All of lore.kernel.org
 help / color / mirror / Atom feed
From: Robert Elliott <elliott@hpe.com>
To: herbert@gondor.apana.org.au, davem@davemloft.net,
	tim.c.chen@linux.intel.com, ap420073@gmail.com, ardb@kernel.org,
	Jason@zx2c4.com, David.Laight@ACULAB.COM, ebiggers@kernel.org,
	linux-crypto@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Robert Elliott <elliott@hpe.com>
Subject: [PATCH v3 17/17] crypto: x86/nhpoly1305, poly1305 - load based on CPU features
Date: Wed,  2 Nov 2022 23:27:40 -0500	[thread overview]
Message-ID: <20221103042740.6556-18-elliott@hpe.com> (raw)
In-Reply-To: <20221103042740.6556-1-elliott@hpe.com>

Like commit aa031b8f702e ("crypto: x86/sha512 - load based on CPU
features"), add module aliases for x86-optimized crypto modules:
    nhpoly1305, poly1305
based on CPU feature bits so udev gets a chance to load them later
in the boot process when the filesystems are all running.

Signed-off-by: Robert Elliott <elliott@hpe.com>
---
 arch/x86/crypto/nhpoly1305-avx2-glue.c | 10 ++++++++++
 arch/x86/crypto/nhpoly1305-sse2-glue.c | 10 ++++++++++
 arch/x86/crypto/poly1305_glue.c        | 12 ++++++++++++
 3 files changed, 32 insertions(+)

diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index f7dc9c563bb5..15f98b53bfda 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -11,6 +11,7 @@
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
+#include <asm/cpu_device_id.h>
 #include <asm/simd.h>
 
 /* avoid kernel_fpu_begin/end scheduler/rcu stalls */
@@ -60,8 +61,17 @@ static struct shash_alg nhpoly1305_alg = {
 	.descsize		= sizeof(struct nhpoly1305_state),
 };
 
+static const struct x86_cpu_id module_cpu_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
+
 static int __init nhpoly1305_mod_init(void)
 {
+	if (!x86_match_cpu(module_cpu_ids))
+		return -ENODEV;
+
 	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
 	    !boot_cpu_has(X86_FEATURE_OSXSAVE))
 		return -ENODEV;
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index daffcc7019ad..533db3e0e06f 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -11,6 +11,7 @@
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
+#include <asm/cpu_device_id.h>
 #include <asm/simd.h>
 
 /* avoid kernel_fpu_begin/end scheduler/rcu stalls */
@@ -60,8 +61,17 @@ static struct shash_alg nhpoly1305_alg = {
 	.descsize		= sizeof(struct nhpoly1305_state),
 };
 
+static const struct x86_cpu_id module_cpu_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_XMM2, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
+
 static int __init nhpoly1305_mod_init(void)
 {
+	if (!x86_match_cpu(module_cpu_ids))
+		return -ENODEV;
+
 	if (!boot_cpu_has(X86_FEATURE_XMM2))
 		return -ENODEV;
 
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 16831c036d71..2ff4358e4b3f 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
+#include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/simd.h>
 
@@ -268,8 +269,19 @@ static struct shash_alg alg = {
 	},
 };
 
+static const struct x86_cpu_id module_cpu_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
+	X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
+	X86_MATCH_FEATURE(X86_FEATURE_AVX512F, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
+
 static int __init poly1305_simd_mod_init(void)
 {
+	if (!x86_match_cpu(module_cpu_ids))
+		return -ENODEV;
+
 	if (boot_cpu_has(X86_FEATURE_AVX) &&
 	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		static_branch_enable(&poly1305_use_avx);
-- 
2.37.3


  parent reply	other threads:[~2022-11-03  4:30 UTC|newest]

Thread overview: 127+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-06 22:31 [RFC PATCH 0/7] crypto: x86 - fix RCU stalls Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 1/7] rcu: correct CONFIG_EXT_RCU_CPU_STALL_TIMEOUT descriptions Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 2/7] crypto: x86/sha - limit FPU preemption Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 3/7] crypto: x86/crc " Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 4/7] crypto: x86/sm3 " Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 5/7] crypto: x86/ghash - restructure FPU context saving Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 6/7] crypto: x86/ghash - limit FPU preemption Robert Elliott
2022-10-06 22:31 ` [RFC PATCH 7/7] crypto: x86 - use common macro for FPU limit Robert Elliott
2022-10-12 21:59 ` [PATCH v2 00/19] crypto: x86 - fix RCU stalls Robert Elliott
2022-10-12 21:59   ` [PATCH v2 01/19] crypto: tcrypt - test crc32 Robert Elliott
2022-10-12 21:59   ` [PATCH v2 02/19] crypto: tcrypt - test nhpoly1305 Robert Elliott
2022-10-12 21:59   ` [PATCH v2 03/19] crypto: tcrypt - reschedule during cycles speed tests Robert Elliott
2022-10-12 21:59   ` [PATCH v2 04/19] crypto: x86/sha - limit FPU preemption Robert Elliott
2022-10-13  0:41     ` Jason A. Donenfeld
2022-10-13 21:50       ` Elliott, Robert (Servers)
2022-10-14 11:01       ` David Laight
2022-10-13  5:57     ` Eric Biggers
2022-10-13  6:04       ` Herbert Xu
2022-10-13  6:08         ` Eric Biggers
2022-10-13  7:50           ` Herbert Xu
2022-10-13 22:41       ` :Re: " Elliott, Robert (Servers)
2022-10-12 21:59   ` [PATCH v2 05/19] crypto: x86/crc " Robert Elliott
2022-10-13  2:00     ` Herbert Xu
2022-10-13 22:34       ` Elliott, Robert (Servers)
2022-10-14  4:02     ` David Laight
2022-10-24  2:03     ` kernel test robot
2022-10-24  2:03       ` [LTP] " kernel test robot
2022-10-12 21:59   ` [PATCH v2 06/19] crypto: x86/sm3 " Robert Elliott
2022-10-12 21:59   ` [PATCH v2 07/19] crypto: x86/ghash - restructure FPU context saving Robert Elliott
2022-10-12 21:59   ` [PATCH v2 08/19] crypto: x86/ghash - limit FPU preemption Robert Elliott
2022-10-13  6:03     ` Eric Biggers
2022-10-13 22:52       ` Elliott, Robert (Servers)
2022-10-12 21:59   ` [PATCH v2 09/19] crypto: x86 - use common macro for FPU limit Robert Elliott
2022-10-13  0:35     ` Jason A. Donenfeld
2022-10-13 21:48       ` Elliott, Robert (Servers)
2022-10-14  1:26         ` Jason A. Donenfeld
2022-10-18  0:06           ` Elliott, Robert (Servers)
2022-10-12 21:59   ` [PATCH v2 10/19] crypto: x86/sha1, sha256 - load based on CPU features Robert Elliott
2022-10-12 21:59   ` [PATCH v2 11/19] crypto: x86/crc " Robert Elliott
2022-10-12 21:59   ` [PATCH v2 12/19] crypto: x86/sm3 " Robert Elliott
2022-10-12 21:59   ` [PATCH v2 13/19] crypto: x86/ghash " Robert Elliott
2022-10-12 21:59   ` [PATCH v2 14/19] crypto: x86 " Robert Elliott
2022-10-14 14:26     ` Elliott, Robert (Servers)
2022-10-12 21:59   ` [PATCH v2 15/19] crypto: x86 - add pr_fmt to all modules Robert Elliott
2022-10-12 21:59   ` [PATCH v2 16/19] crypto: x86 - print CPU optimized loaded messages Robert Elliott
2022-10-13  0:40     ` Jason A. Donenfeld
2022-10-13 13:47     ` kernel test robot
2022-10-13 13:48     ` kernel test robot
2022-10-12 21:59   ` [PATCH v2 17/19] crypto: x86 - standardize suboptimal prints Robert Elliott
2022-10-13  0:38     ` Jason A. Donenfeld
2022-10-12 21:59   ` [PATCH v2 18/19] crypto: x86 - standardize not loaded prints Robert Elliott
2022-10-13  0:42     ` Jason A. Donenfeld
2022-10-13 22:20       ` Elliott, Robert (Servers)
2022-11-10 22:06         ` Elliott, Robert (Servers)
2022-10-12 21:59   ` [PATCH v2 19/19] crypto: x86/sha - register only the best function Robert Elliott
2022-10-13  6:07     ` Eric Biggers
2022-10-13  7:52       ` Herbert Xu
2022-10-13 22:59         ` Elliott, Robert (Servers)
2022-10-14  8:22           ` Herbert Xu
2022-11-01 21:34   ` [PATCH v2 00/19] crypto: x86 - fix RCU stalls Elliott, Robert (Servers)
2022-11-03  4:27   ` [PATCH v3 00/17] crypt: " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 01/17] crypto: tcrypt - test crc32 Robert Elliott
2022-11-03  4:27     ` [PATCH v3 02/17] crypto: tcrypt - test nhpoly1305 Robert Elliott
2022-11-03  4:27     ` [PATCH v3 03/17] crypto: tcrypt - reschedule during cycles speed tests Robert Elliott
2022-11-03  4:27     ` [PATCH v3 04/17] crypto: x86/sha - limit FPU preemption Robert Elliott
2022-11-03  4:27     ` [PATCH v3 05/17] crypto: x86/crc " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 06/17] crypto: x86/sm3 " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 07/17] crypto: x86/ghash - use u8 rather than char Robert Elliott
2022-11-03  4:27     ` [PATCH v3 08/17] crypto: x86/ghash - restructure FPU context saving Robert Elliott
2022-11-03  4:27     ` [PATCH v3 09/17] crypto: x86/ghash - limit FPU preemption Robert Elliott
2022-11-03  4:27     ` [PATCH v3 10/17] crypto: x86/*poly* " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 11/17] crypto: x86/sha - register all variations Robert Elliott
2022-11-03  9:26       ` kernel test robot
2022-11-03  4:27     ` [PATCH v3 12/17] crypto: x86/sha - minimize time in FPU context Robert Elliott
2022-11-03  4:27     ` [PATCH v3 13/17] crypto: x86/sha1, sha256 - load based on CPU features Robert Elliott
2022-11-03  4:27     ` [PATCH v3 14/17] crypto: x86/crc " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 15/17] crypto: x86/sm3 " Robert Elliott
2022-11-03  4:27     ` [PATCH v3 16/17] crypto: x86/ghash,polyval " Robert Elliott
2022-11-03  4:27     ` Robert Elliott [this message]
2022-11-16  4:13     ` [PATCH v4 00/24] crypto: fix RCU stalls Robert Elliott
2022-11-16  4:13       ` [PATCH v4 01/24] crypto: tcrypt - test crc32 Robert Elliott
2022-11-16  4:13       ` [PATCH v4 02/24] crypto: tcrypt - test nhpoly1305 Robert Elliott
2022-11-16  4:13       ` [PATCH v4 03/24] crypto: tcrypt - reschedule during cycles speed tests Robert Elliott
2022-11-16  4:13       ` [PATCH v4 04/24] crypto: x86/sha - limit FPU preemption Robert Elliott
2022-11-16  4:13       ` [PATCH v4 05/24] crypto: x86/crc " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 06/24] crypto: x86/sm3 " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 07/24] crypto: x86/ghash - use u8 rather than char Robert Elliott
2022-11-16  4:13       ` [PATCH v4 08/24] crypto: x86/ghash - restructure FPU context saving Robert Elliott
2022-11-16  4:13       ` [PATCH v4 09/24] crypto: x86/ghash - limit FPU preemption Robert Elliott
2022-11-16  4:13       ` [PATCH v4 10/24] crypto: x86/poly " Robert Elliott
2022-11-16 11:13         ` Jason A. Donenfeld
2022-11-22  5:06           ` Elliott, Robert (Servers)
2022-11-22  9:07             ` David Laight
2022-11-25  8:40           ` Herbert Xu
2022-11-25  8:59             ` Ard Biesheuvel
2022-11-25  9:03               ` Herbert Xu
2022-11-28 16:57                 ` Elliott, Robert (Servers)
2022-11-28 18:48                   ` Elliott, Robert (Servers)
2022-12-02  6:21             ` Elliott, Robert (Servers)
2022-12-02  9:25               ` Herbert Xu
2022-12-02 16:15                 ` Elliott, Robert (Servers)
2022-12-06  4:27                   ` Herbert Xu
2022-12-06 14:03                     ` Peter Lafreniere
2022-12-06 14:44                       ` David Laight
2022-12-06 23:06               ` Peter Lafreniere
2022-12-10  0:34                 ` Elliott, Robert (Servers)
2022-12-16 22:12                   ` Elliott, Robert (Servers)
2022-11-16  4:13       ` [PATCH v4 11/24] crypto: x86/aegis " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 12/24] crypto: x86/sha - register all variations Robert Elliott
2022-11-16  4:13       ` [PATCH v4 13/24] crypto: x86/sha - minimize time in FPU context Robert Elliott
2022-11-16  4:13       ` [PATCH v4 14/24] crypto: x86/sha - load based on CPU features Robert Elliott
2022-11-16  4:13       ` [PATCH v4 15/24] crypto: x86/crc " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 16/24] crypto: x86/sm3 " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 17/24] crypto: x86/poly " Robert Elliott
2022-11-16 11:19         ` Jason A. Donenfeld
2022-11-16  4:13       ` [PATCH v4 18/24] crypto: x86/ghash " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 19/24] crypto: x86/aesni - avoid type conversions Robert Elliott
2022-11-16  4:13       ` [PATCH v4 20/24] crypto: x86/ciphers - load based on CPU features Robert Elliott
2022-11-16 11:30         ` Jason A. Donenfeld
2022-11-16  4:13       ` [PATCH v4 21/24] crypto: x86 - report used CPU features via module parameters Robert Elliott
2022-11-16 11:26         ` Jason A. Donenfeld
2022-11-16  4:13       ` [PATCH v4 22/24] crypto: x86 - report missing " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 23/24] crypto: x86 - report suboptimal CPUs " Robert Elliott
2022-11-16  4:13       ` [PATCH v4 24/24] crypto: x86 - standarize module descriptions Robert Elliott
2022-11-17  3:58       ` [PATCH v4 00/24] crypto: fix RCU stalls Herbert Xu
2022-11-17 15:13         ` Elliott, Robert (Servers)
2022-11-17 15:15           ` Jason A. Donenfeld

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221103042740.6556-18-elliott@hpe.com \
    --to=elliott@hpe.com \
    --cc=David.Laight@ACULAB.COM \
    --cc=Jason@zx2c4.com \
    --cc=ap420073@gmail.com \
    --cc=ardb@kernel.org \
    --cc=davem@davemloft.net \
    --cc=ebiggers@kernel.org \
    --cc=herbert@gondor.apana.org.au \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tim.c.chen@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.