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, 111 insertions, 0 deletions

diff --git a/drivers/firmware/efi/ovmf-debug-log.c b/drivers/firmware/efi/ovmf-debug-log.c
new file mode 100644
index 000000000..5b2471ffa
--- /dev/null
+++ b/drivers/firmware/efi/ovmf-debug-log.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/sysfs.h>
+
+#define OVMF_DEBUG_LOG_MAGIC1  0x3167646d666d766f  // "ovmfmdg1"
+#define OVMF_DEBUG_LOG_MAGIC2  0x3267646d666d766f  // "ovmfmdg2"
+
+struct ovmf_debug_log_header {
+	u64    magic1;
+	u64    magic2;
+	u64    hdr_size;
+	u64    log_size;
+	u64    lock; // edk2 spinlock
+	u64    head_off;
+	u64    tail_off;
+	u64    truncated;
+	u8     fw_version[128];
+};
+
+static struct ovmf_debug_log_header *hdr;
+static u8 *logbuf;
+static u64 logbufsize;
+
+static ssize_t ovmf_log_read(struct file *filp, struct kobject *kobj,
+			     const struct bin_attribute *attr, char *buf,
+			     loff_t offset, size_t count)
+{
+	u64 start, end;
+
+	start = hdr->head_off + offset;
+	if (hdr->head_off > hdr->tail_off && start >= hdr->log_size)
+		start -= hdr->log_size;
+
+	end = start + count;
+	if (start > hdr->tail_off) {
+		if (end > hdr->log_size)
+			end = hdr->log_size;
+	} else {
+		if (end > hdr->tail_off)
+			end = hdr->tail_off;
+	}
+
+	if (start > logbufsize || end > logbufsize)
+		return 0;
+	if (start >= end)
+		return 0;
+
+	memcpy(buf, logbuf + start, end - start);
+	return end - start;
+}
+
+static struct bin_attribute ovmf_log_bin_attr = {
+	.attr = {
+		.name = "ovmf_debug_log",
+		.mode = 0444,
+	},
+	.read = ovmf_log_read,
+};
+
+int __init ovmf_log_probe(unsigned long ovmf_debug_log_table)
+{
+	int ret = -EINVAL;
+	u64 size;
+
+	/* map + verify header */
+	hdr = memremap(ovmf_debug_log_table, sizeof(*hdr), MEMREMAP_WB);
+	if (!hdr) {
+		pr_err("OVMF debug log: header map failed\n");
+		return -EINVAL;
+	}
+
+	if (hdr->magic1 != OVMF_DEBUG_LOG_MAGIC1 ||
+	    hdr->magic2 != OVMF_DEBUG_LOG_MAGIC2) {
+		printk(KERN_ERR "OVMF debug log: magic mismatch\n");
+		goto err_unmap;
+	}
+
+	size = hdr->hdr_size + hdr->log_size;
+	pr_info("OVMF debug log: firmware version: \"%s\"\n", hdr->fw_version);
+	pr_info("OVMF debug log: buffer size: %lluk\n", size / 1024);
+
+	/* map complete log buffer */
+	memunmap(hdr);
+	hdr = memremap(ovmf_debug_log_table, size, MEMREMAP_WB);
+	if (!hdr) {
+		pr_err("OVMF debug log: buffer map failed\n");
+		return -EINVAL;
+	}
+	logbuf = (void *)hdr + hdr->hdr_size;
+	logbufsize = hdr->log_size;
+
+	ovmf_log_bin_attr.size = size;
+	ret = sysfs_create_bin_file(efi_kobj, &ovmf_log_bin_attr);
+	if (ret != 0) {
+		pr_err("OVMF debug log: sysfs register failed\n");
+		goto err_unmap;
+	}
+
+	return 0;
+
+err_unmap:
+	memunmap(hdr);
+	return ret;
+}