[RFC PATCH v5 1/2] selftests/x86: sysret_rip: Handle syscall in a FRED system

[Ammar Faizi]

From: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>

The current selftest asserts (%r11 == %rflags) after the 'syscall'
returns to user. Such an assertion doesn't apply to the FRED system
because in that system the 'syscall' instruction does not set
%r11=%rflags and %rcx=%rip.

Handle the FRED case. Now, test that:

  - "syscall" in a FRED system doesn't clobber %rcx and %r11.
  - "syscall" in a non-FRED system sets %rcx=%rip and %r11=%rflags.

The 'raise()' function from libc can't be used to control those
registers. Therefore, create a syscall wrapper in inline Assembly to
fully control them.

Fixes: 660602140103 ("selftests/x86: Add a selftest for SYSRET to noncanonical addresses")
Link: https://lore.kernel.org/lkml/25b96960-a07e-a952-5c23-786b55054126@xxxxxxxxx
Reported-by: Xin Li <xin3.li@xxxxxxxxx>
Co-developed-by: H. Peter Anvin (Intel) <hpa@xxxxxxxxx>
Signed-off-by: H. Peter Anvin (Intel) <hpa@xxxxxxxxx>
Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>
---
 tools/testing/selftests/x86/sysret_rip.c | 126 +++++++++++++++++++++--
 1 file changed, 119 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c
index 84d74be1d90207ab..d3dc5ec496854179 100644
--- a/tools/testing/selftests/x86/sysret_rip.c
+++ b/tools/testing/selftests/x86/sysret_rip.c
@@ -39,6 +39,112 @@ asm (
 extern const char test_page[];
 static void const *current_test_page_addr = test_page;
 
+/* Arbitrary values */
+static const unsigned long r11_sentinel = 0xfeedfacedeadbeef;
+static const unsigned long rcx_sentinel = 0x5ca1ab1e0b57ac1e;
+
+/* An arbitrary *valid* RFLAGS value */
+static const unsigned long rflags_sentinel = 0x200a93;
+
+enum regs_ok {
+	REGS_UNDEFINED	= -2,	/* For consistency checker init, never returned */
+	REGS_ERROR	= -1,	/* Invalid register contents */
+	REGS_SAVED	=  0,	/* Registers properly preserved */
+	REGS_SYSRET	=  1	/* Registers match syscall/sysret */
+};
+
+/*
+ * Returns:
+ *  0 = %rcx and %r11 preserved.
+ *  1 = %rcx and %r11 set to %rflags and %rip.
+ * -1 = %rcx and/or %r11 set to any other values.
+ *
+ * @rbx should be set to the syscall return %rip.
+ */
+static enum regs_ok check_regs_result(unsigned long r11, unsigned long rcx,
+				      unsigned long rbx)
+{
+	if (r11 == r11_sentinel && rcx == rcx_sentinel)
+		return REGS_SAVED;
+
+	if (r11 == rflags_sentinel && rcx == rbx)
+		return REGS_SYSRET;
+
+	printf("[FAIL] check_regs_result\n");
+	printf("        r11_sentinel = %#lx; %%r11 = %#lx;\n", r11_sentinel, r11);
+	printf("        rcx_sentinel = %#lx; %%rcx = %#lx;\n", rcx_sentinel, rcx);
+	printf("        rflags_sentinel = %#lx\n", rflags_sentinel);
+	return REGS_ERROR;
+}
+
+static long do_syscall(long nr_syscall, unsigned long arg1, unsigned long arg2,
+		       unsigned long arg3, unsigned long arg4,
+		       unsigned long arg5, unsigned long arg6)
+{
+	static enum regs_ok regs_ok_state = REGS_UNDEFINED;
+	register unsigned long r11 asm("%r11");
+	register unsigned long r10 asm("%r10");
+	register unsigned long r8 asm("%r8");
+	register unsigned long r9 asm("%r9");
+	register void *rsp asm("%rsp");
+	unsigned long rcx, rbx;
+	enum regs_ok ret;
+
+	r11 = r11_sentinel;
+	rcx = rcx_sentinel;
+	r10 = arg4;
+	r8 = arg5;
+	r9 = arg6;
+
+	asm volatile (
+		"pushq	%[rflags_sentinel]\n\t"
+		"popf\n\t"
+		"leaq	1f(%%rip), %[rbx]\n\t"
+		"syscall\n"
+		"1:"
+
+		: "+a" (nr_syscall),
+		  "+r" (r11),
+		  "+c" (rcx),
+		  [rbx] "=b" (rbx),
+		  "+r" (rsp)	/* Clobber the redzone */
+
+		: [rflags_sentinel] "g" (rflags_sentinel),
+		  "D" (arg1),	/* %rdi */
+		  "S" (arg2),	/* %rsi */
+		  "d" (arg3),	/* %rdx */
+		  "r" (r10),
+		  "r" (r8),
+		  "r" (r9)
+
+		: "memory"
+	);
+
+	/*
+	 * Test that:
+	 *
+	 * - "syscall" in a FRED system doesn't clobber %rcx and %r11.
+	 * - "syscall" in a non-FRED system sets %rcx=%rip and %r11=%rflags.
+	 */
+	ret = check_regs_result(r11, rcx, rbx);
+	assert(ret != REGS_ERROR);
+
+	/*
+	 * Test that we don't get a mix of REGS_SAVED and REGS_SYSRET.
+	 * It needs at least calling do_syscall() twice to assert.
+	 */
+	if (regs_ok_state == REGS_UNDEFINED) {
+		/*
+		 * First time calling do_syscall().
+		 */
+		regs_ok_state = ret;
+	} else {
+		assert(regs_ok_state == ret);
+	}
+
+	return nr_syscall;
+}
+
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		       int flags)
 {
@@ -85,27 +191,33 @@ static void sigsegv_for_sigreturn_test(int sig, siginfo_t *info, void *ctx_void)
 static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
+	enum regs_ok ret;
 
 	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 
+	ret = check_regs_result(ctx->uc_mcontext.gregs[REG_R11],
+				ctx->uc_mcontext.gregs[REG_RCX],
+				ctx->uc_mcontext.gregs[REG_RBX]);
+
+	assert(ret != REGS_ERROR);
+
 	/* Set IP and CX to match so that SYSRET can happen. */
 	ctx->uc_mcontext.gregs[REG_RIP] = rip;
 	ctx->uc_mcontext.gregs[REG_RCX] = rip;
-
-	/* R11 and EFLAGS should already match. */
-	assert(ctx->uc_mcontext.gregs[REG_EFL] ==
-	       ctx->uc_mcontext.gregs[REG_R11]);
-
 	sethandler(SIGSEGV, sigsegv_for_sigreturn_test, SA_RESETHAND);
 
-	return;
+}
+
+static void __raise(int sig)
+{
+	do_syscall(__NR_kill, getpid(), sig, 0, 0, 0, 0);
 }
 
 static void test_sigreturn_to(unsigned long ip)
 {
 	rip = ip;
 	printf("[RUN]\tsigreturn to 0x%lx\n", ip);
-	raise(SIGUSR1);
+	__raise(SIGUSR1);
 }
 
 static jmp_buf jmpbuf;
-- 
Ammar Faizi