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, 264 insertions, 0 deletions

diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
new file mode 100644
index 000000000..e3fa9c151
--- /dev/null
+++ b/arch/nios2/mm/fault.c
@@ -0,0 +1,264 @@
+/*
+ * Copyright (C) 2009 Wind River Systems Inc
+ *   Implemented by fredrik.markstrom@gmail.com and ivarholmqvist@gmail.com
+ *
+ * based on arch/mips/mm/fault.c which is:
+ *
+ * Copyright (C) 1995-2000 Ralf Baechle
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/extable.h>
+#include <linux/uaccess.h>
+#include <linux/perf_event.h>
+
+#include <asm/mmu_context.h>
+#include <asm/traps.h>
+
+#define EXC_SUPERV_INSN_ACCESS	9  /* Supervisor only instruction address */
+#define EXC_SUPERV_DATA_ACCESS	11 /* Supervisor only data address */
+#define EXC_X_PROTECTION_FAULT	13 /* TLB permission violation (x) */
+#define EXC_R_PROTECTION_FAULT	14 /* TLB permission violation (r) */
+#define EXC_W_PROTECTION_FAULT	15 /* TLB permission violation (w) */
+
+/*
+ * This routine handles page faults.  It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ */
+asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
+				unsigned long address)
+{
+	struct vm_area_struct *vma = NULL;
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+	int code = SEGV_MAPERR;
+	vm_fault_t fault;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+
+	cause >>= 2;
+
+	/* Restart the instruction */
+	regs->ea -= 4;
+
+	/*
+	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END)) {
+		if (user_mode(regs))
+			goto bad_area_nosemaphore;
+		else
+			goto vmalloc_fault;
+	}
+
+	if (unlikely(address >= TASK_SIZE))
+		goto bad_area_nosemaphore;
+
+	/*
+	 * If we're in an interrupt or have no user
+	 * context, we must not take the fault..
+	 */
+	if (faulthandler_disabled() || !mm)
+		goto bad_area_nosemaphore;
+
+	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..
+ */
+	code = SEGV_ACCERR;
+
+	switch (cause) {
+	case EXC_SUPERV_INSN_ACCESS:
+		goto bad_area;
+	case EXC_SUPERV_DATA_ACCESS:
+		goto bad_area;
+	case EXC_X_PROTECTION_FAULT:
+		if (!(vma->vm_flags & VM_EXEC))
+			goto bad_area;
+		break;
+	case EXC_R_PROTECTION_FAULT:
+		if (!(vma->vm_flags & VM_READ))
+			goto bad_area;
+		break;
+	case EXC_W_PROTECTION_FAULT:
+		if (!(vma->vm_flags & VM_WRITE))
+			goto bad_area;
+		flags = FAULT_FLAG_WRITE;
+		break;
+	}
+
+	/*
+	 * 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:
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		if (unhandled_signal(current, SIGSEGV) && printk_ratelimit()) {
+			pr_info("%s: unhandled page fault (%d) at 0x%08lx, "
+				"cause %ld\n", current->comm, SIGSEGV, address, cause);
+			show_regs(regs);
+		}
+		_exception(SIGSEGV, regs, code, address);
+		return;
+	}
+
+no_context:
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	bust_spinlocks(1);
+
+	pr_alert("Unable to handle kernel %s at virtual address %08lx",
+		address < PAGE_SIZE ? "NULL pointer dereference" :
+		"paging request", address);
+	pr_alert("ea = %08lx, ra = %08lx, cause = %ld\n", regs->ea, regs->ra,
+		cause);
+	panic("Oops");
+	return;
+
+/*
+ * 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);
+
+	/* Kernel mode? Handle exceptions or die */
+	if (!user_mode(regs))
+		goto no_context;
+
+	_exception(SIGBUS, regs, BUS_ADRERR, address);
+	return;
+
+vmalloc_fault:
+	{
+		/*
+		 * Synchronize this task's top level page-table
+		 * with the 'reference' page table.
+		 *
+		 * Do _not_ use "tsk" here. We might be inside
+		 * an interrupt in the middle of a task switch..
+		 */
+		int offset = pgd_index(address);
+		pgd_t *pgd, *pgd_k;
+		p4d_t *p4d, *p4d_k;
+		pud_t *pud, *pud_k;
+		pmd_t *pmd, *pmd_k;
+		pte_t *pte_k;
+
+		pgd = pgd_current + offset;
+		pgd_k = init_mm.pgd + offset;
+
+		if (!pgd_present(*pgd_k))
+			goto no_context;
+		set_pgd(pgd, *pgd_k);
+
+		p4d = p4d_offset(pgd, address);
+		p4d_k = p4d_offset(pgd_k, address);
+		if (!p4d_present(*p4d_k))
+			goto no_context;
+		pud = pud_offset(p4d, address);
+		pud_k = pud_offset(p4d_k, address);
+		if (!pud_present(*pud_k))
+			goto no_context;
+		pmd = pmd_offset(pud, address);
+		pmd_k = pmd_offset(pud_k, address);
+		if (!pmd_present(*pmd_k))
+			goto no_context;
+		set_pmd(pmd, *pmd_k);
+
+		pte_k = pte_offset_kernel(pmd_k, address);
+		if (!pte_present(*pte_k))
+			goto no_context;
+
+		flush_tlb_kernel_page(address);
+		return;
+	}
+}