1 files changed, 106 insertions, 65 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b58ab1157b7e..1761ad125f97 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -39,6 +39,7 @@
 static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
+	vm_flags_t flags = vmf->vma->vm_flags;
 	vm_fault_t ret;
 
 	ret = filemap_fault(vmf);
@@ -46,7 +47,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 		f2fs_update_iostat(F2FS_I_SB(inode), inode,
 					APP_MAPPED_READ_IO, F2FS_BLKSIZE);
 
-	trace_f2fs_filemap_fault(inode, vmf->pgoff, vmf->vma->vm_flags, ret);
+	trace_f2fs_filemap_fault(inode, vmf->pgoff, flags, ret);
 
 	return ret;
 }
@@ -394,9 +395,20 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	return f2fs_do_sync_file(file, start, end, datasync, false);
 }
 
-static bool __found_offset(struct address_space *mapping, block_t blkaddr,
-				pgoff_t index, int whence)
+static bool __found_offset(struct address_space *mapping,
+		struct dnode_of_data *dn, pgoff_t index, int whence)
 {
+	block_t blkaddr = f2fs_data_blkaddr(dn);
+	struct inode *inode = mapping->host;
+	bool compressed_cluster = false;
+
+	if (f2fs_compressed_file(inode)) {
+		block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page,
+		    ALIGN_DOWN(dn->ofs_in_node, F2FS_I(inode)->i_cluster_size));
+
+		compressed_cluster = first_blkaddr == COMPRESS_ADDR;
+	}
+
 	switch (whence) {
 	case SEEK_DATA:
 		if (__is_valid_data_blkaddr(blkaddr))
@@ -404,8 +416,12 @@ static bool __found_offset(struct address_space *mapping, block_t blkaddr,
 		if (blkaddr == NEW_ADDR &&
 		    xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY))
 			return true;
+		if (compressed_cluster)
+			return true;
 		break;
 	case SEEK_HOLE:
+		if (compressed_cluster)
+			return false;
 		if (blkaddr == NULL_ADDR)
 			return true;
 		break;
@@ -474,7 +490,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 				goto fail;
 			}
 
-			if (__found_offset(file->f_mapping, blkaddr,
+			if (__found_offset(file->f_mapping, &dn,
 							pgofs, whence)) {
 				f2fs_put_dnode(&dn);
 				goto found;
@@ -590,8 +606,10 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		f2fs_set_data_blkaddr(dn, NULL_ADDR);
 
 		if (__is_valid_data_blkaddr(blkaddr)) {
-			if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
-					DATA_GENERIC_ENHANCE))
+			if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE))
+				continue;
+			if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr,
+						DATA_GENERIC_ENHANCE))
 				continue;
 			if (compressed_cluster)
 				valid_blocks++;
@@ -818,8 +836,6 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
 	 */
 	if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE))
 		return true;
-	if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi))
-		return true;
 	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
 		return true;
 
@@ -1192,7 +1208,6 @@ next_dnode:
 			!f2fs_is_valid_blkaddr(sbi, *blkaddr,
 					DATA_GENERIC_ENHANCE)) {
 			f2fs_put_dnode(&dn);
-			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 			return -EFSCORRUPTED;
 		}
 
@@ -1478,7 +1493,6 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
 		if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr,
 					DATA_GENERIC_ENHANCE)) {
 			ret = -EFSCORRUPTED;
-			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 			break;
 		}
 
@@ -1662,10 +1676,12 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	}
 	filemap_invalidate_unlock(mapping);
 	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	if (ret)
+		return ret;
 
 	/* write out all moved pages, if possible */
 	filemap_invalidate_lock(mapping);
-	filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
+	ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
 	truncate_pagecache(inode, offset);
 	filemap_invalidate_unlock(mapping);
 
@@ -1731,9 +1747,11 @@ next_alloc:
 
 		f2fs_down_write(&sbi->pin_sem);
 
-		f2fs_lock_op(sbi);
-		f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
-		f2fs_unlock_op(sbi);
+		err = f2fs_allocate_pinning_section(sbi);
+		if (err) {
+			f2fs_up_write(&sbi->pin_sem);
+			goto out_err;
+		}
 
 		map.m_seg_type = CURSEG_COLD_DATA_PINNED;
 		err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_DIO);
@@ -2066,7 +2084,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 
 	inode_lock(inode);
 
-	if (!f2fs_disable_compressed_file(inode)) {
+	if (!f2fs_disable_compressed_file(inode) ||
+			f2fs_is_pinned_file(inode)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -2243,8 +2262,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
 		ret = f2fs_sync_fs(sb, 1);
-		if (ret)
+		if (ret) {
+			if (ret == -EIO)
+				ret = 0;
 			goto out;
+		}
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
 		break;
 	case F2FS_GOING_DOWN_NOSYNC:
@@ -2260,6 +2282,8 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 		set_sbi_flag(sbi, SBI_IS_DIRTY);
 		/* do checkpoint only */
 		ret = f2fs_sync_fs(sb, 1);
+		if (ret == -EIO)
+			ret = 0;
 		goto out;
 	default:
 		ret = -EINVAL;
@@ -2578,7 +2602,6 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 					.m_may_create = false };
 	struct extent_info ei = {};
 	pgoff_t pg_start, pg_end, next_pgofs;
-	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	unsigned int total = 0, sec_num;
 	block_t blk_end = 0;
 	bool fragmented = false;
@@ -2687,7 +2710,8 @@ do_map:
 		set_inode_flag(inode, FI_SKIP_WRITES);
 
 		idx = map.m_lblk;
-		while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
+		while (idx < map.m_lblk + map.m_len &&
+						cnt < BLKS_PER_SEG(sbi)) {
 			struct page *page;
 
 			page = f2fs_get_lock_data_page(inode, idx, true);
@@ -2707,7 +2731,7 @@ do_map:
 
 		map.m_lblk = idx;
 check:
-		if (map.m_lblk < pg_end && cnt < blk_per_seg)
+		if (map.m_lblk < pg_end && cnt < BLKS_PER_SEG(sbi))
 			goto do_map;
 
 		clear_inode_flag(inode, FI_SKIP_WRITES);
@@ -2976,8 +3000,8 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
 
 	if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num ||
 			__is_large_section(sbi)) {
-		f2fs_warn(sbi, "Can't flush %u in %d for segs_per_sec %u != 1",
-			  range.dev_num, sbi->s_ndevs, sbi->segs_per_sec);
+		f2fs_warn(sbi, "Can't flush %u in %d for SEGS_PER_SEC %u != 1",
+			  range.dev_num, sbi->s_ndevs, SEGS_PER_SEC(sbi));
 		return -EINVAL;
 	}
 
@@ -3183,6 +3207,7 @@ int f2fs_pin_file_control(struct inode *inode, bool inc)
 static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	__u32 pin;
 	int ret = 0;
 
@@ -3192,7 +3217,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
 
-	if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
 	ret = mnt_want_write_file(filp);
@@ -3205,9 +3230,18 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 		clear_inode_flag(inode, FI_PIN_FILE);
 		f2fs_i_gc_failures_write(inode, 0);
 		goto done;
+	} else if (f2fs_is_pinned_file(inode)) {
+		goto done;
 	}
 
-	if (f2fs_should_update_outplace(inode, NULL)) {
+	if (f2fs_sb_has_blkzoned(sbi) && F2FS_HAS_BLOCKS(inode)) {
+		ret = -EFBIG;
+		goto out;
+	}
+
+	/* Let's allow file pinning on zoned device. */
+	if (!f2fs_sb_has_blkzoned(sbi) &&
+	    f2fs_should_update_outplace(inode, NULL)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -3229,7 +3263,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 	set_inode_flag(inode, FI_PIN_FILE);
 	ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
 done:
-	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+	f2fs_update_time(sbi, REQ_TIME);
 out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
@@ -3438,10 +3472,8 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
 		if (!__is_valid_data_blkaddr(blkaddr))
 			continue;
 		if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
-					DATA_GENERIC_ENHANCE))) {
-			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+					DATA_GENERIC_ENHANCE)))
 			return -EFSCORRUPTED;
-		}
 	}
 
 	while (count) {
@@ -3588,10 +3620,10 @@ out:
 	return ret;
 }
 
-static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count,
+		unsigned int *reserved_blocks)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
-	unsigned int reserved_blocks = 0;
 	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
 	block_t blkaddr;
 	int i;
@@ -3603,10 +3635,8 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
 		if (!__is_valid_data_blkaddr(blkaddr))
 			continue;
 		if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
-					DATA_GENERIC_ENHANCE))) {
-			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+					DATA_GENERIC_ENHANCE)))
 			return -EFSCORRUPTED;
-		}
 	}
 
 	while (count) {
@@ -3614,40 +3644,53 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
 		blkcnt_t reserved;
 		int ret;
 
-		for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
-			blkaddr = f2fs_data_blkaddr(dn);
+		for (i = 0; i < cluster_size; i++) {
+			blkaddr = data_blkaddr(dn->inode, dn->node_page,
+						dn->ofs_in_node + i);
 
 			if (i == 0) {
-				if (blkaddr == COMPRESS_ADDR)
-					continue;
-				dn->ofs_in_node += cluster_size;
-				goto next;
+				if (blkaddr != COMPRESS_ADDR) {
+					dn->ofs_in_node += cluster_size;
+					goto next;
+				}
+				continue;
 			}
 
-			if (__is_valid_data_blkaddr(blkaddr)) {
+			/*
+			 * compressed cluster was not released due to it
+			 * fails in release_compress_blocks(), so NEW_ADDR
+			 * is a possible case.
+			 */
+			if (blkaddr == NEW_ADDR ||
+				__is_valid_data_blkaddr(blkaddr)) {
 				compr_blocks++;
 				continue;
 			}
-
-			f2fs_set_data_blkaddr(dn, NEW_ADDR);
 		}
 
 		reserved = cluster_size - compr_blocks;
-		ret = inc_valid_block_count(sbi, dn->inode, &reserved);
-		if (ret)
+
+		/* for the case all blocks in cluster were reserved */
+		if (reserved == 1)
+			goto next;
+
+		ret = inc_valid_block_count(sbi, dn->inode, &reserved, false);
+		if (unlikely(ret))
 			return ret;
 
-		if (reserved != cluster_size - compr_blocks)
-			return -ENOSPC;
+		for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+			if (f2fs_data_blkaddr(dn) == NULL_ADDR)
+				f2fs_set_data_blkaddr(dn, NEW_ADDR);
+		}
 
 		f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
 
-		reserved_blocks += reserved;
+		*reserved_blocks += reserved;
 next:
 		count -= cluster_size;
 	}
 
-	return reserved_blocks;
+	return 0;
 }
 
 static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
@@ -3671,9 +3714,6 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret)
 		return ret;
 
-	if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
-		goto out;
-
 	f2fs_balance_fs(sbi, true);
 
 	inode_lock(inode);
@@ -3683,6 +3723,9 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 		goto unlock_inode;
 	}
 
+	if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
+		goto unlock_inode;
+
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
@@ -3708,7 +3751,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
 		count = round_up(count, F2FS_I(inode)->i_cluster_size);
 
-		ret = reserve_compress_blocks(&dn, count);
+		ret = reserve_compress_blocks(&dn, count, &reserved_blocks);
 
 		f2fs_put_dnode(&dn);
 
@@ -3716,23 +3759,21 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 			break;
 
 		page_idx += count;
-		reserved_blocks += ret;
 	}
 
 	filemap_invalidate_unlock(inode->i_mapping);
 	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 
-	if (ret >= 0) {
+	if (!ret) {
 		clear_inode_flag(inode, FI_COMPRESS_RELEASED);
 		inode_set_ctime_current(inode);
 		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 unlock_inode:
 	inode_unlock(inode);
-out:
 	mnt_drop_write_file(filp);
 
-	if (ret >= 0) {
+	if (!ret) {
 		ret = put_user(reserved_blocks, (u64 __user *)arg);
 	} else if (reserved_blocks &&
 			atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
@@ -3877,8 +3918,6 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 						DATA_GENERIC_ENHANCE)) {
 				ret = -EFSCORRUPTED;
 				f2fs_put_dnode(&dn);
-				f2fs_handle_error(sbi,
-						ERROR_INVALID_BLKADDR);
 				goto out;
 			}
 
@@ -3981,16 +4020,20 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
 				sizeof(option)))
 		return -EFAULT;
 
-	if (!f2fs_compressed_file(inode) ||
-			option.log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
-			option.log_cluster_size > MAX_COMPRESS_LOG_SIZE ||
-			option.algorithm >= COMPRESS_MAX)
+	if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
+		option.log_cluster_size > MAX_COMPRESS_LOG_SIZE ||
+		option.algorithm >= COMPRESS_MAX)
 		return -EINVAL;
 
 	file_start_write(filp);
 	inode_lock(inode);
 
 	f2fs_down_write(&F2FS_I(inode)->i_sem);
+	if (!f2fs_compressed_file(inode)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) {
 		ret = -EBUSY;
 		goto out;
@@ -4066,7 +4109,6 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	pgoff_t page_idx = 0, last_idx;
-	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	int cluster_size = fi->i_cluster_size;
 	int count, ret;
 
@@ -4110,7 +4152,7 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 		if (ret < 0)
 			break;
 
-		if (get_dirty_pages(inode) >= blk_per_seg) {
+		if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) {
 			ret = filemap_fdatawrite(inode->i_mapping);
 			if (ret < 0)
 				break;
@@ -4145,7 +4187,6 @@ static int f2fs_ioc_compress_file(struct file *filp)
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	pgoff_t page_idx = 0, last_idx;
-	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	int cluster_size = F2FS_I(inode)->i_cluster_size;
 	int count, ret;
 
@@ -4188,7 +4229,7 @@ static int f2fs_ioc_compress_file(struct file *filp)
 		if (ret < 0)
 			break;
 
-		if (get_dirty_pages(inode) >= blk_per_seg) {
+		if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) {
 			ret = filemap_fdatawrite(inode->i_mapping);
 			if (ret < 0)
 				break;