[RFC PATCH 2/2] sparc64: Support PERF_SAMPLE_REGS_USER and PERF_SAMPLE_STACK_USER

[Stian Halseth]

Select HAVE_PERF_REGS and HAVE_PERF_USER_STACK_DUMP and add the
perf_regs implementation. The exposed registers mirror struct pt_regs:
%g0-%g7, %o0-%o7 (named from the user's point of view; pt_regs calls
them UREG_I*), %tstate, PC, NPC and %y. %o6 is reported as held in the
register, i.e. with the 2047 stack bias for a 64-bit task, the same as
ptrace and user_stack_pointer(). Values of a 32-bit task are truncated
to 32 bits as genregs32_get() does, since the hardware does not
zero-extend them.

perf_arch_prepare_ustack() flushes the user register windows so the
sampled window's %l and %i registers are in the dumped stack, where a
DWARF unwinder needs them: the CFI of a function after `save` defines
the CFA in terms of %i6.

This makes perf record --call-graph dwarf and eu-stackprof usable on
sparc64.

Signed-off-by: Stian Halseth <stian@xxxxxx>
---
 arch/sparc/Kconfig                      |  2 +
 arch/sparc/include/asm/perf_event.h     |  3 ++
 arch/sparc/include/uapi/asm/perf_regs.h | 33 +++++++++++++
 arch/sparc/kernel/Makefile              |  2 +-
 arch/sparc/kernel/perf_regs.c           | 65 +++++++++++++++++++++++++
 5 files changed, 104 insertions(+), 1 deletion(-)
 create mode 100644 arch/sparc/include/uapi/asm/perf_regs.h
 create mode 100644 arch/sparc/kernel/perf_regs.c

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ab77d3f2536e..9d7f575f359d 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -93,6 +93,8 @@ config SPARC64
 	select RTC_DRV_SUN4V
 	select RTC_DRV_STARFIRE
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select PERF_USE_VMALLOC
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select HAVE_C_RECORDMCOUNT
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index c2aec0c7f4f5..03f1ab1618b9 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -25,6 +25,9 @@ do {							\
 	(regs)->u_regs[UREG_I6] = _fp;			\
 	(regs)->u_regs[UREG_I7] = _i7;			\
 } while (0)
+
+void perf_arch_prepare_ustack(void);
+#define perf_arch_prepare_ustack	perf_arch_prepare_ustack
 #endif
 
 #endif
diff --git a/arch/sparc/include/uapi/asm/perf_regs.h b/arch/sparc/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..17f14335d6c0
--- /dev/null
+++ b/arch/sparc/include/uapi/asm/perf_regs.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_SPARC_PERF_REGS_H
+#define _UAPI_ASM_SPARC_PERF_REGS_H
+
+/*
+ * Mirrors struct pt_regs.  O6 is %sp as held in the register, i.e. biased
+ * by 2047 for a 64-bit task.
+ */
+enum perf_event_sparc_regs {
+	PERF_REG_SPARC_G0,
+	PERF_REG_SPARC_G1,
+	PERF_REG_SPARC_G2,
+	PERF_REG_SPARC_G3,
+	PERF_REG_SPARC_G4,
+	PERF_REG_SPARC_G5,
+	PERF_REG_SPARC_G6,
+	PERF_REG_SPARC_G7,
+	PERF_REG_SPARC_O0,
+	PERF_REG_SPARC_O1,
+	PERF_REG_SPARC_O2,
+	PERF_REG_SPARC_O3,
+	PERF_REG_SPARC_O4,
+	PERF_REG_SPARC_O5,
+	PERF_REG_SPARC_O6,
+	PERF_REG_SPARC_O7,
+	PERF_REG_SPARC_TSTATE,
+	PERF_REG_SPARC_PC,
+	PERF_REG_SPARC_NPC,
+	PERF_REG_SPARC_Y,
+	PERF_REG_SPARC_MAX
+};
+
+#endif /* _UAPI_ASM_SPARC_PERF_REGS_H */
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 497b5714fa8f..a3dd92247c3b 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -113,7 +113,7 @@ obj-$(CONFIG_AUDIT)     += audit.o
 audit--$(CONFIG_AUDIT)  := compat_audit.o
 obj-$(CONFIG_COMPAT)    += $(audit--y)
 
-pc--$(CONFIG_PERF_EVENTS) := perf_event.o
+pc--$(CONFIG_PERF_EVENTS) := perf_event.o perf_regs.o
 obj-$(CONFIG_SPARC64)	+= $(pc--y)
 
 obj-$(CONFIG_UPROBES)	+= uprobes.o
diff --git a/arch/sparc/kernel/perf_regs.c b/arch/sparc/kernel/perf_regs.c
new file mode 100644
index 000000000000..644a0a11cb90
--- /dev/null
+++ b/arch/sparc/kernel/perf_regs.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/perf_event.h>
+#include <linux/perf_regs.h>
+#include <linux/sched/task_stack.h>
+#include <asm/cacheflush.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	u64 val;
+
+	switch (idx) {
+	case PERF_REG_SPARC_G0 ... PERF_REG_SPARC_O7:
+		val = regs->u_regs[idx];
+		break;
+	case PERF_REG_SPARC_TSTATE:
+		return regs->tstate;
+	case PERF_REG_SPARC_PC:
+		val = regs->tpc;
+		break;
+	case PERF_REG_SPARC_NPC:
+		val = regs->tnpc;
+		break;
+	case PERF_REG_SPARC_Y:
+		return regs->y;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	if (test_thread_flag(TIF_32BIT))
+		val = (u32)val;
+
+	return val;
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_SPARC_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_32BIT))
+		return PERF_SAMPLE_REGS_ABI_32;
+
+	return PERF_SAMPLE_REGS_ABI_64;
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
+
+void perf_arch_prepare_ustack(void)
+{
+	flushw_user();
+}
-- 
2.55.0