aarch64: Optimized memset for falkor

The generic memset reads dczid_el0 on every memset.  This has a
significant impact on falkor for a range of sizes because reading
dczid_el0 is slow.

The DZP bit in the dczid_el0 register does not change dynamically, so
it is safe to read once during program startup.  With this patch
dczid_el0 is read once during startup and zva_size is cached.  This is
used to invoke the falkor-specific memset; the generic memset routine
remains unchanged.

The gains due to this are significant for falkor, with run time
reductions as high as 48%.  Here's a sample from the falkor tests:

Function: memset
Variant: walk
                      simple_memset	__memset_falkor	__memset_generic
=====================================================================
length=256, char=0:   139.96 (-698.28%)	   9.07 ( 48.26%)  17.53
length=257, char=0:   140.50 (-699.03%)	   9.53 ( 45.80%)  17.58
length=258, char=0:   140.96 (-703.95%)	   9.58 ( 45.36%)  17.53
length=259, char=0:   141.56 (-705.16%)	   9.53 ( 45.79%)  17.58
length=260, char=0:   142.15 (-710.76%)	   9.57 ( 45.39%)  17.53
length=261, char=0:   142.50 (-710.39%)	   9.53 ( 45.78%)  17.58
length=262, char=0:   142.97 (-715.09%)	   9.57 ( 45.42%)  17.54
length=263, char=0:   143.51 (-716.18%)	   9.53 ( 45.80%)  17.58
length=264, char=0:   143.93 (-720.55%)	   9.58 ( 45.39%)  17.54
length=265, char=0:   144.56 (-722.07%)	   9.53 ( 45.80%)  17.59
length=266, char=0:   144.98 (-726.42%)	   9.58 ( 45.42%)  17.54
length=267, char=0:   145.53 (-727.53%)	   9.53 ( 45.80%)  17.59
length=268, char=0:   146.25 (-731.81%)	   9.53 ( 45.79%)  17.58
length=269, char=0:   146.52 (-735.39%)	   9.53 ( 45.66%)  17.54
length=270, char=0:   146.97 (-735.81%)	   9.53 ( 45.80%)  17.58
length=271, char=0:   147.54 (-741.08%)	   9.58 ( 45.38%)  17.54
length=512, char=0:   268.26 (-1307.85%)  12.06 ( 36.71%)  19.05
length=513, char=0:   268.73 (-1273.89%)  13.56 ( 30.68%)  19.56
length=514, char=0:   269.31 (-1276.89%)  13.56 ( 30.68%)  19.56
length=515, char=0:   269.73 (-1279.05%)  13.56 ( 30.68%)  19.56
length=516, char=0:   270.34 (-1282.24%)  13.56 ( 30.67%)  19.56
length=517, char=0:   270.83 (-1284.71%)  13.56 ( 30.66%)  19.56
length=518, char=0:   271.20 (-1286.54%)  13.56 ( 30.67%)  19.56
length=519, char=0:   271.67 (-1288.67%)  13.65 ( 30.24%)  19.56
length=520, char=0:   272.14 (-1291.04%)  13.65 ( 30.22%)  19.56
length=521, char=0:   272.66 (-1293.69%)  13.65 ( 30.23%)  19.56
length=522, char=0:   273.14 (-1296.13%)  13.65 ( 30.20%)  19.56
length=523, char=0:   273.64 (-1298.75%)  13.65 ( 30.23%)  19.56
length=524, char=0:   274.34 (-1302.16%)  13.66 ( 30.20%)  19.57
length=525, char=0:   274.64 (-1297.78%)  13.56 ( 30.99%)  19.65
length=526, char=0:   275.20 (-1300.04%)  13.56 ( 31.01%)  19.66
length=527, char=0:   275.66 (-1302.86%)  13.56 ( 30.99%)  19.65
length=1024, char=0:  524.46 (-2169.75%)  20.12 ( 12.92%)  23.11
length=1025, char=0:  525.14 (-2124.63%)  21.62 (  8.40%)  23.61
length=1026, char=0:  525.59 (-2125.36%)  21.88 (  7.37%)  23.62
length=1027, char=0:  525.98 (-2127.14%)  21.62 (  8.46%)  23.62
length=1028, char=0:  526.68 (-2131.10%)  21.62 (  8.42%)  23.61
length=1029, char=0:  527.10 (-2131.70%)  21.79 (  7.73%)  23.62
length=1030, char=0:  527.54 (-2118.51%)  21.62 (  9.10%)  23.78
length=1031, char=0:  527.98 (-2136.37%)  21.62 (  8.43%)  23.61
length=1032, char=0:  528.70 (-2139.38%)  21.62 (  8.43%)  23.61
length=1033, char=0:  529.25 (-2124.37%)  21.62 (  9.11%)  23.79
length=1034, char=0:  529.48 (-2142.95%)  21.62 (  8.43%)  23.61
length=1035, char=0:  530.11 (-2145.13%)  21.62 (  8.44%)  23.61
length=1036, char=0:  530.76 (-2147.10%)  21.79 (  7.73%)  23.62
length=1037, char=0:  531.03 (-2149.45%)  21.62 (  8.42%)  23.61
length=1038, char=0:  531.64 (-2151.87%)  21.62 (  8.42%)  23.61
length=1039, char=0:  531.99 (-2151.63%)  21.80 (  7.75%)  23.63

	* sysdeps/aarch64/memset-reg.h: New file.
	* sysdeps/aarch64/memset.S: Use it.
	(__memset): Rename to MEMSET macro.
	[ZVA_MACRO]: Use zva_macro.
	* sysdeps/aarch64/multiarch/Makefile (sysdep_routines):
	Add memset_generic and memset_falkor.
	* sysdeps/aarch64/multiarch/ifunc-impl-list.c
	(__libc_ifunc_impl_list): Add memset ifuncs.
	* sysdeps/aarch64/multiarch/init-arch.h (INIT_ARCH): New
	local variable zva_size.
	* sysdeps/aarch64/multiarch/memset.c: New file.
	* sysdeps/aarch64/multiarch/memset_generic.S: New file.
	* sysdeps/aarch64/multiarch/memset_falkor.S: New file.
	* sysdeps/aarch64/multiarch/rtld-memset.S: New file.
	* sysdeps/unix/sysv/linux/aarch64/cpu-features.c
	(DCZID_DZP_MASK): New macro.
	(DCZID_BS_MASK): Likewise.
	(init_cpu_features): Read and set zva_size.
	* sysdeps/unix/sysv/linux/aarch64/cpu-features.h
	(struct cpu_features): New member zva_size.

1 files changed, 9 insertions, 18 deletions

diff --git a/sysdeps/aarch64/memset.S b/sysdeps/aarch64/memset.S
index 110fd22781..45fb0a86a9 100644
--- a/sysdeps/aarch64/memset.S
+++ b/sysdeps/aarch64/memset.S
@@ -17,6 +17,7 @@
    <http://www.gnu.org/licenses/>.  */
 
 #include <sysdep.h>
+#include "memset-reg.h"
 
 /* Assumptions:
  *
@@ -24,20 +25,7 @@
  *
  */
 
-#define dstin	x0
-#define val	x1
-#define valw	w1
-#define count	x2
-#define dst	x3
-#define dstend	x4
-#define tmp1	x5
-#define tmp1w	w5
-#define tmp2	x6
-#define tmp2w	w6
-#define zva_len x7
-#define zva_lenw w7
-
-ENTRY_ALIGN (__memset, 6)
+ENTRY_ALIGN (MEMSET, 6)
 
 	DELOUSE (0)
 	DELOUSE (2)
@@ -108,8 +96,11 @@ L(tail64):
 	stp	q0, q0, [dstend, -32]
 	ret
 
-	.p2align 3
 L(try_zva):
+#ifdef ZVA_MACRO
+	zva_macro
+#else
+	.p2align 3
 	mrs	tmp1, dczid_el0
 	tbnz	tmp1w, 4, L(no_zva)
 	and	tmp1w, tmp1w, 15
@@ -189,7 +180,7 @@ L(zva_other):
 	b.hs	3b
 4:	add	count, count, zva_len
 	b	L(tail64)
+#endif
 
-END (__memset)
-weak_alias (__memset, memset)
-libc_hidden_builtin_def (memset)
+END (MEMSET)
+libc_hidden_builtin_def (MEMSET)