Merge tag 'fscrypt-for-linus' of git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt

Pull fscrypt updates from Eric Biggers:
 "Add support for direct I/O on encrypted files when blk-crypto (inline
  encryption) is being used for file contents encryption"

* tag 'fscrypt-for-linus' of git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt:
  fscrypt: update documentation for direct I/O support
  f2fs: support direct I/O with fscrypt using blk-crypto
  ext4: support direct I/O with fscrypt using blk-crypto
  iomap: support direct I/O with fscrypt using blk-crypto
  fscrypt: add functions for direct I/O support

7 files changed, 132 insertions, 5 deletions

diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 4ef3f714046a..4fcca79f39ae 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -69,6 +69,14 @@ void fscrypt_free_bounce_page(struct page *bounce_page)
 }
 EXPORT_SYMBOL(fscrypt_free_bounce_page);
 
+/*
+ * Generate the IV for the given logical block number within the given file.
+ * For filenames encryption, lblk_num == 0.
+ *
+ * Keep this in sync with fscrypt_limit_io_blocks().  fscrypt_limit_io_blocks()
+ * needs to know about any IV generation methods where the low bits of IV don't
+ * simply contain the lblk_num (e.g., IV_INO_LBLK_32).
+ */
 void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 			 const struct fscrypt_info *ci)
 {
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index c57bebfa48fe..93c2ca858092 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -17,6 +17,7 @@
 #include <linux/buffer_head.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
+#include <linux/uio.h>
 
 #include "fscrypt_private.h"
 
@@ -315,6 +316,10 @@ EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx_bh);
  *
  * fscrypt_set_bio_crypt_ctx() must have already been called on the bio.
  *
+ * This function isn't required in cases where crypto-mergeability is ensured in
+ * another way, such as I/O targeting only a single file (and thus a single key)
+ * combined with fscrypt_limit_io_blocks() to ensure DUN contiguity.
+ *
  * Return: true iff the I/O is mergeable
  */
 bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode,
@@ -363,3 +368,91 @@ bool fscrypt_mergeable_bio_bh(struct bio *bio,
 	return fscrypt_mergeable_bio(bio, inode, next_lblk);
 }
 EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh);
+
+/**
+ * fscrypt_dio_supported() - check whether a DIO (direct I/O) request is
+ *			     supported as far as encryption is concerned
+ * @iocb: the file and position the I/O is targeting
+ * @iter: the I/O data segment(s)
+ *
+ * Return: %true if there are no encryption constraints that prevent DIO from
+ *	   being supported; %false if DIO is unsupported.  (Note that in the
+ *	   %true case, the filesystem might have other, non-encryption-related
+ *	   constraints that prevent DIO from actually being supported.)
+ */
+bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
+{
+	const struct inode *inode = file_inode(iocb->ki_filp);
+	const unsigned int blocksize = i_blocksize(inode);
+
+	/* If the file is unencrypted, no veto from us. */
+	if (!fscrypt_needs_contents_encryption(inode))
+		return true;
+
+	/* We only support DIO with inline crypto, not fs-layer crypto. */
+	if (!fscrypt_inode_uses_inline_crypto(inode))
+		return false;
+
+	/*
+	 * Since the granularity of encryption is filesystem blocks, the file
+	 * position and total I/O length must be aligned to the filesystem block
+	 * size -- not just to the block device's logical block size as is
+	 * traditionally the case for DIO on many filesystems.
+	 *
+	 * We require that the user-provided memory buffers be filesystem block
+	 * aligned too.  It is simpler to have a single alignment value required
+	 * for all properties of the I/O, as is normally the case for DIO.
+	 * Also, allowing less aligned buffers would imply that data units could
+	 * cross bvecs, which would greatly complicate the I/O stack, which
+	 * assumes that bios can be split at any bvec boundary.
+	 */
+	if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), blocksize))
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(fscrypt_dio_supported);
+
+/**
+ * fscrypt_limit_io_blocks() - limit I/O blocks to avoid discontiguous DUNs
+ * @inode: the file on which I/O is being done
+ * @lblk: the block at which the I/O is being started from
+ * @nr_blocks: the number of blocks we want to submit starting at @lblk
+ *
+ * Determine the limit to the number of blocks that can be submitted in a bio
+ * targeting @lblk without causing a data unit number (DUN) discontiguity.
+ *
+ * This is normally just @nr_blocks, as normally the DUNs just increment along
+ * with the logical blocks.  (Or the file is not encrypted.)
+ *
+ * In rare cases, fscrypt can be using an IV generation method that allows the
+ * DUN to wrap around within logically contiguous blocks, and that wraparound
+ * will occur.  If this happens, a value less than @nr_blocks will be returned
+ * so that the wraparound doesn't occur in the middle of a bio, which would
+ * cause encryption/decryption to produce wrong results.
+ *
+ * Return: the actual number of blocks that can be submitted
+ */
+u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks)
+{
+	const struct fscrypt_info *ci;
+	u32 dun;
+
+	if (!fscrypt_inode_uses_inline_crypto(inode))
+		return nr_blocks;
+
+	if (nr_blocks <= 1)
+		return nr_blocks;
+
+	ci = inode->i_crypt_info;
+	if (!(fscrypt_policy_flags(&ci->ci_policy) &
+	      FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32))
+		return nr_blocks;
+
+	/* With IV_INO_LBLK_32, the DUN can wrap around from U32_MAX to 0. */
+
+	dun = ci->ci_hashed_ino + lblk;
+
+	return min_t(u64, nr_blocks, (u64)U32_MAX + 1 - dun);
+}
+EXPORT_SYMBOL_GPL(fscrypt_limit_io_blocks);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8cc11715518a..8bd66cdc41be 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -36,9 +36,11 @@
 #include "acl.h"
 #include "truncate.h"
 
-static bool ext4_dio_supported(struct inode *inode)
+static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter)
 {
-	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (!fscrypt_dio_supported(iocb, iter))
 		return false;
 	if (fsverity_active(inode))
 		return false;
@@ -61,7 +63,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		inode_lock_shared(inode);
 	}
 
-	if (!ext4_dio_supported(inode)) {
+	if (!ext4_dio_supported(iocb, to)) {
 		inode_unlock_shared(inode);
 		/*
 		 * Fallback to buffered I/O if the operation being performed on
@@ -509,7 +511,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Fallback to buffered I/O if the inode does not support direct I/O. */
-	if (!ext4_dio_supported(inode)) {
+	if (!ext4_dio_supported(iocb, from)) {
 		if (ilock_shared)
 			inode_unlock_shared(inode);
 		else
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 01c9e4f743ba..4cf55ef54193 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3409,6 +3409,13 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret < 0)
 		return ret;
 out:
+	/*
+	 * When inline encryption is enabled, sometimes I/O to an encrypted file
+	 * has to be broken up to guarantee DUN contiguity.  Handle this by
+	 * limiting the length of the mapping returned.
+	 */
+	map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
+
 	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 
 	return 0;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index fc077bce679d..79c9ed74bd8b 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -4032,6 +4032,13 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 
 	iomap->offset = blks_to_bytes(inode, map.m_lblk);
 
+	/*
+	 * When inline encryption is enabled, sometimes I/O to an encrypted file
+	 * has to be broken up to guarantee DUN contiguity.  Handle this by
+	 * limiting the length of the mapping returned.
+	 */
+	map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
+
 	if (map.m_flags & (F2FS_MAP_MAPPED | F2FS_MAP_UNWRITTEN)) {
 		iomap->length = blks_to_bytes(inode, map.m_len);
 		if (map.m_flags & F2FS_MAP_MAPPED) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d51a3ede4b0f..c2c89b03df1e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -4371,7 +4371,11 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	int rw = iov_iter_rw(iter);
 
-	if (f2fs_post_read_required(inode))
+	if (!fscrypt_dio_supported(iocb, iter))
+		return true;
+	if (fsverity_active(inode))
+		return true;
+	if (f2fs_compressed_file(inode))
 		return true;
 
 	/* disallow direct IO if any of devices has unaligned blksize */
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index e2ba13645ef2..67cf9c16f80c 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/fscrypt.h>
 #include <linux/pagemap.h>
 #include <linux/iomap.h>
 #include <linux/backing-dev.h>
@@ -179,11 +180,14 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
 		loff_t pos, unsigned len)
 {
+	struct inode *inode = file_inode(dio->iocb->ki_filp);
 	struct page *page = ZERO_PAGE(0);
 	int flags = REQ_SYNC | REQ_IDLE;
 	struct bio *bio;
 
 	bio = bio_alloc(iter->iomap.bdev, 1, REQ_OP_WRITE | flags, GFP_KERNEL);
+	fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
+				  GFP_KERNEL);
 	bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
@@ -308,6 +312,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		}
 
 		bio = bio_alloc(iomap->bdev, nr_pages, bio_opf, GFP_KERNEL);
+		fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
+					  GFP_KERNEL);
 		bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
 		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_ioprio = dio->iocb->ki_ioprio;