1 files changed, 166 insertions, 112 deletions

diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 6181e9526860..5f5599020e94 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -1,145 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * This contains encryption functions for per-file encryption.
+ * Utility functions for file contents encryption/decryption on
+ * block device-based filesystems.
  *
  * Copyright (C) 2015, Google, Inc.
  * Copyright (C) 2015, Motorola Mobility
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- *	Uday Savagaonkar, 2014
- * Encryption policy handling additions
- *	Ildar Muslukhov, 2014
- * Add fscrypt_pullback_bio_page()
- *	Jaegeuk Kim, 2015.
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
  */
 
-#include <linux/pagemap.h>
-#include <linux/module.h>
 #include <linux/bio.h>
+#include <linux/export.h>
+#include <linux/module.h>
 #include <linux/namei.h>
+#include <linux/pagemap.h>
+
 #include "fscrypt_private.h"
 
-/*
- * Call fscrypt_decrypt_page on every single page, reusing the encryption
- * context.
+/**
+ * fscrypt_decrypt_bio() - decrypt the contents of a bio
+ * @bio: the bio to decrypt
+ *
+ * Decrypt the contents of a "read" bio following successful completion of the
+ * underlying disk read.  The bio must be reading a whole number of blocks of an
+ * encrypted file directly into the page cache.  If the bio is reading the
+ * ciphertext into bounce pages instead of the page cache (for example, because
+ * the file is also compressed, so decompression is required after decryption),
+ * then this function isn't applicable.  This function may sleep, so it must be
+ * called from a workqueue rather than from the bio's bi_end_io callback.
+ *
+ * Return: %true on success; %false on failure.  On failure, bio->bi_status is
+ *	   also set to an error status.
  */
-static void completion_pages(struct work_struct *work)
+bool fscrypt_decrypt_bio(struct bio *bio)
 {
-	struct fscrypt_ctx *ctx =
-		container_of(work, struct fscrypt_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = fscrypt_decrypt_page(page->mapping->host, page,
-				PAGE_SIZE, 0, page->index);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else {
-			SetPageUptodate(page);
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio) {
+		int err = fscrypt_decrypt_pagecache_blocks(fi.folio, fi.length,
+							   fi.offset);
+
+		if (err) {
+			bio->bi_status = errno_to_blk_status(err);
+			return false;
 		}
-		unlock_page(page);
 	}
-	fscrypt_release_ctx(ctx);
-	bio_put(bio);
+	return true;
 }
+EXPORT_SYMBOL(fscrypt_decrypt_bio);
 
-void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode,
+					      pgoff_t lblk, sector_t pblk,
+					      unsigned int len)
 {
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(fscrypt_read_workqueue, &ctx->r.work);
-}
-EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
-
-void fscrypt_pullback_bio_page(struct page **page, bool restore)
-{
-	struct fscrypt_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
+	const unsigned int blockbits = inode->i_blkbits;
+	const unsigned int blocks_per_page = 1 << (PAGE_SHIFT - blockbits);
+	struct bio *bio;
+	int ret, err = 0;
+	int num_pages = 0;
 
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+	/* This always succeeds since __GFP_DIRECT_RECLAIM is set. */
+	bio = bio_alloc(inode->i_sb->s_bdev, BIO_MAX_VECS, REQ_OP_WRITE,
+			GFP_NOFS);
 
-	/* restore control page */
-	*page = ctx->w.control_page;
+	while (len) {
+		unsigned int blocks_this_page = min(len, blocks_per_page);
+		unsigned int bytes_this_page = blocks_this_page << blockbits;
 
-	if (restore)
-		fscrypt_restore_control_page(bounce_page);
+		if (num_pages == 0) {
+			fscrypt_set_bio_crypt_ctx(bio, inode, lblk, GFP_NOFS);
+			bio->bi_iter.bi_sector =
+					pblk << (blockbits - SECTOR_SHIFT);
+		}
+		ret = bio_add_page(bio, ZERO_PAGE(0), bytes_this_page, 0);
+		if (WARN_ON_ONCE(ret != bytes_this_page)) {
+			err = -EIO;
+			goto out;
+		}
+		num_pages++;
+		len -= blocks_this_page;
+		lblk += blocks_this_page;
+		pblk += blocks_this_page;
+		if (num_pages == BIO_MAX_VECS || !len ||
+		    !fscrypt_mergeable_bio(bio, inode, lblk)) {
+			err = submit_bio_wait(bio);
+			if (err)
+				goto out;
+			bio_reset(bio, inode->i_sb->s_bdev, REQ_OP_WRITE);
+			num_pages = 0;
+		}
+	}
+out:
+	bio_put(bio);
+	return err;
 }
-EXPORT_SYMBOL(fscrypt_pullback_bio_page);
 
+/**
+ * fscrypt_zeroout_range() - zero out a range of blocks in an encrypted file
+ * @inode: the file's inode
+ * @lblk: the first file logical block to zero out
+ * @pblk: the first filesystem physical block to zero out
+ * @len: number of blocks to zero out
+ *
+ * Zero out filesystem blocks in an encrypted regular file on-disk, i.e. write
+ * ciphertext blocks which decrypt to the all-zeroes block.  The blocks must be
+ * both logically and physically contiguous.  It's also assumed that the
+ * filesystem only uses a single block device, ->s_bdev.
+ *
+ * Note that since each block uses a different IV, this involves writing a
+ * different ciphertext to each block; we can't simply reuse the same one.
+ *
+ * Return: 0 on success; -errno on failure.
+ */
 int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
-				sector_t pblk, unsigned int len)
+			  sector_t pblk, unsigned int len)
 {
-	struct fscrypt_ctx *ctx;
-	struct page *ciphertext_page = NULL;
+	const struct fscrypt_inode_info *ci = fscrypt_get_inode_info_raw(inode);
+	const unsigned int du_bits = ci->ci_data_unit_bits;
+	const unsigned int du_size = 1U << du_bits;
+	const unsigned int du_per_page_bits = PAGE_SHIFT - du_bits;
+	const unsigned int du_per_page = 1U << du_per_page_bits;
+	u64 du_index = (u64)lblk << (inode->i_blkbits - du_bits);
+	u64 du_remaining = (u64)len << (inode->i_blkbits - du_bits);
+	sector_t sector = pblk << (inode->i_blkbits - SECTOR_SHIFT);
+	struct page *pages[16]; /* write up to 16 pages at a time */
+	unsigned int nr_pages;
+	unsigned int i;
+	unsigned int offset;
 	struct bio *bio;
-	int ret, err = 0;
-
-	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
-
-	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
-	if (IS_ERR(ciphertext_page)) {
-		err = PTR_ERR(ciphertext_page);
-		goto errout;
+	int ret, err;
+
+	if (len == 0)
+		return 0;
+
+	if (fscrypt_inode_uses_inline_crypto(inode))
+		return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk,
+							  len);
+
+	BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS);
+	nr_pages = min_t(u64, ARRAY_SIZE(pages),
+			 (du_remaining + du_per_page - 1) >> du_per_page_bits);
+
+	/*
+	 * We need at least one page for ciphertext.  Allocate the first one
+	 * from a mempool, with __GFP_DIRECT_RECLAIM set so that it can't fail.
+	 *
+	 * Any additional page allocations are allowed to fail, as they only
+	 * help performance, and waiting on the mempool for them could deadlock.
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		pages[i] = fscrypt_alloc_bounce_page(i == 0 ? GFP_NOFS :
+						     GFP_NOWAIT);
+		if (!pages[i])
+			break;
 	}
+	nr_pages = i;
+	if (WARN_ON_ONCE(nr_pages <= 0))
+		return -EINVAL;
+
+	/* This always succeeds since __GFP_DIRECT_RECLAIM is set. */
+	bio = bio_alloc(inode->i_sb->s_bdev, nr_pages, REQ_OP_WRITE, GFP_NOFS);
+
+	do {
+		bio->bi_iter.bi_sector = sector;
+
+		i = 0;
+		offset = 0;
+		do {
+			err = fscrypt_crypt_data_unit(ci, FS_ENCRYPT, du_index,
+						      ZERO_PAGE(0), pages[i],
+						      du_size, offset);
+			if (err)
+				goto out;
+			du_index++;
+			sector += 1U << (du_bits - SECTOR_SHIFT);
+			du_remaining--;
+			offset += du_size;
+			if (offset == PAGE_SIZE || du_remaining == 0) {
+				ret = bio_add_page(bio, pages[i++], offset, 0);
+				if (WARN_ON_ONCE(ret != offset)) {
+					err = -EIO;
+					goto out;
+				}
+				offset = 0;
+			}
+		} while (i != nr_pages && du_remaining != 0);
 
-	while (len--) {
-		err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
-					     ZERO_PAGE(0), ciphertext_page,
-					     PAGE_SIZE, 0, GFP_NOFS);
-		if (err)
-			goto errout;
-
-		bio = bio_alloc(GFP_NOWAIT, 1);
-		if (!bio) {
-			err = -ENOMEM;
-			goto errout;
-		}
-		bio->bi_bdev = inode->i_sb->s_bdev;
-		bio->bi_iter.bi_sector =
-			pblk << (inode->i_sb->s_blocksize_bits - 9);
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-		ret = bio_add_page(bio, ciphertext_page,
-					inode->i_sb->s_blocksize, 0);
-		if (ret != inode->i_sb->s_blocksize) {
-			/* should never happen! */
-			WARN_ON(1);
-			bio_put(bio);
-			err = -EIO;
-			goto errout;
-		}
 		err = submit_bio_wait(bio);
-		if (err == 0 && bio->bi_status)
-			err = -EIO;
-		bio_put(bio);
 		if (err)
-			goto errout;
-		lblk++;
-		pblk++;
-	}
+			goto out;
+		bio_reset(bio, inode->i_sb->s_bdev, REQ_OP_WRITE);
+	} while (du_remaining != 0);
 	err = 0;
-errout:
-	fscrypt_release_ctx(ctx);
+out:
+	bio_put(bio);
+	for (i = 0; i < nr_pages; i++)
+		fscrypt_free_bounce_page(pages[i]);
 	return err;
 }
 EXPORT_SYMBOL(fscrypt_zeroout_range);