From ab43762ef010967e4ccd53627f70a2eecbeafefb Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 6 Aug 2019 11:46:00 +0300 Subject: perf: Allow normal events to output AUX data In some cases, ordinary (non-AUX) events can generate data for AUX events. For example, PEBS events can come out as records in the Intel PT stream instead of their usual DS records, if configured to do so. One requirement for such events is to consistently schedule together, to ensure that the data from the "AUX output" events isn't lost while their corresponding AUX event is not scheduled. We use grouping to provide this guarantee: an "AUX output" event can be added to a group where an AUX event is a group leader, and provided that the former supports writing to the latter. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: kan.liang@linux.intel.com Link: https://lkml.kernel.org/r/20190806084606.4021-2-alexander.shishkin@linux.intel.com --- kernel/events/core.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 93 insertions(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 0463c1151bae..2aad959e6def 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1887,6 +1887,89 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) ctx->generation++; } +static int +perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event) +{ + if (!has_aux(aux_event)) + return 0; + + if (!event->pmu->aux_output_match) + return 0; + + return event->pmu->aux_output_match(aux_event); +} + +static void put_event(struct perf_event *event); +static void event_sched_out(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx); + +static void perf_put_aux_event(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event *iter; + + /* + * If event uses aux_event tear down the link + */ + if (event->aux_event) { + iter = event->aux_event; + event->aux_event = NULL; + put_event(iter); + return; + } + + /* + * If the event is an aux_event, tear down all links to + * it from other events. + */ + for_each_sibling_event(iter, event->group_leader) { + if (iter->aux_event != event) + continue; + + iter->aux_event = NULL; + put_event(event); + + /* + * If it's ACTIVE, schedule it out and put it into ERROR + * state so that we don't try to schedule it again. Note + * that perf_event_enable() will clear the ERROR status. + */ + event_sched_out(iter, cpuctx, ctx); + perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } +} + +static int perf_get_aux_event(struct perf_event *event, + struct perf_event *group_leader) +{ + /* + * Our group leader must be an aux event if we want to be + * an aux_output. This way, the aux event will precede its + * aux_output events in the group, and therefore will always + * schedule first. + */ + if (!group_leader) + return 0; + + if (!perf_aux_output_match(event, group_leader)) + return 0; + + if (!atomic_long_inc_not_zero(&group_leader->refcount)) + return 0; + + /* + * Link aux_outputs to their aux event; this is undone in + * perf_group_detach() by perf_put_aux_event(). When the + * group in torn down, the aux_output events loose their + * link to the aux_event and can't schedule any more. + */ + event->aux_event = group_leader; + + return 1; +} + static void perf_group_detach(struct perf_event *event) { struct perf_event *sibling, *tmp; @@ -1902,6 +1985,8 @@ static void perf_group_detach(struct perf_event *event) event->attach_state &= ~PERF_ATTACH_GROUP; + perf_put_aux_event(event); + /* * If this is a sibling, remove it from its group. */ @@ -10426,6 +10511,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, goto err_ns; } + if (event->attr.aux_output && + !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { + err = -EOPNOTSUPP; + goto err_pmu; + } + err = exclusive_event_init(event); if (err) goto err_pmu; @@ -11082,6 +11173,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + if (event->attr.aux_output && !perf_get_aux_event(event, group_leader)) + goto err_locked; /* * Must be under the same ctx::mutex as perf_install_in_context(), -- cgit v1.2.3 From e336b4027775cb458dc713745e526fa1a1996b2a Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 3 Sep 2019 20:08:21 +0900 Subject: kprobes: Prohibit probing on BUG() and WARN() address Since BUG() and WARN() may use a trap (e.g. UD2 on x86) to get the address where the BUG() has occurred, kprobes can not do single-step out-of-line that instruction. So prohibit probing on such address. Without this fix, if someone put a kprobe on WARN(), the kernel will crash with invalid opcode error instead of outputing warning message, because kernel can not find correct bug address. Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt (VMware) Acked-by: Naveen N. Rao Cc: Anil S Keshavamurthy Cc: David S . Miller Cc: Linus Torvalds Cc: Naveen N . Rao Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/156750890133.19112.3393666300746167111.stgit@devnote2 Signed-off-by: Ingo Molnar --- include/linux/bug.h | 5 +++++ kernel/kprobes.c | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/bug.h b/include/linux/bug.h index fe5916550da8..f639bd0122f3 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -47,6 +47,11 @@ void generic_bug_clear_once(void); #else /* !CONFIG_GENERIC_BUG */ +static inline void *find_bug(unsigned long bugaddr) +{ + return NULL; +} + static inline enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs) { diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d9770a5393c8..ebe8315a756a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1514,7 +1514,8 @@ static int check_kprobe_address_safe(struct kprobe *p, /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || - jump_label_text_reserved(p->addr, p->addr)) { + jump_label_text_reserved(p->addr, p->addr) || + find_bug((unsigned long)p->addr)) { ret = -EINVAL; goto out; } -- cgit v1.2.3