@@ -288,6 +288,34 @@ static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio,
return fbio;
}
+blk_status_t btrfs_check_encrypted_read_bio(struct btrfs_bio *bbio,
+ struct bio *enc_bio)
+{
+ struct btrfs_inode *inode = bbio->inode;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ u32 sectorsize = fs_info->sectorsize;
+ struct bvec_iter iter = bbio->saved_iter;
+ struct btrfs_device *dev = bbio->bio.bi_private;
+ u32 offset = 0;
+
+ /*
+ * We have to use a copy of iter in case there's an error,
+ * btrfs_check_read_bio will handle submitting the repair bios.
+ */
+ while (iter.bi_size) {
+ struct bio_vec bv = bio_iter_iovec(enc_bio, iter);
+
+ bv.bv_len = min(bv.bv_len, sectorsize);
+ if (!btrfs_data_csum_ok(bbio, dev, offset, &bv))
+ return BLK_STS_IOERR;
+ bio_advance_iter_single(enc_bio, &iter, sectorsize);
+ offset += sectorsize;
+ }
+
+ bbio->csum_done = true;
+ return BLK_STS_OK;
+}
+
static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *dev)
{
struct btrfs_inode *inode = bbio->inode;
@@ -313,6 +341,10 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de
/* Clear the I/O error. A failed repair will reset it. */
bbio->bio.bi_status = BLK_STS_OK;
+ /* This was an encrypted bio and we've already done the csum check. */
+ if (status == BLK_STS_OK && bbio->csum_done)
+ goto out;
+
while (iter->bi_size) {
struct bio_vec bv = bio_iter_iovec(&bbio->bio, *iter);
@@ -323,7 +355,7 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de
bio_advance_iter_single(&bbio->bio, iter, sectorsize);
offset += sectorsize;
}
-
+out:
if (bbio->csum != bbio->csum_inline)
kfree(bbio->csum);
@@ -756,10 +788,13 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
/*
* Csum items for reloc roots have already been cloned at this
* point, so they are handled as part of the no-checksum case.
+ *
+ * Encrypted inodes are csum'ed via the ->process_bio callback.
*/
if (inode && !(inode->flags & BTRFS_INODE_NODATASUM) &&
!test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
- !btrfs_is_data_reloc_root(inode->root)) {
+ !btrfs_is_data_reloc_root(inode->root) &&
+ !IS_ENCRYPTED(&inode->vfs_inode)) {
if (should_async_write(bbio) &&
btrfs_wq_submit_bio(bbio, bioc, &smap, mirror_num))
goto done;
@@ -45,6 +45,7 @@ struct btrfs_bio {
struct {
u8 *csum;
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+ bool csum_done;
struct bvec_iter saved_iter;
};
@@ -110,5 +111,7 @@ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_
int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
u64 length, u64 logical, struct folio *folio,
unsigned int folio_offset, int mirror_num);
+blk_status_t btrfs_check_encrypted_read_bio(struct btrfs_bio *bbio,
+ struct bio *enc_bio);
#endif
@@ -337,6 +337,14 @@ static int search_csum_tree(struct btrfs_fs_info *fs_info,
return ret;
}
+static inline bool inode_skip_csum(struct btrfs_inode *inode)
+{
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+ return (inode->flags & BTRFS_INODE_NODATASUM) ||
+ test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
+}
+
/*
* Lookup the checksum for the read bio in csum tree.
*
@@ -356,8 +364,7 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
blk_status_t ret = BLK_STS_OK;
u32 bio_offset = 0;
- if ((inode->flags & BTRFS_INODE_NODATASUM) ||
- test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state))
+ if (inode_skip_csum(inode))
return BLK_STS_OK;
/*
@@ -745,6 +752,9 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio, struct bio *bio)
int i;
unsigned nofs_flag;
+ if (inode_skip_csum(inode))
+ return BLK_STS_OK;
+
nofs_flag = memalloc_nofs_save();
sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
GFP_KERNEL);
@@ -16,6 +16,7 @@
#include "transaction.h"
#include "volumes.h"
#include "xattr.h"
+#include "file-item.h"
/*
* From a given location in a leaf, read a name into a qstr (usually a
@@ -215,6 +216,33 @@ static struct block_device **btrfs_fscrypt_get_devices(struct super_block *sb,
return devs;
}
+static blk_status_t btrfs_process_encrypted_bio(struct bio *orig_bio,
+ struct bio *enc_bio)
+{
+ struct btrfs_bio *bbio;
+
+ /*
+ * If our bio is from the normal fs_bio_set then we know this is a
+ * mirror split and we can skip it, we'll get the real bio on the last
+ * mirror and we can process that one.
+ */
+ if (orig_bio->bi_pool == &fs_bio_set)
+ return BLK_STS_OK;
+
+ bbio = btrfs_bio(orig_bio);
+
+ if (bio_op(orig_bio) == REQ_OP_READ) {
+ /*
+ * We have ->saved_iter based on the orig_bio, so if the block
+ * layer changes we need to notice this asap so we can update
+ * our code to handle the new world order.
+ */
+ ASSERT(orig_bio == enc_bio);
+ return btrfs_check_encrypted_read_bio(bbio, enc_bio);
+ }
+ return btrfs_csum_one_bio(bbio, enc_bio);
+}
+
int btrfs_fscrypt_load_extent_info(struct btrfs_inode *inode,
struct extent_map *em,
struct btrfs_fscrypt_ctx *ctx)
@@ -338,4 +366,5 @@ const struct fscrypt_operations btrfs_fscrypt_ops = {
.set_context = btrfs_fscrypt_set_context,
.empty_dir = btrfs_fscrypt_empty_dir,
.get_devices = btrfs_fscrypt_get_devices,
+ .process_bio = btrfs_process_encrypted_bio,
};
We are going to be checksumming the encrypted data, so we have to implement the ->process_bio fscrypt callback. This will provide us with the original bio and the encrypted bio to do work on. For WRITE's this will happen after the encrypted bio has been encrypted. For READ's this will happen after the read has completed and before the decryption step is done. For write's this is straightforward, we can just pass in the encrypted bio to btrfs_csum_one_bio and then the csums will be added to the bbio as normal. For read's this is relatively straightforward, but requires some care. We assume (because that's how it works currently) that the encrypted bio match the original bio, this is important because we save the iter of the bio before we submit. If this changes in the future we'll need a hook to give us the bi_iter of the decryption bio before it's submitted. We check the csums before decryption. If it doesn't match we simply error out and we let the normal path handle the repair work. Signed-off-by: Josef Bacik <josef@toxicpanda.com> --- fs/btrfs/bio.c | 39 +++++++++++++++++++++++++++++++++++++-- fs/btrfs/bio.h | 3 +++ fs/btrfs/file-item.c | 14 ++++++++++++-- fs/btrfs/fscrypt.c | 29 +++++++++++++++++++++++++++++ 4 files changed, 81 insertions(+), 4 deletions(-)