ptrace: introduce PTRACE_SET_SYSCALL_INFO request

PTRACE_SET_SYSCALL_INFO is a generic ptrace API that complements
PTRACE_GET_SYSCALL_INFO by letting the ptracer modify details of system
calls the tracee is blocked in.

This API allows ptracers to obtain and modify system call details in a
straightforward and architecture-agnostic way, providing a consistent way
of manipulating the system call number and arguments across architectures.

As in case of PTRACE_GET_SYSCALL_INFO, PTRACE_SET_SYSCALL_INFO also does
not aim to address numerous architecture-specific system call ABI
peculiarities, like differences in the number of system call arguments for
such system calls as pread64 and preadv.

The current implementation supports changing only those bits of system
call information that are used by strace system call tampering, namely,
syscall number, syscall arguments, and syscall return value.

Support of changing additional details returned by
PTRACE_GET_SYSCALL_INFO, such as instruction pointer and stack pointer,
could be added later if needed, by using struct ptrace_syscall_info.flags
to specify the additional details that should be set. Currently, "flags"
and "reserved" fields of struct ptrace_syscall_info must be initialized
with zeroes; "arch", "instruction_pointer", and "stack_pointer" fields are
currently ignored.

PTRACE_SET_SYSCALL_INFO currently supports only PTRACE_SYSCALL_INFO_ENTRY,
PTRACE_SYSCALL_INFO_EXIT, and PTRACE_SYSCALL_INFO_SECCOMP operations.
Other operations could be added later if needed.

Ideally, PTRACE_SET_SYSCALL_INFO should have been introduced along with
PTRACE_GET_SYSCALL_INFO, but it didn't happen. The last straw that
convinced me to implement PTRACE_SET_SYSCALL_INFO was apparent failure to
provide an API of changing the first system call argument on riscv
architecture.

ptrace(2) man page:

long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data);
...
PTRACE_SET_SYSCALL_INFO
Modify information about the system call that caused the stop.
The "data" argument is a pointer to struct ptrace_syscall_info
that specifies the system call information to be set.
The "addr" argument should be set to sizeof(struct ptrace_syscall_info)).

Link: https://lore.kernel.org/all/[e-mail]/
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Dmitry V. Levin <[e-mail]>
Reviewed-by: Alexey Gladkov <[e-mail]>
Reviewed-by: Charlie Jenkins <[e-mail]>
Tested-by: Charlie Jenkins <[e-mail]>
Reviewed-by: Eugene Syromiatnikov <[e-mail]>
Reviewed-by: Oleg Nesterov <[e-mail]>
Cc: Alexander Gordeev <[e-mail]>
Cc: Andreas Larsson <[e-mail]>
Cc: anton ivanov <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: Borislav Betkov <[e-mail]>
Cc: Brian Cain <[e-mail]>
Cc: Christian Borntraeger <[e-mail]>
Cc: Christian Zankel <[e-mail]>
Cc: Christophe Leroy <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Davide Berardi <[e-mail]>
Cc: David S. Miller <[e-mail]>
Cc: Dinh Nguyen <[e-mail]>
Cc: Eugene Syromyatnikov <[e-mail]>
Cc: Geert Uytterhoeven <[e-mail]>
Cc: Guo Ren <[e-mail]>
Cc: Heiko Carstens <[e-mail]>
Cc: Helge Deller <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: Huacai Chen <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Johannes Berg <[e-mail]>
Cc: John Paul Adrian Glaubitz <[e-mail]>
Cc: Jonas Bonn <[e-mail]>
Cc: Maciej W. Rozycki <[e-mail]>
Cc: Madhavan Srinivasan <[e-mail]>
Cc: Max Filippov <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Michal Simek <[e-mail]>
Cc: Mike Frysinger <[e-mail]>
Cc: Naveen N Rao <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Renzo Davoi <[e-mail]>
Cc: Richard Weinberger <[e-mail]>
Cc: Rich Felker <[e-mail]>
Cc: Russel King <[e-mail]>
Cc: Shuah Khan <[e-mail]>
Cc: Stafford Horne <[e-mail]>
Cc: Stefan Kristiansson <[e-mail]>
Cc: Sven Schnelle <[e-mail]>
Cc: Thomas Gleinxer <[e-mail]>
Cc: Vasily Gorbik <[e-mail]>
Cc: Vineet Gupta <[e-mail]>
Cc: WANG Xuerui <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Yoshinori Sato <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

include/uapi/linux/ptrace.h

···
 };
 
 #define PTRACE_GET_SYSCALL_INFO		0x420e
+#define PTRACE_SET_SYSCALL_INFO		0x4212
 #define PTRACE_SYSCALL_INFO_NONE	0
 #define PTRACE_SYSCALL_INFO_ENTRY	1
 #define PTRACE_SYSCALL_INFO_EXIT	2
···
 
 struct ptrace_syscall_info {
 	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
-	__u8 pad[3];
+	__u8 reserved;
+	__u16 flags;
 	__u32 arch;
 	__u64 instruction_pointer;
 	__u64 stack_pointer;
···
 			__u64 nr;
 			__u64 args[6];
 			__u32 ret_data;
+			__u32 reserved2;
 		} seccomp;
 	};
 };
···
 	__u64 offset;
 	__u64 len;
 };
+
+/* 0x4212 is PTRACE_SET_SYSCALL_INFO */
 
 /*
  * These values are stored in task->ptrace_message

kernel/ptrace.c

···
 	ptrace_get_syscall_info_entry(child, regs, info);
 	info->seccomp.ret_data = child->ptrace_message;
 
-	/* ret_data is the last field in struct ptrace_syscall_info.seccomp */
+	/*
+	 * ret_data is the last non-reserved field
+	 * in struct ptrace_syscall_info.seccomp
+	 */
 	return offsetofend(struct ptrace_syscall_info, seccomp.ret_data);
 }
 
···
 
 	write_size = min(actual_size, user_size);
 	return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size;
+}
+
+static int
+ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
+			      struct ptrace_syscall_info *info)
+{
+	unsigned long args[ARRAY_SIZE(info->entry.args)];
+	int nr = info->entry.nr;
+	int i;
+
+	/*
+	 * Check that the syscall number specified in info->entry.nr
+	 * is either a value of type "int" or a sign-extended value
+	 * of type "int".
+	 */
+	if (nr != info->entry.nr)
+		return -ERANGE;
+
+	for (i = 0; i < ARRAY_SIZE(args); i++) {
+		args[i] = info->entry.args[i];
+		/*
+		 * Check that the syscall argument specified in
+		 * info->entry.args[i] is either a value of type
+		 * "unsigned long" or a sign-extended value of type "long".
+		 */
+		if (args[i] != info->entry.args[i])
+			return -ERANGE;
+	}
+
+	syscall_set_nr(child, regs, nr);
+	/*
+	 * If the syscall number is set to -1, setting syscall arguments is not
+	 * just pointless, it would also clobber the syscall return value on
+	 * those architectures that share the same register both for the first
+	 * argument of syscall and its return value.
+	 */
+	if (nr != -1)
+		syscall_set_arguments(child, regs, args);
+
+	return 0;
+}
+
+static int
+ptrace_set_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs,
+				struct ptrace_syscall_info *info)
+{
+	/*
+	 * info->entry is currently a subset of info->seccomp,
+	 * info->seccomp.ret_data is currently ignored.
+	 */
+	return ptrace_set_syscall_info_entry(child, regs, info);
+}
+
+static int
+ptrace_set_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
+			     struct ptrace_syscall_info *info)
+{
+	long rval = info->exit.rval;
+
+	/*
+	 * Check that the return value specified in info->exit.rval
+	 * is either a value of type "long" or a sign-extended value
+	 * of type "long".
+	 */
+	if (rval != info->exit.rval)
+		return -ERANGE;
+
+	if (info->exit.is_error)
+		syscall_set_return_value(child, regs, rval, 0);
+	else
+		syscall_set_return_value(child, regs, 0, rval);
+
+	return 0;
+}
+
+static int
+ptrace_set_syscall_info(struct task_struct *child, unsigned long user_size,
+			const void __user *datavp)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	struct ptrace_syscall_info info;
+
+	if (user_size < sizeof(info))
+		return -EINVAL;
+
+	/*
+	 * The compatibility is tracked by info.op and info.flags: if user-space
+	 * does not instruct us to use unknown extra bits from future versions
+	 * of ptrace_syscall_info, we are not going to read them either.
+	 */
+	if (copy_from_user(&info, datavp, sizeof(info)))
+		return -EFAULT;
+
+	/* Reserved for future use. */
+	if (info.flags || info.reserved)
+		return -EINVAL;
+
+	/* Changing the type of the system call stop is not supported yet. */
+	if (ptrace_get_syscall_info_op(child) != info.op)
+		return -EINVAL;
+
+	switch (info.op) {
+	case PTRACE_SYSCALL_INFO_ENTRY:
+		return ptrace_set_syscall_info_entry(child, regs, &info);
+	case PTRACE_SYSCALL_INFO_EXIT:
+		return ptrace_set_syscall_info_exit(child, regs, &info);
+	case PTRACE_SYSCALL_INFO_SECCOMP:
+		return ptrace_set_syscall_info_seccomp(child, regs, &info);
+	default:
+		/* Other types of system call stops are not supported yet. */
+		return -EINVAL;
+	}
 }
 #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
···
 
 	case PTRACE_GET_SYSCALL_INFO:
 		ret = ptrace_get_syscall_info(child, addr, datavp);
+		break;
+
+	case PTRACE_SET_SYSCALL_INFO:
+		ret = ptrace_set_syscall_info(child, addr, datavp);
 		break;
 #endif