f2fs-for-5.7-rc1

In this round, we've mainly focused on fixing bugs and addressing issues in
 recently introduced compression support.
 
 Enhancement:
 - add zstd support, and set LZ4 by default
 - add ioctl() to show # of compressed blocks
 - show mount time in debugfs
 - replace rwsem with spinlock
 - avoid lock contention in DIO reads
 
 Some major bug fixes wrt compression:
 - compressed block count
 - memory access and leak
 - remove obsolete fields
 - flag controls
 
 Other bug fixes and clean ups:
 - fix overflow when handling .flags in inode_info
 - fix SPO issue during resize FS flow
 - fix compression with fsverity enabled
 - potential deadlock when writing compressed pages
 - show missing mount options
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAl6L5f0ACgkQQBSofoJI
 UNImoQ/7BHKpwgpgH/DuydO9ess0XuUgQPQxyj+LE79l0jdBo8FxQZJVNAekx2+h
 ANTDHjsgqry6xuczOJXzFhECoOrCqZuffrkQM1p3owfzOH9Wrx6aiOomFBJyk/WB
 kXAY7LDPUwGF5uDB8tvVhM082qLXOlP0coO57f9Ip/OpaG8YOkti+KbcOKJrJ9o3
 63IAzu89D/9XJw8834rDSersiEenSJm3jLC12uOxgXMzjDb1Ul1JH0P51gEu6g6O
 3df5tiGJcFfaKVVWPHG+UEfav6mvi28+zU9f+dSmL0Wvb8dIqSgUf6ty8KCuRBYw
 kQYi+E0G1dcGi99AitCOrFxzY+oEo/A5wq2HDI6RkNlu6krD8qYNyWcMbP7dNHnU
 /5BVN+5d78iR1vKZpTo4X6dojf6B21Tn/OmABSZ5d7B6pI2fY5bjy2WgSLSY7YvP
 A6sepb9RAAGvpKvvkHI7gYwDKFMel+vfD6em1SKH5iKaDC0rJTUDUy8PTz/qMPBS
 vMn396dLx+TzTa0dZUuSF8NNk6sPZEReC3AuMNAIPSKiuD7tatRxvutHeEg5ktrr
 ggOQB67MfKjPMBKmgMIm6XMuILcCGIB1MqbPRlyKtC6rjdMPIKKOfeHJlLFmYwfF
 gqvCIFlW4DlxHpHH+LbUFKoUA3zofltL91SHUVATJjmiZIT2pqQ=
 =FVxq
 -----END PGP SIGNATURE-----

Merge tag 'f2fs-for-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've mainly focused on fixing bugs and addressing
  issues in recently introduced compression support.

  Enhancement:
   - add zstd support, and set LZ4 by default
   - add ioctl() to show # of compressed blocks
   - show mount time in debugfs
   - replace rwsem with spinlock
   - avoid lock contention in DIO reads

  Some major bug fixes wrt compression:
   - compressed block count
   - memory access and leak
   - remove obsolete fields
   - flag controls

  Other bug fixes and clean ups:
   - fix overflow when handling .flags in inode_info
   - fix SPO issue during resize FS flow
   - fix compression with fsverity enabled
   - potential deadlock when writing compressed pages
   - show missing mount options"

* tag 'f2fs-for-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (66 commits)
  f2fs: keep inline_data when compression conversion
  f2fs: fix to disable compression on directory
  f2fs: add missing CONFIG_F2FS_FS_COMPRESSION
  f2fs: switch discard_policy.timeout to bool type
  f2fs: fix to verify tpage before releasing in f2fs_free_dic()
  f2fs: show compression in statx
  f2fs: clean up dic->tpages assignment
  f2fs: compress: support zstd compress algorithm
  f2fs: compress: add .{init,destroy}_decompress_ctx callback
  f2fs: compress: fix to call missing destroy_compress_ctx()
  f2fs: change default compression algorithm
  f2fs: clean up {cic,dic}.ref handling
  f2fs: fix to use f2fs_readpage_limit() in f2fs_read_multi_pages()
  f2fs: xattr.h: Make stub helpers inline
  f2fs: fix to avoid double unlock
  f2fs: fix potential .flags overflow on 32bit architecture
  f2fs: fix NULL pointer dereference in f2fs_verity_work()
  f2fs: fix to clear PG_error if fsverity failed
  f2fs: don't call fscrypt_get_encryption_info() explicitly in f2fs_tmpfile()
  f2fs: don't trigger data flush in foreground operation
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -318,3 +318,8 @@ Date:		September 2019
 Contact:	"Hridya Valsaraju" <hridya@google.com>
 Description:	Average number of valid blocks.
 		Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/mounted_time_sec
+Date:		February 2020
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Show the mounted time in secs of this partition.

Documentation/filesystems/f2fs.rst

@@ -243,8 +243,8 @@ checkpoint=%s[:%u[%]]  Set to "disable" to turn off checkpointing. Set to "enabl
                        hide up to all remaining free space. The actual space that
                        would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable
                        This space is reclaimed once checkpoint=enable.
-compress_algorithm=%s  Control compress algorithm, currently f2fs supports "lzo"
+compress_algorithm=%s  Control compress algorithm, currently f2fs supports "lzo",
-                       and "lz4" algorithm.
+                       "lz4" and "zstd" algorithm.
 compress_log_size=%u   Support configuring compress cluster size, the size will
                        be 4KB * (1 << %u), 16KB is minimum size, also it's
                        default size.

fs/f2fs/Kconfig

@@ -118,3 +118,12 @@ config F2FS_FS_LZ4
 	default y
 	help
 	  Support LZ4 compress algorithm, if unsure, say Y.
+
+config F2FS_FS_ZSTD
+	bool "ZSTD compression support"
+	depends on F2FS_FS_COMPRESSION
+	select ZSTD_COMPRESS
+	select ZSTD_DECOMPRESS
+	default y
+	help
+	  Support ZSTD compress algorithm, if unsure, say Y.

fs/f2fs/checkpoint.c

@@ -50,9 +50,6 @@ repeat:
 	return page;
 }
 
-/*
- * We guarantee no failure on the returned page.
- */
 static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 							bool is_meta)
 {
@@ -206,7 +203,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 }
 
 /*
- * Readahead CP/NAT/SIT/SSA pages
+ * Readahead CP/NAT/SIT/SSA/POR pages
  */
 int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 							int type, bool sync)
@@ -898,7 +895,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 	/*
 	 * Finding out valid cp block involves read both
-	 * sets( cp pack1 and cp pack 2)
+	 * sets( cp pack 1 and cp pack 2)
 	 */
 	cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
 	cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);
@@ -1250,20 +1247,20 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
 	f2fs_unlock_all(sbi);
 }
 
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
 {
 	DEFINE_WAIT(wait);
 
 	for (;;) {
 		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		if (!get_pages(sbi, F2FS_WB_CP_DATA))
+		if (!get_pages(sbi, type))
 			break;
 
 		if (unlikely(f2fs_cp_error(sbi)))
 			break;
 
-		io_schedule_timeout(5*HZ);
+		io_schedule_timeout(DEFAULT_IO_TIMEOUT);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
@@ -1301,10 +1298,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	else
 		__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
-	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
-		is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
 		__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
+	if (is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
+		__set_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
+	else
+		__clear_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
+
 	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
 		__set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
 	else
@@ -1384,13 +1385,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* Flush all the NAT/SIT pages */
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
-	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
-					!f2fs_cp_error(sbi));
 
-	/*
+	/* start to update checkpoint, cp ver is already updated previously */
-	 * modify checkpoint
-	 * version number is already updated
-	 */
 	ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
 	ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
 	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
@@ -1493,11 +1489,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* Here, we have one bio having CP pack except cp pack 2 page */
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
-	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
+	/* Wait for all dirty meta pages to be submitted for IO */
-					!f2fs_cp_error(sbi));
+	f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META);
 
 	/* wait for previous submitted meta pages writeback */
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	/* flush all device cache */
 	err = f2fs_flush_device_cache(sbi);
@@ -1506,7 +1502,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* barrier and flush checkpoint cp pack 2 page if it can */
 	commit_checkpoint(sbi, ckpt, start_blk);
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	/*
 	 * invalidate intermediate page cache borrowed from meta inode which are
@@ -1543,9 +1539,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
 }
 
-/*
- * We guarantee that this checkpoint procedure will not fail.
- */
 int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -1613,7 +1606,6 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	f2fs_flush_sit_entries(sbi, cpc);
 
-	/* unlock all the fs_lock[] in do_checkpoint() */
 	err = do_checkpoint(sbi, cpc);
 	if (err)
 		f2fs_release_discard_addrs(sbi);
@@ -1626,7 +1618,7 @@ stop:
 	if (cpc->reason & CP_RECOVERY)
 		f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver);
 
-	/* do checkpoint periodically */
+	/* update CP_TIME to trigger checkpoint periodically */
 	f2fs_update_time(sbi, CP_TIME);
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 out:

fs/f2fs/compress.c

@@ -11,6 +11,7 @@
 #include <linux/backing-dev.h>
 #include <linux/lzo.h>
 #include <linux/lz4.h>
+#include <linux/zstd.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -20,6 +21,8 @@ struct f2fs_compress_ops {
 	int (*init_compress_ctx)(struct compress_ctx *cc);
 	void (*destroy_compress_ctx)(struct compress_ctx *cc);
 	int (*compress_pages)(struct compress_ctx *cc);
+	int (*init_decompress_ctx)(struct decompress_io_ctx *dic);
+	void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic);
 	int (*decompress_pages)(struct decompress_io_ctx *dic);
 };
 
@@ -52,7 +55,7 @@ bool f2fs_is_compressed_page(struct page *page)
 }
 
 static void f2fs_set_compressed_page(struct page *page,
-		struct inode *inode, pgoff_t index, void *data, refcount_t *r)
+		struct inode *inode, pgoff_t index, void *data)
 {
 	SetPagePrivate(page);
 	set_page_private(page, (unsigned long)data);
@@ -60,8 +63,6 @@ static void f2fs_set_compressed_page(struct page *page,
 	/* i_crypto_info and iv index */
 	page->index = index;
 	page->mapping = inode->i_mapping;
-	if (r)
-		refcount_inc(r);
 }
 
 static void f2fs_put_compressed_page(struct page *page)
@@ -291,6 +292,165 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = {
 };
 #endif
 
+#ifdef CONFIG_F2FS_FS_ZSTD
+#define F2FS_ZSTD_DEFAULT_CLEVEL	1
+
+static int zstd_init_compress_ctx(struct compress_ctx *cc)
+{
+	ZSTD_parameters params;
+	ZSTD_CStream *stream;
+	void *workspace;
+	unsigned int workspace_size;
+
+	params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen, 0);
+	workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams);
+
+	workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
+					workspace_size, GFP_NOFS);
+	if (!workspace)
+		return -ENOMEM;
+
+	stream = ZSTD_initCStream(params, 0, workspace, workspace_size);
+	if (!stream) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n",
+				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+				__func__);
+		kvfree(workspace);
+		return -EIO;
+	}
+
+	cc->private = workspace;
+	cc->private2 = stream;
+
+	cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE;
+	return 0;
+}
+
+static void zstd_destroy_compress_ctx(struct compress_ctx *cc)
+{
+	kvfree(cc->private);
+	cc->private = NULL;
+	cc->private2 = NULL;
+}
+
+static int zstd_compress_pages(struct compress_ctx *cc)
+{
+	ZSTD_CStream *stream = cc->private2;
+	ZSTD_inBuffer inbuf;
+	ZSTD_outBuffer outbuf;
+	int src_size = cc->rlen;
+	int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE;
+	int ret;
+
+	inbuf.pos = 0;
+	inbuf.src = cc->rbuf;
+	inbuf.size = src_size;
+
+	outbuf.pos = 0;
+	outbuf.dst = cc->cbuf->cdata;
+	outbuf.size = dst_size;
+
+	ret = ZSTD_compressStream(stream, &outbuf, &inbuf);
+	if (ZSTD_isError(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
+				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+				__func__, ZSTD_getErrorCode(ret));
+		return -EIO;
+	}
+
+	ret = ZSTD_endStream(stream, &outbuf);
+	if (ZSTD_isError(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n",
+				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+				__func__, ZSTD_getErrorCode(ret));
+		return -EIO;
+	}
+
+	cc->clen = outbuf.pos;
+	return 0;
+}
+
+static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
+{
+	ZSTD_DStream *stream;
+	void *workspace;
+	unsigned int workspace_size;
+
+	workspace_size = ZSTD_DStreamWorkspaceBound(MAX_COMPRESS_WINDOW_SIZE);
+
+	workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode),
+					workspace_size, GFP_NOFS);
+	if (!workspace)
+		return -ENOMEM;
+
+	stream = ZSTD_initDStream(MAX_COMPRESS_WINDOW_SIZE,
+					workspace, workspace_size);
+	if (!stream) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n",
+				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
+				__func__);
+		kvfree(workspace);
+		return -EIO;
+	}
+
+	dic->private = workspace;
+	dic->private2 = stream;
+
+	return 0;
+}
+
+static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic)
+{
+	kvfree(dic->private);
+	dic->private = NULL;
+	dic->private2 = NULL;
+}
+
+static int zstd_decompress_pages(struct decompress_io_ctx *dic)
+{
+	ZSTD_DStream *stream = dic->private2;
+	ZSTD_inBuffer inbuf;
+	ZSTD_outBuffer outbuf;
+	int ret;
+
+	inbuf.pos = 0;
+	inbuf.src = dic->cbuf->cdata;
+	inbuf.size = dic->clen;
+
+	outbuf.pos = 0;
+	outbuf.dst = dic->rbuf;
+	outbuf.size = dic->rlen;
+
+	ret = ZSTD_decompressStream(stream, &outbuf, &inbuf);
+	if (ZSTD_isError(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
+				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
+				__func__, ZSTD_getErrorCode(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,
+				__func__, dic->rlen,
+				PAGE_SIZE << dic->log_cluster_size);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_zstd_ops = {
+	.init_compress_ctx	= zstd_init_compress_ctx,
+	.destroy_compress_ctx	= zstd_destroy_compress_ctx,
+	.compress_pages		= zstd_compress_pages,
+	.init_decompress_ctx	= zstd_init_decompress_ctx,
+	.destroy_decompress_ctx	= zstd_destroy_decompress_ctx,
+	.decompress_pages	= zstd_decompress_pages,
+};
+#endif
+
 static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
 #ifdef CONFIG_F2FS_FS_LZO
 	&f2fs_lzo_ops,
@@ -302,6 +462,11 @@ static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
 #else
 	NULL,
 #endif
+#ifdef CONFIG_F2FS_FS_ZSTD
+	&f2fs_zstd_ops,
+#else
+	NULL,
+#endif
 };
 
 bool f2fs_is_compress_backend_ready(struct inode *inode)
@@ -334,9 +499,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
 				cc->cluster_size, fi->i_compress_algorithm);
 
-	ret = cops->init_compress_ctx(cc);
+	if (cops->init_compress_ctx) {
-	if (ret)
+		ret = cops->init_compress_ctx(cc);
-		goto out;
+		if (ret)
+			goto out;
+	}
 
 	max_len = COMPRESS_HEADER_SIZE + cc->clen;
 	cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE);
@@ -380,21 +547,27 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	}
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
-	cc->cbuf->chksum = cpu_to_le32(0);
 
 	for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
 		cc->cbuf->reserved[i] = cpu_to_le32(0);
 
+	nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
+
+	/* zero out any unused part of the last page */
+	memset(&cc->cbuf->cdata[cc->clen], 0,
+	       (nr_cpages * PAGE_SIZE) - (cc->clen + COMPRESS_HEADER_SIZE));
+
 	vunmap(cc->cbuf);
 	vunmap(cc->rbuf);
 
-	nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
-
 	for (i = nr_cpages; i < cc->nr_cpages; i++) {
 		f2fs_put_compressed_page(cc->cpages[i]);
 		cc->cpages[i] = NULL;
 	}
 
+	if (cops->destroy_compress_ctx)
+		cops->destroy_compress_ctx(cc);
+
 	cc->nr_cpages = nr_cpages;
 
 	trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
@@ -413,7 +586,8 @@ out_free_cpages:
 	kfree(cc->cpages);
 	cc->cpages = NULL;
 destroy_compress_ctx:
-	cops->destroy_compress_ctx(cc);
+	if (cops->destroy_compress_ctx)
+		cops->destroy_compress_ctx(cc);
 out:
 	trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
 							cc->clen, ret);
@@ -447,10 +621,16 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 		goto out_free_dic;
 	}
 
+	if (cops->init_decompress_ctx) {
+		ret = cops->init_decompress_ctx(dic);
+		if (ret)
+			goto out_free_dic;
+	}
+
 	dic->rbuf = vmap(dic->tpages, dic->cluster_size, VM_MAP, PAGE_KERNEL);
 	if (!dic->rbuf) {
 		ret = -ENOMEM;
-		goto out_free_dic;
+		goto destroy_decompress_ctx;
 	}
 
 	dic->cbuf = vmap(dic->cpages, dic->nr_cpages, VM_MAP, PAGE_KERNEL_RO);
@@ -473,7 +653,12 @@ out_vunmap_cbuf:
 	vunmap(dic->cbuf);
 out_vunmap_rbuf:
 	vunmap(dic->rbuf);
+destroy_decompress_ctx:
+	if (cops->destroy_decompress_ctx)
+		cops->destroy_decompress_ctx(dic);
 out_free_dic:
+	if (verity)
+		refcount_set(&dic->ref, dic->nr_cpages);
 	if (!verity)
 		f2fs_decompress_end_io(dic->rpages, dic->cluster_size,
 								ret, false);
@@ -532,8 +717,7 @@ static bool __cluster_may_compress(struct compress_ctx *cc)
 	return true;
 }
 
-/* return # of compressed block addresses */
+static int __f2fs_cluster_blocks(struct compress_ctx *cc, bool compr)
-static int f2fs_compressed_blocks(struct compress_ctx *cc)
 {
 	struct dnode_of_data dn;
 	int ret;
@@ -554,10 +738,15 @@ static int f2fs_compressed_blocks(struct compress_ctx *cc)
 		for (i = 1; i < cc->cluster_size; i++) {
 			block_t blkaddr;
 
-			blkaddr = datablock_addr(dn.inode,
+			blkaddr = data_blkaddr(dn.inode,
 					dn.node_page, dn.ofs_in_node + i);
-			if (blkaddr != NULL_ADDR)
+			if (compr) {
-				ret++;
+				if (__is_valid_data_blkaddr(blkaddr))
+					ret++;
+			} else {
+				if (blkaddr != NULL_ADDR)
+					ret++;
+			}
 		}
 	}
 fail:
@@ -565,6 +754,18 @@ fail:
 	return ret;
 }
 
+/* return # of compressed blocks in compressed cluster */
+static int f2fs_compressed_blocks(struct compress_ctx *cc)
+{
+	return __f2fs_cluster_blocks(cc, true);
+}
+
+/* return # of valid blocks in compressed cluster */
+static int f2fs_cluster_blocks(struct compress_ctx *cc, bool compr)
+{
+	return __f2fs_cluster_blocks(cc, false);
+}
+
 int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
 {
 	struct compress_ctx cc = {
@@ -574,7 +775,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
 		.cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
 	};
 
-	return f2fs_compressed_blocks(&cc);
+	return f2fs_cluster_blocks(&cc, false);
 }
 
 static bool cluster_may_compress(struct compress_ctx *cc)
@@ -623,7 +824,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 	bool prealloc;
 
 retry:
-	ret = f2fs_compressed_blocks(cc);
+	ret = f2fs_cluster_blocks(cc, false);
 	if (ret <= 0)
 		return ret;
 
@@ -653,7 +854,7 @@ retry:
 		struct bio *bio = NULL;
 
 		ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size,
-						&last_block_in_bio, false);
+					&last_block_in_bio, false, true);
 		f2fs_destroy_compress_ctx(cc);
 		if (ret)
 			goto release_pages;
@@ -772,7 +973,6 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		.encrypted_page = NULL,
 		.compressed_page = NULL,
 		.submitted = false,
-		.need_lock = LOCK_RETRY,
 		.io_type = io_type,
 		.io_wbc = wbc,
 		.encrypted = f2fs_encrypted_file(cc->inode),
@@ -785,16 +985,17 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 	loff_t psize;
 	int i, err;
 
-	set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+	if (!f2fs_trylock_op(sbi))
+		return -EAGAIN;
 
-	f2fs_lock_op(sbi);
+	set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
 
 	err = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
 	if (err)
 		goto out_unlock_op;
 
 	for (i = 0; i < cc->cluster_size; i++) {
-		if (datablock_addr(dn.inode, dn.node_page,
+		if (data_blkaddr(dn.inode, dn.node_page,
 					dn.ofs_in_node + i) == NULL_ADDR)
 			goto out_put_dnode;
 	}
@@ -813,7 +1014,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	cic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
 	cic->inode = inode;
-	refcount_set(&cic->ref, 1);
+	refcount_set(&cic->ref, cc->nr_cpages);
 	cic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
 			cc->log_cluster_size, GFP_NOFS);
 	if (!cic->rpages)
@@ -823,8 +1024,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	for (i = 0; i < cc->nr_cpages; i++) {
 		f2fs_set_compressed_page(cc->cpages[i], inode,
-					cc->rpages[i + 1]->index,
+					cc->rpages[i + 1]->index, cic);
-					cic, i ? &cic->ref : NULL);
 		fio.compressed_page = cc->cpages[i];
 		if (fio.encrypted) {
 			fio.page = cc->rpages[i + 1];
@@ -843,9 +1043,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 	for (i = 0; i < cc->cluster_size; i++, dn.ofs_in_node++) {
 		block_t blkaddr;
 
-		blkaddr = datablock_addr(dn.inode, dn.node_page,
+		blkaddr = f2fs_data_blkaddr(&dn);
-							dn.ofs_in_node);
+		fio.page = cc->rpages[i];
-		fio.page = cic->rpages[i];
 		fio.old_blkaddr = blkaddr;
 
 		/* cluster header */
@@ -895,10 +1094,10 @@ unlock_continue:
 	f2fs_put_dnode(&dn);
 	f2fs_unlock_op(sbi);
 
-	down_write(&fi->i_sem);
+	spin_lock(&fi->i_size_lock);
 	if (fi->last_disk_size < psize)
 		fi->last_disk_size = psize;
-	up_write(&fi->i_sem);
+	spin_unlock(&fi->i_size_lock);
 
 	f2fs_put_rpages(cc);
 	f2fs_destroy_compress_ctx(cc);
@@ -984,24 +1183,30 @@ retry_write:
 				unlock_page(cc->rpages[i]);
 				ret = 0;
 			} else if (ret == -EAGAIN) {
+				/*
+				 * for quota file, just redirty left pages to
+				 * avoid deadlock caused by cluster update race
+				 * from foreground operation.
+				 */
+				if (IS_NOQUOTA(cc->inode)) {
+					err = 0;
+					goto out_err;
+				}
 				ret = 0;
 				cond_resched();
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
 				lock_page(cc->rpages[i]);
 				clear_page_dirty_for_io(cc->rpages[i]);
 				goto retry_write;
 			}
 			err = ret;
-			goto out_fail;
+			goto out_err;
 		}
 
 		*submitted += _submitted;
 	}
 	return 0;
-
-out_fail:
-	/* TODO: revoke partially updated block addresses */
-	BUG_ON(compr_blocks);
 out_err:
 	for (++i; i < cc->cluster_size; i++) {
 		if (!cc->rpages[i])
@@ -1069,7 +1274,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
 
 	dic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
 	dic->inode = cc->inode;
-	refcount_set(&dic->ref, 1);
+	refcount_set(&dic->ref, cc->nr_cpages);
 	dic->cluster_idx = cc->cluster_idx;
 	dic->cluster_size = cc->cluster_size;
 	dic->log_cluster_size = cc->log_cluster_size;
@@ -1093,8 +1298,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
 			goto out_free;
 
 		f2fs_set_compressed_page(page, cc->inode,
-					start_idx + i + 1,
+					start_idx + i + 1, dic);
-					dic, i ? &dic->ref : NULL);
 		dic->cpages[i] = page;
 	}
 
@@ -1104,20 +1308,16 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
 		goto out_free;
 
 	for (i = 0; i < dic->cluster_size; i++) {
-		if (cc->rpages[i])
+		if (cc->rpages[i]) {
+			dic->tpages[i] = cc->rpages[i];
 			continue;
+		}
 
 		dic->tpages[i] = f2fs_grab_page();
 		if (!dic->tpages[i])
 			goto out_free;
 	}
 
-	for (i = 0; i < dic->cluster_size; i++) {
-		if (dic->tpages[i])
-			continue;
-		dic->tpages[i] = cc->rpages[i];
-	}
-
 	return dic;
 
 out_free:
@@ -1133,7 +1333,10 @@ void f2fs_free_dic(struct decompress_io_ctx *dic)
 		for (i = 0; i < dic->cluster_size; i++) {
 			if (dic->rpages[i])
 				continue;
-			f2fs_put_page(dic->tpages[i], 1);
+			if (!dic->tpages[i])
+				continue;
+			unlock_page(dic->tpages[i]);
+			put_page(dic->tpages[i]);
 		}
 		kfree(dic->tpages);
 	}
@@ -1162,15 +1365,17 @@ void f2fs_decompress_end_io(struct page **rpages,
 		if (!rpage)
 			continue;
 
-		if (err || PageError(rpage)) {
+		if (err || PageError(rpage))
-			ClearPageUptodate(rpage);
+			goto clear_uptodate;
-			ClearPageError(rpage);
+
-		} else {
+		if (!verity || fsverity_verify_page(rpage)) {
-			if (!verity || fsverity_verify_page(rpage))
+			SetPageUptodate(rpage);
-				SetPageUptodate(rpage);
+			goto unlock;
-			else
-				SetPageError(rpage);
 		}
+clear_uptodate:
+		ClearPageUptodate(rpage);
+		ClearPageError(rpage);
+unlock:
 		unlock_page(rpage);
 	}
 }

fs/f2fs/data.c

@@ -54,17 +54,13 @@ static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
 }
 
-struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail)
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio)
 {
-	struct bio *bio;
+	if (noio) {
-
-	if (no_fail) {
 		/* No failure on bio allocation */
-		bio = __f2fs_bio_alloc(GFP_NOIO, npages);
+		return __f2fs_bio_alloc(GFP_NOIO, npages);
-		if (!bio)
-			bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
-		return bio;
 	}
+
 	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
 		f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
 		return NULL;
@@ -143,6 +139,8 @@ static void __read_end_io(struct bio *bio, bool compr, bool verity)
 			f2fs_decompress_pages(bio, page, verity);
 			continue;
 		}
+		if (verity)
+			continue;
 #endif
 
 		/* PG_error was set if any post_read step failed */
@@ -191,12 +189,38 @@ static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size)
 
 static void f2fs_verify_bio(struct bio *bio)
 {
-	struct page *page = bio_first_page_all(bio);
+	struct bio_vec *bv;
-	struct decompress_io_ctx *dic =
+	struct bvec_iter_all iter_all;
-			(struct decompress_io_ctx *)page_private(page);
 
-	f2fs_verify_pages(dic->rpages, dic->cluster_size);
+	bio_for_each_segment_all(bv, bio, iter_all) {
-	f2fs_free_dic(dic);
+		struct page *page = bv->bv_page;
+		struct decompress_io_ctx *dic;
+
+		dic = (struct decompress_io_ctx *)page_private(page);
+
+		if (dic) {
+			if (refcount_dec_not_one(&dic->ref))
+				continue;
+			f2fs_verify_pages(dic->rpages,
+						dic->cluster_size);
+			f2fs_free_dic(dic);
+			continue;
+		}
+
+		if (bio->bi_status || PageError(page))
+			goto clear_uptodate;
+
+		if (fsverity_verify_page(page)) {
+			SetPageUptodate(page);
+			goto unlock;
+		}
+clear_uptodate:
+		ClearPageUptodate(page);
+		ClearPageError(page);
+unlock:
+		dec_page_count(F2FS_P_SB(page), __read_io_type(page));
+		unlock_page(page);
+	}
 }
 #endif
 
@@ -364,9 +388,6 @@ static void f2fs_write_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-/*
- * Return true, if pre_bio's bdev is same as its target device.
- */
 struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 				block_t blk_addr, struct bio *bio)
 {
@@ -403,6 +424,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
 	return 0;
 }
 
+/*
+ * Return true, if pre_bio's bdev is same as its target device.
+ */
 static bool __same_bdev(struct f2fs_sb_info *sbi,
 				block_t blk_addr, struct bio *bio)
 {
@@ -410,9 +434,6 @@ static bool __same_bdev(struct f2fs_sb_info *sbi,
 	return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno;
 }
 
-/*
- * Low-level block read/write IO operations.
- */
 static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
@@ -445,7 +466,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 		if (type != DATA && type != NODE)
 			goto submit_io;
 
-		if (test_opt(sbi, LFS) && current->plug)
+		if (f2fs_lfs_mode(sbi) && current->plug)
 			blk_finish_plug(current->plug);
 
 		if (F2FS_IO_ALIGNED(sbi))
@@ -928,14 +949,15 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
 
 static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 				      unsigned nr_pages, unsigned op_flag,
-				      pgoff_t first_idx)
+				      pgoff_t first_idx, bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
 	struct bio_post_read_ctx *ctx;
 	unsigned int post_read_steps = 0;
 
-	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
+	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES),
+								for_write);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 	f2fs_target_device(sbi, blkaddr, bio);
@@ -970,12 +992,12 @@ static void f2fs_release_read_bio(struct bio *bio)
 
 /* This can handle encryption stuffs */
 static int f2fs_submit_page_read(struct inode *inode, struct page *page,
-							block_t blkaddr)
+						block_t blkaddr, bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
 
-	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index);
+	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write);
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -1047,8 +1069,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 	f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true);
 
 	for (; count > 0; dn->ofs_in_node++) {
-		block_t blkaddr = datablock_addr(dn->inode,
+		block_t blkaddr = f2fs_data_blkaddr(dn);
-					dn->node_page, dn->ofs_in_node);
 		if (blkaddr == NULL_ADDR) {
 			dn->data_blkaddr = NEW_ADDR;
 			__set_data_blkaddr(dn);
@@ -1162,7 +1183,7 @@ got_it:
 		return page;
 	}
 
-	err = f2fs_submit_page_read(inode, page, dn.data_blkaddr);
+	err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write);
 	if (err)
 		goto put_err;
 	return page;
@@ -1300,8 +1321,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 	if (err)
 		return err;
 
-	dn->data_blkaddr = datablock_addr(dn->inode,
+	dn->data_blkaddr = f2fs_data_blkaddr(dn);
-				dn->node_page, dn->ofs_in_node);
 	if (dn->data_blkaddr != NULL_ADDR)
 		goto alloc;
 
@@ -1388,13 +1408,9 @@ void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
 }
 
 /*
- * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
+ * f2fs_map_blocks() tries to find or build mapping relationship which
- * f2fs_map_blocks structure.
+ * maps continuous logical blocks to physical blocks, and return such
- * If original data blocks are allocated, then give them to blockdev.
+ * info via f2fs_map_blocks structure.
- * Otherwise,
- *     a. preallocate requested block addresses
- *     b. do not use extent cache for better performance
- *     c. give the block addresses to blockdev
  */
 int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 						int create, int flag)
@@ -1422,7 +1438,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	end = pgofs + maxblocks;
 
 	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
-		if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
+		if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO &&
 							map->m_may_create)
 			goto next_dnode;
 
@@ -1467,7 +1483,7 @@ next_dnode:
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 next_block:
-	blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
+	blkaddr = f2fs_data_blkaddr(&dn);
 
 	if (__is_valid_data_blkaddr(blkaddr) &&
 		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
@@ -1477,7 +1493,7 @@ next_block:
 
 	if (__is_valid_data_blkaddr(blkaddr)) {
 		/* use out-place-update for driect IO under LFS mode */
-		if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
+		if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO &&
 							map->m_may_create) {
 			err = __allocate_data_block(&dn, map->m_seg_type);
 			if (err)
@@ -1980,7 +1996,8 @@ submit_and_realloc:
 	}
 	if (bio == NULL) {
 		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
-				is_readahead ? REQ_RAHEAD : 0, page->index);
+				is_readahead ? REQ_RAHEAD : 0, page->index,
+				false);
 		if (IS_ERR(bio)) {
 			ret = PTR_ERR(bio);
 			bio = NULL;
@@ -2015,7 +2032,7 @@ out:
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 				unsigned nr_pages, sector_t *last_block_in_bio,
-				bool is_readahead)
+				bool is_readahead, bool for_write)
 {
 	struct dnode_of_data dn;
 	struct inode *inode = cc->inode;
@@ -2031,7 +2048,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 
 	f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
 
-	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+	last_block_in_file = (f2fs_readpage_limit(inode) +
+					blocksize - 1) >> blkbits;
 
 	/* get rid of pages beyond EOF */
 	for (i = 0; i < cc->cluster_size; i++) {
@@ -2067,7 +2085,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 	for (i = 1; i < cc->cluster_size; i++) {
 		block_t blkaddr;
 
-		blkaddr = datablock_addr(dn.inode, dn.node_page,
+		blkaddr = data_blkaddr(dn.inode, dn.node_page,
 						dn.ofs_in_node + i);
 
 		if (!__is_valid_data_blkaddr(blkaddr))
@@ -2096,7 +2114,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 		struct page *page = dic->cpages[i];
 		block_t blkaddr;
 
-		blkaddr = datablock_addr(dn.inode, dn.node_page,
+		blkaddr = data_blkaddr(dn.inode, dn.node_page,
 						dn.ofs_in_node + i + 1);
 
 		if (bio && !page_is_mergeable(sbi, bio,
@@ -2109,7 +2127,7 @@ submit_and_realloc:
 		if (!bio) {
 			bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
 					is_readahead ? REQ_RAHEAD : 0,
-					page->index);
+					page->index, for_write);
 			if (IS_ERR(bio)) {
 				ret = PTR_ERR(bio);
 				bio = NULL;
@@ -2210,7 +2228,7 @@ int f2fs_mpage_readpages(struct address_space *mapping,
 				ret = f2fs_read_multi_pages(&cc, &bio,
 							max_nr_pages,
 							&last_block_in_bio,
-							is_readahead);
+							is_readahead, false);
 				f2fs_destroy_compress_ctx(&cc);
 				if (ret)
 					goto set_error_page;
@@ -2253,7 +2271,7 @@ next_page:
 				ret = f2fs_read_multi_pages(&cc, &bio,
 							max_nr_pages,
 							&last_block_in_bio,
-							is_readahead);
+							is_readahead, false);
 				f2fs_destroy_compress_ctx(&cc);
 			}
 		}
@@ -2326,7 +2344,7 @@ retry_encrypt:
 		/* flush pending IOs and wait for a while in the ENOMEM case */
 		if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
 			f2fs_flush_merged_writes(fio->sbi);
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 			gfp_flags |= __GFP_NOFAIL;
 			goto retry_encrypt;
 		}
@@ -2397,7 +2415,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
-	if (test_opt(sbi, LFS))
+	if (f2fs_lfs_mode(sbi))
 		return true;
 	if (S_ISDIR(inode->i_mode))
 		return true;
@@ -2647,10 +2665,10 @@ write:
 	if (err) {
 		file_set_keep_isize(inode);
 	} else {
-		down_write(&F2FS_I(inode)->i_sem);
+		spin_lock(&F2FS_I(inode)->i_size_lock);
 		if (F2FS_I(inode)->last_disk_size < psize)
 			F2FS_I(inode)->last_disk_size = psize;
-		up_write(&F2FS_I(inode)->i_sem);
+		spin_unlock(&F2FS_I(inode)->i_size_lock);
 	}
 
 done:
@@ -2917,7 +2935,7 @@ result:
 					if (wbc->sync_mode == WB_SYNC_ALL) {
 						cond_resched();
 						congestion_wait(BLK_RW_ASYNC,
-								HZ/50);
+							DEFAULT_IO_TIMEOUT);
 						goto retry_write;
 					}
 					goto next;
@@ -2973,15 +2991,17 @@ next:
 static inline bool __should_serialize_io(struct inode *inode,
 					struct writeback_control *wbc)
 {
-	if (!S_ISREG(inode->i_mode))
-		return false;
-	if (f2fs_compressed_file(inode))
-		return true;
-	if (IS_NOQUOTA(inode))
-		return false;
 	/* to avoid deadlock in path of data flush */
 	if (F2FS_I(inode)->cp_task)
 		return false;
+
+	if (!S_ISREG(inode->i_mode))
+		return false;
+	if (IS_NOQUOTA(inode))
+		return false;
+
+	if (f2fs_compressed_file(inode))
+		return true;
 	if (wbc->sync_mode != WB_SYNC_ALL)
 		return true;
 	if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
@@ -3283,7 +3303,7 @@ repeat:
 			err = -EFSCORRUPTED;
 			goto fail;
 		}
-		err = f2fs_submit_page_read(inode, page, blkaddr);
+		err = f2fs_submit_page_read(inode, page, blkaddr, true);
 		if (err)
 			goto fail;
 
@@ -3464,7 +3484,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
 			iter, rw == WRITE ? get_data_block_dio_write :
 			get_data_block_dio, NULL, f2fs_dio_submit_bio,
-			DIO_LOCKING | DIO_SKIP_HOLES);
+			rw == WRITE ? DIO_LOCKING | DIO_SKIP_HOLES :
+			DIO_SKIP_HOLES);
 
 	if (do_opu)
 		up_read(&fi->i_gc_rwsem[READ]);
@@ -3861,7 +3882,7 @@ void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi)
 
 int __init f2fs_init_bio_entry_cache(void)
 {
-	bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab",
+	bio_entry_slab = f2fs_kmem_cache_create("f2fs_bio_entry_slab",
 			sizeof(struct bio_entry));
 	if (!bio_entry_slab)
 		return -ENOMEM;

fs/f2fs/debug.c

@@ -301,6 +301,9 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ssa_area_segs, si->main_area_segs);
 		seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
 			   si->overp_segs, si->rsvd_segs);
+		seq_printf(s, "Current Time Sec: %llu / Mounted Time Sec: %llu\n\n",
+					ktime_get_boottime_seconds(),
+					SIT_I(si->sbi)->mounted_time);
 		if (test_opt(si->sbi, DISCARD))
 			seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n",
 				si->utilization, si->valid_count, si->discard_blks);

fs/f2fs/dir.c

@@ -471,7 +471,6 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
 			struct page *dpage)
 {
 	struct page *page;
-	int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir));
 	int err;
 
 	if (is_inode_flag_set(inode, FI_NEW_INODE)) {
@@ -498,8 +497,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
 		if (err)
 			goto put_error;
 
-		if ((IS_ENCRYPTED(dir) || dummy_encrypt) &&
+		if (IS_ENCRYPTED(inode)) {
-					f2fs_may_encrypt(inode)) {
 			err = fscrypt_inherit_context(dir, inode, page, false);
 			if (err)
 				goto put_error;
@@ -850,12 +848,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 			0);
 	set_page_dirty(page);
 
-	dir->i_ctime = dir->i_mtime = current_time(dir);
-	f2fs_mark_inode_dirty_sync(dir, false);
-
-	if (inode)
-		f2fs_drop_nlink(dir, inode);
-
 	if (bit_pos == NR_DENTRY_IN_BLOCK &&
 		!f2fs_truncate_hole(dir, page->index, page->index + 1)) {
 		f2fs_clear_page_cache_dirty_tag(page);
@@ -867,6 +859,12 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		f2fs_remove_dirty_inode(dir);
 	}
 	f2fs_put_page(page, 1);
+
+	dir->i_ctime = dir->i_mtime = current_time(dir);
+	f2fs_mark_inode_dirty_sync(dir, false);
+
+	if (inode)
+		f2fs_drop_nlink(dir, inode);
 }
 
 bool f2fs_empty_dir(struct inode *dir)

fs/f2fs/f2fs.h

@@ -75,7 +75,6 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 /*
  * For mount options
  */
-#define F2FS_MOUNT_BG_GC		0x00000001
 #define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000002
 #define F2FS_MOUNT_DISCARD		0x00000004
 #define F2FS_MOUNT_NOHEAP		0x00000008
@@ -89,11 +88,8 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_NOBARRIER		0x00000800
 #define F2FS_MOUNT_FASTBOOT		0x00001000
 #define F2FS_MOUNT_EXTENT_CACHE		0x00002000
-#define F2FS_MOUNT_FORCE_FG_GC		0x00004000
 #define F2FS_MOUNT_DATA_FLUSH		0x00008000
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
-#define F2FS_MOUNT_ADAPTIVE		0x00020000
-#define F2FS_MOUNT_LFS			0x00040000
 #define F2FS_MOUNT_USRQUOTA		0x00080000
 #define F2FS_MOUNT_GRPQUOTA		0x00100000
 #define F2FS_MOUNT_PRJQUOTA		0x00200000
@@ -101,6 +97,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
 #define F2FS_MOUNT_RESERVE_ROOT		0x01000000
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
+#define F2FS_MOUNT_NORECOVERY		0x04000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -139,6 +136,8 @@ struct f2fs_mount_info {
 	int whint_mode;
 	int alloc_mode;			/* segment allocation policy */
 	int fsync_mode;			/* fsync policy */
+	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
+	int bggc_mode;			/* bggc mode: off, on or sync */
 	bool test_dummy_encryption;	/* test dummy encryption */
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
@@ -332,8 +331,8 @@ struct discard_policy {
 	bool io_aware;			/* issue discard in idle time */
 	bool sync;			/* submit discard with REQ_SYNC flag */
 	bool ordered;			/* issue discard by lba order */
+	bool timeout;			/* discard timeout for put_super */
 	unsigned int granularity;	/* discard granularity */
-	int timeout;			/* discard timeout for put_super */
 };
 
 struct discard_cmd_control {
@@ -428,6 +427,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
 #define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
 #define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
+#define F2FS_IOC_GET_COMPRESS_BLOCKS	_IOR(F2FS_IOCTL_MAGIC, 17, __u64)
 
 #define F2FS_IOC_GET_VOLUME_NAME	FS_IOC_GETFSLABEL
 #define F2FS_IOC_SET_VOLUME_NAME	FS_IOC_SETFSLABEL
@@ -560,6 +560,9 @@ enum {
 
 #define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */
 
+/* congestion wait timeout value, default: 20ms */
+#define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))
+
 /* maximum retry quota flush count */
 #define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8
 
@@ -676,6 +679,44 @@ enum {
 	MAX_GC_FAILURE
 };
 
+/* used for f2fs_inode_info->flags */
+enum {
+	FI_NEW_INODE,		/* indicate newly allocated inode */
+	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
+	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
+	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
+	FI_INC_LINK,		/* need to increment i_nlink */
+	FI_ACL_MODE,		/* indicate acl mode */
+	FI_NO_ALLOC,		/* should not allocate any blocks */
+	FI_FREE_NID,		/* free allocated nide */
+	FI_NO_EXTENT,		/* not to use the extent cache */
+	FI_INLINE_XATTR,	/* used for inline xattr */
+	FI_INLINE_DATA,		/* used for inline data*/
+	FI_INLINE_DENTRY,	/* used for inline dentry */
+	FI_APPEND_WRITE,	/* inode has appended data */
+	FI_UPDATE_WRITE,	/* inode has in-place-update data */
+	FI_NEED_IPU,		/* used for ipu per file */
+	FI_ATOMIC_FILE,		/* indicate atomic file */
+	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
+	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
+	FI_DROP_CACHE,		/* drop dirty page cache */
+	FI_DATA_EXIST,		/* indicate data exists */
+	FI_INLINE_DOTS,		/* indicate inline dot dentries */
+	FI_DO_DEFRAG,		/* indicate defragment is running */
+	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
+	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
+	FI_HOT_DATA,		/* indicate file is hot */
+	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
+	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
+	FI_PIN_FILE,		/* indicate file should not be gced */
+	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
+	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
+	FI_MMAP_FILE,		/* indicate file was mmapped */
+	FI_MAX,			/* max flag, never be used */
+};
+
 struct f2fs_inode_info {
 	struct inode vfs_inode;		/* serve a vfs inode */
 	unsigned long i_flags;		/* keep an inode flags for ioctl */
@@ -688,7 +729,7 @@ struct f2fs_inode_info {
 	umode_t i_acl_mode;		/* keep file acl mode temporarily */
 
 	/* Use below internally in f2fs*/
-	unsigned long flags;		/* use to pass per-file flags */
+	unsigned long flags[BITS_TO_LONGS(FI_MAX)];	/* use to pass per-file flags */
 	struct rw_semaphore i_sem;	/* protect fi info */
 	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
@@ -697,6 +738,7 @@ struct f2fs_inode_info {
 	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	loff_t	last_disk_size;		/* lastly written file size */
+	spinlock_t i_size_lock;		/* protect last_disk_size */
 
 #ifdef CONFIG_QUOTA
 	struct dquot *i_dquot[MAXQUOTAS];
@@ -1172,6 +1214,20 @@ enum {
 	GC_URGENT,
 };
 
+enum {
+	BGGC_MODE_ON,		/* background gc is on */
+	BGGC_MODE_OFF,		/* background gc is off */
+	BGGC_MODE_SYNC,		/*
+				 * background gc is on, migrating blocks
+				 * like foreground gc
+				 */
+};
+
+enum {
+	FS_MODE_ADAPTIVE,	/* use both lfs/ssr allocation */
+	FS_MODE_LFS,		/* use lfs allocation only */
+};
+
 enum {
 	WHINT_MODE_OFF,		/* not pass down write hints */
 	WHINT_MODE_USER,	/* try to pass down hints given by users */
@@ -1212,13 +1268,13 @@ enum fsync_mode {
 enum compress_algorithm_type {
 	COMPRESS_LZO,
 	COMPRESS_LZ4,
+	COMPRESS_ZSTD,
 	COMPRESS_MAX,
 };
 
-#define COMPRESS_DATA_RESERVED_SIZE		4
+#define COMPRESS_DATA_RESERVED_SIZE		5
 struct compress_data {
 	__le32 clen;			/* compressed data size */
-	__le32 chksum;			/* checksum of compressed data */
 	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
 	u8 cdata[];			/* compressed data */
 };
@@ -1242,6 +1298,7 @@ struct compress_ctx {
 	size_t rlen;			/* valid data length in rbuf */
 	size_t clen;			/* valid data length in cbuf */
 	void *private;			/* payload buffer for specified compression algorithm */
+	void *private2;			/* extra payload buffer */
 };
 
 /* compress context for write IO path */
@@ -1271,11 +1328,14 @@ struct decompress_io_ctx {
 	size_t clen;			/* valid data length in cbuf */
 	refcount_t ref;			/* referrence count of compressed page */
 	bool failed;			/* indicate IO error during decompression */
+	void *private;			/* payload buffer for specified decompression algorithm */
+	void *private2;			/* extra payload buffer */
 };
 
 #define NULL_CLUSTER			((unsigned int)(~0))
 #define MIN_COMPRESS_LOG_SIZE		2
 #define MAX_COMPRESS_LOG_SIZE		8
+#define MAX_COMPRESS_WINDOW_SIZE	((PAGE_SIZE) << MAX_COMPRESS_LOG_SIZE)
 
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
@@ -1471,6 +1531,9 @@ struct f2fs_sb_info {
 	__u32 s_chksum_seed;
 
 	struct workqueue_struct *post_read_wq;	/* post read workqueue */
+
+	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
+	unsigned int inline_xattr_slab_size;	/* default inline xattr slab size */
 };
 
 struct f2fs_private_dio {
@@ -2211,7 +2274,7 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 		dquot_free_inode(inode);
 	} else {
 		if (unlikely(inode->i_blocks == 0)) {
-			f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
+			f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu",
 				  inode->i_ino,
 				  (unsigned long long)inode->i_blocks);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -2379,7 +2442,7 @@ static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
 }
 
 static inline int f2fs_has_extra_attr(struct inode *inode);
-static inline block_t datablock_addr(struct inode *inode,
+static inline block_t data_blkaddr(struct inode *inode,
 			struct page *node_page, unsigned int offset)
 {
 	struct f2fs_node *raw_node;
@@ -2389,9 +2452,9 @@ static inline block_t datablock_addr(struct inode *inode,
 
 	raw_node = F2FS_NODE(node_page);
 
-	/* from GC path only */
 	if (is_inode) {
 		if (!inode)
+			/* from GC path only */
 			base = offset_in_addr(&raw_node->i);
 		else if (f2fs_has_extra_attr(inode))
 			base = get_extra_isize(inode);
@@ -2401,6 +2464,11 @@ static inline block_t datablock_addr(struct inode *inode,
 	return le32_to_cpu(addr_array[base + offset]);
 }
 
+static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn)
+{
+	return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node);
+}
+
 static inline int f2fs_test_bit(unsigned int nr, char *addr)
 {
 	int mask;
@@ -2498,43 +2566,6 @@ static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
 		return flags & F2FS_OTHER_FLMASK;
 }
 
-/* used for f2fs_inode_info->flags */
-enum {
-	FI_NEW_INODE,		/* indicate newly allocated inode */
-	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
-	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
-	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
-	FI_INC_LINK,		/* need to increment i_nlink */
-	FI_ACL_MODE,		/* indicate acl mode */
-	FI_NO_ALLOC,		/* should not allocate any blocks */
-	FI_FREE_NID,		/* free allocated nide */
-	FI_NO_EXTENT,		/* not to use the extent cache */
-	FI_INLINE_XATTR,	/* used for inline xattr */
-	FI_INLINE_DATA,		/* used for inline data*/
-	FI_INLINE_DENTRY,	/* used for inline dentry */
-	FI_APPEND_WRITE,	/* inode has appended data */
-	FI_UPDATE_WRITE,	/* inode has in-place-update data */
-	FI_NEED_IPU,		/* used for ipu per file */
-	FI_ATOMIC_FILE,		/* indicate atomic file */
-	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
-	FI_VOLATILE_FILE,	/* indicate volatile file */
-	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
-	FI_DROP_CACHE,		/* drop dirty page cache */
-	FI_DATA_EXIST,		/* indicate data exists */
-	FI_INLINE_DOTS,		/* indicate inline dot dentries */
-	FI_DO_DEFRAG,		/* indicate defragment is running */
-	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
-	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
-	FI_HOT_DATA,		/* indicate file is hot */
-	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
-	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
-	FI_PIN_FILE,		/* indicate file should not be gced */
-	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
-	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
-	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
-	FI_MMAP_FILE,		/* indicate file was mmapped */
-};
-
 static inline void __mark_inode_dirty_flag(struct inode *inode,
 						int flag, bool set)
 {
@@ -2549,27 +2580,24 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
 	case FI_DATA_EXIST:
 	case FI_INLINE_DOTS:
 	case FI_PIN_FILE:
-	case FI_COMPRESSED_FILE:
 		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 }
 
 static inline void set_inode_flag(struct inode *inode, int flag)
 {
-	if (!test_bit(flag, &F2FS_I(inode)->flags))
+	test_and_set_bit(flag, F2FS_I(inode)->flags);
-		set_bit(flag, &F2FS_I(inode)->flags);
 	__mark_inode_dirty_flag(inode, flag, true);
 }
 
 static inline int is_inode_flag_set(struct inode *inode, int flag)
 {
-	return test_bit(flag, &F2FS_I(inode)->flags);
+	return test_bit(flag, F2FS_I(inode)->flags);
 }
 
 static inline void clear_inode_flag(struct inode *inode, int flag)
 {
-	if (test_bit(flag, &F2FS_I(inode)->flags))
+	test_and_clear_bit(flag, F2FS_I(inode)->flags);
-		clear_bit(flag, &F2FS_I(inode)->flags);
 	__mark_inode_dirty_flag(inode, flag, false);
 }
 
@@ -2660,19 +2688,19 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
 	if (ri->i_inline & F2FS_INLINE_XATTR)
-		set_bit(FI_INLINE_XATTR, &fi->flags);
+		set_bit(FI_INLINE_XATTR, fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DATA)
-		set_bit(FI_INLINE_DATA, &fi->flags);
+		set_bit(FI_INLINE_DATA, fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DENTRY)
-		set_bit(FI_INLINE_DENTRY, &fi->flags);
+		set_bit(FI_INLINE_DENTRY, fi->flags);
 	if (ri->i_inline & F2FS_DATA_EXIST)
-		set_bit(FI_DATA_EXIST, &fi->flags);
+		set_bit(FI_DATA_EXIST, fi->flags);
 	if (ri->i_inline & F2FS_INLINE_DOTS)
-		set_bit(FI_INLINE_DOTS, &fi->flags);
+		set_bit(FI_INLINE_DOTS, fi->flags);
 	if (ri->i_inline & F2FS_EXTRA_ATTR)
-		set_bit(FI_EXTRA_ATTR, &fi->flags);
+		set_bit(FI_EXTRA_ATTR, fi->flags);
 	if (ri->i_inline & F2FS_PIN_FILE)
-		set_bit(FI_PIN_FILE, &fi->flags);
+		set_bit(FI_PIN_FILE, fi->flags);
 }
 
 static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
@@ -2857,9 +2885,9 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
 	if (!f2fs_is_time_consistent(inode))
 		return false;
 
-	down_read(&F2FS_I(inode)->i_sem);
+	spin_lock(&F2FS_I(inode)->i_size_lock);
 	ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
-	up_read(&F2FS_I(inode)->i_sem);
+	spin_unlock(&F2FS_I(inode)->i_size_lock);
 
 	return ret;
 }
@@ -3213,7 +3241,7 @@ void f2fs_drop_inmem_pages(struct inode *inode);
 void f2fs_drop_inmem_page(struct inode *inode, struct page *page);
 int f2fs_commit_inmem_pages(struct inode *inode);
 void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
-void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg);
 int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
 int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
 int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
@@ -3309,7 +3337,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
 void f2fs_update_dirty_page(struct inode *inode, struct page *page);
 void f2fs_remove_dirty_inode(struct inode *inode);
 int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
 int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init f2fs_create_checkpoint_caches(void);
@@ -3320,7 +3348,7 @@ void f2fs_destroy_checkpoint_caches(void);
  */
 int __init f2fs_init_bioset(void);
 void f2fs_destroy_bioset(void);
-struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail);
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio);
 int f2fs_init_bio_entry_cache(void);
 void f2fs_destroy_bio_entry_cache(void);
 void f2fs_submit_bio(struct f2fs_sb_info *sbi,
@@ -3776,7 +3804,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc,
 int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
 int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 				unsigned nr_pages, sector_t *last_block_in_bio,
-				bool is_readahead);
+				bool is_readahead, bool for_write);
 struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
 void f2fs_free_dic(struct decompress_io_ctx *dic);
 void f2fs_decompress_end_io(struct page **rpages,
@@ -3813,6 +3841,7 @@ static inline void set_compress_context(struct inode *inode)
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
 	set_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_inc_compr_inode(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline u64 f2fs_disable_compressed_file(struct inode *inode)
@@ -3821,12 +3850,17 @@ static inline u64 f2fs_disable_compressed_file(struct inode *inode)
 
 	if (!f2fs_compressed_file(inode))
 		return 0;
-	if (fi->i_compr_blocks)
+	if (S_ISREG(inode->i_mode)) {
-		return fi->i_compr_blocks;
+		if (get_dirty_pages(inode))
+			return 1;
+		if (fi->i_compr_blocks)
+			return fi->i_compr_blocks;
+	}
 
 	fi->i_flags &= ~F2FS_COMPR_FL;
-	clear_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_dec_compr_inode(inode);
+	clear_inode_flag(inode, FI_COMPRESSED_FILE);
+	f2fs_mark_inode_dirty_sync(inode, true);
 	return 0;
 }
 
@@ -3903,31 +3937,25 @@ static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi)
 	return false;
 }
 
-
+static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
-static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
 {
-	clear_opt(sbi, ADAPTIVE);
+	return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
-	clear_opt(sbi, LFS);
-
-	switch (mt) {
-	case F2FS_MOUNT_ADAPTIVE:
-		set_opt(sbi, ADAPTIVE);
-		break;
-	case F2FS_MOUNT_LFS:
-		set_opt(sbi, LFS);
-		break;
-	}
 }
 
-static inline bool f2fs_may_encrypt(struct inode *inode)
+static inline bool f2fs_may_encrypt(struct inode *dir, struct inode *inode)
 {
 #ifdef CONFIG_FS_ENCRYPTION
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	umode_t mode = inode->i_mode;
 
-	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
+	/*
-#else
+	 * If the directory encrypted or dummy encryption enabled,
-	return false;
+	 * then we should encrypt the inode.
+	 */
+	if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi))
+		return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
 #endif
+	return false;
 }
 
 static inline bool f2fs_may_compress(struct inode *inode)
@@ -3971,7 +3999,7 @@ static inline int allow_outplace_dio(struct inode *inode,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int rw = iov_iter_rw(iter);
 
-	return (test_opt(sbi, LFS) && (rw == WRITE) &&
+	return (f2fs_lfs_mode(sbi) && (rw == WRITE) &&
 				!block_unaligned_IO(inode, iocb, iter));
 }
 
@@ -3993,7 +4021,7 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 	 */
 	if (f2fs_sb_has_blkzoned(sbi))
 		return true;
-	if (test_opt(sbi, LFS) && (rw == WRITE)) {
+	if (f2fs_lfs_mode(sbi) && (rw == WRITE)) {
 		if (block_unaligned_IO(inode, iocb, iter))
 			return true;
 		if (F2FS_IO_ALIGNED(sbi))

fs/f2fs/file.c

@@ -106,13 +106,20 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		err = f2fs_get_block(&dn, page->index);
 		f2fs_put_dnode(&dn);
 		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
-		if (err) {
-			unlock_page(page);
-			goto out_sem;
-		}
 	}
 
-	/* fill the page */
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (!need_alloc) {
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+		f2fs_put_dnode(&dn);
+	}
+#endif
+	if (err) {
+		unlock_page(page);
+		goto out_sem;
+	}
+
 	f2fs_wait_on_page_writeback(page, DATA, false, true);
 
 	/* wait for GCed page writeback via META_MAPPING */
@@ -448,8 +455,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 				data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
 			block_t blkaddr;
 
-			blkaddr = datablock_addr(dn.inode,
+			blkaddr = f2fs_data_blkaddr(&dn);
-					dn.node_page, dn.ofs_in_node);
 
 			if (__is_valid_data_blkaddr(blkaddr) &&
 				!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
@@ -793,6 +799,8 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
 	}
 
 	flags = fi->i_flags;
+	if (flags & F2FS_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
 	if (flags & F2FS_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;
 	if (IS_ENCRYPTED(inode))
@@ -804,7 +812,8 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
 	if (IS_VERITY(inode))
 		stat->attributes |= STATX_ATTR_VERITY;
 
-	stat->attributes_mask |= (STATX_ATTR_APPEND |
+	stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_APPEND |
 				  STATX_ATTR_ENCRYPTED |
 				  STATX_ATTR_IMMUTABLE |
 				  STATX_ATTR_NODUMP |
@@ -929,10 +938,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 		if (err)
 			return err;
 
-		down_write(&F2FS_I(inode)->i_sem);
+		spin_lock(&F2FS_I(inode)->i_size_lock);
 		inode->i_mtime = inode->i_ctime = current_time(inode);
 		F2FS_I(inode)->last_disk_size = i_size_read(inode);
-		up_write(&F2FS_I(inode)->i_sem);
+		spin_unlock(&F2FS_I(inode)->i_size_lock);
 	}
 
 	__setattr_copy(inode, attr);
@@ -1109,8 +1118,7 @@ next_dnode:
 	done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
 							dn.ofs_in_node, len);
 	for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
-		*blkaddr = datablock_addr(dn.inode,
+		*blkaddr = f2fs_data_blkaddr(&dn);
-					dn.node_page, dn.ofs_in_node);
 
 		if (__is_valid_data_blkaddr(*blkaddr) &&
 			!f2fs_is_valid_blkaddr(sbi, *blkaddr,
@@ -1121,7 +1129,7 @@ next_dnode:
 
 		if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) {
 
-			if (test_opt(sbi, LFS)) {
+			if (f2fs_lfs_mode(sbi)) {
 				f2fs_put_dnode(&dn);
 				return -EOPNOTSUPP;
 			}
@@ -1199,8 +1207,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 				ADDRS_PER_PAGE(dn.node_page, dst_inode) -
 						dn.ofs_in_node, len - i);
 			do {
-				dn.data_blkaddr = datablock_addr(dn.inode,
+				dn.data_blkaddr = f2fs_data_blkaddr(&dn);
-						dn.node_page, dn.ofs_in_node);
 				f2fs_truncate_data_blocks_range(&dn, 1);
 
 				if (do_replace[i]) {
@@ -1376,8 +1383,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
 	int ret;
 
 	for (; index < end; index++, dn->ofs_in_node++) {
-		if (datablock_addr(dn->inode, dn->node_page,
+		if (f2fs_data_blkaddr(dn) == NULL_ADDR)
-					dn->ofs_in_node) == NULL_ADDR)
 			count++;
 	}
 
@@ -1388,8 +1394,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
 
 	dn->ofs_in_node = ofs_in_node;
 	for (index = start; index < end; index++, dn->ofs_in_node++) {
-		dn->data_blkaddr = datablock_addr(dn->inode,
+		dn->data_blkaddr = f2fs_data_blkaddr(dn);
-					dn->node_page, dn->ofs_in_node);
 		/*
 		 * f2fs_reserve_new_blocks will not guarantee entire block
 		 * allocation.
@@ -1787,12 +1792,15 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
 static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
+	u32 masked_flags = fi->i_flags & mask;
+
+	f2fs_bug_on(F2FS_I_SB(inode), (iflags & ~mask));
 
 	/* Is it quota file? Do not allow user to mess with it */
 	if (IS_NOQUOTA(inode))
 		return -EPERM;
 
-	if ((iflags ^ fi->i_flags) & F2FS_CASEFOLD_FL) {
+	if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) {
 		if (!f2fs_sb_has_casefold(F2FS_I_SB(inode)))
 			return -EOPNOTSUPP;
 		if (!f2fs_empty_dir(inode))
@@ -1806,27 +1814,22 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 			return -EINVAL;
 	}
 
-	if ((iflags ^ fi->i_flags) & F2FS_COMPR_FL) {
+	if ((iflags ^ masked_flags) & F2FS_COMPR_FL) {
-		if (S_ISREG(inode->i_mode) &&
+		if (masked_flags & F2FS_COMPR_FL) {
-			(fi->i_flags & F2FS_COMPR_FL || i_size_read(inode) ||
+			if (f2fs_disable_compressed_file(inode))
-						F2FS_HAS_BLOCKS(inode)))
+				return -EINVAL;
-			return -EINVAL;
+		}
 		if (iflags & F2FS_NOCOMP_FL)
 			return -EINVAL;
 		if (iflags & F2FS_COMPR_FL) {
-			int err = f2fs_convert_inline_inode(inode);
-
-			if (err)
-				return err;
-
 			if (!f2fs_may_compress(inode))
 				return -EINVAL;
 
 			set_compress_context(inode);
 		}
 	}
-	if ((iflags ^ fi->i_flags) & F2FS_NOCOMP_FL) {
+	if ((iflags ^ masked_flags) & F2FS_NOCOMP_FL) {
-		if (fi->i_flags & F2FS_COMPR_FL)
+		if (masked_flags & F2FS_COMPR_FL)
 			return -EINVAL;
 	}
 
@@ -3401,6 +3404,21 @@ out:
 	return err;
 }
 
+static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	__u64 blocks;
+
+	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+		return -EOPNOTSUPP;
+
+	if (!f2fs_compressed_file(inode))
+		return -EINVAL;
+
+	blocks = F2FS_I(inode)->i_compr_blocks;
+	return put_user(blocks, (u64 __user *)arg);
+}
+
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
@@ -3481,6 +3499,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_get_volume_name(filp, arg);
 	case F2FS_IOC_SET_VOLUME_NAME:
 		return f2fs_set_volume_name(filp, arg);
+	case F2FS_IOC_GET_COMPRESS_BLOCKS:
+		return f2fs_get_compress_blocks(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -3508,8 +3528,10 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 	}
 
-	if (!f2fs_is_compress_backend_ready(inode))
+	if (!f2fs_is_compress_backend_ready(inode)) {
-		return -EOPNOTSUPP;
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (iocb->ki_flags & IOCB_NOWAIT) {
 		if (!inode_trylock(inode)) {
@@ -3639,6 +3661,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC_MEASURE_VERITY:
 	case F2FS_IOC_GET_VOLUME_NAME:
 	case F2FS_IOC_SET_VOLUME_NAME:
+	case F2FS_IOC_GET_COMPRESS_BLOCKS:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/f2fs/gc.c

@@ -31,6 +31,8 @@ static int gc_thread_func(void *data)
 
 	set_freezable();
 	do {
+		bool sync_mode;
+
 		wait_event_interruptible_timeout(*wq,
 				kthread_should_stop() || freezing(current) ||
 				gc_th->gc_wake,
@@ -101,15 +103,17 @@ static int gc_thread_func(void *data)
 do_gc:
 		stat_inc_bggc_count(sbi->stat_info);
 
+		sync_mode = F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC;
+
 		/* if return value is not zero, no victim was selected */
-		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO))
+		if (f2fs_gc(sbi, sync_mode, true, NULL_SEGNO))
 			wait_ms = gc_th->no_gc_sleep_time;
 
 		trace_f2fs_background_gc(sbi->sb, wait_ms,
 				prefree_segments(sbi), free_segments(sbi));
 
 		/* balancing f2fs's metadata periodically */
-		f2fs_balance_fs_bg(sbi);
+		f2fs_balance_fs_bg(sbi, true);
 next:
 		sb_end_write(sbi->sb);
 
@@ -192,7 +196,10 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->ofs_unit = sbi->segs_per_sec;
 	}
 
-	/* we need to check every dirty segments in the FG_GC case */
+	/*
+	 * adjust candidates range, should select all dirty segments for
+	 * foreground GC and urgent GC cases.
+	 */
 	if (gc_type != FG_GC &&
 			(sbi->gc_mode != GC_URGENT) &&
 			p->max_search > sbi->max_victim_search)
@@ -634,7 +641,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	}
 
 	*nofs = ofs_of_node(node_page);
-	source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node);
+	source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node);
 	f2fs_put_page(node_page, 1);
 
 	if (source_blkaddr != blkaddr) {
@@ -762,7 +769,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 	struct page *page, *mpage;
 	block_t newaddr;
 	int err = 0;
-	bool lfs_mode = test_opt(fio.sbi, LFS);
+	bool lfs_mode = f2fs_lfs_mode(fio.sbi);
 
 	/* do not read out */
 	page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
@@ -970,7 +977,8 @@ retry:
 		if (err) {
 			clear_cold_data(page);
 			if (err == -ENOMEM) {
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
 				goto retry;
 			}
 			if (is_dirty)
@@ -1018,8 +1026,8 @@ next_step:
 		 * race condition along with SSR block allocation.
 		 */
 		if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) ||
-				get_valid_blocks(sbi, segno, false) ==
+				get_valid_blocks(sbi, segno, true) ==
-							sbi->blocks_per_seg)
+							BLKS_PER_SEC(sbi))
 			return submitted;
 
 		if (check_valid_map(sbi, segno, off) == 0)
@@ -1203,7 +1211,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 
 		if (get_valid_blocks(sbi, segno, false) == 0)
 			goto freed;
-		if (__is_large_section(sbi) &&
+		if (gc_type == BG_GC && __is_large_section(sbi) &&
 				migrated >= sbi->migration_granularity)
 			goto skip;
 		if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi)))
@@ -1233,12 +1241,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 							segno, gc_type);
 
 		stat_inc_seg_count(sbi, type, gc_type);
+		migrated++;
 
 freed:
 		if (gc_type == FG_GC &&
 				get_valid_blocks(sbi, segno, false) == 0)
 			seg_freed++;
-		migrated++;
 
 		if (__is_large_section(sbi) && segno + 1 < end_segno)
 			sbi->next_victim_seg[gc_type] = segno + 1;
@@ -1434,12 +1442,19 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
 static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
 {
 	struct f2fs_super_block *raw_sb = F2FS_RAW_SUPER(sbi);
-	int section_count = le32_to_cpu(raw_sb->section_count);
+	int section_count;
-	int segment_count = le32_to_cpu(raw_sb->segment_count);
+	int segment_count;
-	int segment_count_main = le32_to_cpu(raw_sb->segment_count_main);
+	int segment_count_main;
-	long long block_count = le64_to_cpu(raw_sb->block_count);
+	long long block_count;
 	int segs = secs * sbi->segs_per_sec;
 
+	down_write(&sbi->sb_lock);
+
+	section_count = le32_to_cpu(raw_sb->section_count);
+	segment_count = le32_to_cpu(raw_sb->segment_count);
+	segment_count_main = le32_to_cpu(raw_sb->segment_count_main);
+	block_count = le64_to_cpu(raw_sb->block_count);
+
 	raw_sb->section_count = cpu_to_le32(section_count + secs);
 	raw_sb->segment_count = cpu_to_le32(segment_count + segs);
 	raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs);
@@ -1453,6 +1468,8 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
 		raw_sb->devs[last_dev].total_segments =
 						cpu_to_le32(dev_segs + segs);
 	}
+
+	up_write(&sbi->sb_lock);
 }
 
 static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
@@ -1570,11 +1587,17 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
 		goto out;
 	}
 
+	mutex_lock(&sbi->cp_mutex);
 	update_fs_metadata(sbi, -secs);
 	clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
+	mutex_unlock(&sbi->cp_mutex);
+
 	err = f2fs_sync_fs(sbi->sb, 1);
 	if (err) {
+		mutex_lock(&sbi->cp_mutex);
 		update_fs_metadata(sbi, secs);
+		mutex_unlock(&sbi->cp_mutex);
 		update_sb_metadata(sbi, secs);
 		f2fs_commit_super(sbi, false);
 	}

fs/f2fs/inode.c

@@ -291,13 +291,30 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 			fi->i_flags & F2FS_COMPR_FL &&
 			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 						i_log_cluster_size)) {
-		if (ri->i_compress_algorithm >= COMPRESS_MAX)
+		if (ri->i_compress_algorithm >= COMPRESS_MAX) {
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
+				"compress algorithm: %u, run fsck to fix",
+				  __func__, inode->i_ino,
+				  ri->i_compress_algorithm);
 			return false;
-		if (le64_to_cpu(ri->i_compr_blocks) > inode->i_blocks)
+		}
+		if (le64_to_cpu(ri->i_compr_blocks) >
+				SECTOR_TO_BLOCK(inode->i_blocks)) {
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has inconsistent "
+				"i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix",
+				  __func__, inode->i_ino,
+				  le64_to_cpu(ri->i_compr_blocks),
+				  SECTOR_TO_BLOCK(inode->i_blocks));
 			return false;
+		}
 		if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
-			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE)
+			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) {
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
+				"log cluster size: %u, run fsck to fix",
+				  __func__, inode->i_ino,
+				  ri->i_log_cluster_size);
 			return false;
+		}
 	}
 
 	return true;
@@ -345,7 +362,7 @@ static int do_read_inode(struct inode *inode)
 	fi->i_flags = le32_to_cpu(ri->i_flags);
 	if (S_ISREG(inode->i_mode))
 		fi->i_flags &= ~F2FS_PROJINHERIT_FL;
-	fi->flags = 0;
+	bitmap_zero(fi->flags, FI_MAX);
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
@@ -518,7 +535,7 @@ retry:
 	inode = f2fs_iget(sb, ino);
 	if (IS_ERR(inode)) {
 		if (PTR_ERR(inode) == -ENOMEM) {
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 			goto retry;
 		}
 	}
@@ -759,7 +776,7 @@ no_delete:
 	else
 		f2fs_inode_synced(inode);
 
-	/* ino == 0, if f2fs_new_inode() was failed t*/
+	/* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */
 	if (inode->i_ino)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
 							inode->i_ino);

fs/f2fs/namei.c

@@ -75,9 +75,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 
 	set_inode_flag(inode, FI_NEW_INODE);
 
-	/* If the directory encrypted, then we should encrypt the inode. */
+	if (f2fs_may_encrypt(dir, inode))
-	if ((IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) &&
-				f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
 	if (f2fs_sb_has_extra_attr(sbi)) {
@@ -177,7 +175,7 @@ static inline int is_extension_exist(const unsigned char *s, const char *sub)
 }
 
 /*
- * Set multimedia files as cold files for hot/cold data separation
+ * Set file's temperature for hot/cold data separation
  */
 static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode,
 		const unsigned char *name)
@@ -876,12 +874,6 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) {
-		int err = fscrypt_get_encryption_info(dir);
-		if (err)
-			return err;
-	}
-
 	return __f2fs_tmpfile(dir, dentry, mode, NULL);
 }
 

fs/f2fs/node.c

@@ -510,9 +510,6 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 	return nr - nr_shrink;
 }
 
-/*
- * This function always returns success
- */
 int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 						struct node_info *ni)
 {
@@ -716,8 +713,7 @@ got:
 /*
  * Caller should call f2fs_put_dnode(dn).
  * Also, it should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op() only if ro is not set RDONLY_NODE.
+ * f2fs_unlock_op() only if mode is set with ALLOC_NODE.
- * In the case of RDONLY_NODE, we don't need to care about mutex.
  */
 int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 {
@@ -809,8 +805,7 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	dn->nid = nids[level];
 	dn->ofs_in_node = offset[level];
 	dn->node_page = npage[level];
-	dn->data_blkaddr = datablock_addr(dn->inode,
+	dn->data_blkaddr = f2fs_data_blkaddr(dn);
-				dn->node_page, dn->ofs_in_node);
 	return 0;
 
 release_pages:
@@ -1188,8 +1183,9 @@ int f2fs_remove_inode_page(struct inode *inode)
 	}
 
 	if (unlikely(inode->i_blocks != 0 && inode->i_blocks != 8)) {
-		f2fs_warn(F2FS_I_SB(inode), "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
+		f2fs_warn(F2FS_I_SB(inode),
-			  inode->i_ino, (unsigned long long)inode->i_blocks);
+			"f2fs_remove_inode_page: inconsistent i_blocks, ino:%lu, iblocks:%llu",
+			inode->i_ino, (unsigned long long)inode->i_blocks);
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
 	}
 
@@ -1562,15 +1558,16 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	if (atomic && !test_opt(sbi, NOBARRIER))
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 
-	set_page_writeback(page);
+	/* should add to global list before clearing PAGECACHE status */
-	ClearPageError(page);
-
 	if (f2fs_in_warm_node_list(sbi, page)) {
 		seq = f2fs_add_fsync_node_entry(sbi, page);
 		if (seq_id)
 			*seq_id = seq;
 	}
 
+	set_page_writeback(page);
+	ClearPageError(page);
+
 	fio.old_blkaddr = ni.blk_addr;
 	f2fs_do_write_node_page(nid, &fio);
 	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
@@ -1979,7 +1976,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 		goto skip_write;
 
 	/* balancing f2fs's metadata in background */
-	f2fs_balance_fs_bg(sbi);
+	f2fs_balance_fs_bg(sbi, true);
 
 	/* collect a number of dirty node pages and write together */
 	if (wbc->sync_mode != WB_SYNC_ALL &&
@@ -2602,7 +2599,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 retry:
 	ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
 	if (!ipage) {
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 		goto retry;
 	}
 
@@ -3193,22 +3190,22 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 
 int __init f2fs_create_node_manager_caches(void)
 {
-	nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
+	nat_entry_slab = f2fs_kmem_cache_create("f2fs_nat_entry",
 			sizeof(struct nat_entry));
 	if (!nat_entry_slab)
 		goto fail;
 
-	free_nid_slab = f2fs_kmem_cache_create("free_nid",
+	free_nid_slab = f2fs_kmem_cache_create("f2fs_free_nid",
 			sizeof(struct free_nid));
 	if (!free_nid_slab)
 		goto destroy_nat_entry;
 
-	nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set",
+	nat_entry_set_slab = f2fs_kmem_cache_create("f2fs_nat_entry_set",
 			sizeof(struct nat_entry_set));
 	if (!nat_entry_set_slab)
 		goto destroy_free_nid;
 
-	fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry",
+	fsync_node_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_node_entry",
 			sizeof(struct fsync_node_entry));
 	if (!fsync_node_entry_slab)
 		goto destroy_nat_entry_set;

fs/f2fs/recovery.c

@@ -496,8 +496,7 @@ out:
 	return 0;
 
 truncate_out:
-	if (datablock_addr(tdn.inode, tdn.node_page,
+	if (f2fs_data_blkaddr(&tdn) == blkaddr)
-					tdn.ofs_in_node) == blkaddr)
 		f2fs_truncate_data_blocks_range(&tdn, 1);
 	if (dn->inode->i_ino == nid && !dn->inode_page_locked)
 		unlock_page(dn->inode_page);
@@ -535,7 +534,7 @@ retry_dn:
 	err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
 	if (err) {
 		if (err == -ENOMEM) {
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 			goto retry_dn;
 		}
 		goto out;
@@ -560,8 +559,8 @@ retry_dn:
 	for (; start < end; start++, dn.ofs_in_node++) {
 		block_t src, dest;
 
-		src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
+		src = f2fs_data_blkaddr(&dn);
-		dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
+		dest = data_blkaddr(dn.inode, page, dn.ofs_in_node);
 
 		if (__is_valid_data_blkaddr(src) &&
 			!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
@@ -618,7 +617,8 @@ retry_prev:
 			err = check_index_in_prev_nodes(sbi, dest, &dn);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
+					congestion_wait(BLK_RW_ASYNC,
+							DEFAULT_IO_TIMEOUT);
 					goto retry_prev;
 				}
 				goto err;

fs/f2fs/segment.c

@@ -172,7 +172,7 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
 
-	if (test_opt(sbi, LFS))
+	if (f2fs_lfs_mode(sbi))
 		return false;
 	if (sbi->gc_mode == GC_URGENT)
 		return true;
@@ -245,7 +245,8 @@ retry:
 								LOOKUP_NODE);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
+					congestion_wait(BLK_RW_ASYNC,
+							DEFAULT_IO_TIMEOUT);
 					cond_resched();
 					goto retry;
 				}
@@ -312,7 +313,7 @@ next:
 skip:
 		iput(inode);
 	}
-	congestion_wait(BLK_RW_ASYNC, HZ/50);
+	congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 	cond_resched();
 	if (gc_failure) {
 		if (++looped >= count)
@@ -415,7 +416,8 @@ retry:
 			err = f2fs_do_write_data_page(&fio);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
+					congestion_wait(BLK_RW_ASYNC,
+							DEFAULT_IO_TIMEOUT);
 					cond_resched();
 					goto retry;
 				}
@@ -494,7 +496,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 
 	/* balance_fs_bg is able to be pending */
 	if (need && excess_cached_nats(sbi))
-		f2fs_balance_fs_bg(sbi);
+		f2fs_balance_fs_bg(sbi, false);
 
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return;
@@ -509,7 +511,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	}
 }
 
-void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 {
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return;
@@ -538,7 +540,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 			excess_dirty_nats(sbi) ||
 			excess_dirty_nodes(sbi) ||
 			f2fs_time_over(sbi, CP_TIME)) {
-		if (test_opt(sbi, DATA_FLUSH)) {
+		if (test_opt(sbi, DATA_FLUSH) && from_bg) {
 			struct blk_plug plug;
 
 			mutex_lock(&sbi->flush_lock);
@@ -1078,7 +1080,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 
 	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
 	dpolicy->io_aware_gran = MAX_PLIST_NUM;
-	dpolicy->timeout = 0;
+	dpolicy->timeout = false;
 
 	if (discard_type == DPOLICY_BG) {
 		dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
@@ -1103,6 +1105,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 		dpolicy->io_aware = false;
 		/* we need to issue all to keep CP_TRIMMED_FLAG */
 		dpolicy->granularity = 1;
+		dpolicy->timeout = true;
 	}
 }
 
@@ -1471,12 +1474,12 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 	int i, issued = 0;
 	bool io_interrupted = false;
 
-	if (dpolicy->timeout != 0)
+	if (dpolicy->timeout)
-		f2fs_update_time(sbi, dpolicy->timeout);
+		f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT);
 
 	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
-		if (dpolicy->timeout != 0 &&
+		if (dpolicy->timeout &&
-				f2fs_time_over(sbi, dpolicy->timeout))
+				f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
 			break;
 
 		if (i + 1 < dpolicy->granularity)
@@ -1497,8 +1500,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
 
-			if (dpolicy->timeout != 0 &&
+			if (dpolicy->timeout &&
-				f2fs_time_over(sbi, dpolicy->timeout))
+				f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
 				break;
 
 			if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
@@ -1677,7 +1680,6 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
 
 	__init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT,
 					dcc->discard_granularity);
-	dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT;
 	__issue_discard_cmd(sbi, &dpolicy);
 	dropped = __drop_discard_cmd(sbi);
 
@@ -1940,7 +1942,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
 	unsigned int start = 0, end = -1;
 	unsigned int secno, start_segno;
 	bool force = (cpc->reason & CP_DISCARD);
-	bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi);
+	bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -1972,7 +1974,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
 					(end - 1) <= cpc->trim_end)
 				continue;
 
-		if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) {
+		if (!f2fs_lfs_mode(sbi) || !__is_large_section(sbi)) {
 			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
 			continue;
@@ -2801,7 +2803,7 @@ next:
 			blk_finish_plug(&plug);
 			mutex_unlock(&dcc->cmd_lock);
 			trimmed += __wait_all_discard_cmd(sbi, NULL);
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
 			goto next;
 		}
 skip:
@@ -2830,7 +2832,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	struct discard_policy dpolicy;
 	unsigned long long trimmed = 0;
 	int err = 0;
-	bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi);
+	bool need_align = f2fs_lfs_mode(sbi) && __is_large_section(sbi);
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
@@ -3193,7 +3195,7 @@ static void update_device_state(struct f2fs_io_info *fio)
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio);
-	bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA);
+	bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA);
 
 	if (keep_order)
 		down_read(&fio->sbi->io_order_lock);
@@ -4071,7 +4073,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	sit_i->dirty_sentries = 0;
 	sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
 	sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
-	sit_i->mounted_time = ktime_get_real_seconds();
+	sit_i->mounted_time = ktime_get_boottime_seconds();
 	init_rwsem(&sit_i->sentry_lock);
 	return 0;
 }
@@ -4678,7 +4680,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
 	if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
 		sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
 
-	if (!test_opt(sbi, LFS))
+	if (!f2fs_lfs_mode(sbi))
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
@@ -4830,22 +4832,22 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
 
 int __init f2fs_create_segment_manager_caches(void)
 {
-	discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
+	discard_entry_slab = f2fs_kmem_cache_create("f2fs_discard_entry",
 			sizeof(struct discard_entry));
 	if (!discard_entry_slab)
 		goto fail;
 
-	discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd",
+	discard_cmd_slab = f2fs_kmem_cache_create("f2fs_discard_cmd",
 			sizeof(struct discard_cmd));
 	if (!discard_cmd_slab)
 		goto destroy_discard_entry;
 
-	sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
+	sit_entry_set_slab = f2fs_kmem_cache_create("f2fs_sit_entry_set",
 			sizeof(struct sit_entry_set));
 	if (!sit_entry_set_slab)
 		goto destroy_discard_cmd;
 
-	inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
+	inmem_entry_slab = f2fs_kmem_cache_create("f2fs_inmem_page_entry",
 			sizeof(struct inmem_pages));
 	if (!inmem_entry_slab)
 		goto destroy_sit_entry_set;

fs/f2fs/segment.h

@@ -756,7 +756,7 @@ static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi,
 						bool base_time)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	time64_t diff, now = ktime_get_real_seconds();
+	time64_t diff, now = ktime_get_boottime_seconds();
 
 	if (now >= sit_i->mounted_time)
 		return sit_i->elapsed_time + now - sit_i->mounted_time;

fs/f2fs/shrinker.c

@@ -58,7 +58,7 @@ unsigned long f2fs_shrink_count(struct shrinker *shrink,
 		/* count extent cache entries */
 		count += __count_extent_cache(sbi);
 
-		/* shrink clean nat cache entries */
+		/* count clean nat cache entries */
 		count += __count_nat_entries(sbi);
 
 		/* count free nids cache entries */

fs/f2fs/super.c

@@ -428,14 +428,11 @@ static int parse_options(struct super_block *sb, char *options)
 			if (!name)
 				return -ENOMEM;
 			if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
-				set_opt(sbi, BG_GC);
+				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
-				clear_opt(sbi, FORCE_FG_GC);
 			} else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
-				clear_opt(sbi, BG_GC);
+				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_OFF;
-				clear_opt(sbi, FORCE_FG_GC);
 			} else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
-				set_opt(sbi, BG_GC);
+				F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC;
-				set_opt(sbi, FORCE_FG_GC);
 			} else {
 				kvfree(name);
 				return -EINVAL;
@@ -447,7 +444,7 @@ static int parse_options(struct super_block *sb, char *options)
 			break;
 		case Opt_norecovery:
 			/* this option mounts f2fs with ro */
-			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			set_opt(sbi, NORECOVERY);
 			if (!f2fs_readonly(sb))
 				return -EINVAL;
 			break;
@@ -601,10 +598,10 @@ static int parse_options(struct super_block *sb, char *options)
 					kvfree(name);
 					return -EINVAL;
 				}
-				set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
 			} else if (strlen(name) == 3 &&
 					!strncmp(name, "lfs", 3)) {
-				set_opt_mode(sbi, F2FS_MOUNT_LFS);
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
 			} else {
 				kvfree(name);
 				return -EINVAL;
@@ -833,6 +830,10 @@ static int parse_options(struct super_block *sb, char *options)
 					!strcmp(name, "lz4")) {
 				F2FS_OPTION(sbi).compress_algorithm =
 								COMPRESS_LZ4;
+			} else if (strlen(name) == 4 &&
+					!strcmp(name, "zstd")) {
+				F2FS_OPTION(sbi).compress_algorithm =
+								COMPRESS_ZSTD;
 			} else {
 				kfree(name);
 				return -EINVAL;
@@ -905,7 +906,7 @@ static int parse_options(struct super_block *sb, char *options)
 	}
 #endif
 
-	if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
+	if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) {
 		f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO",
 			 F2FS_IO_SIZE_KB(sbi));
 		return -EINVAL;
@@ -935,7 +936,7 @@ static int parse_options(struct super_block *sb, char *options)
 		}
 	}
 
-	if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) {
+	if (test_opt(sbi, DISABLE_CHECKPOINT) && f2fs_lfs_mode(sbi)) {
 		f2fs_err(sbi, "LFS not compatible with checkpoint=disable\n");
 		return -EINVAL;
 	}
@@ -961,6 +962,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	/* Initialize f2fs-specific inode info */
 	atomic_set(&fi->dirty_pages, 0);
 	init_rwsem(&fi->i_sem);
+	spin_lock_init(&fi->i_size_lock);
 	INIT_LIST_HEAD(&fi->dirty_list);
 	INIT_LIST_HEAD(&fi->gdirty_list);
 	INIT_LIST_HEAD(&fi->inmem_ilist);
@@ -1173,7 +1175,7 @@ static void f2fs_put_super(struct super_block *sb)
 	/* our cp_error case, we can wait for any writeback page */
 	f2fs_flush_merged_writes(sbi);
 
-	f2fs_wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
 
 	f2fs_bug_on(sbi, sbi->fsync_node_num);
 
@@ -1205,6 +1207,7 @@ static void f2fs_put_super(struct super_block *sb)
 	kvfree(sbi->raw_super);
 
 	destroy_device_list(sbi);
+	f2fs_destroy_xattr_caches(sbi);
 	mempool_destroy(sbi->write_io_dummy);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
@@ -1421,6 +1424,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 	case COMPRESS_LZ4:
 		algtype = "lz4";
 		break;
+	case COMPRESS_ZSTD:
+		algtype = "zstd";
+		break;
 	}
 	seq_printf(seq, ",compress_algorithm=%s", algtype);
 
@@ -1437,16 +1443,17 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
 
-	if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) {
+	if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC)
-		if (test_opt(sbi, FORCE_FG_GC))
+		seq_printf(seq, ",background_gc=%s", "sync");
-			seq_printf(seq, ",background_gc=%s", "sync");
+	else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_ON)
-		else
+		seq_printf(seq, ",background_gc=%s", "on");
-			seq_printf(seq, ",background_gc=%s", "on");
+	else if (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF)
-	} else {
 		seq_printf(seq, ",background_gc=%s", "off");
-	}
+
 	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
 		seq_puts(seq, ",disable_roll_forward");
+	if (test_opt(sbi, NORECOVERY))
+		seq_puts(seq, ",norecovery");
 	if (test_opt(sbi, DISCARD))
 		seq_puts(seq, ",discard");
 	else
@@ -1498,9 +1505,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",data_flush");
 
 	seq_puts(seq, ",mode=");
-	if (test_opt(sbi, ADAPTIVE))
+	if (F2FS_OPTION(sbi).fs_mode == FS_MODE_ADAPTIVE)
 		seq_puts(seq, "adaptive");
-	else if (test_opt(sbi, LFS))
+	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS)
 		seq_puts(seq, "lfs");
 	seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs);
 	if (test_opt(sbi, RESERVE_ROOT))
@@ -1571,11 +1578,11 @@ static void default_options(struct f2fs_sb_info *sbi)
 	F2FS_OPTION(sbi).test_dummy_encryption = false;
 	F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
 	F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
-	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO;
+	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4;
 	F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE;
 	F2FS_OPTION(sbi).compress_ext_cnt = 0;
+	F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
 
-	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_XATTR);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
@@ -1587,9 +1594,9 @@ static void default_options(struct f2fs_sb_info *sbi)
 	set_opt(sbi, FLUSH_MERGE);
 	set_opt(sbi, DISCARD);
 	if (f2fs_sb_has_blkzoned(sbi))
-		set_opt_mode(sbi, F2FS_MOUNT_LFS);
+		F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
 	else
-		set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+		F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
 
 #ifdef CONFIG_F2FS_FS_XATTR
 	set_opt(sbi, XATTR_USER);
@@ -1658,7 +1665,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 out_unlock:
 	up_write(&sbi->gc_lock);
 restore_flag:
-	sbi->sb->s_flags = s_flags;	/* Restore MS_RDONLY status */
+	sbi->sb->s_flags = s_flags;	/* Restore SB_RDONLY status */
 	return err;
 }
 
@@ -1781,7 +1788,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * or if background_gc = off is passed in mount
 	 * option. Also sync the filesystem.
 	 */
-	if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) {
+	if ((*flags & SB_RDONLY) ||
+			F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF) {
 		if (sbi->gc_thread) {
 			f2fs_stop_gc_thread(sbi);
 			need_restart_gc = true;
@@ -1886,7 +1894,8 @@ repeat:
 		page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS);
 		if (IS_ERR(page)) {
 			if (PTR_ERR(page) == -ENOMEM) {
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
 				goto repeat;
 			}
 			set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
@@ -1928,6 +1937,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	int offset = off & (sb->s_blocksize - 1);
 	size_t towrite = len;
 	struct page *page;
+	void *fsdata = NULL;
 	char *kaddr;
 	int err = 0;
 	int tocopy;
@@ -1937,10 +1947,11 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 								towrite);
 retry:
 		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
-							&page, NULL);
+							&page, &fsdata);
 		if (unlikely(err)) {
 			if (err == -ENOMEM) {
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				congestion_wait(BLK_RW_ASYNC,
+						DEFAULT_IO_TIMEOUT);
 				goto retry;
 			}
 			set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
@@ -1953,7 +1964,7 @@ retry:
 		flush_dcache_page(page);
 
 		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
-						page, NULL);
+						page, fsdata);
 		offset = 0;
 		towrite -= tocopy;
 		off += tocopy;
@@ -3457,12 +3468,17 @@ try_onemore:
 		}
 	}
 
+	/* init per sbi slab cache */
+	err = f2fs_init_xattr_caches(sbi);
+	if (err)
+		goto free_io_dummy;
+
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_err(sbi, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_io_dummy;
+		goto free_xattr_cache;
 	}
 
 	err = f2fs_get_valid_checkpoint(sbi);
@@ -3590,7 +3606,7 @@ try_onemore:
 			f2fs_err(sbi, "Cannot turn on quotas: error %d", err);
 	}
 #endif
-	/* if there are nt orphan nodes free them */
+	/* if there are any orphan inodes, free them */
 	err = f2fs_recover_orphan_inodes(sbi);
 	if (err)
 		goto free_meta;
@@ -3599,7 +3615,8 @@ try_onemore:
 		goto reset_checkpoint;
 
 	/* recover fsynced data */
-	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD) &&
+			!test_opt(sbi, NORECOVERY)) {
 		/*
 		 * mount should be failed, when device has readonly mode, and
 		 * previous checkpoint was not done by clean system shutdown.
@@ -3665,7 +3682,7 @@ reset_checkpoint:
 	 * If filesystem is not mounted as read-only then
 	 * do start the gc_thread.
 	 */
-	if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
+	if (F2FS_OPTION(sbi).bggc_mode != BGGC_MODE_OFF && !f2fs_readonly(sb)) {
 		/* After POR, we can run background GC thread.*/
 		err = f2fs_start_gc_thread(sbi);
 		if (err)
@@ -3734,6 +3751,8 @@ free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
 	sbi->meta_inode = NULL;
+free_xattr_cache:
+	f2fs_destroy_xattr_caches(sbi);
 free_io_dummy:
 	mempool_destroy(sbi->write_io_dummy);
 free_percpu:

fs/f2fs/sysfs.c

@@ -109,47 +109,47 @@ static ssize_t features_show(struct f2fs_attr *a,
 		return sprintf(buf, "0\n");
 
 	if (f2fs_sb_has_encrypt(sbi))
-		len += snprintf(buf, PAGE_SIZE - len, "%s",
+		len += scnprintf(buf, PAGE_SIZE - len, "%s",
 						"encryption");
 	if (f2fs_sb_has_blkzoned(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "blkzoned");
 	if (f2fs_sb_has_extra_attr(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "extra_attr");
 	if (f2fs_sb_has_project_quota(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "projquota");
 	if (f2fs_sb_has_inode_chksum(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "inode_checksum");
 	if (f2fs_sb_has_flexible_inline_xattr(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "flexible_inline_xattr");
 	if (f2fs_sb_has_quota_ino(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "quota_ino");
 	if (f2fs_sb_has_inode_crtime(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "inode_crtime");
 	if (f2fs_sb_has_lost_found(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "lost_found");
 	if (f2fs_sb_has_verity(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "verity");
 	if (f2fs_sb_has_sb_chksum(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "sb_checksum");
 	if (f2fs_sb_has_casefold(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "casefold");
 	if (f2fs_sb_has_compression(sbi))
-		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+		len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "compression");
-	len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+	len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "pin_file");
-	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+	len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
 	return len;
 }
 
@@ -185,6 +185,12 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 	return sprintf(buf, "(none)");
 }
 
+static ssize_t mounted_time_sec_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	return sprintf(buf, "%llu", SIT_I(sbi)->mounted_time);
+}
+
 #ifdef CONFIG_F2FS_STAT_FS
 static ssize_t moved_blocks_foreground_show(struct f2fs_attr *a,
 				struct f2fs_sb_info *sbi, char *buf)
@@ -233,16 +239,16 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 		int hot_count = sbi->raw_super->hot_ext_count;
 		int len = 0, i;
 
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 						"cold file extension:\n");
 		for (i = 0; i < cold_count; i++)
-			len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
+			len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
 								extlist[i]);
 
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 						"hot file extension:\n");
 		for (i = cold_count; i < cold_count + hot_count; i++)
-			len += snprintf(buf + len, PAGE_SIZE - len, "%s\n",
+			len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
 								extlist[i]);
 		return len;
 	}
@@ -544,6 +550,7 @@ F2FS_GENERAL_RO_ATTR(features);
 F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
 F2FS_GENERAL_RO_ATTR(unusable);
 F2FS_GENERAL_RO_ATTR(encoding);
+F2FS_GENERAL_RO_ATTR(mounted_time_sec);
 #ifdef CONFIG_F2FS_STAT_FS
 F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
 F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
@@ -573,7 +580,9 @@ F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY);
 #endif
 F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
 F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION);
+#endif
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -621,6 +630,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(reserved_blocks),
 	ATTR_LIST(current_reserved_blocks),
 	ATTR_LIST(encoding),
+	ATTR_LIST(mounted_time_sec),
 #ifdef CONFIG_F2FS_STAT_FS
 	ATTR_LIST(cp_foreground_calls),
 	ATTR_LIST(cp_background_calls),
@@ -654,7 +664,9 @@ static struct attribute *f2fs_feat_attrs[] = {
 #endif
 	ATTR_LIST(sb_checksum),
 	ATTR_LIST(casefold),
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 	ATTR_LIST(compression),
+#endif
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs_feat);

fs/f2fs/xattr.c

@@ -23,6 +23,25 @@
 #include "xattr.h"
 #include "segment.h"
 
+static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline)
+{
+	if (likely(size == sbi->inline_xattr_slab_size)) {
+		*is_inline = true;
+		return kmem_cache_zalloc(sbi->inline_xattr_slab, GFP_NOFS);
+	}
+	*is_inline = false;
+	return f2fs_kzalloc(sbi, size, GFP_NOFS);
+}
+
+static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr,
+							bool is_inline)
+{
+	if (is_inline)
+		kmem_cache_free(sbi->inline_xattr_slab, xattr_addr);
+	else
+		kvfree(xattr_addr);
+}
+
 static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
 		struct dentry *unused, struct inode *inode,
 		const char *name, void *buffer, size_t size)
@@ -301,7 +320,8 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr)
 static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 				unsigned int index, unsigned int len,
 				const char *name, struct f2fs_xattr_entry **xe,
-				void **base_addr, int *base_size)
+				void **base_addr, int *base_size,
+				bool *is_inline)
 {
 	void *cur_addr, *txattr_addr, *last_txattr_addr;
 	void *last_addr = NULL;
@@ -312,12 +332,12 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 	if (!xnid && !inline_size)
 		return -ENODATA;
 
-	*base_size = XATTR_SIZE(xnid, inode) + XATTR_PADDING_SIZE;
+	*base_size = XATTR_SIZE(inode) + XATTR_PADDING_SIZE;
-	txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS);
+	txattr_addr = xattr_alloc(F2FS_I_SB(inode), *base_size, is_inline);
 	if (!txattr_addr)
 		return -ENOMEM;
 
-	last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(xnid, inode);
+	last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(inode);
 
 	/* read from inline xattr */
 	if (inline_size) {
@@ -362,7 +382,7 @@ check:
 	*base_addr = txattr_addr;
 	return 0;
 out:
-	kvfree(txattr_addr);
+	xattr_free(F2FS_I_SB(inode), txattr_addr, *is_inline);
 	return err;
 }
 
@@ -499,6 +519,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	unsigned int size, len;
 	void *base_addr = NULL;
 	int base_size;
+	bool is_inline;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -509,7 +530,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 
 	down_read(&F2FS_I(inode)->i_xattr_sem);
 	error = lookup_all_xattrs(inode, ipage, index, len, name,
-				&entry, &base_addr, &base_size);
+				&entry, &base_addr, &base_size, &is_inline);
 	up_read(&F2FS_I(inode)->i_xattr_sem);
 	if (error)
 		return error;
@@ -532,14 +553,13 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	}
 	error = size;
 out:
-	kvfree(base_addr);
+	xattr_free(F2FS_I_SB(inode), base_addr, is_inline);
 	return error;
 }
 
 ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
 	struct inode *inode = d_inode(dentry);
-	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	struct f2fs_xattr_entry *entry;
 	void *base_addr, *last_base_addr;
 	int error = 0;
@@ -551,7 +571,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	if (error)
 		return error;
 
-	last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode);
+	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
 
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
@@ -609,7 +629,6 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 {
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr, *last_base_addr;
-	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	int found, newsize;
 	size_t len;
 	__u32 new_hsize;
@@ -633,7 +652,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (error)
 		return error;
 
-	last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode);
+	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
 
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, last_base_addr, index, len, name);
@@ -758,14 +777,34 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
-	/* protect xattr_ver */
-	down_write(&F2FS_I(inode)->i_sem);
 	down_write(&F2FS_I(inode)->i_xattr_sem);
 	err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
 	up_write(&F2FS_I(inode)->i_xattr_sem);
-	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 
 	f2fs_update_time(sbi, REQ_TIME);
 	return err;
 }
+
+int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi)
+{
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+	char slab_name[32];
+
+	sprintf(slab_name, "f2fs_xattr_entry-%u:%u", MAJOR(dev), MINOR(dev));
+
+	sbi->inline_xattr_slab_size = F2FS_OPTION(sbi).inline_xattr_size *
+					sizeof(__le32) + XATTR_PADDING_SIZE;
+
+	sbi->inline_xattr_slab = f2fs_kmem_cache_create(slab_name,
+					sbi->inline_xattr_slab_size);
+	if (!sbi->inline_xattr_slab)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi)
+{
+	kmem_cache_destroy(sbi->inline_xattr_slab);
+}

fs/f2fs/xattr.h

@@ -49,7 +49,7 @@ struct f2fs_xattr_entry {
 	__u8    e_name_index;
 	__u8    e_name_len;
 	__le16  e_value_size;   /* size of attribute value */
-	char    e_name[0];      /* attribute name */
+	char    e_name[];      /* attribute name */
 };
 
 #define XATTR_HDR(ptr)		((struct f2fs_xattr_header *)(ptr))
@@ -73,7 +73,8 @@ struct f2fs_xattr_entry {
 				entry = XATTR_NEXT_ENTRY(entry))
 #define VALID_XATTR_BLOCK_SIZE	(PAGE_SIZE - sizeof(struct node_footer))
 #define XATTR_PADDING_SIZE	(sizeof(__u32))
-#define XATTR_SIZE(x,i)		(((x) ? VALID_XATTR_BLOCK_SIZE : 0) +	\
+#define XATTR_SIZE(i)		((F2FS_I(i)->i_xattr_nid ?		\
+					VALID_XATTR_BLOCK_SIZE : 0) +	\
 						(inline_xattr_size(i)))
 #define MIN_OFFSET(i)		XATTR_ALIGN(inline_xattr_size(i) +	\
 						VALID_XATTR_BLOCK_SIZE)
@@ -130,6 +131,8 @@ extern int f2fs_setxattr(struct inode *, int, const char *,
 extern int f2fs_getxattr(struct inode *, int, const char *, void *,
 						size_t, struct page *);
 extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
+extern int f2fs_init_xattr_caches(struct f2fs_sb_info *);
+extern void f2fs_destroy_xattr_caches(struct f2fs_sb_info *);
 #else
 
 #define f2fs_xattr_handlers	NULL
@@ -150,6 +153,8 @@ static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
 {
 	return -EOPNOTSUPP;
 }
+static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { }
 #endif
 
 #ifdef CONFIG_F2FS_FS_SECURITY

include/linux/f2fs_fs.h

@@ -125,6 +125,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_RESIZEFS_FLAG		0x00004000
 #define CP_DISABLED_QUICK_FLAG		0x00002000
 #define CP_DISABLED_FLAG		0x00001000
 #define CP_QUOTA_NEED_FSCK_FLAG		0x00000800

include/trace/events/f2fs.h

@@ -153,7 +153,8 @@ TRACE_DEFINE_ENUM(CP_PAUSE);
 #define show_compress_algorithm(type)					\
 	__print_symbolic(type,						\
 		{ COMPRESS_LZO,		"LZO" },			\
-		{ COMPRESS_LZ4,		"LZ4" })
+		{ COMPRESS_LZ4,		"LZ4" },			\
+		{ COMPRESS_ZSTD,	"ZSTD" })
 
 struct f2fs_sb_info;
 struct f2fs_io_info;