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, 226 insertions, 0 deletions

diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c
new file mode 100644
index 000000000..347bfe954
--- /dev/null
+++ b/drivers/base/regmap/regmap-spmi.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - SPMI support
+//
+// Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
+//
+// Based on regmap-i2c.c:
+// Copyright 2011 Wolfson Microelectronics plc
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+
+#include <linux/regmap.h>
+#include <linux/spmi.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static int regmap_spmi_base_read(void *context,
+				 const void *reg, size_t reg_size,
+				 void *val, size_t val_size)
+{
+	u8 addr = *(u8 *)reg;
+	int err = 0;
+
+	BUG_ON(reg_size != 1);
+
+	while (val_size-- && !err)
+		err = spmi_register_read(context, addr++, val++);
+
+	return err;
+}
+
+static int regmap_spmi_base_gather_write(void *context,
+					 const void *reg, size_t reg_size,
+					 const void *val, size_t val_size)
+{
+	const u8 *data = val;
+	u8 addr = *(u8 *)reg;
+	int err = 0;
+
+	BUG_ON(reg_size != 1);
+
+	/*
+	 * SPMI defines a more bandwidth-efficient 'Register 0 Write' sequence,
+	 * use it when possible.
+	 */
+	if (addr == 0 && val_size) {
+		err = spmi_register_zero_write(context, *data);
+		if (err)
+			goto err_out;
+
+		data++;
+		addr++;
+		val_size--;
+	}
+
+	while (val_size) {
+		err = spmi_register_write(context, addr, *data);
+		if (err)
+			goto err_out;
+
+		data++;
+		addr++;
+		val_size--;
+	}
+
+err_out:
+	return err;
+}
+
+static int regmap_spmi_base_write(void *context, const void *data,
+				  size_t count)
+{
+	BUG_ON(count < 1);
+	return regmap_spmi_base_gather_write(context, data, 1, data + 1,
+					     count - 1);
+}
+
+static const struct regmap_bus regmap_spmi_base = {
+	.read				= regmap_spmi_base_read,
+	.write				= regmap_spmi_base_write,
+	.gather_write			= regmap_spmi_base_gather_write,
+	.reg_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+};
+
+struct regmap *__regmap_init_spmi_base(struct spmi_device *sdev,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name)
+{
+	return __regmap_init(&sdev->dev, &regmap_spmi_base, sdev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_spmi_base);
+
+struct regmap *__devm_regmap_init_spmi_base(struct spmi_device *sdev,
+					    const struct regmap_config *config,
+					    struct lock_class_key *lock_key,
+					    const char *lock_name)
+{
+	return __devm_regmap_init(&sdev->dev, &regmap_spmi_base, sdev, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_spmi_base);
+
+static int regmap_spmi_ext_read(void *context,
+				const void *reg, size_t reg_size,
+				void *val, size_t val_size)
+{
+	int err = 0;
+	size_t len;
+	u16 addr;
+
+	BUG_ON(reg_size != 2);
+
+	addr = *(u16 *)reg;
+
+	/*
+	 * Split accesses into two to take advantage of the more
+	 * bandwidth-efficient 'Extended Register Read' command when possible
+	 */
+	while (addr <= 0xFF && val_size) {
+		len = min_t(size_t, val_size, 16);
+
+		err = spmi_ext_register_read(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+	while (val_size) {
+		len = min_t(size_t, val_size, 8);
+
+		err = spmi_ext_register_readl(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+err_out:
+	return err;
+}
+
+static int regmap_spmi_ext_gather_write(void *context,
+					const void *reg, size_t reg_size,
+					const void *val, size_t val_size)
+{
+	int err = 0;
+	size_t len;
+	u16 addr;
+
+	BUG_ON(reg_size != 2);
+
+	addr = *(u16 *)reg;
+
+	while (addr <= 0xFF && val_size) {
+		len = min_t(size_t, val_size, 16);
+
+		err = spmi_ext_register_write(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+	while (val_size) {
+		len = min_t(size_t, val_size, 8);
+
+		err = spmi_ext_register_writel(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+err_out:
+	return err;
+}
+
+static int regmap_spmi_ext_write(void *context, const void *data,
+				 size_t count)
+{
+	BUG_ON(count < 2);
+	return regmap_spmi_ext_gather_write(context, data, 2, data + 2,
+					    count - 2);
+}
+
+static const struct regmap_bus regmap_spmi_ext = {
+	.read				= regmap_spmi_ext_read,
+	.write				= regmap_spmi_ext_write,
+	.gather_write			= regmap_spmi_ext_gather_write,
+	.reg_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+};
+
+struct regmap *__regmap_init_spmi_ext(struct spmi_device *sdev,
+				      const struct regmap_config *config,
+				      struct lock_class_key *lock_key,
+				      const char *lock_name)
+{
+	return __regmap_init(&sdev->dev, &regmap_spmi_ext, sdev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_spmi_ext);
+
+struct regmap *__devm_regmap_init_spmi_ext(struct spmi_device *sdev,
+					   const struct regmap_config *config,
+					   struct lock_class_key *lock_key,
+					   const char *lock_name)
+{
+	return __devm_regmap_init(&sdev->dev, &regmap_spmi_ext, sdev, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_spmi_ext);
+
+MODULE_DESCRIPTION("Register map access API - SPMI support");
+MODULE_LICENSE("GPL");