1 files changed, 122 insertions, 53 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 11bc4c69bf16..ffb85a7f0e7c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -46,6 +46,7 @@
 #include "truncate.h"
 
 #include <trace/events/ext4.h>
+#include <trace/events/android_fs.h>
 
 #define MPAGE_DA_EXTENT_TAIL 0x01
 
@@ -423,7 +424,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
 {
 	int ret;
 
-	if (ext4_encrypted_inode(inode))
+	if (IS_ENCRYPTED(inode))
 		return fscrypt_zeroout_range(inode, lblk, pblk, len);
 
 	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
@@ -1164,7 +1165,7 @@ int do_journal_get_write_access(handle_t *handle,
 	return ret;
 }
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#ifdef CONFIG_FS_ENCRYPTION
 static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 				  get_block_t *get_block)
 {
@@ -1231,8 +1232,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 		    (block_start < from || block_end > to)) {
 			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			*wait_bh++ = bh;
-			decrypt = ext4_encrypted_inode(inode) &&
-				S_ISREG(inode->i_mode);
+			decrypt = IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
 		}
 	}
 	/*
@@ -1246,8 +1246,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	if (unlikely(err))
 		page_zero_new_buffers(page, from, to);
 	else if (decrypt)
-		err = fscrypt_decrypt_page(page->mapping->host, page,
-				PAGE_SIZE, 0, page->index);
+		err = fscrypt_decrypt_pagecache_blocks(page, PAGE_SIZE, 0);
 	return err;
 }
 #endif
@@ -1267,6 +1266,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
+	if (trace_android_fs_datawrite_start_enabled()) {
+		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+		path = android_fstrace_get_pathname(pathbuf,
+						    MAX_TRACE_PATHBUF_LEN,
+						    inode);
+		trace_android_fs_datawrite_start(inode, pos, len,
+						 current->pid, path,
+						 current->comm);
+	}
 	trace_ext4_write_begin(inode, pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
@@ -1317,7 +1326,7 @@ retry_journal:
 	/* In case writeback began while the page was unlocked */
 	wait_for_stable_page(page);
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#ifdef CONFIG_FS_ENCRYPTION
 	if (ext4_should_dioread_nolock(inode))
 		ret = ext4_block_write_begin(page, pos, len,
 					     ext4_get_block_unwritten);
@@ -1338,6 +1347,9 @@ retry_journal:
 	}
 
 	if (ret) {
+		bool extended = (pos + len > inode->i_size) &&
+				!ext4_verity_in_progress(inode);
+
 		unlock_page(page);
 		/*
 		 * __block_write_begin may have instantiated a few blocks
@@ -1347,11 +1359,11 @@ retry_journal:
 		 * Add inode to orphan list in case we crash before
 		 * truncate finishes
 		 */
-		if (pos + len > inode->i_size && ext4_can_truncate(inode))
+		if (extended && ext4_can_truncate(inode))
 			ext4_orphan_add(handle, inode);
 
 		ext4_journal_stop(handle);
-		if (pos + len > inode->i_size) {
+		if (extended) {
 			ext4_truncate_failed_write(inode);
 			/*
 			 * If truncate failed early the inode might
@@ -1404,7 +1416,9 @@ static int ext4_write_end(struct file *file,
 	int ret = 0, ret2;
 	int i_size_changed = 0;
 	int inline_data = ext4_has_inline_data(inode);
+	bool verity = ext4_verity_in_progress(inode);
 
+	trace_android_fs_datawrite_end(inode, pos, len);
 	trace_ext4_write_end(inode, pos, len, copied);
 	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
@@ -1421,12 +1435,16 @@ static int ext4_write_end(struct file *file,
 	/*
 	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
+	 *
+	 * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree
+	 * blocks are being written past EOF, so skip the i_size update.
 	 */
-	i_size_changed = ext4_update_inode_size(inode, pos + copied);
+	if (!verity)
+		i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
 	put_page(page);
 
-	if (old_size < pos)
+	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
@@ -1437,7 +1455,7 @@ static int ext4_write_end(struct file *file,
 	if (i_size_changed || inline_data)
 		ext4_mark_inode_dirty(handle, inode);
 
-	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1448,7 +1466,7 @@ errout:
 	if (!ret)
 		ret = ret2;
 
-	if (pos + len > inode->i_size) {
+	if (pos + len > inode->i_size && !verity) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
@@ -1509,7 +1527,9 @@ static int ext4_journalled_write_end(struct file *file,
 	unsigned from, to;
 	int size_changed = 0;
 	int inline_data = ext4_has_inline_data(inode);
+	bool verity = ext4_verity_in_progress(inode);
 
+	trace_android_fs_datawrite_end(inode, pos, len);
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_SIZE - 1);
 	to = from + len;
@@ -1538,13 +1558,14 @@ static int ext4_journalled_write_end(struct file *file,
 		if (!partial)
 			SetPageUptodate(page);
 	}
-	size_changed = ext4_update_inode_size(inode, pos + copied);
+	if (!verity)
+		size_changed = ext4_update_inode_size(inode, pos + copied);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
 	unlock_page(page);
 	put_page(page);
 
-	if (old_size < pos)
+	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 
 	if (size_changed || inline_data) {
@@ -1553,7 +1574,7 @@ static int ext4_journalled_write_end(struct file *file,
 			ret = ret2;
 	}
 
-	if (pos + len > inode->i_size && ext4_can_truncate(inode))
+	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1564,7 +1585,7 @@ errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
-	if (pos + len > inode->i_size) {
+	if (pos + len > inode->i_size && !verity) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
@@ -2130,7 +2151,8 @@ static int ext4_writepage(struct page *page,
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
-	if (page->index == size >> PAGE_SHIFT)
+	if (page->index == size >> PAGE_SHIFT &&
+	    !ext4_verity_in_progress(inode))
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
@@ -2214,7 +2236,8 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	 * after page tables are updated.
 	 */
 	size = i_size_read(mpd->inode);
-	if (page->index == size >> PAGE_SHIFT)
+	if (page->index == size >> PAGE_SHIFT &&
+	    !ext4_verity_in_progress(mpd->inode))
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
@@ -2313,6 +2336,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
+	if (ext4_verity_in_progress(inode))
+		blocks = EXT_MAX_BLOCKS;
+
 	do {
 		BUG_ON(buffer_locked(bh));
 
@@ -2642,8 +2668,8 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 	mpd->map.m_len = 0;
 	mpd->next_page = index;
 	while (index <= end) {
-		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
-			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
+				tag);
 		if (nr_pages == 0)
 			goto out;
 
@@ -2651,16 +2677,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			struct page *page = pvec.pages[i];
 
 			/*
-			 * At this point, the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or
-			 * even swizzled back from swapper_space to tmpfs file
-			 * mapping. However, page->index will not change
-			 * because we have a reference on the page.
-			 */
-			if (page->index > end)
-				goto out;
-
-			/*
 			 * Accumulated enough dirty pages? This doesn't apply
 			 * to WB_SYNC_ALL mode. For integrity sync we have to
 			 * keep going because someone may be concurrently
@@ -3040,13 +3056,23 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 
 	index = pos >> PAGE_SHIFT;
 
-	if (ext4_nonda_switch(inode->i_sb) ||
-	    S_ISLNK(inode->i_mode)) {
+	if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) ||
+	    ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
 					len, flags, pagep, fsdata);
 	}
 	*fsdata = (void *)0;
+	if (trace_android_fs_datawrite_start_enabled()) {
+		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+		path = android_fstrace_get_pathname(pathbuf,
+						    MAX_TRACE_PATHBUF_LEN,
+						    inode);
+		trace_android_fs_datawrite_start(inode, pos, len,
+						 current->pid,
+						 path, current->comm);
+	}
 	trace_ext4_da_write_begin(inode, pos, len, flags);
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
@@ -3097,7 +3123,7 @@ retry_journal:
 	/* In case writeback began while the page was unlocked */
 	wait_for_stable_page(page);
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#ifdef CONFIG_FS_ENCRYPTION
 	ret = ext4_block_write_begin(page, pos, len,
 				     ext4_da_get_block_prep);
 #else
@@ -3165,6 +3191,7 @@ static int ext4_da_write_end(struct file *file,
 		return ext4_write_end(file, mapping, pos,
 				      len, copied, page, fsdata);
 
+	trace_android_fs_datawrite_end(inode, pos, len);
 	trace_ext4_da_write_end(inode, pos, len, copied);
 	start = pos & (PAGE_SIZE - 1);
 	end = start + copied - 1;
@@ -3815,11 +3842,14 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	size_t count = iov_iter_count(iter);
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
+	int rw = iov_iter_rw(iter);
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+#ifdef CONFIG_FS_ENCRYPTION
+	if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
 		return 0;
 #endif
+	if (fsverity_active(inode))
+		return 0;
 
 	/*
 	 * If we are doing data journalling we don't support O_DIRECT
@@ -3835,12 +3865,42 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (WARN_ON_ONCE(IS_DAX(inode)))
 		return 0;
 
+	if (trace_android_fs_dataread_start_enabled() &&
+	    (rw == READ)) {
+		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+		path = android_fstrace_get_pathname(pathbuf,
+						    MAX_TRACE_PATHBUF_LEN,
+						    inode);
+		trace_android_fs_dataread_start(inode, offset, count,
+						current->pid, path,
+						current->comm);
+	}
+	if (trace_android_fs_datawrite_start_enabled() &&
+	    (rw == WRITE)) {
+		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
+
+		path = android_fstrace_get_pathname(pathbuf,
+						    MAX_TRACE_PATHBUF_LEN,
+						    inode);
+		trace_android_fs_datawrite_start(inode, offset, count,
+						 current->pid, path,
+						 current->comm);
+	}
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 	if (iov_iter_rw(iter) == READ)
 		ret = ext4_direct_IO_read(iocb, iter);
 	else
 		ret = ext4_direct_IO_write(iocb, iter);
 	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
+
+	if (trace_android_fs_dataread_start_enabled() &&
+	    (rw == READ))
+		trace_android_fs_dataread_end(inode, offset, count);
+	if (trace_android_fs_datawrite_start_enabled() &&
+	    (rw == WRITE))
+		trace_android_fs_datawrite_end(inode, offset, count);
+
 	return ret;
 }
 
@@ -3995,13 +4055,12 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
 			goto unlock;
-		if (S_ISREG(inode->i_mode) &&
-		    ext4_encrypted_inode(inode)) {
+		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
 			BUG_ON(blocksize != PAGE_SIZE);
-			WARN_ON_ONCE(fscrypt_decrypt_page(page->mapping->host,
-						page, PAGE_SIZE, 0, page->index));
+			WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks(
+						page, PAGE_SIZE, 0));
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -4073,7 +4132,7 @@ static int ext4_block_truncate_page(handle_t *handle,
 	struct inode *inode = mapping->host;
 
 	/* If we are processing an encrypted inode during orphan list handling */
-	if (ext4_encrypted_inode(inode) && !fscrypt_has_encryption_key(inode))
+	if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode))
 		return 0;
 
 	blocksize = inode->i_sb->s_blocksize;
@@ -4636,10 +4695,17 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) &&
 	    !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) &&
-	    !ext4_encrypted_inode(inode))
+	    !(flags & EXT4_ENCRYPT_FL) && !(flags & EXT4_VERITY_FL))
 		new_fl |= S_DAX;
+	if (flags & EXT4_ENCRYPT_FL)
+		new_fl |= S_ENCRYPTED;
+	if (flags & EXT4_CASEFOLD_FL)
+		new_fl |= S_CASEFOLD;
+	if (flags & EXT4_VERITY_FL)
+		new_fl |= S_VERITY;
 	inode_set_flags(inode, new_fl,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
+			S_ENCRYPTED|S_CASEFOLD|S_VERITY);
 }
 
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
@@ -4800,6 +4866,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		 * not initialized on a new filesystem. */
 	}
 	ei->i_flags = le32_to_cpu(raw_inode->i_flags);
+	ext4_set_inode_flags(inode);
 	inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
 	ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
 	if (ext4_has_feature_64bit(sb))
@@ -4910,7 +4977,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &ext4_dir_inode_operations;
 		inode->i_fop = &ext4_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
-		if (ext4_encrypted_inode(inode)) {
+		if (IS_ENCRYPTED(inode)) {
 			inode->i_op = &ext4_encrypted_symlink_inode_operations;
 			ext4_set_aops(inode);
 		} else if (ext4_inode_is_fast_symlink(inode)) {
@@ -4939,8 +5006,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
 		goto bad_inode;
 	}
+	if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb))
+		EXT4_ERROR_INODE(inode,
+				 "casefold flag without casefold feature");
 	brelse(iloc.bh);
-	ext4_set_inode_flags(inode);
 
 	unlock_new_inode(inode);
 	return inode;
@@ -5382,6 +5451,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (error)
 		return error;
 
+	error = fscrypt_prepare_setattr(dentry, attr);
+	if (error)
+		return error;
+
+	error = fsverity_prepare_setattr(dentry, attr);
+	if (error)
+		return error;
+
 	if (is_quota_modification(inode, attr)) {
 		error = dquot_initialize(inode);
 		if (error)
@@ -5427,14 +5504,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		loff_t oldsize = inode->i_size;
 		int shrink = (attr->ia_size <= inode->i_size);
 
-		if (ext4_encrypted_inode(inode)) {
-			error = fscrypt_get_encryption_info(inode);
-			if (error)
-				return error;
-			if (!fscrypt_has_encryption_key(inode))
-				return -ENOKEY;
-		}
-
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);