x86/vdso: Use RDPID in preference to LSL when available

commit a582c540ac1b10f0a7d37415e04c4af42409fd08 upstream.

RDPID is a new instruction that reads MSR_TSC_AUX quickly.  This
should be considerably faster than reading the GDT.  Add a
cpufeature for it and use it from __vdso_getcpu() when available.

Tested-by: Megha Dey <megha.dey@intel.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/4f6c3a22012d10f1c65b9ca15800e01b42c7d39d.1479320367.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 94491e4d21a7949eec4287918521a68cfb53fed2..01ec126c5969676505886d8acb2d90a0bc5fa11a 100644 (file)
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -301,6 +301,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_PKU                (16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE      (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_RDPID      (16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */

diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index f556c4843aa18af74359dfeb2a41d39d9a2c3bb9..51e7533bbf79e8cf7d3a8ef5c2f800cdc3794b59 100644 (file)
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -83,8 +83,13 @@ static inline unsigned int __getcpu(void)
         * works on all CPUs.  This is volatile so that it orders
         * correctly wrt barrier() and to keep gcc from cleverly
         * hoisting it out of the calling function.
+        *
+        * If RDPID is available, use it.
         */
-       asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+       alternative_io ("lsl %[p],%[seg]",
+                       ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
+                       X86_FEATURE_RDPID,
+                       [p] "=a" (p), [seg] "r" (__PER_CPU_SEG));
 
        return p;
 }