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, 81 insertions, 0 deletions

diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h
new file mode 100644
index 000000000..ea9b0ec40
--- /dev/null
+++ b/lib/test_hmm_uapi.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This is a module to test the HMM (Heterogeneous Memory Management) API
+ * of the kernel. It allows a userspace program to expose its entire address
+ * space through the HMM test module device file.
+ */
+#ifndef _LIB_TEST_HMM_UAPI_H
+#define _LIB_TEST_HMM_UAPI_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Structure to pass to the HMM test driver to mimic a device accessing
+ * system memory and ZONE_DEVICE private memory through device page tables.
+ *
+ * @addr: (in) user address the device will read/write
+ * @ptr: (in) user address where device data is copied to/from
+ * @npages: (in) number of pages to read/write
+ * @cpages: (out) number of pages copied
+ * @faults: (out) number of device page faults seen
+ */
+struct hmm_dmirror_cmd {
+	__u64		addr;
+	__u64		ptr;
+	__u64		npages;
+	__u64		cpages;
+	__u64		faults;
+};
+
+/* Expose the address space of the calling process through hmm device file */
+#define HMM_DMIRROR_READ		_IOWR('H', 0x00, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_WRITE		_IOWR('H', 0x01, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_DEV	_IOWR('H', 0x02, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_MIGRATE_TO_SYS	_IOWR('H', 0x03, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_SNAPSHOT		_IOWR('H', 0x04, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_EXCLUSIVE		_IOWR('H', 0x05, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_CHECK_EXCLUSIVE	_IOWR('H', 0x06, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_RELEASE		_IOWR('H', 0x07, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_FLAGS		_IOWR('H', 0x08, struct hmm_dmirror_cmd)
+#define HMM_DMIRROR_READ_UNLOCKED	_IOWR('H', 0x09, struct hmm_dmirror_cmd)
+
+#define HMM_DMIRROR_FLAG_FAIL_ALLOC	(1ULL << 0)
+
+/*
+ * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
+ * HMM_DMIRROR_PROT_ERROR: no valid mirror PTE for this page
+ * HMM_DMIRROR_PROT_NONE: unpopulated PTE or PTE with no access
+ * HMM_DMIRROR_PROT_READ: read-only PTE
+ * HMM_DMIRROR_PROT_WRITE: read/write PTE
+ * HMM_DMIRROR_PROT_PMD: PMD sized page is fully mapped by same permissions
+ * HMM_DMIRROR_PROT_PUD: PUD sized page is fully mapped by same permissions
+ * HMM_DMIRROR_PROT_ZERO: special read-only zero page
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL: Migrated device private page on the
+ *					device the ioctl() is made
+ * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some
+ *					other device
+ * HMM_DMIRROR_PROT_DEV_COHERENT: Migrate device coherent page on the device
+ *				  the ioctl() is made
+ */
+enum {
+	HMM_DMIRROR_PROT_ERROR			= 0xFF,
+	HMM_DMIRROR_PROT_NONE			= 0x00,
+	HMM_DMIRROR_PROT_READ			= 0x01,
+	HMM_DMIRROR_PROT_WRITE			= 0x02,
+	HMM_DMIRROR_PROT_PMD			= 0x04,
+	HMM_DMIRROR_PROT_PUD			= 0x08,
+	HMM_DMIRROR_PROT_ZERO			= 0x10,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL	= 0x20,
+	HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE	= 0x30,
+	HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL	= 0x40,
+	HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE	= 0x50,
+};
+
+enum {
+	/* 0 is reserved to catch uninitialized type fields */
+	HMM_DMIRROR_MEMORY_DEVICE_PRIVATE = 1,
+	HMM_DMIRROR_MEMORY_DEVICE_COHERENT,
+};
+
+#endif /* _LIB_TEST_HMM_UAPI_H */