x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 211 insertions, 0 deletions

diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
new file mode 100644
index 000000000..3a2a84ab9
--- /dev/null
+++ b/arch/um/os-Linux/process.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de)
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/futex.h>
+#include <sys/mman.h>
+#include <sys/ptrace.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <asm/unistd.h>
+#include <init.h>
+#include <longjmp.h>
+#include <os.h>
+#include <skas/skas.h>
+
+void os_alarm_process(int pid)
+{
+	if (pid <= 0)
+		return;
+
+	kill(pid, SIGALRM);
+}
+
+void os_kill_process(int pid, int reap_child)
+{
+	if (pid <= 0)
+		return;
+
+	/* Block signals until child is reaped */
+	block_signals();
+
+	kill(pid, SIGKILL);
+	if (reap_child)
+		CATCH_EINTR(waitpid(pid, NULL, __WALL));
+
+	unblock_signals();
+}
+
+/* Kill off a ptraced child by all means available.  kill it normally first,
+ * then PTRACE_KILL it, then PTRACE_CONT it in case it's in a run state from
+ * which it can't exit directly.
+ */
+
+void os_kill_ptraced_process(int pid, int reap_child)
+{
+	if (pid <= 0)
+		return;
+
+	/* Block signals until child is reaped */
+	block_signals();
+
+	kill(pid, SIGKILL);
+	ptrace(PTRACE_KILL, pid);
+	ptrace(PTRACE_CONT, pid);
+	if (reap_child)
+		CATCH_EINTR(waitpid(pid, NULL, __WALL));
+
+	unblock_signals();
+}
+
+pid_t os_reap_child(void)
+{
+	int status;
+
+	/* Try to reap a child */
+	return waitpid(-1, &status, WNOHANG);
+}
+
+/* Don't use the glibc version, which caches the result in TLS. It misses some
+ * syscalls, and also breaks with clone(), which does not unshare the TLS.
+ */
+
+int os_getpid(void)
+{
+	return syscall(__NR_getpid);
+}
+
+int os_map_memory(void *virt, int fd, unsigned long long off, unsigned long len,
+		  int r, int w, int x)
+{
+	void *loc;
+	int prot;
+
+	prot = (r ? PROT_READ : 0) | (w ? PROT_WRITE : 0) |
+		(x ? PROT_EXEC : 0);
+
+	loc = mmap64((void *) virt, len, prot, MAP_SHARED | MAP_FIXED,
+		     fd, off);
+	if (loc == MAP_FAILED)
+		return -errno;
+	return 0;
+}
+
+int os_protect_memory(void *addr, unsigned long len, int r, int w, int x)
+{
+	int prot = ((r ? PROT_READ : 0) | (w ? PROT_WRITE : 0) |
+		    (x ? PROT_EXEC : 0));
+
+	if (mprotect(addr, len, prot) < 0)
+		return -errno;
+
+	return 0;
+}
+
+int os_unmap_memory(void *addr, int len)
+{
+	int err;
+
+	err = munmap(addr, len);
+	if (err < 0)
+		return -errno;
+	return 0;
+}
+
+#ifndef MADV_REMOVE
+#define MADV_REMOVE KERNEL_MADV_REMOVE
+#endif
+
+int os_drop_memory(void *addr, int length)
+{
+	int err;
+
+	err = madvise(addr, length, MADV_REMOVE);
+	if (err < 0)
+		err = -errno;
+	return err;
+}
+
+int __init can_drop_memory(void)
+{
+	void *addr;
+	int fd, ok = 0;
+
+	printk(UM_KERN_INFO "Checking host MADV_REMOVE support...");
+	fd = create_mem_file(UM_KERN_PAGE_SIZE);
+	if (fd < 0) {
+		printk(UM_KERN_ERR "Creating test memory file failed, "
+		       "err = %d\n", -fd);
+		goto out;
+	}
+
+	addr = mmap64(NULL, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
+		      MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED) {
+		printk(UM_KERN_ERR "Mapping test memory file failed, "
+		       "err = %d\n", -errno);
+		goto out_close;
+	}
+
+	if (madvise(addr, UM_KERN_PAGE_SIZE, MADV_REMOVE) != 0) {
+		printk(UM_KERN_ERR "MADV_REMOVE failed, err = %d\n", -errno);
+		goto out_unmap;
+	}
+
+	printk(UM_KERN_CONT "OK\n");
+	ok = 1;
+
+out_unmap:
+	munmap(addr, UM_KERN_PAGE_SIZE);
+out_close:
+	close(fd);
+out:
+	return ok;
+}
+
+void init_new_thread_signals(void)
+{
+	set_handler(SIGSEGV);
+	set_handler(SIGTRAP);
+	set_handler(SIGFPE);
+	set_handler(SIGILL);
+	set_handler(SIGBUS);
+	signal(SIGHUP, SIG_IGN);
+	set_handler(SIGIO);
+	/* We (currently) only use the child reaper IRQ in seccomp mode */
+	if (using_seccomp)
+		set_handler(SIGCHLD);
+	signal(SIGWINCH, SIG_IGN);
+}
+
+void os_set_pdeathsig(void)
+{
+	prctl(PR_SET_PDEATHSIG, SIGKILL);
+}
+
+int os_futex_wait(void *uaddr, unsigned int val)
+{
+	int r;
+
+	CATCH_EINTR(r = syscall(__NR_futex, uaddr, FUTEX_WAIT, val,
+				NULL, NULL, 0));
+	return r < 0 ? -errno : r;
+}
+
+int os_futex_wake(void *uaddr)
+{
+	int r;
+
+	CATCH_EINTR(r = syscall(__NR_futex, uaddr, FUTEX_WAKE, INT_MAX,
+				NULL, NULL, 0));
+	return r < 0 ? -errno : r;
+}