x86/entry, selftests/x86: Add a test for 32-bit fast syscall arg faults

This test passes on 4.0 and fails on some newer kernels.
Fortunately, the failure is likely not a big deal.

This test will make sure that we don't break it further (e.g. OOPSing)
as we clean up the entry code and that we eventually fix the
regression.

There's arguably no need to preserve the old ABI here --
anything that makes it into a fast (vDSO) syscall with a bad
stack is about to crash no matter what we do.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/9cfcc51005168cb1b06b31991931214d770fc59a.1435952415.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 131 insertions, 1 deletions

diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index caa60d5..e8df47e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,7 +5,7 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
-TARGETS_C_32BIT_ONLY := entry_from_vm86
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
new file mode 100644
index 0000000..7db4fc9
--- /dev/null
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -0,0 +1,130 @@
+/*
+ * syscall_arg_fault.c - tests faults 32-bit fast syscall stack args
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/signal.h>
+#include <sys/ucontext.h>
+#include <err.h>
+#include <setjmp.h>
+#include <errno.h>
+
+/* Our sigaltstack scratch space. */
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static volatile sig_atomic_t sig_traps;
+static sigjmp_buf jmpbuf;
+
+static volatile sig_atomic_t n_errs;
+
+static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (ctx->uc_mcontext.gregs[REG_EAX] != -EFAULT) {
+		printf("[FAIL]\tAX had the wrong value: 0x%x\n",
+		       ctx->uc_mcontext.gregs[REG_EAX]);
+		n_errs++;
+	} else {
+		printf("[OK]\tSeems okay\n");
+	}
+
+	siglongjmp(jmpbuf, 1);
+}
+
+static void sigill(int sig, siginfo_t *info, void *ctx_void)
+{
+	printf("[SKIP]\tIllegal instruction\n");
+	siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+	stack_t stack = {
+		.ss_sp = altstack_data,
+		.ss_size = SIGSTKSZ,
+	};
+	if (sigaltstack(&stack, NULL) != 0)
+		err(1, "sigaltstack");
+
+	sethandler(SIGSEGV, sigsegv, SA_ONSTACK);
+	sethandler(SIGILL, sigill, SA_ONSTACK);
+
+	/*
+	 * Exercise another nasty special case.  The 32-bit SYSCALL
+	 * and SYSENTER instructions (even in compat mode) each
+	 * clobber one register.  A Linux system call has a syscall
+	 * number and six arguments, and the user stack pointer
+	 * needs to live in some register on return.  That means
+	 * that we need eight registers, but SYSCALL and SYSENTER
+	 * only preserve seven registers.  As a result, one argument
+	 * ends up on the stack.  The stack is user memory, which
+	 * means that the kernel can fail to read it.
+	 *
+	 * The 32-bit fast system calls don't have a defined ABI:
+	 * we're supposed to invoke them through the vDSO.  So we'll
+	 * fudge it: we set all regs to invalid pointer values and
+	 * invoke the entry instruction.  The return will fail no
+	 * matter what, and we completely lose our program state,
+	 * but we can fix it up with a signal handler.
+	 */
+
+	printf("[RUN]\tSYSENTER with invalid state\n");
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile (
+			"movl $-1, %%eax\n\t"
+			"movl $-1, %%ebx\n\t"
+			"movl $-1, %%ecx\n\t"
+			"movl $-1, %%edx\n\t"
+			"movl $-1, %%esi\n\t"
+			"movl $-1, %%edi\n\t"
+			"movl $-1, %%ebp\n\t"
+			"movl $-1, %%esp\n\t"
+			"sysenter"
+			: : : "memory", "flags");
+	}
+
+	printf("[RUN]\tSYSCALL with invalid state\n");
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile (
+			"movl $-1, %%eax\n\t"
+			"movl $-1, %%ebx\n\t"
+			"movl $-1, %%ecx\n\t"
+			"movl $-1, %%edx\n\t"
+			"movl $-1, %%esi\n\t"
+			"movl $-1, %%edi\n\t"
+			"movl $-1, %%ebp\n\t"
+			"movl $-1, %%esp\n\t"
+			"syscall\n\t"
+			"pushl $0"	/* make sure we segfault cleanly */
+			: : : "memory", "flags");
+	}
+
+	return 0;
+}