diff mbox series

[4/4] SVE unwinding

Message ID 87shdvmere.fsf@linaro.org
State New
Headers show
Series Add SVE support | expand

Commit Message

Richard Sandiford Nov. 3, 2017, 5:52 p.m. UTC
This patch adds support for unwinding frames that use the SVE
pseudo VG register.  We want this register to act like a normal
register if the CFI explicitly sets it, but want to provide a
default value otherwise.  Computing the default value requires
an SVE target, so we only want to compute it on demand.

aarch64_vg uses a hard-coded .inst in order to avoid a build
dependency on binutils 2.28 or later.


2017-11-03  Richard Sandiford  <richard.sandiford@linaro.org>

libgcc/
	* config/aarch64/value-unwind.h (aarch64_vg): New function.
	(DWARF_LAZY_REGISTER_VALUE): Define.
	* unwind-dw2.c (_Unwind_GetGR): Use DWARF_LAZY_REGISTER_VALUE
	to provide a fallback register value.

gcc/testsuite/
	* g++.target/aarch64/aarch64.exp: New harness.
	* g++.target/aarch64/sve_catch_1.C: New test.
	* g++.target/aarch64/sve_catch_2.C: Likewise.
	* g++.target/aarch64/sve_catch_3.C: Likewise.
	* g++.target/aarch64/sve_catch_4.C: Likewise.
	* g++.target/aarch64/sve_catch_5.C: Likewise.
	* g++.target/aarch64/sve_catch_6.C: Likewise.

Comments

James Greenhalgh Nov. 10, 2017, 10:14 a.m. UTC | #1
On Fri, Nov 03, 2017 at 05:52:05PM +0000, Richard Sandiford wrote:
> This patch adds support for unwinding frames that use the SVE

> pseudo VG register.  We want this register to act like a normal

> register if the CFI explicitly sets it, but want to provide a

> default value otherwise.  Computing the default value requires

> an SVE target, so we only want to compute it on demand.

> 

> aarch64_vg uses a hard-coded .inst in order to avoid a build

> dependency on binutils 2.28 or later.


I think the new hook needs documenting in tm.texi , particularly as it
implies a conditional write to VALUE.

I think this is practice we've seen before, for example
DWARF_REG_TO_UNWIND_COLUMN and REG_VALUE_IN_UNWIND_CONTEXT are defined
in libgcc/config and documented in tm.texi.

Otherwise, the AArch64 parts of this are OK. You mind need to wait for
someone to OK the unwind-dw2.c part.

Thanks,
James

Reviewed-by: James Greenhalgh <james.greenhalgh@arm.com>


> 2017-11-03  Richard Sandiford  <richard.sandiford@linaro.org>

> 

> libgcc/

> 	* config/aarch64/value-unwind.h (aarch64_vg): New function.

> 	(DWARF_LAZY_REGISTER_VALUE): Define.

> 	* unwind-dw2.c (_Unwind_GetGR): Use DWARF_LAZY_REGISTER_VALUE

> 	to provide a fallback register value.

> 

> gcc/testsuite/

> 	* g++.target/aarch64/aarch64.exp: New harness.

> 	* g++.target/aarch64/sve_catch_1.C: New test.

> 	* g++.target/aarch64/sve_catch_2.C: Likewise.

> 	* g++.target/aarch64/sve_catch_3.C: Likewise.

> 	* g++.target/aarch64/sve_catch_4.C: Likewise.

> 	* g++.target/aarch64/sve_catch_5.C: Likewise.

> 	* g++.target/aarch64/sve_catch_6.C: Likewise.

>
diff mbox series

Patch

Index: libgcc/config/aarch64/value-unwind.h
===================================================================
--- libgcc/config/aarch64/value-unwind.h	2017-02-23 19:53:58.000000000 +0000
+++ libgcc/config/aarch64/value-unwind.h	2017-11-03 17:24:20.172023500 +0000
@@ -23,3 +23,19 @@ 
 #if defined __aarch64__ && !defined __LP64__
 # define REG_VALUE_IN_UNWIND_CONTEXT
 #endif
+
+/* Return the value of the pseudo VG register.  This should only be
+   called if we know this is an SVE host.  */
+static inline int
+aarch64_vg (void)
+{
+  register int vg asm ("x0");
+  /* CNTD X0.  */
+  asm (".inst 0x04e0e3e0" : "=r" (vg));
+  return vg;
+}
+
+/* Lazily provide a value for VG, so that we don't try to execute SVE
+   instructions unless we know they're needed.  */
+#define DWARF_LAZY_REGISTER_VALUE(REGNO, VALUE) \
+  ((REGNO) == AARCH64_DWARF_VG && ((*VALUE) = aarch64_vg (), 1))
Index: libgcc/unwind-dw2.c
===================================================================
--- libgcc/unwind-dw2.c	2017-02-23 19:54:02.000000000 +0000
+++ libgcc/unwind-dw2.c	2017-11-03 17:24:20.172023500 +0000
@@ -216,12 +216,12 @@  _Unwind_IsExtendedContext (struct _Unwin
 	  || (context->flags & EXTENDED_CONTEXT_BIT));
 }
 
-/* Get the value of register INDEX as saved in CONTEXT.  */
+/* Get the value of register REGNO as saved in CONTEXT.  */
 
 inline _Unwind_Word
-_Unwind_GetGR (struct _Unwind_Context *context, int index)
+_Unwind_GetGR (struct _Unwind_Context *context, int regno)
 {
-  int size;
+  int size, index;
   _Unwind_Context_Reg_Val val;
 
 #ifdef DWARF_ZERO_REG
@@ -229,7 +229,7 @@  _Unwind_GetGR (struct _Unwind_Context *c
     return 0;
 #endif
 
-  index = DWARF_REG_TO_UNWIND_COLUMN (index);
+  index = DWARF_REG_TO_UNWIND_COLUMN (regno);
   gcc_assert (index < (int) sizeof(dwarf_reg_size_table));
   size = dwarf_reg_size_table[index];
   val = context->reg[index];
@@ -237,6 +237,14 @@  _Unwind_GetGR (struct _Unwind_Context *c
   if (_Unwind_IsExtendedContext (context) && context->by_value[index])
     return _Unwind_Get_Unwind_Word (val);
 
+#ifdef DWARF_LAZY_REGISTER_VALUE
+  {
+    _Unwind_Word value;
+    if (DWARF_LAZY_REGISTER_VALUE (regno, &value))
+      return value;
+  }
+#endif
+
   /* This will segfault if the register hasn't been saved.  */
   if (size == sizeof(_Unwind_Ptr))
     return * (_Unwind_Ptr *) (_Unwind_Internal_Ptr) val;
Index: gcc/testsuite/g++.target/aarch64/aarch64.exp
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/aarch64.exp	2017-11-03 17:24:20.171023116 +0000
@@ -0,0 +1,38 @@ 
+#  Specific regression driver for AArch64.
+#  Copyright (C) 2009-2017 Free Software Foundation, Inc.
+#  Contributed by ARM Ltd.
+#
+#  This file is part of GCC.
+#
+#  GCC is free software; you can redistribute it and/or modify it
+#  under the terms of the GNU General Public License as published by
+#  the Free Software Foundation; either version 3, or (at your option)
+#  any later version.
+#
+#  GCC is distributed in the hope that it will be useful, but
+#  WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with GCC; see the file COPYING3.  If not see
+#  <http://www.gnu.org/licenses/>.  */
+
+# GCC testsuite that uses the `dg.exp' driver.
+
+# Exit immediately if this isn't an AArch64 target.
+if {![istarget aarch64*-*-*] } then {
+  return
+}
+
+# Load support procs.
+load_lib g++-dg.exp
+
+# Initialize `dg'.
+dg-init
+
+# Main loop.
+dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.C]] "" ""
+
+# All done.
+dg-finish
Index: gcc/testsuite/g++.target/aarch64/sve_catch_1.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_1.C	2017-11-03 17:24:20.171023116 +0000
@@ -0,0 +1,70 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+/* Invoke X (P##n) for n in [0, 7].  */
+#define REPEAT8(X, P) \
+  X (P##0) X (P##1) X (P##2) X (P##3) X (P##4) X (P##5) X (P##6) X (P##7)
+
+/* Invoke X (n) for all octal n in [0, 39].  */
+#define REPEAT40(X) \
+  REPEAT8 (X, 0) REPEAT8 (X, 1)  REPEAT8 (X, 2) REPEAT8 (X, 3) REPEAT8 (X, 4)
+
+volatile int testi;
+
+/* Throw to f3.  */
+void __attribute__ ((weak))
+f1 (int x[40][100], int *y)
+{
+  /* A wild write to x and y.  */
+  asm volatile ("" ::: "memory");
+  if (y[testi] == x[testi][testi])
+    throw 100;
+}
+
+/* Expect vector work to be done, with spilling of vector registers.  */
+void __attribute__ ((weak))
+f2 (int x[40][100], int *y)
+{
+  /* Try to force some spilling.  */
+#define DECLARE(N) int y##N = y[N];
+  REPEAT40 (DECLARE);
+  for (int j = 0; j < 20; ++j)
+    {
+      f1 (x, y);
+#pragma omp simd
+      for (int i = 0; i < 100; ++i)
+	{
+#define INC(N) x[N][i] += y##N;
+	  REPEAT40 (INC);
+	}
+    }
+}
+
+/* Catch an exception thrown from f1, via f2.  */
+void __attribute__ ((weak))
+f3 (int x[40][100], int *y, int *z)
+{
+  volatile int extra = 111;
+  try
+    {
+      f2 (x, y);
+    }
+  catch (int val)
+    {
+      *z = val + extra;
+    }
+}
+
+static int x[40][100];
+static int y[40];
+static int z;
+
+int
+main (void)
+{
+  f3 (x, y, &z);
+  if (z != 211)
+    __builtin_abort ();
+  return 0;
+}
Index: gcc/testsuite/g++.target/aarch64/sve_catch_2.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_2.C	2017-11-03 17:24:20.171023116 +0000
@@ -0,0 +1,5 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+#include "sve_catch_1.C"
Index: gcc/testsuite/g++.target/aarch64/sve_catch_3.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_3.C	2017-11-03 17:24:20.171023116 +0000
@@ -0,0 +1,79 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+/* Invoke X (P##n) for n in [0, 7].  */
+#define REPEAT8(X, P) \
+  X (P##0) X (P##1) X (P##2) X (P##3) X (P##4) X (P##5) X (P##6) X (P##7)
+
+/* Invoke X (n) for all octal n in [0, 39].  */
+#define REPEAT40(X) \
+  REPEAT8 (X, 0) REPEAT8 (X, 1)  REPEAT8 (X, 2) REPEAT8 (X, 3) REPEAT8 (X, 4)
+
+volatile int testi, sink;
+
+/* Take 2 stack arguments and throw to f3.  */
+void __attribute__ ((weak))
+f1 (int x[40][100], int *y, int z1, int z2, int z3, int z4,
+    int z5, int z6, int z7, int z8)
+{
+  /* A wild write to x and y.  */
+  sink = z1;
+  sink = z2;
+  sink = z3;
+  sink = z4;
+  sink = z5;
+  sink = z6;
+  sink = z7;
+  sink = z8;
+  asm volatile ("" ::: "memory");
+  if (y[testi] == x[testi][testi])
+    throw 100;
+}
+
+/* Expect vector work to be done, with spilling of vector registers.  */
+void __attribute__ ((weak))
+f2 (int x[40][100], int *y)
+{
+  /* Try to force some spilling.  */
+#define DECLARE(N) int y##N = y[N];
+  REPEAT40 (DECLARE);
+  for (int j = 0; j < 20; ++j)
+    {
+      f1 (x, y, 1, 2, 3, 4, 5, 6, 7, 8);
+#pragma omp simd
+      for (int i = 0; i < 100; ++i)
+	{
+#define INC(N) x[N][i] += y##N;
+	  REPEAT40 (INC);
+	}
+    }
+}
+
+/* Catch an exception thrown from f1, via f2.  */
+void __attribute__ ((weak))
+f3 (int x[40][100], int *y, int *z)
+{
+  volatile int extra = 111;
+  try
+    {
+      f2 (x, y);
+    }
+  catch (int val)
+    {
+      *z = val + extra;
+    }
+}
+
+static int x[40][100];
+static int y[40];
+static int z;
+
+int
+main (void)
+{
+  f3 (x, y, &z);
+  if (z != 211)
+    __builtin_abort ();
+  return 0;
+}
Index: gcc/testsuite/g++.target/aarch64/sve_catch_4.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_4.C	2017-11-03 17:24:20.171023116 +0000
@@ -0,0 +1,5 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+#include "sve_catch_3.C"
Index: gcc/testsuite/g++.target/aarch64/sve_catch_5.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_5.C	2017-11-03 17:24:20.172023500 +0000
@@ -0,0 +1,82 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fno-omit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+/* Invoke X (P##n) for n in [0, 7].  */
+#define REPEAT8(X, P) \
+  X (P##0) X (P##1) X (P##2) X (P##3) X (P##4) X (P##5) X (P##6) X (P##7)
+
+/* Invoke X (n) for all octal n in [0, 39].  */
+#define REPEAT40(X) \
+  REPEAT8 (X, 0) REPEAT8 (X, 1)  REPEAT8 (X, 2) REPEAT8 (X, 3) REPEAT8 (X, 4)
+
+volatile int testi, sink;
+volatile void *ptr;
+
+/* Take 2 stack arguments and throw to f3.  */
+void __attribute__ ((weak))
+f1 (int x[40][100], int *y, int z1, int z2, int z3, int z4,
+    int z5, int z6, int z7, int z8)
+{
+  /* A wild write to x and y.  */
+  sink = z1;
+  sink = z2;
+  sink = z3;
+  sink = z4;
+  sink = z5;
+  sink = z6;
+  sink = z7;
+  sink = z8;
+  asm volatile ("" ::: "memory");
+  if (y[testi] == x[testi][testi])
+    throw 100;
+}
+
+/* Expect vector work to be done, with spilling of vector registers.  */
+void __attribute__ ((weak))
+f2 (int x[40][100], int *y)
+{
+  /* Create a true variable-sized frame.  */
+  ptr = __builtin_alloca (testi + 40);
+  /* Try to force some spilling.  */
+#define DECLARE(N) int y##N = y[N];
+  REPEAT40 (DECLARE);
+  for (int j = 0; j < 20; ++j)
+    {
+      f1 (x, y, 1, 2, 3, 4, 5, 6, 7, 8);
+#pragma omp simd
+      for (int i = 0; i < 100; ++i)
+	{
+#define INC(N) x[N][i] += y##N;
+	  REPEAT40 (INC);
+	}
+    }
+}
+
+/* Catch an exception thrown from f1, via f2.  */
+void __attribute__ ((weak))
+f3 (int x[40][100], int *y, int *z)
+{
+  volatile int extra = 111;
+  try
+    {
+      f2 (x, y);
+    }
+  catch (int val)
+    {
+      *z = val + extra;
+    }
+}
+
+static int x[40][100];
+static int y[40];
+static int z;
+
+int
+main (void)
+{
+  f3 (x, y, &z);
+  if (z != 211)
+    __builtin_abort ();
+  return 0;
+}
Index: gcc/testsuite/g++.target/aarch64/sve_catch_6.C
===================================================================
--- /dev/null	2017-11-03 10:40:07.002381728 +0000
+++ gcc/testsuite/g++.target/aarch64/sve_catch_6.C	2017-11-03 17:24:20.172023500 +0000
@@ -0,0 +1,5 @@ 
+/* { dg-do run } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer" } */
+/* { dg-options "-O3 -fopenmp-simd -fomit-frame-pointer -march=armv8-a+sve" { target aarch64_sve_hw } } */
+
+#include "sve_catch_5.C"