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, 178 insertions, 0 deletions

diff --git a/lib/kunit/resource.c b/lib/kunit/resource.c
new file mode 100644
index 000000000..45e55238c
--- /dev/null
+++ b/lib/kunit/resource.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit resource API for test managed resources (allocations, etc.).
+ *
+ * Copyright (C) 2022, Google LLC.
+ * Author: Daniel Latypov <dlatypov@google.com>
+ */
+
+#include <kunit/resource.h>
+#include <kunit/test.h>
+#include <linux/kref.h>
+
+/*
+ * Used for static resources and when a kunit_resource * has been created by
+ * kunit_alloc_resource().  When an init function is supplied, @data is passed
+ * into the init function; otherwise, we simply set the resource data field to
+ * the data value passed in. Doesn't initialize res->should_kfree.
+ */
+int __kunit_add_resource(struct kunit *test,
+			 kunit_resource_init_t init,
+			 kunit_resource_free_t free,
+			 struct kunit_resource *res,
+			 void *data)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	res->free = free;
+	kref_init(&res->refcount);
+
+	if (init) {
+		ret = init(res, data);
+		if (ret)
+			return ret;
+	} else {
+		res->data = data;
+	}
+
+	spin_lock_irqsave(&test->lock, flags);
+	list_add_tail(&res->node, &test->resources);
+	/* refcount for list is established by kref_init() */
+	spin_unlock_irqrestore(&test->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__kunit_add_resource);
+
+void kunit_remove_resource(struct kunit *test, struct kunit_resource *res)
+{
+	unsigned long flags;
+	bool was_linked;
+
+	spin_lock_irqsave(&test->lock, flags);
+	was_linked = !list_empty(&res->node);
+	list_del_init(&res->node);
+	spin_unlock_irqrestore(&test->lock, flags);
+
+	if (was_linked)
+		kunit_put_resource(res);
+}
+EXPORT_SYMBOL_GPL(kunit_remove_resource);
+
+int kunit_destroy_resource(struct kunit *test, kunit_resource_match_t match,
+			   void *match_data)
+{
+	struct kunit_resource *res = kunit_find_resource(test, match,
+							 match_data);
+
+	if (!res)
+		return -ENOENT;
+
+	kunit_remove_resource(test, res);
+
+	/* We have a reference also via _find(); drop it. */
+	kunit_put_resource(res);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kunit_destroy_resource);
+
+struct kunit_action_ctx {
+	struct kunit_resource res;
+	kunit_action_t *func;
+	void *ctx;
+};
+
+static void __kunit_action_free(struct kunit_resource *res)
+{
+	struct kunit_action_ctx *action_ctx = container_of(res, struct kunit_action_ctx, res);
+
+	action_ctx->func(action_ctx->ctx);
+}
+
+
+int kunit_add_action(struct kunit *test, void (*action)(void *), void *ctx)
+{
+	struct kunit_action_ctx *action_ctx;
+
+	KUNIT_ASSERT_NOT_NULL_MSG(test, action, "Tried to action a NULL function!");
+
+	action_ctx = kzalloc_obj(*action_ctx);
+	if (!action_ctx)
+		return -ENOMEM;
+
+	action_ctx->func = action;
+	action_ctx->ctx = ctx;
+
+	action_ctx->res.should_kfree = true;
+	/* As init is NULL, this cannot fail. */
+	__kunit_add_resource(test, NULL, __kunit_action_free, &action_ctx->res, action_ctx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kunit_add_action);
+
+int kunit_add_action_or_reset(struct kunit *test, void (*action)(void *),
+			      void *ctx)
+{
+	int res = kunit_add_action(test, action, ctx);
+
+	if (res)
+		action(ctx);
+	return res;
+}
+EXPORT_SYMBOL_GPL(kunit_add_action_or_reset);
+
+static bool __kunit_action_match(struct kunit *test,
+				struct kunit_resource *res, void *match_data)
+{
+	struct kunit_action_ctx *match_ctx = (struct kunit_action_ctx *)match_data;
+	struct kunit_action_ctx *res_ctx = container_of(res, struct kunit_action_ctx, res);
+
+	/* Make sure this is a free function. */
+	if (res->free != __kunit_action_free)
+		return false;
+
+	/* Both the function and context data should match. */
+	return (match_ctx->func == res_ctx->func) && (match_ctx->ctx == res_ctx->ctx);
+}
+
+void kunit_remove_action(struct kunit *test,
+			kunit_action_t *action,
+			void *ctx)
+{
+	struct kunit_action_ctx match_ctx;
+	struct kunit_resource *res;
+
+	match_ctx.func = action;
+	match_ctx.ctx = ctx;
+
+	res = kunit_find_resource(test, __kunit_action_match, &match_ctx);
+	if (res) {
+		/* Remove the free function so we don't run the action. */
+		res->free = NULL;
+		kunit_remove_resource(test, res);
+		kunit_put_resource(res);
+	}
+}
+EXPORT_SYMBOL_GPL(kunit_remove_action);
+
+void kunit_release_action(struct kunit *test,
+			 kunit_action_t *action,
+			 void *ctx)
+{
+	struct kunit_action_ctx match_ctx;
+	struct kunit_resource *res;
+
+	match_ctx.func = action;
+	match_ctx.ctx = ctx;
+
+	res = kunit_find_resource(test, __kunit_action_match, &match_ctx);
+	if (res) {
+		kunit_remove_resource(test, res);
+		/* We have to put() this here, else free won't be called. */
+		kunit_put_resource(res);
+	}
+}
+EXPORT_SYMBOL_GPL(kunit_release_action);