diff options
Diffstat (limited to 'tools/perf/util/thread-stack.c')
| -rw-r--r-- | tools/perf/util/thread-stack.c | 76 |
1 files changed, 52 insertions, 24 deletions
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 41942c2aaa18..15134ac9b8f1 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -1,27 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * thread-stack.c: Synthesize a thread's stack using call / return events * Copyright (c) 2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include <linux/rbtree.h> #include <linux/list.h> #include <linux/log2.h> +#include <linux/zalloc.h> #include <errno.h> +#include <stdlib.h> #include "thread.h" #include "event.h" #include "machine.h" #include "env.h" -#include "util.h" #include "debug.h" #include "symbol.h" #include "comm.h" @@ -49,6 +41,8 @@ enum retpoline_state_t { * @timestamp: timestamp (if known) * @ref: external reference (e.g. db_id of sample) * @branch_count: the branch count when the entry was created + * @insn_count: the instruction count when the entry was created + * @cyc_count the cycle count when the entry was created * @db_id: id used for db-export * @cp: call path * @no_call: a 'call' was not seen @@ -60,6 +54,8 @@ struct thread_stack_entry { u64 timestamp; u64 ref; u64 branch_count; + u64 insn_count; + u64 cyc_count; u64 db_id; struct call_path *cp; bool no_call; @@ -75,6 +71,8 @@ struct thread_stack_entry { * @sz: current maximum stack size * @trace_nr: current trace number * @branch_count: running branch count + * @insn_count: running instruction count + * @cyc_count running cycle count * @kernel_start: kernel start address * @last_time: last timestamp * @crp: call/return processor @@ -88,6 +86,8 @@ struct thread_stack { size_t sz; u64 trace_nr; u64 branch_count; + u64 insn_count; + u64 cyc_count; u64 kernel_start; u64 last_time; struct call_return_processor *crp; @@ -289,6 +289,8 @@ static int thread_stack__call_return(struct thread *thread, cr.call_time = tse->timestamp; cr.return_time = timestamp; cr.branch_count = ts->branch_count - tse->branch_count; + cr.insn_count = ts->insn_count - tse->insn_count; + cr.cyc_count = ts->cyc_count - tse->cyc_count; cr.db_id = tse->db_id; cr.call_ref = tse->ref; cr.return_ref = ref; @@ -544,6 +546,8 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr, tse->timestamp = timestamp; tse->ref = ref; tse->branch_count = ts->branch_count; + tse->insn_count = ts->insn_count; + tse->cyc_count = ts->cyc_count; tse->cp = cp; tse->no_call = no_call; tse->trace_end = trace_end; @@ -625,6 +629,23 @@ static int thread_stack__bottom(struct thread_stack *ts, true, false); } +static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts, + struct perf_sample *sample, u64 ref) +{ + u64 tm = sample->time; + int err; + + /* Return to userspace, so pop all kernel addresses */ + while (thread_stack__in_kernel(ts)) { + err = thread_stack__call_return(thread, ts, --ts->cnt, + tm, ref, true); + if (err) + return err; + } + + return 0; +} + static int thread_stack__no_call_return(struct thread *thread, struct thread_stack *ts, struct perf_sample *sample, @@ -644,12 +665,9 @@ static int thread_stack__no_call_return(struct thread *thread, if (ip >= ks && addr < ks) { /* Return to userspace, so pop all kernel addresses */ - while (thread_stack__in_kernel(ts)) { - err = thread_stack__call_return(thread, ts, --ts->cnt, - tm, ref, true); - if (err) - return err; - } + err = thread_stack__pop_ks(thread, ts, sample, ref); + if (err) + return err; /* If the stack is empty, push the userspace address */ if (!ts->cnt) { @@ -659,12 +677,9 @@ static int thread_stack__no_call_return(struct thread *thread, } } else if (thread_stack__in_kernel(ts) && ip < ks) { /* Return to userspace, so pop all kernel addresses */ - while (thread_stack__in_kernel(ts)) { - err = thread_stack__call_return(thread, ts, --ts->cnt, - tm, ref, true); - if (err) - return err; - } + err = thread_stack__pop_ks(thread, ts, sample, ref); + if (err) + return err; } if (ts->cnt) @@ -874,6 +889,8 @@ int thread_stack__process(struct thread *thread, struct comm *comm, } ts->branch_count += 1; + ts->insn_count += sample->insn_cnt; + ts->cyc_count += sample->cyc_cnt; ts->last_time = sample->time; if (sample->flags & PERF_IP_FLAG_CALL) { @@ -905,7 +922,18 @@ int thread_stack__process(struct thread *thread, struct comm *comm, ts->rstate = X86_RETPOLINE_DETECTED; } else if (sample->flags & PERF_IP_FLAG_RETURN) { - if (!sample->ip || !sample->addr) + if (!sample->addr) { + u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET | + PERF_IP_FLAG_INTERRUPT; + + if (!(sample->flags & return_from_kernel)) + return 0; + + /* Pop kernel stack */ + return thread_stack__pop_ks(thread, ts, sample, ref); + } + + if (!sample->ip) return 0; /* x86 retpoline 'return' doesn't match the stack */ |