Resguardo inicial

linux-7.2.3/tools/testing/selftests/syscall_user_dispatch/.gitignore

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sud_test
+sud_benchmark

linux-7.2.3/tools/testing/selftests/syscall_user_dispatch/Makefile

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+top_srcdir = ../../../..
+INSTALL_HDR_PATH = $(top_srcdir)/usr
+LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
+
+CFLAGS += -Wall -I$(LINUX_HDR_PATH)
+
+TEST_GEN_PROGS := sud_test sud_benchmark
+include ../lib.mk

linux-7.2.3/tools/testing/selftests/syscall_user_dispatch/config

@@ -0,0 +1 @@
+CONFIG_GENERIC_ENTRY=y

linux-7.2.3/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c

@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Benchmark and test syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <sys/sysinfo.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF	0
+# define PR_SYS_DISPATCH_ON	1
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00)  /* Bad Linux syscall number */
+#endif
+
+/*
+ * To test returning from a sigsys with selector blocked, the test
+ * requires some per-architecture support (i.e. knowledge about the
+ * signal trampoline address).  On i386, we know it is on the vdso, and
+ * a small trampoline is open-coded for x86_64.  Other architectures
+ * that have a trampoline in the vdso will support TEST_BLOCKED_RETURN
+ * out of the box, but don't enable them until they support syscall user
+ * dispatch.
+ */
+#if defined(__x86_64__) || defined(__i386__)
+#define TEST_BLOCKED_RETURN
+#endif
+
+#ifdef __x86_64__
+void* (syscall_dispatcher_start)(void);
+void* (syscall_dispatcher_end)(void);
+#else
+unsigned long syscall_dispatcher_start = 0;
+unsigned long syscall_dispatcher_end = 0;
+#endif
+
+unsigned long trapped_call_count = 0;
+unsigned long native_call_count = 0;
+
+char selector;
+#define SYSCALL_BLOCK   (selector = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_UNBLOCK (selector = SYSCALL_DISPATCH_FILTER_ALLOW)
+
+#define CALIBRATION_STEP 100000
+#define CALIBRATE_TO_SECS 5
+int factor;
+
+static double one_sysinfo_step(void)
+{
+	struct timespec t1, t2;
+	int i;
+	struct sysinfo info;
+
+	clock_gettime(CLOCK_MONOTONIC, &t1);
+	for (i = 0; i < CALIBRATION_STEP; i++)
+		sysinfo(&info);
+	clock_gettime(CLOCK_MONOTONIC, &t2);
+	return (t2.tv_sec - t1.tv_sec) + 1.0e-9 * (t2.tv_nsec - t1.tv_nsec);
+}
+
+static void calibrate_set(void)
+{
+	double elapsed = 0;
+
+	printf("Calibrating test set to last ~%d seconds...\n", CALIBRATE_TO_SECS);
+
+	while (elapsed < 1) {
+		elapsed += one_sysinfo_step();
+		factor += CALIBRATE_TO_SECS;
+	}
+
+	printf("test iterations = %d\n", CALIBRATION_STEP * factor);
+}
+
+static double perf_syscall(void)
+{
+	unsigned int i;
+	double partial = 0;
+
+	for (i = 0; i < factor; ++i)
+		partial += one_sysinfo_step()/(CALIBRATION_STEP*factor);
+	return partial;
+}
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+	char buf[1024];
+	int len;
+
+	SYSCALL_UNBLOCK;
+
+	/* printf and friends are not signal-safe. */
+	len = snprintf(buf, 1024, "Caught sys_%x\n", info->si_syscall);
+	write(1, buf, len);
+
+	if (info->si_syscall == MAGIC_SYSCALL_1)
+		trapped_call_count++;
+	else
+		native_call_count++;
+
+#ifdef TEST_BLOCKED_RETURN
+	SYSCALL_BLOCK;
+#endif
+
+#ifdef __x86_64__
+	__asm__ volatile("movq $0xf, %rax");
+	__asm__ volatile("leaveq");
+	__asm__ volatile("add $0x8, %rsp");
+	__asm__ volatile("syscall_dispatcher_start:");
+	__asm__ volatile("syscall");
+	__asm__ volatile("nop"); /* Landing pad within dispatcher area */
+	__asm__ volatile("syscall_dispatcher_end:");
+#endif
+
+}
+
+int main(void)
+{
+	struct sigaction act;
+	double time1, time2;
+	int ret;
+	sigset_t mask;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+
+	calibrate_set();
+
+	time1 = perf_syscall();
+	printf("Avg syscall time %.0lfns.\n", time1 * 1.0e9);
+
+	ret = sigaction(SIGSYS, &act, NULL);
+	if (ret) {
+		perror("Error sigaction:");
+		exit(-1);
+	}
+
+	fprintf(stderr, "Enabling syscall trapping.\n");
+
+	if (prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON,
+		  syscall_dispatcher_start,
+		  (syscall_dispatcher_end - syscall_dispatcher_start + 1),
+		  &selector)) {
+		perror("prctl failed\n");
+		exit(-1);
+	}
+
+	SYSCALL_BLOCK;
+	syscall(MAGIC_SYSCALL_1);
+
+#ifdef TEST_BLOCKED_RETURN
+	if (selector == SYSCALL_DISPATCH_FILTER_ALLOW) {
+		fprintf(stderr, "Failed to return with selector blocked.\n");
+		exit(-1);
+	}
+#endif
+
+	SYSCALL_UNBLOCK;
+
+	if (!trapped_call_count) {
+		fprintf(stderr, "syscall trapping does not work.\n");
+		exit(-1);
+	}
+
+	time2 = perf_syscall();
+
+	if (native_call_count) {
+		perror("syscall trapping intercepted more syscalls than expected\n");
+		exit(-1);
+	}
+
+	printf("trapped_call_count %lu, native_call_count %lu.\n",
+	       trapped_call_count, native_call_count);
+	printf("Avg syscall time %.0lfns.\n", time2 * 1.0e9);
+	printf("Interception overhead: %.1lf%% (+%.0lfns).\n",
+	       100.0 * (time2 / time1 - 1.0), 1.0e9 * (time2 - time1));
+	return 0;
+
+}

linux-7.2.3/tools/testing/selftests/syscall_user_dispatch/sud_test.c

@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Test code for syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <sys/prctl.h>
+#include <sys/sysinfo.h>
+#include <sys/syscall.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#include <asm/unistd.h>
+#include "kselftest_harness.h"
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF	0
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
+#endif
+
+#ifndef PR_SYS_DISPATCH_EXCLUSIVE_ON
+# define PR_SYS_DISPATCH_EXCLUSIVE_ON	1
+# define PR_SYS_DISPATCH_INCLUSIVE_ON	2
+#endif
+
+#ifndef SYS_USER_DISPATCH
+# define SYS_USER_DISPATCH	2
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00)  /* Bad Linux syscall number */
+#endif
+
+#define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW)
+
+/* Test Summary:
+ *
+ * - dispatch_trigger_sigsys: Verify if PR_SET_SYSCALL_USER_DISPATCH is
+ *   able to trigger SIGSYS on a syscall.
+ *
+ * - bad_selector: Test that a bad selector value triggers SIGSYS with
+ *   si_errno EINVAL.
+ *
+ * - bad_prctl_param: Test that the API correctly rejects invalid
+ *   parameters on prctl
+ *
+ * - dispatch_and_return: Test that a syscall is selectively dispatched
+ *   to userspace depending on the value of selector.
+ *
+ * - disable_dispatch: Test that the PR_SYS_DISPATCH_OFF correctly
+ *   disables the dispatcher
+ *
+ * - direct_dispatch_range: Test that a syscall within the allowed range
+ *   can bypass the dispatcher.
+ */
+
+TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS)
+{
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	struct sysinfo info;
+	int ret;
+
+	ret = sysinfo(&info);
+	ASSERT_EQ(0, ret);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	SYSCALL_DISPATCH_ON(sel);
+
+	sysinfo(&info);
+
+	EXPECT_FALSE(true) {
+		TH_LOG("Unreachable!");
+	}
+}
+
+static void prctl_valid(struct __test_metadata *_metadata,
+			unsigned long op, unsigned long off,
+			unsigned long size, void *sel)
+{
+	EXPECT_EQ(0, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, sel));
+}
+
+static void prctl_invalid(struct __test_metadata *_metadata,
+			  unsigned long op, unsigned long off,
+			  unsigned long size, void *sel, int err)
+{
+	EXPECT_EQ(-1, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, sel));
+	EXPECT_EQ(err, errno);
+}
+
+TEST(bad_prctl_param)
+{
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	int op;
+
+	/* Invalid op */
+	op = -1;
+	prctl_invalid(_metadata, op, 0, 0, &sel, EINVAL);
+
+	/* PR_SYS_DISPATCH_OFF */
+	op = PR_SYS_DISPATCH_OFF;
+
+	/* offset != 0 */
+	prctl_invalid(_metadata, op, 0x1, 0x0, 0, EINVAL);
+
+	/* len != 0 */
+	prctl_invalid(_metadata, op, 0x0, 0xff, 0, EINVAL);
+
+	/* sel != NULL */
+	prctl_invalid(_metadata, op, 0x0, 0x0, &sel, EINVAL);
+
+	/* Valid parameter */
+	prctl_valid(_metadata, op, 0x0, 0x0, 0x0);
+
+	/* PR_SYS_DISPATCH_EXCLUSIVE_ON */
+	op = PR_SYS_DISPATCH_EXCLUSIVE_ON;
+
+	/* Dispatcher region is bad (offset > 0 && len == 0) */
+	prctl_invalid(_metadata, op, 0x1, 0x0, &sel, EINVAL);
+	prctl_invalid(_metadata, op, -1L, 0x0, &sel, EINVAL);
+
+	/* Invalid selector */
+	prctl_invalid(_metadata, op, 0x0, 0x1, (void *) -1, EFAULT);
+
+	/*
+	 * Dispatcher range overflows unsigned long
+	 */
+	prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, 1, -1L, &sel, EINVAL);
+
+	/*
+	 * Allowed range overflows usigned long
+	 */
+	prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, -1L, 0x1, &sel, EINVAL);
+
+	/* 0 len should fail for PR_SYS_DISPATCH_INCLUSIVE_ON */
+	prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 1, 0, 0, EINVAL);
+
+	/* Range wrap-around should fail */
+	prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, -1L, 2, 0, EINVAL);
+
+	/* Normal range shouldn't fail */
+	prctl_valid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 2, 3, 0);
+
+	/* Invalid selector */
+	prctl_invalid(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, 2, 3, (void *) -1, EFAULT);
+}
+
+/*
+ * Use global selector for handle_sigsys tests, to avoid passing
+ * selector to signal handler
+ */
+char glob_sel;
+int nr_syscalls_emulated;
+int si_code;
+int si_errno;
+unsigned long syscall_addr;
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+	si_code = info->si_code;
+	si_errno = info->si_errno;
+	syscall_addr = (unsigned long)info->si_call_addr;
+
+	if (info->si_syscall == MAGIC_SYSCALL_1)
+		nr_syscalls_emulated++;
+
+	/* In preparation for sigreturn. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	/*
+	 * The tests for argument handling assume that `syscall(x) == x`. This
+	 * is a NOP on x86 because the syscall number is passed in %rax, which
+	 * happens to also be the function ABI return register.  Other
+	 * architectures may need to swizzle the arguments around.
+	 */
+#if defined(__riscv)
+/* REG_A7 is not defined in libc headers */
+# define REG_A7 (REG_A0 + 7)
+
+	((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] =
+			((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7];
+#endif
+}
+
+int setup_sigsys_handler(void)
+{
+	struct sigaction act;
+	sigset_t mask;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+	return sigaction(SIGSYS, &act, NULL);
+}
+
+TEST(dispatch_and_return)
+{
+	long ret;
+
+	glob_sel = 0;
+	nr_syscalls_emulated = 0;
+	si_code = 0;
+	si_errno = 0;
+
+	ASSERT_EQ(0, setup_sigsys_handler());
+
+	/* Make sure selector is good prior to prctl. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &glob_sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	/* MAGIC_SYSCALL_1 doesn't exist. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+	ret = syscall(MAGIC_SYSCALL_1);
+	EXPECT_EQ(-1, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+
+	/* MAGIC_SYSCALL_1 should be emulated. */
+	nr_syscalls_emulated = 0;
+	SYSCALL_DISPATCH_ON(glob_sel);
+
+	ret = syscall(MAGIC_SYSCALL_1);
+	EXPECT_EQ(MAGIC_SYSCALL_1, ret) {
+		TH_LOG("Failed to intercept syscall");
+	}
+	EXPECT_EQ(1, nr_syscalls_emulated) {
+		TH_LOG("Failed to emulate syscall");
+	}
+	ASSERT_EQ(SYS_USER_DISPATCH, si_code) {
+		TH_LOG("Bad si_code in SIGSYS");
+	}
+	ASSERT_EQ(0, si_errno) {
+		TH_LOG("Bad si_errno in SIGSYS");
+	}
+}
+
+TEST_SIGNAL(bad_selector, SIGSYS)
+{
+	long ret;
+	struct sigaction act;
+	sigset_t mask;
+	struct sysinfo info;
+
+	glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+	nr_syscalls_emulated = 0;
+	si_code = 0;
+	si_errno = 0;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&mask);
+
+	act.sa_sigaction = handle_sigsys;
+	act.sa_flags = SA_SIGINFO;
+	act.sa_mask = mask;
+
+	ret = sigaction(SIGSYS, &act, NULL);
+	ASSERT_EQ(0, ret);
+
+	/* Make sure selector is good prior to prctl. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &glob_sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	glob_sel = -1;
+
+	sysinfo(&info);
+
+	/* Even though it is ready to catch SIGSYS, the signal is
+	 * supposed to be uncatchable.
+	 */
+
+	EXPECT_FALSE(true) {
+		TH_LOG("Unreachable!");
+	}
+}
+
+TEST(disable_dispatch)
+{
+	int ret;
+	struct sysinfo info;
+	char sel = 0;
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	/* MAGIC_SYSCALL_1 doesn't exist. */
+	SYSCALL_DISPATCH_OFF(glob_sel);
+
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_OFF, 0, 0, 0);
+	EXPECT_EQ(0, ret) {
+		TH_LOG("Failed to unset syscall user dispatch");
+	}
+
+	/* Shouldn't have any effect... */
+	SYSCALL_DISPATCH_ON(glob_sel);
+
+	ret = syscall(__NR_sysinfo, &info);
+	EXPECT_EQ(0, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+}
+
+TEST(direct_dispatch_range)
+{
+	int ret = 0;
+	struct sysinfo info;
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
+
+	/*
+	 * Instead of calculating libc addresses; allow the entire
+	 * memory map and lock the selector.
+	 */
+	ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, -1L, &sel);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+	}
+
+	SYSCALL_DISPATCH_ON(sel);
+
+	ret = sysinfo(&info);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Dispatch triggered unexpectedly");
+	}
+}
+
+static void test_range(struct __test_metadata *_metadata,
+		       unsigned long op, unsigned long off,
+		       unsigned long size, bool dispatch)
+{
+	nr_syscalls_emulated = 0;
+	SYSCALL_DISPATCH_OFF(glob_sel);
+	EXPECT_EQ(0, prctl(PR_SET_SYSCALL_USER_DISPATCH, op, off, size, &glob_sel));
+	SYSCALL_DISPATCH_ON(glob_sel);
+	if (dispatch) {
+		EXPECT_EQ(syscall(MAGIC_SYSCALL_1), MAGIC_SYSCALL_1);
+		EXPECT_EQ(nr_syscalls_emulated, 1);
+	} else {
+		EXPECT_EQ(syscall(MAGIC_SYSCALL_1), -1);
+		EXPECT_EQ(nr_syscalls_emulated, 0);
+	}
+}
+
+TEST(dispatch_range)
+{
+	ASSERT_EQ(0, setup_sigsys_handler());
+	test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, 0, 0, true);
+	test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr, 1, false);
+	test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr-100, 200, false);
+	test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr+1, 100, true);
+	test_range(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, syscall_addr-100, 100, true);
+	test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr, 1, true);
+	test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr-1, 1, false);
+	test_range(_metadata, PR_SYS_DISPATCH_INCLUSIVE_ON, syscall_addr+1, 1, false);
+	SYSCALL_DISPATCH_OFF(glob_sel);
+}
+
+TEST_HARNESS_MAIN