block: Inline encryption support for blk-mq

We must have some way of letting a storage device driver know what
encryption context it should use for en/decrypting a request. However,
it's the upper layers (like the filesystem/fscrypt) that know about and
manages encryption contexts. As such, when the upper layer submits a bio
to the block layer, and this bio eventually reaches a device driver with
support for inline encryption, the device driver will need to have been
told the encryption context for that bio.

We want to communicate the encryption context from the upper layer to the
storage device along with the bio, when the bio is submitted to the block
layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can
represent an encryption context (note that we can't use the bi_private
field in struct bio to do this because that field does not function to pass
information across layers in the storage stack). We also introduce various
functions to manipulate the bio_crypt_ctx and make the bio/request merging
logic aware of the bio_crypt_ctx.

We also make changes to blk-mq to make it handle bios with encryption
contexts. blk-mq can merge many bios into the same request. These bios need
to have contiguous data unit numbers (the necessary changes to blk-merge
are also made to ensure this) - as such, it suffices to keep the data unit
number of just the first bio, since that's all a storage driver needs to
infer the data unit number to use for each data block in each bio in a
request. blk-mq keeps track of the encryption context to be used for all
the bios in a request with the request's rq_crypt_ctx. When the first bio
is added to an empty request, blk-mq will program the encryption context
of that bio into the request_queue's keyslot manager, and store the
returned keyslot in the request's rq_crypt_ctx. All the functions to
operate on encryption contexts are in blk-crypto.c.

Upper layers only need to call bio_crypt_set_ctx with the encryption key,
algorithm and data_unit_num; they don't have to worry about getting a
keyslot for each encryption context, as blk-mq/blk-crypto handles that.
Blk-crypto also makes it possible for request-based layered devices like
dm-rq to make use of inline encryption hardware by cloning the
rq_crypt_ctx and programming a keyslot in the new request_queue when
necessary.

Note that any user of the block layer can submit bios with an
encryption context, such as filesystems, device-mapper targets, etc.
Signed-off-by: Satya Tangirala <satyat@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/Makefile

@@ -36,4 +36,4 @@ obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
 obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
 obj-$(CONFIG_BLK_PM)		+= blk-pm.o
-obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= keyslot-manager.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION)	+= keyslot-manager.o blk-crypto.o

block/bio.c

@@ -18,6 +18,7 @@
 #include <linux/blk-cgroup.h>
 #include <linux/highmem.h>
 #include <linux/sched/sysctl.h>
+#include <linux/blk-crypto.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -237,6 +238,8 @@ void bio_uninit(struct bio *bio)
 
 	if (bio_integrity(bio))
 		bio_integrity_free(bio);
+
+	bio_crypt_free_ctx(bio);
 }
 EXPORT_SYMBOL(bio_uninit);
 
@@ -708,6 +711,8 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
+	bio_crypt_clone(b, bio, gfp_mask);
+
 	if (bio_integrity(bio)) {
 		int ret;
 
@@ -1172,6 +1177,7 @@ void bio_advance(struct bio *bio, unsigned bytes)
 	if (bio_integrity(bio))
 		bio_integrity_advance(bio, bytes);
 
+	bio_crypt_advance(bio, bytes);
 	bio_advance_iter(bio, &bio->bi_iter, bytes);
 }
 EXPORT_SYMBOL(bio_advance);

block/blk-core.c

@@ -39,6 +39,7 @@
 #include <linux/bpf.h>
 #include <linux/psi.h>
 #include <linux/sched/sysctl.h>
+#include <linux/blk-crypto.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -121,6 +122,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
 	refcount_set(&rq->ref, 1);
+	blk_crypto_rq_set_defaults(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -652,6 +654,8 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
 
+	bio_crypt_free_ctx(bio);
+
 	blk_account_io_start(req, false);
 	return true;
 }
@@ -676,6 +680,8 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio,
 	req->__sector = bio->bi_iter.bi_sector;
 	req->__data_len += bio->bi_iter.bi_size;
 
+	bio_crypt_do_front_merge(req, bio);
+
 	blk_account_io_start(req, false);
 	return true;
 }
@@ -1125,10 +1131,12 @@ blk_qc_t generic_make_request(struct bio *bio)
 			/* Create a fresh bio_list for all subordinate requests */
 			bio_list_on_stack[1] = bio_list_on_stack[0];
 			bio_list_init(&bio_list_on_stack[0]);
+			if (blk_crypto_bio_prep(&bio)) {
 				if (q->make_request_fn)
 					ret = q->make_request_fn(q, bio);
 				else
 					ret = blk_mq_make_request(q, bio);
+			}
 
 			blk_queue_exit(q);
 
@@ -1167,7 +1175,7 @@ EXPORT_SYMBOL(generic_make_request);
 blk_qc_t direct_make_request(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_disk->queue;
-	blk_qc_t ret;
+	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (WARN_ON_ONCE(q->make_request_fn)) {
 		bio_io_error(bio);
@@ -1177,6 +1185,7 @@ blk_qc_t direct_make_request(struct bio *bio)
 		return BLK_QC_T_NONE;
 	if (unlikely(bio_queue_enter(bio)))
 		return BLK_QC_T_NONE;
+	if (blk_crypto_bio_prep(&bio))
 		ret = blk_mq_make_request(q, bio);
 	blk_queue_exit(q);
 	return ret;
@@ -1309,6 +1318,9 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
+	if (blk_crypto_insert_cloned_request(rq))
+		return BLK_STS_IOERR;
+
 	if (blk_queue_io_stat(q))
 		blk_account_io_start(rq, true);
 
@@ -1673,6 +1685,9 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
 	rq->ioprio = rq_src->ioprio;
 
+	if (rq->bio)
+		blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask);
+
 	return 0;
 
 free_and_out:

block/blk-crypto-internal.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_INTERNAL_H
+#define __LINUX_BLK_CRYPTO_INTERNAL_H
+
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+
+/* Represents a crypto mode supported by blk-crypto  */
+struct blk_crypto_mode {
+	unsigned int keysize; /* key size in bytes */
+	unsigned int ivsize; /* iv size in bytes */
+};
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+void bio_crypt_dun_increment(u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
+			     unsigned int inc);
+
+bool bio_crypt_rq_ctx_compatible(struct request *rq, struct bio *bio);
+
+bool bio_crypt_ctx_mergeable(struct bio_crypt_ctx *bc1, unsigned int bc1_bytes,
+			     struct bio_crypt_ctx *bc2);
+
+static inline bool bio_crypt_ctx_back_mergeable(struct request *req,
+						struct bio *bio)
+{
+	return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req),
+				       bio->bi_crypt_context);
+}
+
+static inline bool bio_crypt_ctx_front_mergeable(struct request *req,
+						 struct bio *bio)
+{
+	return bio_crypt_ctx_mergeable(bio->bi_crypt_context,
+				       bio->bi_iter.bi_size, req->crypt_ctx);
+}
+
+static inline bool bio_crypt_ctx_merge_rq(struct request *req,
+					  struct request *next)
+{
+	return bio_crypt_ctx_mergeable(req->crypt_ctx, blk_rq_bytes(req),
+				       next->crypt_ctx);
+}
+
+static inline void blk_crypto_rq_set_defaults(struct request *rq)
+{
+	rq->crypt_ctx = NULL;
+	rq->crypt_keyslot = NULL;
+}
+
+static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
+{
+	return rq->crypt_ctx;
+}
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline bool bio_crypt_rq_ctx_compatible(struct request *rq,
+					       struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_front_mergeable(struct request *req,
+						 struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_back_mergeable(struct request *req,
+						struct bio *bio)
+{
+	return true;
+}
+
+static inline bool bio_crypt_ctx_merge_rq(struct request *req,
+					  struct request *next)
+{
+	return true;
+}
+
+static inline void blk_crypto_rq_set_defaults(struct request *rq) { }
+
+static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
+{
+	return false;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+void __bio_crypt_advance(struct bio *bio, unsigned int bytes);
+static inline void bio_crypt_advance(struct bio *bio, unsigned int bytes)
+{
+	if (bio_has_crypt_ctx(bio))
+		__bio_crypt_advance(bio, bytes);
+}
+
+void __bio_crypt_free_ctx(struct bio *bio);
+static inline void bio_crypt_free_ctx(struct bio *bio)
+{
+	if (bio_has_crypt_ctx(bio))
+		__bio_crypt_free_ctx(bio);
+}
+
+static inline void bio_crypt_do_front_merge(struct request *rq,
+					    struct bio *bio)
+{
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	if (bio_has_crypt_ctx(bio))
+		memcpy(rq->crypt_ctx->bc_dun, bio->bi_crypt_context->bc_dun,
+		       sizeof(rq->crypt_ctx->bc_dun));
+#endif
+}
+
+bool __blk_crypto_bio_prep(struct bio **bio_ptr);
+static inline bool blk_crypto_bio_prep(struct bio **bio_ptr)
+{
+	if (bio_has_crypt_ctx(*bio_ptr))
+		return __blk_crypto_bio_prep(bio_ptr);
+	return true;
+}
+
+blk_status_t __blk_crypto_init_request(struct request *rq);
+static inline blk_status_t blk_crypto_init_request(struct request *rq)
+{
+	if (blk_crypto_rq_is_encrypted(rq))
+		return __blk_crypto_init_request(rq);
+	return BLK_STS_OK;
+}
+
+void __blk_crypto_free_request(struct request *rq);
+static inline void blk_crypto_free_request(struct request *rq)
+{
+	if (blk_crypto_rq_is_encrypted(rq))
+		__blk_crypto_free_request(rq);
+}
+
+void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+			      gfp_t gfp_mask);
+static inline void blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
+					  gfp_t gfp_mask)
+{
+	if (bio_has_crypt_ctx(bio))
+		__blk_crypto_rq_bio_prep(rq, bio, gfp_mask);
+}
+
+/**
+ * blk_crypto_insert_cloned_request - Prepare a cloned request to be inserted
+ *				      into a request queue.
+ * @rq: the request being queued
+ *
+ * Return: BLK_STS_OK on success, nonzero on error.
+ */
+static inline blk_status_t blk_crypto_insert_cloned_request(struct request *rq)
+{
+
+	if (blk_crypto_rq_is_encrypted(rq))
+		return blk_crypto_init_request(rq);
+	return BLK_STS_OK;
+}
+
+#endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */

block/blk-map.c

@@ -550,6 +550,7 @@ int blk_rq_append_bio(struct request *rq, struct bio **bio)
 		rq->biotail->bi_next = *bio;
 		rq->biotail = *bio;
 		rq->__data_len += (*bio)->bi_iter.bi_size;
+		bio_crypt_free_ctx(*bio);
 	}
 
 	return 0;

block/blk-merge.c

@@ -562,6 +562,8 @@ int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
 	if (blk_integrity_rq(req) &&
 	    integrity_req_gap_back_merge(req, bio))
 		return 0;
+	if (!bio_crypt_ctx_back_mergeable(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
 		req_set_nomerge(req->q, req);
@@ -578,6 +580,8 @@ int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs
 	if (blk_integrity_rq(req) &&
 	    integrity_req_gap_front_merge(req, bio))
 		return 0;
+	if (!bio_crypt_ctx_front_mergeable(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
 		req_set_nomerge(req->q, req);
@@ -627,6 +631,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (blk_integrity_merge_rq(q, req, next) == false)
 		return 0;
 
+	if (!bio_crypt_ctx_merge_rq(req, next))
+		return 0;
+
 	/* Merge is OK... */
 	req->nr_phys_segments = total_phys_segments;
 	return 1;
@@ -851,6 +858,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
 
+	/* Only merge if the crypt contexts are compatible */
+	if (!bio_crypt_rq_ctx_compatible(rq, bio))
+		return false;
+
 	/* must be using the same buffer */
 	if (req_op(rq) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(rq->bio, bio))

block/blk-mq.c

@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
+#include <linux/blk-crypto.h>
 
 #include <trace/events/block.h>
 
@@ -317,6 +318,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
 #endif
+	blk_crypto_rq_set_defaults(rq);
 	/* tag was already set */
 	WRITE_ONCE(rq->deadline, 0);
 
@@ -473,6 +475,7 @@ static void __blk_mq_free_request(struct request *rq)
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	const int sched_tag = rq->internal_tag;
 
+	blk_crypto_free_request(rq);
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
 	if (rq->tag != -1)
@@ -1820,6 +1823,7 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(rq, bio, nr_segs);
+	blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO);
 
 	blk_account_io_start(rq, true);
 }
@@ -2021,6 +2025,7 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	struct request *same_queue_rq = NULL;
 	unsigned int nr_segs;
 	blk_qc_t cookie;
+	blk_status_t ret;
 
 	blk_queue_bounce(q, &bio);
 	__blk_queue_split(q, &bio, &nr_segs);
@@ -2054,6 +2059,14 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
+	ret = blk_crypto_init_request(rq);
+	if (ret != BLK_STS_OK) {
+		bio->bi_status = ret;
+		bio_endio(bio);
+		blk_mq_free_request(rq);
+		return BLK_QC_T_NONE;
+	}
+
 	plug = blk_mq_plug(q, bio);
 	if (unlikely(is_flush_fua)) {
 		/* Bypass scheduler for flush requests */

block/blk.h

@@ -5,7 +5,9 @@
 #include <linux/idr.h>
 #include <linux/blk-mq.h>
 #include <linux/part_stat.h>
+#include <linux/blk-crypto.h>
 #include <xen/xen.h>
+#include "blk-crypto-internal.h"
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
 

block/bounce.c

@@ -267,6 +267,8 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
 		break;
 	}
 
+	bio_crypt_clone(bio, bio_src, gfp_mask);
+
 	if (bio_integrity(bio_src)) {
 		int ret;
 

drivers/md/dm.c

@@ -26,6 +26,7 @@
 #include <linux/pr.h>
 #include <linux/refcount.h>
 #include <linux/part_stat.h>
+#include <linux/blk-crypto.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -1334,6 +1335,8 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 
 	__bio_clone_fast(clone, bio);
 
+	bio_crypt_clone(clone, bio, GFP_NOIO);
+
 	if (bio_integrity(bio)) {
 		int r;
 

include/linux/blk-crypto.h

@@ -6,6 +6,8 @@
 #ifndef __LINUX_BLK_CRYPTO_H
 #define __LINUX_BLK_CRYPTO_H
 
+#include <linux/types.h>
+
 enum blk_crypto_mode_num {
 	BLK_ENCRYPTION_MODE_INVALID,
 	BLK_ENCRYPTION_MODE_AES_256_XTS,
@@ -49,4 +51,73 @@ struct blk_crypto_key {
 	u8 raw[BLK_CRYPTO_MAX_KEY_SIZE];
 };
 
+#define BLK_CRYPTO_MAX_IV_SIZE		32
+#define BLK_CRYPTO_DUN_ARRAY_SIZE	(BLK_CRYPTO_MAX_IV_SIZE / sizeof(u64))
+
+/**
+ * struct bio_crypt_ctx - an inline encryption context
+ * @bc_key: the key, algorithm, and data unit size to use
+ * @bc_dun: the data unit number (starting IV) to use
+ *
+ * A bio_crypt_ctx specifies that the contents of the bio will be encrypted (for
+ * write requests) or decrypted (for read requests) inline by the storage device
+ * or controller.
+ */
+struct bio_crypt_ctx {
+	const struct blk_crypto_key	*bc_key;
+	u64				bc_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+};
+
+#include <linux/blk_types.h>
+#include <linux/blkdev.h>
+
+struct request;
+struct request_queue;
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+static inline bool bio_has_crypt_ctx(struct bio *bio)
+{
+	return bio->bi_crypt_context;
+}
+
+void bio_crypt_set_ctx(struct bio *bio, const struct blk_crypto_key *key,
+		       const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
+		       gfp_t gfp_mask);
+
+bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc,
+				 unsigned int bytes,
+				 const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]);
+
+int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key,
+			enum blk_crypto_mode_num crypto_mode,
+			unsigned int dun_bytes,
+			unsigned int data_unit_size);
+
+int blk_crypto_start_using_key(const struct blk_crypto_key *key,
+			       struct request_queue *q);
+
+int blk_crypto_evict_key(struct request_queue *q,
+			 const struct blk_crypto_key *key);
+
+bool blk_crypto_config_supported(struct request_queue *q,
+				 const struct blk_crypto_config *cfg);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline bool bio_has_crypt_ctx(struct bio *bio)
+{
+	return false;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
+static inline void bio_crypt_clone(struct bio *dst, struct bio *src,
+				   gfp_t gfp_mask)
+{
+	if (bio_has_crypt_ctx(src))
+		__bio_crypt_clone(dst, src, gfp_mask);
+}
+
 #endif /* __LINUX_BLK_CRYPTO_H */

include/linux/blk_types.h

@@ -18,6 +18,7 @@ struct block_device;
 struct io_context;
 struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
+struct bio_crypt_ctx;
 
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
@@ -185,6 +186,11 @@ struct bio {
 	u64			bi_iocost_cost;
 #endif
 #endif
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx	*bi_crypt_context;
+#endif
+
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 		struct bio_integrity_payload *bi_integrity; /* data integrity */

include/linux/blkdev.h

@@ -222,6 +222,11 @@ struct request {
 	unsigned short nr_integrity_segments;
 #endif
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx *crypt_ctx;
+	struct blk_ksm_keyslot *crypt_keyslot;
+#endif
+
 	unsigned short write_hint;
 	unsigned short ioprio;