build: support frame-pointer for arm64

Supporting frame-pointer makes Linux's perf and other profilers much more useful
because it lets them gather a stack trace efficiently on profiling events. Major
changes include:
1. save FP on the word below where RSP is pointing to (proposed by Cherry and Austin)
2. adjust some specific offsets in runtime assembly and wrapper code
3. add support to FP in goroutine scheduler
4. adjust link stack overflow check to take the extra word into account
5. adjust nosplit test cases to enable frame sizes which are 16 bytes aligned

Performance impacts on go1 benchmarks:

Enable frame-pointer (by default)

name                      old time/op    new time/op    delta
BinaryTree17-46              5.94s ± 0%     6.00s ± 0%  +1.03%  (p=0.029 n=4+4)
Fannkuch11-46                2.84s ± 1%     2.77s ± 0%  -2.58%  (p=0.008 n=5+5)
FmtFprintfEmpty-46          55.0ns ± 1%    58.9ns ± 1%  +7.06%  (p=0.008 n=5+5)
FmtFprintfString-46          102ns ± 0%     105ns ± 0%  +2.94%  (p=0.008 n=5+5)
FmtFprintfInt-46             118ns ± 0%     117ns ± 1%  -1.19%  (p=0.000 n=4+5)
FmtFprintfIntInt-46          181ns ± 0%     182ns ± 1%    ~     (p=0.444 n=5+5)
FmtFprintfPrefixedInt-46     215ns ± 1%     214ns ± 0%    ~     (p=0.254 n=5+4)
FmtFprintfFloat-46           292ns ± 0%     296ns ± 0%  +1.46%  (p=0.029 n=4+4)
FmtManyArgs-46               720ns ± 0%     732ns ± 0%  +1.72%  (p=0.008 n=5+5)
GobDecode-46                9.82ms ± 1%   10.03ms ± 2%  +2.10%  (p=0.008 n=5+5)
GobEncode-46                8.14ms ± 0%    8.72ms ± 1%  +7.14%  (p=0.008 n=5+5)
Gzip-46                      420ms ± 0%     424ms ± 0%  +0.92%  (p=0.008 n=5+5)
Gunzip-46                   48.2ms ± 0%    48.4ms ± 0%  +0.41%  (p=0.008 n=5+5)
HTTPClientServer-46          201µs ± 4%     201µs ± 0%    ~     (p=0.730 n=5+4)
JSONEncode-46               17.1ms ± 0%    17.7ms ± 1%  +3.80%  (p=0.008 n=5+5)
JSONDecode-46               88.0ms ± 0%    90.1ms ± 0%  +2.42%  (p=0.008 n=5+5)
Mandelbrot200-46            5.06ms ± 0%    5.07ms ± 0%    ~     (p=0.310 n=5+5)
GoParse-46                  5.04ms ± 0%    5.12ms ± 0%  +1.53%  (p=0.008 n=5+5)
RegexpMatchEasy0_32-46       117ns ± 0%     117ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K-46       332ns ± 0%     329ns ± 0%  -0.78%  (p=0.008 n=5+5)
RegexpMatchEasy1_32-46       104ns ± 0%     113ns ± 0%  +8.65%  (p=0.029 n=4+4)
RegexpMatchEasy1_1K-46       563ns ± 0%     569ns ± 0%  +1.10%  (p=0.008 n=5+5)
RegexpMatchMedium_32-46      167ns ± 2%     177ns ± 1%  +5.74%  (p=0.008 n=5+5)
RegexpMatchMedium_1K-46     49.5µs ± 0%    53.4µs ± 0%  +7.81%  (p=0.008 n=5+5)
RegexpMatchHard_32-46       2.56µs ± 1%    2.72µs ± 0%  +6.01%  (p=0.008 n=5+5)
RegexpMatchHard_1K-46       77.0µs ± 0%    81.8µs ± 0%  +6.24%  (p=0.016 n=5+4)
Revcomp-46                   631ms ± 1%     627ms ± 1%    ~     (p=0.095 n=5+5)
Template-46                 81.8ms ± 0%    86.3ms ± 0%  +5.55%  (p=0.008 n=5+5)
TimeParse-46                 423ns ± 0%     432ns ± 0%  +2.32%  (p=0.008 n=5+5)
TimeFormat-46                478ns ± 2%     497ns ± 1%  +3.89%  (p=0.008 n=5+5)
[Geo mean]                  71.6µs         73.3µs       +2.45%

name                      old speed      new speed      delta
GobDecode-46              78.1MB/s ± 1%  76.6MB/s ± 2%  -2.04%  (p=0.008 n=5+5)
GobEncode-46              94.3MB/s ± 0%  88.0MB/s ± 1%  -6.67%  (p=0.008 n=5+5)
Gzip-46                   46.2MB/s ± 0%  45.8MB/s ± 0%  -0.91%  (p=0.008 n=5+5)
Gunzip-46                  403MB/s ± 0%   401MB/s ± 0%  -0.41%  (p=0.008 n=5+5)
JSONEncode-46              114MB/s ± 0%   109MB/s ± 1%  -3.66%  (p=0.008 n=5+5)
JSONDecode-46             22.0MB/s ± 0%  21.5MB/s ± 0%  -2.35%  (p=0.008 n=5+5)
GoParse-46                11.5MB/s ± 0%  11.3MB/s ± 0%  -1.51%  (p=0.008 n=5+5)
RegexpMatchEasy0_32-46     272MB/s ± 0%   272MB/s ± 1%    ~     (p=0.190 n=4+5)
RegexpMatchEasy0_1K-46    3.08GB/s ± 0%  3.11GB/s ± 0%  +0.77%  (p=0.008 n=5+5)
RegexpMatchEasy1_32-46     306MB/s ± 0%   283MB/s ± 0%  -7.63%  (p=0.029 n=4+4)
RegexpMatchEasy1_1K-46    1.82GB/s ± 0%  1.80GB/s ± 0%  -1.07%  (p=0.008 n=5+5)
RegexpMatchMedium_32-46   5.99MB/s ± 0%  5.64MB/s ± 1%  -5.77%  (p=0.016 n=4+5)
RegexpMatchMedium_1K-46   20.7MB/s ± 0%  19.2MB/s ± 0%  -7.25%  (p=0.008 n=5+5)
RegexpMatchHard_32-46     12.5MB/s ± 1%  11.8MB/s ± 0%  -5.66%  (p=0.008 n=5+5)
RegexpMatchHard_1K-46     13.3MB/s ± 0%  12.5MB/s ± 1%  -6.01%  (p=0.008 n=5+5)
Revcomp-46                 402MB/s ± 1%   405MB/s ± 1%    ~     (p=0.095 n=5+5)
Template-46               23.7MB/s ± 0%  22.5MB/s ± 0%  -5.25%  (p=0.008 n=5+5)
[Geo mean]                82.2MB/s       79.6MB/s       -3.26%

Disable frame-pointer (GOEXPERIMENT=noframepointer)

name                      old time/op    new time/op    delta
BinaryTree17-46              5.94s ± 0%     5.96s ± 0%  +0.39%  (p=0.029 n=4+4)
Fannkuch11-46                2.84s ± 1%     2.79s ± 1%  -1.68%  (p=0.008 n=5+5)
FmtFprintfEmpty-46          55.0ns ± 1%    55.2ns ± 3%    ~     (p=0.794 n=5+5)
FmtFprintfString-46          102ns ± 0%     103ns ± 0%  +0.98%  (p=0.016 n=5+4)
FmtFprintfInt-46             118ns ± 0%     115ns ± 0%  -2.54%  (p=0.029 n=4+4)
FmtFprintfIntInt-46          181ns ± 0%     179ns ± 0%  -1.10%  (p=0.000 n=5+4)
FmtFprintfPrefixedInt-46     215ns ± 1%     213ns ± 0%    ~     (p=0.143 n=5+4)
FmtFprintfFloat-46           292ns ± 0%     300ns ± 0%  +2.83%  (p=0.029 n=4+4)
FmtManyArgs-46               720ns ± 0%     739ns ± 0%  +2.64%  (p=0.008 n=5+5)
GobDecode-46                9.82ms ± 1%    9.78ms ± 1%    ~     (p=0.151 n=5+5)
GobEncode-46                8.14ms ± 0%    8.12ms ± 1%    ~     (p=0.690 n=5+5)
Gzip-46                      420ms ± 0%     420ms ± 0%    ~     (p=0.548 n=5+5)
Gunzip-46                   48.2ms ± 0%    48.0ms ± 0%  -0.33%  (p=0.032 n=5+5)
HTTPClientServer-46          201µs ± 4%     199µs ± 3%    ~     (p=0.548 n=5+5)
JSONEncode-46               17.1ms ± 0%    17.2ms ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-46               88.0ms ± 0%    88.6ms ± 0%  +0.64%  (p=0.008 n=5+5)
Mandelbrot200-46            5.06ms ± 0%    5.07ms ± 0%    ~     (p=0.548 n=5+5)
GoParse-46                  5.04ms ± 0%    5.07ms ± 0%  +0.65%  (p=0.008 n=5+5)
RegexpMatchEasy0_32-46       117ns ± 0%     112ns ± 4%  -4.27%  (p=0.016 n=4+5)
RegexpMatchEasy0_1K-46       332ns ± 0%     330ns ± 1%    ~     (p=0.095 n=5+5)
RegexpMatchEasy1_32-46       104ns ± 0%     110ns ± 1%  +5.29%  (p=0.029 n=4+4)
RegexpMatchEasy1_1K-46       563ns ± 0%     567ns ± 2%    ~     (p=0.151 n=5+5)
RegexpMatchMedium_32-46      167ns ± 2%     166ns ± 0%    ~     (p=0.333 n=5+4)
RegexpMatchMedium_1K-46     49.5µs ± 0%    49.6µs ± 0%    ~     (p=0.841 n=5+5)
RegexpMatchHard_32-46       2.56µs ± 1%    2.49µs ± 0%  -2.81%  (p=0.008 n=5+5)
RegexpMatchHard_1K-46       77.0µs ± 0%    75.8µs ± 0%  -1.55%  (p=0.008 n=5+5)
Revcomp-46                   631ms ± 1%     628ms ± 0%    ~     (p=0.095 n=5+5)
Template-46                 81.8ms ± 0%    84.3ms ± 1%  +3.05%  (p=0.008 n=5+5)
TimeParse-46                 423ns ± 0%     425ns ± 0%  +0.52%  (p=0.008 n=5+5)
TimeFormat-46                478ns ± 2%     478ns ± 1%    ~     (p=1.000 n=5+5)
[Geo mean]                  71.6µs         71.6µs       -0.01%

name                      old speed      new speed      delta
GobDecode-46              78.1MB/s ± 1%  78.5MB/s ± 1%    ~     (p=0.151 n=5+5)
GobEncode-46              94.3MB/s ± 0%  94.5MB/s ± 1%    ~     (p=0.690 n=5+5)
Gzip-46                   46.2MB/s ± 0%  46.2MB/s ± 0%    ~     (p=0.571 n=5+5)
Gunzip-46                  403MB/s ± 0%   404MB/s ± 0%  +0.33%  (p=0.032 n=5+5)
JSONEncode-46              114MB/s ± 0%   113MB/s ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-46             22.0MB/s ± 0%  21.9MB/s ± 0%  -0.64%  (p=0.008 n=5+5)
GoParse-46                11.5MB/s ± 0%  11.4MB/s ± 0%  -0.64%  (p=0.008 n=5+5)
RegexpMatchEasy0_32-46     272MB/s ± 0%   285MB/s ± 4%  +4.74%  (p=0.016 n=4+5)
RegexpMatchEasy0_1K-46    3.08GB/s ± 0%  3.10GB/s ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy1_32-46     306MB/s ± 0%   290MB/s ± 1%  -5.21%  (p=0.029 n=4+4)
RegexpMatchEasy1_1K-46    1.82GB/s ± 0%  1.81GB/s ± 2%    ~     (p=0.151 n=5+5)
RegexpMatchMedium_32-46   5.99MB/s ± 0%  6.02MB/s ± 1%    ~     (p=0.063 n=4+5)
RegexpMatchMedium_1K-46   20.7MB/s ± 0%  20.7MB/s ± 0%    ~     (p=0.659 n=5+5)
RegexpMatchHard_32-46     12.5MB/s ± 1%  12.8MB/s ± 0%  +2.88%  (p=0.008 n=5+5)
RegexpMatchHard_1K-46     13.3MB/s ± 0%  13.5MB/s ± 0%  +1.58%  (p=0.008 n=5+5)
Revcomp-46                 402MB/s ± 1%   405MB/s ± 0%    ~     (p=0.095 n=5+5)
Template-46               23.7MB/s ± 0%  23.0MB/s ± 1%  -2.95%  (p=0.008 n=5+5)
[Geo mean]                82.2MB/s       82.3MB/s       +0.04%

Frame-pointer is enabled on Linux by default but can be disabled by setting: GOEXPERIMENT=noframepointer.

Fixes #10110

Change-Id: I1bfaca6dba29a63009d7c6ab04ed7a1413d9479e
Reviewed-on: https://go-review.googlesource.com/61511
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

1 files changed, 25 insertions, 9 deletions

diff --git a/src/runtime/asm_arm64.s b/src/runtime/asm_arm64.s
index af389be9fe..6a6a699241 100644
--- a/src/runtime/asm_arm64.s
+++ b/src/runtime/asm_arm64.s
@@ -39,10 +39,9 @@ TEXT runtime·rt0_go(SB),NOSPLIT,$0
 #endif
 	MOVD	$setg_gcc<>(SB), R1	// arg 1: setg
 	MOVD	g, R0			// arg 0: G
+	SUB	$16, RSP		// reserve 16 bytes for sp-8 where fp may be saved.
 	BL	(R12)
-	MOVD	_cgo_init(SB), R12
-	CMP	$0, R12
-	BEQ	nocgo
+	ADD	$16, RSP
 
 nocgo:
 	// update stackguard after _cgo_init
@@ -107,6 +106,7 @@ TEXT runtime·gosave(SB), NOSPLIT|NOFRAME, $0-8
 	MOVD	buf+0(FP), R3
 	MOVD	RSP, R0
 	MOVD	R0, gobuf_sp(R3)
+	MOVD	R29, gobuf_bp(R3)
 	MOVD	LR, gobuf_pc(R3)
 	MOVD	g, gobuf_g(R3)
 	MOVD	ZR, gobuf_lr(R3)
@@ -128,10 +128,12 @@ TEXT runtime·gogo(SB), NOSPLIT, $24-8
 	MOVD	0(g), R4	// make sure g is not nil
 	MOVD	gobuf_sp(R5), R0
 	MOVD	R0, RSP
+	MOVD	gobuf_bp(R5), R29
 	MOVD	gobuf_lr(R5), LR
 	MOVD	gobuf_ret(R5), R0
 	MOVD	gobuf_ctxt(R5), R26
 	MOVD	$0, gobuf_sp(R5)
+	MOVD	$0, gobuf_bp(R5)
 	MOVD	$0, gobuf_ret(R5)
 	MOVD	$0, gobuf_lr(R5)
 	MOVD	$0, gobuf_ctxt(R5)
@@ -147,6 +149,7 @@ TEXT runtime·mcall(SB), NOSPLIT|NOFRAME, $0-8
 	// Save caller state in g->sched
 	MOVD	RSP, R0
 	MOVD	R0, (g_sched+gobuf_sp)(g)
+	MOVD	R29, (g_sched+gobuf_bp)(g)
 	MOVD	LR, (g_sched+gobuf_pc)(g)
 	MOVD	$0, (g_sched+gobuf_lr)(g)
 	MOVD	g, (g_sched+gobuf_g)(g)
@@ -163,6 +166,7 @@ TEXT runtime·mcall(SB), NOSPLIT|NOFRAME, $0-8
 	MOVD	0(R26), R4			// code pointer
 	MOVD	(g_sched+gobuf_sp)(g), R0
 	MOVD	R0, RSP	// sp = m->g0->sched.sp
+	MOVD	(g_sched+gobuf_bp)(g), R29
 	MOVD	R3, -8(RSP)
 	MOVD	$0, -16(RSP)
 	SUB	$16, RSP
@@ -211,6 +215,7 @@ switch:
 	MOVD	R6, (g_sched+gobuf_pc)(g)
 	MOVD	RSP, R0
 	MOVD	R0, (g_sched+gobuf_sp)(g)
+	MOVD	R29, (g_sched+gobuf_bp)(g)
 	MOVD	$0, (g_sched+gobuf_lr)(g)
 	MOVD	g, (g_sched+gobuf_g)(g)
 
@@ -224,6 +229,7 @@ switch:
 	MOVD	$runtime·mstart(SB), R4
 	MOVD	R4, 0(R3)
 	MOVD	R3, RSP
+	MOVD	(g_sched+gobuf_bp)(g), R29
 
 	// call target function
 	MOVD	0(R26), R3	// code pointer
@@ -235,7 +241,9 @@ switch:
 	BL	runtime·save_g(SB)
 	MOVD	(g_sched+gobuf_sp)(g), R0
 	MOVD	R0, RSP
+	MOVD	(g_sched+gobuf_bp)(g), R29
 	MOVD	$0, (g_sched+gobuf_sp)(g)
+	MOVD	$0, (g_sched+gobuf_bp)(g)
 	RET
 
 noswitch:
@@ -244,6 +252,7 @@ noswitch:
 	// at an intermediate systemstack.
 	MOVD	0(R26), R3	// code pointer
 	MOVD.P	16(RSP), R30	// restore LR
+	SUB	$8, RSP, R29	// restore FP
 	B	(R3)
 
 /*
@@ -278,6 +287,7 @@ TEXT runtime·morestack(SB),NOSPLIT|NOFRAME,$0-0
 	// Set g->sched to context in f
 	MOVD	RSP, R0
 	MOVD	R0, (g_sched+gobuf_sp)(g)
+	MOVD	R29, (g_sched+gobuf_bp)(g)
 	MOVD	LR, (g_sched+gobuf_pc)(g)
 	MOVD	R3, (g_sched+gobuf_lr)(g)
 	MOVD	R26, (g_sched+gobuf_ctxt)(g)
@@ -294,6 +304,7 @@ TEXT runtime·morestack(SB),NOSPLIT|NOFRAME,$0-0
 	BL	runtime·save_g(SB)
 	MOVD	(g_sched+gobuf_sp)(g), R0
 	MOVD	R0, RSP
+	MOVD	(g_sched+gobuf_bp)(g), R29
 	MOVD.W	$0, -16(RSP)	// create a call frame on g0 (saved LR; keep 16-aligned)
 	BL	runtime·newstack(SB)
 
@@ -843,8 +854,9 @@ TEXT runtime·jmpdefer(SB), NOSPLIT|NOFRAME, $0-16
 // Save state of caller into g->sched. Smashes R0.
 TEXT gosave<>(SB),NOSPLIT|NOFRAME,$0
 	MOVD	LR, (g_sched+gobuf_pc)(g)
-	MOVD RSP, R0
+	MOVD	RSP, R0
 	MOVD	R0, (g_sched+gobuf_sp)(g)
+	MOVD	R29, (g_sched+gobuf_bp)(g)
 	MOVD	$0, (g_sched+gobuf_lr)(g)
 	MOVD	$0, (g_sched+gobuf_ret)(g)
 	// Assert ctxt is zero. See func save.
@@ -885,6 +897,7 @@ TEXT ·asmcgocall(SB),NOSPLIT,$0-20
 	BL	runtime·save_g(SB)
 	MOVD	(g_sched+gobuf_sp)(g), R0
 	MOVD	R0, RSP
+	MOVD	(g_sched+gobuf_bp)(g), R29
 	MOVD	R9, R0
 
 	// Now on a scheduling stack (a pthread-created stack).
@@ -996,6 +1009,7 @@ needm:
 	MOVD	m_g0(R8), R3
 	MOVD	RSP, R0
 	MOVD	R0, (g_sched+gobuf_sp)(R3)
+	MOVD	R29, (g_sched+gobuf_bp)(R3)
 
 havem:
 	// Now there's a valid m, and we're running on its m->g0.
@@ -1003,7 +1017,7 @@ havem:
 	// Save current sp in m->g0->sched.sp in preparation for
 	// switch back to m->curg stack.
 	// NOTE: unwindm knows that the saved g->sched.sp is at 16(RSP) aka savedsp-16(SP).
-	// Beware that the frame size is actually 32.
+	// Beware that the frame size is actually 32+16.
 	MOVD	m_g0(R8), R3
 	MOVD	(g_sched+gobuf_sp)(R3), R4
 	MOVD	R4, savedsp-16(SP)
@@ -1030,10 +1044,12 @@ havem:
 	BL	runtime·save_g(SB)
 	MOVD	(g_sched+gobuf_sp)(g), R4 // prepare stack as R4
 	MOVD	(g_sched+gobuf_pc)(g), R5
-	MOVD	R5, -(24+8)(R4)
+	MOVD	R5, -48(R4)
+	MOVD	(g_sched+gobuf_bp)(g), R5
+	MOVD	R5, -56(R4)
 	MOVD	ctxt+24(FP), R0
-	MOVD	R0, -(16+8)(R4)
-	MOVD	$-(24+8)(R4), R0 // maintain 16-byte SP alignment
+	MOVD	R0, -40(R4)
+	MOVD	$-48(R4), R0 // maintain 16-byte SP alignment
 	MOVD	R0, RSP
 	BL	runtime·cgocallbackg(SB)
 
@@ -1041,7 +1057,7 @@ havem:
 	MOVD	0(RSP), R5
 	MOVD	R5, (g_sched+gobuf_pc)(g)
 	MOVD	RSP, R4
-	ADD	$(24+8), R4, R4
+	ADD	$48, R4, R4
 	MOVD	R4, (g_sched+gobuf_sp)(g)
 
 	// Switch back to m->g0's stack and restore m->g0->sched.sp.