perf: RISC-V: Add support for SBI PMU and Sscofpmf

This series improves perf support for RISC-V based system using SBI PMU
and Sscofpmf extensions, by adding a new generic RISC-V perf framework
along with a pair of drivers: one that usese the new
performance-monitoring extensions and one that keeps support for the
existing systems that only have the legacy counters.

Tested-by: Nikita Shubin <n.shubin@yadro.com>

* palmer/riscv-pmu:
  MAINTAINERS: Add entry for RISC-V PMU drivers
  Documentation: riscv: Remove the old documentation
  RISC-V: Add sscofpmf extension support
  RISC-V: Add perf platform driver based on SBI PMU extension
  RISC-V: Add RISC-V SBI PMU extension definitions
  RISC-V: Add a simple platform driver for RISC-V legacy perf
  RISC-V: Add a perf core library for pmu drivers
  RISC-V: Add CSR encodings for all HPMCOUNTERS
  RISC-V: Remove the current perf implementation

9 files changed, 164 insertions, 572 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 81682a152800..339ba6f6580d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -333,19 +333,6 @@ config RISCV_ISA_C
 
 	   If you don't know what to do here, say 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
-
 config FPU
 	bool "FPU support"
 	default y
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 299abdef0cd6..e935f27b10fd 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -66,6 +66,7 @@
 #define IRQ_S_EXT		9
 #define IRQ_VS_EXT		10
 #define IRQ_M_EXT		11
+#define IRQ_PMU_OVF		13
 
 /* Exception causes */
 #define EXC_INST_MISALIGNED	0
@@ -151,9 +152,69 @@
 #define CSR_CYCLE		0xc00
 #define CSR_TIME		0xc01
 #define CSR_INSTRET		0xc02
+#define CSR_HPMCOUNTER3		0xc03
+#define CSR_HPMCOUNTER4		0xc04
+#define CSR_HPMCOUNTER5		0xc05
+#define CSR_HPMCOUNTER6		0xc06
+#define CSR_HPMCOUNTER7		0xc07
+#define CSR_HPMCOUNTER8		0xc08
+#define CSR_HPMCOUNTER9		0xc09
+#define CSR_HPMCOUNTER10	0xc0a
+#define CSR_HPMCOUNTER11	0xc0b
+#define CSR_HPMCOUNTER12	0xc0c
+#define CSR_HPMCOUNTER13	0xc0d
+#define CSR_HPMCOUNTER14	0xc0e
+#define CSR_HPMCOUNTER15	0xc0f
+#define CSR_HPMCOUNTER16	0xc10
+#define CSR_HPMCOUNTER17	0xc11
+#define CSR_HPMCOUNTER18	0xc12
+#define CSR_HPMCOUNTER19	0xc13
+#define CSR_HPMCOUNTER20	0xc14
+#define CSR_HPMCOUNTER21	0xc15
+#define CSR_HPMCOUNTER22	0xc16
+#define CSR_HPMCOUNTER23	0xc17
+#define CSR_HPMCOUNTER24	0xc18
+#define CSR_HPMCOUNTER25	0xc19
+#define CSR_HPMCOUNTER26	0xc1a
+#define CSR_HPMCOUNTER27	0xc1b
+#define CSR_HPMCOUNTER28	0xc1c
+#define CSR_HPMCOUNTER29	0xc1d
+#define CSR_HPMCOUNTER30	0xc1e
+#define CSR_HPMCOUNTER31	0xc1f
 #define CSR_CYCLEH		0xc80
 #define CSR_TIMEH		0xc81
 #define CSR_INSTRETH		0xc82
+#define CSR_HPMCOUNTER3H	0xc83
+#define CSR_HPMCOUNTER4H	0xc84
+#define CSR_HPMCOUNTER5H	0xc85
+#define CSR_HPMCOUNTER6H	0xc86
+#define CSR_HPMCOUNTER7H	0xc87
+#define CSR_HPMCOUNTER8H	0xc88
+#define CSR_HPMCOUNTER9H	0xc89
+#define CSR_HPMCOUNTER10H	0xc8a
+#define CSR_HPMCOUNTER11H	0xc8b
+#define CSR_HPMCOUNTER12H	0xc8c
+#define CSR_HPMCOUNTER13H	0xc8d
+#define CSR_HPMCOUNTER14H	0xc8e
+#define CSR_HPMCOUNTER15H	0xc8f
+#define CSR_HPMCOUNTER16H	0xc90
+#define CSR_HPMCOUNTER17H	0xc91
+#define CSR_HPMCOUNTER18H	0xc92
+#define CSR_HPMCOUNTER19H	0xc93
+#define CSR_HPMCOUNTER20H	0xc94
+#define CSR_HPMCOUNTER21H	0xc95
+#define CSR_HPMCOUNTER22H	0xc96
+#define CSR_HPMCOUNTER23H	0xc97
+#define CSR_HPMCOUNTER24H	0xc98
+#define CSR_HPMCOUNTER25H	0xc99
+#define CSR_HPMCOUNTER26H	0xc9a
+#define CSR_HPMCOUNTER27H	0xc9b
+#define CSR_HPMCOUNTER28H	0xc9c
+#define CSR_HPMCOUNTER29H	0xc9d
+#define CSR_HPMCOUNTER30H	0xc9e
+#define CSR_HPMCOUNTER31H	0xc9f
+
+#define CSR_SSCOUNTOVF		0xda0
 
 #define CSR_SSTATUS		0x100
 #define CSR_SIE			0x104
@@ -241,7 +302,10 @@
 # define RV_IRQ_SOFT		IRQ_S_SOFT
 # define RV_IRQ_TIMER	IRQ_S_TIMER
 # define RV_IRQ_EXT		IRQ_S_EXT
-#endif /* CONFIG_RISCV_M_MODE */
+# define RV_IRQ_PMU	IRQ_PMU_OVF
+# define SIP_LCOFIP     (_AC(0x1, UL) << IRQ_PMU_OVF)
+
+#endif /* !CONFIG_RISCV_M_MODE */
 
 /* IE/IP (Supervisor/Machine Interrupt Enable/Pending) flags */
 #define IE_SIE		(_AC(0x1, UL) << RV_IRQ_SOFT)
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 691fc9c8099b..0734e42f74f2 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -51,6 +51,7 @@ extern unsigned long elf_hwcap;
  * available logical extension id.
  */
 enum riscv_isa_ext_id {
+	RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
 	RISCV_ISA_EXT_ID_MAX = RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h
index 062efd3a1d5d..d42c901f9a97 100644
--- a/arch/riscv/include/asm/perf_event.h
+++ b/arch/riscv/include/asm/perf_event.h
@@ -9,77 +9,5 @@
 #define _ASM_RISCV_PERF_EVENT_H
 
 #include <linux/perf_event.h>
-#include <linux/ptrace.h>
-#include <linux/interrupt.h>
-
-#ifdef CONFIG_RISCV_BASE_PMU
-#define RISCV_BASE_COUNTERS	2
-
-/*
- * The RISCV_MAX_COUNTERS parameter should be specified.
- */
-
-#define RISCV_MAX_COUNTERS	2
-
-/*
- * 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
-#ifdef CONFIG_PERF_EVENTS
 #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs
-#endif
-
 #endif /* _ASM_RISCV_PERF_EVENT_H */
diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
index d1c37479d828..4a430ae60eaa 100644
--- a/arch/riscv/include/asm/sbi.h
+++ b/arch/riscv/include/asm/sbi.h
@@ -29,6 +29,7 @@ enum sbi_ext_id {
 	SBI_EXT_RFENCE = 0x52464E43,
 	SBI_EXT_HSM = 0x48534D,
 	SBI_EXT_SRST = 0x53525354,
+	SBI_EXT_PMU = 0x504D55,
 
 	/* Experimentals extensions must lie within this range */
 	SBI_EXT_EXPERIMENTAL_START = 0x08000000,
@@ -95,6 +96,98 @@ enum sbi_srst_reset_reason {
 	SBI_SRST_RESET_REASON_SYS_FAILURE,
 };
 
+enum sbi_ext_pmu_fid {
+	SBI_EXT_PMU_NUM_COUNTERS = 0,
+	SBI_EXT_PMU_COUNTER_GET_INFO,
+	SBI_EXT_PMU_COUNTER_CFG_MATCH,
+	SBI_EXT_PMU_COUNTER_START,
+	SBI_EXT_PMU_COUNTER_STOP,
+	SBI_EXT_PMU_COUNTER_FW_READ,
+};
+
+#define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(55, 0)
+#define RISCV_PMU_RAW_EVENT_IDX 0x20000
+
+/** General pmu event codes specified in SBI PMU extension */
+enum sbi_pmu_hw_generic_events_t {
+	SBI_PMU_HW_NO_EVENT			= 0,
+	SBI_PMU_HW_CPU_CYCLES			= 1,
+	SBI_PMU_HW_INSTRUCTIONS			= 2,
+	SBI_PMU_HW_CACHE_REFERENCES		= 3,
+	SBI_PMU_HW_CACHE_MISSES			= 4,
+	SBI_PMU_HW_BRANCH_INSTRUCTIONS		= 5,
+	SBI_PMU_HW_BRANCH_MISSES		= 6,
+	SBI_PMU_HW_BUS_CYCLES			= 7,
+	SBI_PMU_HW_STALLED_CYCLES_FRONTEND	= 8,
+	SBI_PMU_HW_STALLED_CYCLES_BACKEND	= 9,
+	SBI_PMU_HW_REF_CPU_CYCLES		= 10,
+
+	SBI_PMU_HW_GENERAL_MAX,
+};
+
+/**
+ * Special "firmware" events provided by the firmware, even if the hardware
+ * does not support performance events. These events are encoded as a raw
+ * event type in Linux kernel perf framework.
+ */
+enum sbi_pmu_fw_generic_events_t {
+	SBI_PMU_FW_MISALIGNED_LOAD	= 0,
+	SBI_PMU_FW_MISALIGNED_STORE	= 1,
+	SBI_PMU_FW_ACCESS_LOAD		= 2,
+	SBI_PMU_FW_ACCESS_STORE		= 3,
+	SBI_PMU_FW_ILLEGAL_INSN		= 4,
+	SBI_PMU_FW_SET_TIMER		= 5,
+	SBI_PMU_FW_IPI_SENT		= 6,
+	SBI_PMU_FW_IPI_RECVD		= 7,
+	SBI_PMU_FW_FENCE_I_SENT		= 8,
+	SBI_PMU_FW_FENCE_I_RECVD	= 9,
+	SBI_PMU_FW_SFENCE_VMA_SENT	= 10,
+	SBI_PMU_FW_SFENCE_VMA_RCVD	= 11,
+	SBI_PMU_FW_SFENCE_VMA_ASID_SENT	= 12,
+	SBI_PMU_FW_SFENCE_VMA_ASID_RCVD	= 13,
+
+	SBI_PMU_FW_HFENCE_GVMA_SENT	= 14,
+	SBI_PMU_FW_HFENCE_GVMA_RCVD	= 15,
+	SBI_PMU_FW_HFENCE_GVMA_VMID_SENT = 16,
+	SBI_PMU_FW_HFENCE_GVMA_VMID_RCVD = 17,
+
+	SBI_PMU_FW_HFENCE_VVMA_SENT	= 18,
+	SBI_PMU_FW_HFENCE_VVMA_RCVD	= 19,
+	SBI_PMU_FW_HFENCE_VVMA_ASID_SENT = 20,
+	SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD = 21,
+	SBI_PMU_FW_MAX,
+};
+
+/* SBI PMU event types */
+enum sbi_pmu_event_type {
+	SBI_PMU_EVENT_TYPE_HW = 0x0,
+	SBI_PMU_EVENT_TYPE_CACHE = 0x1,
+	SBI_PMU_EVENT_TYPE_RAW = 0x2,
+	SBI_PMU_EVENT_TYPE_FW = 0xf,
+};
+
+/* SBI PMU event types */
+enum sbi_pmu_ctr_type {
+	SBI_PMU_CTR_TYPE_HW = 0x0,
+	SBI_PMU_CTR_TYPE_FW,
+};
+
+/* Flags defined for config matching function */
+#define SBI_PMU_CFG_FLAG_SKIP_MATCH	(1 << 0)
+#define SBI_PMU_CFG_FLAG_CLEAR_VALUE	(1 << 1)
+#define SBI_PMU_CFG_FLAG_AUTO_START	(1 << 2)
+#define SBI_PMU_CFG_FLAG_SET_VUINH	(1 << 3)
+#define SBI_PMU_CFG_FLAG_SET_VSNH	(1 << 4)
+#define SBI_PMU_CFG_FLAG_SET_UINH	(1 << 5)
+#define SBI_PMU_CFG_FLAG_SET_SINH	(1 << 6)
+#define SBI_PMU_CFG_FLAG_SET_MINH	(1 << 7)
+
+/* Flags defined for counter start function */
+#define SBI_PMU_START_FLAG_SET_INIT_VALUE (1 << 0)
+
+/* Flags defined for counter stop function */
+#define SBI_PMU_STOP_FLAG_RESET (1 << 0)
+
 #define SBI_SPEC_VERSION_DEFAULT	0x1
 #define SBI_SPEC_VERSION_MAJOR_SHIFT	24
 #define SBI_SPEC_VERSION_MAJOR_MASK	0x7f
@@ -108,6 +201,8 @@ enum sbi_srst_reset_reason {
 #define SBI_ERR_DENIED		-4
 #define SBI_ERR_INVALID_ADDRESS	-5
 #define SBI_ERR_ALREADY_AVAILABLE -6
+#define SBI_ERR_ALREADY_STARTED -7
+#define SBI_ERR_ALREADY_STOPPED -8
 
 extern unsigned long sbi_spec_version;
 struct sbiret {
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 612556faa527..fb63b462ff85 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -51,7 +51,6 @@ obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= mcount-dyn.o
 
-obj-$(CONFIG_RISCV_BASE_PMU)	+= perf_event.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_callchain.o
 obj-$(CONFIG_HAVE_PERF_REGS)	+= perf_regs.o
 obj-$(CONFIG_RISCV_SBI)		+= sbi.o
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index ecc2a09a66a9..d2a936195295 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -87,6 +87,7 @@ int riscv_of_parent_hartid(struct device_node *node)
  *    extensions by an underscore.
  */
 static struct riscv_isa_ext_data isa_ext_arr[] = {
+	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
 	__RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX),
 };
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index a43c08af5f4b..1b2d42d7f589 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -190,6 +190,8 @@ void __init riscv_fill_hwcap(void)
 			if (!ext_long) {
 				this_hwcap |= isa2hwcap[(unsigned char)(*ext)];
 				set_bit(*ext - 'a', this_isa);
+			} else {
+				SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
 			}
 #undef SET_ISA_EXT_MAP
 		}
diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c
deleted file mode 100644
index c835f0362d94..000000000000
--- a/arch/riscv/kernel/perf_event.c
+++ /dev/null
@@ -1,485 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
- * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
- * Copyright (C) 2009 Jaswinder Singh Rajput
- * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
- * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
- * Copyright (C) 2009 Google, Inc., Stephane Eranian
- * Copyright 2014 Tilera Corporation. All Rights Reserved.
- * Copyright (C) 2018 Andes Technology Corporation
- *
- * Perf_events support for RISC-V platforms.
- *
- * Since the spec. (as of now, Priv-Spec 1.10) does not provide enough
- * functionality for perf event to fully work, this file provides
- * the very basic framework only.
- *
- * For platform portings, please check Documentations/riscv/pmu.txt.
- *
- * The Copyright line includes x86 and tile ones.
- */
-
-#include <linux/kprobes.h>
-#include <linux/kernel.h>
-#include <linux/kdebug.h>
-#include <linux/mutex.h>
-#include <linux/bitmap.h>
-#include <linux/irq.h>
-#include <linux/perf_event.h>
-#include <linux/atomic.h>
-#include <linux/of.h>
-#include <asm/perf_event.h>
-
-static const struct riscv_pmu *riscv_pmu __read_mostly;
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
-
-/*
- * Hardware & cache maps and their methods
- */
-
-static const int riscv_hw_event_map[] = {
-	[PERF_COUNT_HW_CPU_CYCLES]		= RISCV_PMU_CYCLE,
-	[PERF_COUNT_HW_INSTRUCTIONS]		= RISCV_PMU_INSTRET,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= RISCV_OP_UNSUPP,
-	[PERF_COUNT_HW_CACHE_MISSES]		= RISCV_OP_UNSUPP,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= RISCV_OP_UNSUPP,
-	[PERF_COUNT_HW_BRANCH_MISSES]		= RISCV_OP_UNSUPP,
-	[PERF_COUNT_HW_BUS_CYCLES]		= RISCV_OP_UNSUPP,
-};
-
-#define C(x) PERF_COUNT_HW_CACHE_##x
-static const int riscv_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
-[PERF_COUNT_HW_CACHE_OP_MAX]
-[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-	[C(DTLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] =  RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] =  RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
-			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
-		},
-	},
-};
-
-static int riscv_map_hw_event(u64 config)
-{
-	if (config >= riscv_pmu->max_events)
-		return -EINVAL;
-
-	return riscv_pmu->hw_events[config];
-}
-
-static int riscv_map_cache_decode(u64 config, unsigned int *type,
-			   unsigned int *op, unsigned int *result)
-{
-	return -ENOENT;
-}
-
-static int riscv_map_cache_event(u64 config)
-{
-	unsigned int type, op, result;
-	int err = -ENOENT;
-		int code;
-
-	err = riscv_map_cache_decode(config, &type, &op, &result);
-	if (!riscv_pmu->cache_events || err)
-		return err;
-
-	if (type >= PERF_COUNT_HW_CACHE_MAX ||
-	    op >= PERF_COUNT_HW_CACHE_OP_MAX ||
-	    result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
-		return -EINVAL;
-
-	code = (*riscv_pmu->cache_events)[type][op][result];
-	if (code == RISCV_OP_UNSUPP)
-		return -EINVAL;
-
-	return code;
-}
-
-/*
- * Low-level functions: reading/writing counters
- */
-
-static inline u64 read_counter(int idx)
-{
-	u64 val = 0;
-
-	switch (idx) {
-	case RISCV_PMU_CYCLE:
-		val = csr_read(CSR_CYCLE);
-		break;
-	case RISCV_PMU_INSTRET:
-		val = csr_read(CSR_INSTRET);
-		break;
-	default:
-		WARN_ON_ONCE(idx < 0 ||	idx > RISCV_MAX_COUNTERS);
-		return -EINVAL;
-	}
-
-	return val;
-}
-
-static inline void write_counter(int idx, u64 value)
-{
-	/* currently not supported */
-	WARN_ON_ONCE(1);
-}
-
-/*
- * pmu->read: read and update the counter
- *
- * Other architectures' implementation often have a xxx_perf_event_update
- * routine, which can return counter values when called in the IRQ, but
- * return void when being called by the pmu->read method.
- */
-static void riscv_pmu_read(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	u64 prev_raw_count, new_raw_count;
-	u64 oldval;
-	int idx = hwc->idx;
-	u64 delta;
-
-	do {
-		prev_raw_count = local64_read(&hwc->prev_count);
-		new_raw_count = read_counter(idx);
-
-		oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-					 new_raw_count);
-	} while (oldval != prev_raw_count);
-
-	/*
-	 * delta is the value to update the counter we maintain in the kernel.
-	 */
-	delta = (new_raw_count - prev_raw_count) &
-		((1ULL << riscv_pmu->counter_width) - 1);
-	local64_add(delta, &event->count);
-	/*
-	 * Something like local64_sub(delta, &hwc->period_left) here is
-	 * needed if there is an interrupt for perf.
-	 */
-}
-
-/*
- * State transition functions:
- *
- * stop()/start() & add()/del()
- */
-
-/*
- * pmu->stop: stop the counter
- */
-static void riscv_pmu_stop(struct perf_event *event, int flags)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-	hwc->state |= PERF_HES_STOPPED;
-
-	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		riscv_pmu->pmu->read(event);
-		hwc->state |= PERF_HES_UPTODATE;
-	}
-}
-
-/*
- * pmu->start: start the event.
- */
-static void riscv_pmu_start(struct perf_event *event, int flags)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return;
-
-	if (flags & PERF_EF_RELOAD) {
-		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
-
-		/*
-		 * Set the counter to the period to the next interrupt here,
-		 * if you have any.
-		 */
-	}
-
-	hwc->state = 0;
-	perf_event_update_userpage(event);
-
-	/*
-	 * Since we cannot write to counters, this serves as an initialization
-	 * to the delta-mechanism in pmu->read(); otherwise, the delta would be
-	 * wrong when pmu->read is called for the first time.
-	 */
-	local64_set(&hwc->prev_count, read_counter(hwc->idx));
-}
-
-/*
- * pmu->add: add the event to PMU.
- */
-static int riscv_pmu_add(struct perf_event *event, int flags)
-{
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (cpuc->n_events == riscv_pmu->num_counters)
-		return -ENOSPC;
-
-	/*
-	 * We don't have general conunters, so no binding-event-to-counter
-	 * process here.
-	 *
-	 * Indexing using hwc->config generally not works, since config may
-	 * contain extra information, but here the only info we have in
-	 * hwc->config is the event index.
-	 */
-	hwc->idx = hwc->config;
-	cpuc->events[hwc->idx] = event;
-	cpuc->n_events++;
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-
-	if (flags & PERF_EF_START)
-		riscv_pmu->pmu->start(event, PERF_EF_RELOAD);
-
-	return 0;
-}
-
-/*
- * pmu->del: delete the event from PMU.
- */
-static void riscv_pmu_del(struct perf_event *event, int flags)
-{
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-
-	cpuc->events[hwc->idx] = NULL;
-	cpuc->n_events--;
-	riscv_pmu->pmu->stop(event, PERF_EF_UPDATE);
-	perf_event_update_userpage(event);
-}
-
-/*
- * Interrupt: a skeletion for reference.
- */
-
-static DEFINE_MUTEX(pmc_reserve_mutex);
-
-static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
-{
-	return IRQ_NONE;
-}
-
-static int reserve_pmc_hardware(void)
-{
-	int err = 0;
-
-	mutex_lock(&pmc_reserve_mutex);
-	if (riscv_pmu->irq >= 0 && riscv_pmu->handle_irq) {
-		err = request_irq(riscv_pmu->irq, riscv_pmu->handle_irq,
-				  IRQF_PERCPU, "riscv-base-perf", NULL);
-	}
-	mutex_unlock(&pmc_reserve_mutex);
-
-	return err;
-}
-
-static void release_pmc_hardware(void)
-{
-	mutex_lock(&pmc_reserve_mutex);
-	if (riscv_pmu->irq >= 0)
-		free_irq(riscv_pmu->irq, NULL);
-	mutex_unlock(&pmc_reserve_mutex);
-}
-
-/*
- * Event Initialization/Finalization
- */
-
-static atomic_t riscv_active_events = ATOMIC_INIT(0);
-
-static void riscv_event_destroy(struct perf_event *event)
-{
-	if (atomic_dec_return(&riscv_active_events) == 0)
-		release_pmc_hardware();
-}
-
-static int riscv_event_init(struct perf_event *event)
-{
-	struct perf_event_attr *attr = &event->attr;
-	struct hw_perf_event *hwc = &event->hw;
-	int err;
-	int code;
-
-	if (atomic_inc_return(&riscv_active_events) == 1) {
-		err = reserve_pmc_hardware();
-
-		if (err) {
-			pr_warn("PMC hardware not available\n");
-			atomic_dec(&riscv_active_events);
-			return -EBUSY;
-		}
-	}
-
-	switch (event->attr.type) {
-	case PERF_TYPE_HARDWARE:
-		code = riscv_pmu->map_hw_event(attr->config);
-		break;
-	case PERF_TYPE_HW_CACHE:
-		code = riscv_pmu->map_cache_event(attr->config);
-		break;
-	case PERF_TYPE_RAW:
-		return -EOPNOTSUPP;
-	default:
-		return -ENOENT;
-	}
-
-	event->destroy = riscv_event_destroy;
-	if (code < 0) {
-		event->destroy(event);
-		return code;
-	}
-
-	/*
-	 * idx is set to -1 because the index of a general event should not be
-	 * decided until binding to some counter in pmu->add().
-	 *
-	 * But since we don't have such support, later in pmu->add(), we just
-	 * use hwc->config as the index instead.
-	 */
-	hwc->config = code;
-	hwc->idx = -1;
-
-	return 0;
-}
-
-/*
- * Initialization
- */
-
-static struct pmu min_pmu = {
-	.name		= "riscv-base",
-	.event_init	= riscv_event_init,
-	.add		= riscv_pmu_add,
-	.del		= riscv_pmu_del,
-	.start		= riscv_pmu_start,
-	.stop		= riscv_pmu_stop,
-	.read		= riscv_pmu_read,
-};
-
-static const struct riscv_pmu riscv_base_pmu = {
-	.pmu = &min_pmu,
-	.max_events = ARRAY_SIZE(riscv_hw_event_map),
-	.map_hw_event = riscv_map_hw_event,
-	.hw_events = riscv_hw_event_map,
-	.map_cache_event = riscv_map_cache_event,
-	.cache_events = &riscv_cache_event_map,
-	.counter_width = 63,
-	.num_counters = RISCV_BASE_COUNTERS + 0,
-	.handle_irq = &riscv_base_pmu_handle_irq,
-
-	/* This means this PMU has no IRQ. */
-	.irq = -1,
-};
-
-static const struct of_device_id riscv_pmu_of_ids[] = {
-	{.compatible = "riscv,base-pmu",	.data = &riscv_base_pmu},
-	{ /* sentinel value */ }
-};
-
-static int __init init_hw_perf_events(void)
-{
-	struct device_node *node = of_find_node_by_type(NULL, "pmu");
-	const struct of_device_id *of_id;
-
-	riscv_pmu = &riscv_base_pmu;
-
-	if (node) {
-		of_id = of_match_node(riscv_pmu_of_ids, node);
-
-		if (of_id)
-			riscv_pmu = of_id->data;
-		of_node_put(node);
-	}
-
-	perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW);
-	return 0;
-}
-arch_initcall(init_hw_perf_events);