diff options
Diffstat (limited to 'arch/riscv/kernel')
-rw-r--r-- | arch/riscv/kernel/Makefile | 4 | ||||
-rw-r--r-- | arch/riscv/kernel/alternative.c | 2 | ||||
-rw-r--r-- | arch/riscv/kernel/cpufeature.c | 256 | ||||
-rw-r--r-- | arch/riscv/kernel/entry.S | 3 | ||||
-rw-r--r-- | arch/riscv/kernel/pi/Makefile | 3 | ||||
-rw-r--r-- | arch/riscv/kernel/ptrace.c | 6 | ||||
-rw-r--r-- | arch/riscv/kernel/smpboot.c | 1 | ||||
-rw-r--r-- | arch/riscv/kernel/sys_hwprobe.c | 13 | ||||
-rw-r--r-- | arch/riscv/kernel/traps.c | 17 | ||||
-rw-r--r-- | arch/riscv/kernel/traps_misaligned.c | 17 | ||||
-rw-r--r-- | arch/riscv/kernel/unaligned_access_speed.c | 282 |
11 files changed, 334 insertions, 270 deletions
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..c8085126a6f9 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -38,7 +38,6 @@ extra-y += vmlinux.lds obj-y += head.o obj-y += soc.o obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o -obj-y += copy-unaligned.o obj-y += cpu.o obj-y += cpufeature.o obj-y += entry.o @@ -62,6 +61,9 @@ obj-y += tests/ obj-$(CONFIG_MMU) += vdso.o vdso/ obj-$(CONFIG_RISCV_MISALIGNED) += traps_misaligned.o +obj-$(CONFIG_RISCV_MISALIGNED) += unaligned_access_speed.o +obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) += copy-unaligned.o + obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_RISCV_ISA_V) += vector.o obj-$(CONFIG_RISCV_ISA_V) += kernel_mode_vector.o diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 319a1da0358b..0128b161bfda 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -43,7 +43,7 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info switch (cpu_mfr_info->vendor_id) { #ifdef CONFIG_ERRATA_ANDES - case ANDESTECH_VENDOR_ID: + case ANDES_VENDOR_ID: cpu_mfr_info->patch_func = andes_errata_patch_func; break; #endif diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 89920f84d0a3..afeae3ff43dc 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -11,7 +11,6 @@ #include <linux/cpu.h> #include <linux/cpuhotplug.h> #include <linux/ctype.h> -#include <linux/jump_label.h> #include <linux/log2.h> #include <linux/memory.h> #include <linux/module.h> @@ -21,20 +20,12 @@ #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> -#include <asm/hwprobe.h> #include <asm/patch.h> #include <asm/processor.h> #include <asm/vector.h> -#include "copy-unaligned.h" - #define NUM_ALPHA_EXTS ('z' - 'a' + 1) -#define MISALIGNED_ACCESS_JIFFIES_LG2 1 -#define MISALIGNED_BUFFER_SIZE 0x4000 -#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) -#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) - unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ @@ -43,11 +34,6 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; /* Per-cpu ISA extensions. */ struct riscv_isainfo hart_isa[NR_CPUS]; -/* Performance information */ -DEFINE_PER_CPU(long, misaligned_access_speed); - -static cpumask_t fast_misaligned_access; - /** * riscv_isa_extension_base() - Get base extension word * @@ -307,6 +293,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __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(xandespmu, RISCV_ISA_EXT_XANDESPMU), }; const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); @@ -706,247 +693,6 @@ unsigned long riscv_get_elf_hwcap(void) return hwcap; } -static int check_unaligned_access(void *param) -{ - int cpu = smp_processor_id(); - u64 start_cycles, end_cycles; - u64 word_cycles; - u64 byte_cycles; - int ratio; - unsigned long start_jiffies, now; - struct page *page = param; - void *dst; - void *src; - long speed = RISCV_HWPROBE_MISALIGNED_SLOW; - - if (check_unaligned_access_emulated(cpu)) - return 0; - - /* Make an unaligned destination buffer. */ - dst = (void *)((unsigned long)page_address(page) | 0x1); - /* Unalign src as well, but differently (off by 1 + 2 = 3). */ - src = dst + (MISALIGNED_BUFFER_SIZE / 2); - src += 2; - word_cycles = -1ULL; - /* Do a warmup. */ - __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); - preempt_disable(); - start_jiffies = jiffies; - while ((now = jiffies) == start_jiffies) - cpu_relax(); - - /* - * For a fixed amount of time, repeatedly try the function, and take - * the best time in cycles as the measurement. - */ - while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { - start_cycles = get_cycles64(); - /* Ensure the CSR read can't reorder WRT to the copy. */ - mb(); - __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); - /* Ensure the copy ends before the end time is snapped. */ - mb(); - end_cycles = get_cycles64(); - if ((end_cycles - start_cycles) < word_cycles) - word_cycles = end_cycles - start_cycles; - } - - byte_cycles = -1ULL; - __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); - start_jiffies = jiffies; - while ((now = jiffies) == start_jiffies) - cpu_relax(); - - while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { - start_cycles = get_cycles64(); - mb(); - __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); - mb(); - end_cycles = get_cycles64(); - if ((end_cycles - start_cycles) < byte_cycles) - byte_cycles = end_cycles - start_cycles; - } - - preempt_enable(); - - /* Don't divide by zero. */ - if (!word_cycles || !byte_cycles) { - pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", - cpu); - - return 0; - } - - if (word_cycles < byte_cycles) - speed = RISCV_HWPROBE_MISALIGNED_FAST; - - ratio = div_u64((byte_cycles * 100), word_cycles); - pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n", - cpu, - ratio / 100, - ratio % 100, - (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); - - per_cpu(misaligned_access_speed, cpu) = speed; - - /* - * Set the value of fast_misaligned_access of a CPU. These operations - * are atomic to avoid race conditions. - */ - if (speed == RISCV_HWPROBE_MISALIGNED_FAST) - cpumask_set_cpu(cpu, &fast_misaligned_access); - else - cpumask_clear_cpu(cpu, &fast_misaligned_access); - - return 0; -} - -static void check_unaligned_access_nonboot_cpu(void *param) -{ - unsigned int cpu = smp_processor_id(); - struct page **pages = param; - - if (smp_processor_id() != 0) - check_unaligned_access(pages[cpu]); -} - -DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key); - -static void modify_unaligned_access_branches(cpumask_t *mask, int weight) -{ - if (cpumask_weight(mask) == weight) - static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key); - else - static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key); -} - -static void set_unaligned_access_static_branches_except_cpu(int cpu) -{ - /* - * Same as set_unaligned_access_static_branches, except excludes the - * given CPU from the result. When a CPU is hotplugged into an offline - * state, this function is called before the CPU is set to offline in - * the cpumask, and thus the CPU needs to be explicitly excluded. - */ - - cpumask_t fast_except_me; - - cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask); - cpumask_clear_cpu(cpu, &fast_except_me); - - modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1); -} - -static void set_unaligned_access_static_branches(void) -{ - /* - * This will be called after check_unaligned_access_all_cpus so the - * result of unaligned access speed for all CPUs will be available. - * - * To avoid the number of online cpus changing between reading - * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be - * held before calling this function. - */ - - cpumask_t fast_and_online; - - cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask); - - modify_unaligned_access_branches(&fast_and_online, num_online_cpus()); -} - -static int lock_and_set_unaligned_access_static_branch(void) -{ - cpus_read_lock(); - set_unaligned_access_static_branches(); - cpus_read_unlock(); - - return 0; -} - -arch_initcall_sync(lock_and_set_unaligned_access_static_branch); - -static int riscv_online_cpu(unsigned int cpu) -{ - static struct page *buf; - - /* We are already set since the last check */ - if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) - goto exit; - - buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!buf) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return -ENOMEM; - } - - check_unaligned_access(buf); - __free_pages(buf, MISALIGNED_BUFFER_ORDER); - -exit: - set_unaligned_access_static_branches(); - - return 0; -} - -static int riscv_offline_cpu(unsigned int cpu) -{ - set_unaligned_access_static_branches_except_cpu(cpu); - - return 0; -} - -/* Measure unaligned access on all CPUs present at boot in parallel. */ -static int check_unaligned_access_all_cpus(void) -{ - unsigned int cpu; - unsigned int cpu_count = num_possible_cpus(); - struct page **bufs = kzalloc(cpu_count * sizeof(struct page *), - GFP_KERNEL); - - if (!bufs) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - return 0; - } - - /* - * Allocate separate buffers for each CPU so there's no fighting over - * cache lines. - */ - for_each_cpu(cpu, cpu_online_mask) { - bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); - if (!bufs[cpu]) { - pr_warn("Allocation failure, not measuring misaligned performance\n"); - goto out; - } - } - - /* Check everybody except 0, who stays behind to tend jiffies. */ - on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); - - /* Check core 0. */ - smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); - - /* - * Setup hotplug callbacks for any new CPUs that come online or go - * offline. - */ - cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", - riscv_online_cpu, riscv_offline_cpu); - -out: - unaligned_emulation_finish(); - for_each_cpu(cpu, cpu_online_mask) { - if (bufs[cpu]) - __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); - } - - kfree(bufs); - return 0; -} - -arch_initcall(check_unaligned_access_all_cpus); - void riscv_user_isa_enable(void) { if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 9d1a305d5508..68a24cf9481a 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -111,6 +111,7 @@ SYM_CODE_START(handle_exception) 1: tail do_trap_unknown SYM_CODE_END(handle_exception) +ASM_NOKPROBE(handle_exception) /* * The ret_from_exception must be called with interrupt disabled. Here is the @@ -184,6 +185,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) sret #endif SYM_CODE_END(ret_from_exception) +ASM_NOKPROBE(ret_from_exception) #ifdef CONFIG_VMAP_STACK SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) @@ -219,6 +221,7 @@ SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) move a0, sp tail handle_bad_stack SYM_CODE_END(handle_kernel_stack_overflow) +ASM_NOKPROBE(handle_kernel_stack_overflow) #endif SYM_CODE_START(ret_from_fork) diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index 07915dc9279e..b75f150b923d 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -9,6 +9,9 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) +# Disable LTO +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS)) + KBUILD_CFLAGS += -mcmodel=medany CFLAGS_cmdline_early.o += -D__NO_FORTIFY diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index e8515aa9d80b..92731ff8c79a 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -377,14 +377,14 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, return ret; } +#else +static const struct user_regset_view compat_riscv_user_native_view = {}; #endif /* CONFIG_COMPAT */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { -#ifdef CONFIG_COMPAT - if (test_tsk_thread_flag(task, TIF_32BIT)) + if (is_compat_thread(&task->thread_info)) return &compat_riscv_user_native_view; else -#endif return &riscv_user_native_view; } diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 519b6bd946e5..cfbe4b840d42 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -28,7 +28,6 @@ #include <asm/cpufeature.h> #include <asm/cpu_ops.h> -#include <asm/cpufeature.h> #include <asm/irq.h> #include <asm/mmu_context.h> #include <asm/numa.h> diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index a7c56b41efd2..8cae41a502dd 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -147,6 +147,7 @@ static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext) return (pair.value & ext); } +#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) static u64 hwprobe_misaligned(const struct cpumask *cpus) { int cpu; @@ -169,6 +170,18 @@ static u64 hwprobe_misaligned(const struct cpumask *cpus) return perf; } +#else +static u64 hwprobe_misaligned(const struct cpumask *cpus) +{ + if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_FAST; + + if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available()) + return RISCV_HWPROBE_MISALIGNED_EMULATED; + + return RISCV_HWPROBE_MISALIGNED_SLOW; +} +#endif static void hwprobe_one_pair(struct riscv_hwprobe *pair, const struct cpumask *cpus) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index a1b9be3c4332..868d6280cf66 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -6,6 +6,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/randomize_kstack.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/signal.h> @@ -310,7 +311,8 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) } } -asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) +asmlinkage __visible __trap_section __no_stack_protector +void do_trap_ecall_u(struct pt_regs *regs) { if (user_mode(regs)) { long syscall = regs->a7; @@ -322,10 +324,23 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) syscall = syscall_enter_from_user_mode(regs, syscall); + add_random_kstack_offset(); + if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); else if (syscall != -1) regs->a0 = -ENOSYS; + /* + * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(), + * so the maximum stack offset is 1k bytes (10 bits). + * + * The actual entropy will be further reduced by the compiler when + * applying stack alignment constraints: 16-byte (i.e. 4-bit) aligned + * for RV32I or RV64I. + * + * The resulting 6 bits of entropy is seen in SP[9:4]. + */ + choose_random_kstack_offset(get_random_u16()); syscall_exit_to_user_mode(regs); } else { diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 8ded225e8c5b..2adb7c3e4dd5 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -413,7 +413,9 @@ int handle_misaligned_load(struct pt_regs *regs) perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_EMULATED; +#endif if (!unaligned_enabled) return -1; @@ -596,7 +598,7 @@ int handle_misaligned_store(struct pt_regs *regs) return 0; } -bool check_unaligned_access_emulated(int cpu) +static bool check_unaligned_access_emulated(int cpu) { long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); unsigned long tmp_var, tmp_val; @@ -623,7 +625,7 @@ bool check_unaligned_access_emulated(int cpu) return misaligned_emu_detected; } -void unaligned_emulation_finish(void) +bool check_unaligned_access_emulated_all_cpus(void) { int cpu; @@ -632,13 +634,12 @@ void unaligned_emulation_finish(void) * accesses emulated since tasks requesting such control can run on any * CPU. */ - for_each_present_cpu(cpu) { - if (per_cpu(misaligned_access_speed, cpu) != - RISCV_HWPROBE_MISALIGNED_EMULATED) { - return; - } - } + for_each_online_cpu(cpu) + if (!check_unaligned_access_emulated(cpu)) + return false; + unaligned_ctl = true; + return true; } bool unaligned_ctl_available(void) diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c new file mode 100644 index 000000000000..52264ea4f0bd --- /dev/null +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -0,0 +1,282 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2024 Rivos Inc. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/jump_label.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/types.h> +#include <asm/cpufeature.h> +#include <asm/hwprobe.h> + +#include "copy-unaligned.h" + +#define MISALIGNED_ACCESS_JIFFIES_LG2 1 +#define MISALIGNED_BUFFER_SIZE 0x4000 +#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) +#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) + +DEFINE_PER_CPU(long, misaligned_access_speed); + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS +static cpumask_t fast_misaligned_access; +static int check_unaligned_access(void *param) +{ + int cpu = smp_processor_id(); + u64 start_cycles, end_cycles; + u64 word_cycles; + u64 byte_cycles; + int ratio; + unsigned long start_jiffies, now; + struct page *page = param; + void *dst; + void *src; + long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + return 0; + + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)page_address(page) | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + word_cycles = -1ULL; + /* Do a warmup. */ + __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + preempt_disable(); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + /* + * For a fixed amount of time, repeatedly try the function, and take + * the best time in cycles as the measurement. + */ + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + /* Ensure the CSR read can't reorder WRT to the copy. */ + mb(); + __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + /* Ensure the copy ends before the end time is snapped. */ + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < word_cycles) + word_cycles = end_cycles - start_cycles; + } + + byte_cycles = -1ULL; + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + mb(); + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < byte_cycles) + byte_cycles = end_cycles - start_cycles; + } + + preempt_enable(); + + /* Don't divide by zero. */ + if (!word_cycles || !byte_cycles) { + pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", + cpu); + + return 0; + } + + if (word_cycles < byte_cycles) + speed = RISCV_HWPROBE_MISALIGNED_FAST; + + ratio = div_u64((byte_cycles * 100), word_cycles); + pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n", + cpu, + ratio / 100, + ratio % 100, + (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); + + per_cpu(misaligned_access_speed, cpu) = speed; + + /* + * Set the value of fast_misaligned_access of a CPU. These operations + * are atomic to avoid race conditions. + */ + if (speed == RISCV_HWPROBE_MISALIGNED_FAST) + cpumask_set_cpu(cpu, &fast_misaligned_access); + else + cpumask_clear_cpu(cpu, &fast_misaligned_access); + + return 0; +} + +static void check_unaligned_access_nonboot_cpu(void *param) +{ + unsigned int cpu = smp_processor_id(); + struct page **pages = param; + + if (smp_processor_id() != 0) + check_unaligned_access(pages[cpu]); +} + +DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); + +static void modify_unaligned_access_branches(cpumask_t *mask, int weight) +{ + if (cpumask_weight(mask) == weight) + static_branch_enable_cpuslocked(&fast_unaligned_access_speed_key); + else + static_branch_disable_cpuslocked(&fast_unaligned_access_speed_key); +} + +static void set_unaligned_access_static_branches_except_cpu(int cpu) +{ + /* + * Same as set_unaligned_access_static_branches, except excludes the + * given CPU from the result. When a CPU is hotplugged into an offline + * state, this function is called before the CPU is set to offline in + * the cpumask, and thus the CPU needs to be explicitly excluded. + */ + + cpumask_t fast_except_me; + + cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask); + cpumask_clear_cpu(cpu, &fast_except_me); + + modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1); +} + +static void set_unaligned_access_static_branches(void) +{ + /* + * This will be called after check_unaligned_access_all_cpus so the + * result of unaligned access speed for all CPUs will be available. + * + * To avoid the number of online cpus changing between reading + * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be + * held before calling this function. + */ + + cpumask_t fast_and_online; + + cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask); + + modify_unaligned_access_branches(&fast_and_online, num_online_cpus()); +} + +static int lock_and_set_unaligned_access_static_branch(void) +{ + cpus_read_lock(); + set_unaligned_access_static_branches(); + cpus_read_unlock(); + + return 0; +} + +arch_initcall_sync(lock_and_set_unaligned_access_static_branch); + +static int riscv_online_cpu(unsigned int cpu) +{ + static struct page *buf; + + /* We are already set since the last check */ + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) + goto exit; + + buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!buf) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return -ENOMEM; + } + + check_unaligned_access(buf); + __free_pages(buf, MISALIGNED_BUFFER_ORDER); + +exit: + set_unaligned_access_static_branches(); + + return 0; +} + +static int riscv_offline_cpu(unsigned int cpu) +{ + set_unaligned_access_static_branches_except_cpu(cpu); + + return 0; +} + +/* Measure unaligned access speed on all CPUs present at boot in parallel. */ +static int check_unaligned_access_speed_all_cpus(void) +{ + unsigned int cpu; + unsigned int cpu_count = num_possible_cpus(); + struct page **bufs = kzalloc(cpu_count * sizeof(struct page *), + GFP_KERNEL); + + if (!bufs) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return 0; + } + + /* + * Allocate separate buffers for each CPU so there's no fighting over + * cache lines. + */ + for_each_cpu(cpu, cpu_online_mask) { + bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!bufs[cpu]) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + goto out; + } + } + + /* Check everybody except 0, who stays behind to tend jiffies. */ + on_each_cpu(check_unaligned_access_nonboot_cpu, bufs, 1); + + /* Check core 0. */ + smp_call_on_cpu(0, check_unaligned_access, bufs[0], true); + + /* + * Setup hotplug callbacks for any new CPUs that come online or go + * offline. + */ + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu, riscv_offline_cpu); + +out: + for_each_cpu(cpu, cpu_online_mask) { + if (bufs[cpu]) + __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + } + + kfree(bufs); + return 0; +} + +static int check_unaligned_access_all_cpus(void) +{ + bool all_cpus_emulated = check_unaligned_access_emulated_all_cpus(); + + if (!all_cpus_emulated) + return check_unaligned_access_speed_all_cpus(); + + return 0; +} +#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ +static int check_unaligned_access_all_cpus(void) +{ + check_unaligned_access_emulated_all_cpus(); + + return 0; +} +#endif + +arch_initcall(check_unaligned_access_all_cpus); |