Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've addressed some performance issues such as lock
  contention, misbehaving compress_cache, allowing extent_cache for
  compressed files, and new sysfs to adjust ra_size for fadvise.

  In order to diagnose the performance issues quickly, we also added an
  iostat which shows the IO latencies periodically.

  On the stability side, we've found two memory leakage cases in the
  error path in compression flow. And, we've also fixed various corner
  cases in fiemap, quota, checkpoint=disable, zstd, and so on.

  Enhancements:
   - avoid long checkpoint latency by releasing nat_tree_lock
   - collect and show iostats periodically
   - support extent_cache for compressed files
   - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL)
   - report f2fs GC status via sysfs
   - add discard_unit=%s in mount option to handle zoned device

  Bug fixes:
   - fix two memory leakages when an error happens in the compressed IO flow
   - fix commpress_cache to get the right LBA
   - fix fiemap to deal with compressed case correctly
   - fix wrong EIO returns due to SBI_NEED_FSCK
   - fix missing writes when enabling checkpoint back
   - fix quota deadlock
   - fix zstd level mount option

  In addition to the above major updates, we've cleaned up several code
  paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity
  check, and typos"

* tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits)
  f2fs: should put a page beyond EOF when preparing a write
  f2fs: deallocate compressed pages when error happens
  f2fs: enable realtime discard iff device supports discard
  f2fs: guarantee to write dirty data when enabling checkpoint back
  f2fs: fix to unmap pages from userspace process in punch_hole()
  f2fs: fix unexpected ENOENT comes from f2fs_map_blocks()
  f2fs: fix to account missing .skipped_gc_rwsem
  f2fs: adjust unlock order for cleanup
  f2fs: Don't create discard thread when device doesn't support realtime discard
  f2fs: rebuild nat_bits during umount
  f2fs: introduce periodic iostat io latency traces
  f2fs: separate out iostat feature
  f2fs: compress: do sanity check on cluster
  f2fs: fix description about main_blkaddr node
  f2fs: convert S_IRUGO to 0444
  f2fs: fix to keep compatibility of fault injection interface
  f2fs: support fault injection for f2fs_kmem_cache_alloc()
  f2fs: compress: allow write compress released file after truncate to zero
  f2fs: correct comment in segment.h
  f2fs: improve sbi status info in debugfs/f2fs/status
  ...

1 files changed, 59 insertions, 11 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 1ff333755721..9c8ef33bd8d3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -23,6 +23,7 @@
 #include <linux/nls.h>
 #include <linux/sched/signal.h>
 #include <linux/fileattr.h>
+#include <linux/fadvise.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -30,6 +31,7 @@
 #include "xattr.h"
 #include "acl.h"
 #include "gc.h"
+#include "iostat.h"
 #include <trace/events/f2fs.h>
 #include <uapi/linux/f2fs.h>
 
@@ -258,8 +260,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	};
 	unsigned int seq_id = 0;
 
-	if (unlikely(f2fs_readonly(inode->i_sb) ||
-				is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+	if (unlikely(f2fs_readonly(inode->i_sb)))
 		return 0;
 
 	trace_f2fs_sync_file_enter(inode);
@@ -273,7 +274,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 	ret = file_write_and_wait_range(file, start, end);
 	clear_inode_flag(inode, FI_NEED_IPU);
 
-	if (ret) {
+	if (ret || is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
 		trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
 		return ret;
 	}
@@ -298,6 +299,18 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
 				f2fs_exist_written_data(sbi, ino, UPDATE_INO))
 			goto flush_out;
 		goto out;
+	} else {
+		/*
+		 * for OPU case, during fsync(), node can be persisted before
+		 * data when lower device doesn't support write barrier, result
+		 * in data corruption after SPO.
+		 * So for strict fsync mode, force to use atomic write sematics
+		 * to keep write order in between data/node and last node to
+		 * avoid potential data corruption.
+		 */
+		if (F2FS_OPTION(sbi).fsync_mode ==
+				FSYNC_MODE_STRICT && !atomic)
+			atomic = true;
 	}
 go_write:
 	/*
@@ -737,6 +750,14 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		return err;
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
+	/*
+	 * For compressed file, after release compress blocks, don't allow write
+	 * direct, but we should allow write direct after truncate to zero.
+	 */
+	if (f2fs_compressed_file(inode) && !free_from
+			&& is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
+		clear_inode_flag(inode, FI_COMPRESS_RELEASED);
+
 	if (from != free_from) {
 		err = f2fs_truncate_partial_cluster(inode, from, lock);
 		if (err)
@@ -1082,7 +1103,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		}
 
 		if (pg_start < pg_end) {
-			struct address_space *mapping = inode->i_mapping;
 			loff_t blk_start, blk_end;
 			struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
@@ -1092,16 +1112,15 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 			blk_end = (loff_t)pg_end << PAGE_SHIFT;
 
 			down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-			filemap_invalidate_lock(mapping);
+			filemap_invalidate_lock(inode->i_mapping);
 
-			truncate_inode_pages_range(mapping, blk_start,
-					blk_end - 1);
+			truncate_pagecache_range(inode, blk_start, blk_end - 1);
 
 			f2fs_lock_op(sbi);
 			ret = f2fs_truncate_hole(inode, pg_start, pg_end);
 			f2fs_unlock_op(sbi);
 
-			filemap_invalidate_unlock(mapping);
+			filemap_invalidate_unlock(inode->i_mapping);
 			up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		}
 	}
@@ -3473,8 +3492,8 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 		released_blocks += ret;
 	}
 
-	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_unlock(inode->i_mapping);
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 out:
 	inode_unlock(inode);
 
@@ -3626,8 +3645,8 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 		reserved_blocks += ret;
 	}
 
-	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_unlock(inode->i_mapping);
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
 	if (ret >= 0) {
 		clear_inode_flag(inode, FI_COMPRESS_RELEASED);
@@ -4290,7 +4309,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			 * back to buffered IO.
 			 */
 			if (!f2fs_force_buffered_io(inode, iocb, from) &&
-					allow_outplace_dio(inode, iocb, from))
+					f2fs_lfs_mode(F2FS_I_SB(inode)))
 				goto write;
 		}
 		preallocated = true;
@@ -4330,6 +4349,34 @@ out:
 	return ret;
 }
 
+static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len,
+		int advice)
+{
+	struct inode *inode;
+	struct address_space *mapping;
+	struct backing_dev_info *bdi;
+
+	if (advice == POSIX_FADV_SEQUENTIAL) {
+		inode = file_inode(filp);
+		if (S_ISFIFO(inode->i_mode))
+			return -ESPIPE;
+
+		mapping = filp->f_mapping;
+		if (!mapping || len < 0)
+			return -EINVAL;
+
+		bdi = inode_to_bdi(mapping->host);
+		filp->f_ra.ra_pages = bdi->ra_pages *
+			F2FS_I_SB(inode)->seq_file_ra_mul;
+		spin_lock(&filp->f_lock);
+		filp->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&filp->f_lock);
+		return 0;
+	}
+
+	return generic_fadvise(filp, offset, len, advice);
+}
+
 #ifdef CONFIG_COMPAT
 struct compat_f2fs_gc_range {
 	u32 sync;
@@ -4458,4 +4505,5 @@ const struct file_operations f2fs_file_operations = {
 #endif
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
+	.fadvise	= f2fs_file_fadvise,
 };