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, 96 insertions, 0 deletions

diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 000000000..81a0f3f6f
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+#define ZCOMP_PARAM_NOT_SET	INT_MIN
+
+struct deflate_params {
+	s32 winbits;
+};
+
+/*
+ * Immutable driver (backend) parameters. The driver may attach private
+ * data to it (e.g. driver representation of the dictionary, etc.).
+ *
+ * This data is kept per-comp and is shared among execution contexts.
+ */
+struct zcomp_params {
+	void *dict;
+	size_t dict_sz;
+	s32 level;
+	union {
+		struct deflate_params deflate;
+	};
+
+	void *drv_data;
+};
+
+/*
+ * Run-time driver context - scratch buffers, etc. It is modified during
+ * request execution (compression/decompression), cannot be shared, so
+ * it's in per-CPU area.
+ */
+struct zcomp_ctx {
+	void *context;
+};
+
+struct zcomp_strm {
+	struct mutex lock;
+	/* compression buffer */
+	void *buffer;
+	/* local copy of handle memory */
+	void *local_copy;
+	struct zcomp_ctx ctx;
+};
+
+struct zcomp_req {
+	const unsigned char *src;
+	const size_t src_len;
+
+	unsigned char *dst;
+	size_t dst_len;
+};
+
+struct zcomp_ops {
+	int (*compress)(struct zcomp_params *params, struct zcomp_ctx *ctx,
+			struct zcomp_req *req);
+	int (*decompress)(struct zcomp_params *params, struct zcomp_ctx *ctx,
+			  struct zcomp_req *req);
+
+	int (*create_ctx)(struct zcomp_params *params, struct zcomp_ctx *ctx);
+	void (*destroy_ctx)(struct zcomp_ctx *ctx);
+
+	int (*setup_params)(struct zcomp_params *params);
+	void (*release_params)(struct zcomp_params *params);
+
+	const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+	struct zcomp_strm __percpu *stream;
+	const struct zcomp_ops *ops;
+	struct zcomp_params *params;
+	struct hlist_node node;
+};
+
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node);
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
+ssize_t zcomp_available_show(const char *comp, char *buf, ssize_t at);
+const char *zcomp_lookup_backend_name(const char *comp);
+
+struct zcomp *zcomp_create(const char *alg, struct zcomp_params *params);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_stream_get(struct zcomp *comp);
+void zcomp_stream_put(struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		   const void *src, unsigned int *dst_len);
+int zcomp_decompress(struct zcomp *comp, struct zcomp_strm *zstrm,
+		     const void *src, unsigned int src_len, void *dst);
+
+#endif /* _ZCOMP_H_ */