Optimize __memset_chk, __memcpy_chk.

This change creates assembler versions of __memcpy_chk/__memset_chk
that is implemented in the memcpy/memset assembler code. This change
avoids an extra call to memcpy/memset, instead allowing a simple fall
through to occur from the chk code into the body of the real
implementation.

Testing:

- Ran the libc_test on __memcpy_chk/__memset_chk on all nexus devices.
- Wrote a small test executable that has three calls to __memcpy_chk and
  three calls to __memset_chk. First call dest_len is length + 1. Second
  call dest_len is length. Third call dest_len is length - 1.
  Verified that the first two calls pass, and the third fails. Examined
  the logcat output on all nexus devices to verify that the fortify
  error message was sent properly.
- I benchmarked the new __memcpy_chk and __memset_chk on all systems. For
  __memcpy_chk and large copies, the savings is relatively small (about 1%).
  For small copies, the savings is large on cortex-a15/krait devices
  (between 5% to 30%).
  For cortex-a9 and small copies, the speed up is present, but relatively
  small (about 3% to 5%).
  For __memset_chk and large copies, the savings is also small (about 1%).
  However, all processors show larger speed-ups on small copies (about 30% to
  100%).

Bug: 9293744

Change-Id: I8926d59fe2673e36e8a27629e02a7b7059ebbc98

libc/arch-arm/generic/bionic/memcpy.S

@@ -28,6 +28,7 @@
 
 #include <machine/cpu-features.h>
 #include <machine/asm.h>
+#include "libc_events.h"
 
         /*
          * Optimized memcpy() for ARM.
@@ -36,6 +37,13 @@
          * so we have to preserve R0.
          */
 
+ENTRY(__memcpy_chk)
+        cmp         r2, r3
+        bgt         fortify_check_failed
+
+        // Fall through to memcpy...
+END(__memcpy_chk)
+
 ENTRY(memcpy)
         /* The stack must always be 64-bits aligned to be compliant with the
          * ARM ABI. Since we have to save R0, we might as well save R4
@@ -377,4 +385,20 @@ copy_last_3_and_return:
         add         sp,  sp, #28
         ldmfd       sp!, {r0, r4, lr}
         bx          lr
+
+        // Only reached when the __memcpy_chk check fails.
+fortify_check_failed:
+        ldr     r0, error_message
+        ldr     r1, error_code
+1:
+        add     r0, pc
+        bl      __fortify_chk_fail
+error_code:
+        .word   BIONIC_EVENT_MEMCPY_BUFFER_OVERFLOW
+error_message:
+        .word   error_string-(1b+8)
 END(memcpy)
+
+        .data
+error_string:
+        .string     "memcpy buffer overflow"

libc/arch-arm/generic/bionic/memset.S

@@ -27,6 +27,7 @@
  */
 
 #include <machine/asm.h>
+#include "libc_events.h"
 
         /*
          * Optimized memset() for ARM.
@@ -34,9 +35,28 @@
          * memset() returns its first argument.
          */
 
+ENTRY(__memset_chk)
+        cmp         r2, r3
+        bls         done
+
+        ldr         r0, error_message
+        ldr         r1, error_code
+1:
+        add         r0, pc
+        bl          __fortify_chk_fail
+error_code:
+        .word       BIONIC_EVENT_MEMSET_BUFFER_OVERFLOW
+error_message:
+        .word       error_string-(1b+8)
+
+END(__memset_chk)
+
 ENTRY(bzero)
         mov     r2, r1
         mov     r1, #0
+
+done:
+        // Fall through to memset...
 END(bzero)
 
 ENTRY(memset)
@@ -107,3 +127,7 @@ ENTRY(memset)
         ldmfd       sp!, {r0, r4-r7, lr}
         bx          lr
 END(memset)
+
+        .data
+error_string:
+        .string     "memset buffer overflow"