1 files changed, 106 insertions, 50 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6bd3de64f2a8..42faaed6a02d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -35,6 +35,17 @@
 #include <trace/events/f2fs.h>
 #include <uapi/linux/f2fs.h>
 
+static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size)
+{
+	loff_t old_size = i_size_read(inode);
+
+	if (old_size >= new_size)
+		return;
+
+	/* zero or drop pages only in range of [old_size, new_size] */
+	truncate_pagecache(inode, old_size);
+}
+
 static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	file_update_time(vmf->vma->vm_file);
 	filemap_invalidate_lock_shared(inode->i_mapping);
+
 	folio_lock(folio);
 	if (unlikely(folio->mapping != inode->i_mapping ||
 			folio_pos(folio) > i_size_read(inode) ||
@@ -473,7 +489,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 			}
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
@@ -532,8 +548,9 @@ static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
 	return -EINVAL;
 }
 
-static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+static int f2fs_file_mmap_prepare(struct vm_area_desc *desc)
 {
+	struct file *file = desc->file;
 	struct inode *inode = file_inode(file);
 
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
@@ -543,7 +560,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EOPNOTSUPP;
 
 	file_accessed(file);
-	vma->vm_ops = &f2fs_file_vm_ops;
+	desc->vm_ops = &f2fs_file_vm_ops;
 
 	f2fs_down_read(&F2FS_I(inode)->i_sem);
 	set_inode_flag(inode, FI_MMAP_FILE);
@@ -612,7 +629,10 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 	if (err)
 		return err;
 
-	return finish_preallocate_blocks(inode);
+	err = finish_preallocate_blocks(inode);
+	if (!err)
+		atomic_inc(&F2FS_I(inode)->open_count);
+	return err;
 }
 
 void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -691,7 +711,7 @@ next:
 		 * once we invalidate valid blkaddr in range [ofs, ofs + count],
 		 * we will invalidate all blkaddr in the whole range.
 		 */
-		fofs = f2fs_start_bidx_of_node(ofs_of_node(&dn->node_folio->page),
+		fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_folio),
 							dn->inode) + ofs;
 		f2fs_update_read_extent_cache_range(dn, fofs, 0, len);
 		f2fs_update_age_extent_cache_range(dn, fofs, len);
@@ -798,12 +818,12 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
-	count = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+	count = ADDRS_PER_PAGE(dn.node_folio, inode);
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
 
-	if (dn.ofs_in_node || IS_INODE(&dn.node_folio->page)) {
+	if (dn.ofs_in_node || IS_INODE(dn.node_folio)) {
 		f2fs_truncate_data_blocks_range(&dn, count);
 		free_from += count;
 	}
@@ -1026,11 +1046,24 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 {
 	struct inode *inode = d_inode(dentry);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int err;
 
-	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
+	err = setattr_prepare(idmap, dentry, attr);
+	if (err)
+		return err;
+
+	err = fscrypt_prepare_setattr(dentry, attr);
+	if (err)
+		return err;
+
+	err = fsverity_prepare_setattr(dentry, attr);
+	if (err)
+		return err;
+
 	if (unlikely(IS_IMMUTABLE(inode)))
 		return -EPERM;
 
@@ -1047,20 +1080,19 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			!IS_ALIGNED(attr->ia_size,
 			F2FS_BLK_TO_BYTES(fi->i_cluster_size)))
 			return -EINVAL;
+		/*
+		 * To prevent scattered pin block generation, we don't allow
+		 * smaller/equal size unaligned truncation for pinned file.
+		 * We only support overwrite IO to pinned file, so don't
+		 * care about larger size truncation.
+		 */
+		if (f2fs_is_pinned_file(inode) &&
+			attr->ia_size <= i_size_read(inode) &&
+			!IS_ALIGNED(attr->ia_size,
+			F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi))))
+			return -EINVAL;
 	}
 
-	err = setattr_prepare(idmap, dentry, attr);
-	if (err)
-		return err;
-
-	err = fscrypt_prepare_setattr(dentry, attr);
-	if (err)
-		return err;
-
-	err = fsverity_prepare_setattr(dentry, attr);
-	if (err)
-		return err;
-
 	if (is_quota_modification(idmap, inode, attr)) {
 		err = f2fs_dquot_initialize(inode);
 		if (err)
@@ -1068,12 +1100,11 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 	if (i_uid_needs_update(idmap, attr, inode) ||
 	    i_gid_needs_update(idmap, attr, inode)) {
-		f2fs_lock_op(F2FS_I_SB(inode));
+		f2fs_lock_op(sbi);
 		err = dquot_transfer(idmap, inode, attr);
 		if (err) {
-			set_sbi_flag(F2FS_I_SB(inode),
-					SBI_QUOTA_NEED_REPAIR);
-			f2fs_unlock_op(F2FS_I_SB(inode));
+			set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+			f2fs_unlock_op(sbi);
 			return err;
 		}
 		/*
@@ -1083,7 +1114,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		i_uid_update(idmap, attr, inode);
 		i_gid_update(idmap, attr, inode);
 		f2fs_mark_inode_dirty_sync(inode, true);
-		f2fs_unlock_op(F2FS_I_SB(inode));
+		f2fs_unlock_op(sbi);
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
@@ -1109,6 +1140,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 		filemap_invalidate_lock(inode->i_mapping);
 
+		if (attr->ia_size > old_size)
+			f2fs_zero_post_eof_page(inode, attr->ia_size);
 		truncate_setsize(inode, attr->ia_size);
 
 		if (attr->ia_size <= old_size)
@@ -1144,7 +1177,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	f2fs_mark_inode_dirty_sync(inode, true);
 
 	/* inode change will produce dirty node pages flushed by checkpoint */
-	f2fs_balance_fs(F2FS_I_SB(inode), true);
+	f2fs_balance_fs(sbi, true);
 
 	return err;
 }
@@ -1204,7 +1237,7 @@ int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 			return err;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
 
 		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
@@ -1227,6 +1260,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (ret)
 		return ret;
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
@@ -1299,7 +1336,7 @@ next_dnode:
 		goto next;
 	}
 
-	done = min((pgoff_t)ADDRS_PER_PAGE(&dn.node_folio->page, inode) -
+	done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, inode) -
 							dn.ofs_in_node, len);
 	for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
 		*blkaddr = f2fs_data_blkaddr(&dn);
@@ -1388,7 +1425,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 			}
 
 			ilen = min((pgoff_t)
-				ADDRS_PER_PAGE(&dn.node_folio->page, dst_inode) -
+				ADDRS_PER_PAGE(dn.node_folio, dst_inode) -
 						dn.ofs_in_node, len - i);
 			do {
 				dn.data_blkaddr = f2fs_data_blkaddr(&dn);
@@ -1430,7 +1467,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 
 			memcpy_folio(fdst, 0, fsrc, 0, PAGE_SIZE);
 			folio_mark_dirty(fdst);
-			set_page_private_gcing(&fdst->page);
+			folio_set_f2fs_gcing(fdst);
 			f2fs_folio_put(fdst, true);
 			f2fs_folio_put(fsrc, true);
 
@@ -1510,6 +1547,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
+	f2fs_zero_post_eof_page(inode, offset + len);
+
 	f2fs_lock_op(sbi);
 	f2fs_drop_extent_tree(inode);
 	truncate_pagecache(inode, offset);
@@ -1631,6 +1670,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	if (ret)
 		return ret;
 
+	filemap_invalidate_lock(mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(mapping);
+
 	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
@@ -1678,7 +1721,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 				goto out;
 			}
 
-			end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+			end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 			end = min(pg_end, end_offset - dn.ofs_in_node + index);
 
 			ret = f2fs_do_zero_range(&dn, index, end);
@@ -1762,6 +1805,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	/* avoid gc operation during block exchange */
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(mapping);
+
+	f2fs_zero_post_eof_page(inode, offset + len);
 	truncate_pagecache(inode, offset);
 
 	while (!ret && idx > pg_start) {
@@ -1819,6 +1864,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
 	if (err)
 		return err;
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	f2fs_balance_fs(sbi, true);
 
 	pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
@@ -1853,9 +1902,8 @@ next_alloc:
 			}
 		}
 
-		if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ?
-			ZONED_PIN_SEC_REQUIRED_COUNT :
-			GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
+		if (has_not_enough_free_secs(sbi, 0,
+				sbi->reserved_pin_section)) {
 			f2fs_down_write(&sbi->gc_lock);
 			stat_inc_gc_call_count(sbi, FOREGROUND);
 			err = f2fs_gc(sbi, &gc_control);
@@ -1993,6 +2041,9 @@ out:
 
 static int f2fs_release_file(struct inode *inode, struct file *filp)
 {
+	if (atomic_dec_and_test(&F2FS_I(inode)->open_count))
+		f2fs_remove_donate_inode(inode);
+
 	/*
 	 * f2fs_release_file is called at every close calls. So we should
 	 * not drop any inmemory pages by close called by other process.
@@ -2943,7 +2994,7 @@ do_map:
 			f2fs_folio_wait_writeback(folio, DATA, true, true);
 
 			folio_mark_dirty(folio);
-			set_page_private_gcing(&folio->page);
+			folio_set_f2fs_gcing(folio);
 			f2fs_folio_put(folio, true);
 
 			idx++;
@@ -3356,7 +3407,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
 }
 #endif
 
-int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int f2fs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -3380,7 +3431,7 @@ int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int f2fs_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	u32 fsflags = fa->flags, mask = F2FS_SETTABLE_FS_FL;
@@ -3841,7 +3892,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 			break;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
 		count = round_up(count, fi->i_cluster_size);
 
@@ -4019,7 +4070,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 			break;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
 		count = round_up(count, fi->i_cluster_size);
 
@@ -4183,7 +4234,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 			goto out;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - index);
 		for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
 			struct block_device *cur_bdev;
@@ -4380,7 +4431,7 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
 		f2fs_folio_wait_writeback(folio, DATA, true, true);
 
 		folio_mark_dirty(folio);
-		set_page_private_gcing(&folio->page);
+		folio_set_f2fs_gcing(folio);
 		redirty_idx = folio_next_index(folio);
 		folio_unlock(folio);
 		folio_put_refs(folio, 2);
@@ -4790,6 +4841,7 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	const loff_t pos = iocb->ki_pos;
 	ssize_t ret;
+	bool dio;
 
 	if (!f2fs_is_compress_backend_ready(inode))
 		return -EOPNOTSUPP;
@@ -4798,12 +4850,15 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos,
 					iov_iter_count(to), READ);
 
+	dio = f2fs_should_use_dio(inode, iocb, to);
+
 	/* In LFS mode, if there is inflight dio, wait for its completion */
 	if (f2fs_lfs_mode(F2FS_I_SB(inode)) &&
-	    get_pages(F2FS_I_SB(inode), F2FS_DIO_WRITE))
+	    get_pages(F2FS_I_SB(inode), F2FS_DIO_WRITE) &&
+		(!f2fs_is_pinned_file(inode) || !dio))
 		inode_dio_wait(inode);
 
-	if (f2fs_should_use_dio(inode, iocb, to)) {
+	if (dio) {
 		ret = f2fs_dio_read_iter(iocb, to);
 	} else {
 		ret = filemap_read(iocb, to, 0);
@@ -4811,8 +4866,7 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			f2fs_update_iostat(F2FS_I_SB(inode), inode,
 						APP_BUFFERED_READ_IO, ret);
 	}
-	if (trace_f2fs_dataread_end_enabled())
-		trace_f2fs_dataread_end(inode, pos, ret);
+	trace_f2fs_dataread_end(inode, pos, ret);
 	return ret;
 }
 
@@ -4835,8 +4889,7 @@ static ssize_t f2fs_file_splice_read(struct file *in, loff_t *ppos,
 		f2fs_update_iostat(F2FS_I_SB(inode), inode,
 				   APP_BUFFERED_READ_IO, ret);
 
-	if (trace_f2fs_dataread_end_enabled())
-		trace_f2fs_dataread_end(inode, pos, ret);
+	trace_f2fs_dataread_end(inode, pos, ret);
 	return ret;
 }
 
@@ -4860,6 +4913,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	err = file_modified(file);
 	if (err)
 		return err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from));
+	filemap_invalidate_unlock(inode->i_mapping);
 	return count;
 }
 
@@ -5177,8 +5234,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			f2fs_dio_write_iter(iocb, from, &may_need_sync) :
 			f2fs_buffered_write_iter(iocb, from);
 
-		if (trace_f2fs_datawrite_end_enabled())
-			trace_f2fs_datawrite_end(inode, orig_pos, ret);
+		trace_f2fs_datawrite_end(inode, orig_pos, ret);
 	}
 
 	/* Don't leave any preallocated blocks around past i_size. */
@@ -5376,7 +5432,7 @@ const struct file_operations f2fs_file_operations = {
 	.iopoll		= iocb_bio_iopoll,
 	.open		= f2fs_file_open,
 	.release	= f2fs_release_file,
-	.mmap		= f2fs_file_mmap,
+	.mmap_prepare	= f2fs_file_mmap_prepare,
 	.flush		= f2fs_file_flush,
 	.fsync		= f2fs_sync_file,
 	.fallocate	= f2fs_fallocate,