MIPS: seccomp: Handle indirect system calls (o32)

When userland uses syscall() to perform an indirect system call
the actually system call that needs to be checked by the filter
is on the first argument. The kernel code needs to handle this case
by looking at the original syscall number in v0 and if it's
NR_syscall, then it needs to examine the first argument to
identify the real system call that will be executed.
Similarly, we need to 'virtually' shift the syscall() arguments
so the syscall_get_arguments() function can fetch the correct
arguments for the indirect system call.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Reviewed-by: James Hogan <james.hogan@imgtec.com>
Reviewed-by: Paul Burton <paul.burton@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/6404/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/include/asm/ptrace.h

@@ -82,7 +82,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 #define instruction_pointer(regs) ((regs)->cp0_epc)
 #define profile_pc(regs) instruction_pointer(regs)
 
-extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
+extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
 extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
 extern void die(const char *, struct pt_regs *) __noreturn;

arch/mips/include/asm/syscall.h

@@ -19,11 +19,22 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 #include <asm/ptrace.h>
+#include <asm/unistd.h>
+
+#ifndef __NR_syscall /* Only defined if _MIPS_SIM == _MIPS_SIM_ABI32 */
+#define __NR_syscall 4000
+#endif
 
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
-	return regs->regs[2];
+	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
+	if ((config_enabled(CONFIG_32BIT) ||
+	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
+	    (regs->regs[2] == __NR_syscall))
+		return regs->regs[4];
+	else
+		return regs->regs[2];
 }
 
 static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
@@ -91,6 +102,13 @@ static inline void syscall_get_arguments(struct task_struct *task,
 {
 	unsigned long arg;
 	int ret;
+	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
+	if ((config_enabled(CONFIG_32BIT) ||
+	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
+	    (regs->regs[2] == __NR_syscall)) {
+		i++;
+		n++;
+	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(&arg, task, regs, i++);

arch/mips/kernel/ptrace.c

@@ -662,9 +662,8 @@ long arch_ptrace(struct task_struct *child, long request,
  * Notification of system call entry/exit
  * - triggered by current->work.syscall_trace
  */
-asmlinkage long syscall_trace_enter(struct pt_regs *regs)
+asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 {
-	long syscall = regs->regs[2];
 	long ret = 0;
 	user_exit();
 

arch/mips/kernel/scall32-o32.S

@@ -118,7 +118,16 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	jal	syscall_trace_enter
+
+	/*
+	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 */
+	addiu	a1, v0,  __NR_O32_Linux
+	bnez	v0, 1f /* __NR_syscall at offset 0 */
+	lw	a1, PT_R4(sp)
+
+1:	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall
 

arch/mips/kernel/scall64-64.S

@@ -80,6 +80,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
+	daddiu	a1, v0, __NR_64_Linux
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall

arch/mips/kernel/scall64-n32.S

@@ -72,6 +72,7 @@ n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
+	daddiu	a1, v0, __NR_N32_Linux
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall

arch/mips/kernel/scall64-o32.S

@@ -112,7 +112,18 @@ trace_a_syscall:
 
 	move	s0, t2			# Save syscall pointer
 	move	a0, sp
-	jal	syscall_trace_enter
+	/*
+	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 * note: NR_syscall is the first O32 syscall but the macro is
+	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
+	 * therefore __NR_O32_Linux is used (4000)
+	 */
+	addiu	a1, v0,  __NR_O32_Linux
+	bnez	v0, 1f /* __NR_syscall at offset 0 */
+	lw	a1, PT_R4(sp)
+
+1:	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall