perf script: Add API for filtering via dynamically loaded shared object

In some cases, users want to filter very large amounts of data (e.g.
from AUX area tracing like Intel PT) looking for something specific.
While scripting such as Python can be used, Python is 10 to 20 times
slower than C. So define a C API so that custom filters can be written
and loaded.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210627131818.810-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

4 files changed, 528 insertions, 0 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 95e15d1035ab..1a909b53dc15 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -126,6 +126,7 @@ perf-y += parse-regs-options.o
 perf-y += parse-sublevel-options.o
 perf-y += term.o
 perf-y += help-unknown-cmd.o
+perf-y += dlfilter.o
 perf-y += mem-events.o
 perf-y += vsprintf.o
 perf-y += units.o
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
new file mode 100644
index 000000000000..03c4bf150656
--- /dev/null
+++ b/tools/perf/util/dlfilter.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dlfilter.c: Interface to perf script --dlfilter shared object
+ * Copyright (c) 2021, Intel Corporation.
+ */
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/zalloc.h>
+#include <linux/build_bug.h>
+
+#include "debug.h"
+#include "event.h"
+#include "evsel.h"
+#include "dso.h"
+#include "map.h"
+#include "thread.h"
+#include "symbol.h"
+#include "dlfilter.h"
+#include "perf_dlfilter.h"
+
+static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
+{
+	struct symbol *sym = al->sym;
+
+	d_al->size = sizeof(*d_al);
+	if (al->map) {
+		struct dso *dso = al->map->dso;
+
+		if (symbol_conf.show_kernel_path && dso->long_name)
+			d_al->dso = dso->long_name;
+		else
+			d_al->dso = dso->name;
+		d_al->is_64_bit = dso->is_64_bit;
+		d_al->buildid_size = dso->bid.size;
+		d_al->buildid = dso->bid.data;
+	} else {
+		d_al->dso = NULL;
+		d_al->is_64_bit = 0;
+		d_al->buildid_size = 0;
+		d_al->buildid = NULL;
+	}
+	if (sym) {
+		d_al->sym = sym->name;
+		d_al->sym_start = sym->start;
+		d_al->sym_end = sym->end;
+		if (al->addr < sym->end)
+			d_al->symoff = al->addr - sym->start;
+		else
+			d_al->symoff = al->addr - al->map->start - sym->start;
+		d_al->sym_binding = sym->binding;
+	} else {
+		d_al->sym = NULL;
+		d_al->sym_start = 0;
+		d_al->sym_end = 0;
+		d_al->symoff = 0;
+		d_al->sym_binding = 0;
+	}
+	d_al->addr = al->addr;
+	d_al->comm = NULL;
+	d_al->filtered = 0;
+}
+
+static struct addr_location *get_al(struct dlfilter *d)
+{
+	struct addr_location *al = d->al;
+
+	if (!al->thread && machine__resolve(d->machine, al, d->sample) < 0)
+		return NULL;
+	return al;
+}
+
+static struct thread *get_thread(struct dlfilter *d)
+{
+	struct addr_location *al = get_al(d);
+
+	return al ? al->thread : NULL;
+}
+
+static const struct perf_dlfilter_al *dlfilter__resolve_ip(void *ctx)
+{
+	struct dlfilter *d = (struct dlfilter *)ctx;
+	struct perf_dlfilter_al *d_al = d->d_ip_al;
+	struct addr_location *al;
+
+	if (!d->ctx_valid)
+		return NULL;
+
+	/* 'size' is also used to indicate already initialized */
+	if (d_al->size)
+		return d_al;
+
+	al = get_al(d);
+	if (!al)
+		return NULL;
+
+	al_to_d_al(al, d_al);
+
+	d_al->is_kernel_ip = machine__kernel_ip(d->machine, d->sample->ip);
+	d_al->comm = al->thread ? thread__comm_str(al->thread) : ":-1";
+	d_al->filtered = al->filtered;
+
+	return d_al;
+}
+
+static const struct perf_dlfilter_al *dlfilter__resolve_addr(void *ctx)
+{
+	struct dlfilter *d = (struct dlfilter *)ctx;
+	struct perf_dlfilter_al *d_addr_al = d->d_addr_al;
+	struct addr_location *addr_al = d->addr_al;
+
+	if (!d->ctx_valid || !d->d_sample->addr_correlates_sym)
+		return NULL;
+
+	/* 'size' is also used to indicate already initialized */
+	if (d_addr_al->size)
+		return d_addr_al;
+
+	if (!addr_al->thread) {
+		struct thread *thread = get_thread(d);
+
+		if (!thread)
+			return NULL;
+		thread__resolve(thread, addr_al, d->sample);
+	}
+
+	al_to_d_al(addr_al, d_addr_al);
+
+	d_addr_al->is_kernel_ip = machine__kernel_ip(d->machine, d->sample->addr);
+
+	return d_addr_al;
+}
+
+static const struct perf_dlfilter_fns perf_dlfilter_fns = {
+	.resolve_ip      = dlfilter__resolve_ip,
+	.resolve_addr    = dlfilter__resolve_addr,
+};
+
+#define CHECK_FLAG(x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
+
+static int dlfilter__init(struct dlfilter *d, const char *file)
+{
+	CHECK_FLAG(BRANCH);
+	CHECK_FLAG(CALL);
+	CHECK_FLAG(RETURN);
+	CHECK_FLAG(CONDITIONAL);
+	CHECK_FLAG(SYSCALLRET);
+	CHECK_FLAG(ASYNC);
+	CHECK_FLAG(INTERRUPT);
+	CHECK_FLAG(TX_ABORT);
+	CHECK_FLAG(TRACE_BEGIN);
+	CHECK_FLAG(TRACE_END);
+	CHECK_FLAG(IN_TX);
+	CHECK_FLAG(VMENTRY);
+	CHECK_FLAG(VMEXIT);
+
+	memset(d, 0, sizeof(*d));
+	d->file = strdup(file);
+	if (!d->file)
+		return -1;
+	return 0;
+}
+
+static void dlfilter__exit(struct dlfilter *d)
+{
+	zfree(&d->file);
+}
+
+static int dlfilter__open(struct dlfilter *d)
+{
+	d->handle = dlopen(d->file, RTLD_NOW);
+	if (!d->handle) {
+		pr_err("dlopen failed for: '%s'\n", d->file);
+		return -1;
+	}
+	d->start = dlsym(d->handle, "start");
+	d->filter_event = dlsym(d->handle, "filter_event");
+	d->stop = dlsym(d->handle, "stop");
+	d->fns = dlsym(d->handle, "perf_dlfilter_fns");
+	if (d->fns)
+		memcpy(d->fns, &perf_dlfilter_fns, sizeof(struct perf_dlfilter_fns));
+	return 0;
+}
+
+static int dlfilter__close(struct dlfilter *d)
+{
+	return dlclose(d->handle);
+}
+
+struct dlfilter *dlfilter__new(const char *file)
+{
+	struct dlfilter *d = malloc(sizeof(*d));
+
+	if (!d)
+		return NULL;
+
+	if (dlfilter__init(d, file))
+		goto err_free;
+
+	if (dlfilter__open(d))
+		goto err_exit;
+
+	return d;
+
+err_exit:
+	dlfilter__exit(d);
+err_free:
+	free(d);
+	return NULL;
+}
+
+static void dlfilter__free(struct dlfilter *d)
+{
+	if (d) {
+		dlfilter__exit(d);
+		free(d);
+	}
+}
+
+int dlfilter__start(struct dlfilter *d, struct perf_session *session)
+{
+	if (d) {
+		d->session = session;
+		if (d->start)
+			return d->start(&d->data, d);
+	}
+	return 0;
+}
+
+static int dlfilter__stop(struct dlfilter *d)
+{
+	if (d && d->stop)
+		return d->stop(d->data, d);
+	return 0;
+}
+
+void dlfilter__cleanup(struct dlfilter *d)
+{
+	if (d) {
+		dlfilter__stop(d);
+		dlfilter__close(d);
+		dlfilter__free(d);
+	}
+}
+
+#define ASSIGN(x) d_sample.x = sample->x
+
+int dlfilter__do_filter_event(struct dlfilter *d,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct evsel *evsel,
+			      struct machine *machine,
+			      struct addr_location *al,
+			      struct addr_location *addr_al)
+{
+	struct perf_dlfilter_sample d_sample;
+	struct perf_dlfilter_al d_ip_al;
+	struct perf_dlfilter_al d_addr_al;
+	int ret;
+
+	d->event       = event;
+	d->sample      = sample;
+	d->evsel       = evsel;
+	d->machine     = machine;
+	d->al          = al;
+	d->addr_al     = addr_al;
+	d->d_sample    = &d_sample;
+	d->d_ip_al     = &d_ip_al;
+	d->d_addr_al   = &d_addr_al;
+
+	d_sample.size  = sizeof(d_sample);
+	d_ip_al.size   = 0; /* To indicate d_ip_al is not initialized */
+	d_addr_al.size = 0; /* To indicate d_addr_al is not initialized */
+
+	ASSIGN(ip);
+	ASSIGN(pid);
+	ASSIGN(tid);
+	ASSIGN(time);
+	ASSIGN(addr);
+	ASSIGN(id);
+	ASSIGN(stream_id);
+	ASSIGN(period);
+	ASSIGN(weight);
+	ASSIGN(ins_lat);
+	ASSIGN(p_stage_cyc);
+	ASSIGN(transaction);
+	ASSIGN(insn_cnt);
+	ASSIGN(cyc_cnt);
+	ASSIGN(cpu);
+	ASSIGN(flags);
+	ASSIGN(data_src);
+	ASSIGN(phys_addr);
+	ASSIGN(data_page_size);
+	ASSIGN(code_page_size);
+	ASSIGN(cgroup);
+	ASSIGN(cpumode);
+	ASSIGN(misc);
+	ASSIGN(raw_size);
+	ASSIGN(raw_data);
+
+	if (sample->branch_stack) {
+		d_sample.brstack_nr = sample->branch_stack->nr;
+		d_sample.brstack = (struct perf_branch_entry *)perf_sample__branch_entries(sample);
+	} else {
+		d_sample.brstack_nr = 0;
+		d_sample.brstack = NULL;
+	}
+
+	if (sample->callchain) {
+		d_sample.raw_callchain_nr = sample->callchain->nr;
+		d_sample.raw_callchain = (__u64 *)sample->callchain->ips;
+	} else {
+		d_sample.raw_callchain_nr = 0;
+		d_sample.raw_callchain = NULL;
+	}
+
+	d_sample.addr_correlates_sym =
+		(evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) &&
+		sample_addr_correlates_sym(&evsel->core.attr);
+
+	d_sample.event = evsel__name(evsel);
+
+	d->ctx_valid = true;
+
+	ret = d->filter_event(d->data, &d_sample, d);
+
+	d->ctx_valid = false;
+
+	return ret;
+}
diff --git a/tools/perf/util/dlfilter.h b/tools/perf/util/dlfilter.h
new file mode 100644
index 000000000000..22b7636028dd
--- /dev/null
+++ b/tools/perf/util/dlfilter.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * dlfilter.h: Interface to perf script --dlfilter shared object
+ * Copyright (c) 2021, Intel Corporation.
+ */
+
+#ifndef PERF_UTIL_DLFILTER_H
+#define PERF_UTIL_DLFILTER_H
+
+struct perf_session;
+union  perf_event;
+struct perf_sample;
+struct evsel;
+struct machine;
+struct addr_location;
+struct perf_dlfilter_fns;
+struct perf_dlfilter_sample;
+struct perf_dlfilter_al;
+
+struct dlfilter {
+	char				*file;
+	void				*handle;
+	void				*data;
+	struct perf_session		*session;
+	bool				ctx_valid;
+
+	union perf_event		*event;
+	struct perf_sample		*sample;
+	struct evsel			*evsel;
+	struct machine			*machine;
+	struct addr_location		*al;
+	struct addr_location		*addr_al;
+	struct perf_dlfilter_sample	*d_sample;
+	struct perf_dlfilter_al		*d_ip_al;
+	struct perf_dlfilter_al		*d_addr_al;
+
+	int (*start)(void **data, void *ctx);
+	int (*stop)(void *data, void *ctx);
+
+	int (*filter_event)(void *data,
+			    const struct perf_dlfilter_sample *sample,
+			    void *ctx);
+
+	struct perf_dlfilter_fns *fns;
+};
+
+struct dlfilter *dlfilter__new(const char *file);
+
+int dlfilter__start(struct dlfilter *d, struct perf_session *session);
+
+int dlfilter__do_filter_event(struct dlfilter *d,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct evsel *evsel,
+			      struct machine *machine,
+			      struct addr_location *al,
+			      struct addr_location *addr_al);
+
+void dlfilter__cleanup(struct dlfilter *d);
+
+static inline int dlfilter__filter_event(struct dlfilter *d,
+					 union perf_event *event,
+					 struct perf_sample *sample,
+					 struct evsel *evsel,
+					 struct machine *machine,
+					 struct addr_location *al,
+					 struct addr_location *addr_al)
+{
+	if (!d || !d->filter_event)
+		return 0;
+	return dlfilter__do_filter_event(d, event, sample, evsel, machine, al, addr_al);
+}
+
+#endif
diff --git a/tools/perf/util/perf_dlfilter.h b/tools/perf/util/perf_dlfilter.h
new file mode 100644
index 000000000000..82833ee8680d
--- /dev/null
+++ b/tools/perf/util/perf_dlfilter.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * perf_dlfilter.h: API for perf --dlfilter shared object
+ * Copyright (c) 2021, Intel Corporation.
+ */
+#ifndef _LINUX_PERF_DLFILTER_H
+#define _LINUX_PERF_DLFILTER_H
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+/* Definitions for perf_dlfilter_sample flags */
+enum {
+	PERF_DLFILTER_FLAG_BRANCH	= 1ULL << 0,
+	PERF_DLFILTER_FLAG_CALL		= 1ULL << 1,
+	PERF_DLFILTER_FLAG_RETURN	= 1ULL << 2,
+	PERF_DLFILTER_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_DLFILTER_FLAG_SYSCALLRET	= 1ULL << 4,
+	PERF_DLFILTER_FLAG_ASYNC	= 1ULL << 5,
+	PERF_DLFILTER_FLAG_INTERRUPT	= 1ULL << 6,
+	PERF_DLFILTER_FLAG_TX_ABORT	= 1ULL << 7,
+	PERF_DLFILTER_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_DLFILTER_FLAG_TRACE_END	= 1ULL << 9,
+	PERF_DLFILTER_FLAG_IN_TX	= 1ULL << 10,
+	PERF_DLFILTER_FLAG_VMENTRY	= 1ULL << 11,
+	PERF_DLFILTER_FLAG_VMEXIT	= 1ULL << 12,
+};
+
+/*
+ * perf sample event information (as per perf script and <linux/perf_event.h>)
+ */
+struct perf_dlfilter_sample {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u16 ins_lat;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u16 p_stage_cyc;	/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 ip;
+	__s32 pid;
+	__s32 tid;
+	__u64 time;
+	__u64 addr;
+	__u64 id;
+	__u64 stream_id;
+	__u64 period;
+	__u64 weight;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 transaction;	/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */
+	__u64 insn_cnt;	/* For instructions-per-cycle (IPC) */
+	__u64 cyc_cnt;		/* For instructions-per-cycle (IPC) */
+	__s32 cpu;
+	__u32 flags;		/* Refer PERF_DLFILTER_FLAG_* above */
+	__u64 data_src;		/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */
+	__u64 phys_addr;	/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */
+	__u64 data_page_size;	/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 code_page_size;	/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 cgroup;		/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */
+	__u8  cpumode;		/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */
+	__u8  addr_correlates_sym; /* True => resolve_addr() can be called */
+	__u16 misc;		/* Refer perf_event_header in <linux/perf_event.h> */
+	__u32 raw_size;		/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	const void *raw_data;	/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	__u64 brstack_nr;	/* Number of brstack entries */
+	const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */
+	__u64 raw_callchain_nr;	/* Number of raw_callchain entries */
+	const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */
+	const char *event;
+};
+
+/*
+ * Address location (as per perf script)
+ */
+struct perf_dlfilter_al {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u32 symoff;
+	const char *sym;
+	__u64 addr; /* Mapped address (from dso) */
+	__u64 sym_start;
+	__u64 sym_end;
+	const char *dso;
+	__u8  sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */
+	__u8  is_64_bit; /* Only valid if dso is not NULL */
+	__u8  is_kernel_ip; /* True if in kernel space */
+	__u32 buildid_size;
+	__u8 *buildid;
+	/* Below members are only populated by resolve_ip() */
+	__u8 filtered; /* True if this sample event will be filtered out */
+	const char *comm;
+};
+
+struct perf_dlfilter_fns {
+	/* Return information about ip */
+	const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+	/* Return information about addr (if addr_correlates_sym) */
+	const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+	/* Reserved */
+	void *(*reserved[126])(void *);
+};
+
+/*
+ * If implemented, 'start' will be called at the beginning,
+ * before any calls to 'filter_event'. Return 0 to indicate success,
+ * or return a negative error code. '*data' can be assigned for use
+ * by other functions. 'ctx' is needed for calls to perf_dlfilter_fns,
+ * but most perf_dlfilter_fns are not valid when called from 'start'.
+ */
+int start(void **data, void *ctx);
+
+/*
+ * If implemented, 'stop' will be called at the end,
+ * after any calls to 'filter_event'. Return 0 to indicate success, or
+ * return a negative error code. 'data' is set by start(). 'ctx' is
+ * needed for calls to perf_dlfilter_fns, but most perf_dlfilter_fns
+ * are not valid when called from 'stop'.
+ */
+int stop(void *data, void *ctx);
+
+/*
+ * If implemented, 'filter_event' will be called for each sample
+ * event. Return 0 to keep the sample event, 1 to filter it out, or
+ * return a negative error code. 'data' is set by start(). 'ctx' is
+ * needed for calls to perf_dlfilter_fns.
+ */
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+
+#endif