4 files changed, 29 insertions, 2 deletions
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..eafce1a130a1 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
 
+perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index b43f8d2a34ec..9ad015a1e202 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,6 +6,7 @@
 #define altinstr_replacement text
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
+#define _ASM_EXTABLE(x, y)
 
 #include "../../arch/x86/lib/memcpy_64.S"
 /*
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
new file mode 100644
index 000000000000..4130734dde84
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c
@@ -0,0 +1,24 @@
+/*
+ * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
+ * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
+ * happy.
+ */
+#include <linux/types.h>
+
+unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
+
+unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
 	u8 *global_data;
 	u8 *process_data;
 	u8 *thread_data;
-	u64 bytes_done;
+	u64 bytes_done, secs;
 	long work_done;
 	u32 l;
 	struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
 	td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
-	td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+	secs = td->runtime_ns / NSEC_PER_SEC;
+	td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
 
 	getrusage(RUSAGE_THREAD, &rusage);
 	td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;