Merge tag 'f2fs-for-6.10.rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tried to address some performance issues on zoned
  storage such as direct IO and write_hints. In addition, we've migrated
  some IO paths using folio. Meanwhile, there are multiple bug fixes in
  the compression paths, sanity check conditions, and error handlers.

  Enhancements:
   - allow direct io of pinned files for zoned storage
   - assign the write hint per stream by default
   - convert read paths and test_writeback to folio
   - avoid allocating WARM_DATA segment for direct IO

  Bug fixes:
   - fix false alarm on invalid block address
   - fix to add missing iput() in gc_data_segment()
   - fix to release node block count in error path of
     f2fs_new_node_page()
   - compress:
       - don't allow unaligned truncation on released compress inode
       - cover {reserve,release}_compress_blocks() w/ cp_rwsem lock
       - fix error path of inc_valid_block_count()
       - fix to update i_compr_blocks correctly
   - fix block migration when section is not aligned to pow2
   - don't trigger OPU on pinfile for direct IO
   - fix to do sanity check on i_xattr_nid in sanity_check_inode()
   - write missing last sum blk of file pinning section
   - clear writeback when compression failed
   - fix to adjust appropirate defragment pg_end

  As usual, there are several minor code clean-ups, and fixes to manage
  missing corner cases in the error paths"

* tag 'f2fs-for-6.10.rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (50 commits)
  f2fs: initialize last_block_in_bio variable
  f2fs: Add inline to f2fs_build_fault_attr() stub
  f2fs: fix some ambiguous comments
  f2fs: fix to add missing iput() in gc_data_segment()
  f2fs: allow dirty sections with zero valid block for checkpoint disabled
  f2fs: compress: don't allow unaligned truncation on released compress inode
  f2fs: fix to release node block count in error path of f2fs_new_node_page()
  f2fs: compress: fix to cover {reserve,release}_compress_blocks() w/ cp_rwsem lock
  f2fs: compress: fix error path of inc_valid_block_count()
  f2fs: compress: fix typo in f2fs_reserve_compress_blocks()
  f2fs: compress: fix to update i_compr_blocks correctly
  f2fs: check validation of fault attrs in f2fs_build_fault_attr()
  f2fs: fix to limit gc_pin_file_threshold
  f2fs: remove unused GC_FAILURE_PIN
  f2fs: use f2fs_{err,info}_ratelimited() for cleanup
  f2fs: fix block migration when section is not aligned to pow2
  f2fs: zone: fix to don't trigger OPU on pinfile for direct IO
  f2fs: fix to do sanity check on i_xattr_nid in sanity_check_inode()
  f2fs: fix to avoid allocating WARM_DATA segment for direct IO
  f2fs: remove redundant parameter in is_next_segment_free()
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -331,7 +331,7 @@ Date:		January 2018
 Contact:	Jaegeuk Kim <[email protected]>
 Description:	This indicates how many GC can be failed for the pinned
 		file. If it exceeds this, F2FS doesn't guarantee its pinning
-		state. 2048 trials is set by default.
+		state. 2048 trials is set by default, and 65535 as maximum.
 
 What:		/sys/fs/f2fs/<disk>/extension_list
 Date:		February 2018

Documentation/filesystems/f2fs.rst

@@ -774,6 +774,35 @@ In order to identify whether the data in the victim segment are valid or not,
 F2FS manages a bitmap. Each bit represents the validity of a block, and the
 bitmap is composed of a bit stream covering whole blocks in main area.
 
+Write-hint Policy
+-----------------
+
+F2FS sets the whint all the time with the below policy.
+
+===================== ======================== ===================
+User                  F2FS                     Block
+===================== ======================== ===================
+N/A                   META                     WRITE_LIFE_NONE|REQ_META
+N/A                   HOT_NODE                 WRITE_LIFE_NONE
+N/A                   WARM_NODE                WRITE_LIFE_MEDIUM
+N/A                   COLD_NODE                WRITE_LIFE_LONG
+ioctl(COLD)           COLD_DATA                WRITE_LIFE_EXTREME
+extension list        "                        "
+
+-- buffered io
+N/A                   COLD_DATA                WRITE_LIFE_EXTREME
+N/A                   HOT_DATA                 WRITE_LIFE_SHORT
+N/A                   WARM_DATA                WRITE_LIFE_NOT_SET
+
+-- direct io
+WRITE_LIFE_EXTREME    COLD_DATA                WRITE_LIFE_EXTREME
+WRITE_LIFE_SHORT      HOT_DATA                 WRITE_LIFE_SHORT
+WRITE_LIFE_NOT_SET    WARM_DATA                WRITE_LIFE_NOT_SET
+WRITE_LIFE_NONE       "                        WRITE_LIFE_NONE
+WRITE_LIFE_MEDIUM     "                        WRITE_LIFE_MEDIUM
+WRITE_LIFE_LONG       "                        WRITE_LIFE_LONG
+===================== ======================== ===================
+
 Fallocate(2) Policy
 -------------------
 

fs/f2fs/checkpoint.c

@@ -179,22 +179,22 @@ static bool __f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 		break;
 	case META_SIT:
 		if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
-			goto err;
+			goto check_only;
 		break;
 	case META_SSA:
 		if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
 			blkaddr < SM_I(sbi)->ssa_blkaddr))
-			goto err;
+			goto check_only;
 		break;
 	case META_CP:
 		if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
 			blkaddr < __start_cp_addr(sbi)))
-			goto err;
+			goto check_only;
 		break;
 	case META_POR:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 			blkaddr < MAIN_BLKADDR(sbi)))
-			goto err;
+			goto check_only;
 		break;
 	case DATA_GENERIC:
 	case DATA_GENERIC_ENHANCE:
@@ -228,6 +228,7 @@ static bool __f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 	return true;
 err:
 	f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+check_only:
 	return false;
 }
 
@@ -345,7 +346,7 @@ static int __f2fs_write_meta_page(struct page *page,
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-	trace_f2fs_writepage(page, META);
+	trace_f2fs_writepage(page_folio(page), META);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
@@ -492,7 +493,7 @@ long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 static bool f2fs_dirty_meta_folio(struct address_space *mapping,
 		struct folio *folio)
 {
-	trace_f2fs_set_page_dirty(&folio->page, META);
+	trace_f2fs_set_page_dirty(folio, META);
 
 	if (!folio_test_uptodate(folio))
 		folio_mark_uptodate(folio);

fs/f2fs/compress.c

@@ -198,8 +198,8 @@ static int lzo_compress_pages(struct compress_ctx *cc)
 	ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
 					&cc->clen, cc->private);
 	if (ret != LZO_E_OK) {
-		printk_ratelimited("%sF2FS-fs (%s): lzo compress failed, ret:%d\n",
-				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+		f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+				"lzo compress failed, ret:%d", ret);
 		return -EIO;
 	}
 	return 0;
@@ -212,17 +212,15 @@ static int lzo_decompress_pages(struct decompress_io_ctx *dic)
 	ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen,
 						dic->rbuf, &dic->rlen);
 	if (ret != LZO_E_OK) {
-		printk_ratelimited("%sF2FS-fs (%s): lzo decompress failed, ret:%d\n",
-				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"lzo decompress failed, ret:%d", ret);
 		return -EIO;
 	}
 
 	if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) {
-		printk_ratelimited("%sF2FS-fs (%s): lzo invalid rlen:%zu, "
-					"expected:%lu\n", KERN_ERR,
-					F2FS_I_SB(dic->inode)->sb->s_id,
-					dic->rlen,
-					PAGE_SIZE << dic->log_cluster_size);
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"lzo invalid rlen:%zu, expected:%lu",
+				dic->rlen, PAGE_SIZE << dic->log_cluster_size);
 		return -EIO;
 	}
 	return 0;
@@ -294,16 +292,15 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic)
 	ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf,
 						dic->clen, dic->rlen);
 	if (ret < 0) {
-		printk_ratelimited("%sF2FS-fs (%s): lz4 decompress failed, ret:%d\n",
-				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"lz4 decompress failed, ret:%d", ret);
 		return -EIO;
 	}
 
 	if (ret != PAGE_SIZE << dic->log_cluster_size) {
-		printk_ratelimited("%sF2FS-fs (%s): lz4 invalid ret:%d, "
-					"expected:%lu\n", KERN_ERR,
-					F2FS_I_SB(dic->inode)->sb->s_id, ret,
-					PAGE_SIZE << dic->log_cluster_size);
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"lz4 invalid ret:%d, expected:%lu",
+				ret, PAGE_SIZE << dic->log_cluster_size);
 		return -EIO;
 	}
 	return 0;
@@ -350,9 +347,8 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
 
 	stream = zstd_init_cstream(&params, 0, workspace, workspace_size);
 	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n",
-				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
-				__func__);
+		f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+				"%s zstd_init_cstream failed", __func__);
 		kvfree(workspace);
 		return -EIO;
 	}
@@ -390,16 +386,16 @@ static int zstd_compress_pages(struct compress_ctx *cc)
 
 	ret = zstd_compress_stream(stream, &outbuf, &inbuf);
 	if (zstd_is_error(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n",
-				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+		f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+				"%s zstd_compress_stream failed, ret: %d",
 				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
 
 	ret = zstd_end_stream(stream, &outbuf);
 	if (zstd_is_error(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n",
-				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+		f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+				"%s zstd_end_stream returned %d",
 				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
@@ -432,9 +428,8 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
 
 	stream = zstd_init_dstream(max_window_size, workspace, workspace_size);
 	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n",
-				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
-				__func__);
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"%s zstd_init_dstream failed", __func__);
 		kvfree(workspace);
 		return -EIO;
 	}
@@ -469,16 +464,15 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic)
 
 	ret = zstd_decompress_stream(stream, &outbuf, &inbuf);
 	if (zstd_is_error(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n",
-				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"%s zstd_decompress_stream failed, ret: %d",
 				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
 
 	if (dic->rlen != outbuf.pos) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD invalid rlen:%zu, "
-				"expected:%lu\n", KERN_ERR,
-				F2FS_I_SB(dic->inode)->sb->s_id,
+		f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+				"%s ZSTD invalid rlen:%zu, expected:%lu",
 				__func__, dic->rlen,
 				PAGE_SIZE << dic->log_cluster_size);
 		return -EIO;
@@ -1031,6 +1025,31 @@ static void set_cluster_writeback(struct compress_ctx *cc)
 	}
 }
 
+static void cancel_cluster_writeback(struct compress_ctx *cc,
+			struct compress_io_ctx *cic, int submitted)
+{
+	int i;
+
+	/* Wait for submitted IOs. */
+	if (submitted > 1) {
+		f2fs_submit_merged_write(F2FS_I_SB(cc->inode), DATA);
+		while (atomic_read(&cic->pending_pages) !=
+					(cc->valid_nr_cpages - submitted + 1))
+			f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
+	}
+
+	/* Cancel writeback and stay locked. */
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (i < submitted) {
+			inode_inc_dirty_pages(cc->inode);
+			lock_page(cc->rpages[i]);
+		}
+		clear_page_private_gcing(cc->rpages[i]);
+		if (folio_test_writeback(page_folio(cc->rpages[i])))
+			end_page_writeback(cc->rpages[i]);
+	}
+}
+
 static void set_cluster_dirty(struct compress_ctx *cc)
 {
 	int i;
@@ -1232,7 +1251,6 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		.page = NULL,
 		.encrypted_page = NULL,
 		.compressed_page = NULL,
-		.submitted = 0,
 		.io_type = io_type,
 		.io_wbc = wbc,
 		.encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ?
@@ -1358,7 +1376,16 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 			fio.compressed_page = cc->cpages[i - 1];
 
 		cc->cpages[i - 1] = NULL;
+		fio.submitted = 0;
 		f2fs_outplace_write_data(&dn, &fio);
+		if (unlikely(!fio.submitted)) {
+			cancel_cluster_writeback(cc, cic, i);
+
+			/* To call fscrypt_finalize_bounce_page */
+			i = cc->valid_nr_cpages;
+			*submitted = 0;
+			goto out_destroy_crypt;
+		}
 		(*submitted)++;
 unlock_continue:
 		inode_dec_dirty_pages(cc->inode);
@@ -1392,8 +1419,11 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 out_destroy_crypt:
 	page_array_free(cc->inode, cic->rpages, cc->cluster_size);
 
-	for (--i; i >= 0; i--)
+	for (--i; i >= 0; i--) {
+		if (!cc->cpages[i])
+			continue;
 		fscrypt_finalize_bounce_page(&cc->cpages[i]);
+	}
 out_put_cic:
 	kmem_cache_free(cic_entry_slab, cic);
 out_put_dnode:
@@ -1484,7 +1514,7 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 		if (!PageDirty(cc->rpages[i]))
 			goto continue_unlock;
 
-		if (PageWriteback(cc->rpages[i])) {
+		if (folio_test_writeback(page_folio(cc->rpages[i]))) {
 			if (wbc->sync_mode == WB_SYNC_NONE)
 				goto continue_unlock;
 			f2fs_wait_on_page_writeback(cc->rpages[i], DATA, true, true);