diff options
Diffstat (limited to 'kernel/trace')
29 files changed, 3363 insertions, 2484 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 5e3de28c7677..fa8b1fe824f3 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -461,6 +461,7 @@ config KPROBE_EVENTS bool "Enable kprobes-based dynamic events" select TRACING select PROBE_EVENTS + select DYNAMIC_EVENTS default y help This allows the user to add tracing events (similar to tracepoints) @@ -500,6 +501,7 @@ config UPROBE_EVENTS depends on PERF_EVENTS select UPROBES select PROBE_EVENTS + select DYNAMIC_EVENTS select TRACING default y help @@ -518,6 +520,9 @@ config BPF_EVENTS help This allows the user to attach BPF programs to kprobe events. +config DYNAMIC_EVENTS + def_bool n + config PROBE_EVENTS def_bool n @@ -630,6 +635,7 @@ config HIST_TRIGGERS depends on ARCH_HAVE_NMI_SAFE_CMPXCHG select TRACING_MAP select TRACING + select DYNAMIC_EVENTS default n help Hist triggers allow one or more arbitrary trace event fields diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index f81dadbc7c4a..c2b2148bb1d2 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += fgraph.o ifeq ($(CONFIG_BLOCK),y) obj-$(CONFIG_EVENT_TRACING) += blktrace.o endif @@ -78,6 +79,7 @@ endif ifeq ($(CONFIG_TRACING),y) obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif +obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..d64c00afceb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -17,6 +17,43 @@ #include "trace_probe.h" #include "trace.h" +#ifdef CONFIG_MODULES +struct bpf_trace_module { + struct module *module; + struct list_head list; +}; + +static LIST_HEAD(bpf_trace_modules); +static DEFINE_MUTEX(bpf_module_mutex); + +static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) +{ + struct bpf_raw_event_map *btp, *ret = NULL; + struct bpf_trace_module *btm; + unsigned int i; + + mutex_lock(&bpf_module_mutex); + list_for_each_entry(btm, &bpf_trace_modules, list) { + for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { + btp = &btm->module->bpf_raw_events[i]; + if (!strcmp(btp->tp->name, name)) { + if (try_module_get(btm->module)) + ret = btp; + goto out; + } + } + } +out: + mutex_unlock(&bpf_module_mutex); + return ret; +} +#else +static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) +{ + return NULL; +} +#endif /* CONFIG_MODULES */ + u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); @@ -133,7 +170,7 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; - if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) + if (!access_ok(unsafe_ptr, size)) return -EPERM; return probe_kernel_write(unsafe_ptr, src, size); @@ -196,11 +233,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; @@ -392,8 +431,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; - perf_event_output(event, sd, regs); - return 0; + return perf_event_output(event, sd, regs); } BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, @@ -1074,7 +1112,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) extern struct bpf_raw_event_map __start__bpf_raw_tp[]; extern struct bpf_raw_event_map __stop__bpf_raw_tp[]; -struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name) +struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { struct bpf_raw_event_map *btp = __start__bpf_raw_tp; @@ -1082,7 +1120,16 @@ struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name) if (!strcmp(btp->tp->name, name)) return btp; } - return NULL; + + return bpf_get_raw_tracepoint_module(name); +} + +void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) +{ + struct module *mod = __module_address((unsigned long)btp); + + if (mod) + module_put(mod); } static __always_inline @@ -1156,22 +1203,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = __bpf_probe_register(btp, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -1220,3 +1257,52 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, return err; } + +#ifdef CONFIG_MODULES +int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) +{ + struct bpf_trace_module *btm, *tmp; + struct module *mod = module; + + if (mod->num_bpf_raw_events == 0 || + (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) + return 0; + + mutex_lock(&bpf_module_mutex); + + switch (op) { + case MODULE_STATE_COMING: + btm = kzalloc(sizeof(*btm), GFP_KERNEL); + if (btm) { + btm->module = module; + list_add(&btm->list, &bpf_trace_modules); + } + break; + case MODULE_STATE_GOING: + list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) { + if (btm->module == module) { + list_del(&btm->list); + kfree(btm); + break; + } + } + break; + } + + mutex_unlock(&bpf_module_mutex); + + return 0; +} + +static struct notifier_block bpf_module_nb = { + .notifier_call = bpf_event_notify, +}; + +int __init bpf_event_init(void) +{ + register_module_notifier(&bpf_module_nb); + return 0; +} + +fs_initcall(bpf_event_init); +#endif /* CONFIG_MODULES */ diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c new file mode 100644 index 000000000000..8dfd5021b933 --- /dev/null +++ b/kernel/trace/fgraph.c @@ -0,0 +1,626 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Infrastructure to took into function calls and returns. + * Copyright (c) 2008-2009 Frederic Weisbecker <[email protected]> + * Mostly borrowed from function tracer which + * is Copyright (c) Steven Rostedt <[email protected]> + * + * Highly modified by Steven Rostedt (VMware). + */ +#include <linux/suspend.h> +#include <linux/ftrace.h> +#include <linux/slab.h> + +#include <trace/events/sched.h> + +#include "ftrace_internal.h" + +#ifdef CONFIG_DYNAMIC_FTRACE +#define ASSIGN_OPS_HASH(opsname, val) \ + .func_hash = val, \ + .local_hash.regex_lock = __MUTEX_INITIALIZER(opsname.local_hash.regex_lock), +#else +#define ASSIGN_OPS_HASH(opsname, val) +#endif + +static bool kill_ftrace_graph; +int ftrace_graph_active; + +/* Both enabled by default (can be cleared by function_graph tracer flags */ +static bool fgraph_sleep_time = true; + +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +bool ftrace_graph_is_dead(void) +{ + return kill_ftrace_graph; +} + +/** + * ftrace_graph_stop - set to permanently disable function graph tracincg + * + * In case of an error int function graph tracing, this is called + * to try to keep function graph tracing from causing any more harm. + * Usually this is pretty severe and this is called to try to at least + * get a warning out to the user. + */ +void ftrace_graph_stop(void) +{ + kill_ftrace_graph = true; +} + +/* Add a function return address to the trace stack on thread info.*/ +static int +ftrace_push_return_trace(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + unsigned long long calltime; + int index; + + if (unlikely(ftrace_graph_is_dead())) + return -EBUSY; + + if (!current->ret_stack) + return -EBUSY; + + /* + * We must make sure the ret_stack is tested before we read + * anything else. + */ + smp_rmb(); + + /* The return trace stack is full */ + if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { + atomic_inc(¤t->trace_overrun); + return -EBUSY; + } + + calltime = trace_clock_local(); + + index = ++current->curr_ret_stack; + barrier(); + current->ret_stack[index].ret = ret; + current->ret_stack[index].func = func; + current->ret_stack[index].calltime = calltime; +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + current->ret_stack[index].fp = frame_pointer; +#endif +#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + current->ret_stack[index].retp = retp; +#endif + return 0; +} + +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = ++current->curr_ret_depth; + + if (ftrace_push_return_trace(ret, func, frame_pointer, retp)) + goto out; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + goto out_ret; + + return 0; + out_ret: + current->curr_ret_stack--; + out: + current->curr_ret_depth--; + return -EBUSY; +} + +/* Retrieve a function return address to the trace stack on thread info.*/ +static void +ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, + unsigned long frame_pointer) +{ + int index; + + index = current->curr_ret_stack; + + if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic, otherwise we have no where to go */ + *ret = (unsigned long)panic; + return; + } + +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + /* + * The arch may choose to record the frame pointer used + * and check it here to make sure that it is what we expect it + * to be. If gcc does not set the place holder of the return + * address in the frame pointer, and does a copy instead, then + * the function graph trace will fail. This test detects this + * case. + * + * Currently, x86_32 with optimize for size (-Os) makes the latest + * gcc do the above. + * + * Note, -mfentry does not use frame pointers, and this test + * is not needed if CC_USING_FENTRY is set. + */ + if (unlikely(current->ret_stack[index].fp != frame_pointer)) { + ftrace_graph_stop(); + WARN(1, "Bad frame pointer: expected %lx, received %lx\n" + " from func %ps return to %lx\n", + current->ret_stack[index].fp, + frame_pointer, + (void *)current->ret_stack[index].func, + current->ret_stack[index].ret); + *ret = (unsigned long)panic; + return; + } +#endif + + *ret = current->ret_stack[index].ret; + trace->func = current->ret_stack[index].func; + trace->calltime = current->ret_stack[index].calltime; + trace->overrun = atomic_read(¤t->trace_overrun); + trace->depth = current->curr_ret_depth--; + /* + * We still want to trace interrupts coming in if + * max_depth is set to 1. Make sure the decrement is + * seen before ftrace_graph_return. + */ + barrier(); +} + +/* + * Hibernation protection. + * The state of the current task is too much unstable during + * suspend/restore to disk. We want to protect against that. + */ +static int +ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state, + void *unused) +{ + switch (state) { + case PM_HIBERNATION_PREPARE: + pause_graph_tracing(); + break; + + case PM_POST_HIBERNATION: + unpause_graph_tracing(); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block ftrace_suspend_notifier = { + .notifier_call = ftrace_suspend_notifier_call, +}; + +/* + * Send the trace to the ring-buffer. + * @return the original return address. + */ +unsigned long ftrace_return_to_handler(unsigned long frame_pointer) +{ + struct ftrace_graph_ret trace; + unsigned long ret; + + ftrace_pop_return_trace(&trace, &ret, frame_pointer); + trace.rettime = trace_clock_local(); + ftrace_graph_return(&trace); + /* + * The ftrace_graph_return() may still access the current + * ret_stack structure, we need to make sure the update of + * curr_ret_stack is after that. + */ + barrier(); + current->curr_ret_stack--; + + if (unlikely(!ret)) { + ftrace_graph_stop(); + WARN_ON(1); + /* Might as well panic. What else to do? */ + ret = (unsigned long)panic; + } + + return ret; +} + +/** + * ftrace_graph_get_ret_stack - return the entry of the shadow stack + * @task: The task to read the shadow stack from + * @idx: Index down the shadow stack + * + * Return the ret_struct on the shadow stack of the @task at the + * call graph at @idx starting with zero. If @idx is zero, it + * will return the last saved ret_stack entry. If it is greater than + * zero, it will return the corresponding ret_stack for the depth + * of saved return addresses. + */ +struct ftrace_ret_stack * +ftrace_graph_get_ret_stack(struct task_struct *task, int idx) +{ + idx = task->curr_ret_stack - idx; + + if (idx >= 0 && idx <= task->curr_ret_stack) + return &task->ret_stack[idx]; + + return NULL; +} + +/** + * ftrace_graph_ret_addr - convert a potentially modified stack return address + * to its original value + * + * This function can be called by stack unwinding code to convert a found stack + * return address ('ret') to its original value, in case the function graph + * tracer has modified it to be 'return_to_handler'. If the address hasn't + * been modified, the unchanged value of 'ret' is returned. + * + * 'idx' is a state variable which should be initialized by the caller to zero + * before the first call. + * + * 'retp' is a pointer to the return address on the stack. It's ignored if + * the arch doesn't have HAVE_FUNCTION_GRAPH_RET_ADDR_PTR defined. + */ +#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR +unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, + unsigned long ret, unsigned long *retp) +{ + int index = task->curr_ret_stack; + int i; + + if (ret != (unsigned long)return_to_handler) + return ret; + + if (index < 0) + return ret; + + for (i = 0; i <= index; i++) + if (task->ret_stack[i].retp == retp) + return task->ret_stack[i].ret; + + return ret; +} +#else /* !HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ +unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, + unsigned long ret, unsigned long *retp) +{ + int task_idx; + + if (ret != (unsigned long)return_to_handler) + return ret; + + task_idx = task->curr_ret_stack; + + if (!task->ret_stack || task_idx < *idx) + return ret; + + task_idx -= *idx; + (*idx)++; + + return task->ret_stack[task_idx].ret; +} +#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ + +static struct ftrace_ops graph_ops = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | + FTRACE_OPS_FL_INITIALIZED | + FTRACE_OPS_FL_PID | + FTRACE_OPS_FL_STUB, +#ifdef FTRACE_GRAPH_TRAMP_ADDR + .trampoline = FTRACE_GRAPH_TRAMP_ADDR, + /* trampoline_size is only needed for dynamically allocated tramps */ +#endif + ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash) +}; + +void ftrace_graph_sleep_time_control(bool enable) +{ + fgraph_sleep_time = enable; +} + +int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) +{ + return 0; +} + +/* The callbacks that hook a function */ +trace_func_graph_ret_t ftrace_graph_return = + (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; +static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; + +/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */ +static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) +{ + int i; + int ret = 0; + int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE; + struct task_struct *g, *t; + + for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { + ret_stack_list[i] = + kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack_list[i]) { + start = 0; + end = i; + ret = -ENOMEM; + goto free; + } + } + + read_lock(&tasklist_lock); + do_each_thread(g, t) { + if (start == end) { + ret = -EAGAIN; + goto unlock; + } + + if (t->ret_stack == NULL) { + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->curr_ret_stack = -1; + t->curr_ret_depth = -1; + /* Make sure the tasks see the -1 first: */ + smp_wmb(); + t->ret_stack = ret_stack_list[start++]; + } + } while_each_thread(g, t); + +unlock: + read_unlock(&tasklist_lock); +free: + for (i = start; i < end; i++) + kfree(ret_stack_list[i]); + return ret; +} + +static void +ftrace_graph_probe_sched_switch(void *ignore, bool preempt, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long long timestamp; + int index; + + /* + * Does the user want to count the time a function was asleep. + * If so, do not update the time stamps. + */ + if (fgraph_sleep_time) + return; + + timestamp = trace_clock_local(); + + prev->ftrace_timestamp = timestamp; + + /* only process tasks that we timestamped */ + if (!next->ftrace_timestamp) + return; + + /* + * Update all the counters in next to make up for the + * time next was sleeping. + */ + timestamp -= next->ftrace_timestamp; + + for (index = next->curr_ret_stack; index >= 0; index--) + next->ret_stack[index].calltime += timestamp; +} + +static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace) +{ + if (!ftrace_ops_test(&global_ops, trace->func, NULL)) + return 0; + return __ftrace_graph_entry(trace); +} + +/* + * The function graph tracer should only trace the functions defined + * by set_ftrace_filter and set_ftrace_notrace. If another function + * tracer ops is registered, the graph tracer requires testing the + * function against the global ops, and not just trace any function + * that any ftrace_ops registered. + */ +void update_function_graph_func(void) +{ + struct ftrace_ops *op; + bool do_test = false; + + /* + * The graph and global ops share the same set of functions + * to test. If any other ops is on the list, then + * the graph tracing needs to test if its the function + * it should call. + */ + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op != &global_ops && op != &graph_ops && + op != &ftrace_list_end) { + do_test = true; + /* in double loop, break out with goto */ + goto out; + } + } while_for_each_ftrace_op(op); + out: + if (do_test) + ftrace_graph_entry = ftrace_graph_entry_test; + else + ftrace_graph_entry = __ftrace_graph_entry; +} + +static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); + +static void +graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) +{ + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; + /* make curr_ret_stack visible before we add the ret_stack */ + smp_wmb(); + t->ret_stack = ret_stack; +} + +/* + * Allocate a return stack for the idle task. May be the first + * time through, or it may be done by CPU hotplug online. + */ +void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) +{ + t->curr_ret_stack = -1; + t->curr_ret_depth = -1; + /* + * The idle task has no parent, it either has its own + * stack or no stack at all. + */ + if (t->ret_stack) + WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = per_cpu(idle_ret_stack, cpu); + if (!ret_stack) { + ret_stack = + kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + per_cpu(idle_ret_stack, cpu) = ret_stack; + } + graph_init_task(t, ret_stack); + } +} + +/* Allocate a return stack for newly created task */ +void ftrace_graph_init_task(struct task_struct *t) +{ + /* Make sure we do not use the parent ret_stack */ + t->ret_stack = NULL; + t->curr_ret_stack = -1; + t->curr_ret_depth = -1; + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = kmalloc_array(FTRACE_RETFUNC_DEPTH, + sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + graph_init_task(t, ret_stack); + } +} + +void ftrace_graph_exit_task(struct task_struct *t) +{ + struct ftrace_ret_stack *ret_stack = t->ret_stack; + + t->ret_stack = NULL; + /* NULL must become visible to IRQs before we free it: */ + barrier(); + + kfree(ret_stack); +} + +/* Allocate a return stack for each task */ +static int start_graph_tracing(void) +{ + struct ftrace_ret_stack **ret_stack_list; + int ret, cpu; + + ret_stack_list = kmalloc_array(FTRACE_RETSTACK_ALLOC_SIZE, + sizeof(struct ftrace_ret_stack *), + GFP_KERNEL); + + if (!ret_stack_list) + return -ENOMEM; + + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + + do { + ret = alloc_retstack_tasklist(ret_stack_list); + } while (ret == -EAGAIN); + + if (!ret) { + ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); + if (ret) + pr_info("ftrace_graph: Couldn't activate tracepoint" + " probe to kernel_sched_switch\n"); + } + + kfree(ret_stack_list); + return ret; +} + +int register_ftrace_graph(struct fgraph_ops *gops) +{ + int ret = 0; + + mutex_lock(&ftrace_lock); + + /* we currently allow only one tracer registered at a time */ + if (ftrace_graph_active) { + ret = -EBUSY; + goto out; + } + + register_pm_notifier(&ftrace_suspend_notifier); + + ftrace_graph_active++; + ret = start_graph_tracing(); + if (ret) { + ftrace_graph_active--; + goto out; + } + + ftrace_graph_return = gops->retfunc; + + /* + * Update the indirect function to the entryfunc, and the + * function that gets called to the entry_test first. Then + * call the update fgraph entry function to determine if + * the entryfunc should be called directly or not. + */ + __ftrace_graph_entry = gops->entryfunc; + ftrace_graph_entry = ftrace_graph_entry_test; + update_function_graph_func(); + + ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET); +out: + mutex_unlock(&ftrace_lock); + return ret; +} + +void unregister_ftrace_graph(struct fgraph_ops *gops) +{ + mutex_lock(&ftrace_lock); + + if (unlikely(!ftrace_graph_active)) + goto out; + + ftrace_graph_active--; + ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_entry = ftrace_graph_entry_stub; + __ftrace_graph_entry = ftrace_graph_entry_stub; + ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); + unregister_pm_notifier(&ftrace_suspend_notifier); + unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); + + out: + mutex_unlock(&ftrace_lock); +} diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..aac7847c0214 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -19,7 +19,6 @@ #include <linux/sched/task.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> -#include <linux/suspend.h> #include <linux/tracefs.h> #include <linux/hardirq.h> #include <linux/kthread.h> @@ -40,6 +39,7 @@ #include <asm/sections.h> #include <asm/setup.h> +#include "ftrace_internal.h" #include "trace_output.h" #include "trace_stat.h" @@ -77,7 +77,12 @@ #define ASSIGN_OPS_HASH(opsname, val) #endif -static struct ftrace_ops ftrace_list_end __read_mostly = { +enum { + FTRACE_MODIFY_ENABLE_FL = (1 << 0), + FTRACE_MODIFY_MAY_SLEEP_FL = (1 << 1), +}; + +struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, INIT_OPS_HASH(ftrace_list_end) @@ -112,11 +117,11 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops); */ static int ftrace_disabled __read_mostly; -static DEFINE_MUTEX(ftrace_lock); +DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; +struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -static struct ftrace_ops global_ops; +struct ftrace_ops global_ops; #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, @@ -127,26 +132,6 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) #endif -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_notrace() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ -#define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_notrace(list); \ - do - -/* - * Optimized for just a single item in the list (as that is the normal case). - */ -#define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ - unlikely((op) != &ftrace_list_end)) - static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE @@ -173,7 +158,7 @@ static void ftrace_sync(struct work_struct *work) { /* * This function is just a stub to implement a hard force - * of synchronize_sched(). This requires synchronizing + * of synchronize_rcu(). This requires synchronizing * tasks even in userspace and idle. * * Yes, function tracing is rude. @@ -186,18 +171,6 @@ static void ftrace_sync_ipi(void *data) smp_rmb(); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void update_function_graph_func(void); - -/* Both enabled by default (can be cleared by function_graph tracer flags */ -static bool fgraph_sleep_time = true; -static bool fgraph_graph_time = true; - -#else -static inline void update_function_graph_func(void) { } -#endif - - static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops) { /* @@ -334,7 +307,7 @@ static int remove_ftrace_ops(struct ftrace_ops __rcu **list, static void ftrace_update_trampoline(struct ftrace_ops *ops); -static int __register_ftrace_function(struct ftrace_ops *ops) +int __register_ftrace_function(struct ftrace_ops *ops) { if (ops->flags & FTRACE_OPS_FL_DELETED) return -EINVAL; @@ -375,7 +348,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) return 0; } -static int __unregister_ftrace_function(struct ftrace_ops *ops) +int __unregister_ftrace_function(struct ftrace_ops *ops) { int ret; @@ -815,9 +788,16 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, } #ifdef CONFIG_FUNCTION_GRAPH_TRACER +static bool fgraph_graph_time = true; + +void ftrace_graph_graph_time_control(bool enable) +{ + fgraph_graph_time = enable; +} + static int profile_graph_entry(struct ftrace_graph_ent *trace) { - int index = trace->depth; + struct ftrace_ret_stack *ret_stack; function_profile_call(trace->func, 0, NULL, NULL); @@ -825,14 +805,16 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace) if (!current->ret_stack) return 0; - if (index >= 0 && index < FTRACE_RETFUNC_DEPTH) - current->ret_stack[index].subtime = 0; + ret_stack = ftrace_graph_get_ret_stack(current, 0); + if (ret_stack) + ret_stack->subtime = 0; return 1; } static void profile_graph_return(struct ftrace_graph_ret *trace) { + struct ftrace_ret_stack *ret_stack; struct ftrace_profile_stat *stat; unsigned long long calltime; struct ftrace_profile *rec; @@ -850,16 +832,15 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) calltime = trace->rettime - trace->calltime; if (!fgraph_graph_time) { - int index; - - index = trace->depth; /* Append this call time to the parent time to subtract */ - if (index) - current->ret_stack[index - 1].subtime += calltime; + ret_stack = ftrace_graph_get_ret_stack(current, 1); + if (ret_stack) + ret_stack->subtime += calltime; - if (current->ret_stack[index].subtime < calltime) - calltime -= current->ret_stack[index].subtime; + ret_stack = ftrace_graph_get_ret_stack(current, 0); + if (ret_stack && ret_stack->subtime < calltime) + calltime -= ret_stack->subtime; else calltime = 0; } @@ -874,15 +855,19 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) local_irq_restore(flags); } +static struct fgraph_ops fprofiler_ops = { + .entryfunc = &profile_graph_entry, + .retfunc = &profile_graph_return, +}; + static int register_ftrace_profiler(void) { - return register_ftrace_graph(&profile_graph_return, - &profile_graph_entry); + return register_ftrace_graph(&fprofiler_ops); } static void unregister_ftrace_profiler(void) { - unregister_ftrace_graph(); + unregister_ftrace_graph(&fprofiler_ops); } #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { @@ -934,7 +919,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, ftrace_profile_enabled = 0; /* * unregister_ftrace_profiler calls stop_machine - * so this acts like an synchronize_sched. + * so this acts like an synchronize_rcu. */ unregister_ftrace_profiler(); } @@ -1021,12 +1006,6 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) } #endif /* CONFIG_FUNCTION_PROFILER */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int ftrace_graph_active; -#else -# define ftrace_graph_active 0 -#endif - #ifdef CONFIG_DYNAMIC_FTRACE static struct ftrace_ops *removed_ops; @@ -1067,7 +1046,7 @@ static const struct ftrace_hash empty_hash = { }; #define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) -static struct ftrace_ops global_ops = { +struct ftrace_ops global_ops = { .func = ftrace_stub, .local_hash.notrace_hash = EMPTY_HASH, .local_hash.filter_hash = EMPTY_HASH, @@ -1086,7 +1065,7 @@ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr) /* * Some of the ops may be dynamically allocated, - * they are freed after a synchronize_sched(). + * they are freed after a synchronize_rcu(). */ preempt_disable_notrace(); @@ -1286,7 +1265,7 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) { if (!hash || hash == EMPTY_HASH) return; - call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); + call_rcu(&hash->rcu, __free_ftrace_hash_rcu); } void ftrace_free_filter(struct ftrace_ops *ops) @@ -1501,9 +1480,9 @@ static bool hash_contains_ip(unsigned long ip, * the ip is not in the ops->notrace_hash. * * This needs to be called with preemption disabled as - * the hashes are freed with call_rcu_sched(). + * the hashes are freed with call_rcu(). */ -static int +int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) { struct ftrace_ops_hash hash; @@ -2415,10 +2394,12 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) return -1; /* unknow ftrace bug */ } -void __weak ftrace_replace_code(int enable) +void __weak ftrace_replace_code(int mod_flags) { struct dyn_ftrace *rec; struct ftrace_page *pg; + int enable = mod_flags & FTRACE_MODIFY_ENABLE_FL; + int schedulable = mod_flags & FTRACE_MODIFY_MAY_SLEEP_FL; int failed; if (unlikely(ftrace_disabled)) @@ -2435,6 +2416,8 @@ void __weak ftrace_replace_code(int enable) /* Stop processing */ return; } + if (schedulable) + cond_resched(); } while_for_each_ftrace_rec(); } @@ -2548,8 +2531,12 @@ int __weak ftrace_arch_code_modify_post_process(void) void ftrace_modify_all_code(int command) { int update = command & FTRACE_UPDATE_TRACE_FUNC; + int mod_flags = 0; int err = 0; + if (command & FTRACE_MAY_SLEEP) + mod_flags = FTRACE_MODIFY_MAY_SLEEP_FL; + /* * If the ftrace_caller calls a ftrace_ops func directly, * we need to make sure that it only traces functions it @@ -2567,9 +2554,9 @@ void ftrace_modify_all_code(int command) } if (command & FTRACE_UPDATE_CALLS) - ftrace_replace_code(1); + ftrace_replace_code(mod_flags | FTRACE_MODIFY_ENABLE_FL); else if (command & FTRACE_DISABLE_CALLS) - ftrace_replace_code(0); + ftrace_replace_code(mod_flags); if (update && ftrace_trace_function != ftrace_ops_list_func) { function_trace_op = set_function_trace_op; @@ -2682,7 +2669,7 @@ static void ftrace_startup_all(int command) update_all_ops = false; } -static int ftrace_startup(struct ftrace_ops *ops, int command) +int ftrace_startup(struct ftrace_ops *ops, int command) { int ret; @@ -2724,7 +2711,7 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return 0; } -static int ftrace_shutdown(struct ftrace_ops *ops, int command) +int ftrace_shutdown(struct ftrace_ops *ops, int command) { int ret; @@ -4496,7 +4483,7 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, if (ftrace_enabled && !ftrace_hash_empty(hash)) ftrace_run_modify_code(&probe->ops, FTRACE_UPDATE_CALLS, &old_hash_ops); - synchronize_sched(); + synchronize_rcu(); hlist_for_each_entry_safe(entry, tmp, &hhd, hlist) { hlist_del(&entry->hlist); @@ -5314,7 +5301,7 @@ ftrace_graph_release(struct inode *inode, struct file *file) mutex_unlock(&graph_lock); /* Wait till all users are no longer using the old hash */ - synchronize_sched(); + synchronize_rcu(); free_ftrace_hash(old_hash); } @@ -5460,6 +5447,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_ENABLED) ftrace_shutdown(ops, 0); ops->flags |= FTRACE_OPS_FL_DELETED; + ftrace_free_filter(ops); mutex_unlock(&ftrace_lock); } @@ -5707,7 +5695,7 @@ void ftrace_release_mod(struct module *mod) list_for_each_entry_safe(mod_map, n, &ftrace_mod_maps, list) { if (mod_map->mod == mod) { list_del_rcu(&mod_map->list); - call_rcu_sched(&mod_map->rcu, ftrace_free_mod_map); + call_rcu(&mod_map->rcu, ftrace_free_mod_map); break; } } @@ -5927,7 +5915,7 @@ ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, struct ftrace_mod_map *mod_map; const char *ret = NULL; - /* mod_map is freed via call_rcu_sched() */ + /* mod_map is freed via call_rcu() */ preempt_disable(); list_for_each_entry_rcu(mod_map, &ftrace_mod_maps, list) { ret = ftrace_func_address_lookup(mod_map, addr, size, off, sym); @@ -6177,7 +6165,7 @@ void ftrace_init_trace_array(struct trace_array *tr) } #else -static struct ftrace_ops global_ops = { +struct ftrace_ops global_ops = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED | @@ -6194,31 +6182,10 @@ core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } static inline void ftrace_startup_all(int command) { } -/* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(ops, command) \ - ({ \ - int ___ret = __register_ftrace_function(ops); \ - if (!___ret) \ - (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ - ___ret; \ - }) -# define ftrace_shutdown(ops, command) \ - ({ \ - int ___ret = __unregister_ftrace_function(ops); \ - if (!___ret) \ - (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \ - ___ret; \ - }) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) -static inline int -ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) -{ - return 1; -} - static void ftrace_update_trampoline(struct ftrace_ops *ops) { } @@ -6262,7 +6229,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, /* * Some of the ops may be dynamically allocated, - * they must be freed after a synchronize_sched(). + * they must be freed after a synchronize_rcu(). */ preempt_disable_notrace(); @@ -6433,7 +6400,7 @@ static void clear_ftrace_pids(struct trace_array *tr) rcu_assign_pointer(tr->function_pids, NULL); /* Wait till all users are no longer using pid filtering */ - synchronize_sched(); + synchronize_rcu(); trace_free_pid_list(pid_list); } @@ -6580,7 +6547,7 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, rcu_assign_pointer(tr->function_pids, pid_list); if (filtered_pids) { - synchronize_sched(); + synchronize_rcu(); trace_free_pid_list(filtered_pids); } else if (pid_list) { /* Register a probe to set whether to ignore the tracing of a task */ @@ -6745,350 +6712,3 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, mutex_unlock(&ftrace_lock); return ret; } - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - -static struct ftrace_ops graph_ops = { - .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | - FTRACE_OPS_FL_INITIALIZED | - FTRACE_OPS_FL_PID | - FTRACE_OPS_FL_STUB, -#ifdef FTRACE_GRAPH_TRAMP_ADDR - .trampoline = FTRACE_GRAPH_TRAMP_ADDR, - /* trampoline_size is only needed for dynamically allocated tramps */ -#endif - ASSIGN_OPS_HASH(graph_ops, &global_ops.local_hash) -}; - -void ftrace_graph_sleep_time_control(bool enable) -{ - fgraph_sleep_time = enable; -} - -void ftrace_graph_graph_time_control(bool enable) -{ - fgraph_graph_time = enable; -} - -int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) -{ - return 0; -} - -/* The callbacks that hook a function */ -trace_func_graph_ret_t ftrace_graph_return = - (trace_func_graph_ret_t)ftrace_stub; -trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; -static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; - -/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */ -static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) -{ - int i; - int ret = 0; - int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE; - struct task_struct *g, *t; - - for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { - ret_stack_list[i] = - kmalloc_array(FTRACE_RETFUNC_DEPTH, - sizeof(struct ftrace_ret_stack), - GFP_KERNEL); - if (!ret_stack_list[i]) { - start = 0; - end = i; - ret = -ENOMEM; - goto free; - } - } - - read_lock(&tasklist_lock); - do_each_thread(g, t) { - if (start == end) { - ret = -EAGAIN; - goto unlock; - } - - if (t->ret_stack == NULL) { - atomic_set(&t->tracing_graph_pause, 0); - atomic_set(&t->trace_overrun, 0); - t->curr_ret_stack = -1; - /* Make sure the tasks see the -1 first: */ - smp_wmb(); - t->ret_stack = ret_stack_list[start++]; - } - } while_each_thread(g, t); - -unlock: - read_unlock(&tasklist_lock); -free: - for (i = start; i < end; i++) - kfree(ret_stack_list[i]); - return ret; -} - -static void -ftrace_graph_probe_sched_switch(void *ignore, bool preempt, - struct task_struct *prev, struct task_struct *next) -{ - unsigned long long timestamp; - int index; - - /* - * Does the user want to count the time a function was asleep. - * If so, do not update the time stamps. - */ - if (fgraph_sleep_time) - return; - - timestamp = trace_clock_local(); - - prev->ftrace_timestamp = timestamp; - - /* only process tasks that we timestamped */ - if (!next->ftrace_timestamp) - return; - - /* - * Update all the counters in next to make up for the - * time next was sleeping. - */ - timestamp -= next->ftrace_timestamp; - - for (index = next->curr_ret_stack; index >= 0; index--) - next->ret_stack[index].calltime += timestamp; -} - -/* Allocate a return stack for each task */ -static int start_graph_tracing(void) -{ - struct ftrace_ret_stack **ret_stack_list; - int ret, cpu; - - ret_stack_list = kmalloc_array(FTRACE_RETSTACK_ALLOC_SIZE, - sizeof(struct ftrace_ret_stack *), - GFP_KERNEL); - - if (!ret_stack_list) - return -ENOMEM; - - /* The cpu_boot init_task->ret_stack will never be freed */ - for_each_online_cpu(cpu) { - if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_idle_task(idle_task(cpu), cpu); - } - - do { - ret = alloc_retstack_tasklist(ret_stack_list); - } while (ret == -EAGAIN); - - if (!ret) { - ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); - if (ret) - pr_info("ftrace_graph: Couldn't activate tracepoint" - " probe to kernel_sched_switch\n"); - } - - kfree(ret_stack_list); - return ret; -} - -/* - * Hibernation protection. - * The state of the current task is too much unstable during - * suspend/restore to disk. We want to protect against that. - */ -static int -ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state, - void *unused) -{ - switch (state) { - case PM_HIBERNATION_PREPARE: - pause_graph_tracing(); - break; - - case PM_POST_HIBERNATION: - unpause_graph_tracing(); - break; - } - return NOTIFY_DONE; -} - -static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace) -{ - if (!ftrace_ops_test(&global_ops, trace->func, NULL)) - return 0; - return __ftrace_graph_entry(trace); -} - -/* - * The function graph tracer should only trace the functions defined - * by set_ftrace_filter and set_ftrace_notrace. If another function - * tracer ops is registered, the graph tracer requires testing the - * function against the global ops, and not just trace any function - * that any ftrace_ops registered. - */ -static void update_function_graph_func(void) -{ - struct ftrace_ops *op; - bool do_test = false; - - /* - * The graph and global ops share the same set of functions - * to test. If any other ops is on the list, then - * the graph tracing needs to test if its the function - * it should call. - */ - do_for_each_ftrace_op(op, ftrace_ops_list) { - if (op != &global_ops && op != &graph_ops && - op != &ftrace_list_end) { - do_test = true; - /* in double loop, break out with goto */ - goto out; - } - } while_for_each_ftrace_op(op); - out: - if (do_test) - ftrace_graph_entry = ftrace_graph_entry_test; - else - ftrace_graph_entry = __ftrace_graph_entry; -} - -static struct notifier_block ftrace_suspend_notifier = { - .notifier_call = ftrace_suspend_notifier_call, -}; - -int register_ftrace_graph(trace_func_graph_ret_t retfunc, - trace_func_graph_ent_t entryfunc) -{ - int ret = 0; - - mutex_lock(&ftrace_lock); - - /* we currently allow only one tracer registered at a time */ - if (ftrace_graph_active) { - ret = -EBUSY; - goto out; - } - - register_pm_notifier(&ftrace_suspend_notifier); - - ftrace_graph_active++; - ret = start_graph_tracing(); - if (ret) { - ftrace_graph_active--; - goto out; - } - - ftrace_graph_return = retfunc; - - /* - * Update the indirect function to the entryfunc, and the - * function that gets called to the entry_test first. Then - * call the update fgraph entry function to determine if - * the entryfunc should be called directly or not. - */ - __ftrace_graph_entry = entryfunc; - ftrace_graph_entry = ftrace_graph_entry_test; - update_function_graph_func(); - - ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET); -out: - mutex_unlock(&ftrace_lock); - return ret; -} - -void unregister_ftrace_graph(void) -{ - mutex_lock(&ftrace_lock); - - if (unlikely(!ftrace_graph_active)) - goto out; - - ftrace_graph_active--; - ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; - ftrace_graph_entry = ftrace_graph_entry_stub; - __ftrace_graph_entry = ftrace_graph_entry_stub; - ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); - unregister_pm_notifier(&ftrace_suspend_notifier); - unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); - - out: - mutex_unlock(&ftrace_lock); -} - -static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); - -static void -graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) -{ - atomic_set(&t->tracing_graph_pause, 0); - atomic_set(&t->trace_overrun, 0); - t->ftrace_timestamp = 0; - /* make curr_ret_stack visible before we add the ret_stack */ - smp_wmb(); - t->ret_stack = ret_stack; -} - -/* - * Allocate a return stack for the idle task. May be the first - * time through, or it may be done by CPU hotplug online. - */ -void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) -{ - t->curr_ret_stack = -1; - /* - * The idle task has no parent, it either has its own - * stack or no stack at all. - */ - if (t->ret_stack) - WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); - - if (ftrace_graph_active) { - struct ftrace_ret_stack *ret_stack; - - ret_stack = per_cpu(idle_ret_stack, cpu); - if (!ret_stack) { - ret_stack = - kmalloc_array(FTRACE_RETFUNC_DEPTH, - sizeof(struct ftrace_ret_stack), - GFP_KERNEL); - if (!ret_stack) - return; - per_cpu(idle_ret_stack, cpu) = ret_stack; - } - graph_init_task(t, ret_stack); - } -} - -/* Allocate a return stack for newly created task */ -void ftrace_graph_init_task(struct task_struct *t) -{ - /* Make sure we do not use the parent ret_stack */ - t->ret_stack = NULL; - t->curr_ret_stack = -1; - - if (ftrace_graph_active) { - struct ftrace_ret_stack *ret_stack; - - ret_stack = kmalloc_array(FTRACE_RETFUNC_DEPTH, - sizeof(struct ftrace_ret_stack), - GFP_KERNEL); - if (!ret_stack) - return; - graph_init_task(t, ret_stack); - } -} - -void ftrace_graph_exit_task(struct task_struct *t) -{ - struct ftrace_ret_stack *ret_stack = t->ret_stack; - - t->ret_stack = NULL; - /* NULL must become visible to IRQs before we free it: */ - barrier(); - - kfree(ret_stack); -} -#endif diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h new file mode 100644 index 000000000000..0515a2096f90 --- /dev/null +++ b/kernel/trace/ftrace_internal.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H +#define _LINUX_KERNEL_FTRACE_INTERNAL_H + +#ifdef CONFIG_FUNCTION_TRACER + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_notrace() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_notrace(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; +extern struct mutex ftrace_lock; +extern struct ftrace_ops global_ops; + +#ifdef CONFIG_DYNAMIC_FTRACE + +int ftrace_startup(struct ftrace_ops *ops, int command); +int ftrace_shutdown(struct ftrace_ops *ops, int command); +int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs); + +#else /* !CONFIG_DYNAMIC_FTRACE */ + +int __register_ftrace_function(struct ftrace_ops *ops); +int __unregister_ftrace_function(struct ftrace_ops *ops); +/* Keep as macros so we do not need to define the commands */ +# define ftrace_startup(ops, command) \ + ({ \ + int ___ret = __register_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) +# define ftrace_shutdown(ops, command) \ + ({ \ + int ___ret = __unregister_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags &= ~FTRACE_OPS_FL_ENABLED; \ + ___ret; \ + }) +static inline int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs) +{ + return 1; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +extern int ftrace_graph_active; +void update_function_graph_func(void); +#else /* !CONFIG_FUNCTION_GRAPH_TRACER */ +# define ftrace_graph_active 0 +static inline void update_function_graph_func(void) { } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#else /* !CONFIG_FUNCTION_TRACER */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 65bd4616220d..06e864a334bb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -487,6 +487,10 @@ struct ring_buffer_per_cpu { local_t dropped_events; local_t committing; local_t commits; + local_t pages_touched; + local_t pages_read; + long last_pages_touch; + size_t shortest_full; unsigned long read; unsigned long read_bytes; u64 write_stamp; @@ -529,6 +533,41 @@ struct ring_buffer_iter { u64 read_stamp; }; +/** + * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer + * @buffer: The ring_buffer to get the number of pages from + * @cpu: The cpu of the ring_buffer to get the number of pages from + * + * Returns the number of pages used by a per_cpu buffer of the ring buffer. + */ +size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu) +{ + return buffer->buffers[cpu]->nr_pages; +} + +/** + * ring_buffer_nr_pages_dirty - get the number of used pages in the ring buffer + * @buffer: The ring_buffer to get the number of pages from + * @cpu: The cpu of the ring_buffer to get the number of pages from + * + * Returns the number of pages that have content in the ring buffer. + */ +size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu) +{ + size_t read; + size_t cnt; + + read = local_read(&buffer->buffers[cpu]->pages_read); + cnt = local_read(&buffer->buffers[cpu]->pages_touched); + /* The reader can read an empty page, but not more than that */ + if (cnt < read) { + WARN_ON_ONCE(read > cnt + 1); + return 0; + } + + return cnt - read; +} + /* * rb_wake_up_waiters - wake up tasks waiting for ring buffer input * @@ -556,7 +595,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) +int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer); DEFINE_WAIT(wait); @@ -571,7 +610,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) if (cpu == RING_BUFFER_ALL_CPUS) { work = &buffer->irq_work; /* Full only makes sense on per cpu reads */ - full = false; + full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; @@ -623,15 +662,22 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) !ring_buffer_empty_cpu(buffer, cpu)) { unsigned long flags; bool pagebusy; + size_t nr_pages; + size_t dirty; if (!full) break; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + nr_pages = cpu_buffer->nr_pages; + dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + if (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full < full) + cpu_buffer->shortest_full = full; raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - - if (!pagebusy) + if (!pagebusy && + (!nr_pages || (dirty * 100) > full * nr_pages)) break; } @@ -1054,6 +1100,7 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); + local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. @@ -1834,7 +1881,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, * There could have been a race between checking * record_disable and incrementing it. */ - synchronize_sched(); + synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; rb_check_pages(cpu_buffer); @@ -2586,7 +2633,9 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, static __always_inline void rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { - bool pagebusy; + size_t nr_pages; + size_t dirty; + size_t full; if (buffer->irq_work.waiters_pending) { buffer->irq_work.waiters_pending = false; @@ -2600,14 +2649,27 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) irq_work_queue(&cpu_buffer->irq_work.work); } - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + if (cpu_buffer->last_pages_touch == local_read(&cpu_buffer->pages_touched)) + return; - if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) { - cpu_buffer->irq_work.wakeup_full = true; - cpu_buffer->irq_work.full_waiters_pending = false; - /* irq_work_queue() supplies it's own memory barriers */ - irq_work_queue(&cpu_buffer->irq_work.work); - } + if (cpu_buffer->reader_page == cpu_buffer->commit_page) + return; + + if (!cpu_buffer->irq_work.full_waiters_pending) + return; + + cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched); + + full = cpu_buffer->shortest_full; + nr_pages = cpu_buffer->nr_pages; + dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu); + if (full && nr_pages && (dirty * 100) <= full * nr_pages) + return; + + cpu_buffer->irq_work.wakeup_full = true; + cpu_buffer->irq_work.full_waiters_pending = false; + /* irq_work_queue() supplies it's own memory barriers */ + irq_work_queue(&cpu_buffer->irq_work.work); } /* @@ -3151,7 +3213,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * - * The caller should call synchronize_sched() after this. + * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable(struct ring_buffer *buffer) { @@ -3253,7 +3315,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer) * This prevents all writes to the buffer. Any attempt to write * to the buffer after this will fail and return NULL. * - * The caller should call synchronize_sched() after this. + * The caller should call synchronize_rcu() after this. */ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu) { @@ -3732,13 +3794,15 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) goto spin; /* - * Yeah! We succeeded in replacing the page. + * Yay! We succeeded in replacing the page. * * Now make the new head point back to the reader page. */ rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; rb_inc_page(cpu_buffer, &cpu_buffer->head_page); + local_inc(&cpu_buffer->pages_read); + /* Finally update the reader page to the new head */ cpu_buffer->reader_page = reader; cpu_buffer->reader_page->read = 0; @@ -4191,7 +4255,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_prepare); void ring_buffer_read_prepare_sync(void) { - synchronize_sched(); + synchronize_rcu(); } EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync); @@ -4334,6 +4398,10 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) local_set(&cpu_buffer->entries, 0); local_set(&cpu_buffer->committing, 0); local_set(&cpu_buffer->commits, 0); + local_set(&cpu_buffer->pages_touched, 0); + local_set(&cpu_buffer->pages_read, 0); + cpu_buffer->last_pages_touch = 0; + cpu_buffer->shortest_full = 0; cpu_buffer->read = 0; cpu_buffer->read_bytes = 0; @@ -4363,7 +4431,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) atomic_inc(&cpu_buffer->record_disabled); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); @@ -4496,7 +4564,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, goto out; /* - * We can't do a synchronize_sched here because this + * We can't do a synchronize_rcu here because this * function can be called in atomic context. * Normally this will be called from the same CPU as cpu. * If not it's up to the caller to protect this. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bf6f1d70484d..c4238b441624 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1431,7 +1431,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ -static int wait_on_pipe(struct trace_iterator *iter, bool full) +static int wait_on_pipe(struct trace_iterator *iter, int full) { /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) @@ -1681,7 +1681,7 @@ void tracing_reset(struct trace_buffer *buf, int cpu) ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); @@ -1698,7 +1698,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf) ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ - synchronize_sched(); + synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); @@ -2250,7 +2250,7 @@ void trace_buffered_event_disable(void) preempt_enable(); /* Wait for all current users to finish */ - synchronize_sched(); + synchronize_rcu(); for_each_tracing_cpu(cpu) { free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); @@ -2452,7 +2452,7 @@ static inline void ftrace_exports_disable(void) static_branch_disable(&ftrace_exports_enabled); } -void ftrace_exports(struct ring_buffer_event *event) +static void ftrace_exports(struct ring_buffer_event *event) { struct trace_export *export; @@ -2727,6 +2727,7 @@ void trace_dump_stack(int skip) __ftrace_trace_stack(global_trace.trace_buffer.buffer, flags, skip, preempt_count(), NULL); } +EXPORT_SYMBOL_GPL(trace_dump_stack); static DEFINE_PER_CPU(int, user_stack_count); @@ -3383,6 +3384,8 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file const char tgid_space[] = " "; const char space[] = " "; + print_event_info(buf, m); + seq_printf(m, "# %s _-----=> irqs-off\n", tgid ? tgid_space : space); seq_printf(m, "# %s / _----=> need-resched\n", @@ -4407,13 +4410,15 @@ static int trace_set_options(struct trace_array *tr, char *option) int neg = 0; int ret; size_t orig_len = strlen(option); + int len; cmp = strstrip(option); - if (strncmp(cmp, "no", 2) == 0) { + len = str_has_prefix(cmp, "no"); + if (len) neg = 1; - cmp += 2; - } + + cmp += len; mutex_lock(&trace_types_lock); @@ -4603,6 +4608,10 @@ static const char readme_msg[] = "\t\t\t traces\n" #endif #endif /* CONFIG_STACK_TRACER */ +#ifdef CONFIG_DYNAMIC_EVENTS + " dynamic_events\t\t- Add/remove/show the generic dynamic events\n" + "\t\t\t Write into this file to define/undefine new trace events.\n" +#endif #ifdef CONFIG_KPROBE_EVENTS " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" @@ -4615,19 +4624,32 @@ static const char readme_msg[] = "\t accepts: event-definitions (one definition per line)\n" "\t Format: p[:[<group>/]<event>] <place> [<args>]\n" "\t r[maxactive][:[<group>/]<event>] <place> [<args>]\n" +#ifdef CONFIG_HIST_TRIGGERS + "\t s:[synthetic/]<event> <field> [<field>]\n" +#endif "\t -:[<group>/]<event>\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS - "\t place: <path>:<offset>\n" + " place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n" #endif "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n" +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + "\t $stack<index>, $stack, $retval, $comm, $arg<N>\n" +#else "\t $stack<index>, $stack, $retval, $comm\n" - "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string,\n" - "\t b<bit-width>@<bit-offset>/<container-size>\n" +#endif + "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n" + "\t b<bit-width>@<bit-offset>/<container-size>,\n" + "\t <type>\\[<array-size>\\]\n" +#ifdef CONFIG_HIST_TRIGGERS + "\t field: <stype> <name>;\n" + "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" + "\t [unsigned] char/int/long\n" +#endif #endif " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" @@ -5392,7 +5414,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (tr->current_trace->reset) tr->current_trace->reset(tr); - /* Current trace needs to be nop_trace before synchronize_sched */ + /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; #ifdef CONFIG_TRACER_MAX_TRACE @@ -5406,7 +5428,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) * The update_max_tr is called from interrupts disabled * so a synchronized_sched() is sufficient. */ - synchronize_sched(); + synchronize_rcu(); free_snapshot(tr); } #endif @@ -5687,7 +5709,7 @@ static int tracing_wait_pipe(struct file *filp) mutex_unlock(&iter->mutex); - ret = wait_on_pipe(iter, false); + ret = wait_on_pipe(iter, 0); mutex_lock(&iter->mutex); @@ -6745,7 +6767,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN; - ret = wait_on_pipe(iter, false); + ret = wait_on_pipe(iter, 0); if (ret) return ret; @@ -6942,7 +6964,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - ret = wait_on_pipe(iter, true); + ret = wait_on_pipe(iter, iter->tr->buffer_percent); if (ret) goto out; @@ -7656,6 +7678,53 @@ static const struct file_operations rb_simple_fops = { .llseek = default_llseek, }; +static ssize_t +buffer_percent_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = tr->buffer_percent; + r = sprintf(buf, "%d\n", r); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +buffer_percent_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (val > 100) + return -EINVAL; + + if (!val) + val = 1; + + tr->buffer_percent = val; + + (*ppos)++; + + return cnt; +} + +static const struct file_operations buffer_percent_fops = { + .open = tracing_open_generic_tr, + .read = buffer_percent_read, + .write = buffer_percent_write, + .release = tracing_release_generic_tr, + .llseek = default_llseek, +}; + struct dentry *trace_instance_dir; static void @@ -7964,6 +8033,11 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("timestamp_mode", 0444, d_tracer, tr, &trace_time_stamp_mode_fops); + tr->buffer_percent = 50; + + trace_create_file("buffer_percent", 0444, d_tracer, + tr, &buffer_percent_fops); + create_trace_options_dir(tr); #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3b8c0e24ab30..08900828d282 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -247,6 +247,7 @@ struct trace_array { int clock_id; int nr_topts; bool clear_trace; + int buffer_percent; struct tracer *current_trace; unsigned int trace_flags; unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE]; @@ -512,12 +513,51 @@ enum { * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, + + /* + * To implement set_graph_notrace, if this bit is set, we ignore + * function graph tracing of called functions, until the return + * function is called to clear it. + */ + TRACE_GRAPH_NOTRACE_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -823,7 +863,12 @@ static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash) #define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT) extern void ftrace_graph_sleep_time_control(bool enable); + +#ifdef CONFIG_FUNCTION_PROFILER extern void ftrace_graph_graph_time_control(bool enable); +#else +static inline void ftrace_graph_graph_time_control(bool enable) { } +#endif extern enum print_line_t print_graph_function_flags(struct trace_iterator *iter, u32 flags); @@ -843,8 +888,9 @@ extern void __trace_graph_return(struct trace_array *tr, extern struct ftrace_hash *ftrace_graph_hash; extern struct ftrace_hash *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { + unsigned long addr = trace->func; int ret = 0; preempt_disable_notrace(); @@ -855,6 +901,14 @@ static inline int ftrace_graph_addr(unsigned long addr) } if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + + /* + * This needs to be cleared on the return functions + * when the depth is zero. + */ + trace_recursion_set(TRACE_GRAPH_BIT); + trace_recursion_set_depth(trace->depth); + /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still @@ -872,6 +926,13 @@ out: return ret; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ + if (trace_recursion_test(TRACE_GRAPH_BIT) && + trace->depth == trace_recursion_depth()) + trace_recursion_clear(TRACE_GRAPH_BIT); +} + static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; @@ -885,7 +946,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } @@ -894,6 +955,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; @@ -901,7 +964,8 @@ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ - return !(trace->depth || ftrace_graph_addr(trace->func)) || + return !(trace_recursion_test(TRACE_GRAPH_BIT) || + ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c new file mode 100644 index 000000000000..dd1f43588d70 --- /dev/null +++ b/kernel/trace/trace_dynevent.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic dynamic event control interface + * + * Copyright (C) 2018 Masami Hiramatsu <[email protected]> + */ + +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/tracefs.h> + +#include "trace.h" +#include "trace_dynevent.h" + +static DEFINE_MUTEX(dyn_event_ops_mutex); +static LIST_HEAD(dyn_event_ops_list); + +int dyn_event_register(struct dyn_event_operations *ops) +{ + if (!ops || !ops->create || !ops->show || !ops->is_busy || + !ops->free || !ops->match) + return -EINVAL; + + INIT_LIST_HEAD(&ops->list); + mutex_lock(&dyn_event_ops_mutex); + list_add_tail(&ops->list, &dyn_event_ops_list); + mutex_unlock(&dyn_event_ops_mutex); + return 0; +} + +int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) +{ + struct dyn_event *pos, *n; + char *system = NULL, *event, *p; + int ret = -ENOENT; + + if (argv[0][0] == '-') { + if (argv[0][1] != ':') + return -EINVAL; + event = &argv[0][2]; + } else { + event = strchr(argv[0], ':'); + if (!event) + return -EINVAL; + event++; + } + + p = strchr(event, '/'); + if (p) { + system = event; + event = p + 1; + *p = '\0'; + } + if (event[0] == '\0') + return -EINVAL; + + mutex_lock(&event_mutex); + for_each_dyn_event_safe(pos, n) { + if (type && type != pos->ops) + continue; + if (pos->ops->match(system, event, pos)) { + ret = pos->ops->free(pos); + break; + } + } + mutex_unlock(&event_mutex); + + return ret; +} + +static int create_dyn_event(int argc, char **argv) +{ + struct dyn_event_operations *ops; + int ret; + + if (argv[0][0] == '-' || argv[0][0] == '!') + return dyn_event_release(argc, argv, NULL); + + mutex_lock(&dyn_event_ops_mutex); + list_for_each_entry(ops, &dyn_event_ops_list, list) { + ret = ops->create(argc, (const char **)argv); + if (!ret || ret != -ECANCELED) + break; + } + mutex_unlock(&dyn_event_ops_mutex); + if (ret == -ECANCELED) + ret = -EINVAL; + + return ret; +} + +/* Protected by event_mutex */ +LIST_HEAD(dyn_event_list); + +void *dyn_event_seq_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&event_mutex); + return seq_list_start(&dyn_event_list, *pos); +} + +void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + return seq_list_next(v, &dyn_event_list, pos); +} + +void dyn_event_seq_stop(struct seq_file *m, void *v) +{ + mutex_unlock(&event_mutex); +} + +static int dyn_event_seq_show(struct seq_file *m, void *v) +{ + struct dyn_event *ev = v; + + if (ev && ev->ops) + return ev->ops->show(m, ev); + + return 0; +} + +static const struct seq_operations dyn_event_seq_op = { + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, + .show = dyn_event_seq_show +}; + +/* + * dyn_events_release_all - Release all specific events + * @type: the dyn_event_operations * which filters releasing events + * + * This releases all events which ->ops matches @type. If @type is NULL, + * all events are released. + * Return -EBUSY if any of them are in use, and return other errors when + * it failed to free the given event. Except for -EBUSY, event releasing + * process will be aborted at that point and there may be some other + * releasable events on the list. + */ +int dyn_events_release_all(struct dyn_event_operations *type) +{ + struct dyn_event *ev, *tmp; + int ret = 0; + + mutex_lock(&event_mutex); + for_each_dyn_event(ev) { + if (type && ev->ops != type) + continue; + if (ev->ops->is_busy(ev)) { + ret = -EBUSY; + goto out; + } + } + for_each_dyn_event_safe(ev, tmp) { + if (type && ev->ops != type) + continue; + ret = ev->ops->free(ev); + if (ret) + break; + } +out: + mutex_unlock(&event_mutex); + + return ret; +} + +static int dyn_event_open(struct inode *inode, struct file *file) +{ + int ret; + + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + ret = dyn_events_release_all(NULL); + if (ret < 0) + return ret; + } + + return seq_open(file, &dyn_event_seq_op); +} + +static ssize_t dyn_event_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + return trace_parse_run_command(file, buffer, count, ppos, + create_dyn_event); +} + +static const struct file_operations dynamic_events_ops = { + .owner = THIS_MODULE, + .open = dyn_event_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, + .write = dyn_event_write, +}; + +/* Make a tracefs interface for controlling dynamic events */ +static __init int init_dynamic_event(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + if (IS_ERR(d_tracer)) + return 0; + + entry = tracefs_create_file("dynamic_events", 0644, d_tracer, + NULL, &dynamic_events_ops); + + /* Event list interface */ + if (!entry) + pr_warn("Could not create tracefs 'dynamic_events' entry\n"); + + return 0; +} +fs_initcall(init_dynamic_event); diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h new file mode 100644 index 000000000000..8c334064e4d6 --- /dev/null +++ b/kernel/trace/trace_dynevent.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common header file for generic dynamic events. + */ + +#ifndef _TRACE_DYNEVENT_H +#define _TRACE_DYNEVENT_H + +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/seq_file.h> + +#include "trace.h" + +struct dyn_event; + +/** + * struct dyn_event_operations - Methods for each type of dynamic events + * + * These methods must be set for each type, since there is no default method. + * Before using this for dyn_event_init(), it must be registered by + * dyn_event_register(). + * + * @create: Parse and create event method. This is invoked when user passes + * a event definition to dynamic_events interface. This must not destruct + * the arguments and return -ECANCELED if given arguments doesn't match its + * command prefix. + * @show: Showing method. This is invoked when user reads the event definitions + * via dynamic_events interface. + * @is_busy: Check whether given event is busy so that it can not be deleted. + * Return true if it is busy, otherwides false. + * @free: Delete the given event. Return 0 if success, otherwides error. + * @match: Check whether given event and system name match this event. + * Return true if it matches, otherwides false. + * + * Except for @create, these methods are called under holding event_mutex. + */ +struct dyn_event_operations { + struct list_head list; + int (*create)(int argc, const char *argv[]); + int (*show)(struct seq_file *m, struct dyn_event *ev); + bool (*is_busy)(struct dyn_event *ev); + int (*free)(struct dyn_event *ev); + bool (*match)(const char *system, const char *event, + struct dyn_event *ev); +}; + +/* Register new dyn_event type -- must be called at first */ +int dyn_event_register(struct dyn_event_operations *ops); + +/** + * struct dyn_event - Dynamic event list header + * + * The dyn_event structure encapsulates a list and a pointer to the operators + * for making a global list of dynamic events. + * User must includes this in each event structure, so that those events can + * be added/removed via dynamic_events interface. + */ +struct dyn_event { + struct list_head list; + struct dyn_event_operations *ops; +}; + +extern struct list_head dyn_event_list; + +static inline +int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops) +{ + if (!ev || !ops) + return -EINVAL; + + INIT_LIST_HEAD(&ev->list); + ev->ops = ops; + return 0; +} + +static inline int dyn_event_add(struct dyn_event *ev) +{ + lockdep_assert_held(&event_mutex); + + if (!ev || !ev->ops) + return -EINVAL; + + list_add_tail(&ev->list, &dyn_event_list); + return 0; +} + +static inline void dyn_event_remove(struct dyn_event *ev) +{ + lockdep_assert_held(&event_mutex); + list_del_init(&ev->list); +} + +void *dyn_event_seq_start(struct seq_file *m, loff_t *pos); +void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos); +void dyn_event_seq_stop(struct seq_file *m, void *v); +int dyn_events_release_all(struct dyn_event_operations *type); +int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type); + +/* + * for_each_dyn_event - iterate over the dyn_event list + * @pos: the struct dyn_event * to use as a loop cursor + * + * This is just a basement of for_each macro. Wrap this for + * each actual event structure with ops filtering. + */ +#define for_each_dyn_event(pos) \ + list_for_each_entry(pos, &dyn_event_list, list) + +/* + * for_each_dyn_event - iterate over the dyn_event list safely + * @pos: the struct dyn_event * to use as a loop cursor + * @n: the struct dyn_event * to use as temporary storage + */ +#define for_each_dyn_event_safe(pos, n) \ + list_for_each_entry_safe(pos, n, &dyn_event_list, list) + +#endif diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 69a3fe926e8c..76217bbef815 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -290,7 +290,8 @@ void perf_kprobe_destroy(struct perf_event *p_event) #endif /* CONFIG_KPROBE_EVENTS */ #ifdef CONFIG_UPROBE_EVENTS -int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe) +int perf_uprobe_init(struct perf_event *p_event, + unsigned long ref_ctr_offset, bool is_retprobe) { int ret; char *path = NULL; @@ -312,8 +313,8 @@ int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe) goto out; } - tp_event = create_local_trace_uprobe( - path, p_event->attr.probe_offset, is_retprobe); + tp_event = create_local_trace_uprobe(path, p_event->attr.probe_offset, + ref_ctr_offset, is_retprobe); if (IS_ERR(tp_event)) { ret = PTR_ERR(tp_event); goto out; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f94be0c2827b..5b3b0c3c8a47 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1251,7 +1251,7 @@ static int f_show(struct seq_file *m, void *v) */ array_descriptor = strchr(field->type, '['); - if (!strncmp(field->type, "__data_loc", 10)) + if (str_has_prefix(field->type, "__data_loc")) array_descriptor = NULL; if (!array_descriptor) @@ -2309,7 +2309,8 @@ static void __add_event_to_tracers(struct trace_event_call *call); int trace_add_event_call(struct trace_event_call *call) { int ret; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + mutex_lock(&trace_types_lock); ret = __register_event(call, NULL); @@ -2317,7 +2318,6 @@ int trace_add_event_call(struct trace_event_call *call) __add_event_to_tracers(call); mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return ret; } @@ -2371,13 +2371,13 @@ int trace_remove_event_call(struct trace_event_call *call) { int ret; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + mutex_lock(&trace_types_lock); down_write(&trace_event_sem); ret = probe_remove_event_call(call); up_write(&trace_event_sem); mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); return ret; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 84a65173b1e9..217ef481fbbb 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -570,11 +570,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, } } + kfree(op_stack); + kfree(inverts); return prog; out_free: kfree(op_stack); - kfree(prog_stack); kfree(inverts); + kfree(prog_stack); return ERR_PTR(ret); } @@ -1299,7 +1301,7 @@ static int parse_pred(const char *str, void *data, /* go past the last quote */ i++; - } else if (isdigit(str[i])) { + } else if (isdigit(str[i]) || str[i] == '-') { /* Make sure the field is not a string */ if (is_string_field(field)) { @@ -1312,6 +1314,9 @@ static int parse_pred(const char *str, void *data, goto err_free; } + if (str[i] == '-') + i++; + /* We allow 0xDEADBEEF */ while (isalnum(str[i])) i++; @@ -1614,7 +1619,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, /* * The calls can still be using the old filters. - * Do a synchronize_sched() and to ensure all calls are + * Do a synchronize_rcu() and to ensure all calls are * done with them before we free them. */ tracepoint_synchronize_unregister(); @@ -1718,6 +1723,7 @@ static int create_filter(struct trace_event_call *call, err = process_preds(call, filter_string, *filterp, pe); if (err && set_str) append_filter_err(pe, *filterp); + create_filter_finish(pe); return err; } @@ -1845,7 +1851,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, if (filter) { /* * No event actually uses the system filter - * we can free it without synchronize_sched(). + * we can free it without synchronize_rcu(). */ __free_filter(system->filter); system->filter = filter; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index d239004aaf29..449d90cfa151 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -15,6 +15,7 @@ #include "tracing_map.h" #include "trace.h" +#include "trace_dynevent.h" #define SYNTH_SYSTEM "synthetic" #define SYNTH_FIELDS_MAX 16 @@ -39,6 +40,16 @@ enum field_op_id { FIELD_OP_UNARY_MINUS, }; +/* + * A hist_var (histogram variable) contains variable information for + * hist_fields having the HIST_FIELD_FL_VAR or HIST_FIELD_FL_VAR_REF + * flag set. A hist_var has a variable name e.g. ts0, and is + * associated with a given histogram trigger, as specified by + * hist_data. The hist_var idx is the unique index assigned to the + * variable by the hist trigger's tracing_map. The idx is what is + * used to set a variable's value and, by a variable reference, to + * retrieve it. + */ struct hist_var { char *name; struct hist_trigger_data *hist_data; @@ -55,12 +66,29 @@ struct hist_field { const char *type; struct hist_field *operands[HIST_FIELD_OPERANDS_MAX]; struct hist_trigger_data *hist_data; + + /* + * Variable fields contain variable-specific info in var. + */ struct hist_var var; enum field_op_id operator; char *system; char *event_name; + + /* + * The name field is used for EXPR and VAR_REF fields. VAR + * fields contain the variable name in var.name. + */ char *name; - unsigned int var_idx; + + /* + * When a histogram trigger is hit, if it has any references + * to variables, the values of those variables are collected + * into a var_ref_vals array by resolve_var_refs(). The + * current value of each variable is read from the tracing_map + * using the hist field's hist_var.idx and entered into the + * var_ref_idx entry i.e. var_ref_vals[var_ref_idx]. + */ unsigned int var_ref_idx; bool read_once; }; @@ -279,8 +307,6 @@ struct hist_trigger_data { struct action_data *actions[HIST_ACTIONS_MAX]; unsigned int n_actions; - struct hist_field *synth_var_refs[SYNTH_FIELDS_MAX]; - unsigned int n_synth_var_refs; struct field_var *field_vars[SYNTH_FIELDS_MAX]; unsigned int n_field_vars; unsigned int n_field_var_str; @@ -292,6 +318,21 @@ struct hist_trigger_data { unsigned int n_max_var_str; }; +static int synth_event_create(int argc, const char **argv); +static int synth_event_show(struct seq_file *m, struct dyn_event *ev); +static int synth_event_release(struct dyn_event *ev); +static bool synth_event_is_busy(struct dyn_event *ev); +static bool synth_event_match(const char *system, const char *event, + struct dyn_event *ev); + +static struct dyn_event_operations synth_event_ops = { + .create = synth_event_create, + .show = synth_event_show, + .is_busy = synth_event_is_busy, + .free = synth_event_release, + .match = synth_event_match, +}; + struct synth_field { char *type; char *name; @@ -301,7 +342,7 @@ struct synth_field { }; struct synth_event { - struct list_head list; + struct dyn_event devent; int ref; char *name; struct synth_field **fields; @@ -312,6 +353,32 @@ struct synth_event { struct tracepoint *tp; }; +static bool is_synth_event(struct dyn_event *ev) +{ + return ev->ops == &synth_event_ops; +} + +static struct synth_event *to_synth_event(struct dyn_event *ev) +{ + return container_of(ev, struct synth_event, devent); +} + +static bool synth_event_is_busy(struct dyn_event *ev) +{ + struct synth_event *event = to_synth_event(ev); + + return event->ref != 0; +} + +static bool synth_event_match(const char *system, const char *event, + struct dyn_event *ev) +{ + struct synth_event *sev = to_synth_event(ev); + + return strcmp(sev->name, event) == 0 && + (!system || strcmp(system, SYNTH_SYSTEM) == 0); +} + struct action_data; typedef void (*action_fn_t) (struct hist_trigger_data *hist_data, @@ -326,6 +393,14 @@ struct action_data { union { struct { + /* + * When a histogram trigger is hit, the values of any + * references to variables, including variables being passed + * as parameters to synthetic events, are collected into a + * var_ref_vals array. This var_ref_idx is the index of the + * first param in the array to be passed to the synthetic + * event invocation. + */ unsigned int var_ref_idx; char *match_event; char *match_event_system; @@ -402,9 +477,6 @@ static bool have_hist_err(void) return false; } -static LIST_HEAD(synth_event_list); -static DEFINE_MUTEX(synth_event_mutex); - struct synth_trace_event { struct trace_entry ent; u64 fields[]; @@ -446,7 +518,7 @@ static int synth_event_define_fields(struct trace_event_call *call) static bool synth_field_signed(char *type) { - if (strncmp(type, "u", 1) == 0) + if (str_has_prefix(type, "u")) return false; return true; @@ -469,7 +541,7 @@ static int synth_field_string_size(char *type) start = strstr(type, "char["); if (start == NULL) return -EINVAL; - start += strlen("char["); + start += sizeof("char[") - 1; end = strchr(type, ']'); if (!end || end < start) @@ -738,14 +810,12 @@ static void free_synth_field(struct synth_field *field) kfree(field); } -static struct synth_field *parse_synth_field(int argc, char **argv, +static struct synth_field *parse_synth_field(int argc, const char **argv, int *consumed) { struct synth_field *field; - const char *prefix = NULL; - char *field_type = argv[0], *field_name; + const char *prefix = NULL, *field_type = argv[0], *field_name, *array; int len, ret = 0; - char *array; if (field_type[0] == ';') field_type++; @@ -762,20 +832,31 @@ static struct synth_field *parse_synth_field(int argc, char **argv, *consumed = 2; } - len = strlen(field_name); - if (field_name[len - 1] == ';') - field_name[len - 1] = '\0'; - field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) return ERR_PTR(-ENOMEM); - len = strlen(field_type) + 1; + len = strlen(field_name); array = strchr(field_name, '['); if (array) + len -= strlen(array); + else if (field_name[len - 1] == ';') + len--; + + field->name = kmemdup_nul(field_name, len, GFP_KERNEL); + if (!field->name) { + ret = -ENOMEM; + goto free; + } + + if (field_type[0] == ';') + field_type++; + len = strlen(field_type) + 1; + if (array) len += strlen(array); if (prefix) len += strlen(prefix); + field->type = kzalloc(len, GFP_KERNEL); if (!field->type) { ret = -ENOMEM; @@ -786,7 +867,8 @@ static struct synth_field *parse_synth_field(int argc, char **argv, strcat(field->type, field_type); if (array) { strcat(field->type, array); - *array = '\0'; + if (field->type[len - 1] == ';') + field->type[len - 1] = '\0'; } field->size = synth_field_size(field->type); @@ -800,11 +882,6 @@ static struct synth_field *parse_synth_field(int argc, char **argv, field->is_signed = synth_field_signed(field->type); - field->name = kstrdup(field_name, GFP_KERNEL); - if (!field->name) { - ret = -ENOMEM; - goto free; - } out: return field; free: @@ -868,9 +945,13 @@ static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals, static struct synth_event *find_synth_event(const char *name) { + struct dyn_event *pos; struct synth_event *event; - list_for_each_entry(event, &synth_event_list, list) { + for_each_dyn_event(pos) { + if (!is_synth_event(pos)) + continue; + event = to_synth_event(pos); if (strcmp(event->name, name) == 0) return event; } @@ -959,7 +1040,7 @@ static void free_synth_event(struct synth_event *event) kfree(event); } -static struct synth_event *alloc_synth_event(char *event_name, int n_fields, +static struct synth_event *alloc_synth_event(const char *name, int n_fields, struct synth_field **fields) { struct synth_event *event; @@ -971,7 +1052,7 @@ static struct synth_event *alloc_synth_event(char *event_name, int n_fields, goto out; } - event->name = kstrdup(event_name, GFP_KERNEL); + event->name = kstrdup(name, GFP_KERNEL); if (!event->name) { kfree(event); event = ERR_PTR(-ENOMEM); @@ -985,6 +1066,8 @@ static struct synth_event *alloc_synth_event(char *event_name, int n_fields, goto out; } + dyn_event_init(&event->devent, &synth_event_ops); + for (i = 0; i < n_fields; i++) event->fields[i] = fields[i]; @@ -1008,29 +1091,11 @@ struct hist_var_data { struct hist_trigger_data *hist_data; }; -static void add_or_delete_synth_event(struct synth_event *event, int delete) -{ - if (delete) - free_synth_event(event); - else { - mutex_lock(&synth_event_mutex); - if (!find_synth_event(event->name)) - list_add(&event->list, &synth_event_list); - else - free_synth_event(event); - mutex_unlock(&synth_event_mutex); - } -} - -static int create_synth_event(int argc, char **argv) +static int __create_synth_event(int argc, const char *name, const char **argv) { struct synth_field *field, *fields[SYNTH_FIELDS_MAX]; struct synth_event *event = NULL; - bool delete_event = false; int i, consumed = 0, n_fields = 0, ret = 0; - char *name; - - mutex_lock(&synth_event_mutex); /* * Argument syntax: @@ -1038,40 +1103,19 @@ static int create_synth_event(int argc, char **argv) * - Remove synthetic event: !<event_name> field[;field] ... * where 'field' = type field_name */ - if (argc < 1) { - ret = -EINVAL; - goto out; - } - name = argv[0]; - if (name[0] == '!') { - delete_event = true; - name++; - } + if (name[0] == '\0' || argc < 1) + return -EINVAL; + + mutex_lock(&event_mutex); event = find_synth_event(name); if (event) { - if (delete_event) { - if (event->ref) { - event = NULL; - ret = -EBUSY; - goto out; - } - list_del(&event->list); - goto out; - } - event = NULL; ret = -EEXIST; goto out; - } else if (delete_event) - goto out; - - if (argc < 2) { - ret = -EINVAL; - goto out; } - for (i = 1; i < argc - 1; i++) { + for (i = 0; i < argc - 1; i++) { if (strcmp(argv[i], ";") == 0) continue; if (n_fields == SYNTH_FIELDS_MAX) { @@ -1099,83 +1143,91 @@ static int create_synth_event(int argc, char **argv) event = NULL; goto err; } + ret = register_synth_event(event); + if (!ret) + dyn_event_add(&event->devent); + else + free_synth_event(event); out: - mutex_unlock(&synth_event_mutex); - - if (event) { - if (delete_event) { - ret = unregister_synth_event(event); - add_or_delete_synth_event(event, !ret); - } else { - ret = register_synth_event(event); - add_or_delete_synth_event(event, ret); - } - } + mutex_unlock(&event_mutex); return ret; err: - mutex_unlock(&synth_event_mutex); - for (i = 0; i < n_fields; i++) free_synth_field(fields[i]); - free_synth_event(event); - return ret; + goto out; } -static int release_all_synth_events(void) +static int create_or_delete_synth_event(int argc, char **argv) { - struct list_head release_events; - struct synth_event *event, *e; - int ret = 0; - - INIT_LIST_HEAD(&release_events); - - mutex_lock(&synth_event_mutex); + const char *name = argv[0]; + struct synth_event *event = NULL; + int ret; - list_for_each_entry(event, &synth_event_list, list) { - if (event->ref) { - mutex_unlock(&synth_event_mutex); - return -EBUSY; - } + /* trace_run_command() ensures argc != 0 */ + if (name[0] == '!') { + mutex_lock(&event_mutex); + event = find_synth_event(name + 1); + if (event) { + if (event->ref) + ret = -EBUSY; + else { + ret = unregister_synth_event(event); + if (!ret) { + dyn_event_remove(&event->devent); + free_synth_event(event); + } + } + } else + ret = -ENOENT; + mutex_unlock(&event_mutex); + return ret; } - list_splice_init(&event->list, &release_events); + ret = __create_synth_event(argc - 1, name, (const char **)argv + 1); + return ret == -ECANCELED ? -EINVAL : ret; +} - mutex_unlock(&synth_event_mutex); +static int synth_event_create(int argc, const char **argv) +{ + const char *name = argv[0]; + int len; - list_for_each_entry_safe(event, e, &release_events, list) { - list_del(&event->list); + if (name[0] != 's' || name[1] != ':') + return -ECANCELED; + name += 2; - ret = unregister_synth_event(event); - add_or_delete_synth_event(event, !ret); + /* This interface accepts group name prefix */ + if (strchr(name, '/')) { + len = sizeof(SYNTH_SYSTEM "/") - 1; + if (strncmp(name, SYNTH_SYSTEM "/", len)) + return -EINVAL; + name += len; } - - return ret; + return __create_synth_event(argc - 1, name, argv + 1); } - -static void *synth_events_seq_start(struct seq_file *m, loff_t *pos) +static int synth_event_release(struct dyn_event *ev) { - mutex_lock(&synth_event_mutex); + struct synth_event *event = to_synth_event(ev); + int ret; - return seq_list_start(&synth_event_list, *pos); -} + if (event->ref) + return -EBUSY; -static void *synth_events_seq_next(struct seq_file *m, void *v, loff_t *pos) -{ - return seq_list_next(v, &synth_event_list, pos); -} + ret = unregister_synth_event(event); + if (ret) + return ret; -static void synth_events_seq_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&synth_event_mutex); + dyn_event_remove(ev); + free_synth_event(event); + return 0; } -static int synth_events_seq_show(struct seq_file *m, void *v) +static int __synth_event_show(struct seq_file *m, struct synth_event *event) { struct synth_field *field; - struct synth_event *event = v; unsigned int i; seq_printf(m, "%s\t", event->name); @@ -1193,11 +1245,30 @@ static int synth_events_seq_show(struct seq_file *m, void *v) return 0; } +static int synth_event_show(struct seq_file *m, struct dyn_event *ev) +{ + struct synth_event *event = to_synth_event(ev); + + seq_printf(m, "s:%s/", event->class.system); + + return __synth_event_show(m, event); +} + +static int synth_events_seq_show(struct seq_file *m, void *v) +{ + struct dyn_event *ev = v; + + if (!is_synth_event(ev)) + return 0; + + return __synth_event_show(m, to_synth_event(ev)); +} + static const struct seq_operations synth_events_seq_op = { - .start = synth_events_seq_start, - .next = synth_events_seq_next, - .stop = synth_events_seq_stop, - .show = synth_events_seq_show + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, + .show = synth_events_seq_show, }; static int synth_events_open(struct inode *inode, struct file *file) @@ -1205,7 +1276,7 @@ static int synth_events_open(struct inode *inode, struct file *file) int ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - ret = release_all_synth_events(); + ret = dyn_events_release_all(&synth_event_ops); if (ret < 0) return ret; } @@ -1218,7 +1289,7 @@ static ssize_t synth_events_write(struct file *file, size_t count, loff_t *ppos) { return trace_parse_run_command(file, buffer, count, ppos, - create_synth_event); + create_or_delete_synth_event); } static const struct file_operations synth_events_fops = { @@ -1255,82 +1326,73 @@ static u64 hist_field_cpu(struct hist_field *hist_field, return cpu; } +/** + * check_field_for_var_ref - Check if a VAR_REF field references a variable + * @hist_field: The VAR_REF field to check + * @var_data: The hist trigger that owns the variable + * @var_idx: The trigger variable identifier + * + * Check the given VAR_REF field to see whether or not it references + * the given variable associated with the given trigger. + * + * Return: The VAR_REF field if it does reference the variable, NULL if not + */ static struct hist_field * check_field_for_var_ref(struct hist_field *hist_field, struct hist_trigger_data *var_data, unsigned int var_idx) { - struct hist_field *found = NULL; - - if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF) { - if (hist_field->var.idx == var_idx && - hist_field->var.hist_data == var_data) { - found = hist_field; - } - } - - return found; -} - -static struct hist_field * -check_field_for_var_refs(struct hist_trigger_data *hist_data, - struct hist_field *hist_field, - struct hist_trigger_data *var_data, - unsigned int var_idx, - unsigned int level) -{ - struct hist_field *found = NULL; - unsigned int i; + WARN_ON(!(hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF)); - if (level > 3) - return found; - - if (!hist_field) - return found; - - found = check_field_for_var_ref(hist_field, var_data, var_idx); - if (found) - return found; - - for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) { - struct hist_field *operand; - - operand = hist_field->operands[i]; - found = check_field_for_var_refs(hist_data, operand, var_data, - var_idx, level + 1); - if (found) - return found; - } + if (hist_field && hist_field->var.idx == var_idx && + hist_field->var.hist_data == var_data) + return hist_field; - return found; + return NULL; } +/** + * find_var_ref - Check if a trigger has a reference to a trigger variable + * @hist_data: The hist trigger that might have a reference to the variable + * @var_data: The hist trigger that owns the variable + * @var_idx: The trigger variable identifier + * + * Check the list of var_refs[] on the first hist trigger to see + * whether any of them are references to the variable on the second + * trigger. + * + * Return: The VAR_REF field referencing the variable if so, NULL if not + */ static struct hist_field *find_var_ref(struct hist_trigger_data *hist_data, struct hist_trigger_data *var_data, unsigned int var_idx) { - struct hist_field *hist_field, *found = NULL; + struct hist_field *hist_field; unsigned int i; - for_each_hist_field(i, hist_data) { - hist_field = hist_data->fields[i]; - found = check_field_for_var_refs(hist_data, hist_field, - var_data, var_idx, 0); - if (found) - return found; - } - - for (i = 0; i < hist_data->n_synth_var_refs; i++) { - hist_field = hist_data->synth_var_refs[i]; - found = check_field_for_var_refs(hist_data, hist_field, - var_data, var_idx, 0); - if (found) - return found; + for (i = 0; i < hist_data->n_var_refs; i++) { + hist_field = hist_data->var_refs[i]; + if (check_field_for_var_ref(hist_field, var_data, var_idx)) + return hist_field; } - return found; + return NULL; } +/** + * find_any_var_ref - Check if there is a reference to a given trigger variable + * @hist_data: The hist trigger + * @var_idx: The trigger variable identifier + * + * Check to see whether the given variable is currently referenced by + * any other trigger. + * + * The trigger the variable is defined on is explicitly excluded - the + * assumption being that a self-reference doesn't prevent a trigger + * from being removed. + * + * Return: The VAR_REF field referencing the variable if so, NULL if not + */ static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data, unsigned int var_idx) { @@ -1349,6 +1411,19 @@ static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data, return found; } +/** + * check_var_refs - Check if there is a reference to any of trigger's variables + * @hist_data: The hist trigger + * + * A trigger can define one or more variables. If any one of them is + * currently referenced by any other trigger, this function will + * determine that. + + * Typically used to determine whether or not a trigger can be removed + * - if there are any references to a trigger's variables, it cannot. + * + * Return: True if there is a reference to any of trigger's variables + */ static bool check_var_refs(struct hist_trigger_data *hist_data) { struct hist_field *field; @@ -1806,8 +1881,8 @@ static int parse_action(char *str, struct hist_trigger_attrs *attrs) if (attrs->n_actions >= HIST_ACTIONS_MAX) return ret; - if ((strncmp(str, "onmatch(", strlen("onmatch(")) == 0) || - (strncmp(str, "onmax(", strlen("onmax(")) == 0)) { + if ((str_has_prefix(str, "onmatch(")) || + (str_has_prefix(str, "onmax("))) { attrs->action_str[attrs->n_actions] = kstrdup(str, GFP_KERNEL); if (!attrs->action_str[attrs->n_actions]) { ret = -ENOMEM; @@ -1824,34 +1899,34 @@ static int parse_assignment(char *str, struct hist_trigger_attrs *attrs) { int ret = 0; - if ((strncmp(str, "key=", strlen("key=")) == 0) || - (strncmp(str, "keys=", strlen("keys=")) == 0)) { + if ((str_has_prefix(str, "key=")) || + (str_has_prefix(str, "keys="))) { attrs->keys_str = kstrdup(str, GFP_KERNEL); if (!attrs->keys_str) { ret = -ENOMEM; goto out; } - } else if ((strncmp(str, "val=", strlen("val=")) == 0) || - (strncmp(str, "vals=", strlen("vals=")) == 0) || - (strncmp(str, "values=", strlen("values=")) == 0)) { + } else if ((str_has_prefix(str, "val=")) || + (str_has_prefix(str, "vals=")) || + (str_has_prefix(str, "values="))) { attrs->vals_str = kstrdup(str, GFP_KERNEL); if (!attrs->vals_str) { ret = -ENOMEM; goto out; } - } else if (strncmp(str, "sort=", strlen("sort=")) == 0) { + } else if (str_has_prefix(str, "sort=")) { attrs->sort_key_str = kstrdup(str, GFP_KERNEL); if (!attrs->sort_key_str) { ret = -ENOMEM; goto out; } - } else if (strncmp(str, "name=", strlen("name=")) == 0) { + } else if (str_has_prefix(str, "name=")) { attrs->name = kstrdup(str, GFP_KERNEL); if (!attrs->name) { ret = -ENOMEM; goto out; } - } else if (strncmp(str, "clock=", strlen("clock=")) == 0) { + } else if (str_has_prefix(str, "clock=")) { strsep(&str, "="); if (!str) { ret = -EINVAL; @@ -1864,7 +1939,7 @@ static int parse_assignment(char *str, struct hist_trigger_attrs *attrs) ret = -ENOMEM; goto out; } - } else if (strncmp(str, "size=", strlen("size=")) == 0) { + } else if (str_has_prefix(str, "size=")) { int map_bits = parse_map_size(str); if (map_bits < 0) { @@ -2149,6 +2224,15 @@ static int contains_operator(char *str) return field_op; } +static void __destroy_hist_field(struct hist_field *hist_field) +{ + kfree(hist_field->var.name); + kfree(hist_field->name); + kfree(hist_field->type); + + kfree(hist_field); +} + static void destroy_hist_field(struct hist_field *hist_field, unsigned int level) { @@ -2160,14 +2244,13 @@ static void destroy_hist_field(struct hist_field *hist_field, if (!hist_field) return; + if (hist_field->flags & HIST_FIELD_FL_VAR_REF) + return; /* var refs will be destroyed separately */ + for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) destroy_hist_field(hist_field->operands[i], level + 1); - kfree(hist_field->var.name); - kfree(hist_field->name); - kfree(hist_field->type); - - kfree(hist_field); + __destroy_hist_field(hist_field); } static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, @@ -2294,6 +2377,12 @@ static void destroy_hist_fields(struct hist_trigger_data *hist_data) hist_data->fields[i] = NULL; } } + + for (i = 0; i < hist_data->n_var_refs; i++) { + WARN_ON(!(hist_data->var_refs[i]->flags & HIST_FIELD_FL_VAR_REF)); + __destroy_hist_field(hist_data->var_refs[i]); + hist_data->var_refs[i] = NULL; + } } static int init_var_ref(struct hist_field *ref_field, @@ -2352,7 +2441,23 @@ static int init_var_ref(struct hist_field *ref_field, goto out; } -static struct hist_field *create_var_ref(struct hist_field *var_field, +/** + * create_var_ref - Create a variable reference and attach it to trigger + * @hist_data: The trigger that will be referencing the variable + * @var_field: The VAR field to create a reference to + * @system: The optional system string + * @event_name: The optional event_name string + * + * Given a variable hist_field, create a VAR_REF hist_field that + * represents a reference to it. + * + * This function also adds the reference to the trigger that + * now references the variable. + * + * Return: The VAR_REF field if successful, NULL if not + */ +static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, + struct hist_field *var_field, char *system, char *event_name) { unsigned long flags = HIST_FIELD_FL_VAR_REF; @@ -2364,6 +2469,9 @@ static struct hist_field *create_var_ref(struct hist_field *var_field, destroy_hist_field(ref_field, 0); return NULL; } + + hist_data->var_refs[hist_data->n_var_refs] = ref_field; + ref_field->var_ref_idx = hist_data->n_var_refs++; } return ref_field; @@ -2437,7 +2545,8 @@ static struct hist_field *parse_var_ref(struct hist_trigger_data *hist_data, var_field = find_event_var(hist_data, system, event_name, var_name); if (var_field) - ref_field = create_var_ref(var_field, system, event_name); + ref_field = create_var_ref(hist_data, var_field, + system, event_name); if (!ref_field) hist_err_event("Couldn't find variable: $", @@ -2555,8 +2664,6 @@ static struct hist_field *parse_atom(struct hist_trigger_data *hist_data, if (!s) { hist_field = parse_var_ref(hist_data, ref_system, ref_event, ref_var); if (hist_field) { - hist_data->var_refs[hist_data->n_var_refs] = hist_field; - hist_field->var_ref_idx = hist_data->n_var_refs++; if (var_name) { hist_field = create_alias(hist_data, hist_field, var_name); if (!hist_field) { @@ -3330,7 +3437,6 @@ static int onmax_create(struct hist_trigger_data *hist_data, unsigned int var_ref_idx = hist_data->n_var_refs; struct field_var *field_var; char *onmax_var_str, *param; - unsigned long flags; unsigned int i; int ret = 0; @@ -3347,18 +3453,10 @@ static int onmax_create(struct hist_trigger_data *hist_data, return -EINVAL; } - flags = HIST_FIELD_FL_VAR_REF; - ref_field = create_hist_field(hist_data, NULL, flags, NULL); + ref_field = create_var_ref(hist_data, var_field, NULL, NULL); if (!ref_field) return -ENOMEM; - if (init_var_ref(ref_field, var_field, NULL, NULL)) { - destroy_hist_field(ref_field, 0); - ret = -ENOMEM; - goto out; - } - hist_data->var_refs[hist_data->n_var_refs] = ref_field; - ref_field->var_ref_idx = hist_data->n_var_refs++; data->onmax.var = ref_field; data->fn = onmax_save; @@ -3460,7 +3558,7 @@ static struct action_data *onmax_parse(char *str) if (!onmax_fn_name || !str) goto free; - if (strncmp(onmax_fn_name, "save", strlen("save")) == 0) { + if (str_has_prefix(onmax_fn_name, "save")) { char *params = strsep(&str, ")"); if (!params) { @@ -3491,7 +3589,7 @@ static void onmatch_destroy(struct action_data *data) { unsigned int i; - mutex_lock(&synth_event_mutex); + lockdep_assert_held(&event_mutex); kfree(data->onmatch.match_event); kfree(data->onmatch.match_event_system); @@ -3504,8 +3602,6 @@ static void onmatch_destroy(struct action_data *data) data->onmatch.synth_event->ref--; kfree(data); - - mutex_unlock(&synth_event_mutex); } static void destroy_field_var(struct field_var *field_var) @@ -3537,23 +3633,6 @@ static void save_field_var(struct hist_trigger_data *hist_data, } -static void destroy_synth_var_refs(struct hist_trigger_data *hist_data) -{ - unsigned int i; - - for (i = 0; i < hist_data->n_synth_var_refs; i++) - destroy_hist_field(hist_data->synth_var_refs[i], 0); -} - -static void save_synth_var_ref(struct hist_trigger_data *hist_data, - struct hist_field *var_ref) -{ - hist_data->synth_var_refs[hist_data->n_synth_var_refs++] = var_ref; - - hist_data->var_refs[hist_data->n_var_refs] = var_ref; - var_ref->var_ref_idx = hist_data->n_var_refs++; -} - static int check_synth_field(struct synth_event *event, struct hist_field *hist_field, unsigned int field_pos) @@ -3656,15 +3735,14 @@ static int onmatch_create(struct hist_trigger_data *hist_data, struct synth_event *event; int ret = 0; - mutex_lock(&synth_event_mutex); + lockdep_assert_held(&event_mutex); + event = find_synth_event(data->onmatch.synth_event_name); if (!event) { hist_err("onmatch: Couldn't find synthetic event: ", data->onmatch.synth_event_name); - mutex_unlock(&synth_event_mutex); return -EINVAL; } event->ref++; - mutex_unlock(&synth_event_mutex); var_ref_idx = hist_data->n_var_refs; @@ -3706,14 +3784,14 @@ static int onmatch_create(struct hist_trigger_data *hist_data, } if (check_synth_field(event, hist_field, field_pos) == 0) { - var_ref = create_var_ref(hist_field, system, event_name); + var_ref = create_var_ref(hist_data, hist_field, + system, event_name); if (!var_ref) { kfree(p); ret = -ENOMEM; goto err; } - save_synth_var_ref(hist_data, var_ref); field_pos++; kfree(p); continue; @@ -3738,9 +3816,7 @@ static int onmatch_create(struct hist_trigger_data *hist_data, out: return ret; err: - mutex_lock(&synth_event_mutex); event->ref--; - mutex_unlock(&synth_event_mutex); goto out; } @@ -4266,12 +4342,13 @@ static int parse_actions(struct hist_trigger_data *hist_data) unsigned int i; int ret = 0; char *str; + int len; for (i = 0; i < hist_data->attrs->n_actions; i++) { str = hist_data->attrs->action_str[i]; - if (strncmp(str, "onmatch(", strlen("onmatch(")) == 0) { - char *action_str = str + strlen("onmatch("); + if ((len = str_has_prefix(str, "onmatch("))) { + char *action_str = str + len; data = onmatch_parse(tr, action_str); if (IS_ERR(data)) { @@ -4279,8 +4356,8 @@ static int parse_actions(struct hist_trigger_data *hist_data) break; } data->fn = action_trace; - } else if (strncmp(str, "onmax(", strlen("onmax(")) == 0) { - char *action_str = str + strlen("onmax("); + } else if ((len = str_has_prefix(str, "onmax("))) { + char *action_str = str + len; data = onmax_parse(action_str); if (IS_ERR(data)) { @@ -4459,7 +4536,6 @@ static void destroy_hist_data(struct hist_trigger_data *hist_data) destroy_actions(hist_data); destroy_field_vars(hist_data); destroy_field_var_hists(hist_data); - destroy_synth_var_refs(hist_data); kfree(hist_data); } @@ -5448,6 +5524,8 @@ static void hist_unreg_all(struct trace_event_file *file) struct synth_event *se; const char *se_name; + lockdep_assert_held(&event_mutex); + if (hist_file_check_refs(file)) return; @@ -5457,12 +5535,10 @@ static void hist_unreg_all(struct trace_event_file *file) list_del_rcu(&test->list); trace_event_trigger_enable_disable(file, 0); - mutex_lock(&synth_event_mutex); se_name = trace_event_name(file->event_call); se = find_synth_event(se_name); if (se) se->ref--; - mutex_unlock(&synth_event_mutex); update_cond_flag(file); if (hist_data->enable_timestamps) @@ -5488,6 +5564,8 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, char *trigger, *p; int ret = 0; + lockdep_assert_held(&event_mutex); + if (glob && strlen(glob)) { last_cmd_set(param); hist_err_clear(); @@ -5514,9 +5592,9 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, p++; continue; } - if (p >= param + strlen(param) - strlen("if") - 1) + if (p >= param + strlen(param) - (sizeof("if") - 1) - 1) return -EINVAL; - if (*(p + strlen("if")) != ' ' && *(p + strlen("if")) != '\t') { + if (*(p + sizeof("if") - 1) != ' ' && *(p + sizeof("if") - 1) != '\t') { p++; continue; } @@ -5578,14 +5656,10 @@ static int event_hist_trigger_func(struct event_command *cmd_ops, } cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file); - - mutex_lock(&synth_event_mutex); se_name = trace_event_name(file->event_call); se = find_synth_event(se_name); if (se) se->ref--; - mutex_unlock(&synth_event_mutex); - ret = 0; goto out_free; } @@ -5621,13 +5695,10 @@ enable: if (ret) goto out_unreg; - mutex_lock(&synth_event_mutex); se_name = trace_event_name(file->event_call); se = find_synth_event(se_name); if (se) se->ref++; - mutex_unlock(&synth_event_mutex); - /* Just return zero, not the number of registered triggers */ ret = 0; out: @@ -5810,6 +5881,12 @@ static __init int trace_events_hist_init(void) struct dentry *d_tracer; int err = 0; + err = dyn_event_register(&synth_event_ops); + if (err) { + pr_warn("Could not register synth_event_ops\n"); + return err; + } + d_tracer = tracing_init_dentry(); if (IS_ERR(d_tracer)) { err = PTR_ERR(d_tracer); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2152d1e530cb..cd12ecb66eb9 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -732,8 +732,10 @@ int set_trigger_filter(char *filter_str, /* The filter is for the 'trigger' event, not the triggered event */ ret = create_event_filter(file->event_call, filter_str, false, &filter); - if (ret) - goto out; + /* + * If create_event_filter() fails, filter still needs to be freed. + * Which the calling code will do with data->filter. + */ assign: tmp = rcu_access_pointer(data->filter); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..c2af1560e856 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -16,33 +16,6 @@ #include "trace.h" #include "trace_output.h" -static bool kill_ftrace_graph; - -/** - * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called - * - * ftrace_graph_stop() is called when a severe error is detected in - * the function graph tracing. This function is called by the critical - * paths of function graph to keep those paths from doing any more harm. - */ -bool ftrace_graph_is_dead(void) -{ - return kill_ftrace_graph; -} - -/** - * ftrace_graph_stop - set to permanently disable function graph tracincg - * - * In case of an error int function graph tracing, this is called - * to try to keep function graph tracing from causing any more harm. - * Usually this is pretty severe and this is called to try to at least - * get a warning out to the user. - */ -void ftrace_graph_stop(void) -{ - kill_ftrace_graph = true; -} - /* When set, irq functions will be ignored */ static int ftrace_graph_skip_irqs; @@ -87,8 +60,12 @@ static struct tracer_opt trace_opts[] = { { TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) }, /* Include sleep time (scheduled out) between entry and return */ { TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) }, + +#ifdef CONFIG_FUNCTION_PROFILER /* Include time within nested functions */ { TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) }, +#endif + { } /* Empty entry */ }; @@ -117,231 +94,6 @@ static void print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); -/* Add a function return address to the trace stack on thread info.*/ -int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp) -{ - unsigned long long calltime; - int index; - - if (unlikely(ftrace_graph_is_dead())) - return -EBUSY; - - if (!current->ret_stack) - return -EBUSY; - - /* - * We must make sure the ret_stack is tested before we read - * anything else. - */ - smp_rmb(); - - /* The return trace stack is full */ - if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { - atomic_inc(¤t->trace_overrun); - return -EBUSY; - } - - /* - * The curr_ret_stack is an index to ftrace return stack of - * current task. Its value should be in [0, FTRACE_RETFUNC_ - * DEPTH) when the function graph tracer is used. To support - * filtering out specific functions, it makes the index - * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH) - * so when it sees a negative index the ftrace will ignore - * the record. And the index gets recovered when returning - * from the filtered function by adding the FTRACE_NOTRACE_ - * DEPTH and then it'll continue to record functions normally. - * - * The curr_ret_stack is initialized to -1 and get increased - * in this function. So it can be less than -1 only if it was - * filtered out via ftrace_graph_notrace_addr() which can be - * set from set_graph_notrace file in tracefs by user. - */ - if (current->curr_ret_stack < -1) - return -EBUSY; - - calltime = trace_clock_local(); - - index = ++current->curr_ret_stack; - if (ftrace_graph_notrace_addr(func)) - current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH; - barrier(); - current->ret_stack[index].ret = ret; - current->ret_stack[index].func = func; - current->ret_stack[index].calltime = calltime; -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - current->ret_stack[index].fp = frame_pointer; -#endif -#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR - current->ret_stack[index].retp = retp; -#endif - *depth = current->curr_ret_stack; - - return 0; -} - -/* Retrieve a function return address to the trace stack on thread info.*/ -static void -ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, - unsigned long frame_pointer) -{ - int index; - - index = current->curr_ret_stack; - - /* - * A negative index here means that it's just returned from a - * notrace'd function. Recover index to get an original - * return address. See ftrace_push_return_trace(). - * - * TODO: Need to check whether the stack gets corrupted. - */ - if (index < 0) - index += FTRACE_NOTRACE_DEPTH; - - if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic, otherwise we have no where to go */ - *ret = (unsigned long)panic; - return; - } - -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - /* - * The arch may choose to record the frame pointer used - * and check it here to make sure that it is what we expect it - * to be. If gcc does not set the place holder of the return - * address in the frame pointer, and does a copy instead, then - * the function graph trace will fail. This test detects this - * case. - * - * Currently, x86_32 with optimize for size (-Os) makes the latest - * gcc do the above. - * - * Note, -mfentry does not use frame pointers, and this test - * is not needed if CC_USING_FENTRY is set. - */ - if (unlikely(current->ret_stack[index].fp != frame_pointer)) { - ftrace_graph_stop(); - WARN(1, "Bad frame pointer: expected %lx, received %lx\n" - " from func %ps return to %lx\n", - current->ret_stack[index].fp, - frame_pointer, - (void *)current->ret_stack[index].func, - current->ret_stack[index].ret); - *ret = (unsigned long)panic; - return; - } -#endif - - *ret = current->ret_stack[index].ret; - trace->func = current->ret_stack[index].func; - trace->calltime = current->ret_stack[index].calltime; - trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; -} - -/* - * Send the trace to the ring-buffer. - * @return the original return address. - */ -unsigned long ftrace_return_to_handler(unsigned long frame_pointer) -{ - struct ftrace_graph_ret trace; - unsigned long ret; - - ftrace_pop_return_trace(&trace, &ret, frame_pointer); - trace.rettime = trace_clock_local(); - barrier(); - current->curr_ret_stack--; - /* - * The curr_ret_stack can be less than -1 only if it was - * filtered out and it's about to return from the function. - * Recover the index and continue to trace normal functions. - */ - if (current->curr_ret_stack < -1) { - current->curr_ret_stack += FTRACE_NOTRACE_DEPTH; - return ret; - } - - /* - * The trace should run after decrementing the ret counter - * in case an interrupt were to come in. We don't want to - * lose the interrupt if max_depth is set. - */ - ftrace_graph_return(&trace); - - if (unlikely(!ret)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic. What else to do? */ - ret = (unsigned long)panic; - } - - return ret; -} - -/** - * ftrace_graph_ret_addr - convert a potentially modified stack return address - * to its original value - * - * This function can be called by stack unwinding code to convert a found stack - * return address ('ret') to its original value, in case the function graph - * tracer has modified it to be 'return_to_handler'. If the address hasn't - * been modified, the unchanged value of 'ret' is returned. - * - * 'idx' is a state variable which should be initialized by the caller to zero - * before the first call. - * - * 'retp' is a pointer to the return address on the stack. It's ignored if - * the arch doesn't have HAVE_FUNCTION_GRAPH_RET_ADDR_PTR defined. - */ -#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR -unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, - unsigned long ret, unsigned long *retp) -{ - int index = task->curr_ret_stack; - int i; - - if (ret != (unsigned long)return_to_handler) - return ret; - - if (index < -1) - index += FTRACE_NOTRACE_DEPTH; - - if (index < 0) - return ret; - - for (i = 0; i <= index; i++) - if (task->ret_stack[i].retp == retp) - return task->ret_stack[i].ret; - - return ret; -} -#else /* !HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ -unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, - unsigned long ret, unsigned long *retp) -{ - int task_idx; - - if (ret != (unsigned long)return_to_handler) - return ret; - - task_idx = task->curr_ret_stack; - - if (!task->ret_stack || task_idx < *idx) - return ret; - - task_idx -= *idx; - (*idx)++; - - return task->ret_stack[task_idx].ret; -} -#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ - int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, unsigned long flags, @@ -382,6 +134,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) int cpu; int pc; + if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) + return 0; + + if (ftrace_graph_notrace_addr(trace->func)) { + trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT); + /* + * Need to return 1 to have the return called + * that will clear the NOTRACE bit. + */ + return 1; + } + if (!ftrace_trace_task(tr)) return 0; @@ -482,6 +246,13 @@ void trace_graph_return(struct ftrace_graph_ret *trace) int cpu; int pc; + ftrace_graph_addr_finish(trace); + + if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { + trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + return; + } + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -505,6 +276,13 @@ void set_graph_array(struct trace_array *tr) static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { + ftrace_graph_addr_finish(trace); + + if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { + trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + return; + } + if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) return; @@ -512,17 +290,25 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) trace_graph_return(trace); } +static struct fgraph_ops funcgraph_thresh_ops = { + .entryfunc = &trace_graph_entry, + .retfunc = &trace_graph_thresh_return, +}; + +static struct fgraph_ops funcgraph_ops = { + .entryfunc = &trace_graph_entry, + .retfunc = &trace_graph_return, +}; + static int graph_trace_init(struct trace_array *tr) { int ret; set_graph_array(tr); if (tracing_thresh) - ret = register_ftrace_graph(&trace_graph_thresh_return, - &trace_graph_entry); + ret = register_ftrace_graph(&funcgraph_thresh_ops); else - ret = register_ftrace_graph(&trace_graph_return, - &trace_graph_entry); + ret = register_ftrace_graph(&funcgraph_ops); if (ret) return ret; tracing_start_cmdline_record(); @@ -533,7 +319,10 @@ static int graph_trace_init(struct trace_array *tr) static void graph_trace_reset(struct trace_array *tr) { tracing_stop_cmdline_record(); - unregister_ftrace_graph(); + if (tracing_thresh) + unregister_ftrace_graph(&funcgraph_thresh_ops); + else + unregister_ftrace_graph(&funcgraph_ops); } static int graph_trace_update_thresh(struct trace_array *tr) @@ -843,10 +632,6 @@ print_graph_entry_leaf(struct trace_iterator *iter, cpu_data = per_cpu_ptr(data->cpu_data, cpu); - /* If a graph tracer ignored set_graph_notrace */ - if (call->depth < -1) - call->depth += FTRACE_NOTRACE_DEPTH; - /* * Comments display at + 1 to depth. Since * this is a leaf function, keep the comments @@ -889,10 +674,6 @@ print_graph_entry_nested(struct trace_iterator *iter, struct fgraph_cpu_data *cpu_data; int cpu = iter->cpu; - /* If a graph tracer ignored set_graph_notrace */ - if (call->depth < -1) - call->depth += FTRACE_NOTRACE_DEPTH; - cpu_data = per_cpu_ptr(data->cpu_data, cpu); cpu_data->depth = call->depth; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b7357f9f82a3..d42a473b8240 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -14,6 +14,7 @@ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include "trace.h" @@ -208,6 +209,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_dec(tr, &data, &flags)) return; @@ -216,6 +219,11 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) atomic_dec(&data->disabled); } +static struct fgraph_ops fgraph_ops = { + .entryfunc = &irqsoff_graph_entry, + .retfunc = &irqsoff_graph_return, +}; + static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) @@ -270,13 +278,6 @@ __trace_function(struct trace_array *tr, #else #define __trace_function trace_function -#ifdef CONFIG_FUNCTION_TRACER -static int irqsoff_graph_entry(struct ftrace_graph_ent *trace) -{ - return -1; -} -#endif - static enum print_line_t irqsoff_print_line(struct trace_iterator *iter) { return TRACE_TYPE_UNHANDLED; @@ -286,7 +287,6 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { } static void irqsoff_trace_close(struct trace_iterator *iter) { } #ifdef CONFIG_FUNCTION_TRACER -static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { } static void irqsoff_print_header(struct seq_file *s) { trace_default_header(s); @@ -366,7 +366,7 @@ out: __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc); } -static inline void +static nokprobe_inline void start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) { int cpu; @@ -402,7 +402,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) atomic_dec(&data->disabled); } -static inline void +static nokprobe_inline void stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) { int cpu; @@ -444,6 +444,7 @@ void start_critical_timings(void) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc); } EXPORT_SYMBOL_GPL(start_critical_timings); +NOKPROBE_SYMBOL(start_critical_timings); void stop_critical_timings(void) { @@ -453,6 +454,7 @@ void stop_critical_timings(void) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc); } EXPORT_SYMBOL_GPL(stop_critical_timings); +NOKPROBE_SYMBOL(stop_critical_timings); #ifdef CONFIG_FUNCTION_TRACER static bool function_enabled; @@ -466,8 +468,7 @@ static int register_irqsoff_function(struct trace_array *tr, int graph, int set) return 0; if (graph) - ret = register_ftrace_graph(&irqsoff_graph_return, - &irqsoff_graph_entry); + ret = register_ftrace_graph(&fgraph_ops); else ret = register_ftrace_function(tr->ops); @@ -483,7 +484,7 @@ static void unregister_irqsoff_function(struct trace_array *tr, int graph) return; if (graph) - unregister_ftrace_graph(); + unregister_ftrace_graph(&fgraph_ops); else unregister_ftrace_function(tr->ops); @@ -613,6 +614,7 @@ void tracer_hardirqs_on(unsigned long a0, unsigned long a1) if (!preempt_trace(pc) && irq_trace()) stop_critical_timing(a0, a1, pc); } +NOKPROBE_SYMBOL(tracer_hardirqs_on); void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { @@ -621,6 +623,7 @@ void tracer_hardirqs_off(unsigned long a0, unsigned long a1) if (!preempt_trace(pc) && irq_trace()) start_critical_timing(a0, a1, pc); } +NOKPROBE_SYMBOL(tracer_hardirqs_off); static int irqsoff_tracer_init(struct trace_array *tr) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c30032367aab..99592c27465e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -12,23 +12,59 @@ #include <linux/rculist.h> #include <linux/error-injection.h> +#include "trace_dynevent.h" #include "trace_kprobe_selftest.h" #include "trace_probe.h" +#include "trace_probe_tmpl.h" #define KPROBE_EVENT_SYSTEM "kprobes" #define KRETPROBE_MAXACTIVE_MAX 4096 +static int trace_kprobe_create(int argc, const char **argv); +static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev); +static int trace_kprobe_release(struct dyn_event *ev); +static bool trace_kprobe_is_busy(struct dyn_event *ev); +static bool trace_kprobe_match(const char *system, const char *event, + struct dyn_event *ev); + +static struct dyn_event_operations trace_kprobe_ops = { + .create = trace_kprobe_create, + .show = trace_kprobe_show, + .is_busy = trace_kprobe_is_busy, + .free = trace_kprobe_release, + .match = trace_kprobe_match, +}; + /** * Kprobe event core functions */ struct trace_kprobe { - struct list_head list; + struct dyn_event devent; struct kretprobe rp; /* Use rp.kp for kprobe use */ unsigned long __percpu *nhit; const char *symbol; /* symbol name */ struct trace_probe tp; }; +static bool is_trace_kprobe(struct dyn_event *ev) +{ + return ev->ops == &trace_kprobe_ops; +} + +static struct trace_kprobe *to_trace_kprobe(struct dyn_event *ev) +{ + return container_of(ev, struct trace_kprobe, devent); +} + +/** + * for_each_trace_kprobe - iterate over the trace_kprobe list + * @pos: the struct trace_kprobe * for each entry + * @dpos: the struct dyn_event * to use as a loop cursor + */ +#define for_each_trace_kprobe(pos, dpos) \ + for_each_dyn_event(dpos) \ + if (is_trace_kprobe(dpos) && (pos = to_trace_kprobe(dpos))) + #define SIZEOF_TRACE_KPROBE(n) \ (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) @@ -61,9 +97,39 @@ static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, return strncmp(mod->name, name, len) == 0 && name[len] == ':'; } -static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk) +static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) +{ + char *p; + bool ret; + + if (!tk->symbol) + return false; + p = strchr(tk->symbol, ':'); + if (!p) + return true; + *p = '\0'; + mutex_lock(&module_mutex); + ret = !!find_module(tk->symbol); + mutex_unlock(&module_mutex); + *p = ':'; + + return ret; +} + +static bool trace_kprobe_is_busy(struct dyn_event *ev) { - return !!strchr(trace_kprobe_symbol(tk), ':'); + struct trace_kprobe *tk = to_trace_kprobe(ev); + + return trace_probe_is_enabled(&tk->tp); +} + +static bool trace_kprobe_match(const char *system, const char *event, + struct dyn_event *ev) +{ + struct trace_kprobe *tk = to_trace_kprobe(ev); + + return strcmp(trace_event_name(&tk->tp.call), event) == 0 && + (!system || strcmp(tk->tp.call.class->system, system) == 0); } static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) @@ -113,191 +179,10 @@ bool trace_kprobe_error_injectable(struct trace_event_call *call) static int register_kprobe_event(struct trace_kprobe *tk); static int unregister_kprobe_event(struct trace_kprobe *tk); -static DEFINE_MUTEX(probe_lock); -static LIST_HEAD(probe_list); - static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs); -/* Memory fetching by symbol */ -struct symbol_cache { - char *symbol; - long offset; - unsigned long addr; -}; - -unsigned long update_symbol_cache(struct symbol_cache *sc) -{ - sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol); - - if (sc->addr) - sc->addr += sc->offset; - - return sc->addr; -} - -void free_symbol_cache(struct symbol_cache *sc) -{ - kfree(sc->symbol); - kfree(sc); -} - -struct symbol_cache *alloc_symbol_cache(const char *sym, long offset) -{ - struct symbol_cache *sc; - - if (!sym || strlen(sym) == 0) - return NULL; - - sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL); - if (!sc) - return NULL; - - sc->symbol = kstrdup(sym, GFP_KERNEL); - if (!sc->symbol) { - kfree(sc); - return NULL; - } - sc->offset = offset; - update_symbol_cache(sc); - - return sc; -} - -/* - * Kprobes-specific fetch functions - */ -#define DEFINE_FETCH_stack(type) \ -static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ - void *offset, void *dest) \ -{ \ - *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \ - (unsigned int)((unsigned long)offset)); \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type)); - -DEFINE_BASIC_FETCH_FUNCS(stack) -/* No string on the stack entry */ -#define fetch_stack_string NULL -#define fetch_stack_string_size NULL - -#define DEFINE_FETCH_memory(type) \ -static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ - void *addr, void *dest) \ -{ \ - type retval; \ - if (probe_kernel_address(addr, retval)) \ - *(type *)dest = 0; \ - else \ - *(type *)dest = retval; \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type)); - -DEFINE_BASIC_FETCH_FUNCS(memory) -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max - * length and relative data location. - */ -static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, - void *addr, void *dest) -{ - int maxlen = get_rloc_len(*(u32 *)dest); - u8 *dst = get_rloc_data(dest); - long ret; - - if (!maxlen) - return; - - /* - * Try to get string again, since the string can be changed while - * probing. - */ - ret = strncpy_from_unsafe(dst, addr, maxlen); - - if (ret < 0) { /* Failed to fetch string */ - dst[0] = '\0'; - *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); - } else { - *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest)); - } -} -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string)); - -/* Return the length of string -- including null terminal byte */ -static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, - void *addr, void *dest) -{ - mm_segment_t old_fs; - int ret, len = 0; - u8 c; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - pagefault_disable(); - - do { - ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); - len++; - } while (c && ret == 0 && len < MAX_STRING_SIZE); - - pagefault_enable(); - set_fs(old_fs); - - if (ret < 0) /* Failed to check the length */ - *(u32 *)dest = 0; - else - *(u32 *)dest = len; -} -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size)); - -#define DEFINE_FETCH_symbol(type) \ -void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\ -{ \ - struct symbol_cache *sc = data; \ - if (sc->addr) \ - fetch_memory_##type(regs, (void *)sc->addr, dest); \ - else \ - *(type *)dest = 0; \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type)); - -DEFINE_BASIC_FETCH_FUNCS(symbol) -DEFINE_FETCH_symbol(string) -DEFINE_FETCH_symbol(string_size) - -/* kprobes don't support file_offset fetch methods */ -#define fetch_file_offset_u8 NULL -#define fetch_file_offset_u16 NULL -#define fetch_file_offset_u32 NULL -#define fetch_file_offset_u64 NULL -#define fetch_file_offset_string NULL -#define fetch_file_offset_string_size NULL - -/* Fetch type information table */ -static const struct fetch_type kprobes_fetch_type_table[] = { - /* Special types */ - [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, - sizeof(u32), 1, "__data_loc char[]"), - [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, - string_size, sizeof(u32), 0, "u32"), - /* Basic types */ - ASSIGN_FETCH_TYPE(u8, u8, 0), - ASSIGN_FETCH_TYPE(u16, u16, 0), - ASSIGN_FETCH_TYPE(u32, u32, 0), - ASSIGN_FETCH_TYPE(u64, u64, 0), - ASSIGN_FETCH_TYPE(s8, u8, 1), - ASSIGN_FETCH_TYPE(s16, u16, 1), - ASSIGN_FETCH_TYPE(s32, u32, 1), - ASSIGN_FETCH_TYPE(s64, u64, 1), - ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0), - ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0), - ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0), - ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0), - - ASSIGN_FETCH_TYPE_END -}; - /* * Allocate new trace_probe and initialize it (including kprobes). */ @@ -355,7 +240,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, if (!tk->tp.class.system) goto error; - INIT_LIST_HEAD(&tk->list); + dyn_event_init(&tk->devent, &trace_kprobe_ops); INIT_LIST_HEAD(&tk->tp.files); return tk; error: @@ -370,6 +255,9 @@ static void free_trace_kprobe(struct trace_kprobe *tk) { int i; + if (!tk) + return; + for (i = 0; i < tk->tp.nr_args; i++) traceprobe_free_probe_arg(&tk->tp.args[i]); @@ -383,9 +271,10 @@ static void free_trace_kprobe(struct trace_kprobe *tk) static struct trace_kprobe *find_trace_kprobe(const char *event, const char *group) { + struct dyn_event *pos; struct trace_kprobe *tk; - list_for_each_entry(tk, &probe_list, list) + for_each_trace_kprobe(tk, pos) if (strcmp(trace_event_name(&tk->tp.call), event) == 0 && strcmp(tk->tp.call.class->system, group) == 0) return tk; @@ -484,7 +373,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) * created with perf_event_open. We don't need to wait for these * trace_kprobes */ - if (list_empty(&tk->list)) + if (list_empty(&tk->devent.list)) wait = 0; out: if (wait) { @@ -496,7 +385,7 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) * event_call related objects, which will be accessed in * the kprobe_trace_func/kretprobe_trace_func. */ - synchronize_sched(); + synchronize_rcu(); kfree(link); /* Ignored if link == NULL */ } @@ -540,8 +429,11 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) return -EINVAL; } - for (i = 0; i < tk->tp.nr_args; i++) - traceprobe_update_arg(&tk->tp.args[i]); + for (i = 0; i < tk->tp.nr_args; i++) { + ret = traceprobe_update_arg(&tk->tp.args[i]); + if (ret) + return ret; + } /* Set/clear disabled flag according to tp->flag */ if (trace_probe_is_enabled(&tk->tp)) @@ -554,19 +446,13 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) else ret = register_kprobe(&tk->rp.kp); - if (ret == 0) + if (ret == 0) { tk->tp.flags |= TP_FLAG_REGISTERED; - else { - if (ret == -ENOENT && trace_kprobe_is_on_module(tk)) { - pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); - ret = 0; - } else if (ret == -EILSEQ) { - pr_warn("Probing address(0x%p) is not an instruction boundary.\n", - tk->rp.kp.addr); - ret = -EINVAL; - } + } else if (ret == -EILSEQ) { + pr_warn("Probing address(0x%p) is not an instruction boundary.\n", + tk->rp.kp.addr); + ret = -EINVAL; } - return ret; } @@ -585,7 +471,7 @@ static void __unregister_trace_kprobe(struct trace_kprobe *tk) } } -/* Unregister a trace_probe and probe_event: call with locking probe_lock */ +/* Unregister a trace_probe and probe_event */ static int unregister_trace_kprobe(struct trace_kprobe *tk) { /* Enabled event can not be unregistered */ @@ -597,7 +483,7 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk) return -EBUSY; __unregister_trace_kprobe(tk); - list_del(&tk->list); + dyn_event_remove(&tk->devent); return 0; } @@ -608,7 +494,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk) struct trace_kprobe *old_tk; int ret; - mutex_lock(&probe_lock); + mutex_lock(&event_mutex); /* Delete old (same name) event if exist */ old_tk = find_trace_kprobe(trace_event_name(&tk->tp.call), @@ -629,13 +515,18 @@ static int register_trace_kprobe(struct trace_kprobe *tk) /* Register k*probe */ ret = __register_trace_kprobe(tk); + if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) { + pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); + ret = 0; + } + if (ret < 0) unregister_kprobe_event(tk); else - list_add_tail(&tk->list, &probe_list); + dyn_event_add(&tk->devent); end: - mutex_unlock(&probe_lock); + mutex_unlock(&event_mutex); return ret; } @@ -644,6 +535,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, unsigned long val, void *data) { struct module *mod = data; + struct dyn_event *pos; struct trace_kprobe *tk; int ret; @@ -651,8 +543,8 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, return NOTIFY_DONE; /* Update probes on coming module */ - mutex_lock(&probe_lock); - list_for_each_entry(tk, &probe_list, list) { + mutex_lock(&event_mutex); + for_each_trace_kprobe(tk, pos) { if (trace_kprobe_within_module(tk, mod)) { /* Don't need to check busy - this should have gone. */ __unregister_trace_kprobe(tk); @@ -663,7 +555,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, mod->name, ret); } } - mutex_unlock(&probe_lock); + mutex_unlock(&event_mutex); return NOTIFY_DONE; } @@ -681,7 +573,7 @@ static inline void sanitize_event_name(char *name) *name = '_'; } -static int create_trace_kprobe(int argc, char **argv) +static int trace_kprobe_create(int argc, const char *argv[]) { /* * Argument syntax: @@ -705,35 +597,43 @@ static int create_trace_kprobe(int argc, char **argv) * FETCHARG:TYPE : use TYPE instead of unsigned long. */ struct trace_kprobe *tk; - int i, ret = 0; - bool is_return = false, is_delete = false; - char *symbol = NULL, *event = NULL, *group = NULL; + int i, len, ret = 0; + bool is_return = false; + char *symbol = NULL, *tmp = NULL; + const char *event = NULL, *group = KPROBE_EVENT_SYSTEM; int maxactive = 0; - char *arg; long offset = 0; void *addr = NULL; char buf[MAX_EVENT_NAME_LEN]; + unsigned int flags = TPARG_FL_KERNEL; - /* argc must be >= 1 */ - if (argv[0][0] == 'p') - is_return = false; - else if (argv[0][0] == 'r') + switch (argv[0][0]) { + case 'r': is_return = true; - else if (argv[0][0] == '-') - is_delete = true; - else { - pr_info("Probe definition must be started with 'p', 'r' or" - " '-'.\n"); - return -EINVAL; + flags |= TPARG_FL_RETURN; + break; + case 'p': + break; + default: + return -ECANCELED; } + if (argc < 2) + return -ECANCELED; event = strchr(&argv[0][1], ':'); - if (event) { - event[0] = '\0'; + if (event) event++; - } + if (is_return && isdigit(argv[0][1])) { - ret = kstrtouint(&argv[0][1], 0, &maxactive); + if (event) + len = event - &argv[0][1] - 1; + else + len = strlen(&argv[0][1]); + if (len > MAX_EVENT_NAME_LEN - 1) + return -E2BIG; + memcpy(buf, &argv[0][1], len); + buf[len] = '\0'; + ret = kstrtouint(buf, 0, &maxactive); if (ret) { pr_info("Failed to parse maxactive.\n"); return ret; @@ -748,70 +648,37 @@ static int create_trace_kprobe(int argc, char **argv) } } - if (event) { - if (strchr(event, '/')) { - group = event; - event = strchr(group, '/') + 1; - event[-1] = '\0'; - if (strlen(group) == 0) { - pr_info("Group name is not specified\n"); - return -EINVAL; - } - } - if (strlen(event) == 0) { - pr_info("Event name is not specified\n"); - return -EINVAL; - } - } - if (!group) - group = KPROBE_EVENT_SYSTEM; - - if (is_delete) { - if (!event) { - pr_info("Delete command needs an event name.\n"); - return -EINVAL; - } - mutex_lock(&probe_lock); - tk = find_trace_kprobe(event, group); - if (!tk) { - mutex_unlock(&probe_lock); - pr_info("Event %s/%s doesn't exist.\n", group, event); - return -ENOENT; - } - /* delete an event */ - ret = unregister_trace_kprobe(tk); - if (ret == 0) - free_trace_kprobe(tk); - mutex_unlock(&probe_lock); - return ret; - } - - if (argc < 2) { - pr_info("Probe point is not specified.\n"); - return -EINVAL; - } - /* try to parse an address. if that fails, try to read the * input as a symbol. */ if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) { + /* Check whether uprobe event specified */ + if (strchr(argv[1], '/') && strchr(argv[1], ':')) + return -ECANCELED; /* a symbol specified */ - symbol = argv[1]; + symbol = kstrdup(argv[1], GFP_KERNEL); + if (!symbol) + return -ENOMEM; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret || offset < 0 || offset > UINT_MAX) { pr_info("Failed to parse either an address or a symbol.\n"); - return ret; + goto out; } - if (offset && is_return && - !kprobe_on_func_entry(NULL, symbol, offset)) { + if (kprobe_on_func_entry(NULL, symbol, offset)) + flags |= TPARG_FL_FENTRY; + if (offset && is_return && !(flags & TPARG_FL_FENTRY)) { pr_info("Given offset is not valid for return probe.\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } } argc -= 2; argv += 2; - /* setup a probe */ - if (!event) { + if (event) { + ret = traceprobe_parse_event_name(&event, &group, buf); + if (ret) + goto out; + } else { /* Make a new event name */ if (symbol) snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld", @@ -822,122 +689,67 @@ static int create_trace_kprobe(int argc, char **argv) sanitize_event_name(buf); event = buf; } + + /* setup a probe */ tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, argc, is_return); if (IS_ERR(tk)) { pr_info("Failed to allocate trace_probe.(%d)\n", (int)PTR_ERR(tk)); - return PTR_ERR(tk); + ret = PTR_ERR(tk); + goto out; } /* parse arguments */ - ret = 0; for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { - struct probe_arg *parg = &tk->tp.args[i]; - - /* Increment count for freeing args in error case */ - tk->tp.nr_args++; - - /* Parse argument name */ - arg = strchr(argv[i], '='); - if (arg) { - *arg++ = '\0'; - parg->name = kstrdup(argv[i], GFP_KERNEL); - } else { - arg = argv[i]; - /* If argument name is omitted, set "argN" */ - snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); - parg->name = kstrdup(buf, GFP_KERNEL); - } - - if (!parg->name) { - pr_info("Failed to allocate argument[%d] name.\n", i); + tmp = kstrdup(argv[i], GFP_KERNEL); + if (!tmp) { ret = -ENOMEM; goto error; } - if (!is_good_name(parg->name)) { - pr_info("Invalid argument[%d] name: %s\n", - i, parg->name); - ret = -EINVAL; - goto error; - } - - if (traceprobe_conflict_field_name(parg->name, - tk->tp.args, i)) { - pr_info("Argument[%d] name '%s' conflicts with " - "another field.\n", i, argv[i]); - ret = -EINVAL; - goto error; - } - - /* Parse fetch argument */ - ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg, - is_return, true, - kprobes_fetch_type_table); - if (ret) { - pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + ret = traceprobe_parse_probe_arg(&tk->tp, i, tmp, flags); + kfree(tmp); + if (ret) goto error; - } } ret = register_trace_kprobe(tk); if (ret) goto error; - return 0; +out: + kfree(symbol); + return ret; error: free_trace_kprobe(tk); - return ret; + goto out; } -static int release_all_trace_kprobes(void) +static int create_or_delete_trace_kprobe(int argc, char **argv) { - struct trace_kprobe *tk; - int ret = 0; - - mutex_lock(&probe_lock); - /* Ensure no probe is in use. */ - list_for_each_entry(tk, &probe_list, list) - if (trace_probe_is_enabled(&tk->tp)) { - ret = -EBUSY; - goto end; - } - /* TODO: Use batch unregistration */ - while (!list_empty(&probe_list)) { - tk = list_entry(probe_list.next, struct trace_kprobe, list); - ret = unregister_trace_kprobe(tk); - if (ret) - goto end; - free_trace_kprobe(tk); - } + int ret; -end: - mutex_unlock(&probe_lock); + if (argv[0][0] == '-') + return dyn_event_release(argc, argv, &trace_kprobe_ops); - return ret; + ret = trace_kprobe_create(argc, (const char **)argv); + return ret == -ECANCELED ? -EINVAL : ret; } -/* Probes listing interfaces */ -static void *probes_seq_start(struct seq_file *m, loff_t *pos) +static int trace_kprobe_release(struct dyn_event *ev) { - mutex_lock(&probe_lock); - return seq_list_start(&probe_list, *pos); -} + struct trace_kprobe *tk = to_trace_kprobe(ev); + int ret = unregister_trace_kprobe(tk); -static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) -{ - return seq_list_next(v, &probe_list, pos); -} - -static void probes_seq_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&probe_lock); + if (!ret) + free_trace_kprobe(tk); + return ret; } -static int probes_seq_show(struct seq_file *m, void *v) +static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev) { - struct trace_kprobe *tk = v; + struct trace_kprobe *tk = to_trace_kprobe(ev); int i; seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p'); @@ -959,10 +771,20 @@ static int probes_seq_show(struct seq_file *m, void *v) return 0; } +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct dyn_event *ev = v; + + if (!is_trace_kprobe(ev)) + return 0; + + return trace_kprobe_show(m, ev); +} + static const struct seq_operations probes_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, .show = probes_seq_show }; @@ -971,7 +793,7 @@ static int probes_open(struct inode *inode, struct file *file) int ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - ret = release_all_trace_kprobes(); + ret = dyn_events_release_all(&trace_kprobe_ops); if (ret < 0) return ret; } @@ -983,7 +805,7 @@ static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return trace_parse_run_command(file, buffer, count, ppos, - create_trace_kprobe); + create_or_delete_trace_kprobe); } static const struct file_operations kprobe_events_ops = { @@ -998,8 +820,13 @@ static const struct file_operations kprobe_events_ops = { /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { - struct trace_kprobe *tk = v; + struct dyn_event *ev = v; + struct trace_kprobe *tk; + if (!is_trace_kprobe(ev)) + return 0; + + tk = to_trace_kprobe(ev); seq_printf(m, " %-44s %15lu %15lu\n", trace_event_name(&tk->tp.call), trace_kprobe_nhit(tk), @@ -1009,9 +836,9 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) } static const struct seq_operations profile_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; @@ -1028,6 +855,98 @@ static const struct file_operations kprobe_profile_ops = { .release = seq_release, }; +/* Kprobe specific fetch functions */ + +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen(unsigned long addr) +{ + int ret, len = 0; + u8 c; + + do { + ret = probe_kernel_read(&c, (u8 *)addr + len, 1); + len++; + } while (c && ret == 0 && len < MAX_STRING_SIZE); + + return (ret < 0) ? ret : len; +} + +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max + * length and relative data location. + */ +static nokprobe_inline int +fetch_store_string(unsigned long addr, void *dest, void *base) +{ + int maxlen = get_loc_len(*(u32 *)dest); + u8 *dst = get_loc_data(dest, base); + long ret; + + if (unlikely(!maxlen)) + return -ENOMEM; + /* + * Try to get string again, since the string can be changed while + * probing. + */ + ret = strncpy_from_unsafe(dst, (void *)addr, maxlen); + + if (ret >= 0) + *(u32 *)dest = make_data_loc(ret, (void *)dst - base); + return ret; +} + +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ + return probe_kernel_read(dest, src, size); +} + +/* Note that we don't verify it, since the code does not come from user space */ +static int +process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, + void *base) +{ + unsigned long val; + +retry: + /* 1st stage: get value from context */ + switch (code->op) { + case FETCH_OP_REG: + val = regs_get_register(regs, code->param); + break; + case FETCH_OP_STACK: + val = regs_get_kernel_stack_nth(regs, code->param); + break; + case FETCH_OP_STACKP: + val = kernel_stack_pointer(regs); + break; + case FETCH_OP_RETVAL: + val = regs_return_value(regs); + break; + case FETCH_OP_IMM: + val = code->immediate; + break; + case FETCH_OP_COMM: + val = (unsigned long)current->comm; + break; +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + case FETCH_OP_ARG: + val = regs_get_kernel_argument(regs, code->param); + break; +#endif + case FETCH_NOP_SYMBOL: /* Ignore a place holder */ + code++; + goto retry; + default: + return -EILSEQ; + } + code++; + + return process_fetch_insn_bottom(code, val, dest, base); +} +NOKPROBE_SYMBOL(process_fetch_insn) + /* Kprobe handler */ static nokprobe_inline void __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, @@ -1059,7 +978,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, entry = ring_buffer_event_data(event); entry->ip = (unsigned long)tk->rp.kp.addr; - store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); event_trigger_unlock_commit_regs(trace_file, buffer, event, entry, irq_flags, pc, regs); @@ -1108,7 +1027,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry = ring_buffer_event_data(event); entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; - store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); event_trigger_unlock_commit_regs(trace_file, buffer, event, entry, irq_flags, pc, regs); @@ -1133,8 +1052,6 @@ print_kprobe_event(struct trace_iterator *iter, int flags, struct kprobe_trace_entry_head *field; struct trace_seq *s = &iter->seq; struct trace_probe *tp; - u8 *data; - int i; field = (struct kprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); @@ -1146,11 +1063,9 @@ print_kprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - data = (u8 *)&field[1]; - for (i = 0; i < tp->nr_args; i++) - if (!tp->args[i].type->print(s, tp->args[i].name, - data + tp->args[i].offset, field)) - goto out; + if (print_probe_args(s, tp->args, tp->nr_args, + (u8 *)&field[1], field) < 0) + goto out; trace_seq_putc(s, '\n'); out: @@ -1164,8 +1079,6 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, struct kretprobe_trace_entry_head *field; struct trace_seq *s = &iter->seq; struct trace_probe *tp; - u8 *data; - int i; field = (struct kretprobe_trace_entry_head *)iter->ent; tp = container_of(event, struct trace_probe, call.event); @@ -1182,11 +1095,9 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - data = (u8 *)&field[1]; - for (i = 0; i < tp->nr_args; i++) - if (!tp->args[i].type->print(s, tp->args[i].name, - data + tp->args[i].offset, field)) - goto out; + if (print_probe_args(s, tp->args, tp->nr_args, + (u8 *)&field[1], field) < 0) + goto out; trace_seq_putc(s, '\n'); @@ -1197,49 +1108,25 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, static int kprobe_event_define_fields(struct trace_event_call *event_call) { - int ret, i; + int ret; struct kprobe_trace_entry_head field; struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); - /* Set argument names as fields */ - for (i = 0; i < tk->tp.nr_args; i++) { - struct probe_arg *parg = &tk->tp.args[i]; - - ret = trace_define_field(event_call, parg->type->fmttype, - parg->name, - sizeof(field) + parg->offset, - parg->type->size, - parg->type->is_signed, - FILTER_OTHER); - if (ret) - return ret; - } - return 0; + + return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp); } static int kretprobe_event_define_fields(struct trace_event_call *event_call) { - int ret, i; + int ret; struct kretprobe_trace_entry_head field; struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); - /* Set argument names as fields */ - for (i = 0; i < tk->tp.nr_args; i++) { - struct probe_arg *parg = &tk->tp.args[i]; - - ret = trace_define_field(event_call, parg->type->fmttype, - parg->name, - sizeof(field) + parg->offset, - parg->type->size, - parg->type->is_signed, - FILTER_OTHER); - if (ret) - return ret; - } - return 0; + + return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp); } #ifdef CONFIG_PERF_EVENTS @@ -1286,7 +1173,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); - store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -1322,7 +1209,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; - store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); + store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -1457,7 +1344,7 @@ static int register_kprobe_event(struct trace_kprobe *tk) init_trace_event_call(tk, call); - if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) + if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) return -ENOMEM; ret = register_trace_event(&call->event); if (!ret) { @@ -1496,7 +1383,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, char *event; /* - * local trace_kprobes are not added to probe_list, so they are never + * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of * duplicated name here. */ @@ -1514,7 +1401,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, init_trace_event_call(tk, &tk->tp.call); - if (set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) { + if (traceprobe_set_print_fmt(&tk->tp, trace_kprobe_is_return(tk)) < 0) { ret = -ENOMEM; goto error; } @@ -1554,6 +1441,11 @@ static __init int init_kprobe_trace(void) { struct dentry *d_tracer; struct dentry *entry; + int ret; + + ret = dyn_event_register(&trace_kprobe_ops); + if (ret) + return ret; if (register_module_notifier(&trace_kprobe_module_nb)) return -EINVAL; @@ -1611,9 +1503,8 @@ static __init int kprobe_trace_self_tests_init(void) pr_info("Testing kprobe tracing: "); - ret = trace_run_command("p:testprobe kprobe_trace_selftest_target " - "$stack $stack0 +0($stack)", - create_trace_kprobe); + ret = trace_run_command("p:testprobe kprobe_trace_selftest_target $stack $stack0 +0($stack)", + create_or_delete_trace_kprobe); if (WARN_ON_ONCE(ret)) { pr_warn("error on probing function entry.\n"); warn++; @@ -1633,8 +1524,8 @@ static __init int kprobe_trace_self_tests_init(void) } } - ret = trace_run_command("r:testprobe2 kprobe_trace_selftest_target " - "$retval", create_trace_kprobe); + ret = trace_run_command("r:testprobe2 kprobe_trace_selftest_target $retval", + create_or_delete_trace_kprobe); if (WARN_ON_ONCE(ret)) { pr_warn("error on probing function return.\n"); warn++; @@ -1704,20 +1595,24 @@ static __init int kprobe_trace_self_tests_init(void) disable_trace_kprobe(tk, file); } - ret = trace_run_command("-:testprobe", create_trace_kprobe); + ret = trace_run_command("-:testprobe", create_or_delete_trace_kprobe); if (WARN_ON_ONCE(ret)) { pr_warn("error on deleting a probe.\n"); warn++; } - ret = trace_run_command("-:testprobe2", create_trace_kprobe); + ret = trace_run_command("-:testprobe2", create_or_delete_trace_kprobe); if (WARN_ON_ONCE(ret)) { pr_warn("error on deleting a probe.\n"); warn++; } end: - release_all_trace_kprobes(); + ret = dyn_events_release_all(&trace_kprobe_ops); + if (WARN_ON_ONCE(ret)) { + pr_warn("error on cleaning up probes.\n"); + warn++; + } /* * Wait for the optimizer work to finish. Otherwise it might fiddle * with probes in already freed __init text. diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 6e6cc64faa38..54373d93e251 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -339,43 +339,24 @@ static inline const char *kretprobed(const char *name) #endif /* CONFIG_KRETPROBES */ static void -seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +seq_print_sym(struct trace_seq *s, unsigned long address, bool offset) { - char str[KSYM_SYMBOL_LEN]; #ifdef CONFIG_KALLSYMS - const char *name; - - kallsyms_lookup(address, NULL, NULL, NULL, str); - - name = kretprobed(str); - - if (name && strlen(name)) { - trace_seq_printf(s, fmt, name); - return; - } -#endif - snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address); - trace_seq_printf(s, fmt, str); -} - -static void -seq_print_sym_offset(struct trace_seq *s, const char *fmt, - unsigned long address) -{ char str[KSYM_SYMBOL_LEN]; -#ifdef CONFIG_KALLSYMS const char *name; - sprint_symbol(str, address); + if (offset) + sprint_symbol(str, address); + else + kallsyms_lookup(address, NULL, NULL, NULL, str); name = kretprobed(str); if (name && strlen(name)) { - trace_seq_printf(s, fmt, name); + trace_seq_puts(s, name); return; } #endif - snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address); - trace_seq_printf(s, fmt, str); + trace_seq_printf(s, "0x%08lx", address); } #ifndef CONFIG_64BIT @@ -424,10 +405,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) goto out; } - if (sym_flags & TRACE_ITER_SYM_OFFSET) - seq_print_sym_offset(s, "%s", ip); - else - seq_print_sym_short(s, "%s", ip); + seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET); if (sym_flags & TRACE_ITER_SYM_ADDR) trace_seq_printf(s, " <" IP_FMT ">", ip); diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 71f553cceb3c..4d8e99fdbbbe 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -9,6 +9,7 @@ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include "trace.h" #define CREATE_TRACE_POINTS @@ -30,6 +31,7 @@ void trace_hardirqs_on(void) lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); +NOKPROBE_SYMBOL(trace_hardirqs_on); void trace_hardirqs_off(void) { @@ -43,6 +45,7 @@ void trace_hardirqs_off(void) lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off); +NOKPROBE_SYMBOL(trace_hardirqs_off); __visible void trace_hardirqs_on_caller(unsigned long caller_addr) { @@ -56,6 +59,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr) lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on_caller); +NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { @@ -69,6 +73,7 @@ __visible void trace_hardirqs_off_caller(unsigned long caller_addr) lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); +NOKPROBE_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_TRACE_PREEMPT_TOGGLE diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index b0875b327f5c..c3fd849d4a8f 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -115,7 +115,7 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self, * section, then we need to read the link list pointers. The trick is * we pass the address of the string to the seq function just like * we do for the kernel core formats. To get back the structure that - * holds the format, we simply use containerof() and then go to the + * holds the format, we simply use container_of() and then go to the * next format in the list. */ static const char ** diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index e99c3ce7aa65..9962cb5da8ac 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -26,14 +26,12 @@ const char *reserved_field_names[] = { /* Printing in basic type function template */ #define DEFINE_BASIC_PRINT_TYPE_FUNC(tname, type, fmt) \ -int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, const char *name, \ - void *data, void *ent) \ +int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, void *data, void *ent)\ { \ - trace_seq_printf(s, " %s=" fmt, name, *(type *)data); \ + trace_seq_printf(s, fmt, *(type *)data); \ return !trace_seq_has_overflowed(s); \ } \ -const char PRINT_TYPE_FMT_NAME(tname)[] = fmt; \ -NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(tname)); +const char PRINT_TYPE_FMT_NAME(tname)[] = fmt; DEFINE_BASIC_PRINT_TYPE_FUNC(u8, u8, "%u") DEFINE_BASIC_PRINT_TYPE_FUNC(u16, u16, "%u") @@ -48,193 +46,52 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(x16, u16, "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(x32, u32, "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(x64, u64, "0x%Lx") +int PRINT_TYPE_FUNC_NAME(symbol)(struct trace_seq *s, void *data, void *ent) +{ + trace_seq_printf(s, "%pS", (void *)*(unsigned long *)data); + return !trace_seq_has_overflowed(s); +} +const char PRINT_TYPE_FMT_NAME(symbol)[] = "%pS"; + /* Print type function for string type */ -int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name, - void *data, void *ent) +int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, void *data, void *ent) { int len = *(u32 *)data >> 16; if (!len) - trace_seq_printf(s, " %s=(fault)", name); + trace_seq_puts(s, "(fault)"); else - trace_seq_printf(s, " %s=\"%s\"", name, + trace_seq_printf(s, "\"%s\"", (const char *)get_loc_data(data, ent)); return !trace_seq_has_overflowed(s); } -NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string)); const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; -#define CHECK_FETCH_FUNCS(method, fn) \ - (((FETCH_FUNC_NAME(method, u8) == fn) || \ - (FETCH_FUNC_NAME(method, u16) == fn) || \ - (FETCH_FUNC_NAME(method, u32) == fn) || \ - (FETCH_FUNC_NAME(method, u64) == fn) || \ - (FETCH_FUNC_NAME(method, string) == fn) || \ - (FETCH_FUNC_NAME(method, string_size) == fn)) \ - && (fn != NULL)) - -/* Data fetch function templates */ -#define DEFINE_FETCH_reg(type) \ -void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest) \ -{ \ - *(type *)dest = (type)regs_get_register(regs, \ - (unsigned int)((unsigned long)offset)); \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type)); -DEFINE_BASIC_FETCH_FUNCS(reg) -/* No string on the register */ -#define fetch_reg_string NULL -#define fetch_reg_string_size NULL - -#define DEFINE_FETCH_retval(type) \ -void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs, \ - void *dummy, void *dest) \ -{ \ - *(type *)dest = (type)regs_return_value(regs); \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type)); -DEFINE_BASIC_FETCH_FUNCS(retval) -/* No string on the retval */ -#define fetch_retval_string NULL -#define fetch_retval_string_size NULL - -/* Dereference memory access function */ -struct deref_fetch_param { - struct fetch_param orig; - long offset; - fetch_func_t fetch; - fetch_func_t fetch_size; +/* Fetch type information table */ +static const struct fetch_type probe_fetch_types[] = { + /* Special types */ + __ASSIGN_FETCH_TYPE("string", string, string, sizeof(u32), 1, + "__data_loc char[]"), + /* Basic types */ + ASSIGN_FETCH_TYPE(u8, u8, 0), + ASSIGN_FETCH_TYPE(u16, u16, 0), + ASSIGN_FETCH_TYPE(u32, u32, 0), + ASSIGN_FETCH_TYPE(u64, u64, 0), + ASSIGN_FETCH_TYPE(s8, u8, 1), + ASSIGN_FETCH_TYPE(s16, u16, 1), + ASSIGN_FETCH_TYPE(s32, u32, 1), + ASSIGN_FETCH_TYPE(s64, u64, 1), + ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0), + ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0), + ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0), + ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0), + ASSIGN_FETCH_TYPE_ALIAS(symbol, ADDR_FETCH_TYPE, ADDR_FETCH_TYPE, 0), + + ASSIGN_FETCH_TYPE_END }; -#define DEFINE_FETCH_deref(type) \ -void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs, \ - void *data, void *dest) \ -{ \ - struct deref_fetch_param *dprm = data; \ - unsigned long addr; \ - call_fetch(&dprm->orig, regs, &addr); \ - if (addr) { \ - addr += dprm->offset; \ - dprm->fetch(regs, (void *)addr, dest); \ - } else \ - *(type *)dest = 0; \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type)); -DEFINE_BASIC_FETCH_FUNCS(deref) -DEFINE_FETCH_deref(string) - -void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs, - void *data, void *dest) -{ - struct deref_fetch_param *dprm = data; - unsigned long addr; - - call_fetch(&dprm->orig, regs, &addr); - if (addr && dprm->fetch_size) { - addr += dprm->offset; - dprm->fetch_size(regs, (void *)addr, dest); - } else - *(string_size *)dest = 0; -} -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size)); - -static void update_deref_fetch_param(struct deref_fetch_param *data) -{ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - update_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - update_symbol_cache(data->orig.data); -} -NOKPROBE_SYMBOL(update_deref_fetch_param); - -static void free_deref_fetch_param(struct deref_fetch_param *data) -{ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - free_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - free_symbol_cache(data->orig.data); - kfree(data); -} -NOKPROBE_SYMBOL(free_deref_fetch_param); - -/* Bitfield fetch function */ -struct bitfield_fetch_param { - struct fetch_param orig; - unsigned char hi_shift; - unsigned char low_shift; -}; - -#define DEFINE_FETCH_bitfield(type) \ -void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs, \ - void *data, void *dest) \ -{ \ - struct bitfield_fetch_param *bprm = data; \ - type buf = 0; \ - call_fetch(&bprm->orig, regs, &buf); \ - if (buf) { \ - buf <<= bprm->hi_shift; \ - buf >>= bprm->low_shift; \ - } \ - *(type *)dest = buf; \ -} \ -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type)); -DEFINE_BASIC_FETCH_FUNCS(bitfield) -#define fetch_bitfield_string NULL -#define fetch_bitfield_string_size NULL - -static void -update_bitfield_fetch_param(struct bitfield_fetch_param *data) -{ - /* - * Don't check the bitfield itself, because this must be the - * last fetch function. - */ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - update_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - update_symbol_cache(data->orig.data); -} - -static void -free_bitfield_fetch_param(struct bitfield_fetch_param *data) -{ - /* - * Don't check the bitfield itself, because this must be the - * last fetch function. - */ - if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) - free_deref_fetch_param(data->orig.data); - else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) - free_symbol_cache(data->orig.data); - - kfree(data); -} - -void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs, - void *data, void *dest) -{ - int maxlen = get_rloc_len(*(u32 *)dest); - u8 *dst = get_rloc_data(dest); - long ret; - - if (!maxlen) - return; - - ret = strlcpy(dst, current->comm, maxlen); - *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest)); -} -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string)); - -void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs, - void *data, void *dest) -{ - *(u32 *)dest = strlen(current->comm) + 1; -} -NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size)); - -static const struct fetch_type *find_fetch_type(const char *type, - const struct fetch_type *ftbl) +static const struct fetch_type *find_fetch_type(const char *type) { int i; @@ -255,58 +112,27 @@ static const struct fetch_type *find_fetch_type(const char *type, switch (bs) { case 8: - return find_fetch_type("u8", ftbl); + return find_fetch_type("u8"); case 16: - return find_fetch_type("u16", ftbl); + return find_fetch_type("u16"); case 32: - return find_fetch_type("u32", ftbl); + return find_fetch_type("u32"); case 64: - return find_fetch_type("u64", ftbl); + return find_fetch_type("u64"); default: goto fail; } } - for (i = 0; ftbl[i].name; i++) { - if (strcmp(type, ftbl[i].name) == 0) - return &ftbl[i]; + for (i = 0; probe_fetch_types[i].name; i++) { + if (strcmp(type, probe_fetch_types[i].name) == 0) + return &probe_fetch_types[i]; } fail: return NULL; } -/* Special function : only accept unsigned long */ -static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest) -{ - *(unsigned long *)dest = kernel_stack_pointer(regs); -} -NOKPROBE_SYMBOL(fetch_kernel_stack_address); - -static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest) -{ - *(unsigned long *)dest = user_stack_pointer(regs); -} -NOKPROBE_SYMBOL(fetch_user_stack_address); - -static fetch_func_t get_fetch_size_function(const struct fetch_type *type, - fetch_func_t orig_fn, - const struct fetch_type *ftbl) -{ - int i; - - if (type != &ftbl[FETCH_TYPE_STRING]) - return NULL; /* Only string type needs size function */ - - for (i = 0; i < FETCH_MTD_END; i++) - if (type->fetch[i] == orig_fn) - return ftbl[FETCH_TYPE_STRSIZE].fetch[i]; - - WARN_ON(1); /* This should not happen */ - - return NULL; -} - /* Split symbol and offset. */ int traceprobe_split_symbol_offset(char *symbol, long *offset) { @@ -328,44 +154,75 @@ int traceprobe_split_symbol_offset(char *symbol, long *offset) return 0; } +/* @buf must has MAX_EVENT_NAME_LEN size */ +int traceprobe_parse_event_name(const char **pevent, const char **pgroup, + char *buf) +{ + const char *slash, *event = *pevent; + + slash = strchr(event, '/'); + if (slash) { + if (slash == event) { + pr_info("Group name is not specified\n"); + return -EINVAL; + } + if (slash - event + 1 > MAX_EVENT_NAME_LEN) { + pr_info("Group name is too long\n"); + return -E2BIG; + } + strlcpy(buf, event, slash - event + 1); + *pgroup = buf; + *pevent = slash + 1; + } + if (strlen(event) == 0) { + pr_info("Event name is not specified\n"); + return -EINVAL; + } + return 0; +} + #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) static int parse_probe_vars(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return, - bool is_kprobe) + struct fetch_insn *code, unsigned int flags) { - int ret = 0; unsigned long param; + int ret = 0; + int len; if (strcmp(arg, "retval") == 0) { - if (is_return) - f->fn = t->fetch[FETCH_MTD_retval]; + if (flags & TPARG_FL_RETURN) + code->op = FETCH_OP_RETVAL; else ret = -EINVAL; - } else if (strncmp(arg, "stack", 5) == 0) { - if (arg[5] == '\0') { - if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR)) - return -EINVAL; - - if (is_kprobe) - f->fn = fetch_kernel_stack_address; - else - f->fn = fetch_user_stack_address; - } else if (isdigit(arg[5])) { - ret = kstrtoul(arg + 5, 10, ¶m); - if (ret || (is_kprobe && param > PARAM_MAX_STACK)) + } else if ((len = str_has_prefix(arg, "stack"))) { + if (arg[len] == '\0') { + code->op = FETCH_OP_STACKP; + } else if (isdigit(arg[len])) { + ret = kstrtoul(arg + len, 10, ¶m); + if (ret || ((flags & TPARG_FL_KERNEL) && + param > PARAM_MAX_STACK)) ret = -EINVAL; else { - f->fn = t->fetch[FETCH_MTD_stack]; - f->data = (void *)param; + code->op = FETCH_OP_STACK; + code->param = (unsigned int)param; } } else ret = -EINVAL; } else if (strcmp(arg, "comm") == 0) { - if (strcmp(t->name, "string") != 0 && - strcmp(t->name, "string_size") != 0) + code->op = FETCH_OP_COMM; +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + } else if (((flags & TPARG_FL_MASK) == + (TPARG_FL_KERNEL | TPARG_FL_FENTRY)) && + (len = str_has_prefix(arg, "arg"))) { + if (!isdigit(arg[len])) return -EINVAL; - f->fn = t->fetch[FETCH_MTD_comm]; + ret = kstrtoul(arg + len, 10, ¶m); + if (ret || !param || param > PARAM_MAX_STACK) + return -EINVAL; + code->op = FETCH_OP_ARG; + code->param = (unsigned int)param - 1; +#endif } else ret = -EINVAL; @@ -373,25 +230,27 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, } /* Recursive argument parser */ -static int parse_probe_arg(char *arg, const struct fetch_type *t, - struct fetch_param *f, bool is_return, bool is_kprobe, - const struct fetch_type *ftbl) +static int +parse_probe_arg(char *arg, const struct fetch_type *type, + struct fetch_insn **pcode, struct fetch_insn *end, + unsigned int flags) { + struct fetch_insn *code = *pcode; unsigned long param; - long offset; + long offset = 0; char *tmp; int ret = 0; switch (arg[0]) { case '$': - ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe); + ret = parse_probe_vars(arg + 1, type, code, flags); break; case '%': /* named register */ ret = regs_query_register_offset(arg + 1); if (ret >= 0) { - f->fn = t->fetch[FETCH_MTD_reg]; - f->data = (void *)(unsigned long)ret; + code->op = FETCH_OP_REG; + code->param = (unsigned int)ret; ret = 0; } break; @@ -401,33 +260,42 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, ret = kstrtoul(arg + 1, 0, ¶m); if (ret) break; - - f->fn = t->fetch[FETCH_MTD_memory]; - f->data = (void *)param; + /* load address */ + code->op = FETCH_OP_IMM; + code->immediate = param; } else if (arg[1] == '+') { /* kprobes don't support file offsets */ - if (is_kprobe) + if (flags & TPARG_FL_KERNEL) return -EINVAL; ret = kstrtol(arg + 2, 0, &offset); if (ret) break; - f->fn = t->fetch[FETCH_MTD_file_offset]; - f->data = (void *)offset; + code->op = FETCH_OP_FOFFS; + code->immediate = (unsigned long)offset; // imm64? } else { /* uprobes don't support symbols */ - if (!is_kprobe) + if (!(flags & TPARG_FL_KERNEL)) return -EINVAL; - ret = traceprobe_split_symbol_offset(arg + 1, &offset); - if (ret) - break; + /* Preserve symbol for updating */ + code->op = FETCH_NOP_SYMBOL; + code->data = kstrdup(arg + 1, GFP_KERNEL); + if (!code->data) + return -ENOMEM; + if (++code == end) + return -E2BIG; - f->data = alloc_symbol_cache(arg + 1, offset); - if (f->data) - f->fn = t->fetch[FETCH_MTD_symbol]; + code->op = FETCH_OP_IMM; + code->immediate = 0; } + /* These are fetching from memory */ + if (++code == end) + return -E2BIG; + *pcode = code; + code->op = FETCH_OP_DEREF; + code->offset = offset; break; case '+': /* deref memory */ @@ -435,11 +303,10 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, case '-': tmp = strchr(arg, '('); if (!tmp) - break; + return -EINVAL; *tmp = '\0'; ret = kstrtol(arg, 0, &offset); - if (ret) break; @@ -447,36 +314,27 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, tmp = strrchr(arg, ')'); if (tmp) { - struct deref_fetch_param *dprm; - const struct fetch_type *t2; + const struct fetch_type *t2 = find_fetch_type(NULL); - t2 = find_fetch_type(NULL, ftbl); *tmp = '\0'; - dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL); - - if (!dprm) - return -ENOMEM; - - dprm->offset = offset; - dprm->fetch = t->fetch[FETCH_MTD_memory]; - dprm->fetch_size = get_fetch_size_function(t, - dprm->fetch, ftbl); - ret = parse_probe_arg(arg, t2, &dprm->orig, is_return, - is_kprobe, ftbl); + ret = parse_probe_arg(arg, t2, &code, end, flags); if (ret) - kfree(dprm); - else { - f->fn = t->fetch[FETCH_MTD_deref]; - f->data = (void *)dprm; - } + break; + if (code->op == FETCH_OP_COMM) + return -EINVAL; + if (++code == end) + return -E2BIG; + *pcode = code; + + code->op = FETCH_OP_DEREF; + code->offset = offset; } break; } - if (!ret && !f->fn) { /* Parsed, but do not find fetch method */ - pr_info("%s type has no corresponding fetch method.\n", t->name); + if (!ret && code->op == FETCH_OP_NOP) { + /* Parsed, but do not find fetch method */ ret = -EINVAL; } - return ret; } @@ -485,22 +343,15 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t, /* Bitfield type needs to be parsed into a fetch function */ static int __parse_bitfield_probe_arg(const char *bf, const struct fetch_type *t, - struct fetch_param *f) + struct fetch_insn **pcode) { - struct bitfield_fetch_param *bprm; + struct fetch_insn *code = *pcode; unsigned long bw, bo; char *tail; if (*bf != 'b') return 0; - bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); - if (!bprm) - return -ENOMEM; - - bprm->orig = *f; - f->fn = t->fetch[FETCH_MTD_bitfield]; - f->data = (void *)bprm; bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */ if (bw == 0 || *tail != '@') @@ -511,20 +362,26 @@ static int __parse_bitfield_probe_arg(const char *bf, if (tail == bf || *tail != '/') return -EINVAL; + code++; + if (code->op != FETCH_OP_NOP) + return -E2BIG; + *pcode = code; - bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo); - bprm->low_shift = bprm->hi_shift + bo; + code->op = FETCH_OP_MOD_BF; + code->lshift = BYTES_TO_BITS(t->size) - (bw + bo); + code->rshift = BYTES_TO_BITS(t->size) - bw; + code->basesize = t->size; return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; } /* String length checking wrapper */ -int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return, bool is_kprobe, - const struct fetch_type *ftbl) +static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, + struct probe_arg *parg, unsigned int flags) { - const char *t; - int ret; + struct fetch_insn *code, *scode, *tmp = NULL; + char *t, *t2; + int ret, len; if (strlen(arg) > MAX_ARGSTR_LEN) { pr_info("Argument is too long.: %s\n", arg); @@ -535,43 +392,135 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size, pr_info("Failed to allocate memory for command '%s'.\n", arg); return -ENOMEM; } - t = strchr(parg->comm, ':'); + t = strchr(arg, ':'); if (t) { - arg[t - parg->comm] = '\0'; - t++; + *t = '\0'; + t2 = strchr(++t, '['); + if (t2) { + *t2 = '\0'; + parg->count = simple_strtoul(t2 + 1, &t2, 0); + if (strcmp(t2, "]") || parg->count == 0) + return -EINVAL; + if (parg->count > MAX_ARRAY_LEN) + return -E2BIG; + } } /* * The default type of $comm should be "string", and it can't be * dereferenced. */ if (!t && strcmp(arg, "$comm") == 0) - t = "string"; - parg->type = find_fetch_type(t, ftbl); + parg->type = find_fetch_type("string"); + else + parg->type = find_fetch_type(t); if (!parg->type) { pr_info("Unsupported type: %s\n", t); return -EINVAL; } parg->offset = *size; - *size += parg->type->size; - ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, - is_kprobe, ftbl); - - if (ret >= 0 && t != NULL) - ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); - - if (ret >= 0) { - parg->fetch_size.fn = get_fetch_size_function(parg->type, - parg->fetch.fn, - ftbl); - parg->fetch_size.data = parg->fetch.data; + *size += parg->type->size * (parg->count ?: 1); + + if (parg->count) { + len = strlen(parg->type->fmttype) + 6; + parg->fmt = kmalloc(len, GFP_KERNEL); + if (!parg->fmt) + return -ENOMEM; + snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, + parg->count); } + code = tmp = kzalloc(sizeof(*code) * FETCH_INSN_MAX, GFP_KERNEL); + if (!code) + return -ENOMEM; + code[FETCH_INSN_MAX - 1].op = FETCH_OP_END; + + ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1], + flags); + if (ret) + goto fail; + + /* Store operation */ + if (!strcmp(parg->type->name, "string")) { + if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_IMM && + code->op != FETCH_OP_COMM) { + pr_info("string only accepts memory or address.\n"); + ret = -EINVAL; + goto fail; + } + if (code->op != FETCH_OP_DEREF || parg->count) { + /* + * IMM and COMM is pointing actual address, those must + * be kept, and if parg->count != 0, this is an array + * of string pointers instead of string address itself. + */ + code++; + if (code->op != FETCH_OP_NOP) { + ret = -E2BIG; + goto fail; + } + } + code->op = FETCH_OP_ST_STRING; /* In DEREF case, replace it */ + code->size = parg->type->size; + parg->dynamic = true; + } else if (code->op == FETCH_OP_DEREF) { + code->op = FETCH_OP_ST_MEM; + code->size = parg->type->size; + } else { + code++; + if (code->op != FETCH_OP_NOP) { + ret = -E2BIG; + goto fail; + } + code->op = FETCH_OP_ST_RAW; + code->size = parg->type->size; + } + scode = code; + /* Modify operation */ + if (t != NULL) { + ret = __parse_bitfield_probe_arg(t, parg->type, &code); + if (ret) + goto fail; + } + /* Loop(Array) operation */ + if (parg->count) { + if (scode->op != FETCH_OP_ST_MEM && + scode->op != FETCH_OP_ST_STRING) { + pr_info("array only accepts memory or address\n"); + ret = -EINVAL; + goto fail; + } + code++; + if (code->op != FETCH_OP_NOP) { + ret = -E2BIG; + goto fail; + } + code->op = FETCH_OP_LP_ARRAY; + code->param = parg->count; + } + code++; + code->op = FETCH_OP_END; + + /* Shrink down the code buffer */ + parg->code = kzalloc(sizeof(*code) * (code - tmp + 1), GFP_KERNEL); + if (!parg->code) + ret = -ENOMEM; + else + memcpy(parg->code, tmp, sizeof(*code) * (code - tmp + 1)); + +fail: + if (ret) { + for (code = tmp; code < tmp + FETCH_INSN_MAX; code++) + if (code->op == FETCH_NOP_SYMBOL) + kfree(code->data); + } + kfree(tmp); + return ret; } /* Return 1 if name is reserved or already used by another argument */ -int traceprobe_conflict_field_name(const char *name, - struct probe_arg *args, int narg) +static int traceprobe_conflict_field_name(const char *name, + struct probe_arg *args, int narg) { int i; @@ -586,35 +535,104 @@ int traceprobe_conflict_field_name(const char *name, return 0; } -void traceprobe_update_arg(struct probe_arg *arg) +int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, char *arg, + unsigned int flags) { - if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) - update_bitfield_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) - update_deref_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) - update_symbol_cache(arg->fetch.data); + struct probe_arg *parg = &tp->args[i]; + char *body; + int ret; + + /* Increment count for freeing args in error case */ + tp->nr_args++; + + body = strchr(arg, '='); + if (body) { + parg->name = kmemdup_nul(arg, body - arg, GFP_KERNEL); + body++; + } else { + /* If argument name is omitted, set "argN" */ + parg->name = kasprintf(GFP_KERNEL, "arg%d", i + 1); + body = arg; + } + if (!parg->name) + return -ENOMEM; + + if (!is_good_name(parg->name)) { + pr_info("Invalid argument[%d] name: %s\n", + i, parg->name); + return -EINVAL; + } + + if (traceprobe_conflict_field_name(parg->name, tp->args, i)) { + pr_info("Argument[%d]: '%s' conflicts with another field.\n", + i, parg->name); + return -EINVAL; + } + + /* Parse fetch argument */ + ret = traceprobe_parse_probe_arg_body(body, &tp->size, parg, flags); + if (ret) + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + return ret; } void traceprobe_free_probe_arg(struct probe_arg *arg) { - if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) - free_bitfield_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) - free_deref_fetch_param(arg->fetch.data); - else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) - free_symbol_cache(arg->fetch.data); + struct fetch_insn *code = arg->code; + while (code && code->op != FETCH_OP_END) { + if (code->op == FETCH_NOP_SYMBOL) + kfree(code->data); + code++; + } + kfree(arg->code); kfree(arg->name); kfree(arg->comm); + kfree(arg->fmt); +} + +int traceprobe_update_arg(struct probe_arg *arg) +{ + struct fetch_insn *code = arg->code; + long offset; + char *tmp; + char c; + int ret = 0; + + while (code && code->op != FETCH_OP_END) { + if (code->op == FETCH_NOP_SYMBOL) { + if (code[1].op != FETCH_OP_IMM) + return -EINVAL; + + tmp = strpbrk(code->data, "+-"); + if (tmp) + c = *tmp; + ret = traceprobe_split_symbol_offset(code->data, + &offset); + if (ret) + return ret; + + code[1].immediate = + (unsigned long)kallsyms_lookup_name(code->data); + if (tmp) + *tmp = c; + if (!code[1].immediate) + return -ENOENT; + code[1].immediate += offset; + } + code++; + } + return 0; } +/* When len=0, we just calculate the needed length */ +#define LEN_OR_ZERO (len ? len - pos : 0) static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, bool is_return) { - int i; + struct probe_arg *parg; + int i, j; int pos = 0; - const char *fmt, *arg; if (!is_return) { @@ -625,35 +643,51 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; } - /* When len=0, we just calculate the needed length */ -#define LEN_OR_ZERO (len ? len - pos : 0) - pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt); for (i = 0; i < tp->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s", - tp->args[i].name, tp->args[i].type->fmt); + parg = tp->args + i; + pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=", parg->name); + if (parg->count) { + pos += snprintf(buf + pos, LEN_OR_ZERO, "{%s", + parg->type->fmt); + for (j = 1; j < parg->count; j++) + pos += snprintf(buf + pos, LEN_OR_ZERO, ",%s", + parg->type->fmt); + pos += snprintf(buf + pos, LEN_OR_ZERO, "}"); + } else + pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", + parg->type->fmt); } pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); for (i = 0; i < tp->nr_args; i++) { - if (strcmp(tp->args[i].type->name, "string") == 0) + parg = tp->args + i; + if (parg->count) { + if (strcmp(parg->type->name, "string") == 0) + fmt = ", __get_str(%s[%d])"; + else + fmt = ", REC->%s[%d]"; + for (j = 0; j < parg->count; j++) + pos += snprintf(buf + pos, LEN_OR_ZERO, + fmt, parg->name, j); + } else { + if (strcmp(parg->type->name, "string") == 0) + fmt = ", __get_str(%s)"; + else + fmt = ", REC->%s"; pos += snprintf(buf + pos, LEN_OR_ZERO, - ", __get_str(%s)", - tp->args[i].name); - else - pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", - tp->args[i].name); + fmt, parg->name); + } } -#undef LEN_OR_ZERO - /* return the length of print_fmt */ return pos; } +#undef LEN_OR_ZERO -int set_print_fmt(struct trace_probe *tp, bool is_return) +int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return) { int len; char *print_fmt; @@ -670,3 +704,28 @@ int set_print_fmt(struct trace_probe *tp, bool is_return) return 0; } + +int traceprobe_define_arg_fields(struct trace_event_call *event_call, + size_t offset, struct trace_probe *tp) +{ + int ret, i; + + /* Set argument names as fields */ + for (i = 0; i < tp->nr_args; i++) { + struct probe_arg *parg = &tp->args[i]; + const char *fmt = parg->type->fmttype; + int size = parg->type->size; + + if (parg->fmt) + fmt = parg->fmt; + if (parg->count) + size *= parg->count; + ret = trace_define_field(event_call, fmt, parg->name, + offset + parg->offset, size, + parg->type->is_signed, + FILTER_OTHER); + if (ret) + return ret; + } + return 0; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 5f52668e165d..8a63f8bc01bc 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -23,6 +23,7 @@ #include <linux/stringify.h> #include <linux/limits.h> #include <linux/uaccess.h> +#include <linux/bitops.h> #include <asm/bitsperlong.h> #include "trace.h" @@ -30,6 +31,7 @@ #define MAX_TRACE_ARGS 128 #define MAX_ARGSTR_LEN 63 +#define MAX_ARRAY_LEN 64 #define MAX_STRING_SIZE PATH_MAX /* Reserved field names */ @@ -54,50 +56,74 @@ #define TP_FLAG_PROFILE 2 #define TP_FLAG_REGISTERED 4 +/* data_loc: data location, compatible with u32 */ +#define make_data_loc(len, offs) \ + (((u32)(len) << 16) | ((u32)(offs) & 0xffff)) +#define get_loc_len(dl) ((u32)(dl) >> 16) +#define get_loc_offs(dl) ((u32)(dl) & 0xffff) -/* data_rloc: data relative location, compatible with u32 */ -#define make_data_rloc(len, roffs) \ - (((u32)(len) << 16) | ((u32)(roffs) & 0xffff)) -#define get_rloc_len(dl) ((u32)(dl) >> 16) -#define get_rloc_offs(dl) ((u32)(dl) & 0xffff) - -/* - * Convert data_rloc to data_loc: - * data_rloc stores the offset from data_rloc itself, but data_loc - * stores the offset from event entry. - */ -#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) - -static nokprobe_inline void *get_rloc_data(u32 *dl) +static nokprobe_inline void *get_loc_data(u32 *dl, void *ent) { - return (u8 *)dl + get_rloc_offs(*dl); + return (u8 *)ent + get_loc_offs(*dl); } -/* For data_loc conversion */ -static nokprobe_inline void *get_loc_data(u32 *dl, void *ent) +static nokprobe_inline u32 update_data_loc(u32 loc, int consumed) { - return (u8 *)ent + get_rloc_offs(*dl); + u32 maxlen = get_loc_len(loc); + u32 offset = get_loc_offs(loc); + + return make_data_loc(maxlen - consumed, offset + consumed); } -/* Data fetch function type */ -typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); /* Printing function type */ -typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *); - -/* Fetch types */ -enum { - FETCH_MTD_reg = 0, - FETCH_MTD_stack, - FETCH_MTD_retval, - FETCH_MTD_comm, - FETCH_MTD_memory, - FETCH_MTD_symbol, - FETCH_MTD_deref, - FETCH_MTD_bitfield, - FETCH_MTD_file_offset, - FETCH_MTD_END, +typedef int (*print_type_func_t)(struct trace_seq *, void *, void *); + +enum fetch_op { + FETCH_OP_NOP = 0, + // Stage 1 (load) ops + FETCH_OP_REG, /* Register : .param = offset */ + FETCH_OP_STACK, /* Stack : .param = index */ + FETCH_OP_STACKP, /* Stack pointer */ + FETCH_OP_RETVAL, /* Return value */ + FETCH_OP_IMM, /* Immediate : .immediate */ + FETCH_OP_COMM, /* Current comm */ + FETCH_OP_ARG, /* Function argument : .param */ + FETCH_OP_FOFFS, /* File offset: .immediate */ + // Stage 2 (dereference) op + FETCH_OP_DEREF, /* Dereference: .offset */ + // Stage 3 (store) ops + FETCH_OP_ST_RAW, /* Raw: .size */ + FETCH_OP_ST_MEM, /* Mem: .offset, .size */ + FETCH_OP_ST_STRING, /* String: .offset, .size */ + // Stage 4 (modify) op + FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */ + // Stage 5 (loop) op + FETCH_OP_LP_ARRAY, /* Array: .param = loop count */ + FETCH_OP_END, + FETCH_NOP_SYMBOL, /* Unresolved Symbol holder */ }; +struct fetch_insn { + enum fetch_op op; + union { + unsigned int param; + struct { + unsigned int size; + int offset; + }; + struct { + unsigned char basesize; + unsigned char lshift; + unsigned char rshift; + }; + unsigned long immediate; + void *data; + }; +}; + +/* fetch + deref*N + store + mod + end <= 16, this allows N=12, enough */ +#define FETCH_INSN_MAX 16 + /* Fetch type information table */ struct fetch_type { const char *name; /* Name of type */ @@ -106,13 +132,6 @@ struct fetch_type { print_type_func_t print; /* Print functions */ const char *fmt; /* Fromat string */ const char *fmttype; /* Name in format file */ - /* Fetch functions */ - fetch_func_t fetch[FETCH_MTD_END]; -}; - -struct fetch_param { - fetch_func_t fn; - void *data; }; /* For defining macros, define string/string_size types */ @@ -124,8 +143,7 @@ typedef u32 string_size; /* Printing in basic type function template */ #define DECLARE_BASIC_PRINT_TYPE_FUNC(type) \ -int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name, \ - void *data, void *ent); \ +int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, void *data, void *ent);\ extern const char PRINT_TYPE_FMT_NAME(type)[] DECLARE_BASIC_PRINT_TYPE_FUNC(u8); @@ -142,57 +160,7 @@ DECLARE_BASIC_PRINT_TYPE_FUNC(x32); DECLARE_BASIC_PRINT_TYPE_FUNC(x64); DECLARE_BASIC_PRINT_TYPE_FUNC(string); - -#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type - -/* Declare macro for basic types */ -#define DECLARE_FETCH_FUNC(method, type) \ -extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, \ - void *data, void *dest) - -#define DECLARE_BASIC_FETCH_FUNCS(method) \ -DECLARE_FETCH_FUNC(method, u8); \ -DECLARE_FETCH_FUNC(method, u16); \ -DECLARE_FETCH_FUNC(method, u32); \ -DECLARE_FETCH_FUNC(method, u64) - -DECLARE_BASIC_FETCH_FUNCS(reg); -#define fetch_reg_string NULL -#define fetch_reg_string_size NULL - -DECLARE_BASIC_FETCH_FUNCS(retval); -#define fetch_retval_string NULL -#define fetch_retval_string_size NULL - -DECLARE_BASIC_FETCH_FUNCS(symbol); -DECLARE_FETCH_FUNC(symbol, string); -DECLARE_FETCH_FUNC(symbol, string_size); - -DECLARE_BASIC_FETCH_FUNCS(deref); -DECLARE_FETCH_FUNC(deref, string); -DECLARE_FETCH_FUNC(deref, string_size); - -DECLARE_BASIC_FETCH_FUNCS(bitfield); -#define fetch_bitfield_string NULL -#define fetch_bitfield_string_size NULL - -/* comm only makes sense as a string */ -#define fetch_comm_u8 NULL -#define fetch_comm_u16 NULL -#define fetch_comm_u32 NULL -#define fetch_comm_u64 NULL -DECLARE_FETCH_FUNC(comm, string); -DECLARE_FETCH_FUNC(comm, string_size); - -/* - * Define macro for basic types - we don't need to define s* types, because - * we have to care only about bitwidth at recording time. - */ -#define DEFINE_BASIC_FETCH_FUNCS(method) \ -DEFINE_FETCH_##method(u8) \ -DEFINE_FETCH_##method(u16) \ -DEFINE_FETCH_##method(u32) \ -DEFINE_FETCH_##method(u64) +DECLARE_BASIC_PRINT_TYPE_FUNC(symbol); /* Default (unsigned long) fetch type */ #define __DEFAULT_FETCH_TYPE(t) x##t @@ -200,8 +168,9 @@ DEFINE_FETCH_##method(u64) #define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) #define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) -#define ASSIGN_FETCH_FUNC(method, type) \ - [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type) +#define __ADDR_FETCH_TYPE(t) u##t +#define _ADDR_FETCH_TYPE(t) __ADDR_FETCH_TYPE(t) +#define ADDR_FETCH_TYPE _ADDR_FETCH_TYPE(BITS_PER_LONG) #define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ {.name = _name, \ @@ -210,64 +179,23 @@ DEFINE_FETCH_##method(u64) .print = PRINT_TYPE_FUNC_NAME(ptype), \ .fmt = PRINT_TYPE_FMT_NAME(ptype), \ .fmttype = _fmttype, \ - .fetch = { \ -ASSIGN_FETCH_FUNC(reg, ftype), \ -ASSIGN_FETCH_FUNC(stack, ftype), \ -ASSIGN_FETCH_FUNC(retval, ftype), \ -ASSIGN_FETCH_FUNC(comm, ftype), \ -ASSIGN_FETCH_FUNC(memory, ftype), \ -ASSIGN_FETCH_FUNC(symbol, ftype), \ -ASSIGN_FETCH_FUNC(deref, ftype), \ -ASSIGN_FETCH_FUNC(bitfield, ftype), \ -ASSIGN_FETCH_FUNC(file_offset, ftype), \ - } \ } - +#define _ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ + __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, #_fmttype) #define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ - __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype) + _ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, ptype) /* If ptype is an alias of atype, use this macro (show atype in format) */ #define ASSIGN_FETCH_TYPE_ALIAS(ptype, atype, ftype, sign) \ - __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #atype) + _ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, atype) #define ASSIGN_FETCH_TYPE_END {} - -#define FETCH_TYPE_STRING 0 -#define FETCH_TYPE_STRSIZE 1 +#define MAX_ARRAY_LEN 64 #ifdef CONFIG_KPROBE_EVENTS -struct symbol_cache; -unsigned long update_symbol_cache(struct symbol_cache *sc); -void free_symbol_cache(struct symbol_cache *sc); -struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); bool trace_kprobe_on_func_entry(struct trace_event_call *call); bool trace_kprobe_error_injectable(struct trace_event_call *call); #else -/* uprobes do not support symbol fetch methods */ -#define fetch_symbol_u8 NULL -#define fetch_symbol_u16 NULL -#define fetch_symbol_u32 NULL -#define fetch_symbol_u64 NULL -#define fetch_symbol_string NULL -#define fetch_symbol_string_size NULL - -struct symbol_cache { -}; -static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc) -{ - return 0; -} - -static inline void __used free_symbol_cache(struct symbol_cache *sc) -{ -} - -static inline struct symbol_cache * __used -alloc_symbol_cache(const char *sym, long offset) -{ - return NULL; -} - static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call) { return false; @@ -280,11 +208,13 @@ static inline bool trace_kprobe_error_injectable(struct trace_event_call *call) #endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { - struct fetch_param fetch; - struct fetch_param fetch_size; + struct fetch_insn *code; + bool dynamic;/* Dynamic array (string) is used */ unsigned int offset; /* Offset from argument entry */ + unsigned int count; /* Array count */ const char *name; /* Name of this argument */ const char *comm; /* Command of this argument */ + char *fmt; /* Format string if needed */ const struct fetch_type *type; /* Type of this argument */ }; @@ -313,12 +243,6 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp) return !!(tp->flags & TP_FLAG_REGISTERED); } -static nokprobe_inline void call_fetch(struct fetch_param *fprm, - struct pt_regs *regs, void *dest) -{ - return fprm->fn(regs, fprm->data, dest); -} - /* Check the name is good for event/group/fields */ static inline bool is_good_name(const char *name) { @@ -343,67 +267,22 @@ find_event_file_link(struct trace_probe *tp, struct trace_event_file *file) return NULL; } -extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size, - struct probe_arg *parg, bool is_return, bool is_kprobe, - const struct fetch_type *ftbl); +#define TPARG_FL_RETURN BIT(0) +#define TPARG_FL_KERNEL BIT(1) +#define TPARG_FL_FENTRY BIT(2) +#define TPARG_FL_MASK GENMASK(2, 0) -extern int traceprobe_conflict_field_name(const char *name, - struct probe_arg *args, int narg); +extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, + char *arg, unsigned int flags); -extern void traceprobe_update_arg(struct probe_arg *arg); +extern int traceprobe_update_arg(struct probe_arg *arg); extern void traceprobe_free_probe_arg(struct probe_arg *arg); extern int traceprobe_split_symbol_offset(char *symbol, long *offset); +extern int traceprobe_parse_event_name(const char **pevent, + const char **pgroup, char *buf); -/* Sum up total data length for dynamic arraies (strings) */ -static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs) -{ - int i, ret = 0; - u32 len; - - for (i = 0; i < tp->nr_args; i++) - if (unlikely(tp->args[i].fetch_size.fn)) { - call_fetch(&tp->args[i].fetch_size, regs, &len); - ret += len; - } - - return ret; -} - -/* Store the value of each argument */ -static nokprobe_inline void -store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs, - u8 *data, int maxlen) -{ - int i; - u32 end = tp->size; - u32 *dl; /* Data (relative) location */ - - for (i = 0; i < tp->nr_args; i++) { - if (unlikely(tp->args[i].fetch_size.fn)) { - /* - * First, we set the relative location and - * maximum data length to *dl - */ - dl = (u32 *)(data + tp->args[i].offset); - *dl = make_data_rloc(maxlen, end - tp->args[i].offset); - /* Then try to fetch string or dynamic array data */ - call_fetch(&tp->args[i].fetch, regs, dl); - /* Reduce maximum length */ - end += get_rloc_len(*dl); - maxlen -= get_rloc_len(*dl); - /* Trick here, convert data_rloc to data_loc */ - *dl = convert_rloc_to_loc(*dl, - ent_size + tp->args[i].offset); - } else - /* Just fetching data normally */ - call_fetch(&tp->args[i].fetch, regs, - data + tp->args[i].offset); - } -} - -extern int set_print_fmt(struct trace_probe *tp, bool is_return); +extern int traceprobe_set_print_fmt(struct trace_probe *tp, bool is_return); #ifdef CONFIG_PERF_EVENTS extern struct trace_event_call * @@ -412,6 +291,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, extern void destroy_local_trace_kprobe(struct trace_event_call *event_call); extern struct trace_event_call * -create_local_trace_uprobe(char *name, unsigned long offs, bool is_return); +create_local_trace_uprobe(char *name, unsigned long offs, + unsigned long ref_ctr_offset, bool is_return); extern void destroy_local_trace_uprobe(struct trace_event_call *event_call); #endif +extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, + size_t offset, struct trace_probe *tp); diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h new file mode 100644 index 000000000000..4737bb8c07a3 --- /dev/null +++ b/kernel/trace/trace_probe_tmpl.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Traceprobe fetch helper inlines + */ + +static nokprobe_inline void +fetch_store_raw(unsigned long val, struct fetch_insn *code, void *buf) +{ + switch (code->size) { + case 1: + *(u8 *)buf = (u8)val; + break; + case 2: + *(u16 *)buf = (u16)val; + break; + case 4: + *(u32 *)buf = (u32)val; + break; + case 8: + //TBD: 32bit signed + *(u64 *)buf = (u64)val; + break; + default: + *(unsigned long *)buf = val; + } +} + +static nokprobe_inline void +fetch_apply_bitfield(struct fetch_insn *code, void *buf) +{ + switch (code->basesize) { + case 1: + *(u8 *)buf <<= code->lshift; + *(u8 *)buf >>= code->rshift; + break; + case 2: + *(u16 *)buf <<= code->lshift; + *(u16 *)buf >>= code->rshift; + break; + case 4: + *(u32 *)buf <<= code->lshift; + *(u32 *)buf >>= code->rshift; + break; + case 8: + *(u64 *)buf <<= code->lshift; + *(u64 *)buf >>= code->rshift; + break; + } +} + +/* + * These functions must be defined for each callsite. + * Return consumed dynamic data size (>= 0), or error (< 0). + * If dest is NULL, don't store result and return required dynamic data size. + */ +static int +process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, + void *dest, void *base); +static nokprobe_inline int fetch_store_strlen(unsigned long addr); +static nokprobe_inline int +fetch_store_string(unsigned long addr, void *dest, void *base); +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size); + +/* From the 2nd stage, routine is same */ +static nokprobe_inline int +process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val, + void *dest, void *base) +{ + struct fetch_insn *s3 = NULL; + int total = 0, ret = 0, i = 0; + u32 loc = 0; + unsigned long lval = val; + +stage2: + /* 2nd stage: dereference memory if needed */ + while (code->op == FETCH_OP_DEREF) { + lval = val; + ret = probe_mem_read(&val, (void *)val + code->offset, + sizeof(val)); + if (ret) + return ret; + code++; + } + + s3 = code; +stage3: + /* 3rd stage: store value to buffer */ + if (unlikely(!dest)) { + if (code->op == FETCH_OP_ST_STRING) { + ret += fetch_store_strlen(val + code->offset); + code++; + goto array; + } else + return -EILSEQ; + } + + switch (code->op) { + case FETCH_OP_ST_RAW: + fetch_store_raw(val, code, dest); + break; + case FETCH_OP_ST_MEM: + probe_mem_read(dest, (void *)val + code->offset, code->size); + break; + case FETCH_OP_ST_STRING: + loc = *(u32 *)dest; + ret = fetch_store_string(val + code->offset, dest, base); + break; + default: + return -EILSEQ; + } + code++; + + /* 4th stage: modify stored value if needed */ + if (code->op == FETCH_OP_MOD_BF) { + fetch_apply_bitfield(code, dest); + code++; + } + +array: + /* the last stage: Loop on array */ + if (code->op == FETCH_OP_LP_ARRAY) { + total += ret; + if (++i < code->param) { + code = s3; + if (s3->op != FETCH_OP_ST_STRING) { + dest += s3->size; + val += s3->size; + goto stage3; + } + code--; + val = lval + sizeof(char *); + if (dest) { + dest += sizeof(u32); + *(u32 *)dest = update_data_loc(loc, ret); + } + goto stage2; + } + code++; + ret = total; + } + + return code->op == FETCH_OP_END ? ret : -EILSEQ; +} + +/* Sum up total data length for dynamic arraies (strings) */ +static nokprobe_inline int +__get_data_size(struct trace_probe *tp, struct pt_regs *regs) +{ + struct probe_arg *arg; + int i, len, ret = 0; + + for (i = 0; i < tp->nr_args; i++) { + arg = tp->args + i; + if (unlikely(arg->dynamic)) { + len = process_fetch_insn(arg->code, regs, NULL, NULL); + if (len > 0) + ret += len; + } + } + + return ret; +} + +/* Store the value of each argument */ +static nokprobe_inline void +store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs, + int header_size, int maxlen) +{ + struct probe_arg *arg; + void *base = data - header_size; + void *dyndata = data + tp->size; + u32 *dl; /* Data location */ + int ret, i; + + for (i = 0; i < tp->nr_args; i++) { + arg = tp->args + i; + dl = data + arg->offset; + /* Point the dynamic data area if needed */ + if (unlikely(arg->dynamic)) + *dl = make_data_loc(maxlen, dyndata - base); + ret = process_fetch_insn(arg->code, regs, dl, base); + if (unlikely(ret < 0 && arg->dynamic)) { + *dl = make_data_loc(0, dyndata - base); + } else { + dyndata += ret; + maxlen -= ret; + } + } +} + +static inline int +print_probe_args(struct trace_seq *s, struct probe_arg *args, int nr_args, + u8 *data, void *field) +{ + void *p; + int i, j; + + for (i = 0; i < nr_args; i++) { + struct probe_arg *a = args + i; + + trace_seq_printf(s, " %s=", a->name); + if (likely(!a->count)) { + if (!a->type->print(s, data + a->offset, field)) + return -ENOMEM; + continue; + } + trace_seq_putc(s, '{'); + p = data + a->offset; + for (j = 0; j < a->count; j++) { + if (!a->type->print(s, p, field)) + return -ENOMEM; + trace_seq_putc(s, j == a->count - 1 ? '}' : ','); + p += a->type->size; + } + } + return 0; +} diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index a86b303e6c67..4ea7e6845efb 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -35,26 +35,19 @@ static arch_spinlock_t wakeup_lock = static void wakeup_reset(struct trace_array *tr); static void __wakeup_reset(struct trace_array *tr); +static int start_func_tracer(struct trace_array *tr, int graph); +static void stop_func_tracer(struct trace_array *tr, int graph); static int save_flags; #ifdef CONFIG_FUNCTION_GRAPH_TRACER -static int wakeup_display_graph(struct trace_array *tr, int set); # define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH) #else -static inline int wakeup_display_graph(struct trace_array *tr, int set) -{ - return 0; -} # define is_graph(tr) false #endif - #ifdef CONFIG_FUNCTION_TRACER -static int wakeup_graph_entry(struct ftrace_graph_ent *trace); -static void wakeup_graph_return(struct ftrace_graph_ret *trace); - static bool function_enabled; /* @@ -104,122 +97,8 @@ out_enable: return 0; } -/* - * wakeup uses its own tracer function to keep the overhead down: - */ -static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) -{ - struct trace_array *tr = wakeup_trace; - struct trace_array_cpu *data; - unsigned long flags; - int pc; - - if (!func_prolog_preempt_disable(tr, &data, &pc)) - return; - - local_irq_save(flags); - trace_function(tr, ip, parent_ip, flags, pc); - local_irq_restore(flags); - - atomic_dec(&data->disabled); - preempt_enable_notrace(); -} - -static int register_wakeup_function(struct trace_array *tr, int graph, int set) -{ - int ret; - - /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ - if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION))) - return 0; - - if (graph) - ret = register_ftrace_graph(&wakeup_graph_return, - &wakeup_graph_entry); - else - ret = register_ftrace_function(tr->ops); - - if (!ret) - function_enabled = true; - - return ret; -} - -static void unregister_wakeup_function(struct trace_array *tr, int graph) -{ - if (!function_enabled) - return; - - if (graph) - unregister_ftrace_graph(); - else - unregister_ftrace_function(tr->ops); - - function_enabled = false; -} - -static int wakeup_function_set(struct trace_array *tr, u32 mask, int set) -{ - if (!(mask & TRACE_ITER_FUNCTION)) - return 0; - - if (set) - register_wakeup_function(tr, is_graph(tr), 1); - else - unregister_wakeup_function(tr, is_graph(tr)); - return 1; -} -#else -static int register_wakeup_function(struct trace_array *tr, int graph, int set) -{ - return 0; -} -static void unregister_wakeup_function(struct trace_array *tr, int graph) { } -static int wakeup_function_set(struct trace_array *tr, u32 mask, int set) -{ - return 0; -} -#endif /* CONFIG_FUNCTION_TRACER */ - -static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) -{ - struct tracer *tracer = tr->current_trace; - - if (wakeup_function_set(tr, mask, set)) - return 0; - #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (mask & TRACE_ITER_DISPLAY_GRAPH) - return wakeup_display_graph(tr, set); -#endif - - return trace_keep_overwrite(tracer, mask, set); -} -static int start_func_tracer(struct trace_array *tr, int graph) -{ - int ret; - - ret = register_wakeup_function(tr, graph, 0); - - if (!ret && tracing_is_enabled()) - tracer_enabled = 1; - else - tracer_enabled = 0; - - return ret; -} - -static void stop_func_tracer(struct trace_array *tr, int graph) -{ - tracer_enabled = 0; - - unregister_wakeup_function(tr, graph); -} - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER static int wakeup_display_graph(struct trace_array *tr, int set) { if (!(is_graph(tr) ^ set)) @@ -270,6 +149,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_preempt_disable(tr, &data, &pc)) return; @@ -281,6 +162,11 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) return; } +static struct fgraph_ops fgraph_wakeup_ops = { + .entryfunc = &wakeup_graph_entry, + .retfunc = &wakeup_graph_return, +}; + static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) @@ -316,20 +202,87 @@ static void wakeup_print_header(struct seq_file *s) else trace_default_header(s); } +#endif /* else CONFIG_FUNCTION_GRAPH_TRACER */ +/* + * wakeup uses its own tracer function to keep the overhead down: + */ static void -__trace_function(struct trace_array *tr, - unsigned long ip, unsigned long parent_ip, - unsigned long flags, int pc) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { - if (is_graph(tr)) - trace_graph_function(tr, ip, parent_ip, flags, pc); + struct trace_array *tr = wakeup_trace; + struct trace_array_cpu *data; + unsigned long flags; + int pc; + + if (!func_prolog_preempt_disable(tr, &data, &pc)) + return; + + local_irq_save(flags); + trace_function(tr, ip, parent_ip, flags, pc); + local_irq_restore(flags); + + atomic_dec(&data->disabled); + preempt_enable_notrace(); +} + +static int register_wakeup_function(struct trace_array *tr, int graph, int set) +{ + int ret; + + /* 'set' is set if TRACE_ITER_FUNCTION is about to be set */ + if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION))) + return 0; + + if (graph) + ret = register_ftrace_graph(&fgraph_wakeup_ops); else - trace_function(tr, ip, parent_ip, flags, pc); + ret = register_ftrace_function(tr->ops); + + if (!ret) + function_enabled = true; + + return ret; } -#else -#define __trace_function trace_function +static void unregister_wakeup_function(struct trace_array *tr, int graph) +{ + if (!function_enabled) + return; + + if (graph) + unregister_ftrace_graph(&fgraph_wakeup_ops); + else + unregister_ftrace_function(tr->ops); + + function_enabled = false; +} + +static int wakeup_function_set(struct trace_array *tr, u32 mask, int set) +{ + if (!(mask & TRACE_ITER_FUNCTION)) + return 0; + + if (set) + register_wakeup_function(tr, is_graph(tr), 1); + else + unregister_wakeup_function(tr, is_graph(tr)); + return 1; +} +#else /* CONFIG_FUNCTION_TRACER */ +static int register_wakeup_function(struct trace_array *tr, int graph, int set) +{ + return 0; +} +static void unregister_wakeup_function(struct trace_array *tr, int graph) { } +static int wakeup_function_set(struct trace_array *tr, u32 mask, int set) +{ + return 0; +} +#endif /* else CONFIG_FUNCTION_TRACER */ + +#ifndef CONFIG_FUNCTION_GRAPH_TRACER static enum print_line_t wakeup_print_line(struct trace_iterator *iter) { return TRACE_TYPE_UNHANDLED; @@ -338,23 +291,58 @@ static enum print_line_t wakeup_print_line(struct trace_iterator *iter) static void wakeup_trace_open(struct trace_iterator *iter) { } static void wakeup_trace_close(struct trace_iterator *iter) { } -#ifdef CONFIG_FUNCTION_TRACER -static int wakeup_graph_entry(struct ftrace_graph_ent *trace) -{ - return -1; -} -static void wakeup_graph_return(struct ftrace_graph_ret *trace) { } static void wakeup_print_header(struct seq_file *s) { trace_default_header(s); } -#else -static void wakeup_print_header(struct seq_file *s) +#endif /* !CONFIG_FUNCTION_GRAPH_TRACER */ + +static void +__trace_function(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, + unsigned long flags, int pc) { - trace_latency_header(s); + if (is_graph(tr)) + trace_graph_function(tr, ip, parent_ip, flags, pc); + else + trace_function(tr, ip, parent_ip, flags, pc); +} + +static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set) +{ + struct tracer *tracer = tr->current_trace; + + if (wakeup_function_set(tr, mask, set)) + return 0; + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (mask & TRACE_ITER_DISPLAY_GRAPH) + return wakeup_display_graph(tr, set); +#endif + + return trace_keep_overwrite(tracer, mask, set); +} + +static int start_func_tracer(struct trace_array *tr, int graph) +{ + int ret; + + ret = register_wakeup_function(tr, graph, 0); + + if (!ret && tracing_is_enabled()) + tracer_enabled = 1; + else + tracer_enabled = 0; + + return ret; +} + +static void stop_func_tracer(struct trace_array *tr, int graph) +{ + tracer_enabled = 0; + + unregister_wakeup_function(tr, graph); } -#endif /* CONFIG_FUNCTION_TRACER */ -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ /* * Should this new latency be reported/recorded? diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 11e9daa4a568..9d402e7fc949 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -741,6 +741,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) return trace_graph_entry(trace); } +static struct fgraph_ops fgraph_ops __initdata = { + .entryfunc = &trace_graph_entry_watchdog, + .retfunc = &trace_graph_return, +}; + /* * Pretty much the same than for the function tracer from which the selftest * has been borrowed. @@ -765,8 +770,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, */ tracing_reset_online_cpus(&tr->trace_buffer); set_graph_array(tr); - ret = register_ftrace_graph(&trace_graph_return, - &trace_graph_entry_watchdog); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); goto out; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4237eba4ef20..eec648a0d673 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,7 @@ check_stack(unsigned long ip, unsigned long *stack) stack_trace_max_size = this_size; stack_trace_max.nr_entries = 0; - stack_trace_max.skip = 3; + stack_trace_max.skip = 0; save_stack_trace(&stack_trace_max); @@ -286,7 +286,7 @@ __next(struct seq_file *m, loff_t *pos) { long n = *pos - 1; - if (n > stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX) + if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX) return NULL; m->private = (void *)n; @@ -448,8 +448,10 @@ static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata; static __init int enable_stacktrace(char *str) { - if (strncmp(str, "_filter=", 8) == 0) - strncpy(stack_trace_filter_buf, str+8, COMMAND_LINE_SIZE); + int len; + + if ((len = str_has_prefix(str, "_filter="))) + strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE); stack_tracer_enabled = 1; last_stack_tracer_enabled = 1; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e696667da29a..9bde07c06362 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -5,8 +5,9 @@ * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <[email protected]> */ -#define pr_fmt(fmt) "trace_kprobe: " fmt +#define pr_fmt(fmt) "trace_uprobe: " fmt +#include <linux/ctype.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/uprobes.h> @@ -14,7 +15,9 @@ #include <linux/string.h> #include <linux/rculist.h> +#include "trace_dynevent.h" #include "trace_probe.h" +#include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" @@ -36,21 +39,56 @@ struct trace_uprobe_filter { struct list_head perf_events; }; +static int trace_uprobe_create(int argc, const char **argv); +static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); +static int trace_uprobe_release(struct dyn_event *ev); +static bool trace_uprobe_is_busy(struct dyn_event *ev); +static bool trace_uprobe_match(const char *system, const char *event, + struct dyn_event *ev); + +static struct dyn_event_operations trace_uprobe_ops = { + .create = trace_uprobe_create, + .show = trace_uprobe_show, + .is_busy = trace_uprobe_is_busy, + .free = trace_uprobe_release, + .match = trace_uprobe_match, +}; + /* * uprobe event core functions */ struct trace_uprobe { - struct list_head list; + struct dyn_event devent; struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; char *filename; unsigned long offset; + unsigned long ref_ctr_offset; unsigned long nhit; struct trace_probe tp; }; +static bool is_trace_uprobe(struct dyn_event *ev) +{ + return ev->ops == &trace_uprobe_ops; +} + +static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) +{ + return container_of(ev, struct trace_uprobe, devent); +} + +/** + * for_each_trace_uprobe - iterate over the trace_uprobe list + * @pos: the struct trace_uprobe * for each entry + * @dpos: the struct dyn_event * to use as a loop cursor + */ +#define for_each_trace_uprobe(pos, dpos) \ + for_each_dyn_event(dpos) \ + if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) + #define SIZEOF_TRACE_UPROBE(n) \ (offsetof(struct trace_uprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) @@ -58,9 +96,6 @@ struct trace_uprobe { static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); -static DEFINE_MUTEX(uprobe_lock); -static LIST_HEAD(uprobe_list); - struct uprobe_dispatch_data { struct trace_uprobe *tu; unsigned long bp_addr; @@ -98,74 +133,59 @@ static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) /* * Uprobes-specific fetch functions */ -#define DEFINE_FETCH_stack(type) \ -static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs, \ - void *offset, void *dest) \ -{ \ - *(type *)dest = (type)get_user_stack_nth(regs, \ - ((unsigned long)offset)); \ -} -DEFINE_BASIC_FETCH_FUNCS(stack) -/* No string on the stack entry */ -#define fetch_stack_string NULL -#define fetch_stack_string_size NULL - -#define DEFINE_FETCH_memory(type) \ -static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs, \ - void *addr, void *dest) \ -{ \ - type retval; \ - void __user *vaddr = (void __force __user *) addr; \ - \ - if (copy_from_user(&retval, vaddr, sizeof(type))) \ - *(type *)dest = 0; \ - else \ - *(type *) dest = retval; \ +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ + void __user *vaddr = (void __force __user *)src; + + return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } -DEFINE_BASIC_FETCH_FUNCS(memory) /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ -static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, - void *addr, void *dest) +static nokprobe_inline int +fetch_store_string(unsigned long addr, void *dest, void *base) { long ret; - u32 rloc = *(u32 *)dest; - int maxlen = get_rloc_len(rloc); - u8 *dst = get_rloc_data(dest); + u32 loc = *(u32 *)dest; + int maxlen = get_loc_len(loc); + u8 *dst = get_loc_data(dest, base); void __user *src = (void __force __user *) addr; - if (!maxlen) - return; + if (unlikely(!maxlen)) + return -ENOMEM; ret = strncpy_from_user(dst, src, maxlen); - if (ret == maxlen) - dst[--ret] = '\0'; - - if (ret < 0) { /* Failed to fetch string */ - ((u8 *)get_rloc_data(dest))[0] = '\0'; - *(u32 *)dest = make_data_rloc(0, get_rloc_offs(rloc)); - } else { - *(u32 *)dest = make_data_rloc(ret, get_rloc_offs(rloc)); + if (ret >= 0) { + if (ret == maxlen) + dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; + *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } + + return ret; } -static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, - void *addr, void *dest) +/* Return the length of string -- including null terminal byte */ +static nokprobe_inline int +fetch_store_strlen(unsigned long addr) { int len; void __user *vaddr = (void __force __user *) addr; len = strnlen_user(vaddr, MAX_STRING_SIZE); - if (len == 0 || len > MAX_STRING_SIZE) /* Failed to check length */ - *(u32 *)dest = 0; - else - *(u32 *)dest = len; + return (len > MAX_STRING_SIZE) ? 0 : len; } -static unsigned long translate_user_vaddr(void *file_offset) +static unsigned long translate_user_vaddr(unsigned long file_offset) { unsigned long base_addr; struct uprobe_dispatch_data *udd; @@ -173,44 +193,44 @@ static unsigned long translate_user_vaddr(void *file_offset) udd = (void *) current->utask->vaddr; base_addr = udd->bp_addr - udd->tu->offset; - return base_addr + (unsigned long)file_offset; + return base_addr + file_offset; } -#define DEFINE_FETCH_file_offset(type) \ -static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs, \ - void *offset, void *dest)\ -{ \ - void *vaddr = (void *)translate_user_vaddr(offset); \ - \ - FETCH_FUNC_NAME(memory, type)(regs, vaddr, dest); \ +/* Note that we don't verify it, since the code does not come from user space */ +static int +process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, + void *base) +{ + unsigned long val; + + /* 1st stage: get value from context */ + switch (code->op) { + case FETCH_OP_REG: + val = regs_get_register(regs, code->param); + break; + case FETCH_OP_STACK: + val = get_user_stack_nth(regs, code->param); + break; + case FETCH_OP_STACKP: + val = user_stack_pointer(regs); + break; + case FETCH_OP_RETVAL: + val = regs_return_value(regs); + break; + case FETCH_OP_IMM: + val = code->immediate; + break; + case FETCH_OP_FOFFS: + val = translate_user_vaddr(code->immediate); + break; + default: + return -EILSEQ; + } + code++; + + return process_fetch_insn_bottom(code, val, dest, base); } -DEFINE_BASIC_FETCH_FUNCS(file_offset) -DEFINE_FETCH_file_offset(string) -DEFINE_FETCH_file_offset(string_size) - -/* Fetch type information table */ -static const struct fetch_type uprobes_fetch_type_table[] = { - /* Special types */ - [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, - sizeof(u32), 1, "__data_loc char[]"), - [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, - string_size, sizeof(u32), 0, "u32"), - /* Basic types */ - ASSIGN_FETCH_TYPE(u8, u8, 0), - ASSIGN_FETCH_TYPE(u16, u16, 0), - ASSIGN_FETCH_TYPE(u32, u32, 0), - ASSIGN_FETCH_TYPE(u64, u64, 0), - ASSIGN_FETCH_TYPE(s8, u8, 1), - ASSIGN_FETCH_TYPE(s16, u16, 1), - ASSIGN_FETCH_TYPE(s32, u32, 1), - ASSIGN_FETCH_TYPE(s64, u64, 1), - ASSIGN_FETCH_TYPE_ALIAS(x8, u8, u8, 0), - ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0), - ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0), - ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0), - - ASSIGN_FETCH_TYPE_END -}; +NOKPROBE_SYMBOL(process_fetch_insn) static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { @@ -229,6 +249,22 @@ static inline bool is_ret_probe(struct trace_uprobe *tu) return tu->consumer.ret_handler != NULL; } +static bool trace_uprobe_is_busy(struct dyn_event *ev) +{ + struct trace_uprobe *tu = to_trace_uprobe(ev); + + return trace_probe_is_enabled(&tu->tp); +} + +static bool trace_uprobe_match(const char *system, const char *event, + struct dyn_event *ev) +{ + struct trace_uprobe *tu = to_trace_uprobe(ev); + + return strcmp(trace_event_name(&tu->tp.call), event) == 0 && + (!system || strcmp(tu->tp.call.class->system, system) == 0); +} + /* * Allocate new trace_uprobe and initialize it (including uprobes). */ @@ -256,7 +292,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu->tp.class.system) goto error; - INIT_LIST_HEAD(&tu->list); + dyn_event_init(&tu->devent, &trace_uprobe_ops); INIT_LIST_HEAD(&tu->tp.files); tu->consumer.handler = uprobe_dispatcher; if (is_ret) @@ -275,6 +311,9 @@ static void free_trace_uprobe(struct trace_uprobe *tu) { int i; + if (!tu) + return; + for (i = 0; i < tu->tp.nr_args; i++) traceprobe_free_probe_arg(&tu->tp.args[i]); @@ -287,9 +326,10 @@ static void free_trace_uprobe(struct trace_uprobe *tu) static struct trace_uprobe *find_probe_event(const char *event, const char *group) { + struct dyn_event *pos; struct trace_uprobe *tu; - list_for_each_entry(tu, &uprobe_list, list) + for_each_trace_uprobe(tu, pos) if (strcmp(trace_event_name(&tu->tp.call), event) == 0 && strcmp(tu->tp.call.class->system, group) == 0) return tu; @@ -297,7 +337,7 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou return NULL; } -/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */ +/* Unregister a trace_uprobe and probe_event */ static int unregister_trace_uprobe(struct trace_uprobe *tu) { int ret; @@ -306,22 +346,56 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu) if (ret) return ret; - list_del(&tu->list); + dyn_event_remove(&tu->devent); free_trace_uprobe(tu); return 0; } +/* + * Uprobe with multiple reference counter is not allowed. i.e. + * If inode and offset matches, reference counter offset *must* + * match as well. Though, there is one exception: If user is + * replacing old trace_uprobe with new one(same group/event), + * then we allow same uprobe with new reference counter as far + * as the new one does not conflict with any other existing + * ones. + */ +static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new) +{ + struct dyn_event *pos; + struct trace_uprobe *tmp, *old = NULL; + struct inode *new_inode = d_real_inode(new->path.dentry); + + old = find_probe_event(trace_event_name(&new->tp.call), + new->tp.call.class->system); + + for_each_trace_uprobe(tmp, pos) { + if ((old ? old != tmp : true) && + new_inode == d_real_inode(tmp->path.dentry) && + new->offset == tmp->offset && + new->ref_ctr_offset != tmp->ref_ctr_offset) { + pr_warn("Reference counter offset mismatch."); + return ERR_PTR(-EINVAL); + } + } + return old; +} + /* Register a trace_uprobe and probe_event */ static int register_trace_uprobe(struct trace_uprobe *tu) { struct trace_uprobe *old_tu; int ret; - mutex_lock(&uprobe_lock); + mutex_lock(&event_mutex); /* register as an event */ - old_tu = find_probe_event(trace_event_name(&tu->tp.call), - tu->tp.call.class->system); + old_tu = find_old_trace_uprobe(tu); + if (IS_ERR(old_tu)) { + ret = PTR_ERR(old_tu); + goto end; + } + if (old_tu) { /* delete old event */ ret = unregister_trace_uprobe(old_tu); @@ -335,10 +409,10 @@ static int register_trace_uprobe(struct trace_uprobe *tu) goto end; } - list_add_tail(&tu->list, &uprobe_list); + dyn_event_add(&tu->devent); end: - mutex_unlock(&uprobe_lock); + mutex_unlock(&event_mutex); return ret; } @@ -349,95 +423,74 @@ end: * * - Remove uprobe: -:[GRP/]EVENT */ -static int create_trace_uprobe(int argc, char **argv) +static int trace_uprobe_create(int argc, const char **argv) { struct trace_uprobe *tu; - char *arg, *event, *group, *filename; + const char *event = NULL, *group = UPROBE_EVENT_SYSTEM; + char *arg, *filename, *rctr, *rctr_end, *tmp; char buf[MAX_EVENT_NAME_LEN]; struct path path; - unsigned long offset; - bool is_delete, is_return; + unsigned long offset, ref_ctr_offset; + bool is_return = false; int i, ret; ret = 0; - is_delete = false; - is_return = false; - event = NULL; - group = NULL; + ref_ctr_offset = 0; /* argc must be >= 1 */ - if (argv[0][0] == '-') - is_delete = true; - else if (argv[0][0] == 'r') + if (argv[0][0] == 'r') is_return = true; - else if (argv[0][0] != 'p') { - pr_info("Probe definition must be started with 'p', 'r' or '-'.\n"); - return -EINVAL; - } + else if (argv[0][0] != 'p' || argc < 2) + return -ECANCELED; - if (argv[0][1] == ':') { + if (argv[0][1] == ':') event = &argv[0][2]; - arg = strchr(event, '/'); - if (arg) { - group = event; - event = arg + 1; - event[-1] = '\0'; + if (!strchr(argv[1], '/')) + return -ECANCELED; - if (strlen(group) == 0) { - pr_info("Group name is not specified\n"); - return -EINVAL; - } - } - if (strlen(event) == 0) { - pr_info("Event name is not specified\n"); - return -EINVAL; - } - } - if (!group) - group = UPROBE_EVENT_SYSTEM; - - if (is_delete) { - int ret; - - if (!event) { - pr_info("Delete command needs an event name.\n"); - return -EINVAL; - } - mutex_lock(&uprobe_lock); - tu = find_probe_event(event, group); - - if (!tu) { - mutex_unlock(&uprobe_lock); - pr_info("Event %s/%s doesn't exist.\n", group, event); - return -ENOENT; - } - /* delete an event */ - ret = unregister_trace_uprobe(tu); - mutex_unlock(&uprobe_lock); - return ret; - } + filename = kstrdup(argv[1], GFP_KERNEL); + if (!filename) + return -ENOMEM; - if (argc < 2) { - pr_info("Probe point is not specified.\n"); - return -EINVAL; - } /* Find the last occurrence, in case the path contains ':' too. */ - arg = strrchr(argv[1], ':'); - if (!arg) - return -EINVAL; + arg = strrchr(filename, ':'); + if (!arg || !isdigit(arg[1])) { + kfree(filename); + return -ECANCELED; + } *arg++ = '\0'; - filename = argv[1]; ret = kern_path(filename, LOOKUP_FOLLOW, &path); - if (ret) + if (ret) { + kfree(filename); return ret; - + } if (!d_is_reg(path.dentry)) { ret = -EINVAL; goto fail_address_parse; } + /* Parse reference counter offset if specified. */ + rctr = strchr(arg, '('); + if (rctr) { + rctr_end = strchr(rctr, ')'); + if (rctr > rctr_end || *(rctr_end + 1) != 0) { + ret = -EINVAL; + pr_info("Invalid reference counter offset.\n"); + goto fail_address_parse; + } + + *rctr++ = '\0'; + *rctr_end = '\0'; + ret = kstrtoul(rctr, 0, &ref_ctr_offset); + if (ret) { + pr_info("Invalid reference counter offset.\n"); + goto fail_address_parse; + } + } + + /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) goto fail_address_parse; @@ -446,7 +499,11 @@ static int create_trace_uprobe(int argc, char **argv) argv += 2; /* setup a probe */ - if (!event) { + if (event) { + ret = traceprobe_parse_event_name(&event, &group, buf); + if (ret) + goto fail_address_parse; + } else { char *tail; char *ptr; @@ -472,62 +529,23 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } tu->offset = offset; + tu->ref_ctr_offset = ref_ctr_offset; tu->path = path; - tu->filename = kstrdup(filename, GFP_KERNEL); - - if (!tu->filename) { - pr_info("Failed to allocate filename.\n"); - ret = -ENOMEM; - goto error; - } + tu->filename = filename; /* parse arguments */ - ret = 0; for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { - struct probe_arg *parg = &tu->tp.args[i]; - - /* Increment count for freeing args in error case */ - tu->tp.nr_args++; - - /* Parse argument name */ - arg = strchr(argv[i], '='); - if (arg) { - *arg++ = '\0'; - parg->name = kstrdup(argv[i], GFP_KERNEL); - } else { - arg = argv[i]; - /* If argument name is omitted, set "argN" */ - snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); - parg->name = kstrdup(buf, GFP_KERNEL); - } - - if (!parg->name) { - pr_info("Failed to allocate argument[%d] name.\n", i); + tmp = kstrdup(argv[i], GFP_KERNEL); + if (!tmp) { ret = -ENOMEM; goto error; } - if (!is_good_name(parg->name)) { - pr_info("Invalid argument[%d] name: %s\n", i, parg->name); - ret = -EINVAL; - goto error; - } - - if (traceprobe_conflict_field_name(parg->name, tu->tp.args, i)) { - pr_info("Argument[%d] name '%s' conflicts with " - "another field.\n", i, argv[i]); - ret = -EINVAL; - goto error; - } - - /* Parse fetch argument */ - ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg, - is_return, false, - uprobes_fetch_type_table); - if (ret) { - pr_info("Parse error at argument[%d]. (%d)\n", i, ret); + ret = traceprobe_parse_probe_arg(&tu->tp, i, tmp, + is_return ? TPARG_FL_RETURN : 0); + kfree(tmp); + if (ret) goto error; - } } ret = register_trace_uprobe(tu); @@ -541,48 +559,35 @@ error: fail_address_parse: path_put(&path); + kfree(filename); pr_info("Failed to parse address or file.\n"); return ret; } -static int cleanup_all_probes(void) +static int create_or_delete_trace_uprobe(int argc, char **argv) { - struct trace_uprobe *tu; - int ret = 0; + int ret; - mutex_lock(&uprobe_lock); - while (!list_empty(&uprobe_list)) { - tu = list_entry(uprobe_list.next, struct trace_uprobe, list); - ret = unregister_trace_uprobe(tu); - if (ret) - break; - } - mutex_unlock(&uprobe_lock); - return ret; -} + if (argv[0][0] == '-') + return dyn_event_release(argc, argv, &trace_uprobe_ops); -/* Probes listing interfaces */ -static void *probes_seq_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&uprobe_lock); - return seq_list_start(&uprobe_list, *pos); + ret = trace_uprobe_create(argc, (const char **)argv); + return ret == -ECANCELED ? -EINVAL : ret; } -static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos) +static int trace_uprobe_release(struct dyn_event *ev) { - return seq_list_next(v, &uprobe_list, pos); -} + struct trace_uprobe *tu = to_trace_uprobe(ev); -static void probes_seq_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&uprobe_lock); + return unregister_trace_uprobe(tu); } -static int probes_seq_show(struct seq_file *m, void *v) +/* Probes listing interfaces */ +static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) { - struct trace_uprobe *tu = v; + struct trace_uprobe *tu = to_trace_uprobe(ev); char c = is_ret_probe(tu) ? 'r' : 'p'; int i; @@ -590,6 +595,9 @@ static int probes_seq_show(struct seq_file *m, void *v) trace_event_name(&tu->tp.call), tu->filename, (int)(sizeof(void *) * 2), tu->offset); + if (tu->ref_ctr_offset) + seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); + for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); @@ -597,11 +605,21 @@ static int probes_seq_show(struct seq_file *m, void *v) return 0; } +static int probes_seq_show(struct seq_file *m, void *v) +{ + struct dyn_event *ev = v; + + if (!is_trace_uprobe(ev)) + return 0; + + return trace_uprobe_show(m, ev); +} + static const struct seq_operations probes_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, - .show = probes_seq_show + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, + .show = probes_seq_show }; static int probes_open(struct inode *inode, struct file *file) @@ -609,7 +627,7 @@ static int probes_open(struct inode *inode, struct file *file) int ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - ret = cleanup_all_probes(); + ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) return ret; } @@ -620,7 +638,8 @@ static int probes_open(struct inode *inode, struct file *file) static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - return trace_parse_run_command(file, buffer, count, ppos, create_trace_uprobe); + return trace_parse_run_command(file, buffer, count, ppos, + create_or_delete_trace_uprobe); } static const struct file_operations uprobe_events_ops = { @@ -635,17 +654,22 @@ static const struct file_operations uprobe_events_ops = { /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { - struct trace_uprobe *tu = v; + struct dyn_event *ev = v; + struct trace_uprobe *tu; + if (!is_trace_uprobe(ev)) + return 0; + + tu = to_trace_uprobe(ev); seq_printf(m, " %s %-44s %15lu\n", tu->filename, trace_event_name(&tu->tp.call), tu->nhit); return 0; } static const struct seq_operations profile_seq_op = { - .start = probes_seq_start, - .next = probes_seq_next, - .stop = probes_seq_stop, + .start = dyn_event_seq_start, + .next = dyn_event_seq_next, + .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; @@ -833,7 +857,6 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; - int i; entry = (struct uprobe_trace_entry_head *)iter->ent; tu = container_of(event, struct trace_uprobe, tp.call.event); @@ -850,12 +873,8 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e data = DATAOF_TRACE_ENTRY(entry, false); } - for (i = 0; i < tu->tp.nr_args; i++) { - struct probe_arg *parg = &tu->tp.args[i]; - - if (!parg->type->print(s, parg->name, data + parg->offset, entry)) - goto out; - } + if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) + goto out; trace_seq_putc(s, '\n'); @@ -905,7 +924,13 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (tu->ref_ctr_offset) { + ret = uprobe_register_refctr(tu->inode, tu->offset, + tu->ref_ctr_offset, &tu->consumer); + } else { + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + } + if (ret) goto err_buffer; @@ -958,7 +983,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) static int uprobe_event_define_fields(struct trace_event_call *event_call) { - int ret, i, size; + int ret, size; struct uprobe_trace_entry_head field; struct trace_uprobe *tu = event_call->data; @@ -970,19 +995,8 @@ static int uprobe_event_define_fields(struct trace_event_call *event_call) DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); size = SIZEOF_TRACE_ENTRY(false); } - /* Set argument names as fields */ - for (i = 0; i < tu->tp.nr_args; i++) { - struct probe_arg *parg = &tu->tp.args[i]; - - ret = trace_define_field(event_call, parg->type->fmttype, - parg->name, size + parg->offset, - parg->type->size, parg->type->is_signed, - FILTER_OTHER); - if (ret) - return ret; - } - return 0; + return traceprobe_define_arg_fields(event_call, size, &tu->tp); } #ifdef CONFIG_PERF_EVENTS @@ -1233,7 +1247,7 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (tu->tp.flags & TP_FLAG_TRACE) ret |= uprobe_trace_func(tu, regs, ucb, dsize); @@ -1268,7 +1282,7 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); - store_trace_args(esize, &tu->tp, regs, ucb->buf, dsize); + store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (tu->tp.flags & TP_FLAG_TRACE) uretprobe_trace_func(tu, func, regs, ucb, dsize); @@ -1304,7 +1318,7 @@ static int register_uprobe_event(struct trace_uprobe *tu) init_trace_event_call(tu, call); - if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) + if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) return -ENOMEM; ret = register_trace_event(&call->event); @@ -1340,7 +1354,8 @@ static int unregister_uprobe_event(struct trace_uprobe *tu) #ifdef CONFIG_PERF_EVENTS struct trace_event_call * -create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) +create_local_trace_uprobe(char *name, unsigned long offs, + unsigned long ref_ctr_offset, bool is_return) { struct trace_uprobe *tu; struct path path; @@ -1356,7 +1371,7 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) } /* - * local trace_kprobes are not added to probe_list, so they are never + * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of * duplicated name "DUMMY_EVENT" here. */ @@ -1372,10 +1387,11 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) tu->offset = offs; tu->path = path; + tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu, &tu->tp.call); - if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) { + if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) { ret = -ENOMEM; goto error; } @@ -1403,6 +1419,11 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call) static __init int init_uprobe_trace(void) { struct dentry *d_tracer; + int ret; + + ret = dyn_event_register(&trace_uprobe_ops); + if (ret) + return ret; d_tracer = tracing_init_dentry(); if (IS_ERR(d_tracer)) |