Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main updates in this cycle were:

   - Lots of perf tooling changes too voluminous to list (big perf trace
     and perf stat improvements, lots of libtraceevent reorganization,
     etc.), so I'll list the authors and refer to the changelog for
     details:

       Benjamin Peterson, Jérémie Galarneau, Kim Phillips, Peter
       Zijlstra, Ravi Bangoria, Sangwon Hong, Sean V Kelley, Steven
       Rostedt, Thomas Gleixner, Ding Xiang, Eduardo Habkost, Thomas
       Richter, Andi Kleen, Sanskriti Sharma, Adrian Hunter, Tzvetomir
       Stoyanov, Arnaldo Carvalho de Melo, Jiri Olsa.

     ... with the bulk of the changes written by Jiri Olsa, Tzvetomir
     Stoyanov and Arnaldo Carvalho de Melo.

   - Continued intel_rdt work with a focus on playing well with perf
     events. This also imported some non-perf RDT work due to
     dependencies. (Reinette Chatre)

   - Implement counter freezing for Arch Perfmon v4 (Skylake and newer).
     This allows to speed up the PMI handler by avoiding unnecessary MSR
     writes and make it more accurate. (Andi Kleen)

   - kprobes cleanups and simplification (Masami Hiramatsu)

   - Intel Goldmont PMU updates (Kan Liang)

   - ... plus misc other fixes and updates"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (155 commits)
  kprobes/x86: Use preempt_enable() in optimized_callback()
  x86/intel_rdt: Prevent pseudo-locking from using stale pointers
  kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
  perf/x86/intel: Export mem events only if there's PEBS support
  x86/cpu: Drop pointless static qualifier in punit_dev_state_show()
  x86/intel_rdt: Fix initial allocation to consider CDP
  x86/intel_rdt: CBM overlap should also check for overlap with CDP peer
  x86/intel_rdt: Introduce utility to obtain CDP peer
  tools lib traceevent, perf tools: Move struct tep_handler definition in a local header file
  tools lib traceevent: Separate out tep_strerror() for strerror_r() issues
  perf python: More portable way to make CFLAGS work with clang
  perf python: Make clang_has_option() work on Python 3
  perf tools: Free temporary 'sys' string in read_event_files()
  perf tools: Avoid double free in read_event_file()
  perf tools: Free 'printk' string in parse_ftrace_printk()
  perf tools: Cleanup trace-event-info 'tdata' leak
  perf strbuf: Match va_{add,copy} with va_end
  perf test: S390 does not support watchpoints in test 22
  perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG
  tools include: Adopt linux/bits.h
  ...

1 files changed, 80 insertions, 0 deletions

diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c
new file mode 100644
index 000000000000..b59e8812ee8c
--- /dev/null
+++ b/tools/perf/examples/bpf/etcsnoop.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the filename syscalls with the contents of the filename pointer argument
+ * filtering only those that do not start with /etc/.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * It'll catch some openat syscalls related to the dynamic linked and
+ * the last one should be the one for '/etc/passwd'.
+ *
+ * This matches what is marshalled into the raw_syscall:sys_enter payload
+ * expected by the 'perf trace' beautifiers, and can be used by them unmodified,
+ * which will be done as that feature is implemented in the next csets, for now
+ * it will appear in a dump done by the default tracepoint handler in 'perf trace',
+ * that uses bpf_output__fprintf() to just dump those contents, as done with
+ * the bpf-output event associated with the __bpf_output__ map declared in
+ * tools/perf/include/bpf/stdio.h.
+ */
+
+#include <stdio.h>
+
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+struct augmented_filename {
+	int	size;
+	int	reserved;
+	char	value[64];
+};
+
+#define augmented_filename_syscall_enter(syscall) 						\
+struct augmented_enter_##syscall##_args {			 				\
+	struct syscall_enter_##syscall##_args	args;				 		\
+	struct augmented_filename		filename;				 	\
+};												\
+int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
+{												\
+	char etc[6] = "/etc/";									\
+	struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; 	\
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);			\
+	augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, 		\
+						      sizeof(augmented_args.filename.value), 	\
+						      args->filename_ptr); 			\
+	if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0)			\
+		return 0;									\
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
+			  &augmented_args, 							\
+			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
+			   augmented_args.filename.size));					\
+	return 0;										\
+}
+
+struct syscall_enter_openat_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   dfd;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(openat);
+
+struct syscall_enter_open_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	char		   *filename_ptr;
+	long		   flags;
+	long		   mode;
+};
+
+augmented_filename_syscall_enter(open);
+
+license(GPL);