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, 174 insertions, 0 deletions

diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c
new file mode 100644
index 000000000..9330d5748
--- /dev/null
+++ b/drivers/md/dm-cache-policy.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-cache-policy-internal.h"
+#include "dm.h"
+
+#include <linux/module.h>
+#include <linux/slab.h>
+
+/*----------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX "cache-policy"
+
+static DEFINE_SPINLOCK(register_lock);
+static LIST_HEAD(register_list);
+
+static struct dm_cache_policy_type *__find_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	list_for_each_entry(t, &register_list, list)
+		if (!strcmp(t->name, name))
+			return t;
+
+	return NULL;
+}
+
+static struct dm_cache_policy_type *__get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t = __find_policy(name);
+
+	if (t && !try_module_get(t->owner)) {
+		DMWARN("couldn't get module %s", name);
+		t = ERR_PTR(-EINVAL);
+	}
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy_once(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	spin_lock(&register_lock);
+	t = __get_policy_once(name);
+	spin_unlock(&register_lock);
+
+	return t;
+}
+
+static struct dm_cache_policy_type *get_policy(const char *name)
+{
+	struct dm_cache_policy_type *t;
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	if (t)
+		return t;
+
+	request_module("dm-cache-%s", name);
+
+	t = get_policy_once(name);
+	if (IS_ERR(t))
+		return NULL;
+
+	return t;
+}
+
+static void put_policy(struct dm_cache_policy_type *t)
+{
+	module_put(t->owner);
+}
+
+int dm_cache_policy_register(struct dm_cache_policy_type *type)
+{
+	int r;
+
+	/* One size fits all for now */
+	if (type->hint_size != 0 && type->hint_size != 4) {
+		DMWARN("hint size must be 0 or 4 but %llu supplied.", (unsigned long long) type->hint_size);
+		return -EINVAL;
+	}
+
+	spin_lock(&register_lock);
+	if (__find_policy(type->name)) {
+		DMWARN("attempt to register policy under duplicate name %s", type->name);
+		r = -EINVAL;
+	} else {
+		list_add(&type->list, &register_list);
+		r = 0;
+	}
+	spin_unlock(&register_lock);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_register);
+
+void dm_cache_policy_unregister(struct dm_cache_policy_type *type)
+{
+	spin_lock(&register_lock);
+	list_del_init(&type->list);
+	spin_unlock(&register_lock);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_unregister);
+
+struct dm_cache_policy *dm_cache_policy_create(const char *name,
+					       dm_cblock_t cache_size,
+					       sector_t origin_size,
+					       sector_t cache_block_size)
+{
+	struct dm_cache_policy *p = NULL;
+	struct dm_cache_policy_type *type;
+
+	type = get_policy(name);
+	if (!type) {
+		DMWARN("unknown policy type");
+		return ERR_PTR(-EINVAL);
+	}
+
+	p = type->create(cache_size, origin_size, cache_block_size);
+	if (!p) {
+		put_policy(type);
+		return ERR_PTR(-ENOMEM);
+	}
+	p->private = type;
+
+	return p;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_create);
+
+void dm_cache_policy_destroy(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	p->destroy(p);
+	put_policy(t);
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_destroy);
+
+const char *dm_cache_policy_get_name(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	/* if t->real is set then an alias was used (e.g. "default") */
+	if (t->real)
+		return t->real->name;
+
+	return t->name;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_name);
+
+const unsigned int *dm_cache_policy_get_version(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->version;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_version);
+
+size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p)
+{
+	struct dm_cache_policy_type *t = p->private;
+
+	return t->hint_size;
+}
+EXPORT_SYMBOL_GPL(dm_cache_policy_get_hint_size);
+
+/*----------------------------------------------------------------*/