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>

Author: ahunter6

tools/perf/Documentation/perf-dlfilter.txt

@@ -0,0 +1,222 @@
+perf-dlfilter(1)
+================
+
+NAME
+----
+perf-dlfilter - Filter sample events using a dynamically loaded shared
+object file
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [--dlfilter file.so ]
+
+DESCRIPTION
+-----------
+
+This option is used to process data through a custom filter provided by a
+dynamically loaded shared object file.
+
+If 'file.so' does not contain "/", then it will be found either in the current
+directory, or perf tools exec path which is ~/libexec/perf-core/dlfilters for
+a local build and install (refer perf --exec-path), or the dynamic linker
+paths.
+
+API
+---
+
+The API for filtering consists of the following:
+
+[source,c]
+----
+#include <perf/perf_dlfilter.h>
+
+const struct perf_dlfilter_fns perf_dlfilter_fns;
+
+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);
+----
+
+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'.
+
+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'.
+
+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'.
+
+The perf_dlfilter_sample structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+'filter_event' is passed a perf_dlfilter_sample
+structure, which contains the following fields:
+[source,c]
+----
+/*
+ * 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;
+};
+----
+
+The perf_dlfilter_fns structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'perf_dlfilter_fns' structure is populated with function pointers when the
+file is loaded. The functions can be called by 'filter_event'.
+
+[source,c]
+----
+struct perf_dlfilter_fns {
+	const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+	const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+	void *(*reserved[126])(void *);
+};
+----
+
+'resolve_ip' returns information about ip.
+
+'resolve_addr' returns information about addr (if addr_correlates_sym).
+
+The perf_dlfilter_al structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'perf_dlfilter_al' structure contains information about an address.
+
+[source,c]
+----
+/*
+ * 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;
+};
+----
+
+perf_dlfilter_sample flags
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'flags' member of 'perf_dlfilter_sample' corresponds with the flags field
+of perf script. The bits of the flags are as follows:
+
+[source,c]
+----
+/* 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,
+};
+----
+
+EXAMPLE
+-------
+
+Filter out everything except branches from "foo" to "bar":
+
+[source,c]
+----
+#include <perf/perf_dlfilter.h>
+#include <string.h>
+
+const struct perf_dlfilter_fns perf_dlfilter_fns;
+
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+	const struct perf_dlfilter_al *al;
+	const struct perf_dlfilter_al *addr_al;
+
+	if (!sample->ip || !sample->addr_correlates_sym)
+		return 1;
+
+	al = perf_dlfilter_fns.resolve_ip(ctx);
+	if (!al || !al->sym || strcmp(al->sym, "foo"))
+		return 1;
+
+	addr_al = perf_dlfilter_fns.resolve_addr(ctx);
+	if (!addr_al || !addr_al->sym || strcmp(addr_al->sym, "bar"))
+		return 1;
+
+	return 0;
+}
+----
+
+To build the shared object, assuming perf has been installed for the local user
+i.e. perf_dlfilter.h is in ~/include/perf :
+
+	gcc -c -I ~/include -fpic dlfilter-example.c
+	gcc -shared -o dlfilter-example.so dlfilter-example.o
+
+To use the filter with perf script:
+
+	perf script --dlfilter dlfilter-example.so
+
+SEE ALSO
+--------
+linkperf:perf-script[1]

tools/perf/Documentation/perf-script.txt

@@ -98,6 +98,10 @@ OPTIONS
         Generate perf-script.[ext] starter script for given language,
         using current perf.data.
 
+--dlfilter=<file>::
+	Filter sample events using the given shared object file.
+	Refer linkperf:perf-dlfilter[1]
+
 -a::
         Force system-wide collection.  Scripts run without a <command>
         normally use -a by default, while scripts run with a <command>
@@ -483,4 +487,5 @@ include::itrace.txt[]
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-script-python[1], linkperf:perf-intel-pt[1]
+linkperf:perf-script-python[1], linkperf:perf-intel-pt[1],
+linkperf:perf-dlfilter[1]

tools/perf/builtin-script.c

@@ -55,6 +55,7 @@
 #include <subcmd/pager.h>
 #include <perf/evlist.h>
 #include <linux/err.h>
+#include "util/dlfilter.h"
 #include "util/record.h"
 #include "util/util.h"
 #include "perf.h"
@@ -79,6 +80,7 @@ static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 static struct perf_stat_config	stat_config;
 static int			max_blocks;
 static bool			native_arch;
+static struct dlfilter		*dlfilter;
 
 unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
 
@@ -2175,6 +2177,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct perf_script *scr = container_of(tool, struct perf_script, tool);
 	struct addr_location al;
 	struct addr_location addr_al;
+	int ret = 0;
 
 	if (perf_time__ranges_skip_sample(scr->ptime_range, scr->range_num,
 					  sample->time)) {
@@ -2213,6 +2216,13 @@ static int process_sample_event(struct perf_tool *tool,
 	if (evswitch__discard(&scr->evswitch, evsel))
 		goto out_put;
 
+	ret = dlfilter__filter_event(dlfilter, event, sample, evsel, machine, &al, &addr_al);
+	if (ret) {
+		if (ret > 0)
+			ret = 0;
+		goto out_put;
+	}
+
 	if (scripting_ops) {
 		struct addr_location *addr_al_ptr = NULL;
 
@@ -2229,7 +2239,7 @@ static int process_sample_event(struct perf_tool *tool,
 
 out_put:
 	addr_location__put(&al);
-	return 0;
+	return ret;
 }
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -3568,6 +3578,7 @@ int cmd_script(int argc, const char **argv)
 	};
 	struct utsname uts;
 	char *script_path = NULL;
+	const char *dlfilter_file = NULL;
 	const char **__argv;
 	int i, j, err = 0;
 	struct perf_script script = {
@@ -3615,6 +3626,7 @@ int cmd_script(int argc, const char **argv)
 		     parse_scriptname),
 	OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
 		   "generate perf-script.xx script in specified language"),
+	OPT_STRING(0, "dlfilter", &dlfilter_file, "file", "filter .so file name"),
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
 		   "do various checks like samples ordering and lost events"),
@@ -3933,6 +3945,12 @@ int cmd_script(int argc, const char **argv)
 		exit(-1);
 	}
 
+	if (dlfilter_file) {
+		dlfilter = dlfilter__new(dlfilter_file);
+		if (!dlfilter)
+			return -1;
+	}
+
 	if (!script_name) {
 		setup_pager();
 		use_browser = 0;
@@ -4032,6 +4050,10 @@ int cmd_script(int argc, const char **argv)
 		goto out_delete;
 	}
 
+	err = dlfilter__start(dlfilter, session);
+	if (err)
+		goto out_delete;
+
 	if (script_name) {
 		err = scripting_ops->start_script(script_name, argc, argv, session);
 		if (err)
@@ -4081,6 +4103,7 @@ int cmd_script(int argc, const char **argv)
 
 	if (script_started)
 		cleanup_scripting();
+	dlfilter__cleanup(dlfilter);
 out:
 	return err;
 }

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