[PATCH v2 0/4] Fix blk-crypto keyslot race condition

[PATCH v2 0/4] Fix blk-crypto keyslot race condition

[Eric Biggers]

This series fixes a race condition in blk-crypto keyslot management and
makes some related cleanups.  It replaces
"[PATCH] blk-crypto: make blk_crypto_evict_key() always try to evict"
(https://lore.kernel.org/r/20230226203816.207449-1-ebiggers@kernel.org),
which was a simpler fix but didn't fix the keyslot reference counting to
work as expected.

Changed in v2:
  - Call blk_crypto_rq_put_keyslot() when requests are merged
  - Add and use blk_crypto_rq_has_keyslot()
  - Add patch "blk-crypto: drop the NULL check from blk_crypto_put_keyslot()"

Eric Biggers (4):
  blk-mq: release crypto keyslot before reporting I/O complete
  blk-crypto: make blk_crypto_evict_key() more robust
  blk-crypto: remove blk_crypto_insert_cloned_request()
  blk-crypto: drop the NULL check from blk_crypto_put_keyslot()

 Documentation/block/inline-encryption.rst |  3 +-
 block/blk-crypto-internal.h               | 38 +++++++-------
 block/blk-crypto-profile.c                | 64 ++++++++---------------
 block/blk-crypto.c                        | 47 +++++++++--------
 block/blk-merge.c                         |  2 +
 block/blk-mq.c                            | 17 +++++-
 6 files changed, 87 insertions(+), 84 deletions(-)


base-commit: 63355b9884b3d1677de6bd1517cd2b8a9bf53978
-- 
2.39.2

[PATCH v2 1/4] blk-mq: release crypto keyslot before reporting I/O complete

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Once all I/O using a blk_crypto_key has completed, filesystems can call
blk_crypto_evict_key().  However, the block layer currently doesn't call
blk_crypto_put_keyslot() until the request is being freed, which happens
after upper layers have been told (via bio_endio()) the I/O has
completed.  This causes a race condition where blk_crypto_evict_key()
can see 'slot_refs != 0' without there being an actual bug.

This makes __blk_crypto_evict_key() hit the
'WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)' and return without
doing anything, eventually causing a use-after-free in
blk_crypto_reprogram_all_keys().  (This is a very rare bug and has only
been seen when per-file keys are being used with fscrypt.)

There are two options to fix this: either release the keyslot before
bio_endio() is called on the request's last bio, or make
__blk_crypto_evict_key() ignore slot_refs.  Let's go with the first
solution, since it preserves the ability to report bugs (via
WARN_ON_ONCE) where a key is evicted while still in-use.

Fixes: a892c8d52c02 ("block: Inline encryption support for blk-mq")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 block/blk-crypto-internal.h | 25 +++++++++++++++++++++----
 block/blk-crypto.c          | 24 ++++++++++++------------
 block/blk-merge.c           |  2 ++
 block/blk-mq.c              | 15 ++++++++++++++-
 4 files changed, 49 insertions(+), 17 deletions(-)

diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
index a8cdaf26851e..4f1de2495f0c 100644
--- a/block/blk-crypto-internal.h
+++ b/block/blk-crypto-internal.h
@@ -65,6 +65,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
 	return rq->crypt_ctx;
 }
 
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return rq->crypt_keyslot;
+}
+
 blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
 				    const struct blk_crypto_key *key,
 				    struct blk_crypto_keyslot **slot_ptr);
@@ -119,6 +124,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
 	return false;
 }
 
+static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 void __bio_crypt_advance(struct bio *bio, unsigned int bytes);
@@ -153,14 +163,21 @@ static inline bool blk_crypto_bio_prep(struct bio **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)
+blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq);
+static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq)
 {
 	if (blk_crypto_rq_is_encrypted(rq))
-		return __blk_crypto_init_request(rq);
+		return __blk_crypto_rq_get_keyslot(rq);
 	return BLK_STS_OK;
 }
 
+void __blk_crypto_rq_put_keyslot(struct request *rq);
+static inline void blk_crypto_rq_put_keyslot(struct request *rq)
+{
+	if (blk_crypto_rq_has_keyslot(rq))
+		__blk_crypto_rq_put_keyslot(rq);
+}
+
 void __blk_crypto_free_request(struct request *rq);
 static inline void blk_crypto_free_request(struct request *rq)
 {
@@ -199,7 +216,7 @@ 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_crypto_rq_get_keyslot(rq);
 	return BLK_STS_OK;
 }
 
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 45378586151f..d0c7feb447e9 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -224,27 +224,27 @@ static bool bio_crypt_check_alignment(struct bio *bio)
 	return true;
 }
 
-blk_status_t __blk_crypto_init_request(struct request *rq)
+blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq)
 {
 	return blk_crypto_get_keyslot(rq->q->crypto_profile,
 				      rq->crypt_ctx->bc_key,
 				      &rq->crypt_keyslot);
 }
 
-/**
- * __blk_crypto_free_request - Uninitialize the crypto fields of a request.
- *
- * @rq: The request whose crypto fields to uninitialize.
- *
- * Completely uninitializes the crypto fields of a request. If a keyslot has
- * been programmed into some inline encryption hardware, that keyslot is
- * released. The rq->crypt_ctx is also freed.
- */
-void __blk_crypto_free_request(struct request *rq)
+void __blk_crypto_rq_put_keyslot(struct request *rq)
 {
 	blk_crypto_put_keyslot(rq->crypt_keyslot);
+	rq->crypt_keyslot = NULL;
+}
+
+void __blk_crypto_free_request(struct request *rq)
+{
+	/* The keyslot, if one was needed, should have been released earlier. */
+	if (WARN_ON_ONCE(rq->crypt_keyslot))
+		__blk_crypto_rq_put_keyslot(rq);
+
 	mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool);
-	blk_crypto_rq_set_defaults(rq);
+	rq->crypt_ctx = NULL;
 }
 
 /**
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 6460abdb2426..65e75efa9bd3 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -867,6 +867,8 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (!blk_discard_mergable(req))
 		elv_merge_requests(q, req, next);
 
+	blk_crypto_rq_put_keyslot(next);
+
 	/*
 	 * 'next' is going away, so update stats accordingly
 	 */
diff --git a/block/blk-mq.c b/block/blk-mq.c
index d0cb2ef18fe2..49825538d932 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -840,6 +840,12 @@ static void blk_complete_request(struct request *req)
 		req->q->integrity.profile->complete_fn(req, total_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	blk_crypto_rq_put_keyslot(req);
+
 	blk_account_io_completion(req, total_bytes);
 
 	do {
@@ -905,6 +911,13 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		req->q->integrity.profile->complete_fn(req, nr_bytes);
 #endif
 
+	/*
+	 * Upper layers may call blk_crypto_evict_key() anytime after the last
+	 * bio_endio().  Therefore, the keyslot must be released before that.
+	 */
+	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
+		__blk_crypto_rq_put_keyslot(req);
+
 	if (unlikely(error && !blk_rq_is_passthrough(req) &&
 		     !(req->rq_flags & RQF_QUIET)) &&
 		     !test_bit(GD_DEAD, &req->q->disk->state)) {
@@ -2967,7 +2980,7 @@ void blk_mq_submit_bio(struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
-	ret = blk_crypto_init_request(rq);
+	ret = blk_crypto_rq_get_keyslot(rq);
 	if (ret != BLK_STS_OK) {
 		bio->bi_status = ret;
 		bio_endio(bio);
-- 
2.39.2

Re: [PATCH v2 1/4] blk-mq: release crypto keyslot before reporting I/O complete

[Nathan Huckleberry]

On Wed, Mar 8, 2023 at 11:39 AM Eric Biggers <ebiggers@kernel.org> wrote:
>
> From: Eric Biggers <ebiggers@google.com>
>
> Once all I/O using a blk_crypto_key has completed, filesystems can call
> blk_crypto_evict_key().  However, the block layer currently doesn't call
> blk_crypto_put_keyslot() until the request is being freed, which happens
> after upper layers have been told (via bio_endio()) the I/O has
> completed.  This causes a race condition where blk_crypto_evict_key()
> can see 'slot_refs != 0' without there being an actual bug.
>
> This makes __blk_crypto_evict_key() hit the
> 'WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)' and return without
> doing anything, eventually causing a use-after-free in
> blk_crypto_reprogram_all_keys().  (This is a very rare bug and has only
> been seen when per-file keys are being used with fscrypt.)
>
> There are two options to fix this: either release the keyslot before
> bio_endio() is called on the request's last bio, or make
> __blk_crypto_evict_key() ignore slot_refs.  Let's go with the first
> solution, since it preserves the ability to report bugs (via
> WARN_ON_ONCE) where a key is evicted while still in-use.
>
> Fixes: a892c8d52c02 ("block: Inline encryption support for blk-mq")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Biggers <ebiggers@google.com>
> ---
>  block/blk-crypto-internal.h | 25 +++++++++++++++++++++----
>  block/blk-crypto.c          | 24 ++++++++++++------------
>  block/blk-merge.c           |  2 ++
>  block/blk-mq.c              | 15 ++++++++++++++-
>  4 files changed, 49 insertions(+), 17 deletions(-)
>
> diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
> index a8cdaf26851e..4f1de2495f0c 100644
> --- a/block/blk-crypto-internal.h
> +++ b/block/blk-crypto-internal.h
> @@ -65,6 +65,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
>         return rq->crypt_ctx;
>  }
>
> +static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
> +{
> +       return rq->crypt_keyslot;
> +}
> +
>  blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
>                                     const struct blk_crypto_key *key,
>                                     struct blk_crypto_keyslot **slot_ptr);
> @@ -119,6 +124,11 @@ static inline bool blk_crypto_rq_is_encrypted(struct request *rq)
>         return false;
>  }
>
> +static inline bool blk_crypto_rq_has_keyslot(struct request *rq)
> +{
> +       return false;
> +}
> +
>  #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
>
>  void __bio_crypt_advance(struct bio *bio, unsigned int bytes);
> @@ -153,14 +163,21 @@ static inline bool blk_crypto_bio_prep(struct bio **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)
> +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq);
> +static inline blk_status_t blk_crypto_rq_get_keyslot(struct request *rq)
>  {
>         if (blk_crypto_rq_is_encrypted(rq))
> -               return __blk_crypto_init_request(rq);
> +               return __blk_crypto_rq_get_keyslot(rq);
>         return BLK_STS_OK;
>  }
>
> +void __blk_crypto_rq_put_keyslot(struct request *rq);
> +static inline void blk_crypto_rq_put_keyslot(struct request *rq)
> +{
> +       if (blk_crypto_rq_has_keyslot(rq))
> +               __blk_crypto_rq_put_keyslot(rq);
> +}
> +
>  void __blk_crypto_free_request(struct request *rq);
>  static inline void blk_crypto_free_request(struct request *rq)
>  {
> @@ -199,7 +216,7 @@ 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_crypto_rq_get_keyslot(rq);
>         return BLK_STS_OK;
>  }
>
> diff --git a/block/blk-crypto.c b/block/blk-crypto.c
> index 45378586151f..d0c7feb447e9 100644
> --- a/block/blk-crypto.c
> +++ b/block/blk-crypto.c
> @@ -224,27 +224,27 @@ static bool bio_crypt_check_alignment(struct bio *bio)
>         return true;
>  }
>
> -blk_status_t __blk_crypto_init_request(struct request *rq)
> +blk_status_t __blk_crypto_rq_get_keyslot(struct request *rq)
>  {
>         return blk_crypto_get_keyslot(rq->q->crypto_profile,
>                                       rq->crypt_ctx->bc_key,
>                                       &rq->crypt_keyslot);
>  }
>
> -/**
> - * __blk_crypto_free_request - Uninitialize the crypto fields of a request.
> - *
> - * @rq: The request whose crypto fields to uninitialize.
> - *
> - * Completely uninitializes the crypto fields of a request. If a keyslot has
> - * been programmed into some inline encryption hardware, that keyslot is
> - * released. The rq->crypt_ctx is also freed.
> - */
> -void __blk_crypto_free_request(struct request *rq)
> +void __blk_crypto_rq_put_keyslot(struct request *rq)
>  {
>         blk_crypto_put_keyslot(rq->crypt_keyslot);
> +       rq->crypt_keyslot = NULL;
> +}
> +
> +void __blk_crypto_free_request(struct request *rq)
> +{
> +       /* The keyslot, if one was needed, should have been released earlier. */
> +       if (WARN_ON_ONCE(rq->crypt_keyslot))
> +               __blk_crypto_rq_put_keyslot(rq);
> +
>         mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool);
> -       blk_crypto_rq_set_defaults(rq);
> +       rq->crypt_ctx = NULL;
>  }
>
>  /**
> diff --git a/block/blk-merge.c b/block/blk-merge.c
> index 6460abdb2426..65e75efa9bd3 100644
> --- a/block/blk-merge.c
> +++ b/block/blk-merge.c
> @@ -867,6 +867,8 @@ static struct request *attempt_merge(struct request_queue *q,
>         if (!blk_discard_mergable(req))
>                 elv_merge_requests(q, req, next);
>
> +       blk_crypto_rq_put_keyslot(next);
> +

This looks good to me, but it looks like there was a pre-existing bug
in the blk-merge code. The elv_merged_request function is only called
when the request does not merge. Does anyone know if that behavior is
correct?

>         /*
>          * 'next' is going away, so update stats accordingly
>          */
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index d0cb2ef18fe2..49825538d932 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -840,6 +840,12 @@ static void blk_complete_request(struct request *req)
>                 req->q->integrity.profile->complete_fn(req, total_bytes);
>  #endif
>
> +       /*
> +        * Upper layers may call blk_crypto_evict_key() anytime after the last
> +        * bio_endio().  Therefore, the keyslot must be released before that.
> +        */
> +       blk_crypto_rq_put_keyslot(req);
> +
>         blk_account_io_completion(req, total_bytes);
>
>         do {
> @@ -905,6 +911,13 @@ bool blk_update_request(struct request *req, blk_status_t error,
>                 req->q->integrity.profile->complete_fn(req, nr_bytes);
>  #endif
>
> +       /*
> +        * Upper layers may call blk_crypto_evict_key() anytime after the last
> +        * bio_endio().  Therefore, the keyslot must be released before that.
> +        */
> +       if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
> +               __blk_crypto_rq_put_keyslot(req);
> +
>         if (unlikely(error && !blk_rq_is_passthrough(req) &&
>                      !(req->rq_flags & RQF_QUIET)) &&
>                      !test_bit(GD_DEAD, &req->q->disk->state)) {
> @@ -2967,7 +2980,7 @@ void blk_mq_submit_bio(struct bio *bio)
>
>         blk_mq_bio_to_request(rq, bio, nr_segs);
>
> -       ret = blk_crypto_init_request(rq);
> +       ret = blk_crypto_rq_get_keyslot(rq);
>         if (ret != BLK_STS_OK) {
>                 bio->bi_status = ret;
>                 bio_endio(bio);
> --
> 2.39.2
>

This patch itself looks good to me.

Reviewed-by: Nathan Huckleberry <nhuck@google.com>

Re: [PATCH v2 1/4] blk-mq: release crypto keyslot before reporting I/O complete

[Eric Biggers]

On Mon, Mar 13, 2023 at 02:26:00PM -0700, Nathan Huckleberry wrote:
> > diff --git a/block/blk-merge.c b/block/blk-merge.c
> > index 6460abdb2426..65e75efa9bd3 100644
> > --- a/block/blk-merge.c
> > +++ b/block/blk-merge.c
> > @@ -867,6 +867,8 @@ static struct request *attempt_merge(struct request_queue *q,
> >         if (!blk_discard_mergable(req))
> >                 elv_merge_requests(q, req, next);
> >
> > +       blk_crypto_rq_put_keyslot(next);
> > +
> 
> This looks good to me, but it looks like there was a pre-existing bug
> in the blk-merge code. The elv_merged_request function is only called
> when the request does not merge. Does anyone know if that behavior is
> correct?

That's very confusing to me too!

I did notice that attempt_merge() calls elv_merge_requests() (not to be confused
with elv_merged_request()) if it merges the requests.

So it seems there is elv_merge_requests() which means the request was merged,
and elv_merged_request() which means the request was *not* merged...  I have no
idea what is going on there :-(
	
> This patch itself looks good to me.
> 
> Reviewed-by: Nathan Huckleberry <nhuck@google.com>

Thanks.

Jens, Christoph, etc., anyone else want to take a look too?

- Eric

Re: [PATCH v2 1/4] blk-mq: release crypto keyslot before reporting I/O complete

[Christoph Hellwig]

On Tue, Mar 14, 2023 at 11:20:14AM -0700, Eric Biggers wrote:
> I did notice that attempt_merge() calls elv_merge_requests() (not to be confused
> with elv_merged_request()) if it merges the requests.
> 
> So it seems there is elv_merge_requests() which means the request was merged,
> and elv_merged_request() which means the request was *not* merged...  I have no
> idea what is going on there :-(

The naming looks very confusing, but that is indeed what the code
does.  The elevator code is in massive need of a cleanup, as it often
is that confusing.

Re: [PATCH v2 1/4] blk-mq: release crypto keyslot before reporting I/O complete

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>

[PATCH v2 2/4] blk-crypto: make blk_crypto_evict_key() more robust

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

If blk_crypto_evict_key() sees that the key is still in-use (due to a
bug) or that ->keyslot_evict failed, it currently just returns an error
while leaving the key linked into the keyslot management structures.

However, blk_crypto_evict_key() is only called in contexts such as inode
eviction where failure is not an option.  So actually the caller
proceeds with freeing the blk_crypto_key regardless of the return value
of blk_crypto_evict_key().

These two assumptions don't match, and the result is that there can be a
use-after-free in blk_crypto_reprogram_all_keys() after one of these
errors occurs.  (Note, these errors *shouldn't* happen; we're just
talking about what happens if they do anyway.)

Fix this by making blk_crypto_evict_key() unlink the key from the
keyslot management structures even on failure.

Fixes: 1b2628397058 ("block: Keyslot Manager for Inline Encryption")
Cc: stable@vger.kernel.org
Reviewed-by: Nathan Huckleberry <nhuck@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 block/blk-crypto-profile.c | 50 +++++++++++++++-----------------------
 block/blk-crypto.c         | 23 +++++++++++-------
 2 files changed, 33 insertions(+), 40 deletions(-)

diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
index 0307fb0d95d3..1b20ead59f39 100644
--- a/block/blk-crypto-profile.c
+++ b/block/blk-crypto-profile.c
@@ -354,22 +354,10 @@ bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
 	return true;
 }
 
-/**
- * __blk_crypto_evict_key() - Evict a key from a device.
- * @profile: the crypto profile of the device
- * @key: the key to evict.  It must not still be used in any I/O.
- *
- * If the device has keyslots, this finds the keyslot (if any) that contains the
- * specified key and calls the driver's keyslot_evict function to evict it.
- *
- * Otherwise, this just calls the driver's keyslot_evict function if it is
- * implemented, passing just the key (without any particular keyslot).  This
- * allows layered devices to evict the key from their underlying devices.
- *
- * Context: Process context. Takes and releases profile->lock.
- * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
- *	   if the keyslot is still in use, or another -errno value on other
- *	   error.
+/*
+ * This is an internal function that evicts a key from an inline encryption
+ * device that can be either a real device or the blk-crypto-fallback "device".
+ * It is used only by blk_crypto_evict_key(); see that function for details.
  */
 int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
 			   const struct blk_crypto_key *key)
@@ -389,22 +377,22 @@ int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
 
 	blk_crypto_hw_enter(profile);
 	slot = blk_crypto_find_keyslot(profile, key);
-	if (!slot)
-		goto out_unlock;
-
-	if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
-		err = -EBUSY;
-		goto out_unlock;
+	if (slot) {
+		if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
+			/* BUG: key is still in use by I/O */
+			err = -EBUSY;
+		} else {
+			err = profile->ll_ops.keyslot_evict(
+					profile, key,
+					blk_crypto_keyslot_index(slot));
+		}
+		/*
+		 * Callers may free the key even on error, so unlink the key
+		 * from the hash table and clear slot->key even on error.
+		 */
+		hlist_del(&slot->hash_node);
+		slot->key = NULL;
 	}
-	err = profile->ll_ops.keyslot_evict(profile, key,
-					    blk_crypto_keyslot_index(slot));
-	if (err)
-		goto out_unlock;
-
-	hlist_del(&slot->hash_node);
-	slot->key = NULL;
-	err = 0;
-out_unlock:
 	blk_crypto_hw_exit(profile);
 	return err;
 }
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index d0c7feb447e9..4e26fac64199 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -399,17 +399,22 @@ int blk_crypto_start_using_key(struct block_device *bdev,
 }
 
 /**
- * blk_crypto_evict_key() - Evict a key from any inline encryption hardware
- *			    it may have been programmed into
- * @bdev: The block_device who's associated inline encryption hardware this key
- *     might have been programmed into
- * @key: The key to evict
+ * blk_crypto_evict_key() - Evict a blk_crypto_key from a block_device
+ * @bdev: a block_device on which I/O using the key may have been done
+ * @key: the key to evict
  *
- * Upper layers (filesystems) must call this function to ensure that a key is
- * evicted from any hardware that it might have been programmed into.  The key
- * must not be in use by any in-flight IO when this function is called.
+ * For a given block_device, this function removes the given blk_crypto_key from
+ * the keyslot management structures and evicts it from any underlying hardware
+ * keyslot(s) or blk-crypto-fallback keyslot it may have been programmed into.
  *
- * Return: 0 on success or if the key wasn't in any keyslot; -errno on error.
+ * Upper layers must call this before freeing the blk_crypto_key.  It must be
+ * called for every block_device the key may have been used on.  The key must no
+ * longer be in use by any I/O when this function is called.
+ *
+ * Context: May sleep.
+ * Return: 0 on success or if the key wasn't in any keyslot; -errno if the key
+ *	   failed to be evicted from a keyslot or is still in-use.  Even on
+ *	   "failure", the key is removed from the keyslot management structures.
  */
 int blk_crypto_evict_key(struct block_device *bdev,
 			 const struct blk_crypto_key *key)
-- 
2.39.2

Re: [PATCH v2 2/4] blk-crypto: make blk_crypto_evict_key() more robust

[Christoph Hellwig]

On Wed, Mar 08, 2023 at 11:36:43AM -0800, Eric Biggers wrote:
>  			   const struct blk_crypto_key *key)
> @@ -389,22 +377,22 @@ int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
>  
>  	blk_crypto_hw_enter(profile);
>  	slot = blk_crypto_find_keyslot(profile, key);
> +	if (slot) {

Isn't !slot also an error condition that we should warn on?

> +		if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
> +			/* BUG: key is still in use by I/O */
> +			err = -EBUSY;

Either way two gotos to jump forward for the error case would improve
the readability of the code a fair bit I think.

> +		} else {
> +			err = profile->ll_ops.keyslot_evict(
> +					profile, key,
> +					blk_crypto_keyslot_index(slot));
> +		}
> +		/*
> +		 * Callers may free the key even on error, so unlink the key
> +		 * from the hash table and clear slot->key even on error.
> +		 */
> +		hlist_del(&slot->hash_node);
> +		slot->key = NULL;
>  	}
>  	blk_crypto_hw_exit(profile);
>  	return err;

Also given your above accurate description of the calling context,
what is the point of even returning an error here vs just logging
an error message?

Re: [PATCH v2 2/4] blk-crypto: make blk_crypto_evict_key() more robust

[Eric Biggers]

On Wed, Mar 15, 2023 at 09:23:12AM -0700, Christoph Hellwig wrote:
> On Wed, Mar 08, 2023 at 11:36:43AM -0800, Eric Biggers wrote:
> >  			   const struct blk_crypto_key *key)
> > @@ -389,22 +377,22 @@ int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
> >  
> >  	blk_crypto_hw_enter(profile);
> >  	slot = blk_crypto_find_keyslot(profile, key);
> > +	if (slot) {
> 
> Isn't !slot also an error condition that we should warn on?

No, definitely not.  Keys are not guaranteed to be in a keyslot.  I'll add a
comment here.

> 
> > +		if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
> > +			/* BUG: key is still in use by I/O */
> > +			err = -EBUSY;
> 
> Either way two gotos to jump forward for the error case would improve
> the readability of the code a fair bit I think.

I slightly prefer it without the gotos, but sure I'll do it that way.

> > +		} else {
> > +			err = profile->ll_ops.keyslot_evict(
> > +					profile, key,
> > +					blk_crypto_keyslot_index(slot));
> > +		}
> > +		/*
> > +		 * Callers may free the key even on error, so unlink the key
> > +		 * from the hash table and clear slot->key even on error.
> > +		 */
> > +		hlist_del(&slot->hash_node);
> > +		slot->key = NULL;
> >  	}
> >  	blk_crypto_hw_exit(profile);
> >  	return err;
> 
> Also given your above accurate description of the calling context,
> what is the point of even returning an error here vs just logging
> an error message?

Yes, I was thinking about that too.  I'll add a patch that makes
blk_crypto_evict_key() log errors and return void.

- Eric

[PATCH v2 3/4] blk-crypto: remove blk_crypto_insert_cloned_request()

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

blk_crypto_insert_cloned_request() is the same as
blk_crypto_rq_get_keyslot(), so just use that directly.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 Documentation/block/inline-encryption.rst |  3 +--
 block/blk-crypto-internal.h               | 15 ---------------
 block/blk-mq.c                            |  2 +-
 3 files changed, 2 insertions(+), 18 deletions(-)

diff --git a/Documentation/block/inline-encryption.rst b/Documentation/block/inline-encryption.rst
index f9bf18ea6509..90b733422ed4 100644
--- a/Documentation/block/inline-encryption.rst
+++ b/Documentation/block/inline-encryption.rst
@@ -270,8 +270,7 @@ Request queue based layered devices like dm-rq that wish to support inline
 encryption need to create their own blk_crypto_profile for their request_queue,
 and expose whatever functionality they choose. When a layered device wants to
 pass a clone of that request to another request_queue, blk-crypto will
-initialize and prepare the clone as necessary; see
-``blk_crypto_insert_cloned_request()``.
+initialize and prepare the clone as necessary.
 
 Interaction between inline encryption and blk integrity
 =======================================================
diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
index 4f1de2495f0c..93a141979694 100644
--- a/block/blk-crypto-internal.h
+++ b/block/blk-crypto-internal.h
@@ -205,21 +205,6 @@ static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio,
 	return 0;
 }
 
-/**
- * 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_rq_get_keyslot(rq);
-	return BLK_STS_OK;
-}
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK
 
 int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 49825538d932..5e819de2f5e7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3049,7 +3049,7 @@ blk_status_t blk_insert_cloned_request(struct request *rq)
 	if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
-	if (blk_crypto_insert_cloned_request(rq))
+	if (blk_crypto_rq_get_keyslot(rq))
 		return BLK_STS_IOERR;
 
 	blk_account_io_start(rq);
-- 
2.39.2

Re: [PATCH v2 3/4] blk-crypto: remove blk_crypto_insert_cloned_request()

[Christoph Hellwig]

> -	if (blk_crypto_insert_cloned_request(rq))
> +	if (blk_crypto_rq_get_keyslot(rq))
>  		return BLK_STS_IOERR;

Wouldn't it be better to propagate the actual error from
blk_crypto_rq_get_keyslot?

Re: [PATCH v2 3/4] blk-crypto: remove blk_crypto_insert_cloned_request()

[Eric Biggers]

On Wed, Mar 15, 2023 at 09:24:04AM -0700, Christoph Hellwig wrote:
> > -	if (blk_crypto_insert_cloned_request(rq))
> > +	if (blk_crypto_rq_get_keyslot(rq))
> >  		return BLK_STS_IOERR;
> 
> Wouldn't it be better to propagate the actual error from
> blk_crypto_rq_get_keyslot?
> 

I'll add a patch that does that.

- Eric

[PATCH v2 4/4] blk-crypto: drop the NULL check from blk_crypto_put_keyslot()

[Eric Biggers]

From: Eric Biggers <ebiggers@google.com>

Now that all callers of blk_crypto_put_keyslot() check for NULL before
calling it, there is no need for blk_crypto_put_keyslot() to do the NULL
check itself.

Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 block/blk-crypto-profile.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
index 1b20ead59f39..6c16edfa0dee 100644
--- a/block/blk-crypto-profile.c
+++ b/block/blk-crypto-profile.c
@@ -227,14 +227,13 @@ EXPORT_SYMBOL_GPL(blk_crypto_keyslot_index);
  * @profile: the crypto profile of the device the key will be used on
  * @key: the key that will be used
  * @slot_ptr: If a keyslot is allocated, an opaque pointer to the keyslot struct
- *	      will be stored here; otherwise NULL will be stored here.
+ *	      will be stored here.  blk_crypto_put_keyslot() must be called
+ *	      later to release it.  Otherwise, NULL will be stored here.
  *
  * If the device has keyslots, this gets a keyslot that's been programmed with
  * the specified key.  If the key is already in a slot, this reuses it;
  * otherwise this waits for a slot to become idle and programs the key into it.
  *
- * This must be paired with a call to blk_crypto_put_keyslot().
- *
  * Context: Process context. Takes and releases profile->lock.
  * Return: BLK_STS_OK on success, meaning that either a keyslot was allocated or
  *	   one wasn't needed; or a blk_status_t error on failure.
@@ -312,20 +311,15 @@ blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
 
 /**
  * blk_crypto_put_keyslot() - Release a reference to a keyslot
- * @slot: The keyslot to release the reference of (may be NULL).
+ * @slot: The keyslot to release the reference of
  *
  * Context: Any context.
  */
 void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot)
 {
-	struct blk_crypto_profile *profile;
+	struct blk_crypto_profile *profile = slot->profile;
 	unsigned long flags;
 
-	if (!slot)
-		return;
-
-	profile = slot->profile;
-
 	if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
 					&profile->idle_slots_lock, flags)) {
 		list_add_tail(&slot->idle_slot_node, &profile->idle_slots);
-- 
2.39.2

Re: [PATCH v2 4/4] blk-crypto: drop the NULL check from blk_crypto_put_keyslot()

[Christoph Hellwig]

Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>