@@ -10,6 +10,7 @@
*/
#include <linux/linkage.h>
+#include <asm/cache.h>
.text
.align 5
@@ -32,19 +33,19 @@
.endif
.endm
- .macro __load, out, in, idx
+ .macro __load, out, in, idx, sz, op
.if __LINUX_ARM_ARCH__ < 7 && \idx > 0
- ldr \out, [ttab, \in, lsr #(8 * \idx) - 2]
+ ldr\op \out, [ttab, \in, lsr #(8 * \idx) - \sz]
.else
- ldr \out, [ttab, \in, lsl #2]
+ ldr\op \out, [ttab, \in, lsl #\sz]
.endif
.endm
- .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc
+ .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op
__select \out0, \in0, 0
__select t0, \in1, 1
- __load \out0, \out0, 0
- __load t0, t0, 1
+ __load \out0, \out0, 0, \sz, \op
+ __load t0, t0, 1, \sz, \op
.if \enc
__select \out1, \in1, 0
@@ -53,10 +54,10 @@
__select \out1, \in3, 0
__select t1, \in0, 1
.endif
- __load \out1, \out1, 0
+ __load \out1, \out1, 0, \sz, \op
__select t2, \in2, 2
- __load t1, t1, 1
- __load t2, t2, 2
+ __load t1, t1, 1, \sz, \op
+ __load t2, t2, 2, \sz, \op
eor \out0, \out0, t0, ror #24
@@ -68,9 +69,9 @@
__select \t3, \in1, 2
__select \t4, \in2, 3
.endif
- __load \t3, \t3, 2
- __load t0, t0, 3
- __load \t4, \t4, 3
+ __load \t3, \t3, 2, \sz, \op
+ __load t0, t0, 3, \sz, \op
+ __load \t4, \t4, 3, \sz, \op
eor \out1, \out1, t1, ror #24
eor \out0, \out0, t2, ror #16
@@ -82,14 +83,14 @@
eor \out1, \out1, t2
.endm
- .macro fround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
- __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+ .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+ __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op
.endm
- .macro iround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
- __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+ .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op
.endm
.macro __rev, out, in
@@ -114,7 +115,7 @@
.endif
.endm
- .macro do_crypt, round, ttab, ltab
+ .macro do_crypt, round, ttab, ltab, bsz
push {r3-r11, lr}
ldr r4, [in]
@@ -146,9 +147,12 @@
1: subs rounds, rounds, #4
\round r8, r9, r10, r11, r4, r5, r6, r7
- __adrl ttab, \ltab, ls
+ bls 2f
\round r4, r5, r6, r7, r8, r9, r10, r11
- bhi 0b
+ b 0b
+
+2: __adrl ttab, \ltab
+ \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b
#ifdef CONFIG_CPU_BIG_ENDIAN
__rev r4, r4
@@ -170,10 +174,48 @@
.ltorg
.endm
+ .align L1_CACHE_SHIFT
+ .type __aes_arm_inverse_sbox, %object
+__aes_arm_inverse_sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .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_fl_tab
+ 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, crypto_il_tab
+ do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0
ENDPROC(__aes_arm_decrypt)
For the final round, avoid the expanded and padded lookup tables exported by the generic AES driver. Instead, for encryption, we can perform byte loads from the same table we used for the inner rounds, which will still be hot in the caches. For decryption, use the inverse AES Sbox directly, which is 4x smaller than the inverse lookup table exported by the generic driver. This should significantly reduce the Dcache footprint of our code, which makes the code more robust against timing attacks. It does not introduce any additional module dependencies, given that we already rely on the core AES module for the shared key expansion routines. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm/crypto/aes-cipher-core.S | 88 +++++++++++++++----- 1 file changed, 65 insertions(+), 23 deletions(-) -- 2.9.3