diff options
| -rw-r--r-- | Documentation/riscv/pmu.txt | 249 | ||||
| -rw-r--r-- | MAINTAINERS | 10 | ||||
| -rw-r--r-- | arch/riscv/Kconfig | 14 | ||||
| -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/perf_event.h | 84 | ||||
| -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/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/traps.c | 2 | ||||
| -rw-r--r-- | arch/riscv/lib/uaccess.S | 19 |
17 files changed, 884 insertions, 15 deletions
diff --git a/Documentation/riscv/pmu.txt b/Documentation/riscv/pmu.txt new file mode 100644 index 000000000000..b29f03a6d82f --- /dev/null +++ b/Documentation/riscv/pmu.txt @@ -0,0 +1,249 @@ +Supporting PMUs on RISC-V platforms +========================================== +Alan Kao <alankao@andestech.com>, Mar 2018 + +Introduction +------------ + +As of this writing, perf_event-related features mentioned in The RISC-V ISA +Privileged Version 1.10 are as follows: +(please check the manual for more details) + +* [m|s]counteren +* mcycle[h], cycle[h] +* minstret[h], instret[h] +* mhpeventx, mhpcounterx[h] + +With such function set only, porting perf would require a lot of work, due to +the lack of the following general architectural performance monitoring features: + +* Enabling/Disabling counters + Counters are just free-running all the time in our case. +* Interrupt caused by counter overflow + No such feature in the spec. +* Interrupt indicator + It is not possible to have many interrupt ports for all counters, so an + interrupt indicator is required for software to tell which counter has + just overflowed. +* Writing to counters + There will be an SBI to support this since the kernel cannot modify the + counters [1]. Alternatively, some vendor considers to implement + hardware-extension for M-S-U model machines to write counters directly. + +This document aims to provide developers a quick guide on supporting their +PMUs in the kernel. The following sections briefly explain perf' mechanism +and todos. + +You may check previous discussions here [1][2]. Also, it might be helpful +to check the appendix for related kernel structures. + + +1. Initialization +----------------- + +*riscv_pmu* is a global pointer of type *struct riscv_pmu*, which contains +various methods according to perf's internal convention and PMU-specific +parameters. One should declare such instance to represent the PMU. By default, +*riscv_pmu* points to a constant structure *riscv_base_pmu*, which has very +basic support to a baseline QEMU model. + +Then he/she can either assign the instance's pointer to *riscv_pmu* so that +the minimal and already-implemented logic can be leveraged, or invent his/her +own *riscv_init_platform_pmu* implementation. + +In other words, existing sources of *riscv_base_pmu* merely provide a +reference implementation. Developers can flexibly decide how many parts they +can leverage, and in the most extreme case, they can customize every function +according to their needs. + + +2. Event Initialization +----------------------- + +When a user launches a perf command to monitor some events, it is first +interpreted by the userspace perf tool into multiple *perf_event_open* +system calls, and then each of them calls to the body of *event_init* +member function that was assigned in the previous step. In *riscv_base_pmu*'s +case, it is *riscv_event_init*. + +The main purpose of this function is to translate the event provided by user +into bitmap, so that HW-related control registers or counters can directly be +manipulated. The translation is based on the mappings and methods provided in +*riscv_pmu*. + +Note that some features can be done in this stage as well: + +(1) interrupt setting, which is stated in the next section; +(2) privilege level setting (user space only, kernel space only, both); +(3) destructor setting. Normally it is sufficient to apply *riscv_destroy_event*; +(4) tweaks for non-sampling events, which will be utilized by functions such as +*perf_adjust_period*, usually something like the follows: + +if (!is_sampling_event(event)) { + hwc->sample_period = x86_pmu.max_period; + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); +} + +In the case of *riscv_base_pmu*, only (3) is provided for now. + + +3. Interrupt +------------ + +3.1. Interrupt Initialization + +This often occurs at the beginning of the *event_init* method. In common +practice, this should be a code segment like + +int x86_reserve_hardware(void) +{ + int err = 0; + + if (!atomic_inc_not_zero(&pmc_refcount)) { + mutex_lock(&pmc_reserve_mutex); + if (atomic_read(&pmc_refcount) == 0) { + if (!reserve_pmc_hardware()) + err = -EBUSY; + else + reserve_ds_buffers(); + } + if (!err) + atomic_inc(&pmc_refcount); + mutex_unlock(&pmc_reserve_mutex); + } + + return err; +} + +And the magic is in *reserve_pmc_hardware*, which usually does atomic +operations to make implemented IRQ accessible from some global function pointer. +*release_pmc_hardware* serves the opposite purpose, and it is used in event +destructors mentioned in previous section. + +(Note: From the implementations in all the architectures, the *reserve/release* +pair are always IRQ settings, so the *pmc_hardware* seems somehow misleading. +It does NOT deal with the binding between an event and a physical counter, +which will be introduced in the next section.) + +3.2. IRQ Structure + +Basically, a IRQ runs the following pseudo code: + +for each hardware counter that triggered this overflow + + get the event of this counter + + // following two steps are defined as *read()*, + // check the section Reading/Writing Counters for details. + count the delta value since previous interrupt + update the event->count (# event occurs) by adding delta, and + event->hw.period_left by subtracting delta + + if the event overflows + sample data + set the counter appropriately for the next overflow + + if the event overflows again + too frequently, throttle this event + fi + fi + +end for + +However as of this writing, none of the RISC-V implementations have designed an +interrupt for perf, so the details are to be completed in the future. + +4. Reading/Writing Counters +--------------------------- + +They seem symmetric but perf treats them quite differently. For reading, there +is a *read* interface in *struct pmu*, but it serves more than just reading. +According to the context, the *read* function not only reads the content of the +counter (event->count), but also updates the left period to the next interrupt +(event->hw.period_left). + +But the core of perf does not need direct write to counters. Writing counters +is hidden behind the abstraction of 1) *pmu->start*, literally start counting so one +has to set the counter to a good value for the next interrupt; 2) inside the IRQ +it should set the counter to the same resonable value. + +Reading is not a problem in RISC-V but writing would need some effort, since +counters are not allowed to be written by S-mode. + + +5. add()/del()/start()/stop() +----------------------------- + +Basic idea: add()/del() adds/deletes events to/from a PMU, and start()/stop() +starts/stop the counter of some event in the PMU. All of them take the same +arguments: *struct perf_event *event* and *int flag*. + +Consider perf as a state machine, then you will find that these functions serve +as the state transition process between those states. +Three states (event->hw.state) are defined: + +* PERF_HES_STOPPED: the counter is stopped +* PERF_HES_UPTODATE: the event->count is up-to-date +* PERF_HES_ARCH: arch-dependent usage ... we don't need this for now + +A normal flow of these state transitions are as follows: + +* A user launches a perf event, resulting in calling to *event_init*. +* When being context-switched in, *add* is called by the perf core, with a flag + PERF_EF_START, which means that the event should be started after it is added. + At this stage, a general event is bound to a physical counter, if any. + The state changes to PERF_HES_STOPPED and PERF_HES_UPTODATE, because it is now + stopped, and the (software) event count does not need updating. +** *start* is then called, and the counter is enabled. + With flag PERF_EF_RELOAD, it writes an appropriate value to the counter (check + previous section for detail). + Nothing is written if the flag does not contain PERF_EF_RELOAD. + The state now is reset to none, because it is neither stopped nor updated + (the counting already started) +* When being context-switched out, *del* is called. It then checks out all the + events in the PMU and calls *stop* to update their counts. +** *stop* is called by *del* + and the perf core with flag PERF_EF_UPDATE, and it often shares the same + subroutine as *read* with the same logic. + The state changes to PERF_HES_STOPPED and PERF_HES_UPTODATE, again. + +** Life cycle of these two pairs: *add* and *del* are called repeatedly as + tasks switch in-and-out; *start* and *stop* is also called when the perf core + needs a quick stop-and-start, for instance, when the interrupt period is being + adjusted. + +Current implementation is sufficient for now and can be easily extended to +features in the future. + +A. Related Structures +--------------------- + +* struct pmu: include/linux/perf_event.h +* struct riscv_pmu: arch/riscv/include/asm/perf_event.h + + Both structures are designed to be read-only. + + *struct pmu* defines some function pointer interfaces, and most of them take +*struct perf_event* as a main argument, dealing with perf events according to +perf's internal state machine (check kernel/events/core.c for details). + + *struct riscv_pmu* defines PMU-specific parameters. The naming follows the +convention of all other architectures. + +* struct perf_event: include/linux/perf_event.h +* struct hw_perf_event + + The generic structure that represents perf events, and the hardware-related +details. + +* struct riscv_hw_events: arch/riscv/include/asm/perf_event.h + + The structure that holds the status of events, has two fixed members: +the number of events and the array of the events. + +References +---------- + +[1] https://github.com/riscv/riscv-linux/pull/124 +[2] https://groups.google.com/a/groups.riscv.org/forum/#!topic/sw-dev/f19TmCNP6yA diff --git a/MAINTAINERS b/MAINTAINERS index cb468a535f32..3b263e2e216a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12179,7 +12179,7 @@ F: drivers/mtd/nand/raw/r852.h RISC-V ARCHITECTURE M: Palmer Dabbelt <palmer@sifive.com> -M: Albert Ou <albert@sifive.com> +M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git S: Supported @@ -12939,6 +12939,14 @@ F: drivers/media/usb/siano/ F: drivers/media/usb/siano/ F: drivers/media/mmc/siano/ +SIFIVE DRIVERS +M: Palmer Dabbelt <palmer@sifive.com> +L: linux-riscv@lists.infradead.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git +S: Supported +K: sifive +N: sifive + SILEAD TOUCHSCREEN DRIVER M: Hans de Goede <hdegoede@redhat.com> L: linux-input@vger.kernel.org diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 42e581a268e1..f12680c9b947 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -32,6 +32,7 @@ config RISCV select HAVE_MEMBLOCK_NODE_MAP 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 @@ -193,6 +194,19 @@ 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" 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/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/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/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/traps.c b/arch/riscv/kernel/traps.c index b99d9dd21fd0..81a1952015a6 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -148,7 +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 |