Resguardo inicial

linux-7.2.3/tools/perf/tests/workloads/Build

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+
+perf-test-y += noploop.o
+perf-test-y += thloop.o
+perf-test-y += named_threads.o
+perf-test-y += leafloop.o
+perf-test-y += sqrtloop.o
+perf-test-y += brstack.o
+perf-test-y += datasym.o
+perf-test-y += landlock.o
+perf-test-y += traploop.o
+perf-test-y += inlineloop.o
+perf-test-y += jitdump.o
+perf-test-y += context_switch_loop.o
+perf-test-y += deterministic.o
+
+ifeq ($(CONFIG_RUST_SUPPORT),y)
+    perf-test-y += code_with_type.o
+    perf-test-y += code_with_type.a
+endif
+
+CFLAGS_sqrtloop.o         = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_leafloop.o         = -g -O0 -fno-inline -fno-omit-frame-pointer -U_FORTIFY_SOURCE
+CFLAGS_brstack.o          = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_datasym.o          = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_traploop.o         = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_inlineloop.o       = -g -O2
+CFLAGS_deterministic.o    = -g -O0 -fno-inline -U_FORTIFY_SOURCE
+CFLAGS_named_threads.o    = -g -O0 -fno-inline -U_FORTIFY_SOURCE

linux-7.2.3/tools/perf/tests/workloads/brstack.c

@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include "../tests.h"
+
+#define BENCH_RUNS 999999
+
+static volatile int cnt;
+
+static void brstack_bar(void) {
+}				/* return */
+
+static void brstack_foo(void) {
+	brstack_bar();		/* call */
+}				/* return */
+
+static void brstack_bench(void) {
+	void (*brstack_foo_ind)(void) = brstack_foo;
+
+	if ((cnt++) % 3)	/* branch (cond) */
+		brstack_foo();	/* call */
+	brstack_bar();		/* call */
+	brstack_foo_ind();	/* call (ind) */
+}
+
+static int brstack(int argc, const char **argv)
+{
+	int num_loops = BENCH_RUNS;
+
+	if (argc > 0)
+		num_loops = atoi(argv[0]);
+
+	while (1) {
+		if ((cnt++) > num_loops)
+			break;
+		brstack_bench();/* call */
+	}			/* branch (uncond) */
+	return 0;
+}
+
+DEFINE_WORKLOAD(brstack);

linux-7.2.3/tools/perf/tests/workloads/code_with_type.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+extern void test_rs(uint count);
+
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int code_with_type(int argc, const char **argv)
+{
+	int sec = 1, num_loops = 100;
+
+	pthread_setname_np(pthread_self(), "perf-code-with-type");
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	if (argc > 1)
+		num_loops = atoi(argv[1]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	/*
+	 * Rust doesn't have signal management in the standard library. To
+	 * not deal with any external crates, offload signal handling to the
+	 * outside code.
+	 */
+	while (!done) {
+		test_rs(num_loops);
+		continue;
+	}
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(code_with_type);

linux-7.2.3/tools/perf/tests/workloads/code_with_type.rs

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// We're going to look for this structure in the data type profiling report
+#[allow(dead_code)]
+struct Buf {
+    data1: u64,
+    data2: String,
+    data3: u64,
+}
+
+#[no_mangle]
+pub extern "C" fn test_rs(count: u32) {
+    let mut b = Buf {
+        data1: 0,
+        data2: String::from("data"),
+        data3: 0,
+    };
+
+    for _ in 1..count {
+        b.data1 += 1;
+        if b.data1 == 123 {
+            b.data1 += 1;
+        }
+
+        b.data3 += b.data1;
+    }
+}

linux-7.2.3/tools/perf/tests/workloads/context_switch_loop.c

@@ -0,0 +1,110 @@
+
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/compiler.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../tests.h"
+
+static int loops = 100;
+static char buf;
+int context_switch_loop_work = 1234;
+
+#define write_block(fd) \
+	do { \
+		if (write(fd, &buf, 1) <= 0) \
+			return 1; \
+	} while (0)
+
+#define read_block(fd) \
+	do { \
+		if (read(fd, &buf, 1) <= 0) \
+			return 1; \
+	} while (0)
+
+/* Not static to avoid LTO clobbering the function name */
+int context_switch_loop_proc1(int in_fd, int out_fd);
+int context_switch_loop_proc1(int in_fd, int out_fd)
+{
+	for (int i = 0; i < loops; i++) {
+		read_block(in_fd);
+		context_switch_loop_work += i * 3;
+		write_block(out_fd);
+	}
+	return 0;
+}
+
+int context_switch_loop_proc2(int in_fd, int out_fd);
+int context_switch_loop_proc2(int in_fd, int out_fd)
+{
+	for (int i = 0; i < loops; i++) {
+		write_block(out_fd);
+		context_switch_loop_work += i * 7;
+		read_block(in_fd);
+	}
+	return 0;
+}
+
+/*
+ * Launches two processes that take turns to execute a multiplication N times
+ */
+static int context_switch_loop(int argc, const char **argv)
+{
+	int a_to_b[2], b_to_a[2];
+	pid_t proc1_pid;
+	int status;
+	int ret;
+
+	if (argc > 0) {
+		loops = atoi(argv[0]);
+		if (loops < 0) {
+			fprintf(stderr, "Invalid number of loops: %s\n", argv[0]);
+			return 1;
+		}
+	}
+
+	if (pipe(a_to_b) || pipe(b_to_a)) {
+		perror("Pipe error");
+		return 1;
+	}
+
+	proc1_pid = fork();
+	if (proc1_pid < 0) {
+		perror("Fork error");
+		return 1;
+	}
+
+	if (!proc1_pid) {
+		close(a_to_b[0]);
+		close(b_to_a[1]);
+		prctl(PR_SET_NAME, "proc1", 0, 0, 0);
+		ret = context_switch_loop_proc1(b_to_a[0], a_to_b[1]);
+		close(a_to_b[1]);
+		close(b_to_a[0]);
+		exit(ret);
+	}
+
+	close(a_to_b[1]);
+	close(b_to_a[0]);
+	prctl(PR_SET_NAME, "proc2", 0, 0, 0);
+	ret = context_switch_loop_proc2(a_to_b[0], b_to_a[1]);
+	close(a_to_b[0]);
+	close(b_to_a[1]);
+
+	if (ret) {
+		kill(proc1_pid, SIGKILL);
+		return ret;
+	}
+
+	if (waitpid(proc1_pid, &status, 0) != proc1_pid || !WIFEXITED(status) ||
+	    WEXITSTATUS(status))
+		return 1;
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(context_switch_loop);

linux-7.2.3/tools/perf/tests/workloads/datasym.c

@@ -0,0 +1,60 @@
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+struct buf {
+	char data1;
+	char reserved[55];
+	char data2;
+} __attribute__((aligned(64)));
+
+/* volatile to try to avoid the compiler seeing reserved as unused. */
+static volatile struct buf workload_datasym_buf1 = {
+	/* to have this in the data section */
+	.reserved[0] = 1,
+};
+
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int datasym(int argc, const char **argv)
+{
+	int sec = 1;
+
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	while (!done) {
+		workload_datasym_buf1.data1++;
+		if (workload_datasym_buf1.data1 == 123) {
+			/*
+			 * Add some 'noise' in the loop to work around errata
+			 * 1694299 on Arm N1.
+			 *
+			 * Bias exists in SPE sampling which can cause the load
+			 * and store instructions to be skipped entirely. This
+			 * comes and goes randomly depending on the offset the
+			 * linker places the datasym loop at in the Perf binary.
+			 * With an extra branch in the middle of the loop that
+			 * isn't always taken, the instruction stream is no
+			 * longer a continuous repeating pattern that interacts
+			 * badly with the bias.
+			 */
+			workload_datasym_buf1.data1++;
+		}
+		workload_datasym_buf1.data2 += workload_datasym_buf1.data1;
+	}
+	return 0;
+}
+
+DEFINE_WORKLOAD(datasym);

linux-7.2.3/tools/perf/tests/workloads/deterministic.c

@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include "../tests.h"
+
+int dt_work = 1234;
+
+static void function1(void)
+{
+	dt_work += 7;
+	dt_work += 7;
+	dt_work += 7;
+}
+
+static void function2(void)
+{
+	dt_work += 7;
+	dt_work += 7;
+	dt_work += 7;
+}
+
+static int deterministic(int argc __maybe_unused,
+			 const char **argv __maybe_unused)
+{
+	dt_work += 7;
+	dt_work += 7;
+	dt_work += 7;
+
+	function1();
+
+	dt_work += 7;
+	dt_work += 7;
+	dt_work += 7;
+
+	function2();
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(deterministic);

linux-7.2.3/tools/perf/tests/workloads/inlineloop.c

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile int a;
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static inline void __attribute__((always_inline)) leaf(int b)
+{
+again:
+	a += b;
+	if (!done)
+		goto again;
+}
+
+static inline void __attribute__((always_inline)) middle(int b)
+{
+	leaf(b);
+}
+
+static noinline void parent(int b)
+{
+	middle(b);
+}
+
+static int inlineloop(int argc, const char **argv)
+{
+	int sec = 1;
+
+	pthread_setname_np(pthread_self(), "perf-inlineloop");
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	parent(sec);
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(inlineloop);

linux-7.2.3/tools/perf/tests/workloads/jitdump.c

@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/jitdump.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <time.h>
+
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "../tests.h"
+
+#ifndef HAVE_GETTID
+#include <sys/syscall.h>
+static inline pid_t gettid(void)
+{
+	return (pid_t)syscall(SYS_gettid);
+}
+#endif
+
+#define CHK_BYTE 0x5a
+
+static inline uint64_t get_timestamp(void)
+{
+#if defined(__x86_64__) || defined(__i386__)
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a"(low), "=d"(high));
+
+	return low | ((uint64_t)high) << 32;
+#else
+	struct timespec ts;
+	int ret;
+
+	ret = clock_gettime(CLOCK_MONOTONIC, &ts);
+	if (ret)
+		return 0;
+
+	return ((uint64_t)ts.tv_sec * 1000000000) + ts.tv_nsec;
+#endif
+}
+
+static FILE *open_jitdump(void)
+{
+	struct jitheader header = {
+		.magic = JITHEADER_MAGIC,
+		.version = JITHEADER_VERSION,
+		.total_size = sizeof(header),
+		.pid = getpid(),
+		.timestamp = get_timestamp(),
+		.flags =
+#if defined(__x86_64__) || defined(__i386__)
+			JITDUMP_FLAGS_ARCH_TIMESTAMP,
+#else
+			0,
+#endif
+	};
+	char filename[256];
+	int fd;
+	FILE *f;
+	void *m;
+
+	snprintf(filename, sizeof(filename), "jit-%d.dump", getpid());
+	/* Securely open using O_CREAT | O_EXCL to prevent symlink attacks. */
+	fd = open(filename, O_CREAT | O_EXCL | O_RDWR, 0644);
+	if (fd < 0) {
+		pr_err("Failed to open jitdump '%s': %s\n", filename, strerror(errno));
+		return NULL;
+	}
+	f = fdopen(fd, "w+");
+	if (!f) {
+		pr_err("Failed to associate stream with fd for '%s'\n", filename);
+		close(fd);
+		unlink(filename);
+		return NULL;
+	}
+	/* Create an MMAP event for the jitdump file. That is how perf tool finds it. */
+	m = mmap(0, getpagesize(), PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(f), 0);
+	if (m == MAP_FAILED) {
+		pr_err("mmap failed: %s\n", strerror(errno));
+		fclose(f);
+		unlink(filename);
+		return NULL;
+	}
+	munmap(m, getpagesize());
+
+	if (fwrite(&header, sizeof(header), 1, f) != 1) {
+		pr_err("Error writing jitdump header\n");
+		fclose(f);
+		unlink(filename);
+		return NULL;
+	}
+	return f;
+}
+
+static int write_jitdump(FILE *f, void *addr, const void *dat, size_t sz, uint64_t *idx)
+{
+	const char *sym = "jit_workload";
+	size_t sym_len = strlen(sym) + 1;
+	struct jr_code_load rec = {
+		.p.id = JIT_CODE_LOAD,
+		.p.total_size = sizeof(rec) + sym_len + sz,
+		.p.timestamp = get_timestamp(),
+		.pid = getpid(),
+		.tid = gettid(),
+		.vma = (unsigned long)addr,
+		.code_addr = (unsigned long)addr,
+		.code_size = sz,
+		.code_index = ++*idx,
+	};
+
+	if (fwrite(&rec, sizeof(rec), 1, f) != 1 ||
+	    fwrite(sym, sym_len, 1, f) != 1 ||
+	    fwrite(dat, sz, 1, f) != 1)
+		return -1;
+	return 0;
+}
+
+static void close_jitdump(FILE *f)
+{
+	fclose(f);
+}
+
+static int jitdump(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+#if defined(__x86_64__) || defined(__i386__)
+	/* Code to execute: mov CHK_BYTE, %eax ; ret */
+	uint8_t dat[] = { 0xb8, CHK_BYTE, 0x00, 0x00, 0x00, 0xc3 };
+#elif defined(__aarch64__)
+	/* Code to execute: mov w0, #CHK_BYTE ; ret */
+	uint8_t dat[] = {
+		(CHK_BYTE << 5) & 0xff, (CHK_BYTE >> 3) & 0xff, 0x80, 0x52,
+		0xc0, 0x03, 0x5f, 0xd6
+	};
+#elif defined(__riscv)
+	/* Code to execute: li a0, CHK_BYTE ; ret */
+	uint8_t dat[] = {
+		0x13, 0x05, (CHK_BYTE << 4) & 0xff, (CHK_BYTE >> 4) & 0xff,
+		0x67, 0x80, 0x00, 0x00
+	};
+#elif defined(__powerpc__)
+	/* Code to execute: li r3, CHK_BYTE ; blr */
+	uint32_t dat[] = { 0x38600000 | (CHK_BYTE & 0xffff), 0x4e800020 };
+#elif defined(__s390x__)
+	/* Code to execute: lhi %r2, CHK_BYTE ; br %r14 */
+	uint8_t dat[] = { 0xa7, 0x28, (CHK_BYTE >> 8) & 0xff, CHK_BYTE & 0xff, 0x07, 0xfe };
+#elif defined(__arm__)
+	/* Code to execute: mov r0, #CHK_BYTE ; bx lr */
+	uint8_t dat[] = {
+		CHK_BYTE & 0xff, 0x00, 0xa0, 0xe3,
+		0x1e, 0xff, 0x2f, 0xe1
+	};
+#elif defined(__mips__)
+	/* Code to execute: addiu $v0, $zero, CHK_BYTE ; jr $ra ; nop */
+	uint32_t dat[] = { 0x24020000 | (CHK_BYTE & 0xffff), 0x03e00008, 0x00000000 };
+#elif defined(__loongarch__)
+	/* Code to execute: addi.w $a0, $zero, CHK_BYTE ; jirl $zero, $ra, 0 */
+	uint32_t dat[] = { 0x02800004 | ((CHK_BYTE & 0xfff) << 10), 0x4c000020 };
+#else
+	uint32_t dat[0];
+#endif
+	void *addr;
+	FILE *f;
+	uint64_t idx = 0;
+	int ret = 1;
+
+	/* Reachable fallback check for unsupported architectures right at start. */
+	if (sizeof(dat) == 0) {
+		pr_err("JITDUMP workload not supported on this architecture\n");
+		return 1;
+	}
+
+	/* Get a memory page to store executable code. */
+	addr = mmap(0, getpagesize(), PROT_READ | PROT_WRITE | PROT_EXEC,
+		    MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (addr == MAP_FAILED) {
+		pr_err("Failed to map 1 -rwx page\n");
+		return 1;
+	}
+
+	f = open_jitdump();
+	if (!f) {
+		pr_err("Failed to open JITDUMP\n");
+		munmap(addr, getpagesize());
+		return 1;
+	}
+	/* Copy executable code to executable memory page. */
+	memcpy(addr, dat, sizeof(dat));
+	/* Synchronize the Instruction and Data caches. */
+	__builtin___clear_cache(addr, (char *)addr + sizeof(dat));
+
+	/* Record it in the jitdump file */
+	if (write_jitdump(f, addr, dat, sizeof(dat), &idx) == 0) {
+		int (*fn)(void) = addr;
+
+		/* Call the function. */
+		ret = fn() - CHK_BYTE;
+	}
+	close_jitdump(f);
+	munmap(addr, getpagesize());
+	return ret;
+}
+
+DEFINE_WORKLOAD(jitdump);

linux-7.2.3/tools/perf/tests/workloads/landlock.c

@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <unistd.h>
+#include "../tests.h"
+
+/* This workload was initially added to test enum augmentation with BTF in perf
+ * trace because its the only syscall that has an enum argument. Since it is
+ * a recent addition to the Linux kernel (at the time of the introduction of this
+ * 'perf test' workload) we just add the required types and defines here instead
+ * of including linux/landlock, that isn't available in older systems.
+ *
+ * We are not interested in the result of the syscall, just in intercepting
+ * its arguments.
+ */
+
+#ifndef __NR_landlock_add_rule
+#define __NR_landlock_add_rule 445
+#endif
+
+#ifndef LANDLOCK_ACCESS_FS_READ_FILE
+#define LANDLOCK_ACCESS_FS_READ_FILE	(1ULL << 2)
+
+#define LANDLOCK_RULE_PATH_BENEATH	1
+
+struct landlock_path_beneath_attr {
+        __u64 allowed_access;
+        __s32 parent_fd;
+};
+#endif
+
+#ifndef LANDLOCK_ACCESS_NET_CONNECT_TCP
+#define LANDLOCK_ACCESS_NET_CONNECT_TCP	(1ULL << 1)
+
+#define LANDLOCK_RULE_NET_PORT		2
+
+struct landlock_net_port_attr {
+	__u64 allowed_access;
+	__u64 port;
+};
+#endif
+
+static int landlock(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+	int fd = 11, flags = 45;
+
+	struct landlock_path_beneath_attr path_beneath_attr = {
+		.allowed_access = LANDLOCK_ACCESS_FS_READ_FILE,
+		.parent_fd = 14,
+	};
+
+	struct landlock_net_port_attr net_port_attr = {
+		.port = 19,
+		.allowed_access = LANDLOCK_ACCESS_NET_CONNECT_TCP,
+	};
+
+	syscall(__NR_landlock_add_rule, fd, LANDLOCK_RULE_PATH_BENEATH,
+		&path_beneath_attr, flags);
+
+	syscall(__NR_landlock_add_rule, fd, LANDLOCK_RULE_NET_PORT,
+		&net_port_attr, flags);
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(landlock);

linux-7.2.3/tools/perf/tests/workloads/leafloop.c

@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <unistd.h>
+#include "../tests.h"
+
+/* We want to check these symbols in perf script */
+noinline void leaf(void);
+noinline void parent(void);
+
+static volatile sig_atomic_t done asm("leafloop_done");
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+#if defined(__aarch64__)
+/*
+ * Write leaf() in assembly so it stays as a minimal leaf function with no
+ * stack frame and won't get silently broken in the future by any Perf wide
+ * compilation options like -fstack-protector-all.
+ */
+asm(
+	".pushsection .text,\"ax\",%progbits\n"
+	".global leaf\n"
+	".type leaf, %function\n"
+	"leaf:\n"
+	"	adrp	x1, leafloop_done\n"
+	"	ldr	w2, [x1, #:lo12:leafloop_done]\n"
+	"	cbz	w2, leaf\n"
+	"	ret\n"
+	".size leaf, .-leaf\n"
+	".popsection\n"
+);
+
+#else
+
+noinline void leaf(void)
+{
+	while (!done)
+		;
+}
+
+#endif
+
+noinline void parent(void)
+{
+	leaf();
+}
+
+static int leafloop(int argc, const char **argv)
+{
+	int sec = 1;
+
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	parent();
+	return 0;
+}
+
+DEFINE_WORKLOAD(leafloop);

linux-7.2.3/tools/perf/tests/workloads/named_threads.c

@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <limits.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+#define MAX_THREADS 25
+
+static int iterations = 500;
+int named_threads_work = 1234;
+
+typedef void *(*thread_fn_t)(void *);
+
+#define DEFINE_THREAD(n)						\
+noinline void *named_threads_thread##n(void *arg __maybe_unused)	\
+{									\
+	pthread_setname_np(pthread_self(), "thread" #n);		\
+	for (int i = 0; i < iterations; i++)				\
+		named_threads_work += 3;				\
+									\
+	return NULL;							\
+}
+
+#define THREAD_LIST(macro)	\
+	macro(1)		\
+	macro(2)		\
+	macro(3)		\
+	macro(4)		\
+	macro(5)		\
+	macro(6)		\
+	macro(7)		\
+	macro(8)		\
+	macro(9)		\
+	macro(10)		\
+	macro(11)		\
+	macro(12)		\
+	macro(13)		\
+	macro(14)		\
+	macro(15)		\
+	macro(16)		\
+	macro(17)		\
+	macro(18)		\
+	macro(19)		\
+	macro(20)		\
+	macro(21)		\
+	macro(22)		\
+	macro(23)		\
+	macro(24)		\
+	macro(25)
+
+#define DECLARE_THREAD(n) void *named_threads_thread##n(void *arg);
+
+THREAD_LIST(DECLARE_THREAD)
+THREAD_LIST(DEFINE_THREAD)
+
+#define THREAD_ENTRY(n) named_threads_thread##n,
+
+static thread_fn_t thread_fns[MAX_THREADS] = {
+	THREAD_LIST(THREAD_ENTRY)
+};
+
+/*
+ * Creates argv[0] threads that run a unique function named "thread[x]" which performs
+ * a multiplication in a loop for argv[1] loops.
+ */
+static int named_threads(int argc, const char **argv)
+{
+	pthread_t threads[MAX_THREADS];
+	int nr_threads = 1;
+	int err = 0;
+
+	if (argc > 0)
+		nr_threads = atoi(argv[0]);
+
+	if (nr_threads <= 0 || nr_threads > MAX_THREADS) {
+		fprintf(stderr, "Error: num threads must be 1 - %d\n", MAX_THREADS);
+		return 1;
+	}
+
+	if (argc > 1)
+		iterations = atoi(argv[1]);
+
+	if (iterations < 0) {
+		fprintf(stderr, "Error: iterations must be non-negative\n");
+		return 1;
+	}
+
+	for (int i = 0; i < nr_threads; i++) {
+		int ret;
+
+		ret = pthread_create(&threads[i], NULL, thread_fns[i], NULL);
+		if (ret) {
+			fprintf(stderr, "Error: failed to create thread%d: %s\n",
+				i + 1, strerror(ret));
+			return 1;
+		}
+	}
+
+	for (int i = 0; i < nr_threads; i++)
+		pthread_join(threads[i], NULL);
+
+	return err;
+}
+
+DEFINE_WORKLOAD(named_threads);

linux-7.2.3/tools/perf/tests/workloads/noploop.c

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int noploop(int argc, const char **argv)
+{
+	int sec = 1;
+
+	pthread_setname_np(pthread_self(), "perf-noploop");
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	while (!done)
+		continue;
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(noploop);

linux-7.2.3/tools/perf/tests/workloads/sqrtloop.c

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <math.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include <sys/wait.h>
+#include "../tests.h"
+
+static volatile sig_atomic_t done;
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static int __sqrtloop(int sec)
+{
+	signal(SIGALRM, sighandler);
+	alarm(sec);
+
+	while (!done)
+		(void)sqrt(rand());
+	return 0;
+}
+
+static int sqrtloop(int argc, const char **argv)
+{
+	int sec = 1;
+
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	switch (fork()) {
+	case 0:
+		return __sqrtloop(sec);
+	case -1:
+		return -1;
+	default:
+		wait(NULL);
+	}
+	return 0;
+}
+
+DEFINE_WORKLOAD(sqrtloop);

linux-7.2.3/tools/perf/tests/workloads/thloop.c

@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <pthread.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+static volatile sig_atomic_t done;
+
+/* We want to check this symbol in perf report */
+noinline void test_loop(void);
+
+static void sighandler(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+noinline void test_loop(void)
+{
+	while (!done);
+}
+
+static void *thfunc(void *arg)
+{
+	void (*loop_fn)(void) = arg;
+
+	loop_fn();
+	return NULL;
+}
+
+static int thloop(int argc, const char **argv)
+{
+	int nt = 2, sec = 1, err = 1;
+	pthread_t *thread_list = NULL;
+
+	if (argc > 0)
+		sec = atoi(argv[0]);
+
+	if (sec <= 0) {
+		fprintf(stderr, "Error: seconds (%d) must be >= 1\n", sec);
+		return 1;
+	}
+
+	if (argc > 1)
+		nt = atoi(argv[1]);
+
+	if (nt <= 0) {
+		fprintf(stderr, "Error: thread count (%d) must be >= 1\n", nt);
+		return 1;
+	}
+
+	signal(SIGINT, sighandler);
+	signal(SIGALRM, sighandler);
+
+	thread_list = calloc(nt, sizeof(pthread_t));
+	if (thread_list == NULL) {
+		fprintf(stderr, "Error: malloc failed for %d threads\n", nt);
+		goto out;
+	}
+	for (int i = 1; i < nt; i++) {
+		int ret = pthread_create(&thread_list[i], NULL, thfunc, test_loop);
+
+		if (ret) {
+			fprintf(stderr, "Error: failed to create thread %d\n", i);
+			done = 1; // Ensure started threads terminate.
+			goto out;
+		}
+	}
+	alarm(sec);
+	test_loop();
+	err = 0;
+out:
+	for (int i = 1; i < nt; i++) {
+		if (thread_list && thread_list[i])
+			pthread_join(thread_list[i], /*retval=*/NULL);
+	}
+	free(thread_list);
+	return err;
+}
+
+DEFINE_WORKLOAD(thloop);

linux-7.2.3/tools/perf/tests/workloads/traploop.c

@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include "../tests.h"
+
+#define BENCH_RUNS 999999
+
+#ifdef __aarch64__
+static void trap_bench(void)
+{
+	unsigned long val;
+
+	asm("mrs %0, ID_AA64ISAR0_EL1" : "=r" (val));   /* TRAP + ERET */
+}
+#else
+static void trap_bench(void) { }
+#endif
+
+static int traploop(int argc, const char **argv)
+{
+	int num_loops = BENCH_RUNS;
+
+	if (argc > 0)
+		num_loops = atoi(argv[0]);
+
+	for (int i = 0; i < num_loops; i++)
+		trap_bench();
+
+	return 0;
+}
+
+DEFINE_WORKLOAD(traploop);