ptrace: add PTRACE_GET_SYSCALL_INFO request

PTRACE_GET_SYSCALL_INFO lets ptracer obtain details of the syscall the tracee is blocked in. The request succeeds when the tracee is in a syscall-enter-stop, syscall-exit-stop or PTRACE_EVENT_SECCOMP stop, and fails with -EINVAL otherwise.

There are two reasons for a special syscall-related ptrace request.

Firstly, with the current ptrace API there are cases when ptracer cannot retrieve necessary information about syscalls. Some examples include:
* The notorious int-0x80-from-64-bit-task issue. See [1] for details. In short, if a 64-bit task performs a syscall through int 0x80, its tracer has no reliable means to find out that the syscall was, in fact, a compat syscall, and misidentifies it.
* Syscall-enter-stop and syscall-exit-stop look the same for the tracer. Common practice is to keep track of the sequence of ptrace-stops in order not to mix the two syscall-stops up. But it is not as simple as it looks; for example, strace had a (just recently fixed) long-standing bug where attaching strace to a tracee that is performing the execve system call led to the tracer identifying the following syscall-exit-stop as syscall-enter-stop, which messed up all the state tracking.
* Since the introduction of commit 84d77d3f06e7e8dea057d10e8ec77ad71f721be3 ("ptrace: Don't allow accessing an undumpable mm"), both PTRACE_PEEKDATA and process_vm_readv become unavailable when the process dumpable flag is cleared. On such architectures as ia64 this results in all syscall arguments being unavailable.

Secondly, ptracers also have to support a lot of arch-specific code for obtaining information about the tracee. For some architectures, this requires a ptrace(PTRACE_PEEKUSER, ...) invocation for every syscall argument and return value.

PTRACE_GET_SYSCALL_INFO returns the following structure:

struct ptrace_syscall_info {
	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
	__u8 __pad0[3];
	__u32 arch;
	union {
		struct {
			__u64 nr;
			__u64 instruction_pointer;
			__u64 stack_pointer;
			__u64 frame_pointer;
			__u64 args[6];
		} entry;
		struct {
			__s64 rval;
			__u8 is_error;
			__u8 __pad1[7];
		} exit;
	};
};

The structure was chosen according to [2], except for the following changes:
* arch is returned unconditionally to aid with tracing system calls such as execve();
* the type of nr field was changed from int to __u64 because syscall numbers are, as a practical matter, 64 bits;
* stack_pointer and frame_pointer fields were added along with instruction_pointer field since they are readily available and can save the tracer from extra PTRACE_GETREGSET calls;
* a boolean is_error field was added along with rval field, this way the tracer can more reliably distinguish a return value
from an error value.

This changeset should be applied on top of [3] and [4].

[1] https://lore.kernel.org/lkml/CA+55aFzcSVmdDj9Lh_gdbz1OzHyEm6ZrGPBDAJnywm2LF_eVyg@mail.gmail.com/
[2] https://lore.kernel.org/lkml/CAObL_7GM0n80N7J_DFw_eQyfLyzq+sf4y2AvsCCV88Tb3AwEHA@mail.gmail.com/
[3] https://lore.kernel.org/lkml/[email protected]/
[4] https://lore.kernel.org/lkml/[email protected]/

v3: Split into three changes.
Change struct ptrace_syscall_info.
Support PTRACE_EVENT_SECCOMP by adding ptrace_event to task_struct. Add proper defines for ptrace_syscall_info.op values. Rename PT_SYSCALL_IS_ENTERING and PT_SYSCALL_IS_EXITING to PTRACE_EVENTMSG_SYSCALL_ENTRY and PTRACE_EVENTMSG_SYSCALL_EXIT and move them to uapi.

Elvira Khabirova (3):
ptrace: pass type of a syscall-stop in ptrace_message
ptrace: add PTRACE_GET_SYSCALL_INFO request
ptrace: add PTRACE_EVENT_SECCOMP support to PTRACE_GET_SYSCALL_INFO

 include/linux/ptrace.h      |  1 +
 include/linux/sched.h       |  1 +
 include/linux/tracehook.h   | 10 ++++---
 include/uapi/linux/ptrace.h | 34 ++++++++++++++++++++++++
 kernel/ptrace.c             | 53 +++++++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 3 deletions(-)

2.19.1

Define two constants, PTRACE_EVENTMSG_SYSCALL_ENTRY and PTRACE_EVENTMSG_SYSCALL_EXIT, and place them in ptrace_message for the duration of syscall-stops.
This way ptracers can distinguish syscall-enter-stops from syscall-exit-stops using PTRACE_GETEVENTMSG request.

---
 include/linux/tracehook.h   |  9 ++++++---
 include/uapi/linux/ptrace.h | 10 ++++++++++
 2 files changed, 16 insertions(+), 3 deletions(-)

index 40b0b4c1bf7b..633a83fe7051 100644
@@ -57,13 +57,15 @@ struct linux_binprm;
 /*
  * ptrace report for syscall entry and exit looks identical.
  */
-static inline int ptrace_report_syscall(struct pt_regs *regs)
+static inline int ptrace_report_syscall(struct pt_regs *regs,
+					unsigned long message)
 {
 	int ptrace = current->ptrace;
 
 	if (!(ptrace & PT_PTRACED))
 		return 0;
 
+	current->ptrace_message = message;
 	ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
 
 	/*

@@ -76,6 +78,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs)
 		current->exit_code = 0;
 	}
 
+	current->ptrace_message = 0;
 	return fatal_signal_pending(current);
 }
 

@@ -101,7 +104,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs)
 static inline __must_check int tracehook_report_syscall_entry(
 	struct pt_regs *regs)
 {
-	return ptrace_report_syscall(regs);
+	return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY);
 }
 
 /**

@@ -126,7 +129,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
 	if (step)
 		user_single_step_report(regs);
 	else
-		ptrace_report_syscall(regs);
+		ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT);
 }
 
 /**

index d5a1b8a492b9..cb138902d042 100644
@@ -104,6 +104,16 @@ struct seccomp_metadata {
 #define PTRACE_O_MASK		(\
 	0x000000ff | PTRACE_O_EXITKILL | PTRACE_O_SUSPEND_SECCOMP)
 
+/*
+ * These values are stored in task->ptrace_message by tracehook_report_syscall_*
+ * to describe current syscall-stop.
+ *
+ * Values for these constants are chosen so that they do not appear
+ * in task->ptrace_message by other means.
+ */
+#define PTRACE_EVENTMSG_SYSCALL_ENTRY	0x80000000U
+#define PTRACE_EVENTMSG_SYSCALL_EXIT	0x90000000U
+
 #include <asm/ptrace.h>
 
 

2.19.1

PTRACE_GET_SYSCALL_INFO lets ptracer obtain details of the syscall the tracee is blocked in. The request succeeds when the tracee is in a syscall-enter-stop or syscall-exit-stop, and fails with -EINVAL otherwise. A subsequent change may extend PTRACE_GET_SYSCALL_INFO for the case of PTRACE_EVENT_SECCOMP stop.

There are two reasons for a special syscall-related ptrace request.

Firstly, with the current ptrace API there are cases when ptracer cannot retrieve necessary information about syscalls. Some examples include:
* The notorious int-0x80-from-64-bit-task issue. See [1] for details. In short, if a 64-bit task performs a syscall through int 0x80, its tracer has no reliable means to find out that the syscall was, in fact, a compat syscall, and misidentifies it.
* Syscall-enter-stop and syscall-exit-stop look the same for the tracer. Common practice is to keep track of the sequence of ptrace-stops in order not to mix the two syscall-stops up. But it is not as simple as it looks; for example, strace had a (just recently fixed) long-standing bug where attaching strace to a tracee that is performing the execve system call led to the tracer identifying the following syscall-exit-stop as syscall-enter-stop, which messed up all the state tracking.
* Since the introduction of commit 84d77d3f06e7e8dea057d10e8ec77ad71f721be3 ("ptrace: Don't allow accessing an undumpable mm"), both PTRACE_PEEKDATA and process_vm_readv become unavailable when the process dumpable flag is cleared. On such architectures as ia64 this results in all syscall arguments being unavailable.

Secondly, ptracers also have to support a lot of arch-specific code for obtaining information about the tracee. For some architectures, this requires a ptrace(PTRACE_PEEKUSER, ...) invocation for every syscall argument and return value.

ptrace(2) man page:

long ptrace(enum __ptrace_request request, pid_t pid,

            void *addr, void *data);

...
PTRACE_GET_SYSCALL_INFO
Retrieve information about the syscall that caused the stop. The information is placed into the buffer pointed by "data" argument, which should be a pointer to a buffer of type "struct ptrace_syscall_info".
The "addr" argument contains the size of the buffer pointed to by "data" (i.e., sizeof(struct ptrace_syscall_info)). The return value contains the number of bytes available to be written by the kernel.
If the size of data to be written by the kernel exceeds the size specified by "addr" argument, the output is truncated. This operation fails with EINVAL if the tracee is not in a syscall-enter-stop, a syscall-exit-stop, or
a PTRACE_EVENT_SECCOMP stop.

---
 include/uapi/linux/ptrace.h | 24 ++++++++++++++++++
 kernel/ptrace.c             | 50 +++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

index cb138902d042..49b0b1b41943 100644
@@ -73,6 +73,30 @@ struct seccomp_metadata {
 	__u64 flags;		/* Output: filter's flags */
 };
 
+#define PTRACE_GET_SYSCALL_INFO		0x420f
+#define PTRACE_SYSCALL_INFO_ENTRY	0
+#define PTRACE_SYSCALL_INFO_EXIT	1
+
+struct ptrace_syscall_info {
+	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
+	__u8 __pad0[3];
+	__u32 arch;
+	union {
+		struct {
+			__u64 nr;
+			__u64 instruction_pointer;
+			__u64 stack_pointer;
+			__u64 frame_pointer;
+			__u64 args[6];
+		} entry;
+		struct {
+			__s64 rval;
+			__u8 is_error;
+			__u8 __pad1[7];
+		} exit;
+	};
+};
+
 /* Read signals from a shared (process wide) queue */
 #define PTRACE_PEEKSIGINFO_SHARED	(1 << 0)
 

2.19.1

Extend PTRACE_GET_SYSCALL_INFO to support PTRACE_EVENT_SECCOMP stops. The information returned is the same as for syscall-enter-stops.

---
 include/linux/ptrace.h    | 1 +
 include/linux/sched.h     | 1 +
 include/linux/tracehook.h | 1 +
 kernel/ptrace.c           | 7 +++++--
 4 files changed, 8 insertions(+), 2 deletions(-)

index 6c2ffed907f5..a993d0fde865 100644
@@ -166,6 +166,7 @@ static inline void ptrace_event(int event, unsigned long message)
 {
 	if (unlikely(ptrace_event_enabled(current, event))) {
 		current->ptrace_message = message;
+		current->ptrace_event = event;
 		ptrace_notify((event << 8) | SIGTRAP);
 	} else if (event == PTRACE_EVENT_EXEC) {
 		/* legacy EXEC report via SIGTRAP */

index a51c13c2b1a0..86215fb654d6 100644
@@ -964,6 +964,7 @@ struct task_struct {
 
 	/* Ptrace state: */
 	unsigned long			ptrace_message;
+	int				ptrace_event;
 	kernel_siginfo_t		*last_siginfo;
 
 	struct task_io_accounting	ioac;

index 633a83fe7051..5d2e5aa07a5c 100644
@@ -66,6 +66,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs,
 		return 0;
 
 	current->ptrace_message = message;
+	current->ptrace_event = 0;
 	ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
 
 	/*

index 92c47cd5ad84..74a37e74c7f1 100644
@@ -904,7 +904,9 @@ static int ptrace_get_syscall(struct task_struct *child,
 	unsigned long actual_size;
 	unsigned long write_size;
 
-	if (child->ptrace_message == PTRACE_EVENTMSG_SYSCALL_ENTRY) {
+	if ((child->ptrace_event == 0 &&
+	     child->ptrace_message == PTRACE_EVENTMSG_SYSCALL_ENTRY) ||
+	    child->ptrace_event == PTRACE_EVENT_SECCOMP) {
 		int i;
 
 		info.op = PTRACE_SYSCALL_INFO_ENTRY;

@@ -917,7 +919,8 @@ static int ptrace_get_syscall(struct task_struct *child,
 		for (i = 0; i < ARRAY_SIZE(args); i++)
 			info.entry.args[i] = args[i];
 		actual_size = offsetofend(struct ptrace_syscall_info, entry);
-	} else if (child->ptrace_message == PTRACE_EVENTMSG_SYSCALL_EXIT) {
+	} else if (child->ptrace_event == 0 &&
+		   child->ptrace_message == PTRACE_EVENTMSG_SYSCALL_EXIT) {
 		info.op = PTRACE_SYSCALL_INFO_EXIT;
 		info.arch = syscall_get_arch(child);
 		info.exit.rval = syscall_get_error(child, regs);

2.19.1