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, 182 insertions, 0 deletions

diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
new file mode 100644
index 000000000..9c4427d0b
--- /dev/null
+++ b/arch/riscv/mm/pgtable.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/pgalloc.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
+
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC)) {
+		if (!pte_same(ptep_get(ptep), entry)) {
+			__set_pte_at(vma->vm_mm, ptep, entry);
+			/* Here only not svadu is impacted */
+			flush_tlb_page(vma, address);
+			return true;
+		}
+
+		return false;
+	}
+
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(vma->vm_mm, ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+bool ptep_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return false;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+EXPORT_SYMBOL_GPL(pud_offset);
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+EXPORT_SYMBOL_GPL(p4d_offset);
+#endif
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+
+void p4d_clear_huge(p4d_t *p4d)
+{
+}
+
+int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
+{
+	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), prot);
+
+	set_pud(pud, new_pud);
+	return 1;
+}
+
+int pud_clear_huge(pud_t *pud)
+{
+	if (!pud_leaf(pudp_get(pud)))
+		return 0;
+	pud_clear(pud);
+	return 1;
+}
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
+	int i;
+
+	pud_clear(pud);
+
+	flush_tlb_kernel_range(addr, addr + PUD_SIZE);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd[i])) {
+			pte_t *pte = (pte_t *)pmd_page_vaddr(pmd[i]);
+
+			pte_free_kernel(NULL, pte);
+		}
+	}
+
+	pmd_free(NULL, pmd);
+
+	return 1;
+}
+
+int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
+{
+	pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), prot);
+
+	set_pmd(pmd, new_pmd);
+	return 1;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (!pmd_leaf(pmdp_get(pmd)))
+		return 0;
+	pmd_clear(pmd);
+	return 1;
+}
+
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
+
+	pmd_clear(pmd);
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	pte_free_kernel(NULL, pte);
+	return 1;
+}
+
+#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp)
+{
+	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
+	/*
+	 * When leaf PTE entries (regular pages) are collapsed into a leaf
+	 * PMD entry (huge page), a valid non-leaf PTE is converted into a
+	 * valid leaf PTE at the level 1 page table.  Since the sfence.vma
+	 * forms that specify an address only apply to leaf PTEs, we need a
+	 * global flush here.  collapse_huge_page() assumes these flushes are
+	 * eager, so just do the fence here.
+	 */
+	flush_tlb_mm(vma->vm_mm);
+	return pmd;
+}
+
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		      pud_t *pudp)
+{
+	VM_WARN_ON_ONCE(!pud_present(*pudp));
+	pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp));
+
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return old;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pte_mkwrite_shstk(pte);
+
+	return pte_mkwrite_novma(pte);
+}
+
+pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pmd_mkwrite_shstk(pmd);
+
+	return pmd_mkwrite_novma(pmd);
+}