#include "compression.h"
#include "delalloc-space.h"
#include "reflink.h"
+#include "subpage.h"
static struct kmem_cache *btrfs_inode_defrag_cachep;
/*
/*
* Copy data from userspace to the current page
*/
- copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
+ copied = copy_page_from_iter_atomic(page, offset, count, i);
/* Flush processor's dcache for this page */
flush_dcache_page(page);
* 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;
+ if (unlikely(copied < count)) {
+ if (!PageUptodate(page)) {
+ iov_iter_revert(i, copied);
+ copied = 0;
+ }
+ if (!copied)
+ break;
+ }
- iov_iter_advance(i, copied);
write_bytes -= copied;
total_copied += copied;
-
- /* Return to btrfs_file_write_iter to fault page */
- if (unlikely(copied == 0))
- break;
-
- if (copied < PAGE_SIZE - offset) {
- offset += copied;
- } else {
+ offset += copied;
+ if (offset == PAGE_SIZE) {
pg++;
offset = 0;
}
start_pos = round_down(pos, fs_info->sectorsize);
num_bytes = round_up(write_bytes + pos - start_pos,
fs_info->sectorsize);
+ ASSERT(num_bytes <= U32_MAX);
end_of_last_block = start_pos + num_bytes - 1;
for (i = 0; i < num_pages; i++) {
struct page *p = pages[i];
- SetPageUptodate(p);
+
+ btrfs_page_clamp_set_uptodate(fs_info, p, start_pos, num_bytes);
ClearPageChecked(p);
- set_page_dirty(p);
+ btrfs_page_clamp_set_dirty(fs_info, p, start_pos, num_bytes);
}
/*
int del_nr = 0;
int del_slot = 0;
int recow;
- int ret;
+ int ret = 0;
u64 ino = btrfs_ino(inode);
path = btrfs_alloc_path();
}
out:
btrfs_free_path(path);
- return 0;
+ return ret;
}
/*
return ret;
}
+static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+ if (btrfs_inode_in_log(inode, fs_info->generation) &&
+ list_empty(&ctx->ordered_extents))
+ return true;
+
+ /*
+ * If we are doing a fast fsync we can not bail out if the inode's
+ * last_trans is <= then the last committed transaction, because we only
+ * update the last_trans of the inode during ordered extent completion,
+ * and for a fast fsync we don't wait for that, we only wait for the
+ * writeback to complete.
+ */
+ if (inode->last_trans <= fs_info->last_trans_committed &&
+ (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
+ list_empty(&ctx->ordered_extents)))
+ return true;
+
+ return false;
+}
+
/*
* fsync call for both files and directories. This logs the inode into
* the tree log instead of forcing full commits whenever possible.
atomic_inc(&root->log_batch);
- /*
- * If we are doing a fast fsync we can not bail out if the inode's
- * last_trans is <= then the last committed transaction, because we only
- * update the last_trans of the inode during ordered extent completion,
- * and for a fast fsync we don't wait for that, we only wait for the
- * writeback to complete.
- */
smp_mb();
- if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
- (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed &&
- (full_sync || list_empty(&ctx.ordered_extents)))) {
+ if (skip_inode_logging(&ctx)) {
/*
* We've had everything committed since the last time we were
* modified so clear this flag in case it was set for whatever
const u64 lockend,
struct extent_state **cached_state)
{
+ /*
+ * For subpage case, if the range is not at page boundary, we could
+ * have pages at the leading/tailing part of the range.
+ * This could lead to dead loop since filemap_range_has_page()
+ * will always return true.
+ * So here we need to do extra page alignment for
+ * filemap_range_has_page().
+ */
+ const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
+ const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+
while (1) {
struct btrfs_ordered_extent *ordered;
int ret;
(ordered->file_offset + ordered->num_bytes <= lockstart ||
ordered->file_offset > lockend)) &&
!filemap_range_has_page(inode->i_mapping,
- lockstart, lockend)) {
+ page_lockstart, page_lockend)) {
if (ordered)
btrfs_put_ordered_extent(ordered);
break;
*/
static int add_falloc_range(struct list_head *head, u64 start, u64 len)
{
- struct falloc_range *prev = NULL;
struct falloc_range *range = NULL;
- if (list_empty(head))
- goto insert;
-
- /*
- * As fallocate iterate by bytenr order, we only need to check
- * the last range.
- */
- prev = list_entry(head->prev, struct falloc_range, list);
- if (prev->start + prev->len == start) {
- prev->len += len;
- return 0;
+ if (!list_empty(head)) {
+ /*
+ * As fallocate iterates by bytenr order, we only need to check
+ * the last range.
+ */
+ range = list_last_entry(head, struct falloc_range, list);
+ if (range->start + range->len == start) {
+ range->len += len;
+ return 0;
+ }
}
-insert:
+
range = kmalloc(sizeof(*range), GFP_KERNEL);
if (!range)
return -ENOMEM;
{
struct inode *inode = rac->mapping->host;
loff_t pos = readahead_pos(rac);
- loff_t length = readahead_length(rac);
+ size_t length = readahead_length(rac);
struct iomap_readpage_ctx ctx = {
.rac = rac,
};
trace_iomap_readahead(inode, readahead_count(rac));
while (length > 0) {
- loff_t ret = iomap_apply(inode, pos, length, 0, ops,
+ ssize_t ret = iomap_apply(inode, pos, length, 0, ops,
&ctx, iomap_readahead_actor);
if (ret <= 0) {
WARN_ON_ONCE(ret == 0);
return status;
}
-int
-iomap_set_page_dirty(struct page *page)
-{
- struct address_space *mapping = page_mapping(page);
- int newly_dirty;
-
- if (unlikely(!mapping))
- return !TestSetPageDirty(page);
-
- /*
- * Lock out page's memcg migration to keep PageDirty
- * synchronized with per-memcg dirty page counters.
- */
- lock_page_memcg(page);
- newly_dirty = !TestSetPageDirty(page);
- if (newly_dirty)
- __set_page_dirty(page, mapping, 0);
- unlock_page_memcg(page);
-
- if (newly_dirty)
- __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- return newly_dirty;
-}
-EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
-
static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
size_t copied, struct page *page)
{
if (unlikely(copied < len && !PageUptodate(page)))
return 0;
iomap_set_range_uptodate(page, offset_in_page(pos), len);
- iomap_set_page_dirty(page);
+ __set_page_dirty_nobuffers(page);
return copied;
}
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
- *
- * Not only is this an optimisation, but it is also required
- * to check that the address is actually valid, when atomic
- * usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
if (mapping_writably_mapped(inode->i_mapping))
flush_dcache_page(page);
- copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+ copied = copy_page_from_iter_atomic(page, offset, bytes, i);
- copied = iomap_write_end(inode, pos, bytes, copied, page, iomap,
+ status = iomap_write_end(inode, pos, bytes, copied, page, iomap,
srcmap);
- cond_resched();
+ if (unlikely(copied != status))
+ iov_iter_revert(i, copied - status);
- iov_iter_advance(i, copied);
- if (unlikely(copied == 0)) {
+ cond_resched();
+ if (unlikely(status == 0)) {
/*
- * If we were unable to copy any data at all, we must
- * fall back to a single segment length write.
- *
- * If we didn't fallback here, we could livelock
- * because not all segments in the iov can be copied at
- * once without a pagefault.
+ * A short copy made iomap_write_end() reject the
+ * thing entirely. Might be memory poisoning
+ * halfway through, might be a race with munmap,
+ * might be severe memory pressure.
*/
- bytes = min_t(unsigned long, PAGE_SIZE - offset,
- iov_iter_single_seg_count(i));
+ if (copied)
+ bytes = copied;
goto again;
}
- pos += copied;
- written += copied;
- length -= copied;
+ pos += status;
+ written += status;
+ length -= status;
balance_dirty_pages_ratelimited(inode->i_mapping);
} while (iov_iter_count(i) && length);
page->index = offset;
if (!huge) {
- error = mem_cgroup_charge(page, current->mm, gfp);
+ error = mem_cgroup_charge(page, NULL, gfp);
if (error)
goto error;
charged = true;
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
- *
- * Not only is this an optimisation, but it is also required
- * to check that the address is actually valid, when atomic
- * usercopies are used, below.
*/
if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
status = -EFAULT;
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
- copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+ copied = copy_page_from_iter_atomic(page, offset, bytes, i);
flush_dcache_page(page);
status = a_ops->write_end(file, mapping, pos, bytes, copied,
page, fsdata);
- if (unlikely(status < 0))
- break;
- copied = status;
-
+ if (unlikely(status != copied)) {
+ iov_iter_revert(i, copied - max(status, 0L));
+ if (unlikely(status < 0))
+ break;
+ }
cond_resched();
- iov_iter_advance(i, copied);
- if (unlikely(copied == 0)) {
+ if (unlikely(status == 0)) {
/*
- * If we were unable to copy any data at all, we must
- * fall back to a single segment length write.
- *
- * If we didn't fallback here, we could livelock
- * because not all segments in the iov can be copied at
- * once without a pagefault.
+ * A short copy made ->write_end() reject the
+ * thing entirely. Might be memory poisoning
+ * halfway through, might be a race with munmap,
+ * might be severe memory pressure.
*/
- bytes = min_t(unsigned long, PAGE_SIZE - offset,
- iov_iter_single_seg_count(i));
+ if (copied)
+ bytes = copied;
goto again;
}
- pos += copied;
- written += copied;
+ pos += status;
+ written += status;
balance_dirty_pages_ratelimited(mapping);
} while (iov_iter_count(i));
projects / J-linux.git / commitdiff