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, 248 insertions, 0 deletions

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
new file mode 100644
index 000000000..a9816bbc9
--- /dev/null
+++ b/arch/alpha/mm/fault.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/arch/alpha/mm/fault.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ */
+
+#include <linux/sched/signal.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/io.h>
+
+#define __EXTERN_INLINE inline
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#undef  __EXTERN_INLINE
+
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/extable.h>
+#include <linux/uaccess.h>
+#include <linux/perf_event.h>
+
+extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
+
+
+/*
+ * Force a new ASN for a task.
+ */
+
+#ifndef CONFIG_SMP
+unsigned long last_asn = ASN_FIRST_VERSION;
+#endif
+
+void
+__load_new_mm_context(struct mm_struct *next_mm)
+{
+	unsigned long mmc;
+	struct pcb_struct *pcb;
+
+	mmc = __get_new_mm_context(next_mm, smp_processor_id());
+	next_mm->context[smp_processor_id()] = mmc;
+
+	pcb = &current_thread_info()->pcb;
+	pcb->asn = mmc & HARDWARE_ASN_MASK;
+	pcb->ptbr = ((unsigned long) next_mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
+
+	__reload_thread(pcb);
+}
+
+
+/*
+ * This routine handles page faults.  It determines the address,
+ * and the problem, and then passes it off to handle_mm_fault().
+ *
+ * mmcsr:
+ *	0 = translation not valid
+ *	1 = access violation
+ *	2 = fault-on-read
+ *	3 = fault-on-execute
+ *	4 = fault-on-write
+ *
+ * cause:
+ *	-1 = instruction fetch
+ *	0 = load
+ *	1 = store
+ *
+ * Registers $9 through $15 are saved in a block just prior to `regs' and
+ * are saved and restored around the call to allow exception code to
+ * modify them.
+ */
+
+/* Macro for exception fixup code to access integer registers.  */
+#define dpf_reg(r)							\
+	(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 :	\
+				 (r) <= 18 ? (r)+11 : (r)-10])
+
+asmlinkage void
+do_page_fault(unsigned long address, unsigned long mmcsr,
+	      long cause, struct pt_regs *regs)
+{
+	struct vm_area_struct * vma;
+	struct mm_struct *mm = current->mm;
+	const struct exception_table_entry *fixup;
+	int si_code = SEGV_MAPERR;
+	vm_fault_t fault;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+
+	/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
+	   (or is suppressed by the PALcode).  Support that for older CPUs
+	   by ignoring such an instruction.  */
+	if (cause == 0) {
+		unsigned int insn;
+		__get_user(insn, (unsigned int __user *)regs->pc);
+		if ((insn >> 21 & 0x1f) == 0x1f &&
+		    /* ldq ldl ldt lds ldg ldf ldwu ldbu */
+		    (1ul << (insn >> 26) & 0x30f00001400ul)) {
+			regs->pc += 4;
+			return;
+		}
+	}
+
+	/* If we're in an interrupt context, or have no user context,
+	   we must not take the fault.  */
+	if (!mm || faulthandler_disabled())
+		goto no_context;
+
+#ifdef CONFIG_ALPHA_LARGE_VMALLOC
+	if (address >= TASK_SIZE)
+		goto vmalloc_fault;
+#endif
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+retry:
+	vma = lock_mm_and_find_vma(mm, address, regs);
+	if (!vma)
+		goto bad_area_nosemaphore;
+
+	/* Ok, we have a good vm_area for this memory access, so
+	   we can handle it.  */
+	si_code = SEGV_ACCERR;
+	if (cause < 0) {
+		if (!(vma->vm_flags & VM_EXEC))
+			goto bad_area;
+	} else if (!cause) {
+		/* Allow reads even for write-only mappings */
+		if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
+			goto bad_area;
+	} else {
+		if (!(vma->vm_flags & VM_WRITE))
+			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
+	}
+
+	/* If for any reason at all we couldn't handle the fault,
+	   make sure we exit gracefully rather than endlessly redo
+	   the fault.  */
+	fault = handle_mm_fault(vma, address, flags, regs);
+
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto no_context;
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		if (fault & VM_FAULT_OOM)
+			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
+		else if (fault & VM_FAULT_SIGBUS)
+			goto do_sigbus;
+		BUG();
+	}
+
+	if (fault & VM_FAULT_RETRY) {
+		flags |= FAULT_FLAG_TRIED;
+
+		/* No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+
+		goto retry;
+	}
+
+	mmap_read_unlock(mm);
+
+	return;
+
+	/* Something tried to access memory that isn't in our memory map.
+	   Fix it, but check if it's kernel or user first.  */
+ bad_area:
+	mmap_read_unlock(mm);
+
+ bad_area_nosemaphore:
+	if (user_mode(regs))
+		goto do_sigsegv;
+
+ no_context:
+	/* Are we prepared to handle this fault as an exception?  */
+	if ((fixup = search_exception_tables(regs->pc)) != 0) {
+		unsigned long newpc;
+		newpc = fixup_exception(dpf_reg, fixup, regs->pc);
+		regs->pc = newpc;
+		return;
+	}
+
+	/* Oops. The kernel tried to access some bad page. We'll have to
+	   terminate things with extreme prejudice.  */
+	printk(KERN_ALERT "Unable to handle kernel paging request at "
+	       "virtual address %016lx\n", address);
+	die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16);
+	make_task_dead(SIGKILL);
+
+	/* We ran out of memory, or some other thing happened to us that
+	   made us unable to handle the page fault gracefully.  */
+ out_of_memory:
+	mmap_read_unlock(mm);
+	if (!user_mode(regs))
+		goto no_context;
+	pagefault_out_of_memory();
+	return;
+
+ do_sigbus:
+	mmap_read_unlock(mm);
+	/* Send a sigbus, regardless of whether we were in kernel
+	   or user mode.  */
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) address);
+	if (!user_mode(regs))
+		goto no_context;
+	return;
+
+ do_sigsegv:
+	force_sig_fault(SIGSEGV, si_code, (void __user *) address);
+	return;
+
+#ifdef CONFIG_ALPHA_LARGE_VMALLOC
+ vmalloc_fault:
+	if (user_mode(regs))
+		goto do_sigsegv;
+	else {
+		/* Synchronize this task's top level page-table
+		   with the "reference" page table from init.  */
+		long index = pgd_index(address);
+		pgd_t *pgd, *pgd_k;
+
+		pgd = current->active_mm->pgd + index;
+		pgd_k = swapper_pg_dir + index;
+		if (!pgd_present(*pgd) && pgd_present(*pgd_k)) {
+			pgd_val(*pgd) = pgd_val(*pgd_k);
+			return;
+		}
+		goto no_context;
+	}
+#endif
+}