summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/Kconfig17
-rw-r--r--block/Makefile3
-rw-r--r--block/bio-crypt-ctx.c142
-rw-r--r--block/bio.c26
-rw-r--r--block/blk-core.c34
-rw-r--r--block/blk-crypto-fallback.c644
-rw-r--r--block/blk-crypto-internal.h67
-rw-r--r--block/blk-crypto.c306
-rw-r--r--block/blk-merge.c11
-rw-r--r--block/cfq-iosched.c81
-rw-r--r--block/keyslot-manager.c664
11 files changed, 1976 insertions, 19 deletions
diff --git a/block/Kconfig b/block/Kconfig
index 28ec55752b68..4d9bcb951d83 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -184,6 +184,23 @@ config BLK_SED_OPAL
Enabling this option enables users to setup/unlock/lock
Locking ranges for SED devices using the Opal protocol.
+config BLK_INLINE_ENCRYPTION
+ bool "Enable inline encryption support in block layer"
+ help
+ Build the blk-crypto subsystem. Enabling this lets the
+ block layer handle encryption, so users can take
+ advantage of inline encryption hardware if present.
+
+config BLK_INLINE_ENCRYPTION_FALLBACK
+ bool "Enable crypto API fallback for blk-crypto"
+ depends on BLK_INLINE_ENCRYPTION
+ select CRYPTO
+ select CRYPTO_BLKCIPHER
+ help
+ Enabling this lets the block layer handle inline encryption
+ by falling back to the kernel crypto API when inline
+ encryption hardware is not present.
+
menu "Partition Types"
source "block/partitions/Kconfig"
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..ab14055d8222 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -35,3 +35,6 @@ obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o
obj-$(CONFIG_BLK_WBT) += blk-wbt.o
obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o bio-crypt-ctx.o \
+ blk-crypto.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o \ No newline at end of file
diff --git a/block/bio-crypt-ctx.c b/block/bio-crypt-ctx.c
new file mode 100644
index 000000000000..75008b2afea2
--- /dev/null
+++ b/block/bio-crypt-ctx.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/keyslot-manager.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "blk-crypto-internal.h"
+
+static int num_prealloc_crypt_ctxs = 128;
+
+module_param(num_prealloc_crypt_ctxs, int, 0444);
+MODULE_PARM_DESC(num_prealloc_crypt_ctxs,
+ "Number of bio crypto contexts to preallocate");
+
+static struct kmem_cache *bio_crypt_ctx_cache;
+static mempool_t *bio_crypt_ctx_pool;
+
+int __init bio_crypt_ctx_init(void)
+{
+ size_t i;
+
+ bio_crypt_ctx_cache = KMEM_CACHE(bio_crypt_ctx, 0);
+ if (!bio_crypt_ctx_cache)
+ return -ENOMEM;
+
+ bio_crypt_ctx_pool = mempool_create_slab_pool(num_prealloc_crypt_ctxs,
+ bio_crypt_ctx_cache);
+ if (!bio_crypt_ctx_pool)
+ return -ENOMEM;
+
+ /* This is assumed in various places. */
+ BUILD_BUG_ON(BLK_ENCRYPTION_MODE_INVALID != 0);
+
+ /* Sanity check that no algorithm exceeds the defined limits. */
+ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) {
+ BUG_ON(blk_crypto_modes[i].keysize > BLK_CRYPTO_MAX_KEY_SIZE);
+ BUG_ON(blk_crypto_modes[i].ivsize > BLK_CRYPTO_MAX_IV_SIZE);
+ }
+
+ return 0;
+}
+
+struct bio_crypt_ctx *bio_crypt_alloc_ctx(gfp_t gfp_mask)
+{
+ return mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+}
+EXPORT_SYMBOL_GPL(bio_crypt_alloc_ctx);
+
+void bio_crypt_free_ctx(struct bio *bio)
+{
+ mempool_free(bio->bi_crypt_context, bio_crypt_ctx_pool);
+ bio->bi_crypt_context = NULL;
+}
+
+void bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
+{
+ const struct bio_crypt_ctx *src_bc = src->bi_crypt_context;
+
+ bio_clone_skip_dm_default_key(dst, src);
+
+ /*
+ * If a bio is fallback_crypted, then it will be decrypted when
+ * bio_endio is called. As we only want the data to be decrypted once,
+ * copies of the bio must not have have a crypt context.
+ */
+ if (!src_bc || bio_crypt_fallback_crypted(src_bc))
+ return;
+
+ dst->bi_crypt_context = bio_crypt_alloc_ctx(gfp_mask);
+ *dst->bi_crypt_context = *src_bc;
+
+ if (src_bc->bc_keyslot >= 0)
+ keyslot_manager_get_slot(src_bc->bc_ksm, src_bc->bc_keyslot);
+}
+EXPORT_SYMBOL_GPL(bio_crypt_clone);
+
+bool bio_crypt_should_process(struct request *rq)
+{
+ struct bio *bio = rq->bio;
+
+ if (!bio || !bio->bi_crypt_context)
+ return false;
+
+ return rq->q->ksm == bio->bi_crypt_context->bc_ksm;
+}
+EXPORT_SYMBOL_GPL(bio_crypt_should_process);
+
+/*
+ * Checks that two bio crypt contexts are compatible - i.e. that
+ * they are mergeable except for data_unit_num continuity.
+ */
+bool bio_crypt_ctx_compatible(struct bio *b_1, struct bio *b_2)
+{
+ struct bio_crypt_ctx *bc1 = b_1->bi_crypt_context;
+ struct bio_crypt_ctx *bc2 = b_2->bi_crypt_context;
+
+ if (!bc1)
+ return !bc2;
+ return bc2 && bc1->bc_key == bc2->bc_key;
+}
+
+/*
+ * Checks that two bio crypt contexts are compatible, and also
+ * that their data_unit_nums are continuous (and can hence be merged)
+ * in the order b_1 followed by b_2.
+ */
+bool bio_crypt_ctx_mergeable(struct bio *b_1, unsigned int b1_bytes,
+ struct bio *b_2)
+{
+ struct bio_crypt_ctx *bc1 = b_1->bi_crypt_context;
+ struct bio_crypt_ctx *bc2 = b_2->bi_crypt_context;
+
+ if (!bio_crypt_ctx_compatible(b_1, b_2))
+ return false;
+
+ return !bc1 || bio_crypt_dun_is_contiguous(bc1, b1_bytes, bc2->bc_dun);
+}
+
+void bio_crypt_ctx_release_keyslot(struct bio_crypt_ctx *bc)
+{
+ keyslot_manager_put_slot(bc->bc_ksm, bc->bc_keyslot);
+ bc->bc_ksm = NULL;
+ bc->bc_keyslot = -1;
+}
+
+int bio_crypt_ctx_acquire_keyslot(struct bio_crypt_ctx *bc,
+ struct keyslot_manager *ksm)
+{
+ int slot = keyslot_manager_get_slot_for_key(ksm, bc->bc_key);
+
+ if (slot < 0)
+ return slot;
+
+ bc->bc_keyslot = slot;
+ bc->bc_ksm = ksm;
+ return 0;
+}
diff --git a/block/bio.c b/block/bio.c
index 30df1b45dde8..a7089b2d2943 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,6 +28,7 @@
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>
+#include <linux/blk-crypto.h>
#include <trace/events/block.h>
#include "blk.h"
@@ -243,6 +244,8 @@ fallback:
void bio_uninit(struct bio *bio)
{
bio_disassociate_task(bio);
+
+ bio_crypt_free_ctx(bio);
}
EXPORT_SYMBOL(bio_uninit);
@@ -628,15 +631,12 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
__bio_clone_fast(b, bio);
- if (bio_integrity(bio)) {
- int ret;
-
- ret = bio_integrity_clone(b, bio, gfp_mask);
+ bio_crypt_clone(b, bio, gfp_mask);
- if (ret < 0) {
- bio_put(b);
- return NULL;
- }
+ if (bio_integrity(bio) &&
+ bio_integrity_clone(b, bio, gfp_mask) < 0) {
+ bio_put(b);
+ return NULL;
}
return b;
@@ -704,6 +704,8 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
break;
}
+ bio_crypt_clone(bio, bio_src, gfp_mask);
+
if (bio_integrity(bio_src)) {
int ret;
@@ -876,6 +878,9 @@ void __bio_add_page(struct bio *bio, struct page *page,
bio->bi_iter.bi_size += len;
bio->bi_vcnt++;
+
+ if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
+ bio_set_flag(bio, BIO_WORKINGSET);
}
EXPORT_SYMBOL_GPL(__bio_add_page);
@@ -1032,6 +1037,7 @@ 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);
@@ -1889,6 +1895,10 @@ void bio_endio(struct bio *bio)
again:
if (!bio_remaining_done(bio))
return;
+
+ if (!blk_crypto_endio(bio))
+ return;
+
if (!bio_integrity_endio(bio))
return;
diff --git a/block/blk-core.c b/block/blk-core.c
index 2407c898ba7d..41cb061c29f2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -34,6 +34,8 @@
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>
#include <linux/debugfs.h>
+#include <linux/psi.h>
+#include <linux/blk-crypto.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
@@ -2226,7 +2228,9 @@ 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]);
- ret = q->make_request_fn(q, bio);
+
+ if (!blk_crypto_submit_bio(&bio))
+ ret = q->make_request_fn(q, bio);
blk_queue_exit(q);
@@ -2271,6 +2275,10 @@ EXPORT_SYMBOL(generic_make_request);
*/
blk_qc_t submit_bio(struct bio *bio)
{
+ bool workingset_read = false;
+ unsigned long pflags;
+ blk_qc_t ret;
+
/*
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
@@ -2286,6 +2294,8 @@ blk_qc_t submit_bio(struct bio *bio)
if (op_is_write(bio_op(bio))) {
count_vm_events(PGPGOUT, count);
} else {
+ if (bio_flagged(bio, BIO_WORKINGSET))
+ workingset_read = true;
task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
@@ -2300,7 +2310,21 @@ blk_qc_t submit_bio(struct bio *bio)
}
}
- return generic_make_request(bio);
+ /*
+ * If we're reading data that is part of the userspace
+ * workingset, count submission time as memory stall. When the
+ * device is congested, or the submitting cgroup IO-throttled,
+ * submission can be a significant part of overall IO time.
+ */
+ if (workingset_read)
+ psi_memstall_enter(&pflags);
+
+ ret = generic_make_request(bio);
+
+ if (workingset_read)
+ psi_memstall_leave(&pflags);
+
+ return ret;
}
EXPORT_SYMBOL(submit_bio);
@@ -3648,5 +3672,11 @@ int __init blk_dev_init(void)
blk_debugfs_root = debugfs_create_dir("block", NULL);
#endif
+ if (bio_crypt_ctx_init() < 0)
+ panic("Failed to allocate mem for bio crypt ctxs\n");
+
+ if (blk_crypto_fallback_init() < 0)
+ panic("Failed to init blk-crypto-fallback\n");
+
return 0;
}
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
new file mode 100644
index 000000000000..ad83e1077ba3
--- /dev/null
+++ b/block/blk-crypto-fallback.c
@@ -0,0 +1,644 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * Refer to Documentation/block/inline-encryption.rst for detailed explanation.
+ */
+
+#define pr_fmt(fmt) "blk-crypto-fallback: " fmt
+
+#include <crypto/skcipher.h>
+#include <linux/blk-cgroup.h>
+#include <linux/blk-crypto.h>
+#include <linux/crypto.h>
+#include <linux/keyslot-manager.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/random.h>
+
+#include "blk-crypto-internal.h"
+
+static unsigned int num_prealloc_bounce_pg = 32;
+module_param(num_prealloc_bounce_pg, uint, 0);
+MODULE_PARM_DESC(num_prealloc_bounce_pg,
+ "Number of preallocated bounce pages for the blk-crypto crypto API fallback");
+
+static unsigned int blk_crypto_num_keyslots = 100;
+module_param_named(num_keyslots, blk_crypto_num_keyslots, uint, 0);
+MODULE_PARM_DESC(num_keyslots,
+ "Number of keyslots for the blk-crypto crypto API fallback");
+
+static unsigned int num_prealloc_fallback_crypt_ctxs = 128;
+module_param(num_prealloc_fallback_crypt_ctxs, uint, 0);
+MODULE_PARM_DESC(num_prealloc_crypt_fallback_ctxs,
+ "Number of preallocated bio fallback crypto contexts for blk-crypto to use during crypto API fallback");
+
+struct bio_fallback_crypt_ctx {
+ struct bio_crypt_ctx crypt_ctx;
+ /*
+ * Copy of the bvec_iter when this bio was submitted.
+ * We only want to en/decrypt the part of the bio as described by the
+ * bvec_iter upon submission because bio might be split before being
+ * resubmitted
+ */
+ struct bvec_iter crypt_iter;
+ u64 fallback_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+};
+
+/* The following few vars are only used during the crypto API fallback */
+static struct kmem_cache *bio_fallback_crypt_ctx_cache;
+static mempool_t *bio_fallback_crypt_ctx_pool;
+
+/*
+ * Allocating a crypto tfm during I/O can deadlock, so we have to preallocate
+ * all of a mode's tfms when that mode starts being used. Since each mode may
+ * need all the keyslots at some point, each mode needs its own tfm for each
+ * keyslot; thus, a keyslot may contain tfms for multiple modes. However, to
+ * match the behavior of real inline encryption hardware (which only supports a
+ * single encryption context per keyslot), we only allow one tfm per keyslot to
+ * be used at a time - the rest of the unused tfms have their keys cleared.
+ */
+static DEFINE_MUTEX(tfms_init_lock);
+static bool tfms_inited[BLK_ENCRYPTION_MODE_MAX];
+
+struct blk_crypto_decrypt_work {
+ struct work_struct work;
+ struct bio *bio;
+};
+
+static struct blk_crypto_keyslot {
+ struct crypto_skcipher *tfm;
+ enum blk_crypto_mode_num crypto_mode;
+ struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX];
+} *blk_crypto_keyslots;
+
+/* The following few vars are only used during the crypto API fallback */
+static struct keyslot_manager *blk_crypto_ksm;
+static struct workqueue_struct *blk_crypto_wq;
+static mempool_t *blk_crypto_bounce_page_pool;
+static struct kmem_cache *blk_crypto_decrypt_work_cache;
+
+bool bio_crypt_fallback_crypted(const struct bio_crypt_ctx *bc)
+{
+ return bc && bc->bc_ksm == blk_crypto_ksm;
+}
+
+/*
+ * This is the key we set when evicting a keyslot. This *should* be the all 0's
+ * key, but AES-XTS rejects that key, so we use some random bytes instead.
+ */
+static u8 blank_key[BLK_CRYPTO_MAX_KEY_SIZE];
+
+static void blk_crypto_evict_keyslot(unsigned int slot)
+{
+ struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ enum blk_crypto_mode_num crypto_mode = slotp->crypto_mode;
+ int err;
+
+ WARN_ON(slotp->crypto_mode == BLK_ENCRYPTION_MODE_INVALID);
+
+ /* Clear the key in the skcipher */
+ err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], blank_key,
+ blk_crypto_modes[crypto_mode].keysize);
+ WARN_ON(err);
+ slotp->crypto_mode = BLK_ENCRYPTION_MODE_INVALID;
+}
+
+static int blk_crypto_keyslot_program(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
+{
+ struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ const enum blk_crypto_mode_num crypto_mode = key->crypto_mode;
+ int err;
+
+ if (crypto_mode != slotp->crypto_mode &&
+ slotp->crypto_mode != BLK_ENCRYPTION_MODE_INVALID) {
+ blk_crypto_evict_keyslot(slot);
+ }
+
+ if (!slotp->tfms[crypto_mode])
+ return -ENOMEM;
+ slotp->crypto_mode = crypto_mode;
+ err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->raw,
+ key->size);
+ if (err) {
+ blk_crypto_evict_keyslot(slot);
+ return err;
+ }
+ return 0;
+}
+
+static int blk_crypto_keyslot_evict(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
+{
+ blk_crypto_evict_keyslot(slot);
+ return 0;
+}
+
+/*
+ * The crypto API fallback KSM ops - only used for a bio when it specifies a
+ * blk_crypto_mode for which we failed to get a keyslot in the device's inline
+ * encryption hardware (which probably means the device doesn't have inline
+ * encryption hardware that supports that crypto mode).
+ */
+static const struct keyslot_mgmt_ll_ops blk_crypto_ksm_ll_ops = {
+ .keyslot_program = blk_crypto_keyslot_program,
+ .keyslot_evict = blk_crypto_keyslot_evict,
+};
+
+static void blk_crypto_encrypt_endio(struct bio *enc_bio)
+{
+ struct bio *src_bio = enc_bio->bi_private;
+ int i;
+
+ for (i = 0; i < enc_bio->bi_vcnt; i++)
+ mempool_free(enc_bio->bi_io_vec[i].bv_page,
+ blk_crypto_bounce_page_pool);
+
+ src_bio->bi_status = enc_bio->bi_status;
+
+ bio_put(enc_bio);
+ bio_endio(src_bio);
+}
+
+static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
+{
+ struct bvec_iter iter;
+ struct bio_vec bv;
+ struct bio *bio;
+
+ bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src), NULL);
+ if (!bio)
+ return NULL;
+ bio->bi_disk = bio_src->bi_disk;
+ bio->bi_opf = bio_src->bi_opf;
+ bio->bi_ioprio = bio_src->bi_ioprio;
+ bio->bi_write_hint = bio_src->bi_write_hint;
+ bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
+ bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
+
+ bio_for_each_segment(bv, bio_src, iter)
+ bio->bi_io_vec[bio->bi_vcnt++] = bv;
+
+ if (bio_integrity(bio_src) &&
+ bio_integrity_clone(bio, bio_src, GFP_NOIO) < 0) {
+ bio_put(bio);
+ return NULL;
+ }
+
+ bio_clone_blkcg_association(bio, bio_src);
+
+ bio_clone_skip_dm_default_key(bio, bio_src);
+
+ return bio;
+}
+
+static int blk_crypto_alloc_cipher_req(struct bio *src_bio,
+ struct skcipher_request **ciph_req_ret,
+ struct crypto_wait *wait)
+{
+ struct skcipher_request *ciph_req;
+ const struct blk_crypto_keyslot *slotp;
+
+ slotp = &blk_crypto_keyslots[src_bio->bi_crypt_context->bc_keyslot];
+ ciph_req = skcipher_request_alloc(slotp->tfms[slotp->crypto_mode],
+ GFP_NOIO);
+ if (!ciph_req) {
+ src_bio->bi_status = BLK_STS_RESOURCE;
+ return -ENOMEM;
+ }
+
+ skcipher_request_set_callback(ciph_req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG |
+ CRYPTO_TFM_REQ_MAY_SLEEP,
+ crypto_req_done, wait);
+ *ciph_req_ret = ciph_req;
+ return 0;
+}
+
+static int blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
+{
+ struct bio *bio = *bio_ptr;
+ unsigned int i = 0;
+ unsigned int num_sectors = 0;
+ struct bio_vec bv;
+ struct bvec_iter iter;
+
+ bio_for_each_segment(bv, bio, iter) {
+ num_sectors += bv.bv_len >> SECTOR_SHIFT;
+ if (++i == BIO_MAX_PAGES)
+ break;
+ }
+ if (num_sectors < bio_sectors(bio)) {
+ struct bio *split_bio;
+
+ split_bio = bio_split(bio, num_sectors, GFP_NOIO, NULL);
+ if (!split_bio) {
+ bio->bi_status = BLK_STS_RESOURCE;
+ return -ENOMEM;
+ }
+ bio_chain(split_bio, bio);
+ generic_make_request(bio);
+ *bio_ptr = split_bio;
+ }
+ return 0;
+}
+
+union blk_crypto_iv {
+ __le64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+ u8 bytes[BLK_CRYPTO_MAX_IV_SIZE];
+};
+
+static void blk_crypto_dun_to_iv(const u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE],
+ union blk_crypto_iv *iv)
+{
+ int i;
+
+ for (i = 0; i < BLK_CRYPTO_DUN_ARRAY_SIZE; i++)
+ iv->dun[i] = cpu_to_le64(dun[i]);
+}
+
+/*
+ * The crypto API fallback's encryption routine.
+ * Allocate a bounce bio for encryption, encrypt the input bio using crypto API,
+ * and replace *bio_ptr with the bounce bio. May split input bio if it's too
+ * large.
+ */
+static int blk_crypto_encrypt_bio(struct bio **bio_ptr)
+{
+ struct bio *src_bio;
+ struct skcipher_request *ciph_req = NULL;
+ DECLARE_CRYPTO_WAIT(wait);
+ u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+ union blk_crypto_iv iv;
+ struct scatterlist src, dst;
+ struct bio *enc_bio;
+ unsigned int i, j;
+ int data_unit_size;
+ struct bio_crypt_ctx *bc;
+ int err = 0;
+
+ /* Split the bio if it's too big for single page bvec */
+ err = blk_crypto_split_bio_if_needed(bio_ptr);
+ if (err)
+ return err;
+
+ src_bio = *bio_ptr;
+ bc = src_bio->bi_crypt_context;
+ data_unit_size = bc->bc_key->data_unit_size;
+
+ /* Allocate bounce bio for encryption */
+ enc_bio = blk_crypto_clone_bio(src_bio);
+ if (!enc_bio) {
+ src_bio->bi_status = BLK_STS_RESOURCE;
+ return -ENOMEM;
+ }
+
+ /*
+ * Use the crypto API fallback keyslot manager to get a crypto_skcipher
+ * for the algorithm and key specified for this bio.
+ */
+ err = bio_crypt_ctx_acquire_keyslot(bc, blk_crypto_ksm);
+ if (err) {
+ src_bio->bi_status = BLK_STS_IOERR;
+ goto out_put_enc_bio;
+ }
+
+ /* and then allocate an skcipher_request for it */
+ err = blk_crypto_alloc_cipher_req(src_bio, &ciph_req, &wait);
+ if (err)
+ goto out_release_keyslot;
+
+ memcpy(curr_dun, bc->bc_dun, sizeof(curr_dun));
+ sg_init_table(&src, 1);
+ sg_init_table(&dst, 1);
+
+ skcipher_request_set_crypt(ciph_req, &src, &dst, data_unit_size,
+ iv.bytes);
+
+ /* Encrypt each page in the bounce bio */
+ for (i = 0; i < enc_bio->bi_vcnt; i++) {
+ struct bio_vec *enc_bvec = &enc_bio->bi_io_vec[i];
+ struct page *plaintext_page = enc_bvec->bv_page;
+ struct page *ciphertext_page =
+ mempool_alloc(blk_crypto_bounce_page_pool, GFP_NOIO);
+
+ enc_bvec->bv_page = ciphertext_page;
+
+ if (!ciphertext_page) {
+ src_bio->bi_status = BLK_STS_RESOURCE;
+ err = -ENOMEM;
+ goto out_free_bounce_pages;
+ }
+
+ sg_set_page(&src, plaintext_page, data_unit_size,
+ enc_bvec->bv_offset);
+ sg_set_page(&dst, ciphertext_page, data_unit_size,
+ enc_bvec->bv_offset);
+
+ /* Encrypt each data unit in this page */
+ for (j = 0; j < enc_bvec->bv_len; j += data_unit_size) {
+ blk_crypto_dun_to_iv(curr_dun, &iv);
+ err = crypto_wait_req(crypto_skcipher_encrypt(ciph_req),
+ &wait);
+ if (err) {
+ i++;
+ src_bio->bi_status = BLK_STS_RESOURCE;
+ goto out_free_bounce_pages;
+ }
+ bio_crypt_dun_increment(curr_dun, 1);
+ src.offset += data_unit_size;
+ dst.offset += data_unit_size;
+ }
+ }
+
+ enc_bio->bi_private = src_bio;
+ enc_bio->bi_end_io = blk_crypto_encrypt_endio;
+ *bio_ptr = enc_bio;
+
+ enc_bio = NULL;
+ err = 0;
+ goto out_free_ciph_req;
+
+out_free_bounce_pages:
+ while (i > 0)
+ mempool_free(enc_bio->bi_io_vec[--i].bv_page,
+ blk_crypto_bounce_page_pool);
+out_free_ciph_req:
+ skcipher_request_free(ciph_req);
+out_release_keyslot:
+ bio_crypt_ctx_release_keyslot(bc);
+out_put_enc_bio:
+ if (enc_bio)
+ bio_put(enc_bio);
+
+ return err;
+}
+
+static void blk_crypto_free_fallback_crypt_ctx(struct bio *bio)
+{
+ mempool_free(container_of(bio->bi_crypt_context,
+ struct bio_fallback_crypt_ctx,
+ crypt_ctx),
+ bio_fallback_crypt_ctx_pool);
+ bio->bi_crypt_context = NULL;
+}
+
+/*
+ * The crypto API fallback's main decryption routine.
+ * Decrypts input bio in place.
+ */
+static void blk_crypto_decrypt_bio(struct work_struct *work)
+{
+ struct blk_crypto_decrypt_work *decrypt_work =
+ container_of(work, struct blk_crypto_decrypt_work, work);
+ struct bio *bio = decrypt_work->bio;
+ struct skcipher_request *ciph_req = NULL;
+ DECLARE_CRYPTO_WAIT(wait);
+ struct bio_vec bv;
+ struct bvec_iter iter;
+ u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
+ union blk_crypto_iv iv;
+ struct scatterlist sg;
+ struct bio_crypt_ctx *bc = bio->bi_crypt_context;
+ struct bio_fallback_crypt_ctx *f_ctx =
+ container_of(bc, struct bio_fallback_crypt_ctx, crypt_ctx);
+ const int data_unit_size = bc->bc_key->data_unit_size;
+ unsigned int i;
+ int err;
+
+ /*
+ * Use the crypto API fallback keyslot manager to get a crypto_skcipher
+ * for the algorithm and key specified for this bio.
+ */
+ if (bio_crypt_ctx_acquire_keyslot(bc, blk_crypto_ksm)) {
+ bio->bi_status = BLK_STS_RESOURCE;
+ goto out_no_keyslot;
+ }
+
+ /* and then allocate an skcipher_request for it */
+ err = blk_crypto_alloc_cipher_req(bio, &ciph_req, &wait);
+ if (err)
+ goto out;
+
+ memcpy(curr_dun, f_ctx->fallback_dun, sizeof(curr_dun));
+ sg_init_table(&sg, 1);
+ skcipher_request_set_crypt(ciph_req, &sg, &sg, data_unit_size,
+ iv.bytes);
+
+ /* Decrypt each segment in the bio */
+ __bio_for_each_segment(bv, bio, iter, f_ctx->crypt_iter) {
+ struct page *page = bv.bv_page;
+
+ sg_set_page(&sg, page, data_unit_size, bv.bv_offset);
+
+ /* Decrypt each data unit in the segment */
+ for (i = 0; i < bv.bv_len; i += data_unit_size) {
+ blk_crypto_dun_to_iv(curr_dun, &iv);
+ if (crypto_wait_req(crypto_skcipher_decrypt(ciph_req),
+ &wait)) {
+ bio->bi_status = BLK_STS_IOERR;
+ goto out;
+ }
+ bio_crypt_dun_increment(curr_dun, 1);
+ sg.offset += data_unit_size;
+ }
+ }
+
+out:
+ skcipher_request_free(ciph_req);
+ bio_crypt_ctx_release_keyslot(bc);
+out_no_keyslot:
+ kmem_cache_free(blk_crypto_decrypt_work_cache, decrypt_work);
+ blk_crypto_free_fallback_crypt_ctx(bio);
+ bio_endio(bio);
+}
+
+/*
+ * Queue bio for decryption.
+ * Returns true iff bio was queued for decryption.
+ */
+bool blk_crypto_queue_decrypt_bio(struct bio *bio)
+{
+ struct blk_crypto_decrypt_work *decrypt_work;
+
+ /* If there was an IO error, don't queue for decrypt. */
+ if (bio->bi_status)
+ goto out;
+
+ decrypt_work = kmem_cache_zalloc(blk_crypto_decrypt_work_cache,
+ GFP_ATOMIC);
+ if (!decrypt_work) {
+ bio->bi_status = BLK_STS_RESOURCE;
+ goto out;
+ }
+
+ INIT_WORK(&decrypt_work->work, blk_crypto_decrypt_bio);
+ decrypt_work->bio = bio;
+ queue_work(blk_crypto_wq, &decrypt_work->work);
+
+ return true;
+out:
+ blk_crypto_free_fallback_crypt_ctx(bio);
+ return false;
+}
+
+/*
+ * Prepare blk-crypto-fallback for the specified crypto mode.
+ * Returns -ENOPKG if the needed crypto API support is missing.
+ */
+int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num)
+{
+ const char *cipher_str = blk_crypto_modes[mode_num].cipher_str;
+ struct blk_crypto_keyslot *slotp;
+ unsigned int i;
+ int err = 0;
+
+ /*
+ * Fast path
+ * Ensure that updates to blk_crypto_keyslots[i].tfms[mode_num]
+ * for each i are visible before we try to access them.
+ */
+ if (likely(smp_load_acquire(&tfms_inited[mode_num])))
+ return 0;
+
+ mutex_lock(&tfms_init_lock);
+ if (likely(tfms_inited[mode_num]))
+ goto out;
+
+ for (i = 0; i < blk_crypto_num_keyslots; i++) {
+ slotp = &blk_crypto_keyslots[i];
+ slotp->tfms[mode_num] = crypto_alloc_skcipher(cipher_str, 0, 0);
+ if (IS_ERR(slotp->tfms[mode_num])) {
+ err = PTR_ERR(slotp->tfms[mode_num]);
+ if (err == -ENOENT) {
+ pr_warn_once("Missing crypto API support for \"%s\"\n",
+ cipher_str);
+ err = -ENOPKG;
+ }
+ slotp->tfms[mode_num] = NULL;
+ goto out_free_tfms;
+ }
+
+ crypto_skcipher_set_flags(slotp->tfms[mode_num],
+ CRYPTO_TFM_REQ_WEAK_KEY);
+ }
+
+ /*
+ * Ensure that updates to blk_crypto_keyslots[i].tfms[mode_num]
+ * for each i are visible before we set tfms_inited[mode_num].
+ */
+ smp_store_release(&tfms_inited[mode_num], true);
+ goto out;
+
+out_free_tfms:
+ for (i = 0; i < blk_crypto_num_keyslots; i++) {
+ slotp = &blk_crypto_keyslots[i];
+ crypto_free_skcipher(slotp->tfms[mode_num]);
+ slotp->tfms[mode_num] = NULL;
+ }
+out:
+ mutex_unlock(&tfms_init_lock);
+ return err;
+}
+
+int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key)
+{
+ return keyslot_manager_evict_key(blk_crypto_ksm, key);
+}
+
+int blk_crypto_fallback_submit_bio(struct bio **bio_ptr)
+{
+ struct bio *bio = *bio_ptr;
+ struct bio_crypt_ctx *bc = bio->bi_crypt_context;
+ struct bio_fallback_crypt_ctx *f_ctx;
+
+ if (bc->bc_key->is_hw_wrapped) {
+ pr_warn_once("HW wrapped key cannot be used with fallback.\n");
+ bio->bi_status = BLK_STS_NOTSUPP;
+ return -EOPNOTSUPP;
+ }
+
+ if (!tfms_inited[bc->bc_key->crypto_mode]) {
+ bio->bi_status = BLK_STS_IOERR;
+ return -EIO;
+ }
+
+ if (bio_data_dir(bio) == WRITE)
+ return blk_crypto_encrypt_bio(bio_ptr);
+
+ /*
+ * Mark bio as fallback crypted and replace the bio_crypt_ctx with
+ * another one contained in a bio_fallback_crypt_ctx, so that the
+ * fallback has space to store the info it needs for decryption.
+ */
+ bc->bc_ksm = blk_crypto_ksm;
+ f_ctx = mempool_alloc(bio_fallback_crypt_ctx_pool, GFP_NOIO);
+ f_ctx->crypt_ctx = *bc;
+ memcpy(f_ctx->fallback_dun, bc->bc_dun, sizeof(f_ctx->fallback_dun));
+ f_ctx->crypt_iter = bio->bi_iter;
+
+ bio_crypt_free_ctx(bio);
+ bio->bi_crypt_context = &f_ctx->crypt_ctx;
+
+ return 0;
+}
+
+int __init blk_crypto_fallback_init(void)
+{
+ int i;
+ unsigned int crypto_mode_supported[BLK_ENCRYPTION_MODE_MAX];
+
+ prandom_bytes(blank_key, BLK_CRYPTO_MAX_KEY_SIZE);
+
+ /* All blk-crypto modes have a crypto API fallback. */
+ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++)
+ crypto_mode_supported[i] = 0xFFFFFFFF;
+ crypto_mode_supported[BLK_ENCRYPTION_MODE_INVALID] = 0;
+
+ blk_crypto_ksm = keyslot_manager_create(
+ NULL, blk_crypto_num_keyslots,
+ &blk_crypto_ksm_ll_ops,
+ BLK_CRYPTO_FEATURE_STANDARD_KEYS,
+ crypto_mode_supported, NULL);
+ if (!blk_crypto_ksm)
+ return -ENOMEM;
+
+ blk_crypto_wq = alloc_workqueue("blk_crypto_wq",
+ WQ_UNBOUND | WQ_HIGHPRI |
+ WQ_MEM_RECLAIM, num_online_cpus());
+ if (!blk_crypto_wq)
+ return -ENOMEM;
+
+ blk_crypto_keyslots = kcalloc(blk_crypto_num_keyslots,
+ sizeof(blk_crypto_keyslots[0]),
+ GFP_KERNEL);
+ if (!blk_crypto_keyslots)
+ return -ENOMEM;
+
+ blk_crypto_bounce_page_pool =
+ mempool_create_page_pool(num_prealloc_bounce_pg, 0);
+ if (!blk_crypto_bounce_page_pool)
+ return -ENOMEM;
+
+ blk_crypto_decrypt_work_cache = KMEM_CACHE(blk_crypto_decrypt_work,
+ SLAB_RECLAIM_ACCOUNT);
+ if (!blk_crypto_decrypt_work_cache)
+ return -ENOMEM;
+
+ bio_fallback_crypt_ctx_cache = KMEM_CACHE(bio_fallback_crypt_ctx, 0);
+ if (!bio_fallback_crypt_ctx_cache)
+ return -ENOMEM;
+
+ bio_fallback_crypt_ctx_pool =
+ mempool_create_slab_pool(num_prealloc_fallback_crypt_ctxs,
+ bio_fallback_crypt_ctx_cache);
+ if (!bio_fallback_crypt_ctx_pool)
+ return -ENOMEM;
+
+ return 0;
+}
diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h
new file mode 100644
index 000000000000..4da998c803f2
--- /dev/null
+++ b/block/blk-crypto-internal.h
@@ -0,0 +1,67 @@
+/* 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>
+
+/* Represents a crypto mode supported by blk-crypto */
+struct blk_crypto_mode {
+ const char *cipher_str; /* crypto API name (for fallback case) */
+ unsigned int keysize; /* key size in bytes */
+ unsigned int ivsize; /* iv size in bytes */
+};
+
+extern const struct blk_crypto_mode blk_crypto_modes[];
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK
+
+int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num);
+
+int blk_crypto_fallback_submit_bio(struct bio **bio_ptr);
+
+bool blk_crypto_queue_decrypt_bio(struct bio *bio);
+
+int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key);
+
+bool bio_crypt_fallback_crypted(const struct bio_crypt_ctx *bc);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */
+
+static inline int
+blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num)
+{
+ pr_warn_once("crypto API fallback is disabled\n");
+ return -ENOPKG;
+}
+
+static inline bool bio_crypt_fallback_crypted(const struct bio_crypt_ctx *bc)
+{
+ return false;
+}
+
+static inline int blk_crypto_fallback_submit_bio(struct bio **bio_ptr)
+{
+ pr_warn_once("crypto API fallback disabled; failing request\n");
+ (*bio_ptr)->bi_status = BLK_STS_NOTSUPP;
+ return -EIO;
+}
+
+static inline bool blk_crypto_queue_decrypt_bio(struct bio *bio)
+{
+ WARN_ON(1);
+ return false;
+}
+
+static inline int
+blk_crypto_fallback_evict_key(const struct blk_crypto_key *key)
+{
+ return 0;
+}
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK */
+
+#endif /* __LINUX_BLK_CRYPTO_INTERNAL_H */
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
new file mode 100644
index 000000000000..e07a37cf8b5f
--- /dev/null
+++ b/block/blk-crypto.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * Refer to Documentation/block/inline-encryption.rst for detailed explanation.
+ */
+
+#define pr_fmt(fmt) "blk-crypto: " fmt
+
+#include <linux/blk-crypto.h>
+#include <linux/blkdev.h>
+#include <linux/keyslot-manager.h>
+#include <linux/random.h>
+#include <linux/siphash.h>
+
+#include "blk-crypto-internal.h"
+
+const struct blk_crypto_mode blk_crypto_modes[] = {
+ [BLK_ENCRYPTION_MODE_AES_256_XTS] = {
+ .cipher_str = "xts(aes)",
+ .keysize = 64,
+ .ivsize = 16,
+ },
+ [BLK_ENCRYPTION_MODE_AES_128_CBC_ESSIV] = {
+ .cipher_str = "essiv(cbc(aes),sha256)",
+ .keysize = 16,
+ .ivsize = 16,
+ },
+ [BLK_ENCRYPTION_MODE_ADIANTUM] = {
+ .cipher_str = "adiantum(xchacha12,aes)",
+ .keysize = 32,
+ .ivsize = 32,
+ },
+};
+
+/* Check that all I/O segments are data unit aligned */
+static int bio_crypt_check_alignment(struct bio *bio)
+{
+ const unsigned int data_unit_size =
+ bio->bi_crypt_context->bc_key->data_unit_size;
+ struct bvec_iter iter;
+ struct bio_vec bv;
+
+ bio_for_each_segment(bv, bio, iter) {
+ if (!IS_ALIGNED(bv.bv_len | bv.bv_offset, data_unit_size))
+ return -EIO;
+ }
+ return 0;
+}
+
+/**
+ * blk_crypto_submit_bio - handle submitting bio for inline encryption
+ *
+ * @bio_ptr: pointer to original bio pointer
+ *
+ * If the bio doesn't have inline encryption enabled or the submitter already
+ * specified a keyslot for the target device, do nothing. Else, a raw key must
+ * have been provided, so acquire a device keyslot for it if supported. Else,
+ * use the crypto API fallback.
+ *
+ * When the crypto API fallback is used for encryption, blk-crypto may choose to
+ * split the bio into 2 - the first one that will continue to be processed and
+ * the second one that will be resubmitted via generic_make_request.
+ * A bounce bio will be allocated to encrypt the contents of the aforementioned
+ * "first one", and *bio_ptr will be updated to this bounce bio.
+ *
+ * Return: 0 if bio submission should continue; nonzero if bio_endio() was
+ * already called so bio submission should abort.
+ */
+int blk_crypto_submit_bio(struct bio **bio_ptr)
+{
+ struct bio *bio = *bio_ptr;
+ struct request_queue *q;
+ struct bio_crypt_ctx *bc = bio->bi_crypt_context;
+ int err;
+
+ if (!bc || !bio_has_data(bio))
+ return 0;
+
+ /*
+ * When a read bio is marked for fallback decryption, its bi_iter is
+ * saved so that when we decrypt the bio later, we know what part of it
+ * was marked for fallback decryption (when the bio is passed down after
+ * blk_crypto_submit bio, it may be split or advanced so we cannot rely
+ * on the bi_iter while decrypting in blk_crypto_endio)
+ */
+ if (bio_crypt_fallback_crypted(bc))
+ return 0;
+
+ err = bio_crypt_check_alignment(bio);
+ if (err) {
+ bio->bi_status = BLK_STS_IOERR;
+ goto out;
+ }
+
+ q = bio->bi_disk->queue;
+
+ if (bc->bc_ksm) {
+ /* Key already programmed into device? */
+ if (q->ksm == bc->bc_ksm)
+ return 0;
+
+ /* Nope, release the existing keyslot. */
+ bio_crypt_ctx_release_keyslot(bc);
+ }
+
+ /* Get device keyslot if supported */
+ if (keyslot_manager_crypto_mode_supported(q->ksm,
+ bc->bc_key->crypto_mode,
+ blk_crypto_key_dun_bytes(bc->bc_key),
+ bc->bc_key->data_unit_size,
+ bc->bc_key->is_hw_wrapped)) {
+ err = bio_crypt_ctx_acquire_keyslot(bc, q->ksm);
+ if (!err)
+ return 0;
+
+ pr_warn_once("Failed to acquire keyslot for %s (err=%d). Falling back to crypto API.\n",
+ bio->bi_disk->disk_name, err);
+ }
+
+ /* Fallback to crypto API */
+ err = blk_crypto_fallback_submit_bio(bio_ptr);
+ if (err)
+ goto out;
+
+ return 0;
+out:
+ bio_endio(*bio_ptr);
+ return err;
+}
+
+/**
+ * blk_crypto_endio - clean up bio w.r.t inline encryption during bio_endio
+ *
+ * @bio: the bio to clean up
+ *
+ * If blk_crypto_submit_bio decided to fallback to crypto API for this bio,
+ * we queue the bio for decryption into a workqueue and return false,
+ * and call bio_endio(bio) at a later time (after the bio has been decrypted).
+ *
+ * If the bio is not to be decrypted by the crypto API, this function releases
+ * the reference to the keyslot that blk_crypto_submit_bio got.
+ *
+ * Return: true if bio_endio should continue; false otherwise (bio_endio will
+ * be called again when bio has been decrypted).
+ */
+bool blk_crypto_endio(struct bio *bio)
+{
+ struct bio_crypt_ctx *bc = bio->bi_crypt_context;
+
+ if (!bc)
+ return true;
+
+ if (bio_crypt_fallback_crypted(bc)) {
+ /*
+ * The only bios who's crypto is handled by the blk-crypto
+ * fallback when they reach here are those with
+ * bio_data_dir(bio) == READ, since WRITE bios that are
+ * encrypted by the crypto API fallback are handled by
+ * blk_crypto_encrypt_endio().
+ */
+ return !blk_crypto_queue_decrypt_bio(bio);
+ }
+
+ if (bc->bc_keyslot >= 0)
+ bio_crypt_ctx_release_keyslot(bc);
+
+ return true;
+}
+
+/**
+ * blk_crypto_init_key() - Prepare a key for use with blk-crypto
+ * @blk_key: Pointer to the blk_crypto_key to initialize.
+ * @raw_key: Pointer to the raw key.
+ * @raw_key_size: Size of raw key. Must be at least the required size for the
+ * chosen @crypto_mode; see blk_crypto_modes[]. (It's allowed
+ * to be longer than the mode's actual key size, in order to
+ * support inline encryption hardware that accepts wrapped keys.
+ * @is_hw_wrapped has to be set for such keys)
+ * @is_hw_wrapped: Denotes @raw_key is wrapped.
+ * @crypto_mode: identifier for the encryption algorithm to use
+ * @dun_bytes: number of bytes that will be used to specify the DUN when this
+ * key is used
+ * @data_unit_size: the data unit size to use for en/decryption
+ *
+ * Return: The blk_crypto_key that was prepared, or an ERR_PTR() on error. When
+ * done using the key, it must be freed with blk_crypto_free_key().
+ */
+int blk_crypto_init_key(struct blk_crypto_key *blk_key,
+ const u8 *raw_key, unsigned int raw_key_size,
+ bool is_hw_wrapped,
+ enum blk_crypto_mode_num crypto_mode,
+ unsigned int dun_bytes,
+ unsigned int data_unit_size)
+{
+ const struct blk_crypto_mode *mode;
+ static siphash_key_t hash_key;
+ u32 hash;
+
+ memset(blk_key, 0, sizeof(*blk_key));
+
+ if (crypto_mode >= ARRAY_SIZE(blk_crypto_modes))
+ return -EINVAL;
+
+ BUILD_BUG_ON(BLK_CRYPTO_MAX_WRAPPED_KEY_SIZE < BLK_CRYPTO_MAX_KEY_SIZE);
+
+ mode = &blk_crypto_modes[crypto_mode];
+ if (is_hw_wrapped) {
+ if (raw_key_size < mode->keysize ||
+ raw_key_size > BLK_CRYPTO_MAX_WRAPPED_KEY_SIZE)
+ return -EINVAL;
+ } else {
+ if (raw_key_size != mode->keysize)
+ return -EINVAL;
+ }
+
+ if (dun_bytes <= 0 || dun_bytes > BLK_CRYPTO_MAX_IV_SIZE)
+ return -EINVAL;
+
+ if (!is_power_of_2(data_unit_size))
+ return -EINVAL;
+
+ blk_key->crypto_mode = crypto_mode;
+ blk_key->data_unit_size = data_unit_size;
+ blk_key->data_unit_size_bits = ilog2(data_unit_size);
+ blk_key->size = raw_key_size;
+ blk_key->is_hw_wrapped = is_hw_wrapped;
+ memcpy(blk_key->raw, raw_key, raw_key_size);
+
+ /*
+ * The keyslot manager uses the SipHash of the key to implement O(1) key
+ * lookups while avoiding leaking information about the keys. It's
+ * precomputed here so that it only needs to be computed once per key.
+ */
+ get_random_once(&hash_key, sizeof(hash_key));
+ hash = (u32)siphash(raw_key, raw_key_size, &hash_key);
+ blk_crypto_key_set_hash_and_dun_bytes(blk_key, hash, dun_bytes);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_init_key);
+
+/**
+ * blk_crypto_start_using_mode() - Start using blk-crypto on a device
+ * @crypto_mode: the crypto mode that will be used
+ * @dun_bytes: number of bytes that will be used to specify the DUN
+ * @data_unit_size: the data unit size that will be used
+ * @is_hw_wrapped_key: whether the key will be hardware-wrapped
+ * @q: the request queue for the device
+ *
+ * Upper layers must call this function to ensure that either the hardware
+ * supports the needed crypto settings, or the crypto API fallback has
+ * transforms for the needed mode allocated and ready to go.
+ *
+ * Return: 0 on success; -ENOPKG if the hardware doesn't support the crypto
+ * settings and blk-crypto-fallback is either disabled or the needed
+ * algorithm is disabled in the crypto API; or another -errno code.
+ */
+int blk_crypto_start_using_mode(enum blk_crypto_mode_num crypto_mode,
+ unsigned int dun_bytes,
+ unsigned int data_unit_size,
+ bool is_hw_wrapped_key,
+ struct request_queue *q)
+{
+ if (keyslot_manager_crypto_mode_supported(q->ksm, crypto_mode,
+ dun_bytes, data_unit_size,
+ is_hw_wrapped_key))
+ return 0;
+ if (is_hw_wrapped_key) {
+ pr_warn_once("hardware doesn't support wrapped keys\n");
+ return -EOPNOTSUPP;
+ }
+ return blk_crypto_fallback_start_using_mode(crypto_mode);
+}
+EXPORT_SYMBOL_GPL(blk_crypto_start_using_mode);
+
+/**
+ * blk_crypto_evict_key() - Evict a key from any inline encryption hardware
+ * it may have been programmed into
+ * @q: The request queue who's keyslot manager this key might have been
+ * programmed into
+ * @key: The key to evict
+ *
+ * Upper layers (filesystems) should call this function to ensure that a key
+ * is evicted from hardware that it might have been programmed into. This
+ * will call keyslot_manager_evict_key on the queue's keyslot manager, if one
+ * exists, and supports the crypto algorithm with the specified data unit size.
+ * Otherwise, it will evict the key from the blk-crypto-fallback's ksm.
+ *
+ * Return: 0 on success, -err on error.
+ */
+int blk_crypto_evict_key(struct request_queue *q,
+ const struct blk_crypto_key *key)
+{
+ if (q->ksm &&
+ keyslot_manager_crypto_mode_supported(q->ksm, key->crypto_mode,
+ blk_crypto_key_dun_bytes(key),
+ key->data_unit_size,
+ key->is_hw_wrapped))
+ return keyslot_manager_evict_key(q->ksm, key);
+
+ return blk_crypto_fallback_evict_key(key);
+}
+EXPORT_SYMBOL_GPL(blk_crypto_evict_key);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 415b5dafd9e6..71768dc75602 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -504,6 +504,8 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
req_set_nomerge(q, req);
return 0;
}
+ if (!bio_crypt_ctx_mergeable(req->bio, blk_rq_bytes(req), bio))
+ return 0;
if (!bio_flagged(req->biotail, BIO_SEG_VALID))
blk_recount_segments(q, req->biotail);
if (!bio_flagged(bio, BIO_SEG_VALID))
@@ -526,6 +528,8 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
req_set_nomerge(q, req);
return 0;
}
+ if (!bio_crypt_ctx_mergeable(bio, bio->bi_iter.bi_size, req->bio))
+ return 0;
if (!bio_flagged(bio, BIO_SEG_VALID))
blk_recount_segments(q, bio);
if (!bio_flagged(req->bio, BIO_SEG_VALID))
@@ -602,6 +606,9 @@ 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_mergeable(req->bio, blk_rq_bytes(req), next->bio))
+ return 0;
+
/* Merge is OK... */
req->nr_phys_segments = total_phys_segments;
return 1;
@@ -850,6 +857,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
if (rq->write_hint != bio->bi_write_hint)
return false;
+ /* Only merge if the crypt contexts are compatible */
+ if (!bio_crypt_ctx_compatible(bio, rq->bio))
+ return false;
+
return true;
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 9c4f1c496c90..8df0fecac3a8 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -225,6 +225,7 @@ struct cfq_group_data {
unsigned int weight;
unsigned int leaf_weight;
+ u64 group_idle;
};
/* This is per cgroup per device grouping structure */
@@ -310,6 +311,7 @@ struct cfq_group {
struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
struct cfq_queue *async_idle_cfqq;
+ u64 group_idle;
};
struct cfq_io_cq {
@@ -802,6 +804,17 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
+static inline u64 get_group_idle(struct cfq_data *cfqd)
+{
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ struct cfq_queue *cfqq = cfqd->active_queue;
+
+ if (cfqq && cfqq->cfqg)
+ return cfqq->cfqg->group_idle;
+#endif
+ return cfqd->cfq_group_idle;
+}
+
#define cfq_log(cfqd, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -822,7 +835,7 @@ static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
if (!sample_valid(ttime->ttime_samples))
return false;
if (group_idle)
- slice = cfqd->cfq_group_idle;
+ slice = get_group_idle(cfqd);
else
slice = cfqd->cfq_slice_idle;
return ttime->ttime_mean > slice;
@@ -1589,6 +1602,7 @@ static void cfq_cpd_init(struct blkcg_policy_data *cpd)
cgd->weight = weight;
cgd->leaf_weight = weight;
+ cgd->group_idle = cfq_group_idle;
}
static void cfq_cpd_free(struct blkcg_policy_data *cpd)
@@ -1633,6 +1647,7 @@ static void cfq_pd_init(struct blkg_policy_data *pd)
cfqg->weight = cgd->weight;
cfqg->leaf_weight = cgd->leaf_weight;
+ cfqg->group_idle = cgd->group_idle;
}
static void cfq_pd_offline(struct blkg_policy_data *pd)
@@ -1754,6 +1769,19 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
return 0;
}
+static int cfq_print_group_idle(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+ u64 val = 0;
+
+ if (cgd)
+ val = cgd->group_idle;
+
+ seq_printf(sf, "%llu\n", div_u64(val, NSEC_PER_USEC));
+ return 0;
+}
+
static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off,
bool on_dfl, bool is_leaf_weight)
@@ -1875,6 +1903,37 @@ static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
return __cfq_set_weight(css, val, false, false, true);
}
+static int cfq_set_group_idle(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
+{
+ struct blkcg *blkcg = css_to_blkcg(css);
+ struct cfq_group_data *cfqgd;
+ struct blkcg_gq *blkg;
+ int ret = 0;
+
+ spin_lock_irq(&blkcg->lock);
+ cfqgd = blkcg_to_cfqgd(blkcg);
+ if (!cfqgd) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ cfqgd->group_idle = val * NSEC_PER_USEC;
+
+ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+ struct cfq_group *cfqg = blkg_to_cfqg(blkg);
+
+ if (!cfqg)
+ continue;
+
+ cfqg->group_idle = cfqgd->group_idle;
+ }
+
+out:
+ spin_unlock_irq(&blkcg->lock);
+ return ret;
+}
+
static int cfqg_print_stat(struct seq_file *sf, void *v)
{
blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
@@ -2020,6 +2079,11 @@ static struct cftype cfq_blkcg_legacy_files[] = {
.seq_show = cfq_print_leaf_weight,
.write_u64 = cfq_set_leaf_weight,
},
+ {
+ .name = "group_idle",
+ .seq_show = cfq_print_group_idle,
+ .write_u64 = cfq_set_group_idle,
+ },
/* statistics, covers only the tasks in the cfqg */
{
@@ -2914,7 +2978,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
* with sync vs async workloads.
*/
if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag &&
- !cfqd->cfq_group_idle)
+ !get_group_idle(cfqd))
return;
WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
@@ -2925,9 +2989,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
*/
if (!cfq_should_idle(cfqd, cfqq)) {
/* no queue idling. Check for group idling */
- if (cfqd->cfq_group_idle)
- group_idle = cfqd->cfq_group_idle;
- else
+ group_idle = get_group_idle(cfqd);
+ if (!group_idle)
return;
}
@@ -2968,7 +3031,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
cfq_mark_cfqq_wait_request(cfqq);
if (group_idle)
- sl = cfqd->cfq_group_idle;
+ sl = group_idle;
else
sl = cfqd->cfq_slice_idle;
@@ -3317,7 +3380,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
* this group, wait for requests to complete.
*/
check_group_idle:
- if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 &&
+ if (get_group_idle(cfqd) && cfqq->cfqg->nr_cfqq == 1 &&
cfqq->cfqg->dispatched &&
!cfq_io_thinktime_big(cfqd, &cfqq->cfqg->ttime, true)) {
cfqq = NULL;
@@ -3880,7 +3943,7 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
cfqd->cfq_slice_idle);
}
#ifdef CONFIG_CFQ_GROUP_IOSCHED
- __cfq_update_io_thinktime(&cfqq->cfqg->ttime, cfqd->cfq_group_idle);
+ __cfq_update_io_thinktime(&cfqq->cfqg->ttime, get_group_idle(cfqd));
#endif
}
@@ -4278,7 +4341,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
if (cfq_should_wait_busy(cfqd, cfqq)) {
u64 extend_sl = cfqd->cfq_slice_idle;
if (!cfqd->cfq_slice_idle)
- extend_sl = cfqd->cfq_group_idle;
+ extend_sl = get_group_idle(cfqd);
cfqq->slice_end = now + extend_sl;
cfq_mark_cfqq_wait_busy(cfqq);
cfq_log_cfqq(cfqd, cfqq, "will busy wait");
diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c
new file mode 100644
index 000000000000..901545c5854c
--- /dev/null
+++ b/block/keyslot-manager.c
@@ -0,0 +1,664 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+/**
+ * DOC: The Keyslot Manager
+ *
+ * Many devices with inline encryption support have a limited number of "slots"
+ * into which encryption contexts may be programmed, and requests can be tagged
+ * with a slot number to specify the key to use for en/decryption.
+ *
+ * As the number of slots are limited, and programming keys is expensive on
+ * many inline encryption hardware, we don't want to program the same key into
+ * multiple slots - if multiple requests are using the same key, we want to
+ * program just one slot with that key and use that slot for all requests.
+ *
+ * The keyslot manager manages these keyslots appropriately, and also acts as
+ * an abstraction between the inline encryption hardware and the upper layers.
+ *
+ * Lower layer devices will set up a keyslot manager in their request queue
+ * and tell it how to perform device specific operations like programming/
+ * evicting keys from keyslots.
+ *
+ * Upper layers will call keyslot_manager_get_slot_for_key() to program a
+ * key into some slot in the inline encryption hardware.
+ */
+#include <crypto/algapi.h>
+#include <linux/keyslot-manager.h>
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/pm_runtime.h>
+#include <linux/wait.h>
+#include <linux/blkdev.h>
+#include <linux/overflow.h>
+
+struct keyslot {
+ atomic_t slot_refs;
+ struct list_head idle_slot_node;
+ struct hlist_node hash_node;
+ struct blk_crypto_key key;
+};
+
+struct keyslot_manager {
+ unsigned int num_slots;
+ struct keyslot_mgmt_ll_ops ksm_ll_ops;
+ unsigned int features;
+ unsigned int crypto_mode_supported[BLK_ENCRYPTION_MODE_MAX];
+ unsigned int max_dun_bytes_supported;
+ void *ll_priv_data;
+
+#ifdef CONFIG_PM
+ /* Device for runtime power management (NULL if none) */
+ struct device *dev;
+#endif
+
+ /* Protects programming and evicting keys from the device */
+ struct rw_semaphore lock;
+
+ /* List of idle slots, with least recently used slot at front */
+ wait_queue_head_t idle_slots_wait_queue;
+ struct list_head idle_slots;
+ spinlock_t idle_slots_lock;
+
+ /*
+ * Hash table which maps key hashes to keyslots, so that we can find a
+ * key's keyslot in O(1) time rather than O(num_slots). Protected by
+ * 'lock'. A cryptographic hash function is used so that timing attacks
+ * can't leak information about the raw keys.
+ */
+ struct hlist_head *slot_hashtable;
+ unsigned int slot_hashtable_size;
+
+ /* Per-keyslot data */
+ struct keyslot slots[];
+};
+
+static inline bool keyslot_manager_is_passthrough(struct keyslot_manager *ksm)
+{
+ return ksm->num_slots == 0;
+}
+
+#ifdef CONFIG_PM
+static inline void keyslot_manager_set_dev(struct keyslot_manager *ksm,
+ struct device *dev)
+{
+ ksm->dev = dev;
+}
+
+/* If there's an underlying device and it's suspended, resume it. */
+static inline void keyslot_manager_pm_get(struct keyslot_manager *ksm)
+{
+ if (ksm->dev)
+ pm_runtime_get_sync(ksm->dev);
+}
+
+static inline void keyslot_manager_pm_put(struct keyslot_manager *ksm)
+{
+ if (ksm->dev)
+ pm_runtime_put_sync(ksm->dev);
+}
+#else /* CONFIG_PM */
+static inline void keyslot_manager_set_dev(struct keyslot_manager *ksm,
+ struct device *dev)
+{
+}
+
+static inline void keyslot_manager_pm_get(struct keyslot_manager *ksm)
+{
+}
+
+static inline void keyslot_manager_pm_put(struct keyslot_manager *ksm)
+{
+}
+#endif /* !CONFIG_PM */
+
+static inline void keyslot_manager_hw_enter(struct keyslot_manager *ksm)
+{
+ /*
+ * Calling into the driver requires ksm->lock held and the device
+ * resumed. But we must resume the device first, since that can acquire
+ * and release ksm->lock via keyslot_manager_reprogram_all_keys().
+ */
+ keyslot_manager_pm_get(ksm);
+ down_write(&ksm->lock);
+}
+
+static inline void keyslot_manager_hw_exit(struct keyslot_manager *ksm)
+{
+ up_write(&ksm->lock);
+ keyslot_manager_pm_put(ksm);
+}
+
+/**
+ * keyslot_manager_create() - Create a keyslot manager
+ * @dev: Device for runtime power management (NULL if none)
+ * @num_slots: The number of key slots to manage.
+ * @ksm_ll_ops: The struct keyslot_mgmt_ll_ops for the device that this keyslot
+ * manager will use to perform operations like programming and
+ * evicting keys.
+ * @features: The supported features as a bitmask of BLK_CRYPTO_FEATURE_* flags.
+ * Most drivers should set BLK_CRYPTO_FEATURE_STANDARD_KEYS here.
+ * @crypto_mode_supported: Array of size BLK_ENCRYPTION_MODE_MAX of
+ * bitmasks that represents whether a crypto mode
+ * and data unit size are supported. The i'th bit
+ * of crypto_mode_supported[crypto_mode] is set iff
+ * a data unit size of (1 << i) is supported. We
+ * only support data unit sizes that are powers of
+ * 2.
+ * @ll_priv_data: Private data passed as is to the functions in ksm_ll_ops.
+ *
+ * Allocate memory for and initialize a keyslot manager. Called by e.g.
+ * storage drivers to set up a keyslot manager in their request_queue.
+ *
+ * Context: May sleep
+ * Return: Pointer to constructed keyslot manager or NULL on error.
+ */
+struct keyslot_manager *keyslot_manager_create(
+ struct device *dev,
+ unsigned int num_slots,
+ const struct keyslot_mgmt_ll_ops *ksm_ll_ops,
+ unsigned int features,
+ const unsigned int crypto_mode_supported[BLK_ENCRYPTION_MODE_MAX],
+ void *ll_priv_data)
+{
+ struct keyslot_manager *ksm;
+ unsigned int slot;
+ unsigned int i;
+
+ if (num_slots == 0)
+ return NULL;
+
+ /* Check that all ops are specified */
+ if (ksm_ll_ops->keyslot_program == NULL ||
+ ksm_ll_ops->keyslot_evict == NULL)
+ return NULL;
+
+ ksm = kvzalloc(struct_size(ksm, slots, num_slots), GFP_KERNEL);
+ if (!ksm)
+ return NULL;
+
+ ksm->num_slots = num_slots;
+ ksm->ksm_ll_ops = *ksm_ll_ops;
+ ksm->features = features;
+ memcpy(ksm->crypto_mode_supported, crypto_mode_supported,
+ sizeof(ksm->crypto_mode_supported));
+ ksm->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
+ ksm->ll_priv_data = ll_priv_data;
+ keyslot_manager_set_dev(ksm, dev);
+
+ init_rwsem(&ksm->lock);
+
+ init_waitqueue_head(&ksm->idle_slots_wait_queue);
+ INIT_LIST_HEAD(&ksm->idle_slots);
+
+ for (slot = 0; slot < num_slots; slot++) {
+ list_add_tail(&ksm->slots[slot].idle_slot_node,
+ &ksm->idle_slots);
+ }
+
+ spin_lock_init(&ksm->idle_slots_lock);
+
+ ksm->slot_hashtable_size = roundup_pow_of_two(num_slots);
+ ksm->slot_hashtable = kvmalloc_array(ksm->slot_hashtable_size,
+ sizeof(ksm->slot_hashtable[0]),
+ GFP_KERNEL);
+ if (!ksm->slot_hashtable)
+ goto err_free_ksm;
+ for (i = 0; i < ksm->slot_hashtable_size; i++)
+ INIT_HLIST_HEAD(&ksm->slot_hashtable[i]);
+
+ return ksm;
+
+err_free_ksm:
+ keyslot_manager_destroy(ksm);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_create);
+
+void keyslot_manager_set_max_dun_bytes(struct keyslot_manager *ksm,
+ unsigned int max_dun_bytes)
+{
+ ksm->max_dun_bytes_supported = max_dun_bytes;
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_set_max_dun_bytes);
+
+static inline struct hlist_head *
+hash_bucket_for_key(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key)
+{
+ return &ksm->slot_hashtable[blk_crypto_key_hash(key) &
+ (ksm->slot_hashtable_size - 1)];
+}
+
+static void remove_slot_from_lru_list(struct keyslot_manager *ksm, int slot)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ksm->idle_slots_lock, flags);
+ list_del(&ksm->slots[slot].idle_slot_node);
+ spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
+}
+
+static int find_keyslot(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key)
+{
+ const struct hlist_head *head = hash_bucket_for_key(ksm, key);
+ const struct keyslot *slotp;
+
+ hlist_for_each_entry(slotp, head, hash_node) {
+ if (slotp->key.hash == key->hash &&
+ slotp->key.crypto_mode == key->crypto_mode &&
+ slotp->key.size == key->size &&
+ slotp->key.data_unit_size == key->data_unit_size &&
+ !crypto_memneq(slotp->key.raw, key->raw, key->size))
+ return slotp - ksm->slots;
+ }
+ return -ENOKEY;
+}
+
+static int find_and_grab_keyslot(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key)
+{
+ int slot;
+
+ slot = find_keyslot(ksm, key);
+ if (slot < 0)
+ return slot;
+ if (atomic_inc_return(&ksm->slots[slot].slot_refs) == 1) {
+ /* Took first reference to this slot; remove it from LRU list */
+ remove_slot_from_lru_list(ksm, slot);
+ }
+ return slot;
+}
+
+/**
+ * keyslot_manager_get_slot_for_key() - Program a key into a keyslot.
+ * @ksm: The keyslot manager to program the key into.
+ * @key: Pointer to the key object to program, including the raw key, crypto
+ * mode, and data unit size.
+ *
+ * Get a keyslot that's been programmed with the specified key. If one already
+ * exists, return it with incremented refcount. Otherwise, wait for a keyslot
+ * to become idle and program it.
+ *
+ * Context: Process context. Takes and releases ksm->lock.
+ * Return: The keyslot on success, else a -errno value.
+ */
+int keyslot_manager_get_slot_for_key(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key)
+{
+ int slot;
+ int err;
+ struct keyslot *idle_slot;
+
+ if (keyslot_manager_is_passthrough(ksm))
+ return 0;
+
+ down_read(&ksm->lock);
+ slot = find_and_grab_keyslot(ksm, key);
+ up_read(&ksm->lock);
+ if (slot != -ENOKEY)
+ return slot;
+
+ for (;;) {
+ keyslot_manager_hw_enter(ksm);
+ slot = find_and_grab_keyslot(ksm, key);
+ if (slot != -ENOKEY) {
+ keyslot_manager_hw_exit(ksm);
+ return slot;
+ }
+
+ /*
+ * If we're here, that means there wasn't a slot that was
+ * already programmed with the key. So try to program it.
+ */
+ if (!list_empty(&ksm->idle_slots))
+ break;
+
+ keyslot_manager_hw_exit(ksm);
+ wait_event(ksm->idle_slots_wait_queue,
+ !list_empty(&ksm->idle_slots));
+ }
+
+ idle_slot = list_first_entry(&ksm->idle_slots, struct keyslot,
+ idle_slot_node);
+ slot = idle_slot - ksm->slots;
+
+ err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot);
+ if (err) {
+ wake_up(&ksm->idle_slots_wait_queue);
+ keyslot_manager_hw_exit(ksm);
+ return err;
+ }
+
+ /* Move this slot to the hash list for the new key. */
+ if (idle_slot->key.crypto_mode != BLK_ENCRYPTION_MODE_INVALID)
+ hlist_del(&idle_slot->hash_node);
+ hlist_add_head(&idle_slot->hash_node, hash_bucket_for_key(ksm, key));
+
+ atomic_set(&idle_slot->slot_refs, 1);
+ idle_slot->key = *key;
+
+ remove_slot_from_lru_list(ksm, slot);
+
+ keyslot_manager_hw_exit(ksm);
+ return slot;
+}
+
+/**
+ * keyslot_manager_get_slot() - Increment the refcount on the specified slot.
+ * @ksm: The keyslot manager that we want to modify.
+ * @slot: The slot to increment the refcount of.
+ *
+ * This function assumes that there is already an active reference to that slot
+ * and simply increments the refcount. This is useful when cloning a bio that
+ * already has a reference to a keyslot, and we want the cloned bio to also have
+ * its own reference.
+ *
+ * Context: Any context.
+ */
+void keyslot_manager_get_slot(struct keyslot_manager *ksm, unsigned int slot)
+{
+ if (keyslot_manager_is_passthrough(ksm))
+ return;
+
+ if (WARN_ON(slot >= ksm->num_slots))
+ return;
+
+ WARN_ON(atomic_inc_return(&ksm->slots[slot].slot_refs) < 2);
+}
+
+/**
+ * keyslot_manager_put_slot() - Release a reference to a slot
+ * @ksm: The keyslot manager to release the reference from.
+ * @slot: The slot to release the reference from.
+ *
+ * Context: Any context.
+ */
+void keyslot_manager_put_slot(struct keyslot_manager *ksm, unsigned int slot)
+{
+ unsigned long flags;
+
+ if (keyslot_manager_is_passthrough(ksm))
+ return;
+
+ if (WARN_ON(slot >= ksm->num_slots))
+ return;
+
+ if (atomic_dec_and_lock_irqsave(&ksm->slots[slot].slot_refs,
+ &ksm->idle_slots_lock, flags)) {
+ list_add_tail(&ksm->slots[slot].idle_slot_node,
+ &ksm->idle_slots);
+ spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
+ wake_up(&ksm->idle_slots_wait_queue);
+ }
+}
+
+/**
+ * keyslot_manager_crypto_mode_supported() - Find out if a crypto_mode /
+ * data unit size / is_hw_wrapped_key
+ * combination is supported by a ksm.
+ * @ksm: The keyslot manager to check
+ * @crypto_mode: The crypto mode to check for.
+ * @dun_bytes: The number of bytes that will be used to specify the DUN
+ * @data_unit_size: The data_unit_size for the mode.
+ * @is_hw_wrapped_key: Whether a hardware-wrapped key will be used.
+ *
+ * Calls and returns the result of the crypto_mode_supported function specified
+ * by the ksm.
+ *
+ * Context: Process context.
+ * Return: Whether or not this ksm supports the specified crypto settings.
+ */
+bool keyslot_manager_crypto_mode_supported(struct keyslot_manager *ksm,
+ enum blk_crypto_mode_num crypto_mode,
+ unsigned int dun_bytes,
+ unsigned int data_unit_size,
+ bool is_hw_wrapped_key)
+{
+ if (!ksm)
+ return false;
+ if (WARN_ON(crypto_mode >= BLK_ENCRYPTION_MODE_MAX))
+ return false;
+ if (WARN_ON(!is_power_of_2(data_unit_size)))
+ return false;
+ if (is_hw_wrapped_key) {
+ if (!(ksm->features & BLK_CRYPTO_FEATURE_WRAPPED_KEYS))
+ return false;
+ } else {
+ if (!(ksm->features & BLK_CRYPTO_FEATURE_STANDARD_KEYS))
+ return false;
+ }
+ if (!(ksm->crypto_mode_supported[crypto_mode] & data_unit_size))
+ return false;
+
+ return ksm->max_dun_bytes_supported >= dun_bytes;
+}
+
+/**
+ * keyslot_manager_evict_key() - Evict a key from the lower layer device.
+ * @ksm: The keyslot manager to evict from
+ * @key: The key to evict
+ *
+ * Find the keyslot that the specified key was programmed into, and evict that
+ * slot from the lower layer device if that slot is not currently in use.
+ *
+ * Context: Process context. Takes and releases ksm->lock.
+ * Return: 0 on success, -EBUSY if the key is still in use, or another
+ * -errno value on other error.
+ */
+int keyslot_manager_evict_key(struct keyslot_manager *ksm,
+ const struct blk_crypto_key *key)
+{
+ int slot;
+ int err;
+ struct keyslot *slotp;
+
+ if (keyslot_manager_is_passthrough(ksm)) {
+ if (ksm->ksm_ll_ops.keyslot_evict) {
+ keyslot_manager_hw_enter(ksm);
+ err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1);
+ keyslot_manager_hw_exit(ksm);
+ return err;
+ }
+ return 0;
+ }
+
+ keyslot_manager_hw_enter(ksm);
+
+ slot = find_keyslot(ksm, key);
+ if (slot < 0) {
+ err = slot;
+ goto out_unlock;
+ }
+ slotp = &ksm->slots[slot];
+
+ if (atomic_read(&slotp->slot_refs) != 0) {
+ err = -EBUSY;
+ goto out_unlock;
+ }
+ err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, slot);
+ if (err)
+ goto out_unlock;
+
+ hlist_del(&slotp->hash_node);
+ memzero_explicit(&slotp->key, sizeof(slotp->key));
+ err = 0;
+out_unlock:
+ keyslot_manager_hw_exit(ksm);
+ return err;
+}
+
+/**
+ * keyslot_manager_reprogram_all_keys() - Re-program all keyslots.
+ * @ksm: The keyslot manager
+ *
+ * Re-program all keyslots that are supposed to have a key programmed. This is
+ * intended only for use by drivers for hardware that loses its keys on reset.
+ *
+ * Context: Process context. Takes and releases ksm->lock.
+ */
+void keyslot_manager_reprogram_all_keys(struct keyslot_manager *ksm)
+{
+ unsigned int slot;
+
+ if (WARN_ON(keyslot_manager_is_passthrough(ksm)))
+ return;
+
+ /* This is for device initialization, so don't resume the device */
+ down_write(&ksm->lock);
+ for (slot = 0; slot < ksm->num_slots; slot++) {
+ const struct keyslot *slotp = &ksm->slots[slot];
+ int err;
+
+ if (slotp->key.crypto_mode == BLK_ENCRYPTION_MODE_INVALID)
+ continue;
+
+ err = ksm->ksm_ll_ops.keyslot_program(ksm, &slotp->key, slot);
+ WARN_ON(err);
+ }
+ up_write(&ksm->lock);
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_reprogram_all_keys);
+
+/**
+ * keyslot_manager_private() - return the private data stored with ksm
+ * @ksm: The keyslot manager
+ *
+ * Returns the private data passed to the ksm when it was created.
+ */
+void *keyslot_manager_private(struct keyslot_manager *ksm)
+{
+ return ksm->ll_priv_data;
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_private);
+
+void keyslot_manager_destroy(struct keyslot_manager *ksm)
+{
+ if (ksm) {
+ kvfree(ksm->slot_hashtable);
+ memzero_explicit(ksm, struct_size(ksm, slots, ksm->num_slots));
+ kvfree(ksm);
+ }
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_destroy);
+
+/**
+ * keyslot_manager_create_passthrough() - Create a passthrough keyslot manager
+ * @dev: Device for runtime power management (NULL if none)
+ * @ksm_ll_ops: The struct keyslot_mgmt_ll_ops
+ * @features: Bitmask of BLK_CRYPTO_FEATURE_* flags
+ * @crypto_mode_supported: Bitmasks for supported encryption modes
+ * @ll_priv_data: Private data passed as is to the functions in ksm_ll_ops.
+ *
+ * Allocate memory for and initialize a passthrough keyslot manager.
+ * Called by e.g. storage drivers to set up a keyslot manager in their
+ * request_queue, when the storage driver wants to manage its keys by itself.
+ * This is useful for inline encryption hardware that don't have a small fixed
+ * number of keyslots, and for layered devices.
+ *
+ * See keyslot_manager_create() for more details about the parameters.
+ *
+ * Context: This function may sleep
+ * Return: Pointer to constructed keyslot manager or NULL on error.
+ */
+struct keyslot_manager *keyslot_manager_create_passthrough(
+ struct device *dev,
+ const struct keyslot_mgmt_ll_ops *ksm_ll_ops,
+ unsigned int features,
+ const unsigned int crypto_mode_supported[BLK_ENCRYPTION_MODE_MAX],
+ void *ll_priv_data)
+{
+ struct keyslot_manager *ksm;
+
+ ksm = kzalloc(sizeof(*ksm), GFP_KERNEL);
+ if (!ksm)
+ return NULL;
+
+ ksm->ksm_ll_ops = *ksm_ll_ops;
+ ksm->features = features;
+ memcpy(ksm->crypto_mode_supported, crypto_mode_supported,
+ sizeof(ksm->crypto_mode_supported));
+ ksm->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
+ ksm->ll_priv_data = ll_priv_data;
+ keyslot_manager_set_dev(ksm, dev);
+
+ init_rwsem(&ksm->lock);
+
+ return ksm;
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_create_passthrough);
+
+/**
+ * keyslot_manager_intersect_modes() - restrict supported modes by child device
+ * @parent: The keyslot manager for parent device
+ * @child: The keyslot manager for child device, or NULL
+ *
+ * Clear any crypto mode support bits in @parent that aren't set in @child.
+ * If @child is NULL, then all parent bits are cleared.
+ *
+ * Only use this when setting up the keyslot manager for a layered device,
+ * before it's been exposed yet.
+ */
+void keyslot_manager_intersect_modes(struct keyslot_manager *parent,
+ const struct keyslot_manager *child)
+{
+ if (child) {
+ unsigned int i;
+
+ parent->features &= child->features;
+ parent->max_dun_bytes_supported =
+ min(parent->max_dun_bytes_supported,
+ child->max_dun_bytes_supported);
+ for (i = 0; i < ARRAY_SIZE(child->crypto_mode_supported); i++) {
+ parent->crypto_mode_supported[i] &=
+ child->crypto_mode_supported[i];
+ }
+ } else {
+ parent->features = 0;
+ parent->max_dun_bytes_supported = 0;
+ memset(parent->crypto_mode_supported, 0,
+ sizeof(parent->crypto_mode_supported));
+ }
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_intersect_modes);
+
+/**
+ * keyslot_manager_derive_raw_secret() - Derive software secret from wrapped key
+ * @ksm: The keyslot manager
+ * @wrapped_key: The wrapped key
+ * @wrapped_key_size: Size of the wrapped key in bytes
+ * @secret: (output) the software secret
+ * @secret_size: (output) the number of secret bytes to derive
+ *
+ * Given a hardware-wrapped key, ask the hardware to derive a secret which
+ * software can use for cryptographic tasks other than inline encryption. The
+ * derived secret is guaranteed to be cryptographically isolated from the key
+ * with which any inline encryption with this wrapped key would actually be
+ * done. I.e., both will be derived from the unwrapped key.
+ *
+ * Return: 0 on success, -EOPNOTSUPP if hardware-wrapped keys are unsupported,
+ * or another -errno code.
+ */
+int keyslot_manager_derive_raw_secret(struct keyslot_manager *ksm,
+ const u8 *wrapped_key,
+ unsigned int wrapped_key_size,
+ u8 *secret, unsigned int secret_size)
+{
+ int err;
+
+ if (ksm->ksm_ll_ops.derive_raw_secret) {
+ keyslot_manager_hw_enter(ksm);
+ err = ksm->ksm_ll_ops.derive_raw_secret(ksm, wrapped_key,
+ wrapped_key_size,
+ secret, secret_size);
+ keyslot_manager_hw_exit(ksm);
+ } else {
+ err = -EOPNOTSUPP;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(keyslot_manager_derive_raw_secret);