1 files changed, 126 insertions, 70 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5474aaa274b9..88b124677189 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * fs/f2fs/file.c
  *
  * Copyright (c) 2012 Samsung Electronics Co., Ltd.
  *             http://www.samsung.com/
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
@@ -50,7 +47,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dnode_of_data dn;
+	struct dnode_of_data dn = { .node_changed = false };
 	int err;
 
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -62,19 +59,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
-	/* block allocation */
-	f2fs_lock_op(sbi);
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = f2fs_reserve_block(&dn, page->index);
-	if (err) {
-		f2fs_unlock_op(sbi);
-		goto out;
-	}
-	f2fs_put_dnode(&dn);
-	f2fs_unlock_op(sbi);
-
-	f2fs_balance_fs(sbi, dn.node_changed);
-
 	file_update_time(vmf->vma->vm_file);
 	down_read(&F2FS_I(inode)->i_mmap_sem);
 	lock_page(page);
@@ -86,11 +70,28 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		goto out_sem;
 	}
 
+	/* block allocation */
+	__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	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 */
+	f2fs_wait_on_page_writeback(page, DATA, false);
+
+	/* wait for GCed page writeback via META_MAPPING */
+	f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
+
 	/*
 	 * check to see if the page is mapped already (no holes)
 	 */
 	if (PageMappedToDisk(page))
-		goto mapped;
+		goto out_sem;
 
 	/* page is wholly or partially inside EOF */
 	if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
@@ -105,21 +106,15 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		SetPageUptodate(page);
 
 	f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
+	f2fs_update_time(sbi, REQ_TIME);
 
 	trace_f2fs_vm_page_mkwrite(page, DATA);
-mapped:
-	/* fill the page */
-	f2fs_wait_on_page_writeback(page, DATA, false);
-
-	/* wait for GCed page writeback via META_MAPPING */
-	if (f2fs_post_read_required(inode))
-		f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr);
-
 out_sem:
 	up_read(&F2FS_I(inode)->i_mmap_sem);
-out:
+
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	sb_end_pagefault(inode->i_sb);
-	f2fs_update_time(sbi, REQ_TIME);
 err:
 	return block_page_mkwrite_return(err);
 }
@@ -215,7 +210,8 @@ 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)))
+	if (unlikely(f2fs_readonly(inode->i_sb) ||
+				is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		return 0;
 
 	trace_f2fs_sync_file_enter(inode);
@@ -590,7 +586,8 @@ truncate_out:
 	return 0;
 }
 
-int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock,
+							bool buf_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
@@ -598,6 +595,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 	int count = 0, err = 0;
 	struct page *ipage;
 	bool truncate_page = false;
+	int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO;
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
@@ -607,7 +605,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto free_partial;
 
 	if (lock)
-		f2fs_lock_op(sbi);
+		__do_map_lock(sbi, flag, true);
 
 	ipage = f2fs_get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
@@ -645,7 +643,7 @@ free_next:
 	err = f2fs_truncate_inode_blocks(inode, free_from);
 out:
 	if (lock)
-		f2fs_unlock_op(sbi);
+		__do_map_lock(sbi, flag, false);
 free_partial:
 	/* lastly zero out the first data page */
 	if (!err)
@@ -680,7 +678,7 @@ int f2fs_truncate(struct inode *inode)
 			return err;
 	}
 
-	err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
+	err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false);
 	if (err)
 		return err;
 
@@ -789,9 +787,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 		!uid_eq(attr->ia_uid, inode->i_uid)) ||
 		(attr->ia_valid & ATTR_GID &&
 		!gid_eq(attr->ia_gid, inode->i_gid))) {
+		f2fs_lock_op(F2FS_I_SB(inode));
 		err = dquot_transfer(inode, attr);
-		if (err)
+		if (err) {
+			set_sbi_flag(F2FS_I_SB(inode),
+					SBI_QUOTA_NEED_REPAIR);
+			f2fs_unlock_op(F2FS_I_SB(inode));
 			return err;
+		}
+		/*
+		 * update uid/gid under lock_op(), so that dquot and inode can
+		 * be updated atomically.
+		 */
+		if (attr->ia_valid & ATTR_UID)
+			inode->i_uid = attr->ia_uid;
+		if (attr->ia_valid & ATTR_GID)
+			inode->i_gid = attr->ia_gid;
+		f2fs_mark_inode_dirty_sync(inode, true);
+		f2fs_unlock_op(F2FS_I_SB(inode));
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
@@ -1246,7 +1259,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	new_size = i_size_read(inode) - len;
 	truncate_pagecache(inode, new_size);
 
-	ret = f2fs_truncate_blocks(inode, new_size, true);
+	ret = f2fs_truncate_blocks(inode, new_size, true, false);
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
@@ -1431,7 +1444,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	f2fs_balance_fs(sbi, true);
 
 	down_write(&F2FS_I(inode)->i_mmap_sem);
-	ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
+	ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false);
 	up_write(&F2FS_I(inode)->i_mmap_sem);
 	if (ret)
 		return ret;
@@ -1978,7 +1991,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!blk_queue_discard(q))
+	if (!f2fs_hw_support_discard(F2FS_SB(sb)))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&range, (struct fstrim_range __user *)arg,
@@ -2162,6 +2175,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"Skipping Checkpoint. Checkpoints currently disabled.");
+		return -EINVAL;
+	}
+
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
@@ -2533,6 +2552,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
 	if (f2fs_readonly(sbi->sb))
 		return -EROFS;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+		return -EINVAL;
+
 	if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
 							sizeof(range)))
 		return -EFAULT;
@@ -2591,13 +2613,29 @@ static int f2fs_ioc_get_features(struct file *filp, unsigned long arg)
 }
 
 #ifdef CONFIG_QUOTA
+int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
+{
+	struct dquot *transfer_to[MAXQUOTAS] = {};
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct super_block *sb = sbi->sb;
+	int err = 0;
+
+	transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
+	if (!IS_ERR(transfer_to[PRJQUOTA])) {
+		err = __dquot_transfer(inode, transfer_to);
+		if (err)
+			set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+		dqput(transfer_to[PRJQUOTA]);
+	}
+	return err;
+}
+
 static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct super_block *sb = sbi->sb;
-	struct dquot *transfer_to[MAXQUOTAS] = {};
 	struct page *ipage;
 	kprojid_t kprojid;
 	int err;
@@ -2617,53 +2655,45 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
 	if (projid_eq(kprojid, F2FS_I(inode)->i_projid))
 		return 0;
 
-	err = mnt_want_write_file(filp);
-	if (err)
-		return err;
-
 	err = -EPERM;
-	inode_lock(inode);
-
 	/* Is it quota file? Do not allow user to mess with it */
 	if (IS_NOQUOTA(inode))
-		goto out_unlock;
+		return err;
 
 	ipage = f2fs_get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage)) {
-		err = PTR_ERR(ipage);
-		goto out_unlock;
-	}
+	if (IS_ERR(ipage))
+		return PTR_ERR(ipage);
 
 	if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize,
 								i_projid)) {
 		err = -EOVERFLOW;
 		f2fs_put_page(ipage, 1);
-		goto out_unlock;
+		return err;
 	}
 	f2fs_put_page(ipage, 1);
 
 	err = dquot_initialize(inode);
 	if (err)
-		goto out_unlock;
+		return err;
 
-	transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
-	if (!IS_ERR(transfer_to[PRJQUOTA])) {
-		err = __dquot_transfer(inode, transfer_to);
-		dqput(transfer_to[PRJQUOTA]);
-		if (err)
-			goto out_dirty;
-	}
+	f2fs_lock_op(sbi);
+	err = f2fs_transfer_project_quota(inode, kprojid);
+	if (err)
+		goto out_unlock;
 
 	F2FS_I(inode)->i_projid = kprojid;
 	inode->i_ctime = current_time(inode);
-out_dirty:
 	f2fs_mark_inode_dirty_sync(inode, true);
 out_unlock:
-	inode_unlock(inode);
-	mnt_drop_write_file(filp);
+	f2fs_unlock_op(sbi);
 	return err;
 }
 #else
+int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
+{
+	return 0;
+}
+
 static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
 {
 	if (projid != F2FS_DEF_PROJID)
@@ -2736,6 +2766,30 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
 	return 0;
 }
 
+static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa)
+{
+	/*
+	 * Project Quota ID state is only allowed to change from within the init
+	 * namespace. Enforce that restriction only if we are trying to change
+	 * the quota ID state. Everything else is allowed in user namespaces.
+	 */
+	if (current_user_ns() == &init_user_ns)
+		return 0;
+
+	if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid)
+		return -EINVAL;
+
+	if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) {
+		if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT))
+			return -EINVAL;
+	} else {
+		if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -2763,19 +2817,20 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
 		return err;
 
 	inode_lock(inode);
+	err = f2fs_ioctl_check_project(inode, &fa);
+	if (err)
+		goto out;
 	flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) |
 				(flags & F2FS_FL_XFLAG_VISIBLE);
 	err = __f2fs_ioc_setflags(inode, flags);
-	inode_unlock(inode);
-	mnt_drop_write_file(filp);
 	if (err)
-		return err;
+		goto out;
 
 	err = f2fs_ioc_setproject(filp, fa.fsx_projid);
-	if (err)
-		return err;
-
-	return 0;
+out:
+	inode_unlock(inode);
+	mnt_drop_write_file(filp);
+	return err;
 }
 
 int f2fs_pin_file_control(struct inode *inode, bool inc)
@@ -2992,7 +3047,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 				if (!f2fs_overwrite_io(inode, iocb->ki_pos,
 						iov_iter_count(from)) ||
 					f2fs_has_inline_data(inode) ||
-					f2fs_force_buffered_io(inode, WRITE)) {
+					f2fs_force_buffered_io(inode,
+							iocb, from)) {
 						clear_inode_flag(inode,
 								FI_NO_PREALLOC);
 						inode_unlock(inode);