEM;
+ goto out;
+ }
/* generic_write_checks can change our pos */
start_pos = pos;
@@ -939,39 +1010,13 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
first_index = pos >> PAGE_CACHE_SHIFT;
last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
- /*
- * there are lots of better ways to do this, but this code
- * makes sure the first and last page in the file range are
- * up to date and ready for cow
- */
- if ((pos & (PAGE_CACHE_SIZE - 1))) {
- pinned[0] = grab_cache_page(inode->i_mapping, first_index);
- if (!PageUptodate(pinned[0])) {
- ret = btrfs_readpage(NULL, pinned[0]);
- BUG_ON(ret);
- wait_on_page_locked(pinned[0]);
- } else {
- unlock_page(pinned[0]);
- }
- }
- if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) {
- pinned[1] = grab_cache_page(inode->i_mapping, last_index);
- if (!PageUptodate(pinned[1])) {
- ret = btrfs_readpage(NULL, pinned[1]);
- BUG_ON(ret);
- wait_on_page_locked(pinned[1]);
- } else {
- unlock_page(pinned[1]);
- }
- }
-
while (iov_iter_count(&i) > 0) {
size_t offset = pos & (PAGE_CACHE_SIZE - 1);
size_t write_bytes = min(iov_iter_count(&i),
nrptrs * (size_t)PAGE_CACHE_SIZE -
offset);
- size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
+ size_t num_pages = (write_bytes + offset +
+ PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
WARN_ON(num_pages > nrptrs);
memset(pages, 0, sizeof(struct page *) * nrptrs);
@@ -1001,8 +1046,20 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
copied = btrfs_copy_from_user(pos, num_pages,
write_bytes, pages, &i);
- dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
+
+ /*
+ * if we have trouble faulting in the pages, fall
+ * back to one page at a time
+ */
+ if (copied < write_bytes)
+ nrptrs = 1;
+
+ if (copied == 0)
+ dirty_pages = 0;
+ else
+ dirty_pages = (copied + offset +
+ PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
if (num_pages > dirty_pages) {
if (copied > 0)
@@ -1046,10 +1103,6 @@ out:
err = ret;
kfree(pages);
- if (pinned[0])
- page_cache_release(pinned[0]);
- if (pinned[1])
- page_cache_release(pinned[1]);
*ppos = pos;
/*
@@ -1237,6 +1290,117 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma)
return 0;
}
+static long btrfs_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct extent_state *cached_state = NULL;
+ u64 cur_offset;
+ u64 last_byte;
+ u64 alloc_start;
+ u64 alloc_end;
+ u64 alloc_hint = 0;
+ u64 locked_end;
+ u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
+ struct extent_map *em;
+ int ret;
+
+ alloc_start = offset & ~mask;
+ alloc_end = (offset + len + mask) & ~mask;
+
+ /* We only support the FALLOC_FL_KEEP_SIZE mode */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ return -EOPNOTSUPP;
+
+ /*
+ * wait for ordered IO before we have any locks. We'll loop again
+ * below with the locks held.
+ */
+ btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
+
+ mutex_lock(&inode->i_mutex);
+ ret = inode_newsize_ok(inode, alloc_end);
+ if (ret)
+ goto out;
+
+ if (alloc_start > inode->i_size) {
+ ret = btrfs_cont_expand(inode, alloc_start);
+ if (ret)
+ goto out;
+ }
+
+ ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+ if (ret)
+ goto out;
+
+ locked_end = alloc_end - 1;
+ while (1) {
+ struct btrfs_ordered_extent *ordered;
+
+ /* the extent lock is ordered inside the running
+ * transaction
+ */
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
+ locked_end, 0, &cached_state, GFP_NOFS);
+ ordered = btrfs_lookup_first_ordered_extent(inode,
+ alloc_end - 1);
+ if (ordered &&
+ ordered->file_offset + ordered->len > alloc_start &&
+ ordered->file_offset < alloc_end) {
+ btrfs_put_ordered_extent(ordered);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+ /*
+ * we can't wait on the range with the transaction
+ * running or with the extent lock held
+ */
+ btrfs_wait_ordered_range(inode, alloc_start,
+ alloc_end - alloc_start);
+ } else {
+ if (ordered)
+ btrfs_put_ordered_extent(ordered);
+ break;
+ }
+ }
+
+ cur_offset = alloc_start;
+ while (1) {
+ em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+ alloc_end - cur_offset, 0);
+ BUG_ON(IS_ERR(em) || !em);
+ last_byte = min(extent_map_end(em), alloc_end);
+ last_byte = (last_byte + mask) & ~mask;
+ if (em->block_start == EXTENT_MAP_HOLE ||
+ (cur_offset >= inode->i_size &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+ ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
+ last_byte - cur_offset,
+ 1 << inode->i_blkbits,
+ offset + len,
+ &alloc_hint);
+ if (ret < 0) {
+ free_extent_map(em);
+ break;
+ }
+ }
+ free_extent_map(em);
+
+ cur_offset = last_byte;
+ if (cur_offset >= alloc_end) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+
+ btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+out:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
const struct file_operations btrfs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -1248,6 +1412,7 @@ const struct file_operations btrfs_file_operations = {
.open = generic_file_open,
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
+ .fallocate = btrfs_fallocate,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_ioctl,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-01 21:01:54 +0000