aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/crypto
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/crypto')
-rw-r--r--arch/arm/crypto/Kconfig1
-rw-r--r--arch/arm/crypto/Makefile4
-rw-r--r--arch/arm/crypto/aes-cipher-core.S19
-rw-r--r--arch/arm/crypto/chacha20-neon-core.S287
-rw-r--r--arch/arm/crypto/crc32-ce-glue.c2
-rw-r--r--arch/arm/crypto/ghash-ce-core.S108
-rw-r--r--arch/arm/crypto/ghash-ce-glue.c43
-rw-r--r--arch/arm/crypto/sha1-armv4-large.S10
-rw-r--r--arch/arm/crypto/sha1-ce-glue.c1
-rw-r--r--arch/arm/crypto/sha1_glue.c1
-rw-r--r--arch/arm/crypto/sha1_neon_glue.c1
-rw-r--r--arch/arm/crypto/sha2-ce-glue.c2
-rw-r--r--arch/arm/crypto/sha256-armv4.pl11
-rw-r--r--arch/arm/crypto/sha256-core.S_shipped11
-rw-r--r--arch/arm/crypto/sha256_glue.c4
-rw-r--r--arch/arm/crypto/sha256_neon_glue.c6
-rw-r--r--arch/arm/crypto/sha512-armv4.pl11
-rw-r--r--arch/arm/crypto/sha512-core.S_shipped11
-rw-r--r--arch/arm/crypto/sha512-glue.c2
-rw-r--r--arch/arm/crypto/sha512-neon-glue.c2
20 files changed, 343 insertions, 194 deletions
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index b8e69fe282b8..ef0c7feea6e2 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -99,6 +99,7 @@ config CRYPTO_GHASH_ARM_CE
depends on KERNEL_MODE_NEON
select CRYPTO_HASH
select CRYPTO_CRYPTD
+ select CRYPTO_GF128MUL
help
Use an implementation of GHASH (used by the GCM AEAD chaining mode)
that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 30ef8e291271..bd5bceef0605 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -54,6 +54,7 @@ crct10dif-arm-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
+ifdef REGENERATE_ARM_CRYPTO
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)
@@ -62,5 +63,6 @@ $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
$(call cmd,perl)
+endif
-.PRECIOUS: $(obj)/sha256-core.S $(obj)/sha512-core.S
+targets += sha256-core.S sha512-core.S
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
index 54b384084637..184d6c2d15d5 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -174,6 +174,16 @@
.ltorg
.endm
+ENTRY(__aes_arm_encrypt)
+ do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
+ENDPROC(__aes_arm_encrypt)
+
+ .align 5
+ENTRY(__aes_arm_decrypt)
+ do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
+ENDPROC(__aes_arm_decrypt)
+
+ .section ".rodata", "a"
.align L1_CACHE_SHIFT
.type __aes_arm_inverse_sbox, %object
__aes_arm_inverse_sbox:
@@ -210,12 +220,3 @@ __aes_arm_inverse_sbox:
.byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
.byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
.size __aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox
-
-ENTRY(__aes_arm_encrypt)
- do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
-ENDPROC(__aes_arm_encrypt)
-
- .align 5
-ENTRY(__aes_arm_decrypt)
- do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
-ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/chacha20-neon-core.S b/arch/arm/crypto/chacha20-neon-core.S
index 3fecb2124c35..50e7b9896818 100644
--- a/arch/arm/crypto/chacha20-neon-core.S
+++ b/arch/arm/crypto/chacha20-neon-core.S
@@ -18,6 +18,34 @@
* (at your option) any later version.
*/
+ /*
+ * NEON doesn't have a rotate instruction. The alternatives are, more or less:
+ *
+ * (a) vshl.u32 + vsri.u32 (needs temporary register)
+ * (b) vshl.u32 + vshr.u32 + vorr (needs temporary register)
+ * (c) vrev32.16 (16-bit rotations only)
+ * (d) vtbl.8 + vtbl.8 (multiple of 8 bits rotations only,
+ * needs index vector)
+ *
+ * ChaCha20 has 16, 12, 8, and 7-bit rotations. For the 12 and 7-bit
+ * rotations, the only choices are (a) and (b). We use (a) since it takes
+ * two-thirds the cycles of (b) on both Cortex-A7 and Cortex-A53.
+ *
+ * For the 16-bit rotation, we use vrev32.16 since it's consistently fastest
+ * and doesn't need a temporary register.
+ *
+ * For the 8-bit rotation, we use vtbl.8 + vtbl.8. On Cortex-A7, this sequence
+ * is twice as fast as (a), even when doing (a) on multiple registers
+ * simultaneously to eliminate the stall between vshl and vsri. Also, it
+ * parallelizes better when temporary registers are scarce.
+ *
+ * A disadvantage is that on Cortex-A53, the vtbl sequence is the same speed as
+ * (a), so the need to load the rotation table actually makes the vtbl method
+ * slightly slower overall on that CPU (~1.3% slower ChaCha20). Still, it
+ * seems to be a good compromise to get a more significant speed boost on some
+ * CPUs, e.g. ~4.8% faster ChaCha20 on Cortex-A7.
+ */
+
#include <linux/linkage.h>
.text
@@ -46,14 +74,15 @@ ENTRY(chacha20_block_xor_neon)
vmov q10, q2
vmov q11, q3
+ adr ip, .Lrol8_table
mov r3, #10
+ vld1.8 {d10}, [ip, :64]
.Ldoubleround:
// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vadd.i32 q0, q0, q1
- veor q4, q3, q0
- vshl.u32 q3, q4, #16
- vsri.u32 q3, q4, #16
+ veor q3, q3, q0
+ vrev32.16 q3, q3
// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vadd.i32 q2, q2, q3
@@ -63,9 +92,9 @@ ENTRY(chacha20_block_xor_neon)
// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vadd.i32 q0, q0, q1
- veor q4, q3, q0
- vshl.u32 q3, q4, #8
- vsri.u32 q3, q4, #24
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vadd.i32 q2, q2, q3
@@ -82,9 +111,8 @@ ENTRY(chacha20_block_xor_neon)
// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
vadd.i32 q0, q0, q1
- veor q4, q3, q0
- vshl.u32 q3, q4, #16
- vsri.u32 q3, q4, #16
+ veor q3, q3, q0
+ vrev32.16 q3, q3
// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
vadd.i32 q2, q2, q3
@@ -94,9 +122,9 @@ ENTRY(chacha20_block_xor_neon)
// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
vadd.i32 q0, q0, q1
- veor q4, q3, q0
- vshl.u32 q3, q4, #8
- vsri.u32 q3, q4, #24
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
vadd.i32 q2, q2, q3
@@ -141,13 +169,17 @@ ENTRY(chacha20_block_xor_neon)
bx lr
ENDPROC(chacha20_block_xor_neon)
+ .align 4
+.Lctrinc: .word 0, 1, 2, 3
+.Lrol8_table: .byte 3, 0, 1, 2, 7, 4, 5, 6
+
.align 5
ENTRY(chacha20_4block_xor_neon)
- push {r4-r6, lr}
- mov ip, sp // preserve the stack pointer
- sub r3, sp, #0x20 // allocate a 32 byte buffer
- bic r3, r3, #0x1f // aligned to 32 bytes
- mov sp, r3
+ push {r4-r5}
+ mov r4, sp // preserve the stack pointer
+ sub ip, sp, #0x20 // allocate a 32 byte buffer
+ bic ip, ip, #0x1f // aligned to 32 bytes
+ mov sp, ip
// r0: Input state matrix, s
// r1: 4 data blocks output, o
@@ -157,25 +189,24 @@ ENTRY(chacha20_4block_xor_neon)
// This function encrypts four consecutive ChaCha20 blocks by loading
// the state matrix in NEON registers four times. The algorithm performs
// each operation on the corresponding word of each state matrix, hence
- // requires no word shuffling. For final XORing step we transpose the
- // matrix by interleaving 32- and then 64-bit words, which allows us to
- // do XOR in NEON registers.
+ // requires no word shuffling. The words are re-interleaved before the
+ // final addition of the original state and the XORing step.
//
- // x0..15[0-3] = s0..3[0..3]
- add r3, r0, #0x20
+ // x0..15[0-3] = s0..15[0-3]
+ add ip, r0, #0x20
vld1.32 {q0-q1}, [r0]
- vld1.32 {q2-q3}, [r3]
+ vld1.32 {q2-q3}, [ip]
- adr r3, CTRINC
+ adr r5, .Lctrinc
vdup.32 q15, d7[1]
vdup.32 q14, d7[0]
- vld1.32 {q11}, [r3, :128]
+ vld1.32 {q4}, [r5, :128]
vdup.32 q13, d6[1]
vdup.32 q12, d6[0]
- vadd.i32 q12, q12, q11 // x12 += counter values 0-3
vdup.32 q11, d5[1]
vdup.32 q10, d5[0]
+ vadd.u32 q12, q12, q4 // x12 += counter values 0-3
vdup.32 q9, d4[1]
vdup.32 q8, d4[0]
vdup.32 q7, d3[1]
@@ -187,9 +218,13 @@ ENTRY(chacha20_4block_xor_neon)
vdup.32 q1, d0[1]
vdup.32 q0, d0[0]
+ adr ip, .Lrol8_table
mov r3, #10
+ b 1f
.Ldoubleround4:
+ vld1.32 {q8-q9}, [sp, :256]
+1:
// x0 += x4, x12 = rotl32(x12 ^ x0, 16)
// x1 += x5, x13 = rotl32(x13 ^ x1, 16)
// x2 += x6, x14 = rotl32(x14 ^ x2, 16)
@@ -238,24 +273,25 @@ ENTRY(chacha20_4block_xor_neon)
// x1 += x5, x13 = rotl32(x13 ^ x1, 8)
// x2 += x6, x14 = rotl32(x14 ^ x2, 8)
// x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
vadd.i32 q0, q0, q4
vadd.i32 q1, q1, q5
vadd.i32 q2, q2, q6
vadd.i32 q3, q3, q7
- veor q8, q12, q0
- veor q9, q13, q1
- vshl.u32 q12, q8, #8
- vshl.u32 q13, q9, #8
- vsri.u32 q12, q8, #24
- vsri.u32 q13, q9, #24
+ veor q12, q12, q0
+ veor q13, q13, q1
+ veor q14, q14, q2
+ veor q15, q15, q3
- veor q8, q14, q2
- veor q9, q15, q3
- vshl.u32 q14, q8, #8
- vshl.u32 q15, q9, #8
- vsri.u32 q14, q8, #24
- vsri.u32 q15, q9, #24
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
vld1.32 {q8-q9}, [sp, :256]
@@ -334,24 +370,25 @@ ENTRY(chacha20_4block_xor_neon)
// x1 += x6, x12 = rotl32(x12 ^ x1, 8)
// x2 += x7, x13 = rotl32(x13 ^ x2, 8)
// x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
vadd.i32 q0, q0, q5
vadd.i32 q1, q1, q6
vadd.i32 q2, q2, q7
vadd.i32 q3, q3, q4
- veor q8, q15, q0
- veor q9, q12, q1
- vshl.u32 q15, q8, #8
- vshl.u32 q12, q9, #8
- vsri.u32 q15, q8, #24
- vsri.u32 q12, q9, #24
+ veor q15, q15, q0
+ veor q12, q12, q1
+ veor q13, q13, q2
+ veor q14, q14, q3
- veor q8, q13, q2
- veor q9, q14, q3
- vshl.u32 q13, q8, #8
- vshl.u32 q14, q9, #8
- vsri.u32 q13, q8, #24
- vsri.u32 q14, q9, #24
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
vld1.32 {q8-q9}, [sp, :256]
@@ -381,104 +418,76 @@ ENTRY(chacha20_4block_xor_neon)
vsri.u32 q6, q9, #25
subs r3, r3, #1
- beq 0f
-
- vld1.32 {q8-q9}, [sp, :256]
- b .Ldoubleround4
-
- // x0[0-3] += s0[0]
- // x1[0-3] += s0[1]
- // x2[0-3] += s0[2]
- // x3[0-3] += s0[3]
-0: ldmia r0!, {r3-r6}
- vdup.32 q8, r3
- vdup.32 q9, r4
- vadd.i32 q0, q0, q8
- vadd.i32 q1, q1, q9
- vdup.32 q8, r5
- vdup.32 q9, r6
- vadd.i32 q2, q2, q8
- vadd.i32 q3, q3, q9
-
- // x4[0-3] += s1[0]
- // x5[0-3] += s1[1]
- // x6[0-3] += s1[2]
- // x7[0-3] += s1[3]
- ldmia r0!, {r3-r6}
- vdup.32 q8, r3
- vdup.32 q9, r4
- vadd.i32 q4, q4, q8
- vadd.i32 q5, q5, q9
- vdup.32 q8, r5
- vdup.32 q9, r6
- vadd.i32 q6, q6, q8
- vadd.i32 q7, q7, q9
-
- // interleave 32-bit words in state n, n+1
- vzip.32 q0, q1
- vzip.32 q2, q3
- vzip.32 q4, q5
- vzip.32 q6, q7
-
- // interleave 64-bit words in state n, n+2
+ bne .Ldoubleround4
+
+ // x0..7[0-3] are in q0-q7, x10..15[0-3] are in q10-q15.
+ // x8..9[0-3] are on the stack.
+
+ // Re-interleave the words in the first two rows of each block (x0..7).
+ // Also add the counter values 0-3 to x12[0-3].
+ vld1.32 {q8}, [r5, :128] // load counter values 0-3
+ vzip.32 q0, q1 // => (0 1 0 1) (0 1 0 1)
+ vzip.32 q2, q3 // => (2 3 2 3) (2 3 2 3)
+ vzip.32 q4, q5 // => (4 5 4 5) (4 5 4 5)
+ vzip.32 q6, q7 // => (6 7 6 7) (6 7 6 7)
+ vadd.u32 q12, q8 // x12 += counter values 0-3
vswp d1, d4
vswp d3, d6
+ vld1.32 {q8-q9}, [r0]! // load s0..7
vswp d9, d12
vswp d11, d14
- // xor with corresponding input, write to output
+ // Swap q1 and q4 so that we'll free up consecutive registers (q0-q1)
+ // after XORing the first 32 bytes.
+ vswp q1, q4
+
+ // First two rows of each block are (q0 q1) (q2 q6) (q4 q5) (q3 q7)
+
+ // x0..3[0-3] += s0..3[0-3] (add orig state to 1st row of each block)
+ vadd.u32 q0, q0, q8
+ vadd.u32 q2, q2, q8
+ vadd.u32 q4, q4, q8
+ vadd.u32 q3, q3, q8
+
+ // x4..7[0-3] += s4..7[0-3] (add orig state to 2nd row of each block)
+ vadd.u32 q1, q1, q9
+ vadd.u32 q6, q6, q9
+ vadd.u32 q5, q5, q9
+ vadd.u32 q7, q7, q9
+
+ // XOR first 32 bytes using keystream from first two rows of first block
vld1.8 {q8-q9}, [r2]!
veor q8, q8, q0
- veor q9, q9, q4
+ veor q9, q9, q1
vst1.8 {q8-q9}, [r1]!
+ // Re-interleave the words in the last two rows of each block (x8..15).
vld1.32 {q8-q9}, [sp, :256]
-
- // x8[0-3] += s2[0]
- // x9[0-3] += s2[1]
- // x10[0-3] += s2[2]
- // x11[0-3] += s2[3]
- ldmia r0!, {r3-r6}
- vdup.32 q0, r3
- vdup.32 q4, r4
- vadd.i32 q8, q8, q0
- vadd.i32 q9, q9, q4
- vdup.32 q0, r5
- vdup.32 q4, r6
- vadd.i32 q10, q10, q0
- vadd.i32 q11, q11, q4
-
- // x12[0-3] += s3[0]
- // x13[0-3] += s3[1]
- // x14[0-3] += s3[2]
- // x15[0-3] += s3[3]
- ldmia r0!, {r3-r6}
- vdup.32 q0, r3
- vdup.32 q4, r4
- adr r3, CTRINC
- vadd.i32 q12, q12, q0
- vld1.32 {q0}, [r3, :128]
- vadd.i32 q13, q13, q4
- vadd.i32 q12, q12, q0 // x12 += counter values 0-3
-
- vdup.32 q0, r5
- vdup.32 q4, r6
- vadd.i32 q14, q14, q0
- vadd.i32 q15, q15, q4
-
- // interleave 32-bit words in state n, n+1
- vzip.32 q8, q9
- vzip.32 q10, q11
- vzip.32 q12, q13
- vzip.32 q14, q15
-
- // interleave 64-bit words in state n, n+2
- vswp d17, d20
- vswp d19, d22
+ vzip.32 q12, q13 // => (12 13 12 13) (12 13 12 13)
+ vzip.32 q14, q15 // => (14 15 14 15) (14 15 14 15)
+ vzip.32 q8, q9 // => (8 9 8 9) (8 9 8 9)
+ vzip.32 q10, q11 // => (10 11 10 11) (10 11 10 11)
+ vld1.32 {q0-q1}, [r0] // load s8..15
vswp d25, d28
vswp d27, d30
+ vswp d17, d20
+ vswp d19, d22
+
+ // Last two rows of each block are (q8 q12) (q10 q14) (q9 q13) (q11 q15)
+
+ // x8..11[0-3] += s8..11[0-3] (add orig state to 3rd row of each block)
+ vadd.u32 q8, q8, q0
+ vadd.u32 q10, q10, q0
+ vadd.u32 q9, q9, q0
+ vadd.u32 q11, q11, q0
+
+ // x12..15[0-3] += s12..15[0-3] (add orig state to 4th row of each block)
+ vadd.u32 q12, q12, q1
+ vadd.u32 q14, q14, q1
+ vadd.u32 q13, q13, q1
+ vadd.u32 q15, q15, q1
- vmov q4, q1
+ // XOR the rest of the data with the keystream
vld1.8 {q0-q1}, [r2]!
veor q0, q0, q8
@@ -511,13 +520,11 @@ ENTRY(chacha20_4block_xor_neon)
vst1.8 {q0-q1}, [r1]!
vld1.8 {q0-q1}, [r2]
+ mov sp, r4 // restore original stack pointer
veor q0, q0, q11
veor q1, q1, q15
vst1.8 {q0-q1}, [r1]
- mov sp, ip
- pop {r4-r6, pc}
+ pop {r4-r5}
+ bx lr
ENDPROC(chacha20_4block_xor_neon)
-
- .align 4
-CTRINC: .word 0, 1, 2, 3
diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c
index 96e62ec105d0..cd9e93b46c2d 100644
--- a/arch/arm/crypto/crc32-ce-glue.c
+++ b/arch/arm/crypto/crc32-ce-glue.c
@@ -236,7 +236,7 @@ static void __exit crc32_pmull_mod_exit(void)
ARRAY_SIZE(crc32_pmull_algs));
}
-static const struct cpu_feature crc32_cpu_feature[] = {
+static const struct cpu_feature __maybe_unused crc32_cpu_feature[] = {
{ cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { }
};
MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature);
diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S
index 2f78c10b1881..406009afa9cf 100644
--- a/arch/arm/crypto/ghash-ce-core.S
+++ b/arch/arm/crypto/ghash-ce-core.S
@@ -63,6 +63,33 @@
k48 .req d31
SHASH2_p64 .req d31
+ HH .req q10
+ HH3 .req q11
+ HH4 .req q12
+ HH34 .req q13
+
+ HH_L .req d20
+ HH_H .req d21
+ HH3_L .req d22
+ HH3_H .req d23
+ HH4_L .req d24
+ HH4_H .req d25
+ HH34_L .req d26
+ HH34_H .req d27
+ SHASH2_H .req d29
+
+ XL2 .req q5
+ XM2 .req q6
+ XH2 .req q7
+ T3 .req q8
+
+ XL2_L .req d10
+ XL2_H .req d11
+ XM2_L .req d12
+ XM2_H .req d13
+ T3_L .req d16
+ T3_H .req d17
+
.text
.fpu crypto-neon-fp-armv8
@@ -175,12 +202,77 @@
beq 0f
vld1.64 {T1}, [ip]
teq r0, #0
- b 1f
+ b 3f
+
+0: .ifc \pn, p64
+ tst r0, #3 // skip until #blocks is a
+ bne 2f // round multiple of 4
+
+ vld1.8 {XL2-XM2}, [r2]!
+1: vld1.8 {T3-T2}, [r2]!
+ vrev64.8 XL2, XL2
+ vrev64.8 XM2, XM2
+
+ subs r0, r0, #4
+
+ vext.8 T1, XL2, XL2, #8
+ veor XL2_H, XL2_H, XL_L
+ veor XL, XL, T1
+
+ vrev64.8 T3, T3
+ vrev64.8 T1, T2
+
+ vmull.p64 XH, HH4_H, XL_H // a1 * b1
+ veor XL2_H, XL2_H, XL_H
+ vmull.p64 XL, HH4_L, XL_L // a0 * b0
+ vmull.p64 XM, HH34_H, XL2_H // (a1 + a0)(b1 + b0)
+
+ vmull.p64 XH2, HH3_H, XM2_L // a1 * b1
+ veor XM2_L, XM2_L, XM2_H
+ vmull.p64 XL2, HH3_L, XM2_H // a0 * b0
+ vmull.p64 XM2, HH34_L, XM2_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
+
+ vmull.p64 XH2, HH_H, T3_L // a1 * b1
+ veor T3_L, T3_L, T3_H
+ vmull.p64 XL2, HH_L, T3_H // a0 * b0
+ vmull.p64 XM2, SHASH2_H, T3_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
+
+ vmull.p64 XH2, SHASH_H, T1_L // a1 * b1
+ veor T1_L, T1_L, T1_H
+ vmull.p64 XL2, SHASH_L, T1_H // a0 * b0
+ vmull.p64 XM2, SHASH2_p64, T1_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
-0: vld1.64 {T1}, [r2]!
+ beq 4f
+
+ vld1.8 {XL2-XM2}, [r2]!
+
+ veor T1, XL, XH
+ veor XM, XM, T1
+
+ __pmull_reduce_p64
+
+ veor T1, T1, XH
+ veor XL, XL, T1
+
+ b 1b
+ .endif
+
+2: vld1.64 {T1}, [r2]!
subs r0, r0, #1
-1: /* multiply XL by SHASH in GF(2^128) */
+3: /* multiply XL by SHASH in GF(2^128) */
#ifndef CONFIG_CPU_BIG_ENDIAN
vrev64.8 T1, T1
#endif
@@ -193,7 +285,7 @@
__pmull_\pn XL, XL_L, SHASH_L, s1l, s2l, s3l, s4l @ a0 * b0
__pmull_\pn XM, T1_L, SHASH2_\pn @ (a1+a0)(b1+b0)
- veor T1, XL, XH
+4: veor T1, XL, XH
veor XM, XM, T1
__pmull_reduce_\pn
@@ -212,8 +304,14 @@
* struct ghash_key const *k, const char *head)
*/
ENTRY(pmull_ghash_update_p64)
- vld1.64 {SHASH}, [r3]
+ vld1.64 {SHASH}, [r3]!
+ vld1.64 {HH}, [r3]!
+ vld1.64 {HH3-HH4}, [r3]
+
veor SHASH2_p64, SHASH_L, SHASH_H
+ veor SHASH2_H, HH_L, HH_H
+ veor HH34_L, HH3_L, HH3_H
+ veor HH34_H, HH4_L, HH4_H
vmov.i8 MASK, #0xe1
vshl.u64 MASK, MASK, #57
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index d9bb52cae2ac..b7d30b6cf49c 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -1,7 +1,7 @@
/*
* Accelerated GHASH implementation with ARMv8 vmull.p64 instructions.
*
- * Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -28,8 +28,10 @@ MODULE_ALIAS_CRYPTO("ghash");
#define GHASH_DIGEST_SIZE 16
struct ghash_key {
- u64 a;
- u64 b;
+ u64 h[2];
+ u64 h2[2];
+ u64 h3[2];
+ u64 h4[2];
};
struct ghash_desc_ctx {
@@ -117,26 +119,40 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
return 0;
}
+static void ghash_reflect(u64 h[], const be128 *k)
+{
+ u64 carry = be64_to_cpu(k->a) >> 63;
+
+ h[0] = (be64_to_cpu(k->b) << 1) | carry;
+ h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63);
+
+ if (carry)
+ h[1] ^= 0xc200000000000000UL;
+}
+
static int ghash_setkey(struct crypto_shash *tfm,
const u8 *inkey, unsigned int keylen)
{
struct ghash_key *key = crypto_shash_ctx(tfm);
- u64 a, b;
+ be128 h, k;
if (keylen != GHASH_BLOCK_SIZE) {
crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
- /* perform multiplication by 'x' in GF(2^128) */
- b = get_unaligned_be64(inkey);
- a = get_unaligned_be64(inkey + 8);
+ memcpy(&k, inkey, GHASH_BLOCK_SIZE);
+ ghash_reflect(key->h, &k);
+
+ h = k;
+ gf128mul_lle(&h, &k);
+ ghash_reflect(key->h2, &h);
- key->a = (a << 1) | (b >> 63);
- key->b = (b << 1) | (a >> 63);
+ gf128mul_lle(&h, &k);
+ ghash_reflect(key->h3, &h);
- if (b >> 63)
- key->b ^= 0xc200000000000000UL;
+ gf128mul_lle(&h, &k);
+ ghash_reflect(key->h4, &h);
return 0;
}
@@ -152,7 +168,7 @@ static struct shash_alg ghash_alg = {
.cra_name = "__ghash",
.cra_driver_name = "__driver-ghash-ce",
.cra_priority = 0,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_INTERNAL,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = GHASH_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct ghash_key),
.cra_module = THIS_MODULE,
@@ -308,9 +324,8 @@ static struct ahash_alg ghash_async_alg = {
.cra_name = "ghash",
.cra_driver_name = "ghash-ce",
.cra_priority = 300,
- .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+ .cra_flags = CRYPTO_ALG_ASYNC,
.cra_blocksize = GHASH_BLOCK_SIZE,
- .cra_type = &crypto_ahash_type,
.cra_ctxsize = sizeof(struct ghash_async_ctx),
.cra_module = THIS_MODULE,
.cra_init = ghash_async_init_tfm,
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index 99207c45ec10..f82cd8cf5a09 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -1,4 +1,14 @@
#define __ARM_ARCH__ __LINUX_ARM_ARCH__
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
+
@ ====================================================================
@ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
@ project. The module is, however, dual licensed under OpenSSL and
diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index 555f72b5e659..b732522e20f8 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -75,7 +75,6 @@ static struct shash_alg alg = {
.cra_name = "sha1",
.cra_driver_name = "sha1-ce",
.cra_priority = 200,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 6fc73bf8766d..98ab8239f919 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -67,7 +67,6 @@ static struct shash_alg alg = {
.cra_name = "sha1",
.cra_driver_name= "sha1-asm",
.cra_priority = 150,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 4e22f122f966..d15e0ea2c95e 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -83,7 +83,6 @@ static struct shash_alg alg = {
.cra_name = "sha1",
.cra_driver_name = "sha1-neon",
.cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
index df4dcef054ae..1211a5c129fc 100644
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -78,7 +78,6 @@ static struct shash_alg algs[] = { {
.cra_name = "sha224",
.cra_driver_name = "sha224-ce",
.cra_priority = 300,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA256_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
@@ -93,7 +92,6 @@ static struct shash_alg algs[] = { {
.cra_name = "sha256",
.cra_driver_name = "sha256-ce",
.cra_priority = 300,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA256_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index fac0533ea633..b9ec44060ed3 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -1,12 +1,19 @@
#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
# ====================================================================
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
# project. The module is, however, dual licensed under OpenSSL and
# CRYPTOGAMS licenses depending on where you obtain it. For further
# details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPL terms is granted.
# ====================================================================
# SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index 555a1a8eec90..3b58300d611c 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -1,11 +1,18 @@
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
@ ====================================================================
@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@ project. The module is, however, dual licensed under OpenSSL and
@ CRYPTOGAMS licenses depending on where you obtain it. For further
@ details see http://www.openssl.org/~appro/cryptogams/.
-@
-@ Permission to use under GPL terms is granted.
@ ====================================================================
@ SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
index a84e869ef900..0ae900e778f3 100644
--- a/arch/arm/crypto/sha256_glue.c
+++ b/arch/arm/crypto/sha256_glue.c
@@ -2,7 +2,7 @@
* Glue code for the SHA256 Secure Hash Algorithm assembly implementation
* using optimized ARM assembler and NEON instructions.
*
- * Copyright © 2015 Google Inc.
+ * Copyright © 2015 Google Inc.
*
* This file is based on sha256_ssse3_glue.c:
* Copyright (C) 2013 Intel Corporation
@@ -71,7 +71,6 @@ static struct shash_alg algs[] = { {
.cra_name = "sha256",
.cra_driver_name = "sha256-asm",
.cra_priority = 150,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA256_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
@@ -86,7 +85,6 @@ static struct shash_alg algs[] = { {
.cra_name = "sha224",
.cra_driver_name = "sha224-asm",
.cra_priority = 150,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA224_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index 39ccd658817e..1d82c6cd31a4 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -2,10 +2,10 @@
* Glue code for the SHA256 Secure Hash Algorithm assembly implementation
* using NEON instructions.
*
- * Copyright © 2015 Google Inc.
+ * Copyright © 2015 Google Inc.
*
* This file is based on sha512_neon_glue.c:
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the Free
@@ -79,7 +79,6 @@ struct shash_alg sha256_neon_algs[] = { {
.cra_name = "sha256",
.cra_driver_name = "sha256-neon",
.cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA256_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
@@ -94,7 +93,6 @@ struct shash_alg sha256_neon_algs[] = { {
.cra_name = "sha224",
.cra_driver_name = "sha224-neon",
.cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA224_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index a2b11a844357..fb5d15048c0b 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -1,12 +1,19 @@
#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore this program is free software;
+# you can redistribute it and/or modify it under the terms of the GNU General
+# Public License version 2 as published by the Free Software Foundation.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
# ====================================================================
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
# project. The module is, however, dual licensed under OpenSSL and
# CRYPTOGAMS licenses depending on where you obtain it. For further
# details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPL terms is granted.
# ====================================================================
# SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index 3694c4d4ca2b..b1c334a49cda 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -1,11 +1,18 @@
+@ SPDX-License-Identifier: GPL-2.0
+
+@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
+@ has relicensed it under the GPLv2. Therefore this program is free software;
+@ you can redistribute it and/or modify it under the terms of the GNU General
+@ Public License version 2 as published by the Free Software Foundation.
+@
+@ The original headers, including the original license headers, are
+@ included below for completeness.
@ ====================================================================
@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@ project. The module is, however, dual licensed under OpenSSL and
@ CRYPTOGAMS licenses depending on where you obtain it. For further
@ details see http://www.openssl.org/~appro/cryptogams/.
-@
-@ Permission to use under GPL terms is granted.
@ ====================================================================
@ SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
index 269a394e4a53..86540cd4a6fa 100644
--- a/arch/arm/crypto/sha512-glue.c
+++ b/arch/arm/crypto/sha512-glue.c
@@ -63,7 +63,6 @@ static struct shash_alg sha512_arm_algs[] = { {
.cra_name = "sha384",
.cra_driver_name = "sha384-arm",
.cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA512_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
@@ -78,7 +77,6 @@ static struct shash_alg sha512_arm_algs[] = { {
.cra_name = "sha512",
.cra_driver_name = "sha512-arm",
.cra_priority = 250,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA512_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
index 32693684a3ab..8a5642b41fd6 100644
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -75,7 +75,6 @@ struct shash_alg sha512_neon_algs[] = { {
.cra_name = "sha384",
.cra_driver_name = "sha384-neon",
.cra_priority = 300,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA384_BLOCK_SIZE,
.cra_module = THIS_MODULE,
@@ -91,7 +90,6 @@ struct shash_alg sha512_neon_algs[] = { {
.cra_name = "sha512",
.cra_driver_name = "sha512-neon",
.cra_priority = 300,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
.cra_blocksize = SHA512_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-30 22:58:26 +0000