From: rth <rth@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Wed, 9 Nov 2011 19:51:49 +0000 (+0000)
Subject: libitm: Avoid non-portable x86 branch prediction mnemonic.
X-Git-Url: http://git.sourceforge.jp/view?p=pf3gnuchains%2Fgcc-fork.git;a=commitdiff_plain;h=f3210a53394de39a8aa74ec9dcb23f2cc0551322;hp=57df6e5819addfc5c860d0b15fd2f0cde055a8fa

libitm: Avoid non-portable x86 branch prediction mnemonic.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@181233 138bc75d-0d04-0410-961f-82ee72b054a4
---

diff --git a/libitm/ChangeLog b/libitm/ChangeLog
index e78716d2a37..0501d168a23 100644
--- a/libitm/ChangeLog
+++ b/libitm/ChangeLog
@@ -1,5 +1,8 @@
 2011-11-09  Richard Henderson  <rth@redhat.com>
 
+	* config/x86/cacheline.h (gtm_cacheline::store_mask): Use .byte
+	to emit branch prediction hint.
+
 	* config/x86/sjlj.S: Protect elf directives with __ELF__.
 	Protect .note.GNU-stack with __linux__.
 
diff --git a/libitm/config/x86/cacheline.h b/libitm/config/x86/cacheline.h
index 15a95b0be5b..f91d7ccb802 100644
--- a/libitm/config/x86/cacheline.h
+++ b/libitm/config/x86/cacheline.h
@@ -144,7 +144,7 @@ gtm_cacheline::operator= (const gtm_cacheline & __restrict s)
 }
 #endif
 
-// ??? Support masked integer stores more efficiently with an unlocked cmpxchg
+// Support masked integer stores more efficiently with an unlocked cmpxchg
 // insn.  My reasoning is that while we write to locations that we do not wish
 // to modify, we do it in an uninterruptable insn, and so we either truely
 // write back the original data or the insn fails -- unlike with a
@@ -171,7 +171,8 @@ gtm_cacheline::store_mask (uint32_t *d, uint32_t s, uint8_t m)
 		"and	%[m], %[n]\n\t"
 		"or	%[s], %[n]\n\t"
 		"cmpxchg %[n], %[d]\n\t"
-		"jnz,pn	0b"
+		".byte	0x2e\n\t"	// predict not-taken, aka jnz,pn
+		"jnz	0b"
 		: [d] "+m"(*d), [n] "=&r" (n), [o] "+a"(o)
 		: [s] "r" (s & bm), [m] "r" (~bm));
 	}
@@ -198,7 +199,8 @@ gtm_cacheline::store_mask (uint64_t *d, uint64_t s, uint8_t m)
 		"and	%[m], %[n]\n\t"
 		"or	%[s], %[n]\n\t"
 		"cmpxchg %[n], %[d]\n\t"
-		"jnz,pn	0b"
+		".byte	0x2e\n\t"	// predict not-taken, aka jnz,pn
+		"jnz	0b"
 		: [d] "+m"(*d), [n] "=&r" (n), [o] "+a"(o)
 		: [s] "r" (s & bm), [m] "r" (~bm));
 #else