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, 116 insertions, 0 deletions

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
new file mode 100644
index 000000000..cdd431027
--- /dev/null
+++ b/drivers/firmware/efi/tpm.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Google, Inc.
+ *     Thiebaud Weksteen <tweek@google.com>
+ */
+
+#define TPM_MEMREMAP(start, size) early_memremap(start, size)
+#define TPM_MEMUNMAP(start, size) early_memunmap(start, size)
+
+#include <asm/early_ioremap.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/tpm_eventlog.h>
+
+int efi_tpm_final_log_size;
+EXPORT_SYMBOL(efi_tpm_final_log_size);
+
+static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info)
+{
+	struct tcg_pcr_event2_head *header;
+	u32 event_size, size = 0;
+
+	while (count > 0) {
+		header = data + size;
+		event_size = __calc_tpm2_event_size(header, size_info, true);
+		if (event_size == 0)
+			return -1;
+		size += event_size;
+		count--;
+	}
+
+	return size;
+}
+
+/*
+ * Reserve the memory associated with the TPM Event Log configuration table.
+ */
+int __init efi_tpm_eventlog_init(void)
+{
+	struct linux_efi_tpm_eventlog *log_tbl;
+	struct efi_tcg2_final_events_table *final_tbl;
+	unsigned int tbl_size;
+	int final_tbl_size;
+	int ret = 0;
+
+	if (efi.tpm_log == EFI_INVALID_TABLE_ADDR) {
+		/*
+		 * We can't calculate the size of the final events without the
+		 * first entry in the TPM log, so bail here.
+		 */
+		return 0;
+	}
+
+	log_tbl = early_memremap(efi.tpm_log, sizeof(*log_tbl));
+	if (!log_tbl) {
+		pr_err("Failed to map TPM Event Log table @ 0x%lx\n",
+		       efi.tpm_log);
+		efi.tpm_log = EFI_INVALID_TABLE_ADDR;
+		return -ENOMEM;
+	}
+
+	tbl_size = sizeof(*log_tbl) + log_tbl->size;
+	if (memblock_reserve(efi.tpm_log, tbl_size)) {
+		pr_err("TPM Event Log memblock reserve fails (0x%lx, 0x%x)\n",
+		       efi.tpm_log, tbl_size);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR) {
+		pr_info("TPM Final Events table not present\n");
+		goto out;
+	} else if (log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
+		pr_warn(FW_BUG "TPM Final Events table invalid\n");
+		goto out;
+	}
+
+	final_tbl = early_memremap(efi.tpm_final_log, sizeof(*final_tbl));
+
+	if (!final_tbl) {
+		pr_err("Failed to map TPM Final Event Log table @ 0x%lx\n",
+		       efi.tpm_final_log);
+		efi.tpm_final_log = EFI_INVALID_TABLE_ADDR;
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	final_tbl_size = 0;
+	if (final_tbl->nr_events != 0) {
+		void *events = (void *)efi.tpm_final_log
+				+ sizeof(final_tbl->version)
+				+ sizeof(final_tbl->nr_events);
+
+		final_tbl_size = tpm2_calc_event_log_size(events,
+							  final_tbl->nr_events,
+							  log_tbl->log);
+	}
+
+	if (final_tbl_size < 0) {
+		pr_err(FW_BUG "Failed to parse event in TPM Final Events Log\n");
+		ret = -EINVAL;
+		goto out_calc;
+	}
+
+	memblock_reserve(efi.tpm_final_log,
+			 final_tbl_size + sizeof(*final_tbl));
+	efi_tpm_final_log_size = final_tbl_size;
+
+out_calc:
+	early_memunmap(final_tbl, sizeof(*final_tbl));
+out:
+	early_memunmap(log_tbl, sizeof(*log_tbl));
+	return ret;
+}
+