lkml.org 
[lkml]   [2022]   [Nov]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v4 13/24] crypto: x86/sha - minimize time in FPU context
Date
Narrow the kernel_fpu_begin()/kernel_fpu_end() to just wrap the
assembly functions, not any extra C code around them (which includes
several memcpy() calls).

This reduces unnecessary time in FPU context, in which the scheduler
is prevented from preempting and the RCU subsystem is kept from
doing its work.

Example results measuring a boot, in which SHA-512 is used to check all
module signatures using finup() calls:

Before:
calls maxcycles bpf update finup algorithm module
======== ============ ======== ======== ======== =========== ==============
168390 1233188 19456 0 19456 sha512-avx2 sha512_ssse3

After:
182694 1007224 19456 0 19456 sha512-avx2 sha512_ssse3

That means it stayed in FPU context for 226k fewer clocks cycles (which
is 102 microseconds on this system, 18% less).

Signed-off-by: Robert Elliott <elliott@hpe.com>
---
arch/x86/crypto/sha1_ssse3_glue.c | 82 ++++++++++++++++++++---------
arch/x86/crypto/sha256_ssse3_glue.c | 67 ++++++++++++++++++-----
arch/x86/crypto/sha512_ssse3_glue.c | 48 ++++++++++++-----
3 files changed, 145 insertions(+), 52 deletions(-)

diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index e75a1060bb5f..32f3310e19e2 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -34,6 +34,54 @@ static const unsigned int bytes_per_fpu_avx2 = 34 * 1024;
static const unsigned int bytes_per_fpu_avx = 30 * 1024;
static const unsigned int bytes_per_fpu_ssse3 = 26 * 1024;

+asmlinkage void sha1_transform_ssse3(struct sha1_state *state,
+ const u8 *data, int blocks);
+
+asmlinkage void sha1_transform_avx(struct sha1_state *state,
+ const u8 *data, int blocks);
+
+asmlinkage void sha1_transform_avx2(struct sha1_state *state,
+ const u8 *data, int blocks);
+
+#ifdef CONFIG_AS_SHA1_NI
+asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data,
+ int rounds);
+#endif
+
+static void fpu_sha1_transform_ssse3(struct sha1_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha1_transform_ssse3(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha1_transform_avx(struct sha1_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha1_transform_avx(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha1_transform_avx2(struct sha1_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha1_transform_avx2(state, data, blocks);
+ kernel_fpu_end();
+}
+
+#ifdef CONFIG_AS_SHA1_NI
+static void fpu_sha1_transform_shani(struct sha1_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha1_ni_transform(state, data, blocks);
+ kernel_fpu_end();
+}
+#endif
+
static int using_x86_ssse3;
static int using_x86_avx;
static int using_x86_avx2;
@@ -60,9 +108,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha1_base_do_update(desc, data, chunk, sha1_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
@@ -81,36 +127,29 @@ static int sha1_finup(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha1_base_do_update(desc, data, chunk, sha1_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
}

- kernel_fpu_begin();
sha1_base_do_finalize(desc, sha1_xform);
- kernel_fpu_end();

return sha1_base_finish(desc, out);
}

-asmlinkage void sha1_transform_ssse3(struct sha1_state *state,
- const u8 *data, int blocks);
-
static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, bytes_per_fpu_ssse3,
- sha1_transform_ssse3);
+ fpu_sha1_transform_ssse3);
}

static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, bytes_per_fpu_ssse3, out,
- sha1_transform_ssse3);
+ fpu_sha1_transform_ssse3);
}

/* Add padding and return the message digest. */
@@ -143,21 +182,18 @@ static void unregister_sha1_ssse3(void)
}
}

-asmlinkage void sha1_transform_avx(struct sha1_state *state,
- const u8 *data, int blocks);
-
static int sha1_avx_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, bytes_per_fpu_avx,
- sha1_transform_avx);
+ fpu_sha1_transform_avx);
}

static int sha1_avx_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, bytes_per_fpu_avx, out,
- sha1_transform_avx);
+ fpu_sha1_transform_avx);
}

static int sha1_avx_final(struct shash_desc *desc, u8 *out)
@@ -191,17 +227,14 @@ static void unregister_sha1_avx(void)

#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */

-asmlinkage void sha1_transform_avx2(struct sha1_state *state,
- const u8 *data, int blocks);
-
static void sha1_apply_transform_avx2(struct sha1_state *state,
const u8 *data, int blocks)
{
/* Select the optimal transform based on data block size */
if (blocks >= SHA1_AVX2_BLOCK_OPTSIZE)
- sha1_transform_avx2(state, data, blocks);
+ fpu_sha1_transform_avx2(state, data, blocks);
else
- sha1_transform_avx(state, data, blocks);
+ fpu_sha1_transform_avx(state, data, blocks);
}

static int sha1_avx2_update(struct shash_desc *desc, const u8 *data,
@@ -248,21 +281,18 @@ static void unregister_sha1_avx2(void)
}

#ifdef CONFIG_AS_SHA1_NI
-asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data,
- int rounds);
-
static int sha1_ni_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, bytes_per_fpu_shani,
- sha1_ni_transform);
+ fpu_sha1_transform_shani);
}

static int sha1_ni_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, bytes_per_fpu_shani, out,
- sha1_ni_transform);
+ fpu_sha1_transform_shani);
}

static int sha1_ni_final(struct shash_desc *desc, u8 *out)
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index c6261ede4bae..839da1b36273 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -51,6 +51,51 @@ static const unsigned int bytes_per_fpu_ssse3 = 11 * 1024;
asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
const u8 *data, int blocks);

+asmlinkage void sha256_transform_avx(struct sha256_state *state,
+ const u8 *data, int blocks);
+
+asmlinkage void sha256_transform_rorx(struct sha256_state *state,
+ const u8 *data, int blocks);
+
+#ifdef CONFIG_AS_SHA256_NI
+asmlinkage void sha256_ni_transform(struct sha256_state *digest,
+ const u8 *data, int rounds);
+#endif
+
+static void fpu_sha256_transform_ssse3(struct sha256_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha256_transform_ssse3(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha256_transform_avx(struct sha256_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha256_transform_avx(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha256_transform_avx2(struct sha256_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha256_transform_rorx(state, data, blocks);
+ kernel_fpu_end();
+}
+
+#ifdef CONFIG_AS_SHA1_NI
+static void fpu_sha256_transform_shani(struct sha256_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha256_ni_transform(state, data, blocks);
+ kernel_fpu_end();
+}
+#endif
+
static int using_x86_ssse3;
static int using_x86_avx;
static int using_x86_avx2;
@@ -77,9 +122,7 @@ static int _sha256_update(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha256_base_do_update(desc, data, chunk, sha256_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
@@ -98,17 +141,13 @@ static int sha256_finup(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha256_base_do_update(desc, data, chunk, sha256_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
}

- kernel_fpu_begin();
sha256_base_do_finalize(desc, sha256_xform);
- kernel_fpu_end();

return sha256_base_finish(desc, out);
}
@@ -117,14 +156,14 @@ static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return _sha256_update(desc, data, len, bytes_per_fpu_ssse3,
- sha256_transform_ssse3);
+ fpu_sha256_transform_ssse3);
}

static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha256_finup(desc, data, len, bytes_per_fpu_ssse3,
- out, sha256_transform_ssse3);
+ out, fpu_sha256_transform_ssse3);
}

/* Add padding and return the message digest. */
@@ -179,14 +218,14 @@ static int sha256_avx_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return _sha256_update(desc, data, len, bytes_per_fpu_avx,
- sha256_transform_avx);
+ fpu_sha256_transform_avx);
}

static int sha256_avx_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha256_finup(desc, data, len, bytes_per_fpu_avx,
- out, sha256_transform_avx);
+ out, fpu_sha256_transform_avx);
}

static int sha256_avx_final(struct shash_desc *desc, u8 *out)
@@ -240,14 +279,14 @@ static int sha256_avx2_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return _sha256_update(desc, data, len, bytes_per_fpu_avx2,
- sha256_transform_rorx);
+ fpu_sha256_transform_avx2);
}

static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha256_finup(desc, data, len, bytes_per_fpu_avx2,
- out, sha256_transform_rorx);
+ out, fpu_sha256_transform_avx2);
}

static int sha256_avx2_final(struct shash_desc *desc, u8 *out)
@@ -302,14 +341,14 @@ static int sha256_ni_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return _sha256_update(desc, data, len, bytes_per_fpu_shani,
- sha256_ni_transform);
+ fpu_sha256_transform_shani);
}

static int sha256_ni_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha256_finup(desc, data, len, bytes_per_fpu_shani,
- out, sha256_ni_transform);
+ out, fpu_sha256_transform_shani);
}

static int sha256_ni_final(struct shash_desc *desc, u8 *out)
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index feae85933270..48586ab40d55 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -47,6 +47,36 @@ static const unsigned int bytes_per_fpu_ssse3 = 17 * 1024;
asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
const u8 *data, int blocks);

+asmlinkage void sha512_transform_avx(struct sha512_state *state,
+ const u8 *data, int blocks);
+
+asmlinkage void sha512_transform_rorx(struct sha512_state *state,
+ const u8 *data, int blocks);
+
+static void fpu_sha512_transform_ssse3(struct sha512_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha512_transform_ssse3(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha512_transform_avx(struct sha512_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha512_transform_avx(state, data, blocks);
+ kernel_fpu_end();
+}
+
+static void fpu_sha512_transform_avx2(struct sha512_state *state,
+ const u8 *data, int blocks)
+{
+ kernel_fpu_begin();
+ sha512_transform_rorx(state, data, blocks);
+ kernel_fpu_end();
+}
+
static int using_x86_ssse3;
static int using_x86_avx;
static int using_x86_avx2;
@@ -70,9 +100,7 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha512_base_do_update(desc, data, chunk, sha512_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
@@ -91,17 +119,13 @@ static int sha512_finup(struct shash_desc *desc, const u8 *data,
while (len) {
unsigned int chunk = min(len, bytes_per_fpu);

- kernel_fpu_begin();
sha512_base_do_update(desc, data, chunk, sha512_xform);
- kernel_fpu_end();

len -= chunk;
data += chunk;
}

- kernel_fpu_begin();
sha512_base_do_finalize(desc, sha512_xform);
- kernel_fpu_end();

return sha512_base_finish(desc, out);
}
@@ -110,14 +134,14 @@ static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha512_update(desc, data, len, bytes_per_fpu_ssse3,
- sha512_transform_ssse3);
+ fpu_sha512_transform_ssse3);
}

static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha512_finup(desc, data, len, bytes_per_fpu_ssse3,
- out, sha512_transform_ssse3);
+ out, fpu_sha512_transform_ssse3);
}

/* Add padding and return the message digest. */
@@ -172,14 +196,14 @@ static int sha512_avx_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha512_update(desc, data, len, bytes_per_fpu_avx,
- sha512_transform_avx);
+ fpu_sha512_transform_avx);
}

static int sha512_avx_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha512_finup(desc, data, len, bytes_per_fpu_avx,
- out, sha512_transform_avx);
+ out, fpu_sha512_transform_avx);
}

/* Add padding and return the message digest. */
@@ -234,14 +258,14 @@ static int sha512_avx2_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha512_update(desc, data, len, bytes_per_fpu_avx2,
- sha512_transform_rorx);
+ fpu_sha512_transform_avx2);
}

static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha512_finup(desc, data, len, bytes_per_fpu_avx2,
- out, sha512_transform_rorx);
+ out, fpu_sha512_transform_avx2);
}

/* Add padding and return the message digest. */
--
2.38.1
\
 
 \ /
  Last update: 2022-11-16 05:16    [W:0.771 / U:0.944 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site