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 1472-byte test to tcrypt for IPsec
   - Reintroduced crypto stats interface with numerous changes
   - Support incremental algorithm dumps

  Algorithms:
   - Add xchacha12/20
   - Add nhpoly1305
   - Add adiantum
   - Add streebog hash
   - Mark cts(cbc(aes)) as FIPS allowed

  Drivers:
   - Improve performance of arm64/chacha20
   - Improve performance of x86/chacha20
   - Add NEON-accelerated nhpoly1305
   - Add SSE2 accelerated nhpoly1305
   - Add AVX2 accelerated nhpoly1305
   - Add support for 192/256-bit keys in gcmaes AVX
   - Add SG support in gcmaes AVX
   - ESN for inline IPsec tx in chcr
   - Add support for CryptoCell 703 in ccree
   - Add support for CryptoCell 713 in ccree
   - Add SM4 support in ccree
   - Add SM3 support in ccree
   - Add support for chacha20 in caam/qi2
   - Add support for chacha20 + poly1305 in caam/jr
   - Add support for chacha20 + poly1305 in caam/qi2
   - Add AEAD cipher support in cavium/nitrox"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (130 commits)
  crypto: skcipher - remove remnants of internal IV generators
  crypto: cavium/nitrox - Fix build with !CONFIG_DEBUG_FS
  crypto: salsa20-generic - don't unnecessarily use atomic walk
  crypto: skcipher - add might_sleep() to skcipher_walk_virt()
  crypto: x86/chacha - avoid sleeping under kernel_fpu_begin()
  crypto: cavium/nitrox - Added AEAD cipher support
  crypto: mxc-scc - fix build warnings on ARM64
  crypto: api - document missing stats member
  crypto: user - remove unused dump functions
  crypto: chelsio - Fix wrong error counter increments
  crypto: chelsio - Reset counters on cxgb4 Detach
  crypto: chelsio - Handle PCI shutdown event
  crypto: chelsio - cleanup:send addr as value in function argument
  crypto: chelsio - Use same value for both channel in single WR
  crypto: chelsio - Swap location of AAD and IV sent in WR
  crypto: chelsio - remove set but not used variable 'kctx_len'
  crypto: ux500 - Use proper enum in hash_set_dma_transfer
  crypto: ux500 - Use proper enum in cryp_set_dma_transfer
  crypto: aesni - Add scatter/gather avx stubs, and use them in C
  crypto: aesni - Introduce partial block macro
  ..

2 files changed, 52 insertions, 9 deletions

diff --git a/lib/Makefile b/lib/Makefile
index f5262d30bfe6..e1b59da71418 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -20,7 +20,7 @@ KCOV_INSTRUMENT_dynamic_debug.o := n
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o int_sqrt.o extable.o \
-	 sha1.o chacha20.o irq_regs.o argv_split.o \
+	 sha1.o chacha.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
diff --git a/lib/chacha20.c b/lib/chacha.c
index d907fec6a9ed..a46d2832dbab 100644
--- a/lib/chacha20.c
+++ b/lib/chacha.c
@@ -1,5 +1,5 @@
 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539
+ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -14,17 +14,16 @@
 #include <linux/bitops.h>
 #include <linux/cryptohash.h>
 #include <asm/unaligned.h>
-#include <crypto/chacha20.h>
+#include <crypto/chacha.h>
 
-void chacha20_block(u32 *state, u8 *stream)
+static void chacha_permute(u32 *x, int nrounds)
 {
-	u32 x[16];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(x); i++)
-		x[i] = state[i];
+	/* whitelist the allowed round counts */
+	WARN_ON_ONCE(nrounds != 20 && nrounds != 12);
 
-	for (i = 0; i < 20; i += 2) {
+	for (i = 0; i < nrounds; i += 2) {
 		x[0]  += x[4];    x[12] = rol32(x[12] ^ x[0],  16);
 		x[1]  += x[5];    x[13] = rol32(x[13] ^ x[1],  16);
 		x[2]  += x[6];    x[14] = rol32(x[14] ^ x[2],  16);
@@ -65,10 +64,54 @@ void chacha20_block(u32 *state, u8 *stream)
 		x[8]  += x[13];   x[7]  = rol32(x[7]  ^ x[8],   7);
 		x[9]  += x[14];   x[4]  = rol32(x[4]  ^ x[9],   7);
 	}
+}
+
+/**
+ * chacha_block - generate one keystream block and increment block counter
+ * @state: input state matrix (16 32-bit words)
+ * @stream: output keystream block (64 bytes)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * This is the ChaCha core, a function from 64-byte strings to 64-byte strings.
+ * The caller has already converted the endianness of the input.  This function
+ * also handles incrementing the block counter in the input matrix.
+ */
+void chacha_block(u32 *state, u8 *stream, int nrounds)
+{
+	u32 x[16];
+	int i;
+
+	memcpy(x, state, 64);
+
+	chacha_permute(x, nrounds);
 
 	for (i = 0; i < ARRAY_SIZE(x); i++)
 		put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
 
 	state[12]++;
 }
-EXPORT_SYMBOL(chacha20_block);
+EXPORT_SYMBOL(chacha_block);
+
+/**
+ * hchacha_block - abbreviated ChaCha core, for XChaCha
+ * @in: input state matrix (16 32-bit words)
+ * @out: output (8 32-bit words)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
+ * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf).  HChaCha
+ * skips the final addition of the initial state, and outputs only certain words
+ * of the state.  It should not be used for streaming directly.
+ */
+void hchacha_block(const u32 *in, u32 *out, int nrounds)
+{
+	u32 x[16];
+
+	memcpy(x, in, 64);
+
+	chacha_permute(x, nrounds);
+
+	memcpy(&out[0], &x[0], 16);
+	memcpy(&out[4], &x[12], 16);
+}
+EXPORT_SYMBOL(hchacha_block);