diff options
Diffstat (limited to 'arch/riscv')
| -rw-r--r-- | arch/riscv/Kconfig | 63 | ||||
| -rw-r--r-- | arch/riscv/Makefile | 3 | ||||
| -rw-r--r-- | arch/riscv/configs/defconfig | 1 | ||||
| -rw-r--r-- | arch/riscv/include/asm/Kbuild | 1 | ||||
| -rw-r--r-- | arch/riscv/include/asm/cacheflush.h | 2 | ||||
| -rw-r--r-- | arch/riscv/include/asm/dma-mapping.h | 15 | ||||
| -rw-r--r-- | arch/riscv/include/asm/pci.h | 3 | ||||
| -rw-r--r-- | arch/riscv/include/asm/perf_event.h | 84 | ||||
| -rw-r--r-- | arch/riscv/include/asm/pgtable-bits.h | 3 | ||||
| -rw-r--r-- | arch/riscv/include/asm/tlbflush.h | 2 | ||||
| -rw-r--r-- | arch/riscv/include/asm/uaccess.h | 8 | ||||
| -rw-r--r-- | arch/riscv/kernel/Makefile | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/cacheinfo.c | 1 | ||||
| -rw-r--r-- | arch/riscv/kernel/mcount.S | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/module.c | 12 | ||||
| -rw-r--r-- | arch/riscv/kernel/perf_event.c | 485 | ||||
| -rw-r--r-- | arch/riscv/kernel/riscv_ksyms.c | 3 | ||||
| -rw-r--r-- | arch/riscv/kernel/setup.c | 2 | ||||
| -rw-r--r-- | arch/riscv/kernel/traps.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/uaccess.S | 19 |
20 files changed, 658 insertions, 71 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index cd4fd85fde84..f12680c9b947 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -3,8 +3,16 @@ # see Documentation/kbuild/kconfig-language.txt. # +config 64BIT + bool + +config 32BIT + bool + config RISCV def_bool y + # even on 32-bit, physical (and DMA) addresses are > 32-bits + select PHYS_ADDR_T_64BIT select OF select OF_EARLY_FLATTREE select OF_IRQ @@ -22,9 +30,9 @@ config RISCV select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - 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 @@ -35,20 +43,14 @@ config RISCV select THREAD_INFO_IN_TASK select RISCV_TIMER select GENERIC_IRQ_MULTI_HANDLER + select ARCH_HAS_PTE_SPECIAL config MMU def_bool y -# even on 32-bit, physical (and DMA) addresses are > 32-bits -config ARCH_PHYS_ADDR_T_64BIT - def_bool y - config ZONE_DMA32 bool - default y - -config ARCH_DMA_ADDR_T_64BIT - def_bool y + default y if 64BIT config PAGE_OFFSET hex @@ -101,21 +103,20 @@ choice config ARCH_RV32I bool "RV32I" - select CPU_SUPPORTS_32BIT_KERNEL select 32BIT - select GENERIC_ASHLDI3 - select GENERIC_ASHRDI3 - select GENERIC_LSHRDI3 + select GENERIC_LIB_ASHLDI3 + select GENERIC_LIB_ASHRDI3 + select GENERIC_LIB_LSHRDI3 config ARCH_RV64I bool "RV64I" - select CPU_SUPPORTS_64BIT_KERNEL select 64BIT select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select SWIOTLB endchoice @@ -171,11 +172,6 @@ config NR_CPUS depends on SMP default "8" -config CPU_SUPPORTS_32BIT_KERNEL - bool -config CPU_SUPPORTS_64BIT_KERNEL - bool - choice prompt "CPU Tuning" default TUNE_GENERIC @@ -198,27 +194,22 @@ config RISCV_ISA_C config RISCV_ISA_A def_bool y -endmenu - -menu "Kernel type" +menu "supported PMU type" + depends on PERF_EVENTS -choice - prompt "Kernel code model" - default 64BIT - -config 32BIT - bool "32-bit kernel" - depends on CPU_SUPPORTS_32BIT_KERNEL +config RISCV_BASE_PMU + bool "Base Performance Monitoring Unit" + def_bool y help - Select this option to build a 32-bit kernel. + 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. -config 64BIT - bool "64-bit kernel" - depends on CPU_SUPPORTS_64BIT_KERNEL - help - Select this option to build a 64-bit kernel. +endmenu -endchoice +endmenu + +menu "Kernel type" source "mm/Kconfig" diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 76e958a5414a..6d4a5f6c3f4f 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -71,6 +71,9 @@ KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) # architectures. It's faster to have GCC emit only aligned accesses. KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +# arch specific predefines for sparse +CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) + head-y := arch/riscv/kernel/head.o core-y += arch/riscv/kernel/ arch/riscv/mm/ diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index bca0eee733b0..07326466871b 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_HVC_RISCV_SBI=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_RADEON=y diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 4286a5f83876..576ffdca06ba 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/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 diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index efd89a88d2d0..8f13074413a7 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -47,7 +47,7 @@ static inline void flush_dcache_page(struct page *page) #else /* CONFIG_SMP */ -#define flush_icache_all() sbi_remote_fence_i(0) +#define flush_icache_all() sbi_remote_fence_i(NULL) void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ diff --git a/arch/riscv/include/asm/dma-mapping.h b/arch/riscv/include/asm/dma-mapping.h new file mode 100644 index 000000000000..8facc1c8fa05 --- /dev/null +++ b/arch/riscv/include/asm/dma-mapping.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _RISCV_ASM_DMA_MAPPING_H +#define _RISCV_ASM_DMA_MAPPING_H 1 + +#ifdef CONFIG_SWIOTLB +#include <linux/swiotlb.h> +static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) +{ + return &swiotlb_dma_ops; +} +#else +#include <asm-generic/dma-mapping.h> +#endif /* CONFIG_SWIOTLB */ + +#endif /* _RISCV_ASM_DMA_MAPPING_H */ diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h index 0f2fc9ef20fc..b3638c505728 100644 --- a/arch/riscv/include/asm/pci.h +++ b/arch/riscv/include/asm/pci.h @@ -26,9 +26,6 @@ /* RISC-V shim does not initialize PCI bus */ #define pcibios_assign_all_busses() 1 -/* We do not have an IOMMU */ -#define PCI_DMA_BUS_IS_PHYS 1 - extern int isa_dma_bridge_buggy; #ifdef CONFIG_PCI diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h new file mode 100644 index 000000000000..0e638a0c3feb --- /dev/null +++ b/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 */ diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 997ddbb1d370..2fa2942be221 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -42,7 +42,4 @@ _PAGE_WRITE | _PAGE_EXEC | \ _PAGE_USER | _PAGE_GLOBAL)) -/* Advertise support for _PAGE_SPECIAL */ -#define __HAVE_ARCH_PTE_SPECIAL - #endif /* _ASM_RISCV_PGTABLE_BITS_H */ diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 7b209aec355d..85c2d8bae957 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -49,7 +49,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, #include <asm/sbi.h> -#define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1) +#define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1) #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0) #define flush_tlb_range(vma, start, end) \ sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 14b0b22fb578..473cfc84e412 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -392,19 +392,21 @@ do { \ }) -extern unsigned long __must_check __copy_user(void __user *to, +extern unsigned long __must_check __asm_copy_to_user(void __user *to, + const void *from, unsigned long n); +extern unsigned long __must_check __asm_copy_from_user(void *to, const void __user *from, unsigned long n); static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) { - return __copy_user(to, from, n); + return __asm_copy_to_user(to, from, n); } static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) { - return __copy_user(to, from, n); + return __asm_copy_from_user(to, from, n); } extern long strncpy_from_user(char *dest, const char __user *src, long count); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 8586dd96c2f0..e1274fc03af4 100644 --- a/arch/riscv/kernel/Makefile +++ b/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: diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index 10ed2749e246..0bc86e5f8f3f 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -20,7 +20,6 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, struct device_node *node, enum cache_type type, unsigned int level) { - this_leaf->of_node = node; this_leaf->level = level; this_leaf->type = type; /* not a sector cache */ diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index ce9bdc57a2a1..5721624886a1 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -126,5 +126,5 @@ do_trace: RESTORE_ABI_STATE ret ENDPROC(_mcount) -EXPORT_SYMBOL(_mcount) #endif +EXPORT_SYMBOL(_mcount) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 5dddba301d0a..1d5e9b934b8c 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -17,6 +17,17 @@ #include <linux/errno.h> #include <linux/moduleloader.h> +static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) +{ + if (v != (u32)v) { + pr_err("%s: value %016llx out of range for 32-bit field\n", + me->name, v); + return -EINVAL; + } + *location = v; + return 0; +} + static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v) { *(u64 *)location = v; @@ -265,6 +276,7 @@ static int apply_r_riscv_sub32_rela(struct module *me, u32 *location, static int (*reloc_handlers_rela[]) (struct module *me, u32 *location, Elf_Addr v) = { + [R_RISCV_32] = apply_r_riscv_32_rela, [R_RISCV_64] = apply_r_riscv_64_rela, [R_RISCV_BRANCH] = apply_r_riscv_branch_rela, [R_RISCV_JAL] = apply_r_riscv_jal_rela, diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c new file mode 100644 index 000000000000..b0e10c4e9f77 --- /dev/null +++ b/arch/riscv/kernel/perf_event.c @@ -0,0 +1,485 @@ +/* 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/interrupt.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]; +} + +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(cycle); + break; + case RISCV_PMU_INSTRET: + val = csr_read(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); + +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; +} + +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 */ } +}; + +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; + } + + perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW); + return 0; +} +arch_initcall(init_hw_perf_events); diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c index 551734248748..f247d6d2137c 100644 --- a/arch/riscv/kernel/riscv_ksyms.c +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -13,6 +13,7 @@ * Assembly functions that may be used (directly or indirectly) by modules */ EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__copy_user); +EXPORT_SYMBOL(__asm_copy_to_user); +EXPORT_SYMBOL(__asm_copy_from_user); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index c11f40c1b2a8..ee44a48faf79 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -29,6 +29,7 @@ #include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/sched/task.h> +#include <linux/swiotlb.h> #include <asm/setup.h> #include <asm/sections.h> @@ -206,6 +207,7 @@ void __init setup_arch(char **cmdline_p) setup_bootmem(); paging_init(); unflatten_device_tree(); + swiotlb_init(1); #ifdef CONFIG_SMP setup_smp(); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 93132cb59184..81a1952015a6 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -63,18 +63,6 @@ void die(struct pt_regs *regs, const char *str) do_exit(SIGSEGV); } -static inline void do_trap_siginfo(int signo, int code, - unsigned long addr, struct task_struct *tsk) -{ - siginfo_t info; - - info.si_signo = signo; - info.si_errno = 0; - info.si_code = code; - info.si_addr = (void __user *)addr; - force_sig_info(signo, &info, tsk); -} - void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr, struct task_struct *tsk) { @@ -87,7 +75,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, show_regs(regs); } - do_trap_siginfo(signo, code, addr, tsk); + force_sig_fault(signo, code, (void __user *)addr, tsk); } static void do_trap_error(struct pt_regs *regs, int signo, int code, @@ -149,7 +137,7 @@ asmlinkage void do_trap_break(struct pt_regs *regs) } #endif /* CONFIG_GENERIC_BUG */ - do_trap_siginfo(SIGTRAP, TRAP_BRKPT, regs->sepc, current); + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc), current); regs->sepc += 0x4; } @@ -160,7 +148,7 @@ int is_valid_bugaddr(unsigned long pc) if (pc < PAGE_OFFSET) return 0; - if (probe_kernel_address((bug_insn_t __user *)pc, insn)) + if (probe_kernel_address((bug_insn_t *)pc, insn)) return 0; return (insn == __BUG_INSN); } diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index 58fb2877c865..399e6f0c2d98 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -13,7 +13,8 @@ _epc: .previous .endm -ENTRY(__copy_user) +ENTRY(__asm_copy_to_user) +ENTRY(__asm_copy_from_user) /* Enable access to user memory */ li t6, SR_SUM @@ -63,7 +64,8 @@ ENTRY(__copy_user) addi a0, a0, 1 bltu a1, a3, 5b j 3b -ENDPROC(__copy_user) +ENDPROC(__asm_copy_to_user) +ENDPROC(__asm_copy_from_user) ENTRY(__clear_user) @@ -84,7 +86,7 @@ ENTRY(__clear_user) bgeu t0, t1, 2f bltu a0, t0, 4f 1: - fixup REG_S, zero, (a0), 10f + fixup REG_S, zero, (a0), 11f addi a0, a0, SZREG bltu a0, t1, 1b 2: @@ -96,12 +98,12 @@ ENTRY(__clear_user) li a0, 0 ret 4: /* Edge case: unalignment */ - fixup sb, zero, (a0), 10f + fixup sb, zero, (a0), 11f addi a0, a0, 1 bltu a0, t0, 4b j 1b 5: /* Edge case: remainder */ - fixup sb, zero, (a0), 10f + fixup sb, zero, (a0), 11f addi a0, a0, 1 bltu a0, a3, 5b j 3b @@ -109,9 +111,14 @@ ENDPROC(__clear_user) .section .fixup,"ax" .balign 4 + /* Fixup code for __copy_user(10) and __clear_user(11) */ 10: /* Disable access to user memory */ csrs sstatus, t6 - sub a0, a3, a0 + mv a0, a2 + ret +11: + csrs sstatus, t6 + mv a0, a1 ret .previous |