diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-11-03 18:13:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-11-03 18:13:43 -0700 |
commit | 01897f3e05ede4d66c0f9df465fde1d67a1d733f (patch) | |
tree | 3c0f1e0fb8bc352e6821d16e46f335484cc3868a /tools/perf/util/machine.c | |
parent | e9ebc2151f88600e726e51e5f7ca9c33ad53b35f (diff) | |
parent | 29995d296e3e9ce4f9767963ecbef143ade26c36 (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates and fixes from Ingo Molnar:
"These are almost all tooling updates: 'perf top', 'perf trace' and
'perf script' fixes and updates, an UAPI header sync with the merge
window versions, license marker updates, much improved Sparc support
from David Miller, and a number of fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
perf intel-pt/bts: Calculate cpumode for synthesized samples
perf intel-pt: Insert callchain context into synthesized callchains
perf tools: Don't clone maps from parent when synthesizing forks
perf top: Start display thread earlier
tools headers uapi: Update linux/if_link.h header copy
tools headers uapi: Update linux/netlink.h header copy
tools headers: Sync the various kvm.h header copies
tools include uapi: Update linux/mmap.h copy
perf trace beauty: Use the mmap flags table generated from headers
perf beauty: Wire up the mmap flags table generator to the Makefile
perf beauty: Add a generator for MAP_ mmap's flag constants
tools include uapi: Update asound.h copy
tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h copies
tools include uapi: Update linux/fs.h copy
perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}
perf cs-etm: Correct CPU mode for samples
perf unwind: Take pgoff into account when reporting elf to libdwfl
perf top: Do not use overwrite mode by default
perf top: Allow disabling the overwrite mode
perf trace: Beautify mount's first pathname arg
...
Diffstat (limited to 'tools/perf/util/machine.c')
-rw-r--r-- | tools/perf/util/machine.c | 54 |
1 files changed, 52 insertions, 2 deletions
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 111ae858cbcb..8f36ce813bc5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event struct thread *parent = machine__findnew_thread(machine, event->fork.ppid, event->fork.ptid); + bool do_maps_clone = true; int err = 0; if (dump_trace) @@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); + /* + * When synthesizing FORK events, we are trying to create thread + * objects for the already running tasks on the machine. + * + * Normally, for a kernel FORK event, we want to clone the parent's + * maps because that is what the kernel just did. + * + * But when synthesizing, this should not be done. If we do, we end up + * with overlapping maps as we process the sythesized MMAP2 events that + * get delivered shortly thereafter. + * + * Use the FORK event misc flags in an internal way to signal this + * situation, so we can elide the map clone when appropriate. + */ + if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC) + do_maps_clone = false; if (thread == NULL || parent == NULL || - thread__fork(thread, parent, sample->time) < 0) { + thread__fork(thread, parent, sample->time, do_maps_clone) < 0) { dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n"); err = -1; } @@ -2140,6 +2157,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread, return 0; } +static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, + struct callchain_cursor *cursor, + struct symbol **parent, + struct addr_location *root_al, + u8 *cpumode, int ent) +{ + int err = 0; + + while (--ent >= 0) { + u64 ip = chain->ips[ent]; + + if (ip >= PERF_CONTEXT_MAX) { + err = add_callchain_ip(thread, cursor, parent, + root_al, cpumode, ip, + false, NULL, NULL, 0); + break; + } + } + return err; +} + static int thread__resolve_callchain_sample(struct thread *thread, struct callchain_cursor *cursor, struct perf_evsel *evsel, @@ -2246,6 +2284,12 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: + if (callchain_param.order != ORDER_CALLEE) { + err = find_prev_cpumode(chain, thread, cursor, parent, root_al, + &cpumode, chain->nr - first_call); + if (err) + return (err < 0) ? err : 0; + } for (i = first_call, nr_entries = 0; i < chain_nr && nr_entries < max_stack; i++) { u64 ip; @@ -2260,9 +2304,15 @@ check_calls: continue; #endif ip = chain->ips[j]; - if (ip < PERF_CONTEXT_MAX) ++nr_entries; + else if (callchain_param.order != ORDER_CALLEE) { + err = find_prev_cpumode(chain, thread, cursor, parent, + root_al, &cpumode, j); + if (err) + return (err < 0) ? err : 0; + continue; + } err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip, |