Re: [PATCH v2 2/2] crypto: arm/aes - add some hardening against cache-timing attacks
Hi Eric,
Thanks for looking into this.
On 17 October 2018 at 14:18, Eric Biggers wrote:
> From: Eric Biggers
>
> Make the ARM scalar AES implementation closer to constant-time by
> disabling interrupts and prefetching the tables into L1 cache. This is
> feasible because due to ARM's "free" rotations, the main tables are only
> 1024 bytes instead of the usual 4096 used by most AES implementations.
>
> On ARM Cortex-A7, the speed loss is only about 5%. The resulting
> implementation is still over twice as fast as aes_ti.c.
>
> Note that even after these changes, the implementation still isn't
> necessarily guaranteed to be constant-time; see
> https://cr.yp.to/antiforgery/cachetiming-20050414.pdf for a discussion
> of the many difficulties involved in writing truly constant-time AES
> software. But it's valuable to make such attacks more difficult.
>
> Suggested-by: Ard Biesheuvel
> Signed-off-by: Eric Biggers
> ---
> arch/arm/crypto/aes-cipher-core.S | 26 ++
> arch/arm/crypto/aes-cipher-glue.c | 13 +
> crypto/aes_generic.c | 9 +
> 3 files changed, 44 insertions(+), 4 deletions(-)
>
> diff --git a/arch/arm/crypto/aes-cipher-core.S
> b/arch/arm/crypto/aes-cipher-core.S
> index 184d6c2d15d5..ba9d4aefe585 100644
> --- a/arch/arm/crypto/aes-cipher-core.S
> +++ b/arch/arm/crypto/aes-cipher-core.S
> @@ -138,6 +138,23 @@
> eor r7, r7, r11
>
> __adrl ttab, \ttab
> + /*
> +* Prefetch the 1024-byte 'ft' or 'it' table into L1 cache, assuming
> +* cacheline size >= 32. This, along with the caller disabling
> +* interrupts, is a hardening measure intended to make cache-timing
> +* attacks more difficult. They may not be fully prevented, however;
> +* see the paper https://cr.yp.to/antiforgery/cachetiming-20050414.pdf
> +* ("Cache-timing attacks on AES") for a discussion of the many
> +* difficulties involved in writing truly constant-time AES software.
> +*/
> + .set i, 0
> +.rept 1024 / 128
> + ldr r8, [ttab, #i + 0]
> + ldr r9, [ttab, #i + 32]
> + ldr r10, [ttab, #i + 64]
> + ldr r11, [ttab, #i + 96]
> + .set i, i + 128
> +.endr
>
Mind sticking a bit more to the coding style of the file? I.e., indent
the gas directives with the code, and putting two tabs after them
> tst rounds, #2
> bne 1f
> @@ -152,6 +169,15 @@
> b 0b
>
> 2: __adrl ttab, \ltab
> +.if \bsz == 0
> + /* Prefetch the 256-byte inverse S-box; see explanation above */
> + .set i, 0
> +.rept 256 / 64
> + ldr t0, [ttab, #i + 0]
> + ldr t1, [ttab, #i + 32]
> + .set i, i + 64
> +.endr
> +.endif
> \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b
>
> #ifdef CONFIG_CPU_BIG_ENDIAN
> diff --git a/arch/arm/crypto/aes-cipher-glue.c
> b/arch/arm/crypto/aes-cipher-glue.c
> index c222f6e072ad..f40e35eb22e4 100644
> --- a/arch/arm/crypto/aes-cipher-glue.c
> +++ b/arch/arm/crypto/aes-cipher-glue.c
> @@ -23,16 +23,29 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out,
> const u8 *in)
> {
> struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
> int rounds = 6 + ctx->key_length / 4;
> + unsigned long flags;
>
> + /*
> +* This AES implementation prefetches the lookup table into L1 cache
> to
> +* try to make timing attacks on the table lookups more difficult.
> +* Temporarily disable interrupts to avoid races where cachelines are
> +* evicted when the CPU is interrupted to do something else.
> +*/
> + local_irq_save(flags);
> __aes_arm_encrypt(ctx->key_enc, rounds, in, out);
> + local_irq_restore(flags);
> }
>
Disabling interrupts like that is going to raise some eyebrows, so I'd
prefer it if we can reduce the scope of the IRQ blackout as much as we
can. This means we should move the IRQ en/disable into the .S file,
and only let it cover the parts of the code where we are actually
doing table lookups that are indexed by the input.
> static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
> {
> struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
> int rounds = 6 + ctx->key_length / 4;
> + unsigned long flags;
>
> + /* Disable interrupts to help mitigate timing attacks, see above */
> + local_irq_save(flags);
> __aes_arm_decrypt(ctx->key_dec, rounds, in, out);
> + local_irq_restore(flags);
> }
>
> static struct crypto_alg aes_alg = {
> diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
> index ca554d57d01e..13df33aca463 100644
> --- a/crypto/aes_generic.c
> +++ b/crypto/aes_generic.c
> @@ -63,7 +63,8 @@ static inline u8 byte(const u32 x, const unsigned n)
>
> static const u32 rco_tab[10] = { 1, 2, 4,
[PATCH v2 2/2] crypto: arm/aes - add some hardening against cache-timing attacks
From: Eric Biggers
Make the ARM scalar AES implementation closer to constant-time by
disabling interrupts and prefetching the tables into L1 cache. This is
feasible because due to ARM's "free" rotations, the main tables are only
1024 bytes instead of the usual 4096 used by most AES implementations.
On ARM Cortex-A7, the speed loss is only about 5%. The resulting
implementation is still over twice as fast as aes_ti.c.
Note that even after these changes, the implementation still isn't
necessarily guaranteed to be constant-time; see
https://cr.yp.to/antiforgery/cachetiming-20050414.pdf for a discussion
of the many difficulties involved in writing truly constant-time AES
software. But it's valuable to make such attacks more difficult.
Suggested-by: Ard Biesheuvel
Signed-off-by: Eric Biggers
---
arch/arm/crypto/aes-cipher-core.S | 26 ++
arch/arm/crypto/aes-cipher-glue.c | 13 +
crypto/aes_generic.c | 9 +
3 files changed, 44 insertions(+), 4 deletions(-)
diff --git a/arch/arm/crypto/aes-cipher-core.S
b/arch/arm/crypto/aes-cipher-core.S
index 184d6c2d15d5..ba9d4aefe585 100644
--- a/arch/arm/crypto/aes-cipher-core.S
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -138,6 +138,23 @@
eor r7, r7, r11
__adrl ttab, \ttab
+ /*
+* Prefetch the 1024-byte 'ft' or 'it' table into L1 cache, assuming
+* cacheline size >= 32. This, along with the caller disabling
+* interrupts, is a hardening measure intended to make cache-timing
+* attacks more difficult. They may not be fully prevented, however;
+* see the paper https://cr.yp.to/antiforgery/cachetiming-20050414.pdf
+* ("Cache-timing attacks on AES") for a discussion of the many
+* difficulties involved in writing truly constant-time AES software.
+*/
+ .set i, 0
+.rept 1024 / 128
+ ldr r8, [ttab, #i + 0]
+ ldr r9, [ttab, #i + 32]
+ ldr r10, [ttab, #i + 64]
+ ldr r11, [ttab, #i + 96]
+ .set i, i + 128
+.endr
tst rounds, #2
bne 1f
@@ -152,6 +169,15 @@
b 0b
2: __adrl ttab, \ltab
+.if \bsz == 0
+ /* Prefetch the 256-byte inverse S-box; see explanation above */
+ .set i, 0
+.rept 256 / 64
+ ldr t0, [ttab, #i + 0]
+ ldr t1, [ttab, #i + 32]
+ .set i, i + 64
+.endr
+.endif
\round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b
#ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arm/crypto/aes-cipher-glue.c
b/arch/arm/crypto/aes-cipher-glue.c
index c222f6e072ad..f40e35eb22e4 100644
--- a/arch/arm/crypto/aes-cipher-glue.c
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -23,16 +23,29 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out,
const u8 *in)
{
struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
int rounds = 6 + ctx->key_length / 4;
+ unsigned long flags;
+ /*
+* This AES implementation prefetches the lookup table into L1 cache to
+* try to make timing attacks on the table lookups more difficult.
+* Temporarily disable interrupts to avoid races where cachelines are
+* evicted when the CPU is interrupted to do something else.
+*/
+ local_irq_save(flags);
__aes_arm_encrypt(ctx->key_enc, rounds, in, out);
+ local_irq_restore(flags);
}
static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
int rounds = 6 + ctx->key_length / 4;
+ unsigned long flags;
+ /* Disable interrupts to help mitigate timing attacks, see above */
+ local_irq_save(flags);
__aes_arm_decrypt(ctx->key_dec, rounds, in, out);
+ local_irq_restore(flags);
}
static struct crypto_alg aes_alg = {
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index ca554d57d01e..13df33aca463 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -63,7 +63,8 @@ static inline u8 byte(const u32 x, const unsigned n)
static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 };
-__visible const u32 crypto_ft_tab[4][256] = {
+/* cacheline-aligned to facilitate prefetching into cache */
+__visible const u32 crypto_ft_tab[4][256] __cacheline_aligned = {
{
0xa56363c6, 0x847c7cf8, 0x99ee, 0x8d7b7bf6,
0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591,
@@ -327,7 +328,7 @@ __visible const u32 crypto_ft_tab[4][256] = {
}
};
-__visible const u32 crypto_fl_tab[4][256] = {
+__visible const u32 crypto_fl_tab[4][256] __cacheline_aligned = {
{
0x0063, 0x007c, 0x0077, 0x007b,
0x00f2, 0x006b, 0x006f, 0x00c5,
@@ -591,7 +592,7 @@ __visible const u32 crypto_fl_tab[4][256] = {
}
};
