From: H.J. Lu <hjl.tools@gmail.com>
Date: Thu, 18 May 2017 21:02:02 +0000 (-0700)
Subject: Correct comments in x86_64/multiarch/memcmp.S
X-Git-Tag: glibc-2.26~492
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=a7fbedff76494b5b694f647e9c681cf8988056ce;p=thirdparty%2Fglibc.git

Correct comments in x86_64/multiarch/memcmp.S

	* sysdeps/x86_64/multiarch/memcmp.S (__GI_memcmp): Correct
	comments.
---

diff --git a/ChangeLog b/ChangeLog
index 06ef5789b0b..5ebd3a04abc 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2017-05-18  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* sysdeps/x86_64/multiarch/memcmp.S (__GI_memcmp): Correct
+	comments.
+
 2017-05-18  Siddhesh Poyarekar  <siddhesh@sourceware.org>
 
 	* elf/Makefile (tst-env-setuid-ENV): Reduce value of
diff --git a/sysdeps/x86_64/multiarch/memcmp.S b/sysdeps/x86_64/multiarch/memcmp.S
index 82623173d68..61298200931 100644
--- a/sysdeps/x86_64/multiarch/memcmp.S
+++ b/sysdeps/x86_64/multiarch/memcmp.S
@@ -56,9 +56,9 @@ END(memcmp)
 
 # ifdef SHARED
 #  undef libc_hidden_builtin_def
-/* IFUNC doesn't work with the hidden functions in shared library since
-   they will be called without setting up EBX needed for PLT which is
-   used by IFUNC.  */
+/* It doesn't make sense to send libc-internal memcmp calls through a PLT.
+   The speedup we get from using SSE4 instructions is likely eaten away
+   by the indirect call in the PLT.  */
 #  define libc_hidden_builtin_def(name) \
 	.globl __GI_memcmp; __GI_memcmp = __memcmp_sse2
 # endif