1 files changed, 87 insertions, 93 deletions

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d7c81c..58294c9a7e1d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -37,7 +37,11 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	inode_lock_shared(inode);
+	if (!inode_trylock_shared(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock_shared(inode);
+	}
 	/*
 	 * Recheck under inode lock - at this point we are sure it cannot
 	 * change anymore
@@ -57,6 +61,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+		return -EIO;
+
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
@@ -175,9 +182,12 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
-	bool overwrite = false;
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -188,16 +198,9 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out;
 
-	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 out:
-	if (!overwrite)
-		inode_unlock(inode);
-	else
-		inode_unlock_shared(inode);
+	inode_unlock(inode);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	return ret;
@@ -213,12 +216,20 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(inode))
 		return ext4_dax_write_iter(iocb, from);
 #endif
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
+
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -237,9 +248,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	iocb->private = &overwrite;
 	/* Check whether we do a DIO overwrite or not */
-	if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-	    ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)))
-		overwrite = 1;
+	if (o_direct && !unaligned_aio) {
+		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
+			if (ext4_should_dioread_nolock(inode))
+				overwrite = 1;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
+	}
 
 	ret = __generic_file_write_iter(iocb, from);
 	inode_unlock(inode);
@@ -255,46 +272,43 @@ out:
 }
 
 #ifdef CONFIG_FS_DAX
-static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ext4_dax_huge_fault(struct vm_fault *vmf,
+		enum page_entry_size pe_size)
 {
 	int result;
-	struct inode *inode = file_inode(vma->vm_file);
+	handle_t *handle = NULL;
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+					       EXT4_DATA_TRANS_BLOCKS(sb));
+	} else {
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 	}
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
+	if (!IS_ERR(handle))
+		result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
+	else
+		result = VM_FAULT_SIGBUS;
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
+	} else {
+		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
 
 	return result;
 }
 
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
+static int ext4_dax_fault(struct vm_fault *vmf)
 {
-	int result;
-	struct inode *inode = file_inode(vma->vm_file);
-	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
-
-	if (write) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-				     &ext4_iomap_ops);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
-		sb_end_pagefault(sb);
-
-	return result;
+	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
 /*
@@ -306,22 +320,21 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
  * wp_pfn_shared() fails. Thus fault gets retried and things work out as
  * desired.
  */
-static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
-				struct vm_fault *vmf)
+static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	loff_t size;
 	int ret;
 
 	sb_start_pagefault(sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	down_read(&EXT4_I(inode)->i_mmap_sem);
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else
-		ret = dax_pfn_mkwrite(vma, vmf);
+		ret = dax_pfn_mkwrite(vmf);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(sb);
 
@@ -330,7 +343,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
-	.pmd_fault	= ext4_dax_pmd_fault,
+	.huge_fault	= ext4_dax_huge_fault,
 	.page_mkwrite	= ext4_dax_fault,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
@@ -348,13 +361,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
 
-	if (ext4_encrypted_inode(inode)) {
-		int err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return 0;
-		if (!fscrypt_has_encryption_key(inode))
-			return -ENOKEY;
-	}
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -375,6 +384,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	char buf[64], *cp;
 	int ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
 		     !(sb->s_flags & MS_RDONLY))) {
 		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
@@ -435,6 +447,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ret < 0)
 			return ret;
 	}
+
+	/* Set the flags to support nowait AIO */
+	filp->f_mode |= FMODE_AIO_NOWAIT;
+
 	return dquot_file_open(inode, filp);
 }
 
@@ -474,57 +490,37 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	endoff = (loff_t)end_blk << blkbits;
 
 	index = startoff >> PAGE_SHIFT;
-	end = endoff >> PAGE_SHIFT;
+	end = (endoff - 1) >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 	do {
 		int i, num;
 		unsigned long nr_pages;
 
-		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
-			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -564,20 +560,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
@@ -757,7 +751,7 @@ const struct file_operations ext4_file_operations = {
 
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
-	.getattr	= ext4_getattr,
+	.getattr	= ext4_file_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,