summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorJussi Kivilinna <jussi.kivilinna@mbnet.fi>2011-12-20 12:20:16 +0200
committerHerbert Xu <herbert@gondor.apana.org.au>2012-01-13 16:38:39 +1100
commita522ee85ba979e7897a75b1c97db1b0304b68b5c (patch)
tree79e826ab14309f8f291f6eecba929eb4d0e1fba3 /arch
parentf1df57d02a0f83e764b4dc9187f58665d70f190e (diff)
downloadlinux-a522ee85ba979e7897a75b1c97db1b0304b68b5c.tar.bz2
crypto: twofish-x86_64-3way - blacklist pentium4 and atom
Performance of twofish-x86_64-3way on Intel Pentium 4 and Atom is lower than of twofish-x86_64 module. So blacklist these CPUs. Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c47
1 files changed, 47 insertions, 0 deletions
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 7fee8c152f93..0afd134d8c9c 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -25,6 +25,7 @@
*
*/
+#include <asm/processor.h>
#include <linux/crypto.h>
#include <linux/init.h>
#include <linux/module.h>
@@ -637,10 +638,56 @@ static struct crypto_alg blk_xts_alg = {
},
};
+static bool is_blacklisted_cpu(void)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return false;
+
+ if (boot_cpu_data.x86 == 0x06 &&
+ (boot_cpu_data.x86_model == 0x1c ||
+ boot_cpu_data.x86_model == 0x26 ||
+ boot_cpu_data.x86_model == 0x36)) {
+ /*
+ * On Atom, twofish-3way is slower than original assembler
+ * implementation. Twofish-3way trades off some performance in
+ * 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 parallellism and
+ * should be blacklisted.
+ */
+ return true;
+ }
+
+ if (boot_cpu_data.x86 == 0x0f) {
+ /*
+ * On Pentium 4, twofish-3way is slower than original assembler
+ * implementation because excessive uses of 64bit rotate and
+ * left-shifts (which are really slow on P4) needed to store and
+ * handle 128bit block in two 64bit registers.
+ */
+ return true;
+ }
+
+ return false;
+}
+
+static int force;
+module_param(force, int, 0);
+MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+
int __init init(void)
{
int err;
+ 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;
+ }
+
err = crypto_register_alg(&blk_ecb_alg);
if (err)
goto ecb_err;