diff options
128 files changed, 2515 insertions, 1591 deletions
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 8b679e2ca3c3..89e5d864e923 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -53,8 +53,8 @@ obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o obj-$(CONFIG_ARM_ARCH_TIMER) += arch_timer.o obj-$(CONFIG_FUNCTION_TRACER) += entry-ftrace.o -obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o patch.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o patch.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o # Main staffs in KPROBES are in arch/arm/probes/ . diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index bda949fd84e8..2a5ff69c28e6 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -22,6 +22,7 @@ #include <asm/ftrace.h> #include <asm/insn.h> #include <asm/set_memory.h> +#include <asm/patch.h> #ifdef CONFIG_THUMB2_KERNEL #define NOP 0xf85deb04 /* pop.w {lr} */ @@ -35,9 +36,7 @@ static int __ftrace_modify_code(void *data) { int *command = data; - set_kernel_text_rw(); ftrace_modify_all_code(*command); - set_kernel_text_ro(); return 0; } @@ -59,13 +58,11 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr) int ftrace_arch_code_modify_prepare(void) { - set_all_modules_text_rw(); return 0; } int ftrace_arch_code_modify_post_process(void) { - set_all_modules_text_ro(); /* Make sure any TLB misses during machine stop are cleared. */ flush_tlb_all(); return 0; @@ -97,10 +94,7 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, return -EINVAL; } - if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE)) - return -EPERM; - - flush_icache_range(pc, pc + MCOUNT_INSN_SIZE); + __patch_text((void *)pc, new); return 0; } diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index fd2a54b8cd57..22ab77ea27ad 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -89,18 +89,6 @@ int __init ftrace_dyn_arch_init(void) return 0; } -int ftrace_arch_code_modify_prepare(void) -{ - set_all_modules_text_rw(); - return 0; -} - -int ftrace_arch_code_modify_post_process(void) -{ - set_all_modules_text_ro(); - return 0; -} - static unsigned long gen_sethi_insn(unsigned long addr) { unsigned long opcode = 0x46000000; diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index a7752cd78b89..1f22b6bbda68 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -14,6 +14,10 @@ static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); static unsigned long perf_nmi_window; +/* AMD Event 0xFFF: Merge. Used with Large Increment per Cycle events */ +#define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL) +#define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE) + static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -301,6 +305,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } +/* + * AMD64 events are detected based on their event codes. + */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + +static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) +{ + if (!(x86_pmu.flags & PMU_FL_PAIR)) + return false; + + switch (amd_get_event_code(hwc)) { + case 0x003: return true; /* Retired SSE/AVX FLOPs */ + default: return false; + } +} + static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -316,15 +339,10 @@ static int amd_core_hw_config(struct perf_event *event) else if (event->attr.exclude_guest) event->hw.config |= AMD64_EVENTSEL_HOSTONLY; - return 0; -} + if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw)) + event->hw.flags |= PERF_X86_EVENT_PAIR; -/* - * AMD64 events are detected based on their event codes. - */ -static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) -{ - return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); + return 0; } static inline int amd_is_nb_event(struct hw_perf_event *hwc) @@ -855,6 +873,29 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, } } +static struct event_constraint pair_constraint; + +static struct event_constraint * +amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (amd_is_pair_event_code(hwc)) + return &pair_constraint; + + return &unconstrained; +} + +static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (is_counter_pair(hwc)) + --cpuc->n_pair; +} + static ssize_t amd_event_sysfs_show(char *page, u64 config) { u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | @@ -898,33 +939,15 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { + u64 even_ctr_mask = 0ULL; + int i; + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; - /* Avoid calulating the value each time in the NMI handler */ + /* Avoid calculating the value each time in the NMI handler */ perf_nmi_window = msecs_to_jiffies(100); - switch (boot_cpu_data.x86) { - case 0x15: - pr_cont("Fam15h "); - x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - break; - case 0x17: - pr_cont("Fam17h "); - /* - * In family 17h, there are no event constraints in the PMC hardware. - * We fallback to using default amd_get_event_constraints. - */ - break; - case 0x18: - pr_cont("Fam18h "); - /* Using default amd_get_event_constraints. */ - break; - default: - pr_err("core perfctr but no constraints; unknown hardware!\n"); - return -ENODEV; - } - /* * If core performance counter extensions exists, we must use * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also @@ -939,6 +962,32 @@ static int __init amd_core_pmu_init(void) */ x86_pmu.amd_nb_constraints = 0; + if (boot_cpu_data.x86 == 0x15) { + pr_cont("Fam15h "); + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + } + if (boot_cpu_data.x86 >= 0x17) { + pr_cont("Fam17h+ "); + /* + * Family 17h and compatibles have constraints for Large + * Increment per Cycle events: they may only be assigned an + * even numbered counter that has a consecutive adjacent odd + * numbered counter following it. + */ + for (i = 0; i < x86_pmu.num_counters - 1; i += 2) + even_ctr_mask |= 1 << i; + + pair_constraint = (struct event_constraint) + __EVENT_CONSTRAINT(0, even_ctr_mask, 0, + x86_pmu.num_counters / 2, 0, + PERF_X86_EVENT_PAIR); + + x86_pmu.get_event_constraints = amd_get_event_constraints_f17h; + x86_pmu.put_event_constraints = amd_put_event_constraints_f17h; + x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE; + x86_pmu.flags |= PMU_FL_PAIR; + } + pr_cont("core perfctr, "); return 0; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index f118af9f0718..3bb738f5a472 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -618,6 +618,7 @@ void x86_pmu_disable_all(void) int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; u64 val; if (!test_bit(idx, cpuc->active_mask)) @@ -627,6 +628,8 @@ void x86_pmu_disable_all(void) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu_config_addr(idx), val); + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(idx + 1), 0); } } @@ -699,7 +702,7 @@ struct sched_state { int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ - unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 used; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ @@ -756,8 +759,12 @@ static bool perf_sched_restore_state(struct perf_sched *sched) sched->saved_states--; sched->state = sched->saved[sched->saved_states]; - /* continue with next counter: */ - clear_bit(sched->state.counter++, sched->state.used); + /* this assignment didn't work out */ + /* XXX broken vs EVENT_PAIR */ + sched->state.used &= ~BIT_ULL(sched->state.counter); + + /* try the next one */ + sched->state.counter++; return true; } @@ -782,20 +789,32 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { - if (!__test_and_set_bit(idx, sched->state.used)) - goto done; + u64 mask = BIT_ULL(idx); + + if (sched->state.used & mask) + continue; + + sched->state.used |= mask; + goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { - if (!__test_and_set_bit(idx, sched->state.used)) { - if (sched->state.nr_gp++ >= sched->max_gp) - return false; + u64 mask = BIT_ULL(idx); - goto done; - } + if (c->flags & PERF_X86_EVENT_PAIR) + mask |= mask << 1; + + if (sched->state.used & mask) + continue; + + if (sched->state.nr_gp++ >= sched->max_gp) + return false; + + sched->state.used |= mask; + goto done; } return false; @@ -872,12 +891,10 @@ EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; - unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; - - bitmap_zero(used_mask, X86_PMC_IDX_MAX); + u64 used_mask = 0; /* * Compute the number of events already present; see x86_pmu_add(), @@ -920,6 +937,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { + u64 mask; + hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; @@ -931,11 +950,16 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!test_bit(hwc->idx, c->idxmsk)) break; + mask = BIT_ULL(hwc->idx); + if (is_counter_pair(hwc)) + mask |= mask << 1; + /* not already used */ - if (test_bit(hwc->idx, used_mask)) + if (used_mask & mask) break; - __set_bit(hwc->idx, used_mask); + used_mask |= mask; + if (assign) assign[i] = hwc->idx; } @@ -958,6 +982,15 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; + /* + * Reduce the amount of available counters to allow fitting + * the extra Merge events needed by large increment events. + */ + if (x86_pmu.flags & PMU_FL_PAIR) { + gpmax = x86_pmu.num_counters - cpuc->n_pair; + WARN_ON(gpmax <= 0); + } + unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } @@ -1038,6 +1071,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, return -EINVAL; cpuc->event_list[n] = leader; n++; + if (is_counter_pair(&leader->hw)) + cpuc->n_pair++; } if (!dogrp) return n; @@ -1052,6 +1087,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, cpuc->event_list[n] = event; n++; + if (is_counter_pair(&event->hw)) + cpuc->n_pair++; } return n; } @@ -1238,6 +1275,13 @@ int x86_perf_event_set_period(struct perf_event *event) wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* + * Clear the Merge event counter's upper 16 bits since + * we currently declare a 48-bit counter width + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_event_addr(idx + 1), 0); + + /* * Due to erratum on certan cpu we need * a second write to be sure the register * is updated properly diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 5053a403e4ae..09913121e726 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -741,6 +741,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE, model_skl), {}, }; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 930611db8f9a..f1cd1ca1a77b 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -77,6 +77,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ #define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */ +#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -272,6 +273,7 @@ struct cpu_hw_events { struct amd_nb *amd_nb; /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; + int n_pair; /* Large increment events */ void *kfree_on_online[X86_PERF_KFREE_MAX]; }; @@ -694,6 +696,7 @@ struct x86_pmu { * AMD bits */ unsigned int amd_nb_constraints : 1; + u64 perf_ctr_pair_en; /* * Extra registers for events @@ -743,6 +746,7 @@ do { \ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ +#define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -838,6 +842,11 @@ int x86_pmu_hw_config(struct perf_event *event); void x86_pmu_disable_all(void); +static inline bool is_counter_pair(struct hw_perf_event *hwc) +{ + return hwc->flags & PERF_X86_EVENT_PAIR; +} + static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { @@ -845,6 +854,14 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, if (hwc->extra_reg.reg) wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + + /* + * Add enabled Merge event on next counter + * if large increment event being enabled on this counter + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en); + wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask); } @@ -861,6 +878,9 @@ static inline void x86_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; wrmsrl(hwc->config_base, hwc->config); + + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0); } void x86_pmu_enable_event(struct perf_event *event); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index c2a7458f912c..85be2f506272 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -47,8 +47,6 @@ struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; -int ftrace_int3_handler(struct pt_regs *regs); - #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 5dc909d9ad81..95b1f053bd96 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -11,12 +11,11 @@ #include <asm-generic/kprobes.h> -#define BREAKPOINT_INSTRUCTION 0xcc - #ifdef CONFIG_KPROBES #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/text-patching.h> #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -25,10 +24,7 @@ struct pt_regs; struct kprobe; typedef u8 kprobe_opcode_t; -#define RELATIVEJUMP_OPCODE 0xe9 -#define RELATIVEJUMP_SIZE 5 -#define RELATIVECALL_OPCODE 0xe8 -#define RELATIVE_ADDR_SIZE 4 + #define MAX_STACK_SIZE 64 #define CUR_STACK_SIZE(ADDR) \ (current_top_of_stack() - (unsigned long)(ADDR)) @@ -43,11 +39,11 @@ extern __visible kprobe_opcode_t optprobe_template_entry[]; extern __visible kprobe_opcode_t optprobe_template_val[]; extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; -#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)optprobe_template_end - \ (unsigned long)optprobe_template_entry) + \ - MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) + MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE) extern const int kretprobe_blacklist_size; @@ -73,7 +69,7 @@ struct arch_specific_insn { struct arch_optimized_insn { /* copy of the original instructions */ - kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE]; + kprobe_opcode_t copied_insn[DISP32_SIZE]; /* detour code buffer */ kprobe_opcode_t *insn; /* the size of instructions copied to detour code buffer */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 2ee8e469dcf5..64c3dce374e5 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -81,8 +81,6 @@ int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); extern int kernel_set_to_readonly; -void set_kernel_text_rw(void); -void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 static inline int set_mce_nospec(unsigned long pfn) diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 23c626a742e8..67315fa3956a 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -25,14 +25,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, */ #define POKE_MAX_OPCODE_SIZE 5 -struct text_poke_loc { - void *addr; - int len; - s32 rel32; - u8 opcode; - const u8 text[POKE_MAX_OPCODE_SIZE]; -}; - extern void text_poke_early(void *addr, const void *opcode, size_t len); /* @@ -50,21 +42,13 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); * an inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); +extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); -extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries); -extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr, - const void *opcode, size_t len, const void *emulate); -extern int after_bootmem; -extern __ro_after_init struct mm_struct *poking_mm; -extern __ro_after_init unsigned long poking_addr; -#ifndef CONFIG_UML_X86 -static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) -{ - regs->ip = ip; -} +extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate); +extern void text_poke_finish(void); #define INT3_INSN_SIZE 1 #define INT3_INSN_OPCODE 0xCC @@ -78,6 +62,67 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) #define JMP8_INSN_SIZE 2 #define JMP8_INSN_OPCODE 0xEB +#define DISP32_SIZE 4 + +static inline int text_opcode_size(u8 opcode) +{ + int size = 0; + +#define __CASE(insn) \ + case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break + + switch(opcode) { + __CASE(INT3); + __CASE(CALL); + __CASE(JMP32); + __CASE(JMP8); + } + +#undef __CASE + + return size; +} + +union text_poke_insn { + u8 text[POKE_MAX_OPCODE_SIZE]; + struct { + u8 opcode; + s32 disp; + } __attribute__((packed)); +}; + +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + int size = text_opcode_size(opcode); + + insn.opcode = opcode; + + if (size > 1) { + insn.disp = (long)dest - (long)(addr + size); + if (size == 2) { + /* + * Ensure that for JMP9 the displacement + * actually fits the signed byte. + */ + BUG_ON((insn.disp >> 31) != (insn.disp >> 7)); + } + } + + return &insn.text; +} + +extern int after_bootmem; +extern __ro_after_init struct mm_struct *poking_mm; +extern __ro_after_init unsigned long poking_addr; + +#ifndef CONFIG_UML_X86 +static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) { /* @@ -85,6 +130,9 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) * stack where the break point happened, and the saving of * pt_regs. We can extend the original stack because of * this gap. See the idtentry macro's create_gap option. + * + * Similarly entry_32.S will have a gap on the stack for (any) hardware + * exception and pt_regs; see FIXUP_FRAME. */ regs->sp -= sizeof(unsigned long); *(unsigned long *)regs->sp = val; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 9ec463fe96f2..34360ca301a2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -936,44 +936,81 @@ static void do_sync_core(void *info) sync_core(); } -static struct bp_patching_desc { +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +struct text_poke_loc { + s32 rel_addr; /* addr := _stext + rel_addr */ + s32 rel32; + u8 opcode; + const u8 text[POKE_MAX_OPCODE_SIZE]; +}; + +struct bp_patching_desc { struct text_poke_loc *vec; int nr_entries; -} bp_patching; + atomic_t refs; +}; + +static struct bp_patching_desc *bp_desc; + +static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +{ + struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */ + + if (!desc || !atomic_inc_not_zero(&desc->refs)) + return NULL; + + return desc; +} + +static inline void put_desc(struct bp_patching_desc *desc) +{ + smp_mb__before_atomic(); + atomic_dec(&desc->refs); +} -static int patch_cmp(const void *key, const void *elt) +static inline void *text_poke_addr(struct text_poke_loc *tp) +{ + return _stext + tp->rel_addr; +} + +static int notrace patch_cmp(const void *key, const void *elt) { struct text_poke_loc *tp = (struct text_poke_loc *) elt; - if (key < tp->addr) + if (key < text_poke_addr(tp)) return -1; - if (key > tp->addr) + if (key > text_poke_addr(tp)) return 1; return 0; } NOKPROBE_SYMBOL(patch_cmp); -int poke_int3_handler(struct pt_regs *regs) +int notrace poke_int3_handler(struct pt_regs *regs) { + struct bp_patching_desc *desc; struct text_poke_loc *tp; + int len, ret = 0; void *ip; + if (user_mode(regs)) + return 0; + /* * Having observed our INT3 instruction, we now must observe - * bp_patching.nr_entries. + * bp_desc: * - * nr_entries != 0 INT3 + * bp_desc = desc INT3 * WMB RMB - * write INT3 if (nr_entries) - * - * Idem for other elements in bp_patching. + * write INT3 if (desc) */ smp_rmb(); - if (likely(!bp_patching.nr_entries)) - return 0; - - if (user_mode(regs)) + desc = try_get_desc(&bp_desc); + if (!desc) return 0; /* @@ -984,19 +1021,20 @@ int poke_int3_handler(struct pt_regs *regs) /* * Skip the binary search if there is a single member in the vector. */ - if (unlikely(bp_patching.nr_entries > 1)) { - tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries, + if (unlikely(desc->nr_entries > 1)) { + tp = bsearch(ip, desc->vec, desc->nr_entries, sizeof(struct text_poke_loc), patch_cmp); if (!tp) - return 0; + goto out_put; } else { - tp = bp_patching.vec; - if (tp->addr != ip) - return 0; + tp = desc->vec; + if (text_poke_addr(tp) != ip) + goto out_put; } - ip += tp->len; + len = text_opcode_size(tp->opcode); + ip += len; switch (tp->opcode) { case INT3_INSN_OPCODE: @@ -1004,7 +1042,7 @@ int poke_int3_handler(struct pt_regs *regs) * Someone poked an explicit INT3, they'll want to handle it, * do not consume. */ - return 0; + goto out_put; case CALL_INSN_OPCODE: int3_emulate_call(regs, (long)ip + tp->rel32); @@ -1019,10 +1057,18 @@ int poke_int3_handler(struct pt_regs *regs) BUG(); } - return 1; + ret = 1; + +out_put: + put_desc(desc); + return ret; } NOKPROBE_SYMBOL(poke_int3_handler); +#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) +static struct text_poke_loc tp_vec[TP_VEC_MAX]; +static int tp_vec_nr; + /** * text_poke_bp_batch() -- update instructions on live kernel on SMP * @tp: vector of instructions to patch @@ -1044,16 +1090,20 @@ NOKPROBE_SYMBOL(poke_int3_handler); * replacing opcode * - sync cores */ -void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) +static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { + struct bp_patching_desc desc = { + .vec = tp, + .nr_entries = nr_entries, + .refs = ATOMIC_INIT(1), + }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - bp_patching.vec = tp; - bp_patching.nr_entries = nr_entries; + smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ /* * Corresponding read barrier in int3 notifier for making sure the @@ -1065,18 +1115,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * First step: add a int3 trap to the address that will be patched. */ for (i = 0; i < nr_entries; i++) - text_poke(tp[i].addr, &int3, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE); - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].len - sizeof(int3) > 0) { - text_poke((char *)tp[i].addr + sizeof(int3), - (const char *)tp[i].text + sizeof(int3), - tp[i].len - sizeof(int3)); + int len = text_opcode_size(tp[i].opcode); + + if (len - INT3_INSN_SIZE > 0) { + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, + (const char *)tp[i].text + INT3_INSN_SIZE, + len - INT3_INSN_SIZE); do_sync++; } } @@ -1087,7 +1139,7 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * not necessary and we'd be safe even without it. But * better safe than sorry (plus there's not only Intel). */ - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); } /* @@ -1098,19 +1150,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) if (tp[i].text[0] == INT3_INSN_OPCODE) continue; - text_poke(tp[i].addr, tp[i].text, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); do_sync++; } if (do_sync) - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* - * sync_core() implies an smp_mb() and orders this store against - * the writing of the new instruction. + * Remove and synchronize_rcu(), except we have a very primitive + * refcount based completion. */ - bp_patching.vec = NULL; - bp_patching.nr_entries = 0; + WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ + if (!atomic_dec_and_test(&desc.refs)) + atomic_cond_read_acquire(&desc.refs, !VAL); } void text_poke_loc_init(struct text_poke_loc *tp, void *addr, @@ -1118,11 +1171,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, { struct insn insn; - if (!opcode) - opcode = (void *)tp->text; - else - memcpy((void *)tp->text, opcode, len); - + memcpy((void *)tp->text, opcode, len); if (!emulate) emulate = opcode; @@ -1132,8 +1181,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(!insn_complete(&insn)); BUG_ON(len != insn.length); - tp->addr = addr; - tp->len = len; + tp->rel_addr = addr - (void *)_stext; tp->opcode = insn.opcode.bytes[0]; switch (tp->opcode) { @@ -1167,6 +1215,55 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, } } +/* + * We hard rely on the tp_vec being ordered; ensure this is so by flushing + * early if needed. + */ +static bool tp_order_fail(void *addr) +{ + struct text_poke_loc *tp; + + if (!tp_vec_nr) + return false; + + if (!addr) /* force */ + return true; + + tp = &tp_vec[tp_vec_nr - 1]; + if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr) + return true; + + return false; +} + +static void text_poke_flush(void *addr) +{ + if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) { + text_poke_bp_batch(tp_vec, tp_vec_nr); + tp_vec_nr = 0; + } +} + +void text_poke_finish(void) +{ + text_poke_flush(NULL); +} + +void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate) +{ + struct text_poke_loc *tp; + + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + + text_poke_flush(addr); + + tp = &tp_vec[tp_vec_nr++]; + text_poke_loc_init(tp, addr, opcode, len, emulate); +} + /** * text_poke_bp() -- update instructions on live kernel on SMP * @addr: address to patch @@ -1178,10 +1275,15 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, * dynamically allocated memory. This function should be used when it is * not possible to allocate memory. */ -void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) +void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) { struct text_poke_loc tp; + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + text_poke_loc_init(&tp, addr, opcode, len, emulate); text_poke_bp_batch(&tp, 1); } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 2009047bb015..37a0aeaf89e7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -35,6 +35,8 @@ #ifdef CONFIG_DYNAMIC_FTRACE +static int ftrace_poke_late = 0; + int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { @@ -44,84 +46,37 @@ int ftrace_arch_code_modify_prepare(void) * ftrace has it set to "read/write". */ mutex_lock(&text_mutex); - set_kernel_text_rw(); - set_all_modules_text_rw(); + ftrace_poke_late = 1; return 0; } int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { - set_all_modules_text_ro(); - set_kernel_text_ro(); + /* + * ftrace_make_{call,nop}() may be called during + * module load, and we need to finish the text_poke_queue() + * that they do, here. + */ + text_poke_finish(); + ftrace_poke_late = 0; mutex_unlock(&text_mutex); return 0; } -union ftrace_code_union { - char code[MCOUNT_INSN_SIZE]; - struct { - unsigned char op; - int offset; - } __attribute__((packed)); -}; - -static int ftrace_calc_offset(long ip, long addr) -{ - return (int)(addr - ip); -} - -static unsigned char * -ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) +static const char *ftrace_nop_replace(void) { - static union ftrace_code_union calc; - - calc.op = op; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - return calc.code; -} - -static unsigned char * -ftrace_call_replace(unsigned long ip, unsigned long addr) -{ - return ftrace_text_replace(0xe8, ip, addr); -} - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) -{ - return addr >= start && addr < end; + return ideal_nops[NOP_ATOMIC5]; } -static unsigned long text_ip_addr(unsigned long ip) +static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) { - /* - * On x86_64, kernel text mappings are mapped read-only, so we use - * the kernel identity mapping instead of the kernel text mapping - * to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); - - return ip; + return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); } -static const unsigned char *ftrace_nop_replace(void) +static int ftrace_verify_code(unsigned long ip, const char *old_code) { - return ideal_nops[NOP_ATOMIC5]; -} - -static int -ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - - ftrace_expected = old_code; + char cur_code[MCOUNT_INSN_SIZE]; /* * Note: @@ -130,31 +85,46 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, * Carefully read and modify the code with probe_kernel_*(), and make * sure what we read is what we expected it to be before modifying it. */ - /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + WARN_ON(1); return -EFAULT; + } /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) { + WARN_ON(1); return -EINVAL; + } - ip = text_ip_addr(ip); - - /* replace the text with the new text */ - if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) - return -EPERM; + return 0; +} - sync_core(); +/* + * Marked __ref because it calls text_poke_early() which is .init.text. That is + * ok because that call will happen early, during boot, when .init sections are + * still present. + */ +static int __ref +ftrace_modify_code_direct(unsigned long ip, const char *old_code, + const char *new_code) +{ + int ret = ftrace_verify_code(ip, old_code); + if (ret) + return ret; + /* replace the text with the new text */ + if (ftrace_poke_late) + text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); + else + text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); return 0; } -int ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_call_replace(ip, addr); new = ftrace_nop_replace(); @@ -168,19 +138,20 @@ int ftrace_make_nop(struct module *mod, * just modify the code directly. */ if (addr == MCOUNT_ADDR) - return ftrace_modify_code_direct(rec->ip, old, new); + return ftrace_modify_code_direct(ip, old, new); - ftrace_expected = NULL; - - /* Normal cases use add_brk_on_nop */ + /* + * x86 overrides ftrace_replace_code -- this function will never be used + * in this case. + */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_nop_replace(); new = ftrace_call_replace(ip, addr); @@ -190,43 +161,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* - * The modifying_ftrace_code is used to tell the breakpoint - * handler to call ftrace_int3_handler(). If it fails to - * call this handler for a breakpoint added by ftrace, then - * the kernel may crash. - * - * As atomic_writes on x86 do not need a barrier, we do not - * need to add smp_mb()s for this to work. It is also considered - * that we can not read the modifying_ftrace_code before - * executing the breakpoint. That would be quite remarkable if - * it could do that. Here's the flow that is required: - * - * CPU-0 CPU-1 - * - * atomic_inc(mfc); - * write int3s - * <trap-int3> // implicit (r)mb - * if (atomic_read(mfc)) - * call ftrace_int3_handler() - * - * Then when we are finished: - * - * atomic_dec(mfc); - * - * If we hit a breakpoint that was not set by ftrace, it does not - * matter if ftrace_int3_handler() is called or not. It will - * simply be ignored. But it is crucial that a ftrace nop/caller - * breakpoint is handled. No other user should ever place a - * breakpoint on an ftrace nop/caller location. It must only - * be done by this code. - */ -atomic_t modifying_ftrace_code __read_mostly; - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code); - -/* * Should never be called: * As it is only called by __ftrace_replace_code() which is called by * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() @@ -238,452 +172,84 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); - ftrace_expected = NULL; return -EINVAL; } -static unsigned long ftrace_update_func; -static unsigned long ftrace_update_func_call; - -static int update_ftrace_func(unsigned long ip, void *new) -{ - unsigned char old[MCOUNT_INSN_SIZE]; - int ret; - - memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); - - ftrace_update_func = ip; - /* Make sure the breakpoints see the ftrace_update_func update */ - smp_wmb(); - - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - - ret = ftrace_modify_code(ip, old, new); - - atomic_dec(&modifying_ftrace_code); - - return ret; -} - int ftrace_update_ftrace_func(ftrace_func_t func) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char *new; - int ret; - - ftrace_update_func_call = (unsigned long)func; - - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - - /* Also update the regs callback function */ - if (!ret) { - ip = (unsigned long)(&ftrace_regs_call); - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - } - - return ret; -} - -static nokprobe_inline int is_ftrace_caller(unsigned long ip) -{ - if (ip == ftrace_update_func) - return 1; - - return 0; -} - -/* - * A breakpoint was added to the code address we are about to - * modify, and this is the handle that will just skip over it. - * We are either changing a nop into a trace call, or a trace - * call to a nop. While the change is taking place, we treat - * it just like it was a nop. - */ -int ftrace_int3_handler(struct pt_regs *regs) -{ unsigned long ip; + const char *new; - if (WARN_ON_ONCE(!regs)) - return 0; - - ip = regs->ip - INT3_INSN_SIZE; - - if (ftrace_location(ip)) { - int3_emulate_call(regs, (unsigned long)ftrace_regs_caller); - return 1; - } else if (is_ftrace_caller(ip)) { - if (!ftrace_update_func_call) { - int3_emulate_jmp(regs, ip + CALL_INSN_SIZE); - return 1; - } - int3_emulate_call(regs, ftrace_update_func_call); - return 1; - } - - return 0; -} -NOKPROBE_SYMBOL(ftrace_int3_handler); - -static int ftrace_write(unsigned long ip, const char *val, int size) -{ - ip = text_ip_addr(ip); - - if (probe_kernel_write((void *)ip, val, size)) - return -EPERM; - - return 0; -} - -static int add_break(unsigned long ip, const char *old) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - ftrace_expected = old; - - /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) - return -EINVAL; - - return ftrace_write(ip, &brk, 1); -} - -static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned const char *old; - unsigned long ip = rec->ip; - - old = ftrace_call_replace(ip, addr); - - return add_break(rec->ip, old); -} - - -static int add_brk_on_nop(struct dyn_ftrace *rec) -{ - unsigned const char *old; - - old = ftrace_nop_replace(); - - return add_break(rec->ip, old); -} - -static int add_breakpoints(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ftrace_addr = ftrace_get_addr_curr(rec); - - ret = ftrace_test_record(rec, enable); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_brk_on_nop(rec); - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_brk_on_call(rec, ftrace_addr); - } - return 0; -} - -/* - * On error, we need to remove breakpoints. This needs to - * be done caefully. If the address does not currently have a - * breakpoint, we know we are done. Otherwise, we look at the - * remaining 4 bytes of the instruction. If it matches a nop - * we replace the breakpoint with the nop. Otherwise we replace - * it with the call instruction. - */ -static int remove_breakpoint(struct dyn_ftrace *rec) -{ - unsigned char ins[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - const unsigned char *nop; - unsigned long ftrace_addr; - unsigned long ip = rec->ip; - - /* If we fail the read, just give up */ - if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* If this does not have a breakpoint, we are done */ - if (ins[0] != brk) - return 0; - - nop = ftrace_nop_replace(); - - /* - * If the last 4 bytes of the instruction do not match - * a nop, then we assume that this is a call to ftrace_addr. - */ - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) { - /* - * For extra paranoidism, we check if the breakpoint is on - * a call that would actually jump to the ftrace_addr. - * If not, don't touch the breakpoint, we make just create - * a disaster. - */ - ftrace_addr = ftrace_get_addr_new(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) - goto update; - - /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = ftrace_get_addr_curr(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - ftrace_expected = nop; - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) - return -EINVAL; - } - - update: - return ftrace_write(ip, nop, 1); -} - -static int add_update_code(unsigned long ip, unsigned const char *new) -{ - /* skip breakpoint */ - ip++; - new++; - return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1); -} - -static int add_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - return add_update_code(ip, new); -} - -static int add_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - return add_update_code(ip, new); -} - -static int add_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_test_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_update_call(rec, ftrace_addr); - - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_update_nop(rec); - } - - return 0; -} - -static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - - return ftrace_write(ip, new, 1); -} - -static int finish_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - - return ftrace_write(ip, new, 1); -} - -static int finish_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_update_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return finish_update_call(rec, ftrace_addr); + ip = (unsigned long)(&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return finish_update_nop(rec); - } + ip = (unsigned long)(&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); return 0; } -static void do_sync_core(void *data) -{ - sync_core(); -} - -static void run_sync(void) -{ - int enable_irqs; - - /* No need to sync if there's only one CPU */ - if (num_online_cpus() == 1) - return; - - enable_irqs = irqs_disabled(); - - /* We may be called with interrupts disabled (on bootup). */ - if (enable_irqs) - local_irq_enable(); - on_each_cpu(do_sync_core, NULL, 1); - if (enable_irqs) - local_irq_disable(); -} - void ftrace_replace_code(int enable) { struct ftrace_rec_iter *iter; struct dyn_ftrace *rec; - const char *report = "adding breakpoints"; - int count = 0; + const char *new, *old; int ret; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = add_breakpoints(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } - - run_sync(); + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - report = "updating code"; - count = 0; + case FTRACE_UPDATE_MAKE_CALL: + old = ftrace_nop_replace(); + break; - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); + case FTRACE_UPDATE_MODIFY_CALL: + case FTRACE_UPDATE_MAKE_NOP: + old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec)); + break; + } - ret = add_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; + ret = ftrace_verify_code(rec->ip, old); + if (ret) { + ftrace_bug(ret, rec); + return; + } } - run_sync(); - - report = "removing breakpoints"; - count = 0; - for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = finish_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - run_sync(); + case FTRACE_UPDATE_MAKE_CALL: + case FTRACE_UPDATE_MODIFY_CALL: + new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec)); + break; - return; + case FTRACE_UPDATE_MAKE_NOP: + new = ftrace_nop_replace(); + break; + } - remove_breakpoints: - pr_warn("Failed on %s (%d):\n", report, count); - ftrace_bug(ret, rec); - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); - /* - * Breakpoints are handled only when this function is in - * progress. The system could not work with them. - */ - if (remove_breakpoint(rec)) - BUG(); + text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL); + ftrace_update_record(rec, enable); } - run_sync(); -} - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - int ret; - - ret = add_break(ip, old_code); - if (ret) - goto out; - - run_sync(); - - ret = add_update_code(ip, new_code); - if (ret) - goto fail_update; - - run_sync(); - - ret = ftrace_write(ip, new_code, 1); - /* - * The breakpoint is handled only when this function is in progress. - * The system could not work if we could not remove it. - */ - BUG_ON(ret); - out: - run_sync(); - return ret; - - fail_update: - /* Also here the system could not work with the breakpoint */ - if (ftrace_write(ip, old_code, 1)) - BUG(); - goto out; + text_poke_finish(); } void arch_ftrace_update_code(int command) { - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - ftrace_modify_all_code(command); - - atomic_dec(&modifying_ftrace_code); } int __init ftrace_dyn_arch_init(void) @@ -748,6 +314,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long start_offset; unsigned long end_offset; unsigned long op_offset; + unsigned long call_offset; unsigned long offset; unsigned long npages; unsigned long size; @@ -764,10 +331,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) start_offset = (unsigned long)ftrace_regs_caller; end_offset = (unsigned long)ftrace_regs_caller_end; op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + call_offset = (unsigned long)ftrace_regs_call; } else { start_offset = (unsigned long)ftrace_caller; end_offset = (unsigned long)ftrace_epilogue; op_offset = (unsigned long)ftrace_caller_op_ptr; + call_offset = (unsigned long)ftrace_call; } size = end_offset - start_offset; @@ -824,16 +393,21 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* put in the new offset to the ftrace_ops */ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + /* put in the call to the function */ + mutex_lock(&text_mutex); + call_offset -= start_offset; + memcpy(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, + trampoline + call_offset, + ftrace_ops_get_func(ops)), CALL_INSN_SIZE); + mutex_unlock(&text_mutex); + /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; set_vm_flush_reset_perms(trampoline); - /* - * Module allocation needs to be completed by making the page - * executable. The page is still writable, which is a security hazard, - * but anyhow ftrace breaks W^X completely. - */ + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -860,62 +434,54 @@ static unsigned long calc_trampoline_call_offset(bool save_regs) void arch_ftrace_update_trampoline(struct ftrace_ops *ops) { ftrace_func_t func; - unsigned char *new; unsigned long offset; unsigned long ip; unsigned int size; - int ret, npages; + const char *new; - if (ops->trampoline) { - /* - * The ftrace_ops caller may set up its own trampoline. - * In such a case, this code must not modify it. - */ - if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) - return; - npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; - set_memory_rw(ops->trampoline, npages); - } else { + if (!ops->trampoline) { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; - npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + return; } + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); ip = ops->trampoline + offset; - func = ftrace_ops_get_func(ops); - ftrace_update_func_call = (unsigned long)func; - + mutex_lock(&text_mutex); /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - set_memory_ro(ops->trampoline, npages); - - /* The update should never fail */ - WARN_ON(ret); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + mutex_unlock(&text_mutex); } /* Return the address of the function the trampoline calls */ static void *addr_from_call(void *ptr) { - union ftrace_code_union calc; + union text_poke_insn call; int ret; - ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE); + ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.op != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.op); + if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) { + pr_warn("Expected E8, got %x\n", call.opcode); return NULL; } - return ptr + MCOUNT_INSN_SIZE + calc.offset; + return ptr + CALL_INSN_SIZE + call.disp; } void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, @@ -982,19 +548,18 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - return ftrace_text_replace(0xe9, ip, addr); + return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); } static int ftrace_mod_jmp(unsigned long ip, void *func) { - unsigned char *new; + const char *new; - ftrace_update_func_call = 0UL; new = ftrace_jmp_replace(ip, (unsigned long)func); - - return update_ftrace_func(ip, new); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + return 0; } int ftrace_enable_ftrace_graph_caller(void) @@ -1020,10 +585,9 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { + unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; int faulted; - unsigned long return_hooker = (unsigned long) - &return_to_handler; /* * When resuming from suspend-to-ram, this function can be indirectly diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c1a8b9e71408..9c4498ea0b3c 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -16,15 +16,7 @@ #include <asm/alternative.h> #include <asm/text-patching.h> -union jump_code_union { - char code[JUMP_LABEL_NOP_SIZE]; - struct { - char jump; - int offset; - } __attribute__((packed)); -}; - -static void bug_at(unsigned char *ip, int line) +static void bug_at(const void *ip, int line) { /* * The location is not an op that we were expecting. @@ -35,42 +27,42 @@ static void bug_at(unsigned char *ip, int line) BUG(); } -static void __jump_label_set_jump_code(struct jump_entry *entry, - enum jump_label_type type, - union jump_code_union *code, - int init) +static const void * +__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init) { const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - const void *expect; + const void *expect, *code; + const void *addr, *dest; int line; - code->jump = 0xe9; - code->offset = jump_entry_target(entry) - - (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); + addr = (void *)jump_entry_code(entry); + dest = (void *)jump_entry_target(entry); + + code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); if (init) { expect = default_nop; line = __LINE__; } else if (type == JUMP_LABEL_JMP) { expect = ideal_nop; line = __LINE__; } else { - expect = code->code; line = __LINE__; + expect = code; line = __LINE__; } - if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE)) - bug_at((void *)jump_entry_code(entry), line); + if (memcmp(addr, expect, JUMP_LABEL_NOP_SIZE)) + bug_at(addr, line); if (type == JUMP_LABEL_NOP) - memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE); + code = ideal_nop; + + return code; } -static void __ref __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void inline __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { - union jump_code_union code; - - __jump_label_set_jump_code(entry, type, &code, init); + const void *opcode = __jump_label_set_jump_code(entry, type, init); /* * As long as only a single processor is running and the code is still @@ -84,31 +76,33 @@ static void __ref __jump_label_transform(struct jump_entry *entry, * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { - text_poke_early((void *)jump_entry_code(entry), &code, + text_poke_early((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE); return; } - text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL); + text_poke_bp((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE, NULL); } -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +static void __ref jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { mutex_lock(&text_mutex); - __jump_label_transform(entry, type, 0); + __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } -#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) -static struct text_poke_loc tp_vec[TP_VEC_MAX]; -static int tp_vec_nr; +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_transform(entry, type, 0); +} bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { - struct text_poke_loc *tp; - void *entry_code; + const void *opcode; if (system_state == SYSTEM_BOOTING) { /* @@ -118,53 +112,19 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, return true; } - /* - * No more space in the vector, tell upper layer to apply - * the queue before continuing. - */ - if (tp_vec_nr == TP_VEC_MAX) - return false; - - tp = &tp_vec[tp_vec_nr]; - - entry_code = (void *)jump_entry_code(entry); - - /* - * The INT3 handler will do a bsearch in the queue, so we need entries - * to be sorted. We can survive an unsorted list by rejecting the entry, - * forcing the generic jump_label code to apply the queue. Warning once, - * to raise the attention to the case of an unsorted entry that is - * better not happen, because, in the worst case we will perform in the - * same way as we do without batching - with some more overhead. - */ - if (tp_vec_nr > 0) { - int prev = tp_vec_nr - 1; - struct text_poke_loc *prev_tp = &tp_vec[prev]; - - if (WARN_ON_ONCE(prev_tp->addr > entry_code)) - return false; - } - - __jump_label_set_jump_code(entry, type, - (union jump_code_union *)&tp->text, 0); - - text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL); - - tp_vec_nr++; - + mutex_lock(&text_mutex); + opcode = __jump_label_set_jump_code(entry, type, 0); + text_poke_queue((void *)jump_entry_code(entry), + opcode, JUMP_LABEL_NOP_SIZE, NULL); + mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { - if (!tp_vec_nr) - return; - mutex_lock(&text_mutex); - text_poke_bp_batch(tp_vec, tp_vec_nr); + text_poke_finish(); mutex_unlock(&text_mutex); - - tp_vec_nr = 0; } static enum { @@ -193,5 +153,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, jlstate = JL_STATE_NO_UPDATE; } if (jlstate == JL_STATE_UPDATE) - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a0c223ab7264..4d7022a740ab 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -120,14 +120,14 @@ __synthesize_relative_insn(void *dest, void *from, void *to, u8 op) /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -302,7 +302,7 @@ static int can_probe(unsigned long paddr) * Another debugging subsystem might insert this breakpoint. * In that case, we can't recover it. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; addr += insn.length; } @@ -357,7 +357,7 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* Another subsystem puts a breakpoint, failed to recover */ - if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* We should not singlestep on the exception masking instructions */ @@ -401,14 +401,14 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, int len = insn->length; if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; @@ -502,12 +502,14 @@ int arch_prepare_kprobe(struct kprobe *p) void arch_arm_kprobe(struct kprobe *p) { - text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); + text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1); + text_poke_sync(); } void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); + text_poke_sync(); } void arch_remove_kprobe(struct kprobe *p) @@ -610,7 +612,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, regs->flags |= X86_EFLAGS_TF; regs->flags &= ~X86_EFLAGS_IF; /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) + if (p->opcode == INT3_INSN_OPCODE) regs->ip = (unsigned long)p->addr; else regs->ip = (unsigned long)p->ainsn.insn; @@ -696,7 +698,7 @@ int kprobe_int3_handler(struct pt_regs *regs) reset_current_kprobe(); return 1; } - } else if (*addr != BREAKPOINT_INSTRUCTION) { + } else if (*addr != INT3_INSN_OPCODE) { /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 8900329c28a7..3f45b5c43a71 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -38,7 +38,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) long offs; int i; - for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + for (i = 0; i < JMP32_INSN_SIZE; i++) { kp = get_kprobe((void *)addr - i); /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { @@ -62,10 +62,10 @@ found: if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE); } else { offs = addr - (unsigned long)kp->addr - 1; - memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs); } return (unsigned long)buf; @@ -141,8 +141,6 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_END_IDX \ ((long)optprobe_template_end - (long)optprobe_template_entry) -#define INT3_SIZE sizeof(kprobe_opcode_t) - /* Optimized kprobe call back function: called from optinsn */ static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) @@ -162,7 +160,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; regs->orig_ax = ~0UL; __this_cpu_write(current_kprobe, &op->kp); @@ -179,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) struct insn insn; int len = 0, ret; - while (len < RELATIVEJUMP_SIZE) { + while (len < JMP32_INSN_SIZE) { ret = __copy_instruction(dest + len, src + len, real + len, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; @@ -271,7 +269,7 @@ static int can_optimize(unsigned long paddr) return 0; /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) + if (size - offset < JMP32_INSN_SIZE) return 0; /* Decode instructions */ @@ -290,15 +288,15 @@ static int can_optimize(unsigned long paddr) kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); /* Check any instructions don't jump into target */ if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) + insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE, + DISP32_SIZE)) return 0; addr += insn.length; } @@ -374,7 +372,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE; if (abs(rel) > 0x7fffffff) { ret = -ERANGE; goto err; @@ -401,7 +399,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, /* Set returning jmp instruction at the tail of out-of-line buffer */ synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; /* We have to use text_poke() for instruction buffer because it is RO */ text_poke(slot, buf, len); @@ -416,49 +414,50 @@ err: } /* - * Replace breakpoints (int3) with relative jumps. + * Replace breakpoints (INT3) with relative jumps (JMP.d32). * Caller must call with locking kprobe_mutex and text_mutex. + * + * The caller will have installed a regular kprobe and after that issued + * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in + * the 4 bytes after the INT3 are unused and can now be overwritten. */ void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - u8 insn_buff[RELATIVEJUMP_SIZE]; + u8 insn_buff[JMP32_INSN_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + ((long)op->kp.addr + JMP32_INSN_SIZE)); WARN_ON(kprobe_disabled(&op->kp)); /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE, + DISP32_SIZE); - insn_buff[0] = RELATIVEJUMP_OPCODE; + insn_buff[0] = JMP32_INSN_OPCODE; *(s32 *)(&insn_buff[1]) = rel; - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL); + text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL); list_del_init(&op->list); } } -/* Replace a relative jump with a breakpoint (int3). */ +/* + * Replace a relative jump (JMP.d32) with a breakpoint (INT3). + * + * After that, we can restore the 4 bytes after the INT3 to undo what + * arch_optimize_kprobes() scribbled. This is safe since those bytes will be + * unused once the INT3 lands. + */ void arch_unoptimize_kprobe(struct optimized_kprobe *op) { - u8 insn_buff[RELATIVEJUMP_SIZE]; - u8 emulate_buff[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - insn_buff[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - emulate_buff[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, - emulate_buff); + arch_arm_kprobe(&op->kp); + text_poke(op->kp.addr + INT3_INSN_SIZE, + op->optinsn.copied_insn, DISP32_SIZE); + text_poke_sync(); } /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 05da6b5b167b..f19de6f45d48 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -572,15 +572,6 @@ NOKPROBE_SYMBOL(do_general_protection); dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * ftrace must be first, everything else may cause a recursive crash. - * See note by declaration of modifying_ftrace_code in ftrace.c - */ - if (unlikely(atomic_read(&modifying_ftrace_code)) && - ftrace_int3_handler(regs)) - return; -#endif if (poke_int3_handler(regs)) return; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8d29ae8d3eb7..23df4885bbed 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -873,34 +873,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, int kernel_set_to_readonly __read_mostly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, start+size); - - set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, start+size); - - set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); -} - static void mark_nxdata_nx(void) { /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bcfede46fe02..abbdecb75fad 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1258,42 +1258,6 @@ void __init mem_init(void) int kernel_set_to_readonly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(_etext); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, end); - - /* - * Make the kernel identity mapping for text RW. Kernel text - * mapping will always be RO. Refer to the comment in - * static_protections() in pageattr.c - */ - set_memory_rw(start, (end - start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(_etext); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, end); - - /* - * Set the kernel identity mapping for text RO. - */ - set_memory_ro(start, (end - start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); diff --git a/drivers/infiniband/hw/hfi1/trace_tid.h b/drivers/infiniband/hw/hfi1/trace_tid.h index 343fb9894a82..985ffa9cc958 100644 --- a/drivers/infiniband/hw/hfi1/trace_tid.h +++ b/drivers/infiniband/hw/hfi1/trace_tid.h @@ -138,10 +138,10 @@ TRACE_EVENT(/* put_tid */ TP_ARGS(dd, index, type, pa, order), TP_STRUCT__entry(/* entry */ DD_DEV_ENTRY(dd) - __field(unsigned long, pa); - __field(u32, index); - __field(u32, type); - __field(u16, order); + __field(unsigned long, pa) + __field(u32, index) + __field(u32, type) + __field(u16, order) ), TP_fast_assign(/* assign */ DD_DEV_ASSIGN(dd); diff --git a/drivers/infiniband/hw/hfi1/trace_tx.h b/drivers/infiniband/hw/hfi1/trace_tx.h index 09eb0c9ada00..769e5e4710c6 100644 --- a/drivers/infiniband/hw/hfi1/trace_tx.h +++ b/drivers/infiniband/hw/hfi1/trace_tx.h @@ -588,7 +588,7 @@ TRACE_EVENT(hfi1_sdma_user_reqinfo, TP_PROTO(struct hfi1_devdata *dd, u16 ctxt, u8 subctxt, u16 *i), TP_ARGS(dd, ctxt, subctxt, i), TP_STRUCT__entry( - DD_DEV_ENTRY(dd); + DD_DEV_ENTRY(dd) __field(u16, ctxt) __field(u8, subctxt) __field(u8, ver_opcode) diff --git a/drivers/lightnvm/pblk-trace.h b/drivers/lightnvm/pblk-trace.h index 9534503b69d9..47b67c6bff7a 100644 --- a/drivers/lightnvm/pblk-trace.h +++ b/drivers/lightnvm/pblk-trace.h @@ -46,7 +46,7 @@ TRACE_EVENT(pblk_chunk_reset, TP_STRUCT__entry( __string(name, name) __field(u64, ppa) - __field(int, state); + __field(int, state) ), TP_fast_assign( @@ -72,7 +72,7 @@ TRACE_EVENT(pblk_chunk_state, TP_STRUCT__entry( __string(name, name) __field(u64, ppa) - __field(int, state); + __field(int, state) ), TP_fast_assign( @@ -98,7 +98,7 @@ TRACE_EVENT(pblk_line_state, TP_STRUCT__entry( __string(name, name) __field(int, line) - __field(int, state); + __field(int, state) ), TP_fast_assign( @@ -121,7 +121,7 @@ TRACE_EVENT(pblk_state, TP_STRUCT__entry( __string(name, name) - __field(int, state); + __field(int, state) ), TP_fast_assign( diff --git a/drivers/net/fjes/fjes_trace.h b/drivers/net/fjes/fjes_trace.h index c611b6a80b20..9237b69d8e21 100644 --- a/drivers/net/fjes/fjes_trace.h +++ b/drivers/net/fjes/fjes_trace.h @@ -28,7 +28,7 @@ TRACE_EVENT(fjes_hw_issue_request_command, __field(u8, cs_busy) __field(u8, cs_complete) __field(int, timeout) - __field(int, ret); + __field(int, ret) ), TP_fast_assign( __entry->cr_req = cr->bits.req_code; diff --git a/drivers/net/wireless/ath/ath10k/trace.h b/drivers/net/wireless/ath/ath10k/trace.h index ab916459d237..842e42ec814f 100644 --- a/drivers/net/wireless/ath/ath10k/trace.h +++ b/drivers/net/wireless/ath/ath10k/trace.h @@ -239,7 +239,7 @@ TRACE_EVENT(ath10k_wmi_dbglog, TP_STRUCT__entry( __string(device, dev_name(ar->dev)) __string(driver, dev_driver_string(ar->dev)) - __field(u8, hw_type); + __field(u8, hw_type) __field(size_t, buf_len) __dynamic_array(u8, buf, buf_len) ), @@ -269,7 +269,7 @@ TRACE_EVENT(ath10k_htt_pktlog, TP_STRUCT__entry( __string(device, dev_name(ar->dev)) __string(driver, dev_driver_string(ar->dev)) - __field(u8, hw_type); + __field(u8, hw_type) __field(u16, buf_len) __dynamic_array(u8, pktlog, buf_len) ), @@ -435,7 +435,7 @@ TRACE_EVENT(ath10k_htt_rx_desc, TP_STRUCT__entry( __string(device, dev_name(ar->dev)) __string(driver, dev_driver_string(ar->dev)) - __field(u8, hw_type); + __field(u8, hw_type) __field(u16, len) __dynamic_array(u8, rxdesc, len) ), diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 3362bae28b46..096203119934 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -329,7 +329,7 @@ TRACE_EVENT(xchk_btree_op_error, __field(int, level) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, bno) - __field(int, ptr); + __field(int, ptr) __field(int, error) __field(void *, ret_ip) ), @@ -414,7 +414,7 @@ TRACE_EVENT(xchk_btree_error, __field(int, level) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, bno) - __field(int, ptr); + __field(int, ptr) __field(void *, ret_ip) ), TP_fast_assign( @@ -452,7 +452,7 @@ TRACE_EVENT(xchk_ifork_btree_error, __field(int, level) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, bno) - __field(int, ptr); + __field(int, ptr) __field(void *, ret_ip) ), TP_fast_assign( diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index a86be7f807ee..e242988f57fb 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -218,8 +218,8 @@ DECLARE_EVENT_CLASS(xfs_bmap_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) - __field(void *, leaf); - __field(int, pos); + __field(void *, leaf) + __field(int, pos) __field(xfs_fileoff_t, startoff) __field(xfs_fsblock_t, startblock) __field(xfs_filblks_t, blockcount) diff --git a/include/linux/module.h b/include/linux/module.h index bd165ba68617..0c7366c317bd 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -849,13 +849,9 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_STRICT_MODULE_RWX -extern void set_all_modules_text_rw(void); -extern void set_all_modules_text_ro(void); extern void module_enable_ro(const struct module *mod, bool after_init); extern void module_disable_ro(const struct module *mod); #else -static inline void set_all_modules_text_rw(void) { } -static inline void set_all_modules_text_ro(void) { } static inline void module_enable_ro(const struct module *mod, bool after_init) { } static inline void module_disable_ro(const struct module *mod) { } #endif diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 4c6e15605766..13ea7f7d54ac 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -192,6 +192,22 @@ enum trace_reg { struct trace_event_call; +#define TRACE_FUNCTION_TYPE ((const char *)~0UL) + +struct trace_event_fields { + const char *type; + union { + struct { + const char *name; + const int size; + const int align; + const int is_signed; + const int filter_type; + }; + int (*define_fields)(struct trace_event_call *); + }; +}; + struct trace_event_class { const char *system; void *probe; @@ -200,7 +216,7 @@ struct trace_event_class { #endif int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); - int (*define_fields)(struct trace_event_call *); + struct trace_event_fields *fields_array; struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; int (*raw_init)(struct trace_event_call *); diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h index ee05db7ee8d2..796053e162d2 100644 --- a/include/trace/events/filemap.h +++ b/include/trace/events/filemap.h @@ -85,7 +85,7 @@ TRACE_EVENT(file_check_and_advance_wb_err, TP_ARGS(file, old), TP_STRUCT__entry( - __field(struct file *, file); + __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 472b33d23a10..96d77e5e0664 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -400,22 +400,16 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) #undef __field_ext -#define __field_ext(type, item, filter_type) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = _filter_type }, #undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - 0, filter_type); \ - if (ret) \ - return ret; +#define __field_struct_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + 0, .filter_type = _filter_type }, #undef __field #define __field(type, item) __field_ext(type, item, FILTER_OTHER) @@ -424,25 +418,16 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) #undef __array -#define __array(type, item, len) \ - do { \ - char *type_str = #type"["__stringify(len)"]"; \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - BUILD_BUG_ON(len <= 0); \ - ret = trace_define_field(event_call, type_str, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), FILTER_OTHER); \ - if (ret) \ - return ret; \ - } while (0); +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __dynamic_array -#define __dynamic_array(type, item, len) \ - ret = trace_define_field(event_call, "__data_loc " #type "[]", #item, \ - offsetof(typeof(field), __data_loc_##item), \ - sizeof(field.__data_loc_##item), \ - is_signed_type(type), FILTER_OTHER); +#define __dynamic_array(_type, _item, _len) { \ + .type = "__data_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __string #define __string(item, src) __dynamic_array(char, item, -1) @@ -452,16 +437,9 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ -static int notrace __init \ -trace_event_define_fields_##call(struct trace_event_call *event_call) \ -{ \ - struct trace_event_raw_##call field; \ - int ret; \ - \ - tstruct; \ - \ - return ret; \ -} +static struct trace_event_fields trace_event_fields_##call[] = { \ + tstruct \ + {} }; #undef DEFINE_EVENT #define DEFINE_EVENT(template, name, proto, args) @@ -619,7 +597,7 @@ static inline notrace int trace_event_get_offsets_##call( \ * * static struct trace_event_class __used event_class_<template> = { * .system = "<system>", - * .define_fields = trace_event_define_fields_<call>, + * .fields_array = trace_event_fields_<call>, * .fields = LIST_HEAD_INIT(event_class_##call.fields), * .raw_init = trace_event_raw_init, * .probe = trace_event_raw_event_##call, @@ -768,7 +746,7 @@ _TRACE_PERF_PROTO(call, PARAMS(proto)); \ static char print_fmt_##call[] = print; \ static struct trace_event_class __used __refdata event_class_##call = { \ .system = TRACE_SYSTEM_STRING, \ - .define_fields = trace_event_define_fields_##call, \ + .fields_array = trace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_##call.fields),\ .raw_init = trace_event_raw_init, \ .probe = trace_event_raw_event_##call, \ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 53534aa258a6..2625c241ac00 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -510,6 +510,8 @@ static void do_unoptimize_kprobes(void) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Switching from detour code to origin */ + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -610,6 +612,18 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } +static bool optprobe_queued_unopt(struct optimized_kprobe *op) +{ + struct optimized_kprobe *_op; + + list_for_each_entry(_op, &unoptimizing_list, list) { + if (op == _op) + return true; + } + + return false; +} + /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { @@ -631,17 +645,21 @@ static void optimize_kprobe(struct kprobe *p) return; /* Check if it is already optimized. */ - if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { + if (optprobe_queued_unopt(op)) { + /* This is under unoptimizing. Just dequeue the probe */ + list_del_init(&op->list); + } return; + } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; - if (!list_empty(&op->list)) - /* This is under unoptimizing. Just dequeue the probe */ - list_del_init(&op->list); - else { - list_add(&op->list, &optimizing_list); - kick_kprobe_optimizer(); - } + /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ + if (WARN_ON_ONCE(!list_empty(&op->list))) + return; + + list_add(&op->list, &optimizing_list); + kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ @@ -649,6 +667,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -662,31 +681,33 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); - if (!kprobe_optimized(p)) { - /* Unoptimized or unoptimizing case */ - if (force && !list_empty(&op->list)) { - /* - * Only if this is unoptimizing kprobe and forced, - * forcibly unoptimize it. (No need to unoptimize - * unoptimized kprobe again :) - */ - list_del_init(&op->list); - force_unoptimize_kprobe(op); - } + if (!kprobe_optimized(p)) return; - } - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (!list_empty(&op->list)) { - /* Dequeue from the optimization queue */ - list_del_init(&op->list); + if (optprobe_queued_unopt(op)) { + /* Queued in unoptimizing queue */ + if (force) { + /* + * Forcibly unoptimize the kprobe here, and queue it + * in the freeing list for release afterwards. + */ + force_unoptimize_kprobe(op); + list_move(&op->list, &freeing_list); + } + } else { + /* Dequeue from the optimizing queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } return; } + /* Optimized kprobe case */ - if (force) + if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); - else { + } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } diff --git a/kernel/module.c b/kernel/module.c index b56f3224b161..ac058a5ad1d1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2031,49 +2031,6 @@ static void module_enable_nx(const struct module *mod) frob_writable_data(&mod->init_layout, set_memory_nx); } -/* Iterate through all modules and set each module's text as RW */ -void set_all_modules_text_rw(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - - frob_text(&mod->core_layout, set_memory_rw); - frob_text(&mod->init_layout, set_memory_rw); - } - mutex_unlock(&module_mutex); -} - -/* Iterate through all modules and set each module's text as RO */ -void set_all_modules_text_ro(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - /* - * Ignore going modules since it's possible that ro - * protection has already been disabled, otherwise we'll - * run into protection faults at module deallocation. - */ - if (mod->state == MODULE_STATE_UNFORMED || - mod->state == MODULE_STATE_GOING) - continue; - - frob_text(&mod->core_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - } - mutex_unlock(&module_mutex); -} #else /* !CONFIG_STRICT_MODULE_RWX */ static void module_enable_nx(const struct module *mod) { } #endif /* CONFIG_STRICT_MODULE_RWX */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 63bf60f79398..a98dce1b3334 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -52,6 +52,9 @@ enum trace_type { #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_struct #define __field_struct(type, item) __field(type, item) @@ -71,26 +74,22 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct struct_name { \ struct trace_entry ent; \ tstruct \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ - filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) __packed +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed #include "trace_entries.h" @@ -1917,17 +1916,15 @@ extern void tracing_log_err(struct trace_array *tr, #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct trace_event_call \ __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index fc8e97328e54..3e9d81608284 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -61,15 +61,13 @@ FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, F_STRUCT( - __field( unsigned long, ip ) - __field( unsigned long, parent_ip ) + __field_fn( unsigned long, ip ) + __field_fn( unsigned long, parent_ip ) ), F_printk(" %ps <-- %ps", (void *)__entry->ip, (void *)__entry->parent_ip), - FILTER_TRACE_FN, - perf_ftrace_event_register ); @@ -84,9 +82,7 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth), - - FILTER_OTHER + F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth) ); /* Function return entry */ @@ -97,18 +93,16 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long, ret, overrun ) __field_desc( unsigned long long, ret, calltime) __field_desc( unsigned long long, ret, rettime ) - __field_desc( unsigned long, ret, overrun ) __field_desc( int, ret, depth ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", (void *)__entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth), - - FILTER_OTHER + __entry->depth) ); /* @@ -137,9 +131,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -157,9 +149,7 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -183,9 +173,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -203,9 +191,7 @@ FTRACE_ENTRY(user_stack, userstack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); /* @@ -222,9 +208,7 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->fmt), - - FILTER_OTHER + (void *)__entry->ip, __entry->fmt) ); FTRACE_ENTRY_REG(print, print_entry, @@ -239,8 +223,6 @@ FTRACE_ENTRY_REG(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER, - ftrace_event_register ); @@ -254,9 +236,7 @@ FTRACE_ENTRY(raw_data, raw_data_entry, ), F_printk("id:%04x %08x", - __entry->id, (int)__entry->buf[0]), - - FILTER_OTHER + __entry->id, (int)__entry->buf[0]) ); FTRACE_ENTRY(bputs, bputs_entry, @@ -269,9 +249,7 @@ FTRACE_ENTRY(bputs, bputs_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->str), - - FILTER_OTHER + (void *)__entry->ip, __entry->str) ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -283,16 +261,14 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, __field_desc( resource_size_t, rw, phys ) __field_desc( unsigned long, rw, value ) __field_desc( unsigned long, rw, pc ) - __field_desc( int, rw, map_id ) + __field_desc( int, rw, map_id ) __field_desc( unsigned char, rw, opcode ) __field_desc( unsigned char, rw, width ) ), F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width), - - FILTER_OTHER + __entry->map_id, __entry->opcode, __entry->width) ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -304,15 +280,13 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __field_desc( resource_size_t, map, phys ) __field_desc( unsigned long, map, virt ) __field_desc( unsigned long, map, len ) - __field_desc( int, map, map_id ) + __field_desc( int, map, map_id ) __field_desc( unsigned char, map, opcode ) ), F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode), - - FILTER_OTHER + __entry->map_id, __entry->opcode) ); @@ -334,9 +308,7 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)%s", __entry->line, __entry->func, __entry->file, __entry->correct, - __entry->constant ? " CONSTANT" : ""), - - FILTER_OTHER + __entry->constant ? " CONSTANT" : "") ); @@ -362,7 +334,5 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __entry->duration, __entry->outer_duration, __entry->nmi_total_ts, - __entry->nmi_count), - - FILTER_OTHER + __entry->nmi_count) ); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a5b614cc3887..c8622a44d300 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -24,6 +24,7 @@ #include <linux/delay.h> #include <trace/events/sched.h> +#include <trace/syscall.h> #include <asm/setup.h> @@ -2017,7 +2018,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) */ head = trace_get_fields(call); if (list_empty(head)) { - ret = call->class->define_fields(call); + struct trace_event_fields *field = call->class->fields_array; + unsigned int offset = sizeof(struct trace_entry); + + for (; field->type; field++) { + if (field->type == TRACE_FUNCTION_TYPE) { + ret = field->define_fields(call); + break; + } + + offset = ALIGN(offset, field->align); + ret = trace_define_field(call, field->type, field->name, + offset, field->size, + field->is_signed, field->filter_type); + if (ret) + break; + + offset += field->size; + } if (ret < 0) { pr_warn("Could not initialize trace point events/%s\n", name); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6ac35b9e195d..f2896d13001b 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1155,6 +1155,12 @@ static struct synth_event *find_synth_event(const char *name) return NULL; } +static struct trace_event_fields synth_event_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = synth_event_define_fields }, + {} +}; + static int register_synth_event(struct synth_event *event) { struct trace_event_call *call = &event->call; @@ -1176,7 +1182,7 @@ static int register_synth_event(struct synth_event *event) INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &synth_event_funcs; - call->class->define_fields = synth_event_define_fields; + call->class->fields_array = synth_event_fields_array; ret = register_trace_event(&call->event); if (!ret) { diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 2e6d2e9741cc..77ce5a3b6773 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -29,10 +29,8 @@ static int ftrace_event_register(struct trace_event_call *call, * function and thus become accesible via perf. */ #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) /* not needed for this file */ #undef __field_struct @@ -41,6 +39,9 @@ static int ftrace_event_register(struct trace_event_call *call, #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_desc #define __field_desc(type, container, item) type item; @@ -60,7 +61,7 @@ static int ftrace_event_register(struct trace_event_call *call, #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct ____ftrace_##name { \ tstruct \ }; \ @@ -73,76 +74,46 @@ static void __always_unused ____ftrace_check_##name(void) \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = _filter_type }, + #undef __field -#define __field(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER) + +#undef __field_fn +#define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) #undef __field_desc -#define __field_desc(type, container, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __array -#define __array(type, item, len) \ - do { \ - char *type_str = #type"["__stringify(len)"]"; \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, type_str, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; \ - } while (0); +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __array_desc -#define __array_desc(type, container, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) #undef __dynamic_array -#define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type "[]", #item, \ - offsetof(typeof(field), item), \ - 0, is_signed_type(type), filter_type);\ - if (ret) \ - return ret; +#define __dynamic_array(_type, _item) { \ + .type = #_type "[]", .name = #_item, \ + .size = 0, .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ -static int __init \ -ftrace_define_fields_##name(struct trace_event_call *event_call) \ -{ \ - struct struct_name field; \ - int ret; \ - int filter_type = filter; \ - \ - tstruct; \ - \ - return ret; \ -} +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +static struct trace_event_fields ftrace_event_fields_##name[] = { \ + tstruct \ + {} }; #include "trace_entries.h" @@ -152,6 +123,9 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #undef __field #define __field(type, item) +#undef __field_fn +#define __field_fn(type, item) + #undef __field_desc #define __field_desc(type, container, item) @@ -168,12 +142,10 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ - regfn) \ - \ +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \ static struct trace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ - .define_fields = ftrace_define_fields_##call, \ + .fields_array = ftrace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ .reg = regfn, \ }; \ @@ -191,9 +163,9 @@ static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ - PARAMS(tstruct), PARAMS(print), filter, NULL) + PARAMS(tstruct), PARAMS(print), NULL) bool ftrace_event_is_function(struct trace_event_call *call) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 3f54dc2f6e1c..aa515d578c5b 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1555,16 +1555,28 @@ static struct trace_event_functions kprobe_funcs = { .trace = print_kprobe_event }; +static struct trace_event_fields kretprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kretprobe_event_define_fields }, + {} +}; + +static struct trace_event_fields kprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_kprobe *tk) { struct trace_event_call *call = trace_probe_event_call(&tk->tp); if (trace_kprobe_is_return(tk)) { call->event.funcs = &kretprobe_funcs; - call->class->define_fields = kretprobe_event_define_fields; + call->class->fields_array = kretprobe_fields_array; } else { call->event.funcs = &kprobe_funcs; - call->class->define_fields = kprobe_event_define_fields; + call->class->fields_array = kprobe_fields_array; } call->flags = TRACE_EVENT_FL_KPROBE; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 16fa218556fa..2978c29d87d4 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -203,11 +203,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, field, name) \ - sizeof(type) != sizeof(trace.field) ? \ - __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), field), \ - sizeof(trace.field), is_signed_type(type) +#define SYSCALL_FIELD(_type, _name) { \ + .type = #_type, .name = #_name, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER } static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -274,42 +273,23 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; - int ret; - int i; int offset = offsetof(typeof(trace), args); - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; + int ret = 0; + int i; for (i = 0; i < meta->nb_args; i++) { ret = trace_define_field(call, meta->types[i], meta->args[i], offset, sizeof(unsigned long), 0, FILTER_OTHER); + if (ret) + break; offset += sizeof(unsigned long); } return ret; } -static int __init syscall_exit_define_fields(struct trace_event_call *call) -{ - struct syscall_trace_exit trace; - int ret; - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; - - ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), - FILTER_OTHER); - - return ret; -} - static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { struct trace_array *tr = data; @@ -507,6 +487,13 @@ static int __init init_syscall_trace(struct trace_event_call *call) return id; } +static struct trace_event_fields __refdata syscall_enter_fields_array[] = { + SYSCALL_FIELD(int, __syscall_nr), + { .type = TRACE_FUNCTION_TYPE, + .define_fields = syscall_enter_define_fields }, + {} +}; + struct trace_event_functions enter_syscall_print_funcs = { .trace = print_syscall_enter, }; @@ -518,7 +505,7 @@ struct trace_event_functions exit_syscall_print_funcs = { struct trace_event_class __refdata event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, + .fields_array = syscall_enter_fields_array, .get_fields = syscall_get_enter_fields, .raw_init = init_syscall_trace, }; @@ -526,7 +513,11 @@ struct trace_event_class __refdata event_class_syscall_enter = { struct trace_event_class __refdata event_class_syscall_exit = { .system = "syscalls", .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, + .fields_array = (struct trace_event_fields[]){ + SYSCALL_FIELD(int, __syscall_nr), + SYSCALL_FIELD(long, ret), + {} + }, .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), .raw_init = init_syscall_trace, }; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 2619bc5ed520..7885ebd23d0c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1528,12 +1528,17 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; +static struct trace_event_fields uprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = uprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); - call->event.funcs = &uprobe_funcs; - call->class->define_fields = uprobe_event_define_fields; + call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 4768322dc202..427f51a0a994 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -408,20 +408,20 @@ TRACE_EVENT(drv_bss_info_changed, __field(u32, basic_rates) __array(int, mcast_rate, NUM_NL80211_BANDS) __field(u16, ht_operation_mode) - __field(s32, cqm_rssi_thold); - __field(s32, cqm_rssi_hyst); - __field(u32, channel_width); - __field(u32, channel_cfreq1); + __field(s32, cqm_rssi_thold) + __field(s32, cqm_rssi_hyst) + __field(u32, channel_width) + __field(u32, channel_cfreq1) __dynamic_array(u32, arp_addr_list, info->arp_addr_cnt > IEEE80211_BSS_ARP_ADDR_LIST_LEN ? IEEE80211_BSS_ARP_ADDR_LIST_LEN : - info->arp_addr_cnt); - __field(int, arp_addr_cnt); - __field(bool, qos); - __field(bool, idle); - __field(bool, ps); - __dynamic_array(u8, ssid, info->ssid_len); - __field(bool, hidden_ssid); + info->arp_addr_cnt) + __field(int, arp_addr_cnt) + __field(bool, qos) + __field(bool, idle) + __field(bool, ps) + __dynamic_array(u8, ssid, info->ssid_len) + __field(bool, hidden_ssid) __field(int, txpower) __field(u8, p2p_oppps_ctwindow) ), @@ -1672,8 +1672,8 @@ TRACE_EVENT(drv_start_ap, VIF_ENTRY __field(u8, dtimper) __field(u16, bcnint) - __dynamic_array(u8, ssid, info->ssid_len); - __field(bool, hidden_ssid); + __dynamic_array(u8, ssid, info->ssid_len) + __field(bool, hidden_ssid) ), TP_fast_assign( @@ -1739,7 +1739,7 @@ TRACE_EVENT(drv_join_ibss, VIF_ENTRY __field(u8, dtimper) __field(u16, bcnint) - __dynamic_array(u8, ssid, info->ssid_len); + __dynamic_array(u8, ssid, info->ssid_len) ), TP_fast_assign( diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 8677d7ab7d69..3ef1679b0e66 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2014,7 +2014,7 @@ TRACE_EVENT(rdev_start_nan, WIPHY_ENTRY WDEV_ENTRY __field(u8, master_pref) - __field(u8, bands); + __field(u8, bands) ), TP_fast_assign( WIPHY_ASSIGN; @@ -2036,8 +2036,8 @@ TRACE_EVENT(rdev_nan_change_conf, WIPHY_ENTRY WDEV_ENTRY __field(u8, master_pref) - __field(u8, bands); - __field(u32, changes); + __field(u8, bands) + __field(u32, changes) ), TP_fast_assign( WIPHY_ASSIGN; diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index f30a89046aa3..7ac0d8088565 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto $(OUTPUT)test-gtk2.bin: - $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) + $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) -Wno-deprecated-declarations $(OUTPUT)test-gtk2-infobar.bin: $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp index a2b3f092d2f0..7d87075cd1c5 100644 --- a/tools/build/feature/test-clang.cpp +++ b/tools/build/feature/test-clang.cpp @@ -1,9 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#include "clang/Basic/Version.h" +#if CLANG_VERSION_MAJOR < 8 #include "clang/Basic/VirtualFileSystem.h" +#endif #include "clang/Driver/Driver.h" #include "clang/Frontend/TextDiagnosticPrinter.h" #include "llvm/ADT/IntrusiveRefCntPtr.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 8 +#include "llvm/Support/VirtualFileSystem.h" +#endif #include "llvm/Support/raw_ostream.h" using namespace clang; diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 05dca5c203f3..477a1cae513f 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -15,6 +15,8 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits); void bitmap_clear(unsigned long *map, unsigned int start, int len); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) @@ -124,6 +126,15 @@ static inline unsigned long *bitmap_alloc(int nbits) } /* + * bitmap_free - Free bitmap + * @bitmap: pointer to bitmap + */ +static inline void bitmap_free(unsigned long *bitmap) +{ + free(bitmap); +} + +/* * bitmap_scnprintf - print bitmap list into buffer * @bitmap: bitmap * @nbits: size of bitmap @@ -148,4 +159,23 @@ static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, return __bitmap_and(dst, src1, src2, nbits); } +#ifdef __LITTLE_ENDIAN +#define BITMAP_MEM_ALIGNMENT 8 +#else +#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) +#endif +#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +static inline int bitmap_equal(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); + if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) + return !memcmp(src1, src2, nbits / 8); + return __bitmap_equal(src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index 980cb9266718..5e9e781905ed 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -17,7 +17,15 @@ int strtobool(const char *s, bool *res); * However uClibc headers also define __GLIBC__ hence the hack below */ #if defined(__GLIBC__) && !defined(__UCLIBC__) +// pragma diagnostic was introduced in gcc 4.6 +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wredundant-decls" +#endif extern size_t strlcpy(char *dest, const char *src, size_t size); +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC diagnostic pop +#endif #endif char *str_error_r(int errnum, char *buf, size_t buflen); diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 11b3885e833e..027b18f7ed8c 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -210,6 +210,7 @@ static bool fs__env_override(struct fs *fs) size_t name_len = strlen(fs->name); /* name + "_PATH" + '\0' */ char upper_name[name_len + 5 + 1]; + memcpy(upper_name, fs->name, name_len); mem_toupper(upper_name, name_len); strcpy(&upper_name[name_len], "_PATH"); @@ -219,7 +220,8 @@ static bool fs__env_override(struct fs *fs) return false; fs->found = true; - strncpy(fs->path, override_path, sizeof(fs->path)); + strncpy(fs->path, override_path, sizeof(fs->path) - 1); + fs->path[sizeof(fs->path) - 1] = '\0'; return true; } diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 38494782be06..5043747ef6c5 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -71,3 +71,18 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, BITMAP_LAST_WORD_MASK(bits)); return result != 0; } + +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] != bitmap2[k]) + return 0; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} diff --git a/tools/perf/lib/Build b/tools/lib/perf/Build index 2ef9a4ec6d99..2ef9a4ec6d99 100644 --- a/tools/perf/lib/Build +++ b/tools/lib/perf/Build diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile new file mode 100644 index 000000000000..972754082a85 --- /dev/null +++ b/tools/lib/perf/Documentation/Makefile @@ -0,0 +1,156 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/perf/Documentation/Makefile + +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +MAN3_TXT = libperf.txt +MAN7_TXT = libperf-counting.txt libperf-sampling.txt +MAN_EX = examples/*.c + +MAN_TXT = $(MAN3_TXT) $(MAN7_TXT) + +_MAN_XML = $(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML = $(patsubst %.txt,%.html,$(MAN_TXT)) +_MAN_3 = $(patsubst %.txt,%.3,$(MAN3_TXT)) +_MAN_7 = $(patsubst %.txt,%.7,$(MAN7_TXT)) + +MAN_XML = $(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML = $(addprefix $(OUTPUT),$(_MAN_HTML)) +MAN_3 = $(addprefix $(OUTPUT),$(_MAN_3)) +MAN_7 = $(addprefix $(OUTPUT),$(_MAN_7)) +MAN_X = $(MAN_3) $(MAN_7) + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR + prefix ?=$(HOME) +endif + +mandir ?= $(prefix)/share/man +man3dir = $(mandir)/man3 +man7dir = $(mandir)/man7 + +docdir ?= $(prefix)/share/doc/libperf +htmldir = $(docdir)/html +exdir = $(docdir)/examples + +ASCIIDOC = asciidoc +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 +MANPAGE_XSL = manpage-normal.xsl +XMLTO_EXTRA = +XMLTO =xmlto + +INSTALL ?= install +RM ?= rm -f + +# For asciidoc ... +# -7.1.2, no extra settings are needed. +# 8.0-, set ASCIIDOC8. +# + +# For docbook-xsl ... +# -1.68.1, set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0) +# 1.69.0, no extra settings are needed? +# 1.69.1-1.71.0, set DOCBOOK_SUPPRESS_SP? +# 1.71.1, no extra settings are needed? +# 1.72.0, set DOCBOOK_XSL_172. +# 1.73.0-, set ASCIIDOC_NO_ROFF + +# If you had been using DOCBOOK_XSL_172 in an attempt to get rid +# of 'the ".ft C" problem' in your generated manpages, and you +# instead ended up with weird characters around callouts, try +# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8). + +ifdef ASCIIDOC8 + ASCIIDOC_EXTRA += -a asciidoc7compatible +endif +ifdef DOCBOOK_XSL_172 + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + MANPAGE_XSL = manpage-1.72.xsl +else + ifdef ASCIIDOC_NO_ROFF + # docbook-xsl after 1.72 needs the regular XSL, but will not + # pass-thru raw roff codes from asciidoc.conf, so turn them off. + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + endif +endif +ifdef MAN_BOLD_LITERAL + XMLTO_EXTRA += -m manpage-bold-literal.xsl +endif +ifdef DOCBOOK_SUPPRESS_SP + XMLTO_EXTRA += -m manpage-suppress-sp.xsl +endif + +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +export DESTDIR DESTDIR_SQ + +# Please note that there is a minor bug in asciidoc. +# The version after 6.0.3 _will_ include the patch found here: +# http://marc.theaimsgroup.com/?l=libtraceevent&m=111558757202243&w=2 +# +# Until that version is released you may have to apply the patch +# yourself - yes, all 6 characters of it! + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) + PRINT_DIR = --no-print-directory +else # "make -w" + NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) + ifneq ($(V),1) + QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + endif +endif + +all: $(MAN_X) $(MAN_HTML) + +$(MAN_HTML) $(MAN_X): asciidoc.conf + +install-man: all + $(call QUIET_INSTALL, man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \ + $(INSTALL) -m 644 $(MAN_3) $(DESTDIR)$(man3dir); \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \ + $(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir); + +install-html: + $(call QUIET_INSTALL, html) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \ + $(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \ + +install-examples: + $(call QUIET_INSTALL, examples) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(exdir); \ + $(INSTALL) -m 644 $(MAN_EX) $(DESTDIR)$(exdir); \ + +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(MAN_X) + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) + +$(MAN_3): $(OUTPUT)%.3: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_7): $(OUTPUT)%.7: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_XML): $(OUTPUT)%.xml: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b docbook -d manpage \ + $(ASCIIDOC_EXTRA) -alibperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ + +$(MAN_HTML): $(OUTPUT)%.html: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ diff --git a/tools/lib/perf/Documentation/asciidoc.conf b/tools/lib/perf/Documentation/asciidoc.conf new file mode 100644 index 000000000000..9d5a5a5ee091 --- /dev/null +++ b/tools/lib/perf/Documentation/asciidoc.conf @@ -0,0 +1,120 @@ +## linktep: macro +# +# Usage: linktep:command[manpage-section] +# +# Note, {0} is the manpage section, while {target} is the command. +# +# Show TEP link as: <command>(<section>); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?P<name>linktep):(?P<target>\S*?)\[(?P<attrlist>.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linktep-inlinemacro] +{0%{target}} +{0#<citerefentry>} +{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>} +{0#</citerefentry>} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::tep-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +<example><title>{title}</title> +<literallayout> +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] +</literallayout> +{title#}</example> +endif::tep-asciidoc-no-roff[] + +ifdef::tep-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout><simpara></simpara> +{title#}</example> + +[verseblock] +<formalpara{id? id="{id}"}><title>{title}</title><para> +{title%}<literallayout{id? id="{id}"}> +{title#}<literallayout> +| +</literallayout> +{title#}</para></formalpara> +{title%}<simpara></simpara> +endif::doctype-manpage[] +endif::tep-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] +<refentry> +<refmeta> +<refentrytitle>{mantitle}</refentrytitle> +<manvolnum>{manvolnum}</manvolnum> +<refmiscinfo class="source">libperf</refmiscinfo> +<refmiscinfo class="version">{libperf_version}</refmiscinfo> +<refmiscinfo class="manual">libperf Manual</refmiscinfo> +</refmeta> +<refnamediv> + <refname>{manname1}</refname> + <refname>{manname2}</refname> + <refname>{manname3}</refname> + <refname>{manname4}</refname> + <refname>{manname5}</refname> + <refname>{manname6}</refname> + <refname>{manname7}</refname> + <refname>{manname8}</refname> + <refname>{manname9}</refname> + <refname>{manname10}</refname> + <refname>{manname11}</refname> + <refname>{manname12}</refname> + <refname>{manname13}</refname> + <refname>{manname14}</refname> + <refname>{manname15}</refname> + <refname>{manname16}</refname> + <refname>{manname17}</refname> + <refname>{manname18}</refname> + <refname>{manname19}</refname> + <refname>{manname20}</refname> + <refname>{manname21}</refname> + <refname>{manname22}</refname> + <refname>{manname23}</refname> + <refname>{manname24}</refname> + <refname>{manname25}</refname> + <refname>{manname26}</refname> + <refname>{manname27}</refname> + <refname>{manname28}</refname> + <refname>{manname29}</refname> + <refname>{manname30}</refname> + <refpurpose>{manpurpose}</refpurpose> +</refnamediv> +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linktep-inlinemacro] +<a href="{target}.html">{target}{0?({0})}</a> +endif::backend-xhtml11[] diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c new file mode 100644 index 000000000000..8e1a926a9cfe --- /dev/null +++ b/tools/lib/perf/Documentation/examples/sampling.c @@ -0,0 +1,119 @@ +#include <linux/perf_event.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/mmap.h> +#include <perf/core.h> +#include <perf/event.h> +#include <stdio.h> +#include <unistd.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +union u64_swap { + __u64 val64; + __u32 val32[2]; +}; + +int main(int argc, char **argv) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_mmap *map; + struct perf_cpu_map *cpus; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .disabled = 1, + .freq = 1, + .sample_freq = 10, + .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + }; + int err = -1; + union perf_event *event; + + libperf_init(libperf_print); + + cpus = perf_cpu_map__new(NULL); + if (!cpus) { + fprintf(stderr, "failed to create cpus\n"); + return -1; + } + + evlist = perf_evlist__new(); + if (!evlist) { + fprintf(stderr, "failed to create evlist\n"); + goto out_cpus; + } + + evsel = perf_evsel__new(&attr); + if (!evsel) { + fprintf(stderr, "failed to create cycles\n"); + goto out_cpus; + } + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + if (err) { + fprintf(stderr, "failed to open evlist\n"); + goto out_evlist; + } + + err = perf_evlist__mmap(evlist, 4); + if (err) { + fprintf(stderr, "failed to mmap evlist\n"); + goto out_evlist; + } + + perf_evlist__enable(evlist); + sleep(3); + perf_evlist__disable(evlist); + + perf_evlist__for_each_mmap(evlist, map, false) { + if (perf_mmap__read_init(map) < 0) + continue; + + while ((event = perf_mmap__read_event(map)) != NULL) { + int cpu, pid, tid; + __u64 ip, period, *array; + union u64_swap u; + + array = event->sample.array; + + ip = *array; + array++; + + u.val64 = *array; + pid = u.val32[0]; + tid = u.val32[1]; + array++; + + u.val64 = *array; + cpu = u.val32[0]; + array++; + + period = *array; + + fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", + cpu, pid, tid, ip, period); + + perf_mmap__consume(map); + } + + perf_mmap__read_done(map); + } + +out_evlist: + perf_evlist__delete(evlist); +out_cpus: + perf_cpu_map__put(cpus); + return err; +} diff --git a/tools/lib/perf/Documentation/libperf-counting.txt b/tools/lib/perf/Documentation/libperf-counting.txt new file mode 100644 index 000000000000..cae9757f49c1 --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-counting.txt @@ -0,0 +1,211 @@ +libperf-counting(7) +=================== + +NAME +---- +libperf-counting - counting interface + +DESCRIPTION +----------- +The counting interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `counting.c` example. + +It is by no means complete guide to counting, but shows libperf basic API for counting. + +The `counting.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o counting counting.c -lperf +$ sudo ./counting +count 176792, enabled 176944, run 176944 +count 176242, enabled 176242, run 176242 +-- + +It requires root access, because of the `PERF_COUNT_SW_CPU_CLOCK` event, +which is available only for root. + +The `counting.c` example monitors two events on the current process and displays their count, in a nutshel it: + +* creates events +* adds them to the event list +* opens and enables events through the event list +* does some workload +* disables events +* reads and displays event counts +* destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 8 static int libperf_print(enum libperf_print_level level, + 9 const char *fmt, va_list ap) + 10 { + 11 return vfprintf(stderr, fmt, ap); + 12 } + + 14 int main(int argc, char **argv) + 15 { + ... + 35 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining specific events using the `struct perf_event_attr`. + +We create software events for cpu and task: + +[source,c] +-- + 20 struct perf_event_attr attr1 = { + 21 .type = PERF_TYPE_SOFTWARE, + 22 .config = PERF_COUNT_SW_CPU_CLOCK, + 23 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 24 .disabled = 1, + 25 }; + 26 struct perf_event_attr attr2 = { + 27 .type = PERF_TYPE_SOFTWARE, + 28 .config = PERF_COUNT_SW_TASK_CLOCK, + 29 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 30 .disabled = 1, + 31 }; +-- + +The `read_format` setup tells perf to include timing details together with each count. + +Next step is to prepare threads map. + +In this case we will monitor current process, so we create threads map with single pid (0): + +[source,c] +-- + 37 threads = perf_thread_map__new_dummy(); + 38 if (!threads) { + 39 fprintf(stderr, "failed to create threads\n"); + 40 return -1; + 41 } + 42 + 43 perf_thread_map__set_pid(threads, 0, 0); +-- + +Now we create libperf's event list, which will serve as holder for the events we want: + +[source,c] +-- + 45 evlist = perf_evlist__new(); + 46 if (!evlist) { + 47 fprintf(stderr, "failed to create evlist\n"); + 48 goto out_threads; + 49 } +-- + +We create libperf's events for the attributes we defined earlier and add them to the list: + +[source,c] +-- + 51 evsel = perf_evsel__new(&attr1); + 52 if (!evsel) { + 53 fprintf(stderr, "failed to create evsel1\n"); + 54 goto out_evlist; + 55 } + 56 + 57 perf_evlist__add(evlist, evsel); + 58 + 59 evsel = perf_evsel__new(&attr2); + 60 if (!evsel) { + 61 fprintf(stderr, "failed to create evsel2\n"); + 62 goto out_evlist; + 63 } + 64 + 65 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the thread map and open events: + +[source,c] +-- + 67 perf_evlist__set_maps(evlist, NULL, threads); + 68 + 69 err = perf_evlist__open(evlist); + 70 if (err) { + 71 fprintf(stderr, "failed to open evsel\n"); + 72 goto out_evlist; + 73 } +-- + +Both events are created as disabled (note the `disabled = 1` assignment above), +so we need to enable the whole list explicitely (both events). + +From this moment events are counting and we can do our workload. + +When we are done we disable the events list. + +[source,c] +-- + 75 perf_evlist__enable(evlist); + 76 + 77 while (count--); + 78 + 79 perf_evlist__disable(evlist); +-- + +Now we need to get the counts from events, following code iterates throught the events list and read counts: + +[source,c] +-- + 81 perf_evlist__for_each_evsel(evlist, evsel) { + 82 perf_evsel__read(evsel, 0, 0, &counts); + 83 fprintf(stdout, "count %llu, enabled %llu, run %llu\n", + 84 counts.val, counts.ena, counts.run); + 85 } +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- + 87 perf_evlist__close(evlist); + 88 + 89 out_evlist: + 90 perf_evlist__delete(evlist); + 91 out_threads: + 92 perf_thread_map__put(threads); + 93 return err; + 94 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-sampling(7) diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt new file mode 100644 index 000000000000..d71a7b4fcf5f --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-sampling.txt @@ -0,0 +1,243 @@ +libperf-sampling(7) +=================== + +NAME +---- +libperf-sampling - sampling interface + + +DESCRIPTION +----------- +The sampling interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `sampling.c` example. + +It is by no means complete guide to sampling, but shows libperf basic API for sampling. + +The `sampling.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o sampling sampling.c -lperf +$ sudo ./sampling +cpu 0, pid 0, tid 0, ip ffffffffad06c4e6, period 1 +cpu 0, pid 4465, tid 4469, ip ffffffffad118748, period 18322959 +cpu 0, pid 0, tid 0, ip ffffffffad115722, period 33544846 +cpu 0, pid 4465, tid 4470, ip 7f84fe0cdad6, period 23687474 +cpu 0, pid 0, tid 0, ip ffffffffad9e0349, period 34255790 +cpu 0, pid 4465, tid 4469, ip ffffffffad136581, period 38664069 +cpu 0, pid 0, tid 0, ip ffffffffad9e55e2, period 21922384 +cpu 0, pid 4465, tid 4470, ip 7f84fe0ebebf, period 17655175 +... +-- + +It requires root access, because it uses hardware cycles event. + +The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a nutshel it: + +- creates events +- adds them to the event list +- opens and enables events through the event list +- sleeps for 3 seconds +- disables events +- reads and displays recorded samples +- destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 12 static int libperf_print(enum libperf_print_level level, + 13 const char *fmt, va_list ap) + 14 { + 15 return vfprintf(stderr, fmt, ap); + 16 } + + 23 int main(int argc, char **argv) + 24 { + ... + 40 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining cycles event using the `struct perf_event_attr`: + +[source,c] +-- + 29 struct perf_event_attr attr = { + 30 .type = PERF_TYPE_HARDWARE, + 31 .config = PERF_COUNT_HW_CPU_CYCLES, + 32 .disabled = 1, + 33 .freq = 1, + 34 .sample_freq = 10, + 35 .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + 36 }; +-- + +Next step is to prepare cpus map. + +In this case we will monitor all the available CPUs: + +[source,c] +-- + 42 cpus = perf_cpu_map__new(NULL); + 43 if (!cpus) { + 44 fprintf(stderr, "failed to create cpus\n"); + 45 return -1; + 46 } +-- + +Now we create libperf's event list, which will serve as holder for the cycles event: + +[source,c] +-- + 48 evlist = perf_evlist__new(); + 49 if (!evlist) { + 50 fprintf(stderr, "failed to create evlist\n"); + 51 goto out_cpus; + 52 } +-- + +We create libperf's event for the cycles attribute we defined earlier and add it to the list: + +[source,c] +-- + 54 evsel = perf_evsel__new(&attr); + 55 if (!evsel) { + 56 fprintf(stderr, "failed to create cycles\n"); + 57 goto out_cpus; + 58 } + 59 + 60 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the cpus map and open event: + +[source,c] +-- + 62 perf_evlist__set_maps(evlist, cpus, NULL); + 63 + 64 err = perf_evlist__open(evlist); + 65 if (err) { + 66 fprintf(stderr, "failed to open evlist\n"); + 67 goto out_evlist; + 68 } +-- + +Once the events list is open, we can create memory maps AKA perf ring buffers: + +[source,c] +-- + 70 err = perf_evlist__mmap(evlist, 4); + 71 if (err) { + 72 fprintf(stderr, "failed to mmap evlist\n"); + 73 goto out_evlist; + 74 } +-- + +The event is created as disabled (note the `disabled = 1` assignment above), +so we need to enable the events list explicitely. + +From this moment the cycles event is sampling. + +We will sleep for 3 seconds while the ring buffers get data from all CPUs, then we disable the events list. + +[source,c] +-- + 76 perf_evlist__enable(evlist); + 77 sleep(3); + 78 perf_evlist__disable(evlist); +-- + +Following code walks through the ring buffers and reads stored events/samples: + +[source,c] +-- + 80 perf_evlist__for_each_mmap(evlist, map, false) { + 81 if (perf_mmap__read_init(map) < 0) + 82 continue; + 83 + 84 while ((event = perf_mmap__read_event(map)) != NULL) { + + /* process event */ + +108 perf_mmap__consume(map); +109 } +110 perf_mmap__read_done(map); +111 } + +-- + +Each sample needs to get parsed: + +[source,c] +-- + 85 int cpu, pid, tid; + 86 __u64 ip, period, *array; + 87 union u64_swap u; + 88 + 89 array = event->sample.array; + 90 + 91 ip = *array; + 92 array++; + 93 + 94 u.val64 = *array; + 95 pid = u.val32[0]; + 96 tid = u.val32[1]; + 97 array++; + 98 + 99 u.val64 = *array; +100 cpu = u.val32[0]; +101 array++; +102 +103 period = *array; +104 +105 fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", +106 cpu, pid, tid, ip, period); +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- +113 out_evlist: +114 perf_evlist__delete(evlist); +115 out_cpus: +116 perf_cpu_map__put(cpus); +117 return err; +118 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt new file mode 100644 index 000000000000..5a6bb512789d --- /dev/null +++ b/tools/lib/perf/Documentation/libperf.txt @@ -0,0 +1,246 @@ +libperf(3) +========== + +NAME +---- +libperf - Linux kernel perf event library + + +SYNOPSIS +-------- +*Generic API:* + +[source,c] +-- + #include <perf/core.h> + + enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, + }; + + typedef int (*libperf_print_fn_t)(enum libperf_print_level level, + const char *, va_list ap); + + void libperf_init(libperf_print_fn_t fn); +-- + +*API to handle cpu maps:* + +[source,c] +-- + #include <perf/cpumap.h> + + struct perf_cpu_map; + + struct perf_cpu_map *perf_cpu_map__dummy_new(void); + struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); + struct perf_cpu_map *perf_cpu_map__read(FILE *file); + struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); + struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); + void perf_cpu_map__put(struct perf_cpu_map *map); + int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); + int perf_cpu_map__nr(const struct perf_cpu_map *cpus); + bool perf_cpu_map__empty(const struct perf_cpu_map *map); + int perf_cpu_map__max(struct perf_cpu_map *map); + + #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) +-- + +*API to handle thread maps:* + +[source,c] +-- + #include <perf/threadmap.h> + + struct perf_thread_map; + + struct perf_thread_map *perf_thread_map__new_dummy(void); + + void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); + char *perf_thread_map__comm(struct perf_thread_map *map, int thread); + int perf_thread_map__nr(struct perf_thread_map *threads); + pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + + struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); + void perf_thread_map__put(struct perf_thread_map *map); +-- + +*API to handle event lists:* + +[source,c] +-- + #include <perf/evlist.h> + + struct perf_evlist; + + void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel); + void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel); + struct perf_evlist *perf_evlist__new(void); + void perf_evlist__delete(struct perf_evlist *evlist); + struct perf_evsel* perf_evlist__next(struct perf_evlist *evlist, + struct perf_evsel *evsel); + int perf_evlist__open(struct perf_evlist *evlist); + void perf_evlist__close(struct perf_evlist *evlist); + void perf_evlist__enable(struct perf_evlist *evlist); + void perf_evlist__disable(struct perf_evlist *evlist); + + #define perf_evlist__for_each_evsel(evlist, pos) + + void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + int perf_evlist__poll(struct perf_evlist *evlist, int timeout); + int perf_evlist__filter_pollfd(struct perf_evlist *evlist, + short revents_and_mask); + + int perf_evlist__mmap(struct perf_evlist *evlist, int pages); + void perf_evlist__munmap(struct perf_evlist *evlist); + + struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, + struct perf_mmap *map, + bool overwrite); + + #define perf_evlist__for_each_mmap(evlist, pos, overwrite) +-- + +*API to handle events:* + +[source,c] +-- + #include <perf/evsel.h>* + + struct perf_evsel; + + struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; + }; + + struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr); + void perf_evsel__delete(struct perf_evsel *evsel); + int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + void perf_evsel__close(struct perf_evsel *evsel); + void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); + int perf_evsel__enable(struct perf_evsel *evsel); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__disable(struct perf_evsel *evsel); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); + struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); + struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); + struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +-- + +*API to handle maps (perf ring buffers):* + +[source,c] +-- + #include <perf/mmap.h> + + struct perf_mmap; + + void perf_mmap__consume(struct perf_mmap *map); + int perf_mmap__read_init(struct perf_mmap *map); + void perf_mmap__read_done(struct perf_mmap *map); + union perf_event *perf_mmap__read_event(struct perf_mmap *map); +-- + +*Structures to access perf API events:* + +[source,c] +-- + #include <perf/event.h> + + struct perf_record_mmap; + struct perf_record_mmap2; + struct perf_record_comm; + struct perf_record_namespaces; + struct perf_record_fork; + struct perf_record_lost; + struct perf_record_lost_samples; + struct perf_record_read; + struct perf_record_throttle; + struct perf_record_ksymbol; + struct perf_record_bpf_event; + struct perf_record_sample; + struct perf_record_switch; + struct perf_record_header_attr; + struct perf_record_record_cpu_map; + struct perf_record_cpu_map_data; + struct perf_record_cpu_map; + struct perf_record_event_update_cpus; + struct perf_record_event_update_scale; + struct perf_record_event_update; + struct perf_trace_event_type; + struct perf_record_header_event_type; + struct perf_record_header_tracing_data; + struct perf_record_header_build_id; + struct perf_record_id_index; + struct perf_record_auxtrace_info; + struct perf_record_auxtrace; + struct perf_record_auxtrace_error; + struct perf_record_aux; + struct perf_record_itrace_start; + struct perf_record_thread_map_entry; + struct perf_record_thread_map; + struct perf_record_stat_config_entry; + struct perf_record_stat_config; + struct perf_record_stat; + struct perf_record_stat_round; + struct perf_record_time_conv; + struct perf_record_header_feature; + struct perf_record_compressed; +-- + +DESCRIPTION +----------- +The libperf library provides an API to access the linux kernel perf +events subsystem. + +Following objects are key to the libperf interface: + +[horizontal] + +struct perf_cpu_map:: Provides a cpu list abstraction. + +struct perf_thread_map:: Provides a thread list abstraction. + +struct perf_evsel:: Provides an abstraction for single a perf event. + +struct perf_evlist:: Gathers several struct perf_evsel object and performs functions on all of them. + +struct perf_mmap:: Provides an abstraction for accessing perf ring buffer. + +The exported API functions bind these objects together. + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf-sampling(7), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/manpage-1.72.xsl b/tools/lib/perf/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000000..b4d315cb8c47 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ +<!-- manpage-1.72.xsl: + special settings for manpages rendered from asciidoc+docbook + handles peculiarities in docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the special values for the roff control characters + needed for docbook-xsl 1.72.0 --> +<xsl:param name="git.docbook.backslash">▓</xsl:param> +<xsl:param name="git.docbook.dot" >⌂</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-base.xsl b/tools/lib/perf/Documentation/manpage-base.xsl new file mode 100644 index 000000000000..a264fa616093 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ +<!-- manpage-base.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- these params silence some output from xmlto --> +<xsl:param name="man.output.quietly" select="1"/> +<xsl:param name="refentry.meta.get.quietly" select="1"/> + +<!-- convert asciidoc callouts to man page format; + git.docbook.backslash and git.docbook.dot params + must be supplied by another XSL file or other means --> +<xsl:template match="co"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB(', + substring-after(@id,'-'),')', + $git.docbook.backslash,'fR')"/> +</xsl:template> +<xsl:template match="calloutlist"> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>sp </xsl:text> + <xsl:apply-templates/> + <xsl:text> </xsl:text> +</xsl:template> +<xsl:template match="callout"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB', + substring-after(@arearefs,'-'), + '. ',$git.docbook.backslash,'fR')"/> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-bold-literal.xsl b/tools/lib/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000000..608eb5df6281 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-normal.xsl b/tools/lib/perf/Documentation/manpage-normal.xsl new file mode 100644 index 000000000000..a48f5b11f3dc --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-suppress-sp.xsl b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000000..a63c7632a87d --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/perf/lib/Makefile b/tools/lib/perf/Makefile index 0f233638ef1f..3718d65cffac 100644 --- a/tools/perf/lib/Makefile +++ b/tools/lib/perf/Makefile @@ -60,7 +60,7 @@ else endif INCLUDES = \ --I$(srctree)/tools/perf/lib/include \ +-I$(srctree)/tools/lib/perf/include \ -I$(srctree)/tools/lib/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(SRCARCH)/include/ \ @@ -181,7 +181,10 @@ install_pkgconfig: $(LIBPERF_PC) $(call QUIET_INSTALL, $(LIBPERF_PC)) \ $(call do_install,$(LIBPERF_PC),$(libdir_SQ)/pkgconfig,644) -install: install_lib install_headers install_pkgconfig +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig install_doc FORCE: diff --git a/tools/perf/lib/core.c b/tools/lib/perf/core.c index 58fc894b76c5..58fc894b76c5 100644 --- a/tools/perf/lib/core.c +++ b/tools/lib/perf/core.c diff --git a/tools/perf/lib/cpumap.c b/tools/lib/perf/cpumap.c index f93f4e703e4c..f93f4e703e4c 100644 --- a/tools/perf/lib/cpumap.c +++ b/tools/lib/perf/cpumap.c diff --git a/tools/perf/lib/evlist.c b/tools/lib/perf/evlist.c index ae9e65aa2491..5b9f2ca50591 100644 --- a/tools/perf/lib/evlist.c +++ b/tools/lib/perf/evlist.c @@ -164,6 +164,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = perf_thread_map__get(threads); } + if (!evlist->all_cpus && cpus) + evlist->all_cpus = perf_cpu_map__get(cpus); + perf_evlist__propagate_maps(evlist); } diff --git a/tools/perf/lib/evsel.c b/tools/lib/perf/evsel.c index 4dc06289f4c7..4dc06289f4c7 100644 --- a/tools/perf/lib/evsel.c +++ b/tools/lib/perf/evsel.c diff --git a/tools/perf/lib/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 840d4032587b..840d4032587b 100644 --- a/tools/perf/lib/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 74dc8c3f0b66..74dc8c3f0b66 100644 --- a/tools/perf/lib/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index 1ffd083b235e..1ffd083b235e 100644 --- a/tools/perf/lib/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h diff --git a/tools/perf/lib/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h index 5175d491b2d4..5175d491b2d4 100644 --- a/tools/perf/lib/include/internal/lib.h +++ b/tools/lib/perf/include/internal/lib.h diff --git a/tools/perf/lib/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h index be7556e0a2b2..be7556e0a2b2 100644 --- a/tools/perf/lib/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h diff --git a/tools/perf/lib/include/internal/tests.h b/tools/lib/perf/include/internal/tests.h index 2093e8868a67..2093e8868a67 100644 --- a/tools/perf/lib/include/internal/tests.h +++ b/tools/lib/perf/include/internal/tests.h diff --git a/tools/perf/lib/include/internal/threadmap.h b/tools/lib/perf/include/internal/threadmap.h index df748baf9eda..df748baf9eda 100644 --- a/tools/perf/lib/include/internal/threadmap.h +++ b/tools/lib/perf/include/internal/threadmap.h diff --git a/tools/perf/lib/include/internal/xyarray.h b/tools/lib/perf/include/internal/xyarray.h index 51e35d6c8ec4..51e35d6c8ec4 100644 --- a/tools/perf/lib/include/internal/xyarray.h +++ b/tools/lib/perf/include/internal/xyarray.h diff --git a/tools/perf/lib/include/perf/core.h b/tools/lib/perf/include/perf/core.h index a3f6d68edad7..a3f6d68edad7 100644 --- a/tools/perf/lib/include/perf/core.h +++ b/tools/lib/perf/include/perf/core.h diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 6a17ad730cbc..6a17ad730cbc 100644 --- a/tools/perf/lib/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h diff --git a/tools/perf/lib/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 18106899cb4e..18106899cb4e 100644 --- a/tools/perf/lib/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h index 0a7479dc13bf..0a7479dc13bf 100644 --- a/tools/perf/lib/include/perf/evlist.h +++ b/tools/lib/perf/include/perf/evlist.h diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index c82ec39a4ad0..c82ec39a4ad0 100644 --- a/tools/perf/lib/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h diff --git a/tools/perf/lib/include/perf/mmap.h b/tools/lib/perf/include/perf/mmap.h index 9508ad90d8b9..9508ad90d8b9 100644 --- a/tools/perf/lib/include/perf/mmap.h +++ b/tools/lib/perf/include/perf/mmap.h diff --git a/tools/perf/lib/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h index a7c50de8d010..a7c50de8d010 100644 --- a/tools/perf/lib/include/perf/threadmap.h +++ b/tools/lib/perf/include/perf/threadmap.h diff --git a/tools/perf/lib/internal.h b/tools/lib/perf/internal.h index 2c27e158de6b..2c27e158de6b 100644 --- a/tools/perf/lib/internal.h +++ b/tools/lib/perf/internal.h diff --git a/tools/perf/lib/lib.c b/tools/lib/perf/lib.c index 18658931fc71..18658931fc71 100644 --- a/tools/perf/lib/lib.c +++ b/tools/lib/perf/lib.c diff --git a/tools/perf/lib/libperf.map b/tools/lib/perf/libperf.map index 7be1af8a546c..7be1af8a546c 100644 --- a/tools/perf/lib/libperf.map +++ b/tools/lib/perf/libperf.map diff --git a/tools/perf/lib/libperf.pc.template b/tools/lib/perf/libperf.pc.template index 117e4a237b55..117e4a237b55 100644 --- a/tools/perf/lib/libperf.pc.template +++ b/tools/lib/perf/libperf.pc.template diff --git a/tools/perf/lib/mmap.c b/tools/lib/perf/mmap.c index 79d5ed6c38cc..79d5ed6c38cc 100644 --- a/tools/perf/lib/mmap.c +++ b/tools/lib/perf/mmap.c diff --git a/tools/perf/lib/tests/Makefile b/tools/lib/perf/tests/Makefile index a43cd08c5c03..96841775feaf 100644 --- a/tools/perf/lib/tests/Makefile +++ b/tools/lib/perf/tests/Makefile @@ -16,7 +16,7 @@ all: include $(srctree)/tools/scripts/Makefile.include -INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/lib +INCLUDE = -I$(srctree)/tools/lib/perf/include -I$(srctree)/tools/include -I$(srctree)/tools/lib $(TESTS_A): FORCE $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a $(LIBAPI) diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c index c8d45091e7c2..c8d45091e7c2 100644 --- a/tools/perf/lib/tests/test-cpumap.c +++ b/tools/lib/perf/tests/test-cpumap.c diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index 6d8ebe0c2504..6d8ebe0c2504 100644 --- a/tools/perf/lib/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 135722ac965b..135722ac965b 100644 --- a/tools/perf/lib/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c index 7dc4d6fbedde..7dc4d6fbedde 100644 --- a/tools/perf/lib/tests/test-threadmap.c +++ b/tools/lib/perf/tests/test-threadmap.c diff --git a/tools/perf/lib/threadmap.c b/tools/lib/perf/threadmap.c index e92c368b0a6c..e92c368b0a6c 100644 --- a/tools/perf/lib/threadmap.c +++ b/tools/lib/perf/threadmap.c diff --git a/tools/perf/lib/xyarray.c b/tools/lib/perf/xyarray.c index dcd901d154bb..dcd901d154bb 100644 --- a/tools/perf/lib/xyarray.c +++ b/tools/lib/perf/xyarray.c diff --git a/tools/lib/string.c b/tools/lib/string.c index f2ae1b87c719..f645343815de 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -96,6 +96,10 @@ int strtobool(const char *s, bool *res) * If libc has strlcpy() then that version will override this * implementation: */ +#ifdef __clang__ +#pragma clang diagnostic push +#pragma clang diagnostic ignored "-Wignored-attributes" +#endif size_t __weak strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); @@ -107,6 +111,9 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size) } return ret; } +#ifdef __clang__ +#pragma clang diagnostic pop +#endif /** * skip_spaces - Removes leading whitespace from @str. diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index e8c972f89357..1b5042f134a8 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -112,6 +112,12 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --skip-missing:: Skip symbols that cannot be annotated. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8dbe2119686a..db61f16ffa56 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -367,6 +367,12 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --group:: Show event group information together. It forces group output also if there are no groups defined in data file. diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 63f938b887dd..5fbe42bd599b 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -110,6 +110,10 @@ OPTIONS for 'perf sched timehist' --max-stack:: Maximum number of functions to display in backtrace, default 5. +-C=:: +--cpu=:: + Only show events for the given CPU(s) (comma separated list). + -p=:: --pid=:: Only show events for given process ID (comma separated list). diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 5596129a71cf..324b6b53c86b 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -158,6 +158,12 @@ Default is to monitor all CPUS. -M:: --disassembler-style=:: Set disassembler style for objdump. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --source:: Interleave source code with assembly code. Enabled by default, disable with --no-source. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 4934edb5adfd..5d7b947320fb 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -7,6 +7,7 @@ tools/lib/traceevent tools/lib/api tools/lib/bpf tools/lib/subcmd +tools/lib/perf tools/lib/argv_split.c tools/lib/ctype.c tools/lib/hweight.c diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c90f4146e5a2..80e55e796be9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -286,7 +286,7 @@ ifeq ($(DEBUG),0) endif endif -INC_FLAGS += -I$(src-perf)/lib/include +INC_FLAGS += -I$(srctree)/tools/lib/perf/include INC_FLAGS += -I$(src-perf)/util/include INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include INC_FLAGS += -I$(srctree)/tools/include/ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index eae5d5e95952..3eda9d4b88e7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -230,7 +230,7 @@ LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ BPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ -LIBPERF_DIR = $(srctree)/tools/perf/lib/ +LIBPERF_DIR = $(srctree)/tools/lib/perf/ # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. # Without this setting the output feature dump file misses some features, for diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 5898662bc8fb..ff61795a4d13 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -535,6 +535,10 @@ int cmd_annotate(int argc, const char **argv) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "group", &symbol_conf.event_group, @@ -574,6 +578,9 @@ int cmd_annotate(int argc, const char **argv) annotate.sym_hist_filter = argv[0]; } + if (annotate_check_args(&annotate.opts) < 0) + return -EINVAL; + if (symbol_conf.show_nr_samples && annotate.use_gtk) { pr_err("--show-nr-samples is not available in --gtk mode at this time\n"); return ret; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index e69f44941aad..246ac0b4d54f 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -595,8 +595,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused, { struct c2c_hist_entry *c2c_left; struct c2c_hist_entry *c2c_right; - unsigned int tot_hitm_left; - unsigned int tot_hitm_right; + uint64_t tot_hitm_left; + uint64_t tot_hitm_right; c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); @@ -629,7 +629,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused, \ \ c2c_left = container_of(left, struct c2c_hist_entry, he); \ c2c_right = container_of(right, struct c2c_hist_entry, he); \ - return c2c_left->stats.__f - c2c_right->stats.__f; \ + return (uint64_t) c2c_left->stats.__f - \ + (uint64_t) c2c_right->stats.__f; \ } #define STAT_FN(__f) \ @@ -682,7 +683,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused, c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); - return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats); + return (uint64_t) llc_miss(&c2c_left->stats) - + (uint64_t) llc_miss(&c2c_right->stats); } static uint64_t total_records(struct c2c_stats *stats) @@ -2384,7 +2386,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 's': @@ -2453,7 +2455,7 @@ static int perf_c2c__hists_browse(struct hists *hists) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 'q': diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fb19ef63cc35..4c301466101b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -62,6 +62,7 @@ #include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <linux/bitmap.h> struct switch_output { bool enabled; @@ -93,7 +94,7 @@ struct record { bool timestamp_boundary; struct switch_output switch_output; unsigned long long samples; - cpu_set_t affinity_mask; + struct mmap_cpu_mask affinity_mask; unsigned long output_max_size; /* = 0: unlimited */ }; @@ -961,10 +962,15 @@ static struct perf_event_header finished_round_event = { static void record__adjust_affinity(struct record *rec, struct mmap *map) { if (rec->opts.affinity != PERF_AFFINITY_SYS && - !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) { - CPU_ZERO(&rec->affinity_mask); - CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask); - sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask); + !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits, + rec->affinity_mask.nbits)) { + bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits); + bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits, + map->affinity_mask.bits, rec->affinity_mask.nbits); + sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask), + (cpu_set_t *)rec->affinity_mask.bits); + if (verbose == 2) + mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread"); } } @@ -2433,7 +2439,6 @@ int cmd_record(int argc, const char **argv) # undef REASON #endif - CPU_ZERO(&rec->affinity_mask); rec->opts.affinity = PERF_AFFINITY_SYS; rec->evlist = evlist__new(); @@ -2499,6 +2504,16 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); + if (rec->opts.affinity != PERF_AFFINITY_SYS) { + rec->affinity_mask.nbits = cpu__max_cpu(); + rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits); + if (!rec->affinity_mask.bits) { + pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); + return -ENOMEM; + } + pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits); + } + err = record__auxtrace_init(rec); if (err) goto out; @@ -2613,6 +2628,7 @@ int cmd_record(int argc, const char **argv) err = __cmd_record(&record, argc, argv); out: + bitmap_free(rec->affinity_mask.bits); evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index de988589d99b..9483b3f0cae3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep) PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; -#ifndef HAVE_LIBUNWIND_SUPPORT +#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT) if (dwarf_callchain_users) { - ui__warning("Please install libunwind development packages " - "during the perf build.\n"); + ui__warning("Please install libunwind or libdw " + "development packages during the perf build.\n"); } #endif @@ -1164,7 +1164,8 @@ int cmd_report(int argc, const char **argv) report_callchain_help, &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, - "Accumulate callchains of children and show total overhead as well"), + "Accumulate callchains of children and show total overhead as well. " + "Enabled by default, use --no-children to disable."), OPT_INTEGER(0, "max-stack", &report.max_stack, "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " @@ -1207,6 +1208,10 @@ int cmd_report(int argc, const char **argv) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set, @@ -1286,6 +1291,9 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } + if (annotate_check_args(&report.annotation_opts) < 0) + return -EINVAL; + if (report.mmaps_mode) report.tasks_mode = true; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 8a12d71364c3..82fcc2c15fe4 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -51,6 +51,9 @@ #define SYM_LEN 129 #define MAX_PID 1024000 +static const char *cpu_list; +static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); + struct sched_atom; struct task_desc { @@ -2008,6 +2011,9 @@ static void timehist_print_sample(struct perf_sched *sched, char nstr[30]; u64 wait_time; + if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + return; + timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); @@ -2994,6 +3000,12 @@ static int perf_sched__timehist(struct perf_sched *sched) if (IS_ERR(session)) return PTR_ERR(session); + if (cpu_list) { + err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (err < 0) + goto out; + } + evlist = session->evlist; symbol__init(&session->header.env); @@ -3429,6 +3441,7 @@ int cmd_sched(int argc, const char **argv) "analyze events only for given process id(s)"), OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "analyze events only for given thread id(s)"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_PARENT(sched_options) }; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 795e353de095..8affcab75604 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1512,6 +1512,10 @@ int cmd_top(int argc, const char **argv) "objdump binary to use for disassembly and annotations"), OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", "Don't show entries under that percent", parse_percent_limit), @@ -1582,6 +1586,9 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); + if (annotate_check_args(&top.annotation_opts) < 0) + goto out_delete_evlist; + if (!top.evlist->core.nr_entries && perf_evlist__add_default(top.evlist) < 0) { pr_err("Not enough memory for event selector list\n"); diff --git a/tools/perf/lib/Documentation/Makefile b/tools/perf/lib/Documentation/Makefile deleted file mode 100644 index 586425a88795..000000000000 --- a/tools/perf/lib/Documentation/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -all: - rst2man man/libperf.rst > man/libperf.7 - rst2pdf tutorial/tutorial.rst - -clean: - rm -f man/libperf.7 - rm -f tutorial/tutorial.pdf diff --git a/tools/perf/lib/Documentation/man/libperf.rst b/tools/perf/lib/Documentation/man/libperf.rst deleted file mode 100644 index 09a270fccb9c..000000000000 --- a/tools/perf/lib/Documentation/man/libperf.rst +++ /dev/null @@ -1,100 +0,0 @@ -.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -libperf - -The libperf library provides an API to access the linux kernel perf -events subsystem. It provides the following high level objects: - - - struct perf_cpu_map - - struct perf_thread_map - - struct perf_evlist - - struct perf_evsel - -reference -========= -Function reference by header files: - -perf/core.h ------------ -.. code-block:: c - - typedef int (\*libperf_print_fn_t)(enum libperf_print_level level, - const char \*, va_list ap); - - void libperf_set_print(libperf_print_fn_t fn); - -perf/cpumap.h -------------- -.. code-block:: c - - struct perf_cpu_map \*perf_cpu_map__dummy_new(void); - struct perf_cpu_map \*perf_cpu_map__new(const char \*cpu_list); - struct perf_cpu_map \*perf_cpu_map__read(FILE \*file); - struct perf_cpu_map \*perf_cpu_map__get(struct perf_cpu_map \*map); - void perf_cpu_map__put(struct perf_cpu_map \*map); - int perf_cpu_map__cpu(const struct perf_cpu_map \*cpus, int idx); - int perf_cpu_map__nr(const struct perf_cpu_map \*cpus); - perf_cpu_map__for_each_cpu(cpu, idx, cpus) - -perf/threadmap.h ----------------- -.. code-block:: c - - struct perf_thread_map \*perf_thread_map__new_dummy(void); - void perf_thread_map__set_pid(struct perf_thread_map \*map, int thread, pid_t pid); - char \*perf_thread_map__comm(struct perf_thread_map \*map, int thread); - struct perf_thread_map \*perf_thread_map__get(struct perf_thread_map \*map); - void perf_thread_map__put(struct perf_thread_map \*map); - -perf/evlist.h -------------- -.. code-block:: - - void perf_evlist__init(struct perf_evlist \*evlist); - void perf_evlist__add(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - void perf_evlist__remove(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - struct perf_evlist \*perf_evlist__new(void); - void perf_evlist__delete(struct perf_evlist \*evlist); - struct perf_evsel\* perf_evlist__next(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - int perf_evlist__open(struct perf_evlist \*evlist); - void perf_evlist__close(struct perf_evlist \*evlist); - void perf_evlist__enable(struct perf_evlist \*evlist); - void perf_evlist__disable(struct perf_evlist \*evlist); - perf_evlist__for_each_evsel(evlist, pos) - void perf_evlist__set_maps(struct perf_evlist \*evlist, - struct perf_cpu_map \*cpus, - struct perf_thread_map \*threads); - -perf/evsel.h ------------- -.. code-block:: c - - struct perf_counts_values { - union { - struct { - uint64_t val; - uint64_t ena; - uint64_t run; - }; - uint64_t values[3]; - }; - }; - - void perf_evsel__init(struct perf_evsel \*evsel, - struct perf_event_attr \*attr); - struct perf_evsel \*perf_evsel__new(struct perf_event_attr \*attr); - void perf_evsel__delete(struct perf_evsel \*evsel); - int perf_evsel__open(struct perf_evsel \*evsel, struct perf_cpu_map \*cpus, - struct perf_thread_map \*threads); - void perf_evsel__close(struct perf_evsel \*evsel); - int perf_evsel__read(struct perf_evsel \*evsel, int cpu, int thread, - struct perf_counts_values \*count); - int perf_evsel__enable(struct perf_evsel \*evsel); - int perf_evsel__disable(struct perf_evsel \*evsel); - int perf_evsel__apply_filter(struct perf_evsel \*evsel, const char \*filter); - struct perf_cpu_map \*perf_evsel__cpus(struct perf_evsel \*evsel); - struct perf_thread_map \*perf_evsel__threads(struct perf_evsel \*evsel); - struct perf_event_attr \*perf_evsel__attr(struct perf_evsel \*evsel); diff --git a/tools/perf/lib/Documentation/tutorial/tutorial.rst b/tools/perf/lib/Documentation/tutorial/tutorial.rst deleted file mode 100644 index 7be7bc27b385..000000000000 --- a/tools/perf/lib/Documentation/tutorial/tutorial.rst +++ /dev/null @@ -1,123 +0,0 @@ -.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -libperf tutorial -================ - -Compile and install libperf from kernel sources -=============================================== -.. code-block:: bash - - git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git - cd linux/tools/perf/lib - make - sudo make install prefix=/usr - -Libperf object -============== -The libperf library provides several high level objects: - -struct perf_cpu_map - Provides a cpu list abstraction. - -struct perf_thread_map - Provides a thread list abstraction. - -struct perf_evsel - Provides an abstraction for single a perf event. - -struct perf_evlist - Gathers several struct perf_evsel object and performs functions on all of them. - -The exported API binds these objects together, -for full reference see the libperf.7 man page. - -Examples -======== -Examples aim to explain libperf functionality on simple use cases. -They are based in on a checked out linux kernel git tree: - -.. code-block:: bash - - $ cd tools/perf/lib/Documentation/tutorial/ - $ ls -d ex-* - ex-1-compile ex-2-evsel-stat ex-3-evlist-stat - -ex-1-compile example -==================== -This example shows the basic usage of *struct perf_cpu_map*, -how to create it and display its cpus: - -.. code-block:: bash - - $ cd ex-1-compile/ - $ make - gcc -o test test.c -lperf - $ ./test - 0 1 2 3 4 5 6 7 - - -The full code listing is here: - -.. code-block:: c - - 1 #include <perf/cpumap.h> - 2 - 3 int main(int argc, char **Argv) - 4 { - 5 struct perf_cpu_map *cpus; - 6 int cpu, tmp; - 7 - 8 cpus = perf_cpu_map__new(NULL); - 9 - 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) - 11 fprintf(stdout, "%d ", cpu); - 12 - 13 fprintf(stdout, "\n"); - 14 - 15 perf_cpu_map__put(cpus); - 16 return 0; - 17 } - - -First you need to include the proper header to have *struct perf_cpumap* -declaration and functions: - -.. code-block:: c - - 1 #include <perf/cpumap.h> - - -The *struct perf_cpumap* object is created by *perf_cpu_map__new* call. -The *NULL* argument asks it to populate the object with the current online CPUs list: - -.. code-block:: c - - 8 cpus = perf_cpu_map__new(NULL); - -This is paired with a *perf_cpu_map__put*, that drops its reference at the end, possibly deleting it. - -.. code-block:: c - - 15 perf_cpu_map__put(cpus); - -The iteration through the *struct perf_cpumap* CPUs is done using the *perf_cpu_map__for_each_cpu* -macro which requires 3 arguments: - -- cpu - the cpu numer -- tmp - iteration helper variable -- cpus - the *struct perf_cpumap* object - -.. code-block:: c - - 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) - 11 fprintf(stdout, "%d ", cpu); - -ex-2-evsel-stat example -======================= - -TBD - -ex-3-evlist-stat example -======================== - -TBD diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index 415903b48578..da8ec1e8e064 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -263,20 +263,20 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused if (count1 == 11) pr_debug("failed: RF EFLAG recursion issue detected\n"); else - pr_debug("failed: wrong count for bp1%lld\n", count1); + pr_debug("failed: wrong count for bp1: %lld, expected 1\n", count1); } if (overflows != 3) - pr_debug("failed: wrong overflow hit\n"); + pr_debug("failed: wrong overflow (%d) hit, expected 3\n", overflows); if (overflows_2 != 3) - pr_debug("failed: wrong overflow_2 hit\n"); + pr_debug("failed: wrong overflow_2 (%d) hit, expected 3\n", overflows_2); if (count2 != 3) - pr_debug("failed: wrong count for bp2\n"); + pr_debug("failed: wrong count for bp2 (%lld), expected 3\n", count2); if (count3 != 2) - pr_debug("failed: wrong count for bp3\n"); + pr_debug("failed: wrong count for bp3 (%lld), expected 2\n", count3); return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c index 173c8f760763..e0c13e6a5788 100644 --- a/tools/perf/trace/beauty/sockaddr.c +++ b/tools/perf/trace/beauty/sockaddr.c @@ -72,5 +72,5 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg if (arg->augmented.args) return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size); - return scnprintf(bf, size, "%#x", arg->val); + return scnprintf(bf, size, "%#lx", arg->val); } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index d4d3558fdef4..f36dee499320 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -18,7 +18,9 @@ #include "../../util/evlist.h" #include "../../util/header.h" #include "../../util/hist.h" +#include "../../util/machine.h" #include "../../util/map.h" +#include "../../util/maps.h" #include "../../util/symbol.h" #include "../../util/map_symbol.h" #include "../../util/branch.h" @@ -391,6 +393,57 @@ static void hist_entry__init_have_children(struct hist_entry *he) he->init_have_children = true; } +static bool hist_browser__selection_has_children(struct hist_browser *browser) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + + if (!he || !ms) + return false; + + if (ms == &he->ms) + return he->has_children; + + return container_of(ms, struct callchain_list, ms)->has_children; +} + +static bool hist_browser__he_selection_unfolded(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->unfolded : false; +} + +static bool hist_browser__selection_unfolded(struct hist_browser *browser) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + + if (!he || !ms) + return false; + + if (ms == &he->ms) + return he->unfolded; + + return container_of(ms, struct callchain_list, ms)->unfolded; +} + +static char *hist_browser__selection_sym_name(struct hist_browser *browser, char *bf, size_t size) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + struct callchain_list *callchain_entry; + + if (!he || !ms) + return NULL; + + if (ms == &he->ms) { + hist_entry__sym_snprintf(he, bf, size, 0); + return bf + 4; // skip the level, e.g. '[k] ' + } + + callchain_entry = container_of(ms, struct callchain_list, ms); + return callchain_list__sym_name(callchain_entry, bf, size, browser->show_dso); +} + static bool hist_browser__toggle_fold(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -624,10 +677,81 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si return browser->title ? browser->title(browser, bf, size) : 0; } +static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, int key) +{ + switch (key) { + case K_TIMER: { + struct hist_browser_timer *hbt = browser->hbt; + u64 nr_entries; + + WARN_ON_ONCE(!hbt); + + if (hbt) + hbt->timer(hbt->arg); + + if (hist_browser__has_filter(browser) || symbol_conf.report_hierarchy) + hist_browser__update_nr_entries(browser); + + nr_entries = hist_browser__nr_entries(browser); + ui_browser__update_nr_entries(&browser->b, nr_entries); + + if (warn_lost_event && + (browser->hists->stats.nr_lost_warned != + browser->hists->stats.nr_events[PERF_RECORD_LOST])) { + browser->hists->stats.nr_lost_warned = + browser->hists->stats.nr_events[PERF_RECORD_LOST]; + ui_browser__warn_lost_events(&browser->b); + } + + hist_browser__title(browser, title, sizeof(title)); + ui_browser__show_title(&browser->b, title); + break; + } + case 'D': { /* Debug */ + struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); + static int seq; + + ui_helpline__pop(); + ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + seq++, browser->b.nr_entries, browser->hists->nr_entries, + browser->b.extra_title_lines, browser->b.rows, + browser->b.index, browser->b.top_idx, h->row_offset, h->nr_rows); + } + break; + case 'C': + /* Collapse the whole world. */ + hist_browser__set_folding(browser, false); + break; + case 'c': + /* Collapse the selected entry. */ + hist_browser__set_folding_selected(browser, false); + break; + case 'E': + /* Expand the whole world. */ + hist_browser__set_folding(browser, true); + break; + case 'e': + /* Expand the selected entry. */ + hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser)); + break; + case 'H': + browser->show_headers = !browser->show_headers; + hist_browser__update_rows(browser); + break; + case '+': + if (hist_browser__toggle_fold(browser)) + break; + /* fall thru */ + default: + return -1; + } + + return 0; +} + int hist_browser__run(struct hist_browser *browser, const char *help, - bool warn_lost_event) + bool warn_lost_event, int key) { - int key; char title[160]; struct hist_browser_timer *hbt = browser->hbt; int delay_secs = hbt ? hbt->refresh : 0; @@ -640,79 +764,14 @@ int hist_browser__run(struct hist_browser *browser, const char *help, if (ui_browser__show(&browser->b, title, "%s", help) < 0) return -1; + if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, key)) + goto out; + while (1) { key = ui_browser__run(&browser->b, delay_secs); - switch (key) { - case K_TIMER: { - u64 nr_entries; - - WARN_ON_ONCE(!hbt); - - if (hbt) - hbt->timer(hbt->arg); - - if (hist_browser__has_filter(browser) || - symbol_conf.report_hierarchy) - hist_browser__update_nr_entries(browser); - - nr_entries = hist_browser__nr_entries(browser); - ui_browser__update_nr_entries(&browser->b, nr_entries); - - if (warn_lost_event && - (browser->hists->stats.nr_lost_warned != - browser->hists->stats.nr_events[PERF_RECORD_LOST])) { - browser->hists->stats.nr_lost_warned = - browser->hists->stats.nr_events[PERF_RECORD_LOST]; - ui_browser__warn_lost_events(&browser->b); - } - - hist_browser__title(browser, title, sizeof(title)); - ui_browser__show_title(&browser->b, title); - continue; - } - case 'D': { /* Debug */ - static int seq; - struct hist_entry *h = rb_entry(browser->b.top, - struct hist_entry, rb_node); - ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", - seq++, browser->b.nr_entries, - browser->hists->nr_entries, - browser->b.extra_title_lines, - browser->b.rows, - browser->b.index, - browser->b.top_idx, - h->row_offset, h->nr_rows); - } - break; - case 'C': - /* Collapse the whole world. */ - hist_browser__set_folding(browser, false); - break; - case 'c': - /* Collapse the selected entry. */ - hist_browser__set_folding_selected(browser, false); + if (hist_browser__handle_hotkey(browser, warn_lost_event, title, key)) break; - case 'E': - /* Expand the whole world. */ - hist_browser__set_folding(browser, true); - break; - case 'e': - /* Expand the selected entry. */ - hist_browser__set_folding_selected(browser, true); - break; - case 'H': - browser->show_headers = !browser->show_headers; - hist_browser__update_rows(browser); - break; - case K_ENTER: - if (hist_browser__toggle_fold(browser)) - break; - /* fall thru */ - default: - goto out; - } } out: ui_browser__hide(&browser->b); @@ -2339,7 +2398,7 @@ close_file_and_continue: closedir(pwd_dir); if (nr_options) { - choice = ui__popup_menu(nr_options, options); + choice = ui__popup_menu(nr_options, options, NULL); if (choice < nr_options && choice >= 0) { tmp = strdup(abs_path[choice]); if (tmp) { @@ -2411,7 +2470,8 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct map_symbol *ms) { - if (ms->sym == NULL || ms->map->dso->annotate_warned) + if (ms->sym == NULL || ms->map->dso->annotate_warned || + symbol__annotation(ms->sym)->src == NULL) return 0; if (asprintf(optstr, "Annotate %s", ms->sym->name) < 0) @@ -2484,11 +2544,8 @@ add_thread_opt(struct hist_browser *browser, struct popup_action *act, return 1; } -static int -do_zoom_dso(struct hist_browser *browser, struct popup_action *act) +static int hists_browser__zoom_map(struct hist_browser *browser, struct map *map) { - struct map *map = act->ms.map; - if (!hists__has(browser->hists, dso) || map == NULL) return 0; @@ -2511,13 +2568,19 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act) } static int +do_zoom_dso(struct hist_browser *browser, struct popup_action *act) +{ + return hists_browser__zoom_map(browser, act->ms.map); +} + +static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { if (!hists__has(browser->hists, dso) || map == NULL) return 0; - if (asprintf(optstr, "Zoom %s %s DSO", + if (asprintf(optstr, "Zoom %s %s DSO (use the 'k' hotkey to zoom directly into the kernel)", browser->hists->dso_filter ? "out of" : "into", __map__is_kernel(map) ? "the Kernel" : map->dso->short_name) < 0) return 0; @@ -2527,6 +2590,28 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act, return 1; } +static int do_toggle_callchain(struct hist_browser *browser, struct popup_action *act __maybe_unused) +{ + hist_browser__toggle_fold(browser); + return 0; +} + +static int add_callchain_toggle_opt(struct hist_browser *browser, struct popup_action *act, char **optstr) +{ + char sym_name[512]; + + if (!hist_browser__selection_has_children(browser)) + return 0; + + if (asprintf(optstr, "%s [%s] callchain (one level, same as '+' hotkey, use 'e'/'c' for the whole main level entry)", + hist_browser__selection_unfolded(browser) ? "Collapse" : "Expand", + hist_browser__selection_sym_name(browser, sym_name, sizeof(sym_name))) < 0) + return 0; + + act->fn = do_toggle_callchain; + return 1; +} + static int do_browse_map(struct hist_browser *browser __maybe_unused, struct popup_action *act) @@ -2858,12 +2943,15 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, "For symbolic views (--sort has sym):\n\n" \ "ENTER Zoom into DSO/Threads & Annotate current symbol\n" \ "ESC Zoom out\n" \ + "+ Expand/Collapse one callchain level\n" \ "a Annotate current symbol\n" \ "C Collapse all callchains\n" \ "d Zoom into current DSO\n" \ + "e Expand/Collapse main entry callchains\n" \ "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ "H Display column headers\n" \ + "k Zoom into the kernel map\n" \ "L Change percent limit\n" \ "m Display context menu\n" \ "S Zoom into current Processor Socket\n" \ @@ -2914,13 +3002,13 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, while (1) { struct thread *thread = NULL; struct map *map = NULL; - int choice = 0; + int choice; int socked_id = -1; - nr_options = 0; - - key = hist_browser__run(browser, helpline, - warn_lost_event); + key = 0; // reset key +do_hotkey: // key came straight from options ui__popup_menu() + choice = nr_options = 0; + key = hist_browser__run(browser, helpline, warn_lost_event, key); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -2950,6 +3038,14 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, browser->selection->map->dso->annotate_warned) continue; + if (symbol__annotation(browser->selection->sym)->src == NULL) { + ui_browser__warning(&browser->b, delay_secs * 2, + "No samples for the \"%s\" symbol.\n\n" + "Probably appeared just in a callchain", + browser->selection->sym->name); + continue; + } + actions->ms.map = browser->selection->map; actions->ms.sym = browser->selection->sym; do_annotate(browser, actions); @@ -2961,6 +3057,10 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, actions->ms.map = map; do_zoom_dso(browser, actions); continue; + case 'k': + if (browser->selection != NULL) + hists_browser__zoom_map(browser, browser->selection->maps->machine->vmlinux_map); + continue; case 'V': verbose = (verbose + 1) % 4; browser->show_dso = verbose > 0; @@ -3062,6 +3162,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, continue; } + actions->ms.map = map; top = pstack__peek(browser->pstack); if (top == &browser->hists->dso_filter) { /* @@ -3135,6 +3236,7 @@ skip_annotation: &options[nr_options], thread); nr_options += add_dso_opt(browser, &actions[nr_options], &options[nr_options], map); + nr_options += add_callchain_toggle_opt(browser, &actions[nr_options], &options[nr_options]); nr_options += add_map_opt(browser, &actions[nr_options], &options[nr_options], browser->selection ? @@ -3193,10 +3295,13 @@ skip_scripting: do { struct popup_action *act; - choice = ui__popup_menu(nr_options, options); - if (choice == -1 || choice >= nr_options) + choice = ui__popup_menu(nr_options, options, &key); + if (choice == -1) break; + if (choice == nr_options) + goto do_hotkey; + act = &actions[choice]; key = act->fn(browser, act); } while (key == 1); @@ -3492,7 +3597,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, memset(&action, 0, sizeof(action)); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 'q': diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index 078f2f2c7abd..1e938d9ffa5e 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -34,7 +34,7 @@ struct hist_browser { struct hist_browser *hist_browser__new(struct hists *hists); void hist_browser__delete(struct hist_browser *browser); int hist_browser__run(struct hist_browser *browser, const char *help, - bool warn_lost_event); + bool warn_lost_event, int key); void hist_browser__init(struct hist_browser *browser, struct hists *hists); #endif /* _PERF_UI_BROWSER_HISTS_H_ */ diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c index 76d356a18790..7cb2d6678039 100644 --- a/tools/perf/ui/browsers/res_sample.c +++ b/tools/perf/ui/browsers/res_sample.c @@ -56,7 +56,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res, return -1; } } - choice = ui__popup_menu(num_res, names); + choice = ui__popup_menu(num_res, names, NULL); for (i = 0; i < num_res; i++) zfree(&names[i]); free(names); diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index fc733a6354d4..47d2c7a8cbe1 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -126,7 +126,7 @@ static int list_scripts(char *script_name, bool *custom, SCRIPT_FULLPATH_LEN); if (num < 0) num = 0; - choice = ui__popup_menu(num + max_std, (char * const *)names); + choice = ui__popup_menu(num + max_std, (char * const *)names, NULL); if (choice < 0) { ret = -1; goto out; diff --git a/tools/perf/ui/gtk/Build b/tools/perf/ui/gtk/Build index ec22e899a224..eef708c502f4 100644 --- a/tools/perf/ui/gtk/Build +++ b/tools/perf/ui/gtk/Build @@ -1,4 +1,4 @@ -CFLAGS_gtk += -fPIC $(GTK_CFLAGS) +CFLAGS_gtk += -fPIC $(GTK_CFLAGS) -Wno-deprecated-declarations gtk-y += browser.o gtk-y += hists.o @@ -7,3 +7,8 @@ gtk-y += util.o gtk-y += helpline.o gtk-y += progress.o gtk-y += annotate.o +gtk-y += zalloc.o + +$(OUTPUT)ui/gtk/zalloc.o: ../lib/zalloc.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c index b98dd0e31dc1..0f562e2cb1e8 100644 --- a/tools/perf/ui/tui/util.c +++ b/tools/perf/ui/tui/util.c @@ -23,7 +23,7 @@ static void ui_browser__argv_write(struct ui_browser *browser, ui_browser__write_nstring(browser, *arg, browser->width); } -static int popup_menu__run(struct ui_browser *menu) +static int popup_menu__run(struct ui_browser *menu, int *keyp) { int key; @@ -45,6 +45,11 @@ static int popup_menu__run(struct ui_browser *menu) key = -1; break; default: + if (keyp) { + *keyp = key; + key = menu->nr_entries; + break; + } continue; } @@ -55,7 +60,7 @@ static int popup_menu__run(struct ui_browser *menu) return key; } -int ui__popup_menu(int argc, char * const argv[]) +int ui__popup_menu(int argc, char * const argv[], int *keyp) { struct ui_browser menu = { .entries = (void *)argv, @@ -64,8 +69,7 @@ int ui__popup_menu(int argc, char * const argv[]) .write = ui_browser__argv_write, .nr_entries = argc, }; - - return popup_menu__run(&menu); + return popup_menu__run(&menu, keyp); } int ui_browser__input_window(const char *title, const char *text, char *input, diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h index 40891942f465..e30cea807564 100644 --- a/tools/perf/ui/util.h +++ b/tools/perf/ui/util.h @@ -5,7 +5,7 @@ #include <stdarg.h> int ui__getch(int delay_secs); -int ui__popup_menu(int argc, char * const argv[]); +int ui__popup_menu(int argc, char * const argv[], int *keyp); int ui__help_window(const char *text); int ui__dialog_yesno(const char *msg); void __ui__info_window(const char *title, const char *text, const char *exit_msg); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f5e77ed237e8..ca73fb74ad03 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1966,14 +1966,20 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C \"$1\"", + " -l -d %s %s %s %c%s%c %s%s -C \"$1\"", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), opts->show_asm_raw ? "" : "--no-show-raw-insn", - opts->annotate_src ? "-S" : ""); + opts->annotate_src ? "-S" : "", + opts->prefix ? "--prefix " : "", + opts->prefix ? '"' : ' ', + opts->prefix ?: "", + opts->prefix ? '"' : ' ', + opts->prefix_strip ? "--prefix-strip=" : "", + opts->prefix_strip ?: ""); if (err < 0) { pr_err("Failure allocating memory for the command to run\n"); @@ -3204,3 +3210,12 @@ out: free(str1); return err; } + +int annotate_check_args(struct annotation_options *args) +{ + if (args->prefix_strip && !args->prefix) { + pr_err("--prefix-strip requires --prefix\n"); + return -1; + } + return 0; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 7075d98f69d9..455403e8fede 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -94,6 +94,8 @@ struct annotation_options { int context; const char *objdump_path; const char *disassembler_style; + const char *prefix; + const char *prefix_strip; unsigned int percent_type; }; @@ -415,4 +417,7 @@ void annotation_config__init(void); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); + +int annotate_check_args(struct annotation_options *args); + #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index fc361c3f8570..c8885dfa3667 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -71,7 +71,11 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags, CompilerInstance Clang; Clang.createDiagnostics(); +#if CLANG_VERSION_MAJOR < 9 Clang.setVirtualFileSystem(&*VFS); +#else + Clang.createFileManager(&*VFS); +#endif #if CLANG_VERSION_MAJOR < 4 IntrusiveRefCntPtr<CompilerInvocation> CI = diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index f9a20a39b64a..7d226241f1d7 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -12,7 +12,8 @@ #define MAXIDLEN 256 %} -%pure-parser +%define api.pure full + %parse-param { double *final_val } %parse-param { struct parse_ctx *ctx } %parse-param { const char **pp } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 93ad27830e2b..4246e7447e54 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2922,7 +2922,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - stctime = st.st_ctime; + stctime = st.st_mtime; fprintf(fp, "# captured on : %s", ctime(&stctime)); fprintf(fp, "# header version : %u\n", header->version); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 063d1b93c53d..3b664fa673a6 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -23,6 +23,18 @@ #include "mmap.h" #include "../perf.h" #include <internal/lib.h> /* page_size */ +#include <linux/bitmap.h> + +#define MASK_SIZE 1023 +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag) +{ + char buf[MASK_SIZE + 1]; + size_t len; + + len = bitmap_scnprintf(mask->bits, mask->nbits, buf, MASK_SIZE); + buf[len] = '\0'; + pr_debug("%p: %s mask[%zd]: %s\n", mask, tag, mask->nbits, buf); +} size_t mmap__mmap_len(struct mmap *map) { @@ -207,6 +219,8 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) void mmap__munmap(struct mmap *map) { + bitmap_free(map->affinity_mask.bits); + perf_mmap__aio_munmap(map); if (map->data != NULL) { munmap(map->data, mmap__mmap_len(map)); @@ -215,7 +229,7 @@ void mmap__munmap(struct mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } -static void build_node_mask(int node, cpu_set_t *mask) +static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int c, cpu, nr_cpus; const struct perf_cpu_map *cpu_map = NULL; @@ -228,17 +242,23 @@ static void build_node_mask(int node, cpu_set_t *mask) for (c = 0; c < nr_cpus; c++) { cpu = cpu_map->map[c]; /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) - CPU_SET(cpu, mask); + set_bit(cpu, mask->bits); } } -static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) +static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - CPU_ZERO(&map->affinity_mask); + map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits); + if (!map->affinity_mask.bits) + return -1; + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - CPU_SET(map->core.cpu, &map->affinity_mask); + set_bit(map->core.cpu, map->affinity_mask.bits); + + return 0; } int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) @@ -249,7 +269,15 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) return -1; } - perf_mmap__setup_affinity_mask(map, mp); + if (mp->affinity != PERF_AFFINITY_SYS && + perf_mmap__setup_affinity_mask(map, mp)) { + pr_debug2("failed to alloc mmap affinity mask, error %d\n", + errno); + return -1; + } + + if (verbose == 2) + mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap"); map->core.flush = mp->flush; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index bee4e83f7109..9d5f589f02ae 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -15,6 +15,15 @@ #include "event.h" struct aiocb; + +struct mmap_cpu_mask { + unsigned long *bits; + size_t nbits; +}; + +#define MMAP_CPU_MASK_BYTES(m) \ + (BITS_TO_LONGS(((struct mmap_cpu_mask *)m)->nbits) * sizeof(unsigned long)) + /** * struct mmap - perf's ring buffer mmap details * @@ -31,7 +40,7 @@ struct mmap { int nr_cblocks; } aio; #endif - cpu_set_t affinity_mask; + struct mmap_cpu_mask affinity_mask; void *data; int comp_level; }; @@ -52,4 +61,6 @@ int perf_mmap__push(struct mmap *md, void *to, size_t mmap__mmap_len(struct mmap *map); +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); + #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index e2eea4e601b4..94f8bcd83582 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,4 +1,4 @@ -%pure-parser +%define api.pure full %parse-param {void *_parse_state} %parse-param {void *scanner} %lex-param {void* scanner} diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9fcba2872130..ab0cfd790ad0 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -324,8 +324,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms, return ret; } -static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, - size_t size, unsigned int width) +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { return _hist_entry__sym_snprintf(&he->ms, he->ip, he->level, bf, size, width); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 5aff9542d9b7..6c862d62d052 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -164,6 +164,8 @@ static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) return he->callchain_size != 0; } +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width); + static inline bool hist_entry__has_pairs(struct hist_entry *he) { return !list_empty(&he->pairs.node); |