Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 350 insertions, 0 deletions

diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
new file mode 100644
index 000000000..02d47913c
--- /dev/null
+++ b/tools/perf/builtin-bench.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * builtin-bench.c
+ *
+ * General benchmarking collections provided by perf
+ *
+ * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ */
+
+/*
+ * Available benchmark collection list:
+ *
+ *  sched ... scheduler and IPC performance
+ *  syscall ... System call performance
+ *  mem   ... memory access performance
+ *  numa  ... NUMA scheduling and MM performance
+ *  futex ... Futex performance
+ *  epoll ... Event poll performance
+ */
+#include <subcmd/parse-options.h>
+#include "builtin.h"
+#include "bench/bench.h"
+
+#include <locale.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <linux/zalloc.h>
+
+typedef int (*bench_fn_t)(int argc, const char **argv);
+
+struct bench {
+	const char	*name;
+	const char	*summary;
+	bench_fn_t	fn;
+};
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static const struct bench numa_benchmarks[] = {
+	{ "mem",	"Benchmark for NUMA workloads",			bench_numa		},
+	{ "all",	"Run all NUMA benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+#endif
+
+static const struct bench sched_benchmarks[] = {
+	{ "messaging",	"Benchmark for scheduling and IPC",		bench_sched_messaging	},
+	{ "pipe",	"Benchmark for pipe() between two processes",	bench_sched_pipe	},
+	{ "seccomp-notify",	"Benchmark for seccomp user notify",	bench_sched_seccomp_notify},
+	{ "all",	"Run all scheduler benchmarks",		NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
+static const struct bench syscall_benchmarks[] = {
+	{ "basic",	"Benchmark for basic getppid(2) calls",		bench_syscall_basic	},
+	{ "getpgid",	"Benchmark for getpgid(2) calls",		bench_syscall_getpgid	},
+	{ "fork",	"Benchmark for fork(2) calls",			bench_syscall_fork	},
+	{ "execve",	"Benchmark for execve(2) calls",		bench_syscall_execve	},
+	{ "all",	"Run all syscall benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			},
+};
+
+static const struct bench mem_benchmarks[] = {
+	{ "memcpy",	"Benchmark for memcpy() functions",		bench_mem_memcpy	},
+	{ "memset",	"Benchmark for memset() functions",		bench_mem_memset	},
+	{ "find_bit",	"Benchmark for find_bit() functions",		bench_mem_find_bit	},
+	{ "mmap",	"Benchmark for mmap() mappings",		bench_mem_mmap		},
+	{ "all",	"Run all memory access benchmarks",		NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
+static const struct bench futex_benchmarks[] = {
+	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
+	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "wake-parallel", "Benchmark for parallel futex wake calls",   bench_futex_wake_parallel },
+	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
+	/* pi-futexes */
+	{ "lock-pi",	"Benchmark for futex lock_pi calls",            bench_futex_lock_pi	},
+	{ "all",	"Run all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
+#ifdef HAVE_EVENTFD_SUPPORT
+static const struct bench epoll_benchmarks[] = {
+	{ "wait",	"Benchmark epoll concurrent epoll_waits",       bench_epoll_wait	},
+	{ "ctl",	"Benchmark epoll concurrent epoll_ctls",        bench_epoll_ctl		},
+	{ "all",	"Run all futex benchmarks",			NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+#endif // HAVE_EVENTFD_SUPPORT
+
+static const struct bench internals_benchmarks[] = {
+	{ "synthesize", "Benchmark perf event synthesis",	bench_synthesize	},
+	{ "kallsyms-parse", "Benchmark kallsyms parsing",	bench_kallsyms_parse	},
+	{ "inject-build-id", "Benchmark build-id injection",	bench_inject_build_id	},
+	{ "evlist-open-close", "Benchmark evlist open and close",	bench_evlist_open_close	},
+	{ "pmu-scan", "Benchmark sysfs PMU info scanning",	bench_pmu_scan		},
+	{ NULL,		NULL,					NULL			}
+};
+
+static const struct bench breakpoint_benchmarks[] = {
+	{ "thread", "Benchmark thread start/finish with breakpoints", bench_breakpoint_thread},
+	{ "enable", "Benchmark breakpoint enable/disable", bench_breakpoint_enable},
+	{ "all", "Run all breakpoint benchmarks", NULL},
+	{ NULL,	NULL, NULL },
+};
+
+static const struct bench uprobe_benchmarks[] = {
+	{ "baseline",	"Baseline libc usleep(1000) call",				bench_uprobe_baseline,	},
+	{ "empty",	"Attach empty BPF prog to uprobe on usleep, system wide",	bench_uprobe_empty,	},
+	{ "trace_printk", "Attach trace_printk BPF prog to uprobe on usleep syswide",	bench_uprobe_trace_printk,	},
+	{ "empty_ret",	"Attach empty BPF prog to uretprobe on usleep, system wide",	bench_uprobe_empty_ret,	},
+	{ "trace_printk_ret", "Attach trace_printk BPF prog to uretprobe on usleep syswide", bench_uprobe_trace_printk_ret,},
+	{ NULL,	NULL, NULL },
+};
+
+struct collection {
+	const char		*name;
+	const char		*summary;
+	const struct bench	*benchmarks;
+};
+
+static const struct collection collections[] = {
+	{ "sched",	"Scheduler and IPC benchmarks",			sched_benchmarks	},
+	{ "syscall",	"System call benchmarks",			syscall_benchmarks	},
+	{ "mem",	"Memory access benchmarks",			mem_benchmarks		},
+#ifdef HAVE_LIBNUMA_SUPPORT
+	{ "numa",	"NUMA scheduling and MM benchmarks",		numa_benchmarks		},
+#endif
+	{"futex",       "Futex stressing benchmarks",                   futex_benchmarks        },
+#ifdef HAVE_EVENTFD_SUPPORT
+	{"epoll",       "Epoll stressing benchmarks",                   epoll_benchmarks        },
+#endif
+	{ "internals",	"Perf-internals benchmarks",			internals_benchmarks	},
+	{ "breakpoint",	"Breakpoint benchmarks",			breakpoint_benchmarks	},
+	{ "uprobe",	"uprobe benchmarks",				uprobe_benchmarks	},
+	{ "all",	"All benchmarks",				NULL			},
+	{ NULL,		NULL,						NULL			}
+};
+
+/* Iterate over all benchmark collections: */
+#define for_each_collection(coll) \
+	for (coll = collections; coll->name; coll++)
+
+/* Iterate over all benchmarks within a collection: */
+#define for_each_bench(coll, bench) \
+	for (bench = coll->benchmarks; bench && bench->name; bench++)
+
+static void dump_benchmarks(const struct collection *coll)
+{
+	const struct bench *bench;
+
+	printf("\n        # List of available benchmarks for collection '%s':\n\n", coll->name);
+
+	for_each_bench(coll, bench)
+		printf("%14s: %s\n", bench->name, bench->summary);
+
+	printf("\n");
+}
+
+static const char *bench_format_str;
+
+/* Output/formatting style, exported to benchmark modules: */
+int bench_format = BENCH_FORMAT_DEFAULT;
+unsigned int bench_repeat = 10; /* default number of times to repeat the run */
+
+static const struct option bench_options[] = {
+	OPT_STRING('f', "format", &bench_format_str, "default|simple", "Specify the output formatting style"),
+	OPT_UINTEGER('r', "repeat",  &bench_repeat,   "Specify number of times to repeat the run"),
+	OPT_END()
+};
+
+static const char * const bench_usage[] = {
+	"perf bench [<common options>] <collection> <benchmark> [<options>]",
+	NULL
+};
+
+static void print_usage(void)
+{
+	const struct collection *coll;
+	int i;
+
+	printf("Usage: \n");
+	for (i = 0; bench_usage[i]; i++)
+		printf("\t%s\n", bench_usage[i]);
+	printf("\n");
+
+	printf("        # List of all available benchmark collections:\n\n");
+
+	for_each_collection(coll)
+		printf("%14s: %s\n", coll->name, coll->summary);
+	printf("\n");
+}
+
+static int bench_str2int(const char *str)
+{
+	if (!str)
+		return BENCH_FORMAT_DEFAULT;
+
+	if (!strcmp(str, BENCH_FORMAT_DEFAULT_STR))
+		return BENCH_FORMAT_DEFAULT;
+	else if (!strcmp(str, BENCH_FORMAT_SIMPLE_STR))
+		return BENCH_FORMAT_SIMPLE;
+
+	return BENCH_FORMAT_UNKNOWN;
+}
+
+/*
+ * Run a specific benchmark but first rename the running task's ->comm[]
+ * to something meaningful:
+ */
+static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
+		     int argc, const char **argv)
+{
+	int size;
+	char *name;
+	int ret;
+
+	size = strlen(coll_name) + 1 + strlen(bench_name) + 1;
+
+	name = zalloc(size);
+	BUG_ON(!name);
+
+	scnprintf(name, size, "%s-%s", coll_name, bench_name);
+
+	prctl(PR_SET_NAME, name);
+	argv[0] = name;
+
+	ret = fn(argc, argv);
+
+	free(name);
+
+	return ret;
+}
+
+static void run_collection(const struct collection *coll)
+{
+	const struct bench *bench;
+	const char *argv[2];
+
+	argv[1] = NULL;
+	/*
+	 * TODO:
+	 *
+	 * Preparing preset parameters for
+	 * embedded, ordinary PC, HPC, etc...
+	 * would be helpful.
+	 */
+	for_each_bench(coll, bench) {
+		if (!bench->fn)
+			break;
+		printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
+
+		argv[1] = bench->name;
+		run_bench(coll->name, bench->name, bench->fn, 1, argv);
+		printf("\n");
+	}
+}
+
+static void run_all_collections(void)
+{
+	const struct collection *coll;
+
+	for_each_collection(coll)
+		run_collection(coll);
+}
+
+int cmd_bench(int argc, const char **argv)
+{
+	const struct collection *coll;
+	int ret = 0;
+
+	/* Unbuffered output */
+	setvbuf(stdout, NULL, _IONBF, 0);
+	setlocale(LC_ALL, "");
+
+	if (argc < 2) {
+		/* No collection specified. */
+		print_usage();
+		goto end;
+	}
+
+	argc = parse_options(argc, argv, bench_options, bench_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	bench_format = bench_str2int(bench_format_str);
+	if (bench_format == BENCH_FORMAT_UNKNOWN) {
+		printf("Unknown format descriptor: '%s'\n", bench_format_str);
+		goto end;
+	}
+
+	if (bench_repeat == 0) {
+		printf("Invalid repeat option: Must specify a positive value\n");
+		goto end;
+	}
+
+	if (argc < 1) {
+		print_usage();
+		goto end;
+	}
+
+	if (!strcmp(argv[0], "all")) {
+		run_all_collections();
+		goto end;
+	}
+
+	for_each_collection(coll) {
+		const struct bench *bench;
+
+		if (strcmp(coll->name, argv[0]))
+			continue;
+
+		if (argc < 2) {
+			/* No bench specified. */
+			dump_benchmarks(coll);
+			goto end;
+		}
+
+		if (!strcmp(argv[1], "all")) {
+			run_collection(coll);
+			goto end;
+		}
+
+		for_each_bench(coll, bench) {
+			if (strcmp(bench->name, argv[1]))
+				continue;
+
+			if (bench_format == BENCH_FORMAT_DEFAULT)
+				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
+			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
+			goto end;
+		}
+
+		if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
+			dump_benchmarks(coll);
+			goto end;
+		}
+
+		printf("Unknown benchmark: '%s' for collection '%s'\n", argv[1], argv[0]);
+		ret = 1;
+		goto end;
+	}
+
+	printf("Unknown collection: '%s'\n", argv[0]);
+	ret = 1;
+
+end:
+	return ret;
+}