diff options
-rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 7 | ||||
-rw-r--r-- | Documentation/admin-guide/sysctl/kernel.rst | 27 | ||||
-rw-r--r-- | arch/riscv/Kconfig | 19 | ||||
-rw-r--r-- | arch/riscv/Makefile | 3 | ||||
-rw-r--r-- | arch/riscv/include/asm/alternative-macros.h | 2 | ||||
-rw-r--r-- | arch/riscv/include/asm/hwcap.h | 17 | ||||
-rw-r--r-- | arch/riscv/include/uapi/asm/sigcontext.h | 2 | ||||
-rw-r--r-- | arch/riscv/kernel/cpu.c | 181 | ||||
-rw-r--r-- | arch/riscv/kernel/cpufeature.c | 521 | ||||
-rw-r--r-- | arch/riscv/kernel/head.S | 6 | ||||
-rw-r--r-- | arch/riscv/kernel/probes/decode-insn.c | 11 | ||||
-rw-r--r-- | arch/riscv/kernel/probes/simulate-insn.c | 105 | ||||
-rw-r--r-- | arch/riscv/kernel/probes/simulate-insn.h | 5 | ||||
-rw-r--r-- | drivers/perf/riscv_pmu.c | 113 | ||||
-rw-r--r-- | drivers/perf/riscv_pmu_legacy.c | 28 | ||||
-rw-r--r-- | drivers/perf/riscv_pmu_sbi.c | 196 | ||||
-rw-r--r-- | include/linux/perf/riscv_pmu.h | 12 | ||||
-rw-r--r-- | include/linux/perf_event.h | 3 | ||||
-rw-r--r-- | lib/Kconfig.debug | 2 | ||||
-rw-r--r-- | tools/lib/perf/mmap.c | 66 | ||||
-rw-r--r-- | tools/perf/tests/mmap-basic.c | 6 |
21 files changed, 992 insertions, 340 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bd519749968f..c8fe9e7194f1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5469,6 +5469,13 @@ [KNL] Disable ring 3 MONITOR/MWAIT feature on supported CPUs. + riscv_isa_fallback [RISCV] + When CONFIG_RISCV_ISA_FALLBACK is not enabled, permit + falling back to detecting extension support by parsing + "riscv,isa" property on devicetree systems when the + replacement properties are not found. See the Kconfig + entry for RISCV_ISA_FALLBACK. + ro [KNL] Mount root device read-only on boot rodata= [KNL] diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 3800fab1619b..8019103aac10 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -941,16 +941,35 @@ enabled, otherwise writing to this file will return ``-EBUSY``. The default value is 8. -perf_user_access (arm64 only) -================================= +perf_user_access (arm64 and riscv only) +======================================= + +Controls user space access for reading perf event counters. -Controls user space access for reading perf event counters. When set to 1, -user space can read performance monitor counter registers directly. +arm64 +===== The default value is 0 (access disabled). +When set to 1, user space can read performance monitor counter registers +directly. + See Documentation/arch/arm64/perf.rst for more information. +riscv +===== + +When set to 0, user space access is disabled. + +The default value is 1, user space can read performance monitor counter +registers through perf, any direct access without perf intervention will trigger +an illegal instruction. + +When set to 2, which enables legacy mode (user space has direct access to cycle +and insret CSRs only). Note that this legacy value is deprecated and will be +removed once all user space applications are fixed. + +Note that the time CSR is always directly accessible to all modes. pid_max ======= diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 4c07b9189c86..afa7160b136c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,6 +62,7 @@ config RISCV select COMMON_CLK select CPU_PM if CPU_IDLE || HIBERNATION select EDAC_SUPPORT + select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP @@ -848,6 +849,24 @@ config XIP_PHYS_ADDR be linked for and stored to. This address is dependent on your own flash usage. +config RISCV_ISA_FALLBACK + bool "Permit falling back to parsing riscv,isa for extension support by default" + default y + help + Parsing the "riscv,isa" devicetree property has been deprecated and + replaced by a list of explicitly defined strings. For compatibility + with existing platforms, the kernel will fall back to parsing the + "riscv,isa" property if the replacements are not found. + + Selecting N here will result in a kernel that does not use the + fallback, unless the commandline "riscv_isa_fallback" parameter is + present. + + Please see the dt-binding, located at + Documentation/devicetree/bindings/riscv/extensions.yaml for details + on the replacement properties, "riscv,isa-base" and + "riscv,isa-extensions". + endmenu # "Boot options" config BUILTIN_DTB diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6ec6d52a4180..1329e060c548 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -87,9 +87,6 @@ endif ifeq ($(CONFIG_CMODEL_MEDANY),y) KBUILD_CFLAGS += -mcmodel=medany endif -ifeq ($(CONFIG_PERF_EVENTS),y) - KBUILD_CFLAGS += -fno-omit-frame-pointer -endif # Avoid generating .eh_frame sections. KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index b8c55fb3ab2c..721ec275ce57 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -146,7 +146,7 @@ * vendor_id: The CPU vendor ID. * patch_id: The patch ID (erratum ID or cpufeature ID). * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old - * content will alwyas be executed. + * content will always be executed. */ #define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \ _ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index f041bfa7f6a0..b7b58258f6c7 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -14,12 +14,17 @@ #include <uapi/asm/hwcap.h> #define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_b ('b' - 'a') #define RISCV_ISA_EXT_c ('c' - 'a') #define RISCV_ISA_EXT_d ('d' - 'a') #define RISCV_ISA_EXT_f ('f' - 'a') #define RISCV_ISA_EXT_h ('h' - 'a') #define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_j ('j' - 'a') +#define RISCV_ISA_EXT_k ('k' - 'a') #define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_p ('p' - 'a') +#define RISCV_ISA_EXT_q ('q' - 'a') #define RISCV_ISA_EXT_s ('s' - 'a') #define RISCV_ISA_EXT_u ('u' - 'a') #define RISCV_ISA_EXT_v ('v' - 'a') @@ -55,7 +60,6 @@ #define RISCV_ISA_EXT_ZIHPM 42 #define RISCV_ISA_EXT_MAX 64 -#define RISCV_ISA_EXT_NAME_LEN_MAX 32 #ifdef CONFIG_RISCV_M_MODE #define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA @@ -70,12 +74,15 @@ unsigned long riscv_get_elf_hwcap(void); struct riscv_isa_ext_data { - /* Name of the extension displayed to userspace via /proc/cpuinfo */ - char uprop[RISCV_ISA_EXT_NAME_LEN_MAX]; - /* The logical ISA extension ID */ - unsigned int isa_ext_id; + const unsigned int id; + const char *name; + const char *property; }; +extern const struct riscv_isa_ext_data riscv_isa_ext[]; +extern const size_t riscv_isa_ext_count; +extern bool riscv_isa_fallback; + unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); #define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index 8c8712aa9551..cd4f175dc837 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -25,7 +25,7 @@ struct __sc_riscv_v_state { * Signal context structure * * This contains the context saved before a signal handler is invoked; - * it is restored by sys_sigreturn / sys_rt_sigreturn. + * it is restored by sys_rt_sigreturn. */ struct sigcontext { struct user_regs_struct sc_regs; diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..7b793c4321bb 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -41,7 +41,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) return 0; } -int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) +int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) { const char *isa; @@ -61,16 +61,53 @@ int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *har return -ENODEV; } + if (of_property_read_string(node, "riscv,isa-base", &isa)) + goto old_interface; + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv32i", *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv64i", *hart); + return -ENODEV; + } + + if (!of_property_present(node, "riscv,isa-extensions")) + return -ENODEV; + + if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "m") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "a") < 0) { + pr_warn("CPU with hartid=%lu does not support ima", *hart); + return -ENODEV; + } + + return 0; + +old_interface: + if (!riscv_isa_fallback) { + pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"", + *hart); + return -ENODEV; + } + if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart); + pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n", + *hart); return -ENODEV; } - if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv32ima", *hart); return -ENODEV; + } - if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv64ima", *hart); return -ENODEV; + } return 0; } @@ -160,132 +197,46 @@ arch_initcall(riscv_cpuinfo_init); #ifdef CONFIG_PROC_FS -#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ - { \ - .uprop = #UPROP, \ - .isa_ext_id = EXTID, \ - } - -/* - * The canonical order of ISA extension names in the ISA string is defined in - * chapter 27 of the unprivileged specification. - * - * Ordinarily, for in-kernel data structures, this order is unimportant but - * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. - * - * The specification uses vague wording, such as should, when it comes to - * ordering, so for our purposes the following rules apply: - * - * 1. All multi-letter extensions must be separated from other extensions by an - * underscore. - * - * 2. Additional standard extensions (starting with 'Z') must be sorted after - * single-letter extensions and before any higher-privileged extensions. - - * 3. The first letter following the 'Z' conventionally indicates the most - * closely related alphabetical extension category, IMAFDQLCBKJTPVH. - * If multiple 'Z' extensions are named, they must be ordered first by - * category, then alphabetically within a category. - * - * 3. Standard supervisor-level extensions (starting with 'S') must be listed - * after standard unprivileged extensions. If multiple supervisor-level - * extensions are listed, they must be ordered alphabetically. - * - * 4. Standard machine-level extensions (starting with 'Zxm') must be listed - * after any lower-privileged, standard extensions. If multiple - * machine-level extensions are listed, they must be ordered - * alphabetically. - * - * 5. Non-standard extensions (starting with 'X') must be listed after all - * standard extensions. If multiple non-standard extensions are listed, they - * must be ordered alphabetically. - * - * An example string following the order is: - * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux - * - * New entries to this struct should follow the ordering rules described above. - */ -static struct riscv_isa_ext_data isa_ext_arr[] = { - __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), - __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), - __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), - __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), - __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), - __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), - __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), - __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), - __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), - __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), - __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), - __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), - __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), - __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), - __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), - __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), - __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), - __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), -}; - -static void print_isa_ext(struct seq_file *f) +static void print_isa(struct seq_file *f) { - struct riscv_isa_ext_data *edata; - int i = 0, arr_sz; - - arr_sz = ARRAY_SIZE(isa_ext_arr) - 1; + seq_puts(f, "isa\t\t: "); - /* No extension support available */ - if (arr_sz <= 0) - return; + if (IS_ENABLED(CONFIG_32BIT)) + seq_write(f, "rv32", 4); + else + seq_write(f, "rv64", 4); - for (i = 0; i <= arr_sz; i++) { - edata = &isa_ext_arr[i]; - if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id)) + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id)) continue; - seq_printf(f, "_%s", edata->uprop); - } -} -/* - * These are the only valid base (single letter) ISA extensions as per the spec. - * It also specifies the canonical order in which it appears in the spec. - * Some of the extension may just be a place holder for now (B, K, P, J). - * This should be updated once corresponding extensions are ratified. - */ -static const char base_riscv_exts[13] = "imafdqcbkjpvh"; + /* Only multi-letter extensions are split by underscores */ + if (strnlen(riscv_isa_ext[i].name, 2) != 1) + seq_puts(f, "_"); -static void print_isa(struct seq_file *f, const char *isa) -{ - int i; - - seq_puts(f, "isa\t\t: "); - /* Print the rv[64/32] part */ - seq_write(f, isa, 4); - for (i = 0; i < sizeof(base_riscv_exts); i++) { - if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a')) - /* Print only enabled the base ISA extensions */ - seq_write(f, &base_riscv_exts[i], 1); + seq_printf(f, "%s", riscv_isa_ext[i].name); } - print_isa_ext(f); + seq_puts(f, "\n"); } static void print_mmu(struct seq_file *f) { - char sv_type[16]; + const char *sv_type; #ifdef CONFIG_MMU #if defined(CONFIG_32BIT) - strncpy(sv_type, "sv32", 5); + sv_type = "sv32"; #elif defined(CONFIG_64BIT) if (pgtable_l5_enabled) - strncpy(sv_type, "sv57", 5); + sv_type = "sv57"; else if (pgtable_l4_enabled) - strncpy(sv_type, "sv48", 5); + sv_type = "sv48"; else - strncpy(sv_type, "sv39", 5); + sv_type = "sv39"; #endif #else - strncpy(sv_type, "none", 5); + sv_type = "none"; #endif /* CONFIG_MMU */ seq_printf(f, "mmu\t\t: %s\n", sv_type); } @@ -316,27 +267,21 @@ static int c_show(struct seq_file *m, void *v) unsigned long cpu_id = (unsigned long)v - 1; struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); struct device_node *node; - const char *compat, *isa; + const char *compat; seq_printf(m, "processor\t: %lu\n", cpu_id); seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id)); + print_isa(m); + print_mmu(m); if (acpi_disabled) { node = of_get_cpu_node(cpu_id, NULL); - if (!of_property_read_string(node, "riscv,isa", &isa)) - print_isa(m, isa); - print_mmu(m); if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); of_node_put(node); - } else { - if (!acpi_get_riscv_isa(NULL, cpu_id, &isa)) - print_isa(m, isa); - - print_mmu(m); } seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index bdcf460ea53d..71fb840ee246 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -99,29 +99,252 @@ static bool riscv_isa_extension_check(int id) return true; } -void __init riscv_fill_hwcap(void) +#define __RISCV_ISA_EXT_DATA(_name, _id) { \ + .name = #_name, \ + .property = #_name, \ + .id = _id, \ +} + +/* + * The canonical order of ISA extension names in the ISA string is defined in + * chapter 27 of the unprivileged specification. + * + * Ordinarily, for in-kernel data structures, this order is unimportant but + * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. + * + * The specification uses vague wording, such as should, when it comes to + * ordering, so for our purposes the following rules apply: + * + * 1. All multi-letter extensions must be separated from other extensions by an + * underscore. + * + * 2. Additional standard extensions (starting with 'Z') must be sorted after + * single-letter extensions and before any higher-privileged extensions. + * + * 3. The first letter following the 'Z' conventionally indicates the most + * closely related alphabetical extension category, IMAFDQLCBKJTPVH. + * If multiple 'Z' extensions are named, they must be ordered first by + * category, then alphabetically within a category. + * + * 3. Standard supervisor-level extensions (starting with 'S') must be listed + * after standard unprivileged extensions. If multiple supervisor-level + * extensions are listed, they must be ordered alphabetically. + * + * 4. Standard machine-level extensions (starting with 'Zxm') must be listed + * after any lower-privileged, standard extensions. If multiple + * machine-level extensions are listed, they must be ordered + * alphabetically. + * + * 5. Non-standard extensions (starting with 'X') must be listed after all + * standard extensions. If multiple non-standard extensions are listed, they + * must be ordered alphabetically. + * + * An example string following the order is: + * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux + * + * New entries to this struct should follow the ordering rules described above. + */ +const struct riscv_isa_ext_data riscv_isa_ext[] = { + __RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i), + __RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m), + __RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a), + __RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f), + __RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d), + __RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q), + __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), + __RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b), + __RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k), + __RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j), + __RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p), + __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), + __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), + __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), + __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), + __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), + __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), + __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), + __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), + __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), + __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), + __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), +}; + +const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); + +static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo, + unsigned long *isa2hwcap, const char *isa) +{ + /* + * For all possible cpus, we have already validated in + * the boot process that they at least contain "rv" and + * whichever of "32"/"64" this kernel supports, and so this + * section can be skipped. + */ + isa += 4; + + while (*isa) { + const char *ext = isa++; + const char *ext_end = isa; + bool ext_long = false, ext_err = false; + + switch (*ext) { + case 's': + /* + * Workaround for invalid single-letter 's' & 'u'(QEMU). + * No need to set the bit in riscv_isa as 's' & 'u' are + * not valid ISA extensions. It works until multi-letter + * extension starting with "Su" appears. + */ + if (ext[-1] != '_' && ext[1] == 'u') { + ++isa; + ext_err = true; + break; + } + fallthrough; + case 'S': + case 'x': + case 'X': + case 'z': + case 'Z': + /* + * Before attempting to parse the extension itself, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + * + * Next, as the extensions version is currently ignored, we + * eliminate that portion. This is done by parsing backwards from + * the end of the extension, removing any numbers. This may be a + * major or minor number however, so the process is repeated if a + * minor number was found. + * + * ext_end is intended to represent the first character *after* the + * name portion of an extension, but will be decremented to the last + * character itself while eliminating the extensions version number. + * A simple re-increment solves this problem. + */ + ext_long = true; + for (; *isa && *isa != '_'; ++isa) + if (unlikely(!isalnum(*isa))) + ext_err = true; + + ext_end = isa; + if (unlikely(ext_err)) + break; + + if (!isdigit(ext_end[-1])) + break; + + while (isdigit(*--ext_end)) + ; + + if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { + ++ext_end; + break; + } + + while (isdigit(*--ext_end)) + ; + + ++ext_end; + break; + default: + /* + * Things are a little easier for single-letter extensions, as they + * are parsed forwards. + * + * After checking that our starting position is valid, we need to + * ensure that, when isa was incremented at the start of the loop, + * that it arrived at the start of the next extension. + * + * If we are already on a non-digit, there is nothing to do. Either + * we have a multi-letter extension's _, or the start of an + * extension. + * + * Otherwise we have found the current extension's major version + * number. Parse past it, and a subsequent p/minor version number + * if present. The `p` extension must not appear immediately after + * a number, so there is no fear of missing it. + * + */ + if (unlikely(!isalpha(*ext))) { + ext_err = true; + break; + } + + if (!isdigit(*isa)) + break; + + while (isdigit(*++isa)) + ; + + if (tolower(*isa) != 'p') + break; + + if (!isdigit(*++isa)) { + --isa; + break; + } + + while (isdigit(*++isa)) + ; + + break; + } + + /* + * The parser expects that at the start of an iteration isa points to the + * first character of the next extension. As we stop parsing an extension + * on meeting a non-alphanumeric character, an extra increment is needed + * where the succeeding extension is a multi-letter prefixed with an "_". + */ + if (*isa == '_') + ++isa; + +#define SET_ISA_EXT_MAP(name, bit) \ + do { \ + if ((ext_end - ext == strlen(name)) && \ + !strncasecmp(ext, name, strlen(name)) && \ + riscv_isa_extension_check(bit)) \ + set_bit(bit, isainfo->isa); \ + } while (false) \ + + if (unlikely(ext_err)) + continue; + if (!ext_long) { + int nr = tolower(*ext) - 'a'; + + if (riscv_isa_extension_check(nr)) { + *this_hwcap |= isa2hwcap[nr]; + set_bit(nr, isainfo->isa); + } + } else { + for (int i = 0; i < riscv_isa_ext_count; i++) + SET_ISA_EXT_MAP(riscv_isa_ext[i].name, + riscv_isa_ext[i].id); + } +#undef SET_ISA_EXT_MAP + } +} + +static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) { struct device_node *node; const char *isa; - char print_str[NUM_ALPHA_EXTS + 1]; - int i, j, rc; - unsigned long isa2hwcap[26] = {0}; + int rc; struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; - isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; - isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; - isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A; - isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; - isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; - isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; - isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; - - elf_hwcap = 0; - - bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); - if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); if (ACPI_FAILURE(status)) @@ -153,169 +376,7 @@ void __init riscv_fill_hwcap(void) } } - /* - * For all possible cpus, we have already validated in - * the boot process that they at least contain "rv" and - * whichever of "32"/"64" this kernel supports, and so this - * section can be skipped. - */ - isa += 4; - - while (*isa) { - const char *ext = isa++; - const char *ext_end = isa; - bool ext_long = false, ext_err = false; - - switch (*ext) { - case 's': - /* - * Workaround for invalid single-letter 's' & 'u'(QEMU). - * No need to set the bit in riscv_isa as 's' & 'u' are - * not valid ISA extensions. It works until multi-letter - * extension starting with "Su" appears. - */ - if (ext[-1] != '_' && ext[1] == 'u') { - ++isa; - ext_err = true; - break; - } - fallthrough; - case 'S': - case 'x': - case 'X': - case 'z': - case 'Z': - /* - * Before attempting to parse the extension itself, we find its end. - * As multi-letter extensions must be split from other multi-letter - * extensions with an "_", the end of a multi-letter extension will - * either be the null character or the "_" at the start of the next - * multi-letter extension. - * - * Next, as the extensions version is currently ignored, we - * eliminate that portion. This is done by parsing backwards from - * the end of the extension, removing any numbers. This may be a - * major or minor number however, so the process is repeated if a - * minor number was found. - * - * ext_end is intended to represent the first character *after* the - * name portion of an extension, but will be decremented to the last - * character itself while eliminating the extensions version number. - * A simple re-increment solves this problem. - */ - ext_long = true; - for (; *isa && *isa != '_'; ++isa) - if (unlikely(!isalnum(*isa))) - ext_err = true; - - ext_end = isa; - if (unlikely(ext_err)) - break; - - if (!isdigit(ext_end[-1])) - break; - - while (isdigit(*--ext_end)) - ; - - if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { - ++ext_end; - break; - } - - while (isdigit(*--ext_end)) - ; - - ++ext_end; - break; - default: - /* - * Things are a little easier for single-letter extensions, as they - * are parsed forwards. - * - * After checking that our starting position is valid, we need to - * ensure that, when isa was incremented at the start of the loop, - * that it arrived at the start of the next extension. - * - * If we are already on a non-digit, there is nothing to do. Either - * we have a multi-letter extension's _, or the start of an - * extension. - * - * Otherwise we have found the current extension's major version - * number. Parse past it, and a subsequent p/minor version number - * if present. The `p` extension must not appear immediately after - * a number, so there is no fear of missing it. - * - */ - if (unlikely(!isalpha(*ext))) { - ext_err = true; - break; - } - - if (!isdigit(*isa)) - break; - - while (isdigit(*++isa)) - ; - - if (tolower(*isa) != 'p') - break; - - if (!isdigit(*++isa)) { - --isa; - break; - } - - while (isdigit(*++isa)) - ; - - break; - } - - /* - * The parser expects that at the start of an iteration isa points to the - * first character of the next extension. As we stop parsing an extension - * on meeting a non-alphanumeric character, an extra increment is needed - * where the succeeding extension is a multi-letter prefixed with an "_". - */ - if (*isa == '_') - ++isa; - -#define SET_ISA_EXT_MAP(name, bit) \ - do { \ - if ((ext_end - ext == sizeof(name) - 1) && \ - !strncasecmp(ext, name, sizeof(name) - 1) && \ - riscv_isa_extension_check(bit)) \ - set_bit(bit, isainfo->isa); \ - } while (false) \ - - if (unlikely(ext_err)) - continue; - if (!ext_long) { - int nr = tolower(*ext) - 'a'; - - if (riscv_isa_extension_check(nr)) { - this_hwcap |= isa2hwcap[nr]; - set_bit(nr, isainfo->isa); - } - } else { - /* sorted alphabetically */ - SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA); - SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA); - SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); - SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC); - SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); - SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT); - SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); - SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA); - SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); - SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS); - SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); - SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ); - SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE); - } -#undef SET_ISA_EXT_MAP - } + riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa); /* * Linux requires the following extensions, so we may as well @@ -352,9 +413,107 @@ void __init riscv_fill_hwcap(void) if (!acpi_disabled && rhct) acpi_put_table((struct acpi_table_header *)rhct); +} + +static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + unsigned long this_hwcap = 0; + struct device_node *cpu_node; + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + continue; + } + + if (!of_property_present(cpu_node, "riscv,isa-extensions")) { + of_node_put(cpu_node); + continue; + } + + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + riscv_isa_ext[i].property) < 0) + continue; + + if (!riscv_isa_extension_check(riscv_isa_ext[i].id)) + continue; + + /* Only single letter extensions get set in hwcap */ + if (strnlen(riscv_isa_ext[i].name, 2) == 1) + this_hwcap |= isa2hwcap[riscv_isa_ext[i].id]; + + set_bit(riscv_isa_ext[i].id, isainfo->isa); + } + + of_node_put(cpu_node); + + /* + * All "okay" harts should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + } + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + return -ENOENT; + + return 0; +} + +#ifdef CONFIG_RISCV_ISA_FALLBACK +bool __initdata riscv_isa_fallback = true; +#else +bool __initdata riscv_isa_fallback; +static int __init riscv_isa_fallback_setup(char *__unused) +{ + riscv_isa_fallback = true; + return 1; +} +early_param("riscv_isa_fallback", riscv_isa_fallback_setup); +#endif + +void __init riscv_fill_hwcap(void) +{ + char print_str[NUM_ALPHA_EXTS + 1]; + unsigned long isa2hwcap[26] = {0}; + int i, j; + + isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; + isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; + isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A; + isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; + isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; + isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; + isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; + + if (!acpi_disabled) { + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } else { + int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap); + + if (ret && riscv_isa_fallback) { + pr_info("Falling back to deprecated \"riscv,isa\"\n"); + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } + } - /* We don't support systems with F but without D, so mask those out - * here. */ + /* + * We don't support systems with F but without D, so mask those out + * here. + */ if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { pr_info("This kernel does not support systems with F but not D\n"); elf_hwcap &= ~COMPAT_HWCAP_ISA_F; diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11c3b94c4534..3710ea5d160f 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -289,10 +289,6 @@ clear_bss: blt a3, a4, clear_bss clear_bss_done: #endif - /* Save hart ID and DTB physical address */ - mv s0, a0 - mv s1, a1 - la a2, boot_cpu_hartid XIP_FIXUP_OFFSET a2 REG_S a0, (a2) @@ -306,7 +302,7 @@ clear_bss_done: la a0, __dtb_start XIP_FIXUP_OFFSET a0 #else - mv a0, s1 + mv a0, a1 #endif /* CONFIG_BUILTIN_DTB */ call setup_vm #ifdef CONFIG_MMU diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c index 64f6183b4717..65d9590bfb9f 100644 --- a/arch/riscv/kernel/probes/decode-insn.c +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -29,13 +29,14 @@ riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) * TODO: the REJECTED ones below need to be implemented */ #ifdef CONFIG_RISCV_ISA_C - RISCV_INSN_REJECTED(c_j, insn); - RISCV_INSN_REJECTED(c_jr, insn); RISCV_INSN_REJECTED(c_jal, insn); - RISCV_INSN_REJECTED(c_jalr, insn); - RISCV_INSN_REJECTED(c_beqz, insn); - RISCV_INSN_REJECTED(c_bnez, insn); RISCV_INSN_REJECTED(c_ebreak, insn); + + RISCV_INSN_SET_SIMULATE(c_j, insn); + RISCV_INSN_SET_SIMULATE(c_jr, insn); + RISCV_INSN_SET_SIMULATE(c_jalr, insn); + RISCV_INSN_SET_SIMULATE(c_beqz, insn); + RISCV_INSN_SET_SIMULATE(c_bnez, insn); #endif RISCV_INSN_SET_SIMULATE(jal, insn); diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index 7441ac8a6843..d3099d67816d 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -188,3 +188,108 @@ bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *r return true; } + +bool __kprobes simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 15 13 12 2 1 0 + * | funct3 | offset[11|4|9:8|10|6|7|3:1|5] | opcode | + * 3 11 2 + */ + + s32 offset; + + offset = ((opcode >> 3) & 0x7) << 1; + offset |= ((opcode >> 11) & 0x1) << 4; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 7) & 0x1) << 6; + offset |= ((opcode >> 6) & 0x1) << 7; + offset |= ((opcode >> 9) & 0x3) << 8; + offset |= ((opcode >> 8) & 0x1) << 10; + offset |= ((opcode >> 12) & 0x1) << 11; + + instruction_pointer_set(regs, addr + sign_extend32(offset, 11)); + + return true; +} + +static bool __kprobes simulate_c_jr_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_jalr) +{ + /* + * 15 12 11 7 6 2 1 0 + * | funct4 | rs1 | rs2 | op | + * 4 5 5 2 + */ + + unsigned long jump_addr; + + u32 rs1 = (opcode >> 7) & 0x1f; + + if (rs1 == 0) /* C.JR is only valid when rs1 != x0 */ + return false; + + if (!rv_insn_reg_get_val(regs, rs1, &jump_addr)) + return false; + + if (is_jalr && !rv_insn_reg_set_val(regs, 1, addr + 2)) + return false; + + instruction_pointer_set(regs, jump_addr); + + return true; +} + +bool __kprobes simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, false); +} + +bool __kprobes simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, true); +} + +static bool __kprobes simulate_c_bnez_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_bnez) +{ + /* + * 15 13 12 10 9 7 6 2 1 0 + * | funct3 | offset[8|4:3] | rs1' | offset[7:6|2:1|5] | op | + * 3 3 3 5 2 + */ + + s32 offset; + u32 rs1; + unsigned long rs1_val; + + rs1 = 0x8 | ((opcode >> 7) & 0x7); + + if (!rv_insn_reg_get_val(regs, rs1, &rs1_val)) + return false; + + if ((rs1_val != 0 && is_bnez) || (rs1_val == 0 && !is_bnez)) { + offset = ((opcode >> 3) & 0x3) << 1; + offset |= ((opcode >> 10) & 0x3) << 3; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 5) & 0x3) << 6; + offset |= ((opcode >> 12) & 0x1) << 8; + offset = sign_extend32(offset, 8); + } else { + offset = 2; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, true); +} + +bool __kprobes simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, false); +} diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h index 61e35db31001..44ebbc444db9 100644 --- a/arch/riscv/kernel/probes/simulate-insn.h +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -24,5 +24,10 @@ bool simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs); #endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */ diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index ebca5eab9c9b..80c052e93f9e 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -14,9 +14,81 @@ #include <linux/perf/riscv_pmu.h> #include <linux/printk.h> #include <linux/smp.h> +#include <linux/sched_clock.h> #include <asm/sbi.h> +static bool riscv_perf_user_access(struct perf_event *event) +{ + return ((event->attr.type == PERF_TYPE_HARDWARE) || + (event->attr.type == PERF_TYPE_HW_CACHE) || + (event->attr.type == PERF_TYPE_RAW)) && + !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); +} + +void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, u64 now) +{ + struct clock_read_data *rd; + unsigned int seq; + u64 ns; + + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_time_short = 0; + userpg->cap_user_rdpmc = riscv_perf_user_access(event); + +#ifdef CONFIG_RISCV_PMU + /* + * The counters are 64-bit but the priv spec doesn't mandate all the + * bits to be implemented: that's why, counter width can vary based on + * the cpu vendor. + */ + if (userpg->cap_user_rdpmc) + userpg->pmc_width = to_riscv_pmu(event->pmu)->ctr_get_width(event->hw.idx) + 1; +#endif + + do { + rd = sched_clock_read_begin(&seq); + + userpg->time_mult = rd->mult; + userpg->time_shift = rd->shift; + userpg->time_zero = rd->epoch_ns; + userpg->time_cycles = rd->epoch_cyc; + userpg->time_mask = rd->sched_clock_mask; + + /* + * Subtract the cycle base, such that software that + * doesn't know about cap_user_time_short still 'works' + * assuming no wraps. + */ + ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift); + userpg->time_zero -= ns; + + } while (sched_clock_read_retry(seq)); + + userpg->time_offset = userpg->time_zero - now; + + /* + * time_shift is not expected to be greater than 31 due to + * the original published conversion algorithm shifting a + * 32-bit value (now specifies a 64-bit value) - refer + * perf_event_mmap_page documentation in perf_event.h. + */ + if (userpg->time_shift == 32) { + userpg->time_shift = 31; + userpg->time_mult >>= 1; + } + + /* + * Internal timekeeping for enabled/running/stopped times + * is always computed with the sched_clock. + */ + userpg->cap_user_time = 1; + userpg->cap_user_time_zero = 1; + userpg->cap_user_time_short = 1; +} + static unsigned long csr_read_num(int csr_num) { #define switchcase_csr_read(__csr_num, __val) {\ @@ -171,6 +243,8 @@ int riscv_pmu_event_set_period(struct perf_event *event) local64_set(&hwc->prev_count, (u64)-left); + perf_event_update_userpage(event); + return overflow; } @@ -267,6 +341,9 @@ static int riscv_pmu_event_init(struct perf_event *event) hwc->idx = -1; hwc->event_base = mapped_event; + if (rvpmu->event_init) + rvpmu->event_init(event); + if (!is_sampling_event(event)) { /* * For non-sampling runs, limit the sample_period to half @@ -283,6 +360,39 @@ static int riscv_pmu_event_init(struct perf_event *event) return 0; } +static int riscv_pmu_event_idx(struct perf_event *event) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) + return 0; + + if (rvpmu->csr_index) + return rvpmu->csr_index(event) + 1; + + return 0; +} + +static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (rvpmu->event_mapped) { + rvpmu->event_mapped(event, mm); + perf_event_update_userpage(event); + } +} + +static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (rvpmu->event_unmapped) { + rvpmu->event_unmapped(event, mm); + perf_event_update_userpage(event); + } +} + struct riscv_pmu *riscv_pmu_alloc(void) { struct riscv_pmu *pmu; @@ -307,6 +417,9 @@ struct riscv_pmu *riscv_pmu_alloc(void) } pmu->pmu = (struct pmu) { .event_init = riscv_pmu_event_init, + .event_mapped = riscv_pmu_event_mapped, + .event_unmapped = riscv_pmu_event_unmapped, + .event_idx = riscv_pmu_event_idx, .add = riscv_pmu_add, .del = riscv_pmu_del, .start = riscv_pmu_start, diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index ca9e20bfc7ac..79fdd667922e 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -13,7 +13,7 @@ #include <linux/platform_device.h> #define RISCV_PMU_LEGACY_CYCLE 0 -#define RISCV_PMU_LEGACY_INSTRET 1 +#define RISCV_PMU_LEGACY_INSTRET 2 static bool pmu_init_done; @@ -71,6 +71,29 @@ static void pmu_legacy_ctr_start(struct perf_event *event, u64 ival) local64_set(&hwc->prev_count, initial_val); } +static uint8_t pmu_legacy_csr_index(struct perf_event *event) +{ + return event->hw.idx; +} + +static void pmu_legacy_event_mapped(struct perf_event *event, struct mm_struct *mm) +{ + if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES && + event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) + return; + + event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; +} + +static void pmu_legacy_event_unmapped(struct perf_event *event, struct mm_struct *mm) +{ + if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES && + event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) + return; + + event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT; +} + /* * This is just a simple implementation to allow legacy implementations * compatible with new RISC-V PMU driver framework. @@ -91,6 +114,9 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) pmu->ctr_get_width = NULL; pmu->ctr_clear_idx = NULL; pmu->ctr_read = pmu_legacy_read_ctr; + pmu->event_mapped = pmu_legacy_event_mapped; + pmu->event_unmapped = pmu_legacy_event_unmapped; + pmu->csr_index = pmu_legacy_csr_index; perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW); } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 4163ff517471..9a51053b1f99 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -24,6 +24,14 @@ #include <asm/sbi.h> #include <asm/hwcap.h> +#define SYSCTL_NO_USER_ACCESS 0 +#define SYSCTL_USER_ACCESS 1 +#define SYSCTL_LEGACY 2 + +#define PERF_EVENT_FLAG_NO_USER_ACCESS BIT(SYSCTL_NO_USER_ACCESS) +#define PERF_EVENT_FLAG_USER_ACCESS BIT(SYSCTL_USER_ACCESS) +#define PERF_EVENT_FLAG_LEGACY BIT(SYSCTL_LEGACY) + PMU_FORMAT_ATTR(event, "config:0-47"); PMU_FORMAT_ATTR(firmware, "config:63"); @@ -43,6 +51,9 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = { NULL, }; +/* Allow user mode access by default */ +static int sysctl_perf_user_access __read_mostly = SYSCTL_USER_ACCESS; + /* * RISC-V doesn't have heterogeneous harts yet. This need to be part of * per_cpu in case of harts with different pmu counters @@ -301,6 +312,11 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) } EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info); +static uint8_t pmu_sbi_csr_index(struct perf_event *event) +{ + return pmu_ctr_list[event->hw.idx].csr - CSR_CYCLE; +} + static unsigned long pmu_sbi_get_filter_flags(struct perf_event *event) { unsigned long cflags = 0; @@ -329,18 +345,34 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events); struct sbiret ret; int idx; - uint64_t cbase = 0; + uint64_t cbase = 0, cmask = rvpmu->cmask; unsigned long cflags = 0; cflags = pmu_sbi_get_filter_flags(event); + + /* + * In legacy mode, we have to force the fixed counters for those events + * but not in the user access mode as we want to use the other counters + * that support sampling/filtering. + */ + if (hwc->flags & PERF_EVENT_FLAG_LEGACY) { + if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH; + cmask = 1; + } else if (event->attr.config == PERF_COUNT_HW_INSTRUCTIONS) { + cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH; + cmask = 1UL << (CSR_INSTRET - CSR_CYCLE); + } + } + /* retrieve the available counter index */ #if defined(CONFIG_32BIT) ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - rvpmu->cmask, cflags, hwc->event_base, hwc->config, + cmask, cflags, hwc->event_base, hwc->config, hwc->config >> 32); #else ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, - rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0); + cmask, cflags, hwc->event_base, hwc->config, 0); #endif if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", @@ -474,6 +506,22 @@ static u64 pmu_sbi_ctr_read(struct perf_event *event) return val; } +static void pmu_sbi_set_scounteren(void *arg) +{ + struct perf_event *event = (struct perf_event *)arg; + + csr_write(CSR_SCOUNTEREN, + csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event))); +} + +static void pmu_sbi_reset_scounteren(void *arg) +{ + struct perf_event *event = (struct perf_event *)arg; + + csr_write(CSR_SCOUNTEREN, + csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event))); +} + static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) { struct sbiret ret; @@ -490,6 +538,10 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) if (ret.error && (ret.error != SBI_ERR_ALREADY_STARTED)) pr_err("Starting counter idx %d failed with error %d\n", hwc->idx, sbi_err_map_linux_errno(ret.error)); + + if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) && + (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) + pmu_sbi_set_scounteren((void *)event); } static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag) @@ -497,6 +549,10 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag) struct sbiret ret; struct hw_perf_event *hwc = &event->hw; + if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) && + (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) + pmu_sbi_reset_scounteren((void *)event); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0); if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) && flag != SBI_PMU_STOP_FLAG_RESET) @@ -704,10 +760,13 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); /* - * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace, - * as is necessary to maintain uABI compatibility. + * We keep enabling userspace access to CYCLE, TIME and INSTRET via the + * legacy option but that will be removed in the future. */ - csr_write(CSR_SCOUNTEREN, 0x7); + if (sysctl_perf_user_access == SYSCTL_LEGACY) + csr_write(CSR_SCOUNTEREN, 0x7); + else + csr_write(CSR_SCOUNTEREN, 0x2); /* Stop all the counters so that they can be enabled from perf */ pmu_sbi_stop_all(pmu); @@ -838,6 +897,121 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) cpuhp_state_remove_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node); } +static void pmu_sbi_event_init(struct perf_event *event) +{ + /* + * The permissions are set at event_init so that we do not depend + * on the sysctl value that can change. + */ + if (sysctl_perf_user_access == SYSCTL_NO_USER_ACCESS) + event->hw.flags |= PERF_EVENT_FLAG_NO_USER_ACCESS; + else if (sysctl_perf_user_access == SYSCTL_USER_ACCESS) + event->hw.flags |= PERF_EVENT_FLAG_USER_ACCESS; + else + event->hw.flags |= PERF_EVENT_FLAG_LEGACY; +} + +static void pmu_sbi_event_mapped(struct perf_event *event, struct mm_struct *mm) +{ + if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS) + return; + + if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) { + if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES && + event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) { + return; + } + } + + /* + * The user mmapped the event to directly access it: this is where + * we determine based on sysctl_perf_user_access if we grant userspace + * the direct access to this event. That means that within the same + * task, some events may be directly accessible and some other may not, + * if the user changes the value of sysctl_perf_user_accesss in the + * meantime. + */ + + event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; + + /* + * We must enable userspace access *before* advertising in the user page + * that it is possible to do so to avoid any race. + * And we must notify all cpus here because threads that currently run + * on other cpus will try to directly access the counter too without + * calling pmu_sbi_ctr_start. + */ + if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS) + on_each_cpu_mask(mm_cpumask(mm), + pmu_sbi_set_scounteren, (void *)event, 1); +} + +static void pmu_sbi_event_unmapped(struct perf_event *event, struct mm_struct *mm) +{ + if (event->hw.flags & PERF_EVENT_FLAG_NO_USER_ACCESS) + return; + + if (event->hw.flags & PERF_EVENT_FLAG_LEGACY) { + if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES && + event->attr.config != PERF_COUNT_HW_INSTRUCTIONS) { + return; + } + } + + /* + * Here we can directly remove user access since the user does not have + * access to the user page anymore so we avoid the racy window where the + * user could have read cap_user_rdpmc to true right before we disable + * it. + */ + event->hw.flags &= ~PERF_EVENT_FLAG_USER_READ_CNT; + + if (event->hw.flags & PERF_EVENT_FLAG_USER_ACCESS) + on_each_cpu_mask(mm_cpumask(mm), + pmu_sbi_reset_scounteren, (void *)event, 1); +} + +static void riscv_pmu_update_counter_access(void *info) +{ + if (sysctl_perf_user_access == SYSCTL_LEGACY) + csr_write(CSR_SCOUNTEREN, 0x7); + else + csr_write(CSR_SCOUNTEREN, 0x2); +} + +static int riscv_pmu_proc_user_access_handler(struct ctl_table *table, + int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + int prev = sysctl_perf_user_access; + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + /* + * Test against the previous value since we clear SCOUNTEREN when + * sysctl_perf_user_access is set to SYSCTL_USER_ACCESS, but we should + * not do that if that was already the case. + */ + if (ret || !write || prev == sysctl_perf_user_access) + return ret; + + on_each_cpu(riscv_pmu_update_counter_access, NULL, 1); + + return 0; +} + +static struct ctl_table sbi_pmu_sysctl_table[] = { + { + .procname = "perf_user_access", + .data = &sysctl_perf_user_access, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = riscv_pmu_proc_user_access_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; + static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; @@ -881,6 +1055,10 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->ctr_get_width = pmu_sbi_ctr_get_width; pmu->ctr_clear_idx = pmu_sbi_ctr_clear_idx; pmu->ctr_read = pmu_sbi_ctr_read; + pmu->event_init = pmu_sbi_event_init; + pmu->event_mapped = pmu_sbi_event_mapped; + pmu->event_unmapped = pmu_sbi_event_unmapped; + pmu->csr_index = pmu_sbi_csr_index; ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node); if (ret) @@ -894,6 +1072,8 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) if (ret) goto out_unregister; + register_sysctl("kernel", sbi_pmu_sysctl_table); + return 0; out_unregister: @@ -907,7 +1087,7 @@ out_free: static struct platform_driver pmu_sbi_driver = { .probe = pmu_sbi_device_probe, .driver = { - .name = RISCV_PMU_PDEV_NAME, + .name = RISCV_PMU_SBI_PDEV_NAME, }, }; @@ -934,7 +1114,7 @@ static int __init pmu_sbi_devinit(void) if (ret) return ret; - pdev = platform_device_register_simple(RISCV_PMU_PDEV_NAME, -1, NULL, 0); + pdev = platform_device_register_simple(RISCV_PMU_SBI_PDEV_NAME, -1, NULL, 0); if (IS_ERR(pdev)) { platform_driver_unregister(&pmu_sbi_driver); return PTR_ERR(pdev); diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 43fc892aa7d9..43282e22ebe1 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -6,8 +6,8 @@ * */ -#ifndef _ASM_RISCV_PERF_EVENT_H -#define _ASM_RISCV_PERF_EVENT_H +#ifndef _RISCV_PMU_H +#define _RISCV_PMU_H #include <linux/perf_event.h> #include <linux/ptrace.h> @@ -21,7 +21,7 @@ #define RISCV_MAX_COUNTERS 64 #define RISCV_OP_UNSUPP (-EOPNOTSUPP) -#define RISCV_PMU_PDEV_NAME "riscv-pmu" +#define RISCV_PMU_SBI_PDEV_NAME "riscv-pmu-sbi" #define RISCV_PMU_LEGACY_PDEV_NAME "riscv-pmu-legacy" #define RISCV_PMU_STOP_FLAG_RESET 1 @@ -55,6 +55,10 @@ struct riscv_pmu { void (*ctr_start)(struct perf_event *event, u64 init_val); void (*ctr_stop)(struct perf_event *event, unsigned long flag); int (*event_map)(struct perf_event *event, u64 *config); + void (*event_init)(struct perf_event *event); + void (*event_mapped)(struct perf_event *event, struct mm_struct *mm); + void (*event_unmapped)(struct perf_event *event, struct mm_struct *mm); + uint8_t (*csr_index)(struct perf_event *event); struct cpu_hw_events __percpu *hw_events; struct hlist_node node; @@ -81,4 +85,4 @@ int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr); #endif /* CONFIG_RISCV_PMU */ -#endif /* _ASM_RISCV_PERF_EVENT_H */ +#endif /* _RISCV_PMU_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2166a69e3bf2..1269c96bc3b6 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -445,7 +445,8 @@ struct pmu { /* * Will return the value for perf_event_mmap_page::index for this event, - * if no implementation is provided it will default to: event->hw.idx + 1. + * if no implementation is provided it will default to 0 (see + * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fbc89baf7de6..39ffd218e960 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -502,7 +502,7 @@ config SECTION_MISMATCH_WARN_ONLY config DEBUG_FORCE_FUNCTION_ALIGN_64B bool "Force all function address 64B aligned" - depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC || S390) + depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC || RISCV || S390) select FUNCTION_ALIGNMENT_64B help There are cases that a commit from one domain changes the function diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index 0d1634cedf44..2184814b37dd 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -392,6 +392,72 @@ static u64 read_perf_counter(unsigned int counter) static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } +/* __riscv_xlen contains the witdh of the native base integer, here 64-bit */ +#elif defined(__riscv) && __riscv_xlen == 64 + +/* TODO: implement rv32 support */ + +#define CSR_CYCLE 0xc00 +#define CSR_TIME 0xc01 + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__ ("csrr %0, %1" \ + : "=r" (__v) \ + : "i" (csr) : ); \ + __v; \ +}) + +static unsigned long csr_read_num(int csr_num) +{ +#define switchcase_csr_read(__csr_num, __val) {\ + case __csr_num: \ + __val = csr_read(__csr_num); \ + break; } +#define switchcase_csr_read_2(__csr_num, __val) {\ + switchcase_csr_read(__csr_num + 0, __val) \ + switchcase_csr_read(__csr_num + 1, __val)} +#define switchcase_csr_read_4(__csr_num, __val) {\ + switchcase_csr_read_2(__csr_num + 0, __val) \ + switchcase_csr_read_2(__csr_num + 2, __val)} +#define switchcase_csr_read_8(__csr_num, __val) {\ + switchcase_csr_read_4(__csr_num + 0, __val) \ + switchcase_csr_read_4(__csr_num + 4, __val)} +#define switchcase_csr_read_16(__csr_num, __val) {\ + switchcase_csr_read_8(__csr_num + 0, __val) \ + switchcase_csr_read_8(__csr_num + 8, __val)} +#define switchcase_csr_read_32(__csr_num, __val) {\ + switchcase_csr_read_16(__csr_num + 0, __val) \ + switchcase_csr_read_16(__csr_num + 16, __val)} + + unsigned long ret = 0; + + switch (csr_num) { + switchcase_csr_read_32(CSR_CYCLE, ret) + default: + break; + } + + return ret; +#undef switchcase_csr_read_32 +#undef switchcase_csr_read_16 +#undef switchcase_csr_read_8 +#undef switchcase_csr_read_4 +#undef switchcase_csr_read_2 +#undef switchcase_csr_read +} + +static u64 read_perf_counter(unsigned int counter) +{ + return csr_read_num(CSR_CYCLE + counter); +} + +static u64 read_timestamp(void) +{ + return csr_read_num(CSR_TIME); +} + #else static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } static u64 read_timestamp(void) { return 0; } diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index e68ca6229756..886a13a77a16 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -284,7 +284,8 @@ static struct test_case tests__basic_mmap[] = { "permissions"), TEST_CASE_REASON("User space counter reading of instructions", mmap_user_read_instr, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ + (defined(__riscv) && __riscv_xlen == 64) "permissions" #else "unsupported" @@ -292,7 +293,8 @@ static struct test_case tests__basic_mmap[] = { ), TEST_CASE_REASON("User space counter reading of cycles", mmap_user_read_cycles, -#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \ + (defined(__riscv) && __riscv_xlen == 64) "permissions" #else "unsupported" |