summaryrefslogtreecommitdiff
path: root/fs/f2fs/compress.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-04 10:48:47 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-04 10:48:47 -0700
commit6abaa83c7352b31450d7e8c173f674324c16b02b (patch)
treecea534b220e9635bb2af785a954292e416ebdca9 /fs/f2fs/compress.c
parent0961f0c00e69672a8e4a2e591355567dbda44389 (diff)
parent9605f75cf36e0bcc0f4ada07b5be712d30107607 (diff)
downloadlwn-6abaa83c7352b31450d7e8c173f674324c16b02b.tar.gz
lwn-6abaa83c7352b31450d7e8c173f674324c16b02b.zip
Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim: "In this cycle, we've addressed some performance issues such as lock contention, misbehaving compress_cache, allowing extent_cache for compressed files, and new sysfs to adjust ra_size for fadvise. In order to diagnose the performance issues quickly, we also added an iostat which shows the IO latencies periodically. On the stability side, we've found two memory leakage cases in the error path in compression flow. And, we've also fixed various corner cases in fiemap, quota, checkpoint=disable, zstd, and so on. Enhancements: - avoid long checkpoint latency by releasing nat_tree_lock - collect and show iostats periodically - support extent_cache for compressed files - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL) - report f2fs GC status via sysfs - add discard_unit=%s in mount option to handle zoned device Bug fixes: - fix two memory leakages when an error happens in the compressed IO flow - fix commpress_cache to get the right LBA - fix fiemap to deal with compressed case correctly - fix wrong EIO returns due to SBI_NEED_FSCK - fix missing writes when enabling checkpoint back - fix quota deadlock - fix zstd level mount option In addition to the above major updates, we've cleaned up several code paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity check, and typos" * tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits) f2fs: should put a page beyond EOF when preparing a write f2fs: deallocate compressed pages when error happens f2fs: enable realtime discard iff device supports discard f2fs: guarantee to write dirty data when enabling checkpoint back f2fs: fix to unmap pages from userspace process in punch_hole() f2fs: fix unexpected ENOENT comes from f2fs_map_blocks() f2fs: fix to account missing .skipped_gc_rwsem f2fs: adjust unlock order for cleanup f2fs: Don't create discard thread when device doesn't support realtime discard f2fs: rebuild nat_bits during umount f2fs: introduce periodic iostat io latency traces f2fs: separate out iostat feature f2fs: compress: do sanity check on cluster f2fs: fix description about main_blkaddr node f2fs: convert S_IRUGO to 0444 f2fs: fix to keep compatibility of fault injection interface f2fs: support fault injection for f2fs_kmem_cache_alloc() f2fs: compress: allow write compress released file after truncate to zero f2fs: correct comment in segment.h f2fs: improve sbi status info in debugfs/f2fs/status ...
Diffstat (limited to 'fs/f2fs/compress.c')
-rw-r--r--fs/f2fs/compress.c97
1 files changed, 88 insertions, 9 deletions
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 455561826c7d..c1bf9ad4c220 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -28,7 +28,8 @@ static void *page_array_alloc(struct inode *inode, int nr)
unsigned int size = sizeof(struct page *) * nr;
if (likely(size <= sbi->page_array_slab_size))
- return kmem_cache_zalloc(sbi->page_array_slab, GFP_NOFS);
+ return f2fs_kmem_cache_alloc(sbi->page_array_slab,
+ GFP_F2FS_ZERO, false, F2FS_I_SB(inode));
return f2fs_kzalloc(sbi, size, GFP_NOFS);
}
@@ -898,6 +899,54 @@ static bool cluster_has_invalid_data(struct compress_ctx *cc)
return false;
}
+bool f2fs_sanity_check_cluster(struct dnode_of_data *dn)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+ bool compressed = dn->data_blkaddr == COMPRESS_ADDR;
+ int cluster_end = 0;
+ int i;
+ char *reason = "";
+
+ if (!compressed)
+ return false;
+
+ /* [..., COMPR_ADDR, ...] */
+ if (dn->ofs_in_node % cluster_size) {
+ reason = "[*|C|*|*]";
+ goto out;
+ }
+
+ for (i = 1; i < cluster_size; i++) {
+ block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+ /* [COMPR_ADDR, ..., COMPR_ADDR] */
+ if (blkaddr == COMPRESS_ADDR) {
+ reason = "[C|*|C|*]";
+ goto out;
+ }
+ if (compressed) {
+ if (!__is_valid_data_blkaddr(blkaddr)) {
+ if (!cluster_end)
+ cluster_end = i;
+ continue;
+ }
+ /* [COMPR_ADDR, NULL_ADDR or NEW_ADDR, valid_blkaddr] */
+ if (cluster_end) {
+ reason = "[C|N|N|V]";
+ goto out;
+ }
+ }
+ }
+ return false;
+out:
+ f2fs_warn(sbi, "access invalid cluster, ino:%lu, nid:%u, ofs_in_node:%u, reason:%s",
+ dn->inode->i_ino, dn->nid, dn->ofs_in_node, reason);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return true;
+}
+
static int __f2fs_cluster_blocks(struct inode *inode,
unsigned int cluster_idx, bool compr)
{
@@ -915,6 +964,11 @@ static int __f2fs_cluster_blocks(struct inode *inode,
goto fail;
}
+ if (f2fs_sanity_check_cluster(&dn)) {
+ ret = -EFSCORRUPTED;
+ goto fail;
+ }
+
if (dn.data_blkaddr == COMPRESS_ADDR) {
int i;
@@ -1228,7 +1282,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
fio.version = ni.version;
- cic = kmem_cache_zalloc(cic_entry_slab, GFP_NOFS);
+ cic = f2fs_kmem_cache_alloc(cic_entry_slab, GFP_F2FS_ZERO, false, sbi);
if (!cic)
goto out_put_dnode;
@@ -1340,12 +1394,6 @@ out_destroy_crypt:
for (--i; i >= 0; i--)
fscrypt_finalize_bounce_page(&cc->cpages[i]);
- for (i = 0; i < cc->nr_cpages; i++) {
- if (!cc->cpages[i])
- continue;
- f2fs_compress_free_page(cc->cpages[i]);
- cc->cpages[i] = NULL;
- }
out_put_cic:
kmem_cache_free(cic_entry_slab, cic);
out_put_dnode:
@@ -1356,6 +1404,12 @@ out_unlock_op:
else
f2fs_unlock_op(sbi);
out_free:
+ for (i = 0; i < cc->nr_cpages; i++) {
+ if (!cc->cpages[i])
+ continue;
+ f2fs_compress_free_page(cc->cpages[i]);
+ cc->cpages[i] = NULL;
+ }
page_array_free(cc->inode, cc->cpages, cc->nr_cpages);
cc->cpages = NULL;
return -EAGAIN;
@@ -1506,7 +1560,8 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
pgoff_t start_idx = start_idx_of_cluster(cc);
int i;
- dic = kmem_cache_zalloc(dic_entry_slab, GFP_NOFS);
+ dic = f2fs_kmem_cache_alloc(dic_entry_slab, GFP_F2FS_ZERO,
+ false, F2FS_I_SB(cc->inode));
if (!dic)
return ERR_PTR(-ENOMEM);
@@ -1666,6 +1721,30 @@ void f2fs_put_page_dic(struct page *page)
f2fs_put_dic(dic);
}
+/*
+ * check whether cluster blocks are contiguous, and add extent cache entry
+ * only if cluster blocks are logically and physically contiguous.
+ */
+unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn)
+{
+ bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR;
+ int i = compressed ? 1 : 0;
+ block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+ for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) {
+ block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ break;
+ if (first_blkaddr + i - (compressed ? 1 : 0) != blkaddr)
+ return 0;
+ }
+
+ return compressed ? i - 1 : i;
+}
+
const struct address_space_operations f2fs_compress_aops = {
.releasepage = f2fs_release_page,
.invalidatepage = f2fs_invalidate_page,