Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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
Message-Id: <20221103042740.6556-18-elliott@hpe.com>
In-Reply-To: <20221103042740.6556-1-elliott@hpe.com>
References: <20221012215931.3896-1-elliott@hpe.com>
 <20221103042740.6556-1-elliott@hpe.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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