[PATCH v4 23/24] crypto: x86 - report suboptimal CPUs via module parameters

[Robert Elliott <elliott@hpe.com>]

Don't refuse to load modules on certain CPUs and print a message
to the console. Instead, load the module but don't register the
crypto functions, and report this condition via a new module
suboptimal_x86 module parameter with this description:
	Crypto driver not registered because performance on this CPU would be suboptimal

Reword the descriptions of the existing force module parameter
to match this modified behavior:
	force: Force crypto driver registration on suboptimal CPUs

Make the new module parameters readable via sysfs:
	/sys/module/blowfish_x86_64/parameters/suboptimal_x86:0
	/sys/module/camellia_x86_64/parameters/suboptimal_x86:0
	/sys/module/des3_ede_x86_64/parameters/suboptimal_x86:1
	/sys/module/twofish_x86_64_3way/parameters/suboptimal_x86:1

If the module has been loaded and is reporting suboptimal_x86=1,
remove it to try loading again:
	modprobe -r blowfish_x86_64
	modprobe blowfish_x86_64 force=1

or specify it on the kernel command line:
	blowfish_x86_64.force=1

Signed-off-by: Robert Elliott <elliott@hpe.com>
---
 arch/x86/crypto/blowfish_glue.c     | 29 +++++++++++++++++------------
 arch/x86/crypto/camellia_glue.c     | 27 ++++++++++++++++-----------
 arch/x86/crypto/des3_ede_glue.c     | 26 +++++++++++++++++---------
 arch/x86/crypto/twofish_glue_3way.c | 26 +++++++++++++++-----------
 4 files changed, 65 insertions(+), 43 deletions(-)

diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 4c0ead71b198..8e4de7859e34 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -283,7 +283,7 @@ static struct skcipher_alg bf_skcipher_algs[] = {
 	},
 };
 
-static bool is_blacklisted_cpu(void)
+static bool is_suboptimal_cpu(void)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return false;
@@ -292,7 +292,7 @@ static bool is_blacklisted_cpu(void)
 		/*
 		 * On Pentium 4, blowfish-x86_64 is slower than generic C
 		 * implementation because use of 64bit rotates (which are really
-		 * slow on P4). Therefore blacklist P4s.
+		 * slow on P4).
 		 */
 		return true;
 	}
@@ -302,7 +302,12 @@ static bool is_blacklisted_cpu(void)
 
 static int force;
 module_param(force, int, 0);
-MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+MODULE_PARM_DESC(force, "Force crypto driver registration on suboptimal CPUs");
+
+static int suboptimal_x86;
+module_param(suboptimal_x86, int, 0444);
+MODULE_PARM_DESC(suboptimal_x86,
+		 "Crypto driver not registered because performance on this CPU would be suboptimal");
 
 static const struct x86_cpu_id module_cpu_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_ANY, NULL),
@@ -317,12 +322,9 @@ static int __init blowfish_init(void)
 	if (!x86_match_cpu(module_cpu_ids))
 		return -ENODEV;
 
-	if (!force && is_blacklisted_cpu()) {
-		printk(KERN_INFO
-			"blowfish-x86_64: performance on this CPU "
-			"would be suboptimal: disabling "
-			"blowfish-x86_64.\n");
-		return -ENODEV;
+	if (!force && is_suboptimal_cpu()) {
+		suboptimal_x86 = 1;
+		return 0;
 	}
 
 	err = crypto_register_alg(&bf_cipher_alg);
@@ -339,9 +341,12 @@ static int __init blowfish_init(void)
 
 static void __exit blowfish_fini(void)
 {
-	crypto_unregister_alg(&bf_cipher_alg);
-	crypto_unregister_skciphers(bf_skcipher_algs,
-				    ARRAY_SIZE(bf_skcipher_algs));
+	if (!suboptimal_x86) {
+		crypto_unregister_alg(&bf_cipher_alg);
+		crypto_unregister_skciphers(bf_skcipher_algs,
+					    ARRAY_SIZE(bf_skcipher_algs));
+	}
+	suboptimal_x86 = 0;
 }
 
 module_init(blowfish_init);
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index a3df1043ed73..2cb9b24d9437 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1356,7 +1356,7 @@ static struct skcipher_alg camellia_skcipher_algs[] = {
 	}
 };
 
-static bool is_blacklisted_cpu(void)
+static bool is_suboptimal_cpu(void)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return false;
@@ -1376,7 +1376,12 @@ static bool is_blacklisted_cpu(void)
 
 static int force;
 module_param(force, int, 0);
-MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+MODULE_PARM_DESC(force, "Force crypto driver registration on suboptimal CPUs");
+
+static int suboptimal_x86;
+module_param(suboptimal_x86, int, 0444);
+MODULE_PARM_DESC(suboptimal_x86,
+		 "Crypto driver not registered because performance on this CPU would be suboptimal");
 
 static const struct x86_cpu_id module_cpu_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_ANY, NULL),
@@ -1391,12 +1396,9 @@ static int __init camellia_init(void)
 	if (!x86_match_cpu(module_cpu_ids))
 		return -ENODEV;
 
-	if (!force && is_blacklisted_cpu()) {
-		printk(KERN_INFO
-			"camellia-x86_64: performance on this CPU "
-			"would be suboptimal: disabling "
-			"camellia-x86_64.\n");
-		return -ENODEV;
+	if (!force && is_suboptimal_cpu()) {
+		suboptimal_x86 = 1;
+		return 0;
 	}
 
 	err = crypto_register_alg(&camellia_cipher_alg);
@@ -1413,9 +1415,12 @@ static int __init camellia_init(void)
 
 static void __exit camellia_fini(void)
 {
-	crypto_unregister_alg(&camellia_cipher_alg);
-	crypto_unregister_skciphers(camellia_skcipher_algs,
-				    ARRAY_SIZE(camellia_skcipher_algs));
+	if (!suboptimal_x86) {
+		crypto_unregister_alg(&camellia_cipher_alg);
+		crypto_unregister_skciphers(camellia_skcipher_algs,
+					    ARRAY_SIZE(camellia_skcipher_algs));
+	}
+	suboptimal_x86 = 0;
 }
 
 module_init(camellia_init);
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 168cac5c6ca6..a4cac5129148 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -334,7 +334,7 @@ static struct skcipher_alg des3_ede_skciphers[] = {
 	}
 };
 
-static bool is_blacklisted_cpu(void)
+static bool is_suboptimal_cpu(void)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return false;
@@ -343,7 +343,7 @@ static bool is_blacklisted_cpu(void)
 		/*
 		 * On Pentium 4, des3_ede-x86_64 is slower than generic C
 		 * implementation because use of 64bit rotates (which are really
-		 * slow on P4). Therefore blacklist P4s.
+		 * slow on P4).
 		 */
 		return true;
 	}
@@ -353,7 +353,12 @@ static bool is_blacklisted_cpu(void)
 
 static int force;
 module_param(force, int, 0);
-MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+MODULE_PARM_DESC(force, "Force crypto driver registration on suboptimal CPUs");
+
+static int suboptimal_x86;
+module_param(suboptimal_x86, int, 0444);
+MODULE_PARM_DESC(suboptimal_x86,
+		 "Crypto driver not registered because performance on this CPU would be suboptimal");
 
 static const struct x86_cpu_id module_cpu_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_ANY, NULL),
@@ -368,9 +373,9 @@ static int __init des3_ede_x86_init(void)
 	if (!x86_match_cpu(module_cpu_ids))
 		return -ENODEV;
 
-	if (!force && is_blacklisted_cpu()) {
-		pr_info("des3_ede-x86_64: performance on this CPU would be suboptimal: disabling des3_ede-x86_64.\n");
-		return -ENODEV;
+	if (!force && is_suboptimal_cpu()) {
+		suboptimal_x86 = 1;
+		return 0;
 	}
 
 	err = crypto_register_alg(&des3_ede_cipher);
@@ -387,9 +392,12 @@ static int __init des3_ede_x86_init(void)
 
 static void __exit des3_ede_x86_fini(void)
 {
-	crypto_unregister_alg(&des3_ede_cipher);
-	crypto_unregister_skciphers(des3_ede_skciphers,
-				    ARRAY_SIZE(des3_ede_skciphers));
+	if (!suboptimal_x86) {
+		crypto_unregister_alg(&des3_ede_cipher);
+		crypto_unregister_skciphers(des3_ede_skciphers,
+					    ARRAY_SIZE(des3_ede_skciphers));
+	}
+	suboptimal_x86 = 0;
 }
 
 module_init(des3_ede_x86_init);
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 790e5a59a9a7..8db2f23b3056 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -103,7 +103,7 @@ static struct skcipher_alg tf_skciphers[] = {
 	},
 };
 
-static bool is_blacklisted_cpu(void)
+static bool is_suboptimal_cpu(void)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return false;
@@ -118,8 +118,7 @@ static bool is_blacklisted_cpu(void)
 		 * storing blocks in 64bit registers to allow three blocks to
 		 * be processed parallel. Parallel operation then allows gaining
 		 * more performance than was trade off, on out-of-order CPUs.
-		 * However Atom does not benefit from this parallelism and
-		 * should be blacklisted.
+		 * However Atom does not benefit from this parallelism.
 		 */
 		return true;
 	}
@@ -139,7 +138,12 @@ static bool is_blacklisted_cpu(void)
 
 static int force;
 module_param(force, int, 0);
-MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+MODULE_PARM_DESC(force, "Force crypto driver registration on suboptimal CPUs");
+
+static int suboptimal_x86;
+module_param(suboptimal_x86, int, 0444);
+MODULE_PARM_DESC(suboptimal_x86,
+		 "Crypto driver not registered because performance on this CPU would be suboptimal");
 
 static const struct x86_cpu_id module_cpu_ids[] = {
 	X86_MATCH_FEATURE(X86_FEATURE_ANY, NULL),
@@ -152,12 +156,9 @@ static int __init twofish_3way_init(void)
 	if (!x86_match_cpu(module_cpu_ids))
 		return -ENODEV;
 
-	if (!force && is_blacklisted_cpu()) {
-		printk(KERN_INFO
-			"twofish-x86_64-3way: performance on this CPU "
-			"would be suboptimal: disabling "
-			"twofish-x86_64-3way.\n");
-		return -ENODEV;
+	if (!force && is_suboptimal_cpu()) {
+		suboptimal_x86 = 1;
+		return 0;
 	}
 
 	return crypto_register_skciphers(tf_skciphers,
@@ -166,7 +167,10 @@ static int __init twofish_3way_init(void)
 
 static void __exit twofish_3way_fini(void)
 {
-	crypto_unregister_skciphers(tf_skciphers, ARRAY_SIZE(tf_skciphers));
+	if (!suboptimal_x86)
+		crypto_unregister_skciphers(tf_skciphers, ARRAY_SIZE(tf_skciphers));
+
+	suboptimal_x86 = 0;
 }
 
 module_init(twofish_3way_init);
-- 
2.38.1