[PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[Dmitry V. Levin]

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.

Current implementation supports changing only those bits of system call
information that are used by strace, 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 re-using struct ptrace_syscall_info.reserved to specify
the additional details that should be set.  Currently, the reserved
field of struct ptrace_syscall_info must be initialized with zeroes;
arch, instruction_pointer, and stack_pointer fields are 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/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/
Signed-off-by: Dmitry V. Levin <ldv@strace.io>
---
 include/linux/ptrace.h      |   3 ++
 include/uapi/linux/ptrace.h |   3 +-
 kernel/ptrace.c             | 102 ++++++++++++++++++++++++++++++++++++
 3 files changed, 107 insertions(+), 1 deletion(-)

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 90507d4afcd6..c8dbf1e498bf 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -17,6 +17,9 @@ struct syscall_info {
 	struct seccomp_data	data;
 };
 
+/* sizeof() the first published struct ptrace_syscall_info */
+#define PTRACE_SYSCALL_INFO_SIZE_VER0	84
+
 extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 			    void *buf, int len, unsigned int gup_flags);
 
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index 72c038fc71d0..231b8bf7eeff 100644
--- a/include/uapi/linux/ptrace.h
+++ b/include/uapi/linux/ptrace.h
@@ -74,6 +74,7 @@ struct seccomp_metadata {
 };
 
 #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
@@ -81,7 +82,7 @@ struct seccomp_metadata {
 
 struct ptrace_syscall_info {
 	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
-	__u8 pad[3];
+	__u8 reserved[3];
 	__u32 arch;
 	__u64 instruction_pointer;
 	__u64 stack_pointer;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index e7e0003cc8e0..52377653743d 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -1018,6 +1018,104 @@ ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size,
 	write_size = min(actual_size, user_size);
 	return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size;
 }
+
+static unsigned long
+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;
+
+	if (nr != info->entry.nr)
+		return -ERANGE;
+
+	for (i = 0; i < ARRAY_SIZE(args); i++) {
+		args[i] = info->entry.args[i];
+		if (args[i] != info->entry.args[i])
+			return -ERANGE;
+	}
+
+	syscall_set_nr(child, regs, nr);
+	syscall_set_arguments(child, regs, args);
+	if (nr == -1) {
+		/*
+		 * When the syscall number is set to -1, the syscall will be
+		 * skipped.  In this case also set the syscall return value to
+		 * -ENOSYS, otherwise on some architectures the corresponding
+		 * struct pt_regs field will remain unchanged.
+		 *
+		 * Note that on some architectures syscall_set_return_value()
+		 * modifies one of the struct pt_regs fields also modified by
+		 * syscall_set_arguments(), so the former should be called
+		 * after the latter.
+		 */
+		syscall_set_return_value(child, regs, -ENOSYS, 0);
+	}
+
+	return 0;
+}
+
+static unsigned long
+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 unsigned long
+ptrace_set_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
+			     struct ptrace_syscall_info *info)
+{
+	if (info->exit.is_error)
+		syscall_set_return_value(child, regs, info->exit.rval, 0);
+	else
+		syscall_set_return_value(child, regs, 0, info->exit.rval);
+
+	return 0;
+}
+
+static int
+ptrace_set_syscall_info(struct task_struct *child, unsigned long user_size,
+			void __user *datavp)
+{
+	struct pt_regs *regs = task_pt_regs(child);
+	struct ptrace_syscall_info info;
+	int error;
+
+	BUILD_BUG_ON(sizeof(struct ptrace_syscall_info) < PTRACE_SYSCALL_INFO_SIZE_VER0);
+
+	if (user_size < PTRACE_SYSCALL_INFO_SIZE_VER0 || user_size > PAGE_SIZE)
+		return -EINVAL;
+
+	error = copy_struct_from_user(&info, sizeof(info), datavp, user_size);
+	if (error)
+		return error;
+
+	/* Reserved for future use. */
+	if (memchr_inv(info.reserved, 0, sizeof(info.reserved)))
+		return -EINVAL;
+
+	/* Changing the type of the system call stop is not supported. */
+	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. */
+		return -EINVAL;
+	}
+}
 #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
 int ptrace_request(struct task_struct *child, long request,
@@ -1236,6 +1334,10 @@ int ptrace_request(struct task_struct *child, long request,
 	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
 
 	case PTRACE_SECCOMP_GET_FILTER:

-- 
ldv

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[kernel test robot]

Hi Dmitry,

kernel test robot noticed the following build errors:

[auto build test ERROR on openrisc/for-next]
[also build test ERROR on powerpc/next powerpc/fixes s390/features uml/next jcmvbkbc-xtensa/xtensa-for-next arnd-asm-generic/master vgupta-arc/for-curr arm64/for-next/core linus/master uml/fixes tip/x86/core vgupta-arc/for-next v6.13-rc6 next-20250108]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Dmitry-V-Levin/Revert-arch-remove-unused-function-syscall_set_arguments/20250108-070658
base:   https://github.com/openrisc/linux.git for-next
patch link:    https://lore.kernel.org/r/20250107230456.GE30633%40strace.io
patch subject: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request
config: hexagon-allnoconfig (https://download.01.org/0day-ci/archive/20250109/202501090919.TiLTOhaq-lkp@intel.com/config)
compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project 096551537b2a747a3387726ca618ceeb3950e9bc)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250109/202501090919.TiLTOhaq-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501090919.TiLTOhaq-lkp@intel.com/

All errors (new ones prefixed by >>):

>> kernel/ptrace.c:1053:3: error: call to undeclared function 'syscall_set_return_value'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
    1053 |                 syscall_set_return_value(child, regs, -ENOSYS, 0);
         |                 ^
   kernel/ptrace.c:1053:3: note: did you mean 'syscall_get_return_value'?
   arch/hexagon/include/asm/syscall.h:56:20: note: 'syscall_get_return_value' declared here
      56 | static inline long syscall_get_return_value(struct task_struct *task,
         |                    ^
   kernel/ptrace.c:1075:3: error: call to undeclared function 'syscall_set_return_value'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
    1075 |                 syscall_set_return_value(child, regs, info->exit.rval, 0);
         |                 ^
   2 errors generated.


vim +/syscall_set_return_value +1053 kernel/ptrace.c

  1021	
  1022	static unsigned long
  1023	ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
  1024				      struct ptrace_syscall_info *info)
  1025	{
  1026		unsigned long args[ARRAY_SIZE(info->entry.args)];
  1027		int nr = info->entry.nr;
  1028		int i;
  1029	
  1030		if (nr != info->entry.nr)
  1031			return -ERANGE;
  1032	
  1033		for (i = 0; i < ARRAY_SIZE(args); i++) {
  1034			args[i] = info->entry.args[i];
  1035			if (args[i] != info->entry.args[i])
  1036				return -ERANGE;
  1037		}
  1038	
  1039		syscall_set_nr(child, regs, nr);
  1040		syscall_set_arguments(child, regs, args);
  1041		if (nr == -1) {
  1042			/*
  1043			 * When the syscall number is set to -1, the syscall will be
  1044			 * skipped.  In this case also set the syscall return value to
  1045			 * -ENOSYS, otherwise on some architectures the corresponding
  1046			 * struct pt_regs field will remain unchanged.
  1047			 *
  1048			 * Note that on some architectures syscall_set_return_value()
  1049			 * modifies one of the struct pt_regs fields also modified by
  1050			 * syscall_set_arguments(), so the former should be called
  1051			 * after the latter.
  1052			 */
> 1053			syscall_set_return_value(child, regs, -ENOSYS, 0);
  1054		}
  1055	
  1056		return 0;
  1057	}
  1058	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[kernel test robot]

Hi Dmitry,

kernel test robot noticed the following build errors:

[auto build test ERROR on openrisc/for-next]
[also build test ERROR on powerpc/next powerpc/fixes s390/features uml/next jcmvbkbc-xtensa/xtensa-for-next arnd-asm-generic/master vgupta-arc/for-curr arm64/for-next/core linus/master uml/fixes tip/x86/core vgupta-arc/for-next v6.13-rc6 next-20250108]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Dmitry-V-Levin/Revert-arch-remove-unused-function-syscall_set_arguments/20250108-070658
base:   https://github.com/openrisc/linux.git for-next
patch link:    https://lore.kernel.org/r/20250107230456.GE30633%40strace.io
patch subject: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request
config: hexagon-randconfig-001-20250109 (https://download.01.org/0day-ci/archive/20250109/202501090954.gYTxI9sY-lkp@intel.com/config)
compiler: clang version 14.0.6 (https://github.com/llvm/llvm-project f28c006a5895fc0e329fe15fead81e37457cb1d1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250109/202501090954.gYTxI9sY-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501090954.gYTxI9sY-lkp@intel.com/

All errors (new ones prefixed by >>):

>> kernel/ptrace.c:1053:3: error: implicit declaration of function 'syscall_set_return_value' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
                   syscall_set_return_value(child, regs, -ENOSYS, 0);
                   ^
   kernel/ptrace.c:1053:3: note: did you mean 'syscall_get_return_value'?
   arch/hexagon/include/asm/syscall.h:56:20: note: 'syscall_get_return_value' declared here
   static inline long syscall_get_return_value(struct task_struct *task,
                      ^
   kernel/ptrace.c:1075:3: error: implicit declaration of function 'syscall_set_return_value' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
                   syscall_set_return_value(child, regs, info->exit.rval, 0);
                   ^
   2 errors generated.


vim +/syscall_set_return_value +1053 kernel/ptrace.c

  1021	
  1022	static unsigned long
  1023	ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
  1024				      struct ptrace_syscall_info *info)
  1025	{
  1026		unsigned long args[ARRAY_SIZE(info->entry.args)];
  1027		int nr = info->entry.nr;
  1028		int i;
  1029	
  1030		if (nr != info->entry.nr)
  1031			return -ERANGE;
  1032	
  1033		for (i = 0; i < ARRAY_SIZE(args); i++) {
  1034			args[i] = info->entry.args[i];
  1035			if (args[i] != info->entry.args[i])
  1036				return -ERANGE;
  1037		}
  1038	
  1039		syscall_set_nr(child, regs, nr);
  1040		syscall_set_arguments(child, regs, args);
  1041		if (nr == -1) {
  1042			/*
  1043			 * When the syscall number is set to -1, the syscall will be
  1044			 * skipped.  In this case also set the syscall return value to
  1045			 * -ENOSYS, otherwise on some architectures the corresponding
  1046			 * struct pt_regs field will remain unchanged.
  1047			 *
  1048			 * Note that on some architectures syscall_set_return_value()
  1049			 * modifies one of the struct pt_regs fields also modified by
  1050			 * syscall_set_arguments(), so the former should be called
  1051			 * after the latter.
  1052			 */
> 1053			syscall_set_return_value(child, regs, -ENOSYS, 0);
  1054		}
  1055	
  1056		return 0;
  1057	}
  1058	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[kernel test robot]

Hi Dmitry,

kernel test robot noticed the following build warnings:

[auto build test WARNING on openrisc/for-next]
[also build test WARNING on powerpc/next powerpc/fixes s390/features uml/next jcmvbkbc-xtensa/xtensa-for-next arnd-asm-generic/master vgupta-arc/for-curr arm64/for-next/core linus/master uml/fixes tip/x86/core vgupta-arc/for-next v6.13-rc6 next-20250109]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Dmitry-V-Levin/Revert-arch-remove-unused-function-syscall_set_arguments/20250108-070658
base:   https://github.com/openrisc/linux.git for-next
patch link:    https://lore.kernel.org/r/20250107230456.GE30633%40strace.io
patch subject: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request
config: mips-randconfig-r122-20250109 (https://download.01.org/0day-ci/archive/20250109/202501092150.9BH2s9AO-lkp@intel.com/config)
compiler: mips64-linux-gcc (GCC) 14.2.0
reproduce: (https://download.01.org/0day-ci/archive/20250109/202501092150.9BH2s9AO-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202501092150.9BH2s9AO-lkp@intel.com/

sparse warnings: (new ones prefixed by >>)
   kernel/ptrace.c:55:22: sparse: sparse: incompatible types in comparison expression (different address spaces):
   kernel/ptrace.c:55:22: sparse:    struct task_struct *
   kernel/ptrace.c:55:22: sparse:    struct task_struct [noderef] __rcu *
   kernel/ptrace.c:74:23: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected struct task_struct [noderef] __rcu *parent @@     got struct task_struct *new_parent @@
   kernel/ptrace.c:74:23: sparse:     expected struct task_struct [noderef] __rcu *parent
   kernel/ptrace.c:74:23: sparse:     got struct task_struct *new_parent
   kernel/ptrace.c:75:29: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected struct cred const [noderef] __rcu *ptracer_cred @@     got struct cred const * @@
   kernel/ptrace.c:75:29: sparse:     expected struct cred const [noderef] __rcu *ptracer_cred
   kernel/ptrace.c:75:29: sparse:     got struct cred const *
   kernel/ptrace.c:129:18: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected struct cred const *old_cred @@     got struct cred const [noderef] __rcu *ptracer_cred @@
   kernel/ptrace.c:129:18: sparse:     expected struct cred const *old_cred
   kernel/ptrace.c:129:18: sparse:     got struct cred const [noderef] __rcu *ptracer_cred
   kernel/ptrace.c:133:25: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:133:25: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:133:25: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:160:27: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:160:27: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:160:27: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:192:28: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:192:28: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:192:28: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:198:30: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:198:30: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:198:30: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:251:44: sparse: sparse: incompatible types in comparison expression (different address spaces):
   kernel/ptrace.c:251:44: sparse:    struct task_struct [noderef] __rcu *
   kernel/ptrace.c:251:44: sparse:    struct task_struct *
   kernel/ptrace.c:494:54: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct task_struct *parent @@     got struct task_struct [noderef] __rcu *parent @@
   kernel/ptrace.c:494:54: sparse:     expected struct task_struct *parent
   kernel/ptrace.c:494:54: sparse:     got struct task_struct [noderef] __rcu *parent
   kernel/ptrace.c:502:53: sparse: sparse: incorrect type in argument 2 (different address spaces) @@     expected struct task_struct *new_parent @@     got struct task_struct [noderef] __rcu *real_parent @@
   kernel/ptrace.c:502:53: sparse:     expected struct task_struct *new_parent
   kernel/ptrace.c:502:53: sparse:     got struct task_struct [noderef] __rcu *real_parent
   kernel/ptrace.c:550:41: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct task_struct *p1 @@     got struct task_struct [noderef] __rcu *real_parent @@
   kernel/ptrace.c:550:41: sparse:     expected struct task_struct *p1
   kernel/ptrace.c:550:41: sparse:     got struct task_struct [noderef] __rcu *real_parent
   kernel/ptrace.c:552:50: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct sighand_struct *sigh @@     got struct sighand_struct [noderef] __rcu *sighand @@
   kernel/ptrace.c:552:50: sparse:     expected struct sighand_struct *sigh
   kernel/ptrace.c:552:50: sparse:     got struct sighand_struct [noderef] __rcu *sighand
   kernel/ptrace.c:743:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:743:37: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:743:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:751:39: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:751:39: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:751:39: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:862:29: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:862:29: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:862:29: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:866:31: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:866:31: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:866:31: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:1206:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:1206:37: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:1206:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:1208:39: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:1208:39: sparse:     expected struct spinlock [usertype] *lock
   kernel/ptrace.c:1208:39: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c: note: in included file (through include/linux/fwnode.h, include/linux/logic_pio.h, include/asm-generic/io.h, ...):
   include/linux/list.h:83:21: sparse: sparse: self-comparison always evaluates to true
   kernel/ptrace.c: note: in included file (through include/linux/rcuwait.h, include/linux/percpu-rwsem.h, include/linux/fs.h, ...):
   include/linux/sched/signal.h:751:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   include/linux/sched/signal.h:751:37: sparse:     expected struct spinlock [usertype] *lock
   include/linux/sched/signal.h:751:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:380:30: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *l @@     got struct spinlock [noderef] __rcu * @@
   kernel/ptrace.c:380:30: sparse:     expected struct spinlock [usertype] *l
   kernel/ptrace.c:380:30: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:409:12: sparse: sparse: context imbalance in 'ptrace_attach' - different lock contexts for basic block
   kernel/ptrace.c:500:38: sparse: sparse: dereference of noderef expression
   kernel/ptrace.c: note: in included file (through include/linux/fwnode.h, include/linux/logic_pio.h, include/asm-generic/io.h, ...):
   include/linux/list.h:83:21: sparse: sparse: self-comparison always evaluates to true
   kernel/ptrace.c: note: in included file (through include/linux/rcuwait.h, include/linux/percpu-rwsem.h, include/linux/fs.h, ...):
   include/linux/sched/signal.h:751:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   include/linux/sched/signal.h:751:37: sparse:     expected struct spinlock [usertype] *lock
   include/linux/sched/signal.h:751:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:690:9: sparse: sparse: context imbalance in 'ptrace_getsiginfo' - different lock contexts for basic block
   include/linux/sched/signal.h:751:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   include/linux/sched/signal.h:751:37: sparse:     expected struct spinlock [usertype] *lock
   include/linux/sched/signal.h:751:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:706:9: sparse: sparse: context imbalance in 'ptrace_setsiginfo' - different lock contexts for basic block
   kernel/ptrace.c: note: in included file:
   arch/mips/include/asm/syscall.h:85:25: sparse: sparse: incorrect type in initializer (different address spaces) @@     expected int const [noderef] __user *__p @@     got int * @@
   arch/mips/include/asm/syscall.h:85:25: sparse:     expected int const [noderef] __user *__p
   arch/mips/include/asm/syscall.h:85:25: sparse:     got int *
>> arch/mips/include/asm/syscall.h:121:25: sparse: sparse: incorrect type in initializer (different address spaces) @@     expected int [noderef] __user *__p @@     got int * @@
   arch/mips/include/asm/syscall.h:121:25: sparse:     expected int [noderef] __user *__p
   arch/mips/include/asm/syscall.h:121:25: sparse:     got int *
   kernel/ptrace.c: note: in included file (through include/linux/rcuwait.h, include/linux/percpu-rwsem.h, include/linux/fs.h, ...):
   include/linux/sched/signal.h:751:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   include/linux/sched/signal.h:751:37: sparse:     expected struct spinlock [usertype] *lock
   include/linux/sched/signal.h:751:37: sparse:     got struct spinlock [noderef] __rcu *
   include/linux/sched/signal.h:751:37: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected struct spinlock [usertype] *lock @@     got struct spinlock [noderef] __rcu * @@
   include/linux/sched/signal.h:751:37: sparse:     expected struct spinlock [usertype] *lock
   include/linux/sched/signal.h:751:37: sparse:     got struct spinlock [noderef] __rcu *
   kernel/ptrace.c:1369:9: sparse: sparse: context imbalance in 'ptrace_request' - different lock contexts for basic block

vim +121 arch/mips/include/asm/syscall.h

307e4cb2957c2f Dmitry V. Levin 2025-01-08  116  
307e4cb2957c2f Dmitry V. Levin 2025-01-08  117  #ifdef CONFIG_64BIT
307e4cb2957c2f Dmitry V. Levin 2025-01-08  118  	case 4: case 5: case 6: case 7:
307e4cb2957c2f Dmitry V. Levin 2025-01-08  119  #ifdef CONFIG_MIPS32_O32
307e4cb2957c2f Dmitry V. Levin 2025-01-08  120  		if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
307e4cb2957c2f Dmitry V. Levin 2025-01-08 @121  			put_user(*arg, (int *)usp + n);
307e4cb2957c2f Dmitry V. Levin 2025-01-08  122  		else
307e4cb2957c2f Dmitry V. Levin 2025-01-08  123  #endif
307e4cb2957c2f Dmitry V. Levin 2025-01-08  124  			regs->regs[4 + n] = *arg;
307e4cb2957c2f Dmitry V. Levin 2025-01-08  125  
307e4cb2957c2f Dmitry V. Levin 2025-01-08  126  		return;
307e4cb2957c2f Dmitry V. Levin 2025-01-08  127  #endif
307e4cb2957c2f Dmitry V. Levin 2025-01-08  128  	}
307e4cb2957c2f Dmitry V. Levin 2025-01-08  129  }
307e4cb2957c2f Dmitry V. Levin 2025-01-08  130  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[Eugene Syromiatnikov]

On Wed, Jan 08, 2025 at 01:04:56AM +0200, Dmitry V. Levin wrote:
> 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.
> 
> Current implementation supports changing only those bits of system call
> information that are used by strace, 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 re-using struct ptrace_syscall_info.reserved to specify
> the additional details that should be set.  Currently, the reserved
> field of struct ptrace_syscall_info must be initialized with zeroes;
> arch, instruction_pointer, and stack_pointer fields are 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.

> index 72c038fc71d0..231b8bf7eeff 100644
> --- a/include/uapi/linux/ptrace.h
> +++ b/include/uapi/linux/ptrace.h
> @@ -74,6 +74,7 @@ struct seccomp_metadata {
>  };
>  
>  #define PTRACE_GET_SYSCALL_INFO		0x420e
> +#define PTRACE_SET_SYSCALL_INFO		0x4212

It seems prudent to also add a comment about 0x4212 being taken right
after "#define PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG 0x4211", or the
usage of this ptrace request number may be overlooked on the next update.

>  struct ptrace_syscall_info {
>  	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
> -	__u8 pad[3];
> +	__u8 reserved[3];
>  	__u32 arch;
>  	__u64 instruction_pointer;
>  	__u64 stack_pointer;

I would like to suggest adding flags for changing scno and args right
away;  while it is possibly of limited use and seems like an unnecessary
overcomplication, at least changing arguments only seems natural to me,
to avoid possible interaction with scno-related shenanigans that might
present/appear on some kernels and/or architectures.  Also, it makes
the aforementioned possible extensions of the interface (changing
of ip/sp) more natural (as in those cases users might definitely want
to avoid touching syscall number/arguments).

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[Oleg Nesterov]

On 01/08, Dmitry V. Levin wrote:
>
> +ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
> +			      struct ptrace_syscall_info *info)
> +{
...
> +	syscall_set_nr(child, regs, nr);
> +	syscall_set_arguments(child, regs, args);
> +	if (nr == -1) {
> +		/*
> +		 * When the syscall number is set to -1, the syscall will be
> +		 * skipped.  In this case also set the syscall return value to
> +		 * -ENOSYS, otherwise on some architectures the corresponding
> +		 * struct pt_regs field will remain unchanged.
> +		 *
> +		 * Note that on some architectures syscall_set_return_value()
> +		 * modifies one of the struct pt_regs fields also modified by
> +		 * syscall_set_arguments(), so the former should be called
> +		 * after the latter.
> +		 */
> +		syscall_set_return_value(child, regs, -ENOSYS, 0);
> +	}

This doesn't look nice to me...

We don't need this syscall_set_return_value(ENOSYS) on x86, right?

So perhaps we should move this "if (nr == -1) code  into
syscall_set_nr/syscall_set_arguments on those "some architectures" which
actually need it ?

Oleg.

Re: [PATCH 5/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO request

[Dmitry V. Levin]

On Thu, Jan 09, 2025 at 04:21:39PM +0100, Oleg Nesterov wrote:
> On 01/08, Dmitry V. Levin wrote:
> >
> > +ptrace_set_syscall_info_entry(struct task_struct *child, struct pt_regs *regs,
> > +			      struct ptrace_syscall_info *info)
> > +{
> ...
> > +	syscall_set_nr(child, regs, nr);
> > +	syscall_set_arguments(child, regs, args);
> > +	if (nr == -1) {
> > +		/*
> > +		 * When the syscall number is set to -1, the syscall will be
> > +		 * skipped.  In this case also set the syscall return value to
> > +		 * -ENOSYS, otherwise on some architectures the corresponding
> > +		 * struct pt_regs field will remain unchanged.
> > +		 *
> > +		 * Note that on some architectures syscall_set_return_value()
> > +		 * modifies one of the struct pt_regs fields also modified by
> > +		 * syscall_set_arguments(), so the former should be called
> > +		 * after the latter.
> > +		 */
> > +		syscall_set_return_value(child, regs, -ENOSYS, 0);
> > +	}
> 
> This doesn't look nice to me...
> 
> We don't need this syscall_set_return_value(ENOSYS) on x86, right?

No, we don't need this on x86.

> So perhaps we should move this "if (nr == -1) code  into
> syscall_set_nr/syscall_set_arguments on those "some architectures" which
> actually need it ?

Thanks for the suggestion.  I think the best option is to skip
syscall_set_arguments() invocation in case of nr == -1.  It's not just
pointless, but also it would clobber the syscall return value on those
architectures like arm64 that share the same register both for the first
argument of syscall and its return value.

This is what I'm going to implement for the next iteration of the series:

	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);


-- 
ldv