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, 158 insertions, 0 deletions

diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c
new file mode 100644
index 000000000..8680d38cd
--- /dev/null
+++ b/drivers/md/dm-snap-transient.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2001-2002 Sistina Software (UK) Limited.
+ * Copyright (C) 2006-2008 Red Hat GmbH
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-exception-store.h"
+
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/vmalloc.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/dm-io.h>
+
+#define DM_MSG_PREFIX "transient snapshot"
+
+/*
+ *---------------------------------------------------------------
+ * Implementation of the store for non-persistent snapshots.
+ *---------------------------------------------------------------
+ */
+struct transient_c {
+	sector_t next_free;
+};
+
+static void transient_dtr(struct dm_exception_store *store)
+{
+	kfree(store->context);
+}
+
+static int transient_read_metadata(struct dm_exception_store *store,
+				   int (*callback)(void *callback_context,
+						   chunk_t old, chunk_t new),
+				   void *callback_context)
+{
+	return 0;
+}
+
+static int transient_prepare_exception(struct dm_exception_store *store,
+				       struct dm_exception *e)
+{
+	struct transient_c *tc = store->context;
+	sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev);
+
+	if (size < (tc->next_free + store->chunk_size))
+		return -1;
+
+	e->new_chunk = sector_to_chunk(store, tc->next_free);
+	tc->next_free += store->chunk_size;
+
+	return 0;
+}
+
+static void transient_commit_exception(struct dm_exception_store *store,
+				       struct dm_exception *e, int valid,
+				       void (*callback)(void *, int success),
+				       void *callback_context)
+{
+	/* Just succeed */
+	callback(callback_context, valid);
+}
+
+static void transient_usage(struct dm_exception_store *store,
+			    sector_t *total_sectors,
+			    sector_t *sectors_allocated,
+			    sector_t *metadata_sectors)
+{
+	*sectors_allocated = ((struct transient_c *) store->context)->next_free;
+	*total_sectors = get_dev_size(dm_snap_cow(store->snap)->bdev);
+	*metadata_sectors = 0;
+}
+
+static int transient_ctr(struct dm_exception_store *store, char *options)
+{
+	struct transient_c *tc;
+
+	tc = kmalloc_obj(struct transient_c);
+	if (!tc)
+		return -ENOMEM;
+
+	tc->next_free = 0;
+	store->context = tc;
+
+	return 0;
+}
+
+static unsigned int transient_status(struct dm_exception_store *store,
+				 status_type_t status, char *result,
+				 unsigned int maxlen)
+{
+	unsigned int sz = 0;
+
+	switch (status) {
+	case STATUSTYPE_INFO:
+		break;
+	case STATUSTYPE_TABLE:
+		DMEMIT(" N %llu", (unsigned long long)store->chunk_size);
+		break;
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
+	}
+
+	return sz;
+}
+
+static struct dm_exception_store_type _transient_type = {
+	.name = "transient",
+	.module = THIS_MODULE,
+	.ctr = transient_ctr,
+	.dtr = transient_dtr,
+	.read_metadata = transient_read_metadata,
+	.prepare_exception = transient_prepare_exception,
+	.commit_exception = transient_commit_exception,
+	.usage = transient_usage,
+	.status = transient_status,
+};
+
+static struct dm_exception_store_type _transient_compat_type = {
+	.name = "N",
+	.module = THIS_MODULE,
+	.ctr = transient_ctr,
+	.dtr = transient_dtr,
+	.read_metadata = transient_read_metadata,
+	.prepare_exception = transient_prepare_exception,
+	.commit_exception = transient_commit_exception,
+	.usage = transient_usage,
+	.status = transient_status,
+};
+
+int dm_transient_snapshot_init(void)
+{
+	int r;
+
+	r = dm_exception_store_type_register(&_transient_type);
+	if (r) {
+		DMWARN("Unable to register transient exception store type");
+		return r;
+	}
+
+	r = dm_exception_store_type_register(&_transient_compat_type);
+	if (r) {
+		DMWARN("Unable to register old-style transient exception store type");
+		dm_exception_store_type_unregister(&_transient_type);
+		return r;
+	}
+
+	return r;
+}
+
+void dm_transient_snapshot_exit(void)
+{
+	dm_exception_store_type_unregister(&_transient_type);
+	dm_exception_store_type_unregister(&_transient_compat_type);
+}