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, 125 insertions, 0 deletions

diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h
new file mode 100644
index 000000000..0f2a16d7a
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc.h
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: Zlib
+#ifndef DFLTCC_H
+#define DFLTCC_H
+
+#include "../zlib_deflate/defutil.h"
+#include <asm/facility.h>
+#include <asm/setup.h>
+
+/*
+ * Tuning parameters.
+ */
+#define DFLTCC_LEVEL_MASK 0x2 /* DFLTCC compression for level 1 only */
+#define DFLTCC_LEVEL_MASK_DEBUG 0x3fe /* DFLTCC compression for all levels */
+#define DFLTCC_BLOCK_SIZE 1048576
+#define DFLTCC_FIRST_FHT_BLOCK_SIZE 4096
+#define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096
+#define DFLTCC_RIBM 0
+
+#define DFLTCC_FACILITY 151
+
+/*
+ * Parameter Block for Query Available Functions.
+ */
+struct dfltcc_qaf_param {
+    char fns[16];
+    char reserved1[8];
+    char fmts[2];
+    char reserved2[6];
+};
+
+static_assert(sizeof(struct dfltcc_qaf_param) == 32);
+
+#define DFLTCC_FMT0 0
+
+/*
+ * Parameter Block for Generate Dynamic-Huffman Table, Compress and Expand.
+ */
+struct dfltcc_param_v0 {
+    uint16_t pbvn;                     /* Parameter-Block-Version Number */
+    uint8_t mvn;                       /* Model-Version Number */
+    uint8_t ribm;                      /* Reserved for IBM use */
+    unsigned reserved32 : 31;
+    unsigned cf : 1;                   /* Continuation Flag */
+    uint8_t reserved64[8];
+    unsigned nt : 1;                   /* New Task */
+    unsigned reserved129 : 1;
+    unsigned cvt : 1;                  /* Check Value Type */
+    unsigned reserved131 : 1;
+    unsigned htt : 1;                  /* Huffman-Table Type */
+    unsigned bcf : 1;                  /* Block-Continuation Flag */
+    unsigned bcc : 1;                  /* Block Closing Control */
+    unsigned bhf : 1;                  /* Block Header Final */
+    unsigned reserved136 : 1;
+    unsigned reserved137 : 1;
+    unsigned dhtgc : 1;                /* DHT Generation Control */
+    unsigned reserved139 : 5;
+    unsigned reserved144 : 5;
+    unsigned sbb : 3;                  /* Sub-Byte Boundary */
+    uint8_t oesc;                      /* Operation-Ending-Supplemental Code */
+    unsigned reserved160 : 12;
+    unsigned ifs : 4;                  /* Incomplete-Function Status */
+    uint16_t ifl;                      /* Incomplete-Function Length */
+    uint8_t reserved192[8];
+    uint8_t reserved256[8];
+    uint8_t reserved320[4];
+    uint16_t hl;                       /* History Length */
+    unsigned reserved368 : 1;
+    uint16_t ho : 15;                  /* History Offset */
+    uint32_t cv;                       /* Check Value */
+    unsigned eobs : 15;                /* End-of-block Symbol */
+    unsigned reserved431: 1;
+    uint8_t eobl : 4;                  /* End-of-block Length */
+    unsigned reserved436 : 12;
+    unsigned reserved448 : 4;
+    uint16_t cdhtl : 12;               /* Compressed-Dynamic-Huffman Table
+                                          Length */
+    uint8_t reserved464[6];
+    uint8_t cdht[288];
+    uint8_t reserved[32];
+    uint8_t csb[1152];
+};
+
+static_assert(offsetof(struct dfltcc_param_v0, csb) == 384);
+static_assert(sizeof(struct dfltcc_param_v0) == 1536);
+
+#define CVT_CRC32 0
+#define CVT_ADLER32 1
+#define HTT_FIXED 0
+#define HTT_DYNAMIC 1
+
+/*
+ *  Extension of inflate_state and deflate_state for DFLTCC.
+ */
+struct dfltcc_state {
+    struct dfltcc_param_v0 param;      /* Parameter block */
+    struct dfltcc_qaf_param af;        /* Available functions */
+    char msg[64];                      /* Buffer for strm->msg */
+};
+
+/*
+ *  Extension of inflate_state and deflate_state for DFLTCC.
+ */
+struct dfltcc_deflate_state {
+    struct dfltcc_state common;        /* Parameter block */
+    uLong level_mask;                  /* Levels on which to use DFLTCC */
+    uLong block_size;                  /* New block each X bytes */
+    uLong block_threshold;             /* New block after total_in > X */
+    uLong dht_threshold;               /* New block only if avail_in >= X */
+};
+
+#define ALIGN_UP(p, size) (__typeof__(p))(((uintptr_t)(p) + ((size) - 1)) & ~((size) - 1))
+/* Resides right after inflate_state or deflate_state */
+#define GET_DFLTCC_STATE(state) ((struct dfltcc_state *)((char *)(state) + ALIGN_UP(sizeof(*state), 8)))
+
+void dfltcc_reset_state(struct dfltcc_state *dfltcc_state);
+
+static inline int is_dfltcc_enabled(void)
+{
+return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED &&
+        test_facility(DFLTCC_FACILITY));
+}
+
+#define DEFLATE_DFLTCC_ENABLED() is_dfltcc_enabled()
+
+#endif /* DFLTCC_H */