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, 175 insertions, 0 deletions

diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c
new file mode 100644
index 000000000..be8497fd2
--- /dev/null
+++ b/drivers/base/regmap/regcache-flat.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register cache access API - flat caching support
+//
+// Copyright 2012 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/limits.h>
+#include <linux/overflow.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+static inline unsigned int regcache_flat_get_index(const struct regmap *map,
+						   unsigned int reg)
+{
+	return regcache_get_index_by_order(map, reg);
+}
+
+struct regcache_flat_data {
+	unsigned long *valid;
+	unsigned int data[];
+};
+
+static int regcache_flat_init(struct regmap *map)
+{
+	unsigned int cache_size;
+	struct regcache_flat_data *cache;
+
+	if (!map || map->reg_stride_order < 0 || !map->max_register_is_set)
+		return -EINVAL;
+
+	cache_size = regcache_flat_get_index(map, map->max_register) + 1;
+	cache = kzalloc_flex(*cache, data, cache_size, map->alloc_flags);
+	if (!cache)
+		return -ENOMEM;
+
+	cache->valid = bitmap_zalloc(cache_size, map->alloc_flags);
+	if (!cache->valid)
+		goto err_free;
+
+	map->cache = cache;
+
+	return 0;
+
+err_free:
+	kfree(cache);
+	return -ENOMEM;
+}
+
+static void regcache_flat_exit(struct regmap *map)
+{
+	struct regcache_flat_data *cache = map->cache;
+
+	if (cache)
+		bitmap_free(cache->valid);
+
+	kfree(cache);
+	map->cache = NULL;
+}
+
+static int regcache_flat_populate(struct regmap *map)
+{
+	struct regcache_flat_data *cache = map->cache;
+	unsigned int i;
+
+	for (i = 0; i < map->num_reg_defaults; i++) {
+		unsigned int reg = map->reg_defaults[i].reg;
+		unsigned int index = regcache_flat_get_index(map, reg);
+
+		cache->data[index] = map->reg_defaults[i].def;
+		__set_bit(index, cache->valid);
+	}
+
+	if (map->reg_default_cb) {
+		dev_dbg(map->dev,
+			"Populating regcache_flat using reg_default_cb callback\n");
+
+		for (i = 0; i <= map->max_register; i += map->reg_stride) {
+			unsigned int index = regcache_flat_get_index(map, i);
+			unsigned int value;
+
+			if (test_bit(index, cache->valid))
+				continue;
+
+			if (map->reg_default_cb(map->dev, i, &value))
+				continue;
+
+			cache->data[index] = value;
+			__set_bit(index, cache->valid);
+		}
+	}
+
+	return 0;
+}
+
+static int regcache_flat_read(struct regmap *map,
+			      unsigned int reg, unsigned int *value)
+{
+	struct regcache_flat_data *cache = map->cache;
+	unsigned int index = regcache_flat_get_index(map, reg);
+
+	/* legacy behavior: ignore validity, but warn the user */
+	if (unlikely(!test_bit(index, cache->valid)))
+		dev_warn_once(map->dev,
+			"using zero-initialized flat cache, this may cause unexpected behavior");
+
+	*value = cache->data[index];
+
+	return 0;
+}
+
+static int regcache_flat_sparse_read(struct regmap *map,
+				     unsigned int reg, unsigned int *value)
+{
+	struct regcache_flat_data *cache = map->cache;
+	unsigned int index = regcache_flat_get_index(map, reg);
+
+	if (unlikely(!test_bit(index, cache->valid)))
+		return -ENOENT;
+
+	*value = cache->data[index];
+
+	return 0;
+}
+
+static int regcache_flat_write(struct regmap *map, unsigned int reg,
+			       unsigned int value)
+{
+	struct regcache_flat_data *cache = map->cache;
+	unsigned int index = regcache_flat_get_index(map, reg);
+
+	cache->data[index] = value;
+	__set_bit(index, cache->valid);
+
+	return 0;
+}
+
+static int regcache_flat_drop(struct regmap *map, unsigned int min,
+			      unsigned int max)
+{
+	struct regcache_flat_data *cache = map->cache;
+	unsigned int bitmap_min = regcache_flat_get_index(map, min);
+	unsigned int bitmap_max = regcache_flat_get_index(map, max);
+
+	bitmap_clear(cache->valid, bitmap_min, bitmap_max + 1 - bitmap_min);
+
+	return 0;
+}
+
+struct regcache_ops regcache_flat_ops = {
+	.type = REGCACHE_FLAT,
+	.name = "flat",
+	.init = regcache_flat_init,
+	.exit = regcache_flat_exit,
+	.populate = regcache_flat_populate,
+	.read = regcache_flat_read,
+	.write = regcache_flat_write,
+};
+
+struct regcache_ops regcache_flat_sparse_ops = {
+	.type = REGCACHE_FLAT_S,
+	.name = "flat-sparse",
+	.init = regcache_flat_init,
+	.exit = regcache_flat_exit,
+	.populate = regcache_flat_populate,
+	.read = regcache_flat_sparse_read,
+	.write = regcache_flat_write,
+	.drop = regcache_flat_drop,
+};