perf lock: Move common lock contention code to new file

Avoid references from util code to builtin-lock that require python
stubs. Move the functions and related variables to
util/lock-contention.c. Add max_stack_depth parameter to
match_callstack_filter to avoid sharing a global variable.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ilya Leoshkevich <iii@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Veronika Molnarova <vmolnaro@redhat.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Link: https://lore.kernel.org/r/20241119011644.971342-16-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 159 insertions, 22 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index f8e77c53e2f9..5ec97e8d6b6d 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -122,6 +122,7 @@ perf-util-y += topdown.o
 perf-util-y += iostat.o
 perf-util-y += stream.o
 perf-util-y += kvm-stat.o
+perf-util-y += lock-contention.o
 perf-util-$(CONFIG_AUXTRACE) += auxtrace.o
 perf-util-y += intel-pt-decoder/
 perf-util-$(CONFIG_AUXTRACE) += intel-pt.o
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index 41a1ad087895..37e17c56f106 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -458,7 +458,7 @@ int lock_contention_read(struct lock_contention *con)
 		if (con->save_callstack) {
 			bpf_map_lookup_elem(stack, &key.stack_id, stack_trace);
 
-			if (!match_callstack_filter(machine, stack_trace)) {
+			if (!match_callstack_filter(machine, stack_trace, con->max_stack)) {
 				con->nr_filtered += data.count;
 				goto next;
 			}
diff --git a/tools/perf/util/lock-contention.c b/tools/perf/util/lock-contention.c
new file mode 100644
index 000000000000..92e7b7b572a2
--- /dev/null
+++ b/tools/perf/util/lock-contention.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
+#include "env.h"
+#include "lock-contention.h"
+#include "machine.h"
+#include "symbol.h"
+
+#include <limits.h>
+#include <string.h>
+
+#include <linux/hash.h>
+#include <linux/zalloc.h>
+
+#define __lockhashfn(key)	hash_long((unsigned long)key, LOCKHASH_BITS)
+#define lockhashentry(key)	(lockhash_table + __lockhashfn((key)))
+
+struct callstack_filter {
+	struct list_head list;
+	char name[];
+};
+
+static LIST_HEAD(callstack_filters);
+struct hlist_head *lockhash_table;
+
+int parse_call_stack(const struct option *opt __maybe_unused, const char *str,
+		     int unset __maybe_unused)
+{
+	char *s, *tmp, *tok;
+	int ret = 0;
+
+	s = strdup(str);
+	if (s == NULL)
+		return -1;
+
+	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		struct callstack_filter *entry;
+
+		entry = malloc(sizeof(*entry) + strlen(tok) + 1);
+		if (entry == NULL) {
+			pr_err("Memory allocation failure\n");
+			free(s);
+			return -1;
+		}
+
+		strcpy(entry->name, tok);
+		list_add_tail(&entry->list, &callstack_filters);
+	}
+
+	free(s);
+	return ret;
+}
+
+bool needs_callstack(void)
+{
+	return !list_empty(&callstack_filters);
+}
+
+struct lock_stat *lock_stat_find(u64 addr)
+{
+	struct hlist_head *entry = lockhashentry(addr);
+	struct lock_stat *ret;
+
+	hlist_for_each_entry(ret, entry, hash_entry) {
+		if (ret->addr == addr)
+			return ret;
+	}
+	return NULL;
+}
+
+struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags)
+{
+	struct hlist_head *entry = lockhashentry(addr);
+	struct lock_stat *ret, *new;
+
+	hlist_for_each_entry(ret, entry, hash_entry) {
+		if (ret->addr == addr)
+			return ret;
+	}
+
+	new = zalloc(sizeof(struct lock_stat));
+	if (!new)
+		goto alloc_failed;
+
+	new->addr = addr;
+	new->name = strdup(name);
+	if (!new->name) {
+		free(new);
+		goto alloc_failed;
+	}
+
+	new->flags = flags;
+	new->wait_time_min = ULLONG_MAX;
+
+	hlist_add_head(&new->hash_entry, entry);
+	return new;
+
+alloc_failed:
+	pr_err("memory allocation failed\n");
+	return NULL;
+}
+
+bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth)
+{
+	struct map *kmap;
+	struct symbol *sym;
+	u64 ip;
+	const char *arch = perf_env__arch(machine->env);
+
+	if (list_empty(&callstack_filters))
+		return true;
+
+	for (int i = 0; i < max_stack_depth; i++) {
+		struct callstack_filter *filter;
+
+		/*
+		 * In powerpc, the callchain saved by kernel always includes
+		 * first three entries as the NIP (next instruction pointer),
+		 * LR (link register), and the contents of LR save area in the
+		 * second stack frame. In certain scenarios its possible to have
+		 * invalid kernel instruction addresses in either LR or the second
+		 * stack frame's LR. In that case, kernel will store that address as
+		 * zero.
+		 *
+		 * The below check will continue to look into callstack,
+		 * incase first or second callstack index entry has 0
+		 * address for powerpc.
+		 */
+		if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") ||
+						(i != 1 && i != 2))))
+			break;
+
+		ip = callstack[i];
+		sym = machine__find_kernel_symbol(machine, ip, &kmap);
+		if (sym == NULL)
+			continue;
+
+		list_for_each_entry(filter, &callstack_filters, list) {
+			if (strstr(sym->name, filter->name))
+				return true;
+		}
+	}
+	return false;
+}
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
index 1a7248ff3889..bd71fb73825a 100644
--- a/tools/perf/util/lock-contention.h
+++ b/tools/perf/util/lock-contention.h
@@ -67,10 +67,11 @@ struct lock_stat {
  */
 #define MAX_LOCK_DEPTH 48
 
-struct lock_stat *lock_stat_find(u64 addr);
-struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags);
+/* based on kernel/lockdep.c */
+#define LOCKHASH_BITS		12
+#define LOCKHASH_SIZE		(1UL << LOCKHASH_BITS)
 
-bool match_callstack_filter(struct machine *machine, u64 *callstack);
+extern struct hlist_head *lockhash_table;
 
 /*
  * struct lock_seq_stat:
@@ -148,8 +149,17 @@ struct lock_contention {
 	bool save_callstack;
 };
 
-#ifdef HAVE_BPF_SKEL
+struct option;
+int parse_call_stack(const struct option *opt, const char *str, int unset);
+bool needs_callstack(void);
 
+struct lock_stat *lock_stat_find(u64 addr);
+struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags);
+
+bool match_callstack_filter(struct machine *machine, u64 *callstack, int max_stack_depth);
+
+
+#ifdef HAVE_BPF_SKEL
 int lock_contention_prepare(struct lock_contention *con);
 int lock_contention_start(void);
 int lock_contention_stop(void);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index fa25e7ed8a7f..6851f9b07e04 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -18,7 +18,6 @@
 #include "mmap.h"
 #include "util/kwork.h"
 #include "util/sample.h"
-#include "util/lock-contention.h"
 #include <internal/lib.h>
 #include "../builtin.h"
 
@@ -1311,22 +1310,6 @@ struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork __maybe_unused,
 	return NULL;
 }
 
-bool match_callstack_filter(struct machine *machine __maybe_unused, u64 *callstack __maybe_unused)
-{
-	return false;
-}
-
-struct lock_stat *lock_stat_find(u64 addr __maybe_unused)
-{
-	return NULL;
-}
-
-struct lock_stat *lock_stat_findnew(u64 addr __maybe_unused, const char *name __maybe_unused,
-				int flags __maybe_unused)
-{
-	return NULL;
-}
-
 int cmd_inject(int argc __maybe_unused, const char *argv[] __maybe_unused)
 {
 	return -1;