From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/kernel/ptrace.c | 187 ++++++++++++++++++++++++++++++++++++++--------
1 files changed, 152 insertions(+), 35 deletions(-)
diff --git a/kernel/kernel/ptrace.c b/kernel/kernel/ptrace.c
index af74e84..aab480e 100644
--- a/kernel/kernel/ptrace.c
+++ b/kernel/kernel/ptrace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/ptrace.c
*
@@ -30,6 +31,8 @@
#include <linux/cn_proc.h>
#include <linux/compat.h>
#include <linux/sched/signal.h>
+
+#include <asm/syscall.h> /* for syscall_get_* */
/*
* Access another process' address space via ptrace.
@@ -115,6 +118,9 @@
BUG_ON(!child->ptrace);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+#ifdef TIF_SYSCALL_EMU
+ clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
+#endif
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
@@ -364,6 +370,26 @@
return !err;
}
+static int check_ptrace_options(unsigned long data)
+{
+ if (data & ~(unsigned long)PTRACE_O_MASK)
+ return -EINVAL;
+
+ if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
+ if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
+ !IS_ENABLED(CONFIG_SECCOMP))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED ||
+ current->ptrace & PT_SUSPEND_SECCOMP)
+ return -EPERM;
+ }
+ return 0;
+}
+
static int ptrace_attach(struct task_struct *task, long request,
unsigned long addr,
unsigned long flags)
@@ -375,8 +401,16 @@
if (seize) {
if (addr != 0)
goto out;
+ /*
+ * This duplicates the check in check_ptrace_options() because
+ * ptrace_attach() and ptrace_setoptions() have historically
+ * used different error codes for unknown ptrace options.
+ */
if (flags & ~(unsigned long)PTRACE_O_MASK)
goto out;
+ retval = check_ptrace_options(flags);
+ if (retval)
+ return retval;
flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT);
} else {
flags = PT_PTRACED;
@@ -420,7 +454,7 @@
/* SEIZE doesn't trap tracee on attach */
if (!seize)
- send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+ send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
spin_lock(&task->sighand->siglock);
@@ -587,7 +621,7 @@
list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
if (unlikely(p->ptrace & PT_EXITKILL))
- send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
+ send_sig_info(SIGKILL, SEND_SIG_PRIV, p);
if (__ptrace_detach(tracer, p))
list_add(&p->ptrace_entry, dead);
@@ -649,22 +683,11 @@
static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
unsigned flags;
+ int ret;
- if (data & ~(unsigned long)PTRACE_O_MASK)
- return -EINVAL;
-
- if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
- if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
- !IS_ENABLED(CONFIG_SECCOMP))
- return -EINVAL;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED ||
- current->ptrace & PT_SUSPEND_SECCOMP)
- return -EPERM;
- }
+ ret = check_ptrace_options(data);
+ if (ret)
+ return ret;
/* Avoid intermediate state when all opts are cleared */
flags = child->ptrace;
@@ -675,7 +698,7 @@
return 0;
}
-static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
+static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info)
{
unsigned long flags;
int error = -ESRCH;
@@ -691,7 +714,7 @@
return error;
}
-static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
+static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info)
{
unsigned long flags;
int error = -ESRCH;
@@ -737,7 +760,7 @@
pending = &child->pending;
for (i = 0; i < arg.nr; ) {
- siginfo_t info;
+ kernel_siginfo_t info;
unsigned long off = arg.off + i;
bool found = false;
@@ -908,14 +931,107 @@
* to ensure no machine forgets it.
*/
EXPORT_SYMBOL_GPL(task_user_regset_view);
-#endif
+
+static unsigned long
+ptrace_get_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 i;
+
+ info->op = PTRACE_SYSCALL_INFO_ENTRY;
+ info->entry.nr = syscall_get_nr(child, regs);
+ syscall_get_arguments(child, regs, args);
+ for (i = 0; i < ARRAY_SIZE(args); i++)
+ info->entry.args[i] = args[i];
+
+ /* args is the last field in struct ptrace_syscall_info.entry */
+ return offsetofend(struct ptrace_syscall_info, entry.args);
+}
+
+static unsigned long
+ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs,
+ struct ptrace_syscall_info *info)
+{
+ /*
+ * As struct ptrace_syscall_info.entry is currently a subset
+ * of struct ptrace_syscall_info.seccomp, it makes sense to
+ * initialize that subset using ptrace_get_syscall_info_entry().
+ * This can be reconsidered in the future if these structures
+ * diverge significantly enough.
+ */
+ ptrace_get_syscall_info_entry(child, regs, info);
+ info->op = PTRACE_SYSCALL_INFO_SECCOMP;
+ info->seccomp.ret_data = child->ptrace_message;
+
+ /* ret_data is the last field in struct ptrace_syscall_info.seccomp */
+ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data);
+}
+
+static unsigned long
+ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs,
+ struct ptrace_syscall_info *info)
+{
+ info->op = PTRACE_SYSCALL_INFO_EXIT;
+ info->exit.rval = syscall_get_error(child, regs);
+ info->exit.is_error = !!info->exit.rval;
+ if (!info->exit.is_error)
+ info->exit.rval = syscall_get_return_value(child, regs);
+
+ /* is_error is the last field in struct ptrace_syscall_info.exit */
+ return offsetofend(struct ptrace_syscall_info, exit.is_error);
+}
+
+static int
+ptrace_get_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 = {
+ .op = PTRACE_SYSCALL_INFO_NONE,
+ .arch = syscall_get_arch(child),
+ .instruction_pointer = instruction_pointer(regs),
+ .stack_pointer = user_stack_pointer(regs),
+ };
+ unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry);
+ unsigned long write_size;
+
+ /*
+ * This does not need lock_task_sighand() to access
+ * child->last_siginfo because ptrace_freeze_traced()
+ * called earlier by ptrace_check_attach() ensures that
+ * the tracee cannot go away and clear its last_siginfo.
+ */
+ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) {
+ case SIGTRAP | 0x80:
+ switch (child->ptrace_message) {
+ case PTRACE_EVENTMSG_SYSCALL_ENTRY:
+ actual_size = ptrace_get_syscall_info_entry(child, regs,
+ &info);
+ break;
+ case PTRACE_EVENTMSG_SYSCALL_EXIT:
+ actual_size = ptrace_get_syscall_info_exit(child, regs,
+ &info);
+ break;
+ }
+ break;
+ case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8):
+ actual_size = ptrace_get_syscall_info_seccomp(child, regs,
+ &info);
+ break;
+ }
+
+ write_size = min(actual_size, user_size);
+ return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size;
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
int ptrace_request(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
bool seized = child->ptrace & PT_SEIZED;
int ret = -EIO;
- siginfo_t siginfo, *si;
+ kernel_siginfo_t siginfo, *si;
void __user *datavp = (void __user *) data;
unsigned long __user *datalp = datavp;
unsigned long flags;
@@ -949,9 +1065,8 @@
break;
case PTRACE_SETSIGINFO:
- if (copy_from_user(&siginfo, datavp, sizeof siginfo))
- ret = -EFAULT;
- else
+ ret = copy_siginfo_from_user(&siginfo, datavp);
+ if (!ret)
ret = ptrace_setsiginfo(child, &siginfo);
break;
@@ -1104,9 +1219,8 @@
return ptrace_resume(child, request, data);
case PTRACE_KILL:
- if (child->exit_state) /* already dead */
- return 0;
- return ptrace_resume(child, request, SIGKILL);
+ send_sig_info(SIGKILL, SEND_SIG_NOINFO, child);
+ return 0;
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
case PTRACE_GETREGSET:
@@ -1114,7 +1228,7 @@
struct iovec kiov;
struct iovec __user *uiov = datavp;
- if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+ if (!access_ok(uiov, sizeof(*uiov)))
return -EFAULT;
if (__get_user(kiov.iov_base, &uiov->iov_base) ||
@@ -1126,6 +1240,10 @@
ret = __put_user(kiov.iov_len, &uiov->iov_len);
break;
}
+
+ case PTRACE_GET_SYSCALL_INFO:
+ ret = ptrace_get_syscall_info(child, addr, datavp);
+ break;
#endif
case PTRACE_SECCOMP_GET_FILTER:
@@ -1221,7 +1339,7 @@
{
compat_ulong_t __user *datap = compat_ptr(data);
compat_ulong_t word;
- siginfo_t siginfo;
+ kernel_siginfo_t siginfo;
int ret;
switch (request) {
@@ -1255,10 +1373,9 @@
break;
case PTRACE_SETSIGINFO:
- if (copy_siginfo_from_user32(
- &siginfo, (struct compat_siginfo __user *) datap))
- ret = -EFAULT;
- else
+ ret = copy_siginfo_from_user32(
+ &siginfo, (struct compat_siginfo __user *) datap);
+ if (!ret)
ret = ptrace_setsiginfo(child, &siginfo);
break;
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
@@ -1271,7 +1388,7 @@
compat_uptr_t ptr;
compat_size_t len;
- if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+ if (!access_ok(uiov, sizeof(*uiov)))
return -EFAULT;
if (__get_user(ptr, &uiov->iov_base) ||
--
Gitblit v1.6.2