Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Add the ability to abort a skcipher walk.

  Algorithms:
   - Fix XTS to actually do the stealing.
   - Add library helpers for AES and DES for single-block users.
   - Add library helpers for SHA256.
   - Add new DES key verification helper.
   - Add surrounding bits for ESSIV generator.
   - Add accelerations for aegis128.
   - Add test vectors for lzo-rle.

  Drivers:
   - Add i.MX8MQ support to caam.
   - Add gcm/ccm/cfb/ofb aes support in inside-secure.
   - Add ofb/cfb aes support in media-tek.
   - Add HiSilicon ZIP accelerator support.

  Others:
   - Fix potential race condition in padata.
   - Use unbound workqueues in padata"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (311 commits)
  crypto: caam - Cast to long first before pointer conversion
  crypto: ccree - enable CTS support in AES-XTS
  crypto: inside-secure - Probe transform record cache RAM sizes
  crypto: inside-secure - Base RD fetchcount on actual RD FIFO size
  crypto: inside-secure - Base CD fetchcount on actual CD FIFO size
  crypto: inside-secure - Enable extended algorithms on newer HW
  crypto: inside-secure: Corrected configuration of EIP96_TOKEN_CTRL
  crypto: inside-secure - Add EIP97/EIP197 and endianness detection
  padata: remove cpu_index from the parallel_queue
  padata: unbind parallel jobs from specific CPUs
  padata: use separate workqueues for parallel and serial work
  padata, pcrypt: take CPU hotplug lock internally in padata_alloc_possible
  crypto: pcrypt - remove padata cpumask notifier
  padata: make padata_do_parallel find alternate callback CPU
  workqueue: require CPU hotplug read exclusion for apply_workqueue_attrs
  workqueue: unconfine alloc/apply/free_workqueue_attrs()
  padata: allocate workqueue internally
  arm64: dts: imx8mq: Add CAAM node
  random: Use wait_event_freezable() in add_hwgenerator_randomness()
  crypto: ux500 - Fix COMPILE_TEST warnings
  ...

1 files changed, 13 insertions, 26 deletions

diff --git a/crypto/aegis.h b/crypto/aegis.h
index 41a3090c..6920ebe7 100644
--- a/crypto/aegis.h
+++ b/crypto/aegis.h
@@ -10,6 +10,7 @@
 #define _CRYPTO_AEGIS_H
 
 #include <crypto/aes.h>
+#include <linux/bitops.h>
 #include <linux/types.h>
 
 #define AEGIS_BLOCK_SIZE 16
@@ -23,46 +24,32 @@ union aegis_block {
 #define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
 #define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
 
-static const union aegis_block crypto_aegis_const[2] = {
-	{ .words64 = {
-		cpu_to_le64(U64_C(0x0d08050302010100)),
-		cpu_to_le64(U64_C(0x6279e99059372215)),
-	} },
-	{ .words64 = {
-		cpu_to_le64(U64_C(0xf12fc26d55183ddb)),
-		cpu_to_le64(U64_C(0xdd28b57342311120)),
-	} },
-};
-
-static void crypto_aegis_block_xor(union aegis_block *dst,
-				   const union aegis_block *src)
+static __always_inline void crypto_aegis_block_xor(union aegis_block *dst,
+						   const union aegis_block *src)
 {
 	dst->words64[0] ^= src->words64[0];
 	dst->words64[1] ^= src->words64[1];
 }
 
-static void crypto_aegis_block_and(union aegis_block *dst,
-				   const union aegis_block *src)
+static __always_inline void crypto_aegis_block_and(union aegis_block *dst,
+						   const union aegis_block *src)
 {
 	dst->words64[0] &= src->words64[0];
 	dst->words64[1] &= src->words64[1];
 }
 
-static void crypto_aegis_aesenc(union aegis_block *dst,
-				const union aegis_block *src,
-				const union aegis_block *key)
+static __always_inline void crypto_aegis_aesenc(union aegis_block *dst,
+						const union aegis_block *src,
+						const union aegis_block *key)
 {
 	const u8  *s  = src->bytes;
-	const u32 *t0 = crypto_ft_tab[0];
-	const u32 *t1 = crypto_ft_tab[1];
-	const u32 *t2 = crypto_ft_tab[2];
-	const u32 *t3 = crypto_ft_tab[3];
+	const u32 *t = crypto_ft_tab[0];
 	u32 d0, d1, d2, d3;
 
-	d0 = t0[s[ 0]] ^ t1[s[ 5]] ^ t2[s[10]] ^ t3[s[15]];
-	d1 = t0[s[ 4]] ^ t1[s[ 9]] ^ t2[s[14]] ^ t3[s[ 3]];
-	d2 = t0[s[ 8]] ^ t1[s[13]] ^ t2[s[ 2]] ^ t3[s[ 7]];
-	d3 = t0[s[12]] ^ t1[s[ 1]] ^ t2[s[ 6]] ^ t3[s[11]];
+	d0 = t[s[ 0]] ^ rol32(t[s[ 5]], 8) ^ rol32(t[s[10]], 16) ^ rol32(t[s[15]], 24);
+	d1 = t[s[ 4]] ^ rol32(t[s[ 9]], 8) ^ rol32(t[s[14]], 16) ^ rol32(t[s[ 3]], 24);
+	d2 = t[s[ 8]] ^ rol32(t[s[13]], 8) ^ rol32(t[s[ 2]], 16) ^ rol32(t[s[ 7]], 24);
+	d3 = t[s[12]] ^ rol32(t[s[ 1]], 8) ^ rol32(t[s[ 6]], 16) ^ rol32(t[s[11]], 24);
 
 	dst->words32[0] = cpu_to_le32(d0) ^ key->words32[0];
 	dst->words32[1] = cpu_to_le32(d1) ^ key->words32[1];