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/samples/damon/prcl.c b/samples/damon/prcl.c
new file mode 100644
index 000000000..842099bd6
--- /dev/null
+++ b/samples/damon/prcl.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proactive reclamation: monitor access pattern of a given process, find
+ * regions that seems not accessed, and proactively page out the regions.
+ */
+
+#define pr_fmt(fmt) "damon_sample_prcl: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "damon_sample_prcl."
+
+static int target_pid __read_mostly;
+module_param(target_pid, int, 0600);
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops enabled_param_ops = {
+	.set = damon_sample_prcl_enable_store,
+	.get = param_get_bool,
+};
+
+static bool enabled __read_mostly;
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0600);
+MODULE_PARM_DESC(enabled, "Enable or disable DAMON_SAMPLE_PRCL");
+
+static struct damon_ctx *ctx;
+static struct pid *target_pidp;
+
+static int damon_sample_prcl_repeat_call_fn(void *data)
+{
+	struct damon_ctx *c = data;
+	struct damon_target *t;
+
+	damon_for_each_target(t, c) {
+		struct damon_region *r;
+		unsigned long wss = 0;
+
+		damon_for_each_region(r, t) {
+			if (r->nr_accesses > 0)
+				wss += r->ar.end - r->ar.start;
+		}
+		pr_info("wss: %lu\n", wss);
+	}
+	return 0;
+}
+
+static struct damon_call_control repeat_call_control = {
+	.fn = damon_sample_prcl_repeat_call_fn,
+	.repeat = true,
+};
+
+static int damon_sample_prcl_start(void)
+{
+	struct damon_target *target;
+	struct damos *scheme;
+	int err;
+
+	pr_info("start\n");
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+	if (damon_select_ops(ctx, DAMON_OPS_VADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+	target_pidp = find_get_pid(target_pid);
+	if (!target_pidp) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+	target->pid = target_pidp;
+
+	scheme = damon_new_scheme(
+			&(struct damos_access_pattern) {
+			.min_sz_region = PAGE_SIZE,
+			.max_sz_region = ULONG_MAX,
+			.min_nr_accesses = 0,
+			.max_nr_accesses = 0,
+			.min_age_region = 50,
+			.max_age_region = UINT_MAX},
+			DAMOS_PAGEOUT,
+			0,
+			&(struct damos_quota){},
+			&(struct damos_watermarks){},
+			NUMA_NO_NODE);
+	if (!scheme) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_set_schemes(ctx, &scheme, 1);
+
+	err = damon_start(&ctx, 1, true);
+	if (err) {
+		damon_destroy_ctx(ctx);
+		return err;
+	}
+
+	repeat_call_control.data = ctx;
+	err = damon_call(ctx, &repeat_call_control);
+	if (err)
+		damon_destroy_ctx(ctx);
+	return err;
+}
+
+static void damon_sample_prcl_stop(void)
+{
+	pr_info("stop\n");
+	if (ctx) {
+		damon_stop(&ctx, 1);
+		damon_destroy_ctx(ctx);
+	}
+}
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp)
+{
+	bool is_enabled = enabled;
+	int err;
+
+	err = kstrtobool(val, &enabled);
+	if (err)
+		return err;
+
+	if (enabled == is_enabled)
+		return 0;
+
+	if (!damon_initialized())
+		return 0;
+
+	if (enabled) {
+		err = damon_sample_prcl_start();
+		if (err)
+			enabled = false;
+		return err;
+	}
+	damon_sample_prcl_stop();
+	return 0;
+}
+
+static int __init damon_sample_prcl_init(void)
+{
+	int err = 0;
+
+	if (!damon_initialized()) {
+		if (enabled)
+			enabled = false;
+		return -ENOMEM;
+	}
+
+	if (enabled) {
+		err = damon_sample_prcl_start();
+		if (err)
+			enabled = false;
+	}
+	return 0;
+}
+
+module_init(damon_sample_prcl_init);