perf lock: Use BPF for lock contention analysis

Add -b/--use-bpf option to use BPF to collect lock contention stats.
For simplicity it now runs system-wide and requires C-c to stop.
Upcoming changes will add the usual filtering.

  $ sudo perf lock con -b
  ^C
   contended   total wait     max wait     avg wait         type   caller

          42    192.67 us     13.64 us      4.59 us     spinlock   queue_work_on+0x20
          23     85.54 us     10.28 us      3.72 us     spinlock   worker_thread+0x14a
           6     13.92 us      6.51 us      2.32 us        mutex   kernfs_iop_permission+0x30
           3     11.59 us     10.04 us      3.86 us        mutex   kernfs_dop_revalidate+0x3c
           1      7.52 us      7.52 us      7.52 us     spinlock   kthread+0x115
           1      7.24 us      7.24 us      7.24 us     rwlock:W   sys_epoll_wait+0x148
           2      7.08 us      3.99 us      3.54 us     spinlock   delayed_work_timer_fn+0x1b
           1      6.41 us      6.41 us      6.41 us     spinlock   idle_balance+0xa06
           2      2.50 us      1.83 us      1.25 us        mutex   kernfs_iop_lookup+0x2f
           1      1.71 us      1.71 us      1.71 us        mutex   kernfs_iop_getattr+0x2c

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Blake Jones <blakejones@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20220729200756.666106-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/lock-contention.h

@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef PERF_LOCK_CONTENTION_H
+#define PERF_LOCK_CONTENTION_H
+
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct lock_stat {
+	struct hlist_node	hash_entry;
+	struct rb_node		rb;		/* used for sorting */
+
+	u64			addr;		/* address of lockdep_map, used as ID */
+	char			*name;		/* for strcpy(), we cannot use const */
+
+	unsigned int		nr_acquire;
+	unsigned int		nr_acquired;
+	unsigned int		nr_contended;
+	unsigned int		nr_release;
+
+	union {
+		unsigned int	nr_readlock;
+		unsigned int	flags;
+	};
+	unsigned int		nr_trylock;
+
+	/* these times are in nano sec. */
+	u64                     avg_wait_time;
+	u64			wait_time_total;
+	u64			wait_time_min;
+	u64			wait_time_max;
+
+	int			broken; /* flag of blacklist */
+	int			combined;
+};
+
+/*
+ * States of lock_seq_stat
+ *
+ * UNINITIALIZED is required for detecting first event of acquire.
+ * As the nature of lock events, there is no guarantee
+ * that the first event for the locks are acquire,
+ * it can be acquired, contended or release.
+ */
+#define SEQ_STATE_UNINITIALIZED      0	       /* initial state */
+#define SEQ_STATE_RELEASED	1
+#define SEQ_STATE_ACQUIRING	2
+#define SEQ_STATE_ACQUIRED	3
+#define SEQ_STATE_READ_ACQUIRED	4
+#define SEQ_STATE_CONTENDED	5
+
+/*
+ * MAX_LOCK_DEPTH
+ * Imported from include/linux/sched.h.
+ * Should this be synchronized?
+ */
+#define MAX_LOCK_DEPTH 48
+
+/*
+ * struct lock_seq_stat:
+ * Place to put on state of one lock sequence
+ * 1) acquire -> acquired -> release
+ * 2) acquire -> contended -> acquired -> release
+ * 3) acquire (with read or try) -> release
+ * 4) Are there other patterns?
+ */
+struct lock_seq_stat {
+	struct list_head        list;
+	int			state;
+	u64			prev_event_time;
+	u64                     addr;
+
+	int                     read_count;
+};
+
+struct thread_stat {
+	struct rb_node		rb;
+
+	u32                     tid;
+	struct list_head        seq_list;
+};
+
+/*
+ * CONTENTION_STACK_DEPTH
+ * Number of stack trace entries to find callers
+ */
+#define CONTENTION_STACK_DEPTH  8
+
+/*
+ * CONTENTION_STACK_SKIP
+ * Number of stack trace entries to skip when finding callers.
+ * The first few entries belong to the locking implementation itself.
+ */
+#define CONTENTION_STACK_SKIP  3
+
+/*
+ * flags for lock:contention_begin
+ * Imported from include/trace/events/lock.h.
+ */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
+
+struct machine;
+
+#ifdef HAVE_BPF_SKEL
+
+int lock_contention_prepare(void);
+int lock_contention_start(void);
+int lock_contention_stop(void);
+int lock_contention_read(struct machine *machine, struct hlist_head *head);
+int lock_contention_finish(void);
+
+#else  /* !HAVE_BPF_SKEL */
+
+static inline int lock_contention_prepare(void) { return 0; }
+static inline int lock_contention_start(void) { return 0; }
+static inline int lock_contention_stop(void) { return 0; }
+static inline int lock_contention_finish(void) { return 0; }
+
+static inline int lock_contention_read(struct machine *machine __maybe_unused,
+				       struct hlist_head *head __maybe_unused)
+{
+	return 0;
+}
+
+#endif  /* HAVE_BPF_SKEL */
+
+bool is_lock_function(struct machine *machine, u64 addr);
+
+#endif  /* PERF_LOCK_CONTENTION_H */