From: Jan Beulich <jbeulich@suse.com>
Date: Mon, 26 Jan 2015 11:50:21 +0000 (+0100)
Subject: x86: use tzcnt instead of bsf
X-Git-Tag: archive/raspbian/4.8.0-1+rpi1~1^2~3857
X-Git-Url: https://dgit.raspbian.org/?a=commitdiff_plain;h=b18b6daf65554fd9e1b6008513bfd50a7ef5d3e9;p=xen.git

x86: use tzcnt instead of bsf

Following a compiler change done in 2012, make use of the fact that for
non-zero input BSF and TZCNT produce the same numeric result (EFLAGS
setting differs), and that CPUs not knowing of TZCNT will treat the
instruction as BSF (i.e. ignore what looks like a REP prefix to them).
The assumption here is that TZCNT would never have worse performance
than BSF.

Also extend the asm() input in find_first_set_bit() to allow memory
operands.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
---

diff --git a/xen/arch/x86/bitops.c b/xen/arch/x86/bitops.c
index c037567c6e..f6ee71512c 100644
--- a/xen/arch/x86/bitops.c
+++ b/xen/arch/x86/bitops.c
@@ -62,7 +62,7 @@ unsigned int __find_first_zero_bit(
         "   je 2f\n\t"
         "   xor -"STR(BITS_PER_LONG/8)"(%2),%3\n\t"
         "   jz 1b\n\t"
-        "   bsf %3,%0\n\t"
+        "   rep; bsf %3,%0\n\t"
         "   lea -"STR(BITS_PER_LONG/8)"(%2),%2\n\t"
         "2: sub %%ebx,%%edi\n\t"
         "   shl $3,%%edi\n\t"
diff --git a/xen/arch/x86/hvm/vpic.c b/xen/arch/x86/hvm/vpic.c
index 2c6e6e5f3f..d72b6ff3fa 100644
--- a/xen/arch/x86/hvm/vpic.c
+++ b/xen/arch/x86/hvm/vpic.c
@@ -56,7 +56,7 @@ static int vpic_get_priority(struct hvm_hw_vpic *vpic, uint8_t mask)
         return VPIC_PRIO_NONE;
 
     /* prio = ffs(mask ROR vpic->priority_add); */
-    asm ( "ror %%cl,%b1 ; bsf %1,%0"
+    asm ( "ror %%cl,%b1 ; rep; bsf %1,%0"
           : "=r" (prio) : "q" ((uint32_t)mask), "c" (vpic->priority_add) );
     return prio;
 }
diff --git a/xen/include/asm-x86/bitops.h b/xen/include/asm-x86/bitops.h
index 099a74c373..6f0f34bc57 100644
--- a/xen/include/asm-x86/bitops.h
+++ b/xen/include/asm-x86/bitops.h
@@ -391,7 +391,7 @@ static inline unsigned int __scanbit(unsigned long val, unsigned long max)
  */
 static inline unsigned int find_first_set_bit(unsigned long word)
 {
-    asm ( "bsf %1,%0" : "=r" (word) : "r" (word) );
+    asm ( "rep; bsf %1,%0" : "=r" (word) : "rm" (word) );
     return (unsigned int)word;
 }