linux/tools/perf/util/session.h
David Miller 35d48ddfc0 perf tools: Fix mmap limitations on 32-bit
This is a suggested patch to fix the bug I reported at:

	http://marc.info/?l=linux-kernel&m=135033028924652&w=2

Essentially, there is a hard requirement that when perf analyzes a
trace, it must have the entire thing mmap()'d.

Therefore the scheme used on 32-bit where we have a fixed (8) number of
32MB mmaps, and cycle through them, simply does not work.

One of the reasons this requirement exists is because the iterators
maintain references to perf entry objects and those references don't
just simply go away when this mmap code decides to cycle an old mmap
area out and reuse it.  At this point, those entry pointers now point to
garbage resulting in unpredictable behavior and crashes.

It is better to try to mmap() as much as we can and if we do actually
run into address space limitations, the failure of the mmap() call will
indicate that and stop processing.

I noticed that perf_session->mmap_window is set to a constant in one
location, and only used in one other location.  So I got rid of it
altogether.

So we adjust the size of the mmaps[] array to the maximum we could need.
On 64-bit we only need one slot.  On 32-bit we could need up to 128 (128
* 32MB == 4GB).

I've verified that this allows a large (~600MB) perf.data file to be
analyzed properly with a 32-bit perf binary, which previously was not
possible.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20121110.141219.582924082787523608.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-09 08:46:05 -03:00

144 lines
4.1 KiB
C

#ifndef __PERF_SESSION_H
#define __PERF_SESSION_H
#include "hist.h"
#include "event.h"
#include "header.h"
#include "machine.h"
#include "symbol.h"
#include "thread.h"
#include <linux/rbtree.h>
#include <linux/perf_event.h>
struct sample_queue;
struct ip_callchain;
struct thread;
struct ordered_samples {
u64 last_flush;
u64 next_flush;
u64 max_timestamp;
struct list_head samples;
struct list_head sample_cache;
struct list_head to_free;
struct sample_queue *sample_buffer;
struct sample_queue *last_sample;
int sample_buffer_idx;
unsigned int nr_samples;
};
struct perf_session {
struct perf_header header;
unsigned long size;
struct machine host_machine;
struct rb_root machines;
struct perf_evlist *evlist;
struct pevent *pevent;
/*
* FIXME: Need to split this up further, we need global
* stats + per event stats.
*/
struct hists hists;
int fd;
bool fd_pipe;
bool repipe;
int cwdlen;
char *cwd;
struct ordered_samples ordered_samples;
char filename[1];
};
struct perf_tool;
struct perf_session *perf_session__new(const char *filename, int mode,
bool force, bool repipe,
struct perf_tool *tool);
void perf_session__delete(struct perf_session *self);
void perf_event_header__bswap(struct perf_event_header *self);
int __perf_session__process_events(struct perf_session *self,
u64 data_offset, u64 data_size, u64 size,
struct perf_tool *tool);
int perf_session__process_events(struct perf_session *self,
struct perf_tool *tool);
int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent);
bool perf_session__has_traces(struct perf_session *self, const char *msg);
void mem_bswap_64(void *src, int byte_size);
void mem_bswap_32(void *src, int byte_size);
void perf_event__attr_swap(struct perf_event_attr *attr);
int perf_session__create_kernel_maps(struct perf_session *self);
void perf_session__set_id_hdr_size(struct perf_session *session);
void perf_session__remove_thread(struct perf_session *self, struct thread *th);
static inline
struct machine *perf_session__find_host_machine(struct perf_session *self)
{
return &self->host_machine;
}
static inline
struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
{
if (pid == HOST_KERNEL_ID)
return &self->host_machine;
return machines__find(&self->machines, pid);
}
static inline
struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid)
{
if (pid == HOST_KERNEL_ID)
return &self->host_machine;
return machines__findnew(&self->machines, pid);
}
static inline
void perf_session__process_machines(struct perf_session *self,
struct perf_tool *tool,
machine__process_t process)
{
process(&self->host_machine, tool);
return machines__process(&self->machines, process, tool);
}
struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
FILE *fp, bool with_hits);
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample, struct machine *machine,
int print_sym, int print_dso, int print_symoffset);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
struct perf_evsel_str_handler;
int __perf_session__set_tracepoints_handlers(struct perf_session *session,
const struct perf_evsel_str_handler *assocs,
size_t nr_assocs);
#define perf_session__set_tracepoints_handlers(session, array) \
__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
#endif /* __PERF_SESSION_H */