Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753346AbbGAC7k (ORCPT ); Tue, 30 Jun 2015 22:59:40 -0400 Received: from szxga02-in.huawei.com ([119.145.14.65]:33022 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753427AbbGAC6e (ORCPT ); Tue, 30 Jun 2015 22:58:34 -0400 From: He Kuang To: , , , , , , , CC: , Subject: [RFC PATCH 3/5] tracing/kprobe: Separate inc recursion count out of perf_trace_buf_prepare Date: Wed, 1 Jul 2015 02:57:33 +0000 Message-ID: <1435719455-91155-4-git-send-email-hekuang@huawei.com> X-Mailer: git-send-email 1.8.3.4 In-Reply-To: <1435719455-91155-1-git-send-email-hekuang@huawei.com> References: <1435719455-91155-1-git-send-email-hekuang@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.107.197.210] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5779 Lines: 167 Inside perf_trace_buf_prepare(), a recursion count is increased, the count was first introduced by commit 444a2a3bcd6d ("tracing, perf_events: Protect the buffer from recursion in perf") to protect the percpu data buffer from being overwritten. For future patch to enable eBPF saving data into perf extra trace buffer and prevent data buffer being filled recursively, the recursion count is increased outside before entering trace_call_bpf() and decreased in case of error. In this condition, we use the new function perf_trace_buf_prepare_rctx() for not increasing the recursion count a second time. Signed-off-by: He Kuang --- include/linux/ftrace_event.h | 2 ++ kernel/trace/trace_event_perf.c | 27 ++++++++++++++++++++++----- kernel/trace/trace_kprobe.c | 28 ++++++++++++++++++++++------ 3 files changed, 46 insertions(+), 11 deletions(-) diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index b6cf5a3..085d236 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -615,6 +615,8 @@ extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, extern void ftrace_profile_free_filter(struct perf_event *event); extern void *perf_trace_buf_prepare(int size, unsigned short type, struct pt_regs **regs, int *rctxp); +extern void *perf_trace_buf_prepare_rctx(int size, unsigned short type, + struct pt_regs **regs, int rctx); extern void *perf_extra_trace_buf_prepare(int size, int rctx); extern void *get_perf_extra_trace_buf(int rctx); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 603b3da..e683cb6 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -306,8 +306,9 @@ void *get_perf_extra_trace_buf(int rctx) EXPORT_SYMBOL_GPL(get_perf_extra_trace_buf); NOKPROBE_SYMBOL(get_perf_extra_trace_buf); -void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs **regs, int *rctxp) +static void *__perf_trace_buf_prepare(int size, unsigned short type, + struct pt_regs **regs, int *rctxp, + bool update_rctx) { struct trace_entry *entry; unsigned long flags; @@ -322,9 +323,11 @@ void *perf_trace_buf_prepare(int size, unsigned short type, pc = preempt_count(); - *rctxp = perf_swevent_get_recursion_context(); - if (*rctxp < 0) - return NULL; + if (update_rctx) { + *rctxp = perf_swevent_get_recursion_context(); + if (*rctxp < 0) + return NULL; + } if (regs) *regs = this_cpu_ptr(&__perf_regs[*rctxp]); @@ -340,9 +343,23 @@ void *perf_trace_buf_prepare(int size, unsigned short type, return raw_data; } + +void *perf_trace_buf_prepare(int size, unsigned short type, + struct pt_regs **regs, int *rctxp) +{ + return __perf_trace_buf_prepare(size, type, regs, rctxp, true); +} EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); NOKPROBE_SYMBOL(perf_trace_buf_prepare); +void *perf_trace_buf_prepare_rctx(int size, unsigned short type, + struct pt_regs **regs, int rctx) +{ + return __perf_trace_buf_prepare(size, type, regs, &rctx, false); +} +EXPORT_SYMBOL_GPL(perf_trace_buf_prepare_rctx); +NOKPROBE_SYMBOL(perf_trace_buf_prepare_rctx); + #ifdef CONFIG_FUNCTION_TRACER static void perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 5600df8..16ad88e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1145,22 +1145,30 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) if (hlist_empty(head)) return; - if (prog && !trace_call_bpf(prog, regs)) + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) return; + if (prog && !trace_call_bpf(prog, regs)) + goto out; + dsize = __get_data_size(&tk->tp, regs); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + entry = perf_trace_buf_prepare_rctx(size, call->event.type, NULL, rctx); if (!entry) - return; + goto out; 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); perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + + return; +out: + perf_swevent_put_recursion_context(rctx); } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1180,22 +1188,30 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (hlist_empty(head)) return; - if (prog && !trace_call_bpf(prog, regs)) + rctx = perf_swevent_get_recursion_context(); + if (rctx < 0) return; + if (prog && !trace_call_bpf(prog, regs)) + goto out; + dsize = __get_data_size(&tk->tp, regs); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); - entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx); + entry = perf_trace_buf_prepare_rctx(size, call->event.type, NULL, rctx); if (!entry) - return; + goto out; 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); perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL); + + return; +out: + perf_swevent_put_recursion_context(rctx); } NOKPROBE_SYMBOL(kretprobe_perf_func); #endif /* CONFIG_PERF_EVENTS */ -- 1.8.5.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/