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, 77 insertions, 0 deletions

diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
new file mode 100644
index 000000000..fd887d5f3
--- /dev/null
+++ b/arch/nios2/mm/dma-mapping.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch>
+ * Copyright (C) 2009 Wind River Systems Inc
+ *  Implemented by fredrik.markstrom@gmail.com and ivarholmqvist@gmail.com
+ *
+ * Based on DMA code from MIPS.
+ *
+ * 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/types.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/cache.h>
+#include <asm/cacheflush.h>
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		invalidate_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	case DMA_TO_DEVICE:
+		/*
+		 * We just need to flush the caches here , but Nios2 flush
+		 * instruction will do both writeback and invalidate.
+		 */
+	case DMA_BIDIRECTIONAL: /* flush and invalidate */
+		flush_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	default:
+		BUG();
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_FROM_DEVICE:
+		invalidate_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	case DMA_TO_DEVICE:
+		break;
+	default:
+		BUG();
+	}
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	unsigned long start = (unsigned long)page_address(page);
+
+	flush_dcache_range(start, start + size);
+}
+
+void *arch_dma_set_uncached(void *ptr, size_t size)
+{
+	unsigned long addr = (unsigned long)ptr;
+
+	addr |= CONFIG_NIOS2_IO_REGION_BASE;
+
+	return (void *)ptr;
+}