[PATCH v2 04/19] crypto: x86/sha - limit FPU preemption
From: Robert Elliott
Date: Wed Oct 12 2022 - 18:04:38 EST
As done by the ECB and CBC helpers in arch/x86/crypt/ecb_cbc_helpers.h,
limit the number of bytes processed between kernel_fpu_begin() and
kernel_fpu_end() calls.
Those functions call preempt_disable() and preempt_enable(), so
the CPU core is unavailable for scheduling while running.
This leads to "rcu_preempt detected expedited stalls" with stack dumps
pointing to the optimized hash function if the module is loaded and
used a lot:
rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: ...
For example, that can occur during boot with the stack track pointing
to the sha512-x86 function if the system set to use SHA-512 for
module signing. The call trace includes:
module_sig_check
mod_verify_sig
pkcs7_verify
pkcs7_digest
sha512_finup
sha512_base_do_update
Fixes: 66be89515888 ("crypto: sha1 - SSSE3 based SHA1 implementation for x86-64")
Fixes: 8275d1aa6422 ("crypto: sha256 - Create module providing optimized SHA256 routines using SSSE3, AVX or AVX2 instructions.")
Fixes: 87de4579f92d ("crypto: sha512 - Create module providing optimized SHA512 routines using SSSE3, AVX or AVX2 instructions.")
Fixes: aa031b8f702e ("crypto: x86/sha512 - load based on CPU features")
Suggested-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Robert Elliott <elliott@xxxxxxx>
---
arch/x86/crypto/sha1_ssse3_glue.c | 32 ++++++++++++++++++++++++-----
arch/x86/crypto/sha256_ssse3_glue.c | 32 ++++++++++++++++++++++++-----
arch/x86/crypto/sha512_ssse3_glue.c | 32 ++++++++++++++++++++++++-----
3 files changed, 81 insertions(+), 15 deletions(-)
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 44340a1139e0..a9f5779b41ca 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -26,6 +26,8 @@
#include <crypto/sha1_base.h>
#include <asm/simd.h>
+#define FPU_BYTES 4096U /* avoid kernel_fpu_begin/end scheduler/rcu stalls */
+
static int sha1_update(struct shash_desc *desc, const u8 *data,
unsigned int len, sha1_block_fn *sha1_xform)
{
@@ -41,9 +43,18 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
*/
BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
- kernel_fpu_begin();
- sha1_base_do_update(desc, data, len, sha1_xform);
- kernel_fpu_end();
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha1_base_do_update(desc, data, chunk, sha1_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
return 0;
}
@@ -54,9 +65,20 @@ static int sha1_finup(struct shash_desc *desc, const u8 *data,
if (!crypto_simd_usable())
return crypto_sha1_finup(desc, data, len, out);
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha1_base_do_update(desc, data, chunk, sha1_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
+
kernel_fpu_begin();
- if (len)
- sha1_base_do_update(desc, data, len, sha1_xform);
sha1_base_do_finalize(desc, sha1_xform);
kernel_fpu_end();
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 3a5f6be7dbba..322c8aa907af 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -40,6 +40,8 @@
#include <linux/string.h>
#include <asm/simd.h>
+#define FPU_BYTES 4096U /* avoid kernel_fpu_begin/end scheduler/rcu stalls */
+
asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
const u8 *data, int blocks);
@@ -58,9 +60,18 @@ static int _sha256_update(struct shash_desc *desc, const u8 *data,
*/
BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
- kernel_fpu_begin();
- sha256_base_do_update(desc, data, len, sha256_xform);
- kernel_fpu_end();
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha256_base_do_update(desc, data, chunk, sha256_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
return 0;
}
@@ -71,9 +82,20 @@ static int sha256_finup(struct shash_desc *desc, const u8 *data,
if (!crypto_simd_usable())
return crypto_sha256_finup(desc, data, len, out);
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha256_base_do_update(desc, data, chunk, sha256_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
+
kernel_fpu_begin();
- if (len)
- sha256_base_do_update(desc, data, len, sha256_xform);
sha256_base_do_finalize(desc, sha256_xform);
kernel_fpu_end();
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 6d3b85e53d0e..fd5075a32613 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -39,6 +39,8 @@
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
+#define FPU_BYTES 4096U /* avoid kernel_fpu_begin/end scheduler/rcu stalls */
+
asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
const u8 *data, int blocks);
@@ -57,9 +59,18 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
*/
BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0);
- kernel_fpu_begin();
- sha512_base_do_update(desc, data, len, sha512_xform);
- kernel_fpu_end();
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha512_base_do_update(desc, data, chunk, sha512_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
return 0;
}
@@ -70,9 +81,20 @@ static int sha512_finup(struct shash_desc *desc, const u8 *data,
if (!crypto_simd_usable())
return crypto_sha512_finup(desc, data, len, out);
+ do {
+ unsigned int chunk = min(len, FPU_BYTES);
+
+ if (chunk) {
+ kernel_fpu_begin();
+ sha512_base_do_update(desc, data, chunk, sha512_xform);
+ kernel_fpu_end();
+ }
+
+ len -= chunk;
+ data += chunk;
+ } while (len);
+
kernel_fpu_begin();
- if (len)
- sha512_base_do_update(desc, data, len, sha512_xform);
sha512_base_do_finalize(desc, sha512_xform);
kernel_fpu_end();
--
2.37.3