diff options
Diffstat (limited to 'kernel/trace')
| -rw-r--r-- | kernel/trace/Kconfig | 6 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 11 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer.c | 62 | ||||
| -rw-r--r-- | kernel/trace/trace_kprobe.c | 33 | ||||
| -rw-r--r-- | kernel/trace/trace_probe.h | 12 |
5 files changed, 73 insertions, 51 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index ae3a2d519e50..0b249e2f0c3c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES on if you need to profile the system's use of these macros. config PROFILE_ALL_BRANCHES - bool "Profile all if conditionals" + bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING help This tracer profiles all branch conditions. Every if () @@ -533,9 +533,7 @@ config FUNCTION_PROFILER config BPF_KPROBE_OVERRIDE bool "Enable BPF programs to override a kprobed function" depends on BPF_EVENTS - depends on KPROBES_ON_FTRACE - depends on HAVE_KPROBE_OVERRIDE - depends on DYNAMIC_FTRACE_WITH_REGS + depends on FUNCTION_ERROR_INJECTION default n help Allows BPF to override the execution of a probed function and diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f6d2327ecb59..f274468cbc45 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -14,7 +14,7 @@ #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> -#include <asm/kprobes.h> +#include <linux/error-injection.h> #include "trace_probe.h" #include "trace.h" @@ -83,9 +83,8 @@ EXPORT_SYMBOL_GPL(trace_call_bpf); #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { - __this_cpu_write(bpf_kprobe_override, 1); regs_set_return_value(regs, rc); - arch_ftrace_kprobe_override_function(regs); + override_function_with_return(regs); return 0; } @@ -800,11 +799,11 @@ int perf_event_attach_bpf_prog(struct perf_event *event, int ret = -EEXIST; /* - * Kprobe override only works for ftrace based kprobes, and only if they - * are on the opt-in list. + * Kprobe override only works if they are on the function entry, + * and only if they are on the opt-in list. */ if (prog->kprobe_override && - (!trace_kprobe_ftrace(event->tp_event) || + (!trace_kprobe_on_func_entry(event->tp_event) || !trace_kprobe_error_injectable(event->tp_event))) return -EINVAL; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ab18995ff1e..0cddf60186da 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2534,29 +2534,59 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can - * be modified more than once via an interrupt. There are four - * different contexts that we need to consider. + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. * - * Normal context. - * SoftIRQ context - * IRQ context - * NMI context + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. * - * If for some reason the ring buffer starts to recurse, we - * only allow that to happen at most 4 times (one for each - * context). If it happens 5 times, then we consider this a - * recusive loop and do not let it go further. + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { - if (cpu_buffer->current_context >= 4) + unsigned int val = cpu_buffer->current_context; + unsigned long pc = preempt_count(); + int bit; + + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + bit = RB_CTX_NORMAL; + else + bit = pc & NMI_MASK ? RB_CTX_NMI : + pc & HARDIRQ_MASK ? RB_CTX_IRQ : + pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + + if (unlikely(val & (1 << bit))) return 1; - cpu_buffer->current_context++; - /* Interrupts must see this update */ - barrier(); + val |= (1 << bit); + cpu_buffer->current_context = val; return 0; } @@ -2564,9 +2594,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { - /* Don't let the dec leak out */ - barrier(); - cpu_buffer->current_context--; + cpu_buffer->current_context &= cpu_buffer->current_context - 1; } /** diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 91f4b57dab82..1fad24acd444 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/rculist.h> +#include <linux/error-injection.h> #include "trace_probe.h" @@ -42,8 +43,6 @@ struct trace_kprobe { (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) -DEFINE_PER_CPU(int, bpf_kprobe_override); - static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { return tk->rp.handler != NULL; @@ -88,13 +87,16 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } -int trace_kprobe_ftrace(struct trace_event_call *call) +bool trace_kprobe_on_func_entry(struct trace_event_call *call) { struct trace_kprobe *tk = (struct trace_kprobe *)call->data; - return kprobe_ftrace(&tk->rp.kp); + + return kprobe_on_func_entry(tk->rp.kp.addr, + tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name, + tk->rp.kp.addr ? 0 : tk->rp.kp.offset); } -int trace_kprobe_error_injectable(struct trace_event_call *call) +bool trace_kprobe_error_injectable(struct trace_event_call *call) { struct trace_kprobe *tk = (struct trace_kprobe *)call->data; unsigned long addr; @@ -106,7 +108,7 @@ int trace_kprobe_error_injectable(struct trace_event_call *call) } else { addr = (unsigned long)tk->rp.kp.addr; } - return within_kprobe_error_injection_list(addr); + return within_error_injection_list(addr); } static int register_kprobe_event(struct trace_kprobe *tk); @@ -1202,6 +1204,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) int rctx; if (bpf_prog_array_valid(call)) { + unsigned long orig_ip = instruction_pointer(regs); int ret; ret = trace_call_bpf(call, regs); @@ -1209,12 +1212,13 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) /* * We need to check and see if we modified the pc of the * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the instruction skipping. Also reset our state so - * we are clean the next pass through. + * don't do the single stepping. + * The ftrace kprobe handler leaves it up to us to re-enable + * preemption here before returning if we've modified the ip. */ - if (__this_cpu_read(bpf_kprobe_override)) { - __this_cpu_write(bpf_kprobe_override, 0); + if (orig_ip != instruction_pointer(regs)) { reset_current_kprobe(); + preempt_enable_no_resched(); return 1; } if (!ret) @@ -1322,15 +1326,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) if (tk->tp.flags & TP_FLAG_TRACE) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS - if (tk->tp.flags & TP_FLAG_PROFILE) { + if (tk->tp.flags & TP_FLAG_PROFILE) ret = kprobe_perf_func(tk, regs); - /* - * The ftrace kprobe handler leaves it up to us to re-enable - * preemption here before returning if we've modified the ip. - */ - if (ret) - preempt_enable_no_resched(); - } #endif return ret; } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 5e54d748c84c..e101c5bb9eda 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -252,8 +252,8 @@ 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); -int trace_kprobe_ftrace(struct trace_event_call *call); -int trace_kprobe_error_injectable(struct trace_event_call *call); +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 @@ -280,14 +280,14 @@ alloc_symbol_cache(const char *sym, long offset) return NULL; } -static inline int trace_kprobe_ftrace(struct trace_event_call *call) +static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call) { - return 0; + return false; } -static inline int trace_kprobe_error_injectable(struct trace_event_call *call) +static inline bool trace_kprobe_error_injectable(struct trace_event_call *call) { - return 0; + return false; } #endif /* CONFIG_KPROBE_EVENTS */ |