perf: riscv: preliminary RISC-V support

This patch provide a basic PMU, riscv_base_pmu, which supports two
general hardware event, instructions and cycles.  Furthermore, this
PMU serves as a reference implementation to ease the portings in
the future.

riscv_base_pmu should be able to run on any RISC-V machine that
conforms to the Priv-Spec.  Note that the latest qemu model hasn't
fully support a proper behavior of Priv-Spec 1.10 yet, but work
around should be easy with very small fixes.  Please check
https://github.com/riscv/riscv-qemu/pull/115 for future updates.

Cc: Nick Hu <nickhu@andestech.com>
Cc: Greentime Hu <greentime@andestech.com>
Signed-off-by: Alan Kao <alankao@andestech.com>
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>

arch/riscv/Kconfig

@@ -25,6 +25,7 @@ config RISCV
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_GENERIC_DMA_COHERENT
+	select HAVE_PERF_EVENTS
 	select IRQ_DOMAIN
 	select NO_BOOTMEM
 	select RISCV_ISA_A if SMP
@@ -198,6 +199,19 @@ config RISCV_ISA_C
 config RISCV_ISA_A
 	def_bool y
 
+menu "supported PMU type"
+	depends on PERF_EVENTS
+
+config RISCV_BASE_PMU
+	bool "Base Performance Monitoring Unit"
+	def_bool y
+	help
+	  A base PMU that serves as a reference implementation and has limited
+	  feature of perf.  It can run on any RISC-V machines so serves as the
+	  fallback, but this option can also be disable to reduce kernel size.
+
+endmenu
+
 endmenu
 
 menu "Kernel type"

arch/riscv/include/asm/Kbuild

@@ -25,6 +25,7 @@ generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
+generic-y += local64.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h

arch/riscv/include/asm/perf_event.h

@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 SiFive
+ * Copyright (C) 2018 Andes Technology Corporation
+ *
+ */
+
+#ifndef _ASM_RISCV_PERF_EVENT_H
+#define _ASM_RISCV_PERF_EVENT_H
+
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+
+#define RISCV_BASE_COUNTERS	2
+
+/*
+ * The RISCV_MAX_COUNTERS parameter should be specified.
+ */
+
+#ifdef CONFIG_RISCV_BASE_PMU
+#define RISCV_MAX_COUNTERS	2
+#endif
+
+#ifndef RISCV_MAX_COUNTERS
+#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU."
+#endif
+
+/*
+ * These are the indexes of bits in counteren register *minus* 1,
+ * except for cycle.  It would be coherent if it can directly mapped
+ * to counteren bit definition, but there is a *time* register at
+ * counteren[1].  Per-cpu structure is scarce resource here.
+ *
+ * According to the spec, an implementation can support counter up to
+ * mhpmcounter31, but many high-end processors has at most 6 general
+ * PMCs, we give the definition to MHPMCOUNTER8 here.
+ */
+#define RISCV_PMU_CYCLE		0
+#define RISCV_PMU_INSTRET	1
+#define RISCV_PMU_MHPMCOUNTER3	2
+#define RISCV_PMU_MHPMCOUNTER4	3
+#define RISCV_PMU_MHPMCOUNTER5	4
+#define RISCV_PMU_MHPMCOUNTER6	5
+#define RISCV_PMU_MHPMCOUNTER7	6
+#define RISCV_PMU_MHPMCOUNTER8	7
+
+#define RISCV_OP_UNSUPP		(-EOPNOTSUPP)
+
+struct cpu_hw_events {
+	/* # currently enabled events*/
+	int			n_events;
+	/* currently enabled events */
+	struct perf_event	*events[RISCV_MAX_COUNTERS];
+	/* vendor-defined PMU data */
+	void			*platform;
+};
+
+struct riscv_pmu {
+	struct pmu	*pmu;
+
+	/* generic hw/cache events table */
+	const int	*hw_events;
+	const int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+				       [PERF_COUNT_HW_CACHE_OP_MAX]
+				       [PERF_COUNT_HW_CACHE_RESULT_MAX];
+	/* method used to map hw/cache events */
+	int		(*map_hw_event)(u64 config);
+	int		(*map_cache_event)(u64 config);
+
+	/* max generic hw events in map */
+	int		max_events;
+	/* number total counters, 2(base) + x(general) */
+	int		num_counters;
+	/* the width of the counter */
+	int		counter_width;
+
+	/* vendor-defined PMU features */
+	void		*platform;
+
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	int		irq;
+};
+
+#endif /* _ASM_RISCV_PERF_EVENT_H */

arch/riscv/kernel/Makefile

@@ -39,4 +39,6 @@ obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
+obj-$(CONFIG_PERF_EVENTS)      += perf_event.o
+
 clean: