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, 91 insertions, 0 deletions

diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
new file mode 100644
index 000000000..163aadd58
--- /dev/null
+++ b/drivers/soc/ti/Kconfig
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+#
+# TI SOC drivers
+#
+menuconfig SOC_TI
+	bool "TI SOC drivers support"
+
+if SOC_TI
+
+config KEYSTONE_NAVIGATOR_QMSS
+	tristate "Keystone Queue Manager Sub System"
+	depends on ARCH_KEYSTONE
+	help
+	  Say y here to support the Keystone multicore Navigator Queue
+	  Manager support. The Queue Manager is a hardware module that
+	  is responsible for accelerating management of the packet queues.
+	  Packets are queued/de-queued by writing/reading descriptor address
+	  to a particular memory mapped location in the Queue Manager module.
+
+	  If unsure, say N.
+
+config KEYSTONE_NAVIGATOR_DMA
+	tristate "TI Keystone Navigator Packet DMA support"
+	depends on ARCH_KEYSTONE
+	help
+	  Say y tp enable support for the Keystone Navigator Packet DMA on
+	  on Keystone family of devices. It sets up the dma channels for the
+	  Queue Manager Sub System.
+
+	  If unsure, say N.
+
+config AMX3_PM
+	tristate "AMx3 Power Management"
+	depends on SOC_AM33XX || SOC_AM43XX
+	depends on WKUP_M3_IPC && TI_EMIF_SRAM && SRAM && RTC_DRV_OMAP
+	help
+	  Enable power management on AM335x and AM437x. Required for suspend to mem
+	  and standby states on both AM335x and AM437x platforms and for deeper cpuidle
+	  c-states on AM335x. Also required for rtc and ddr in self-refresh low
+	  power mode on AM437x platforms.
+
+config WKUP_M3_IPC
+	tristate "TI AMx3 Wkup-M3 IPC Driver"
+	depends on WKUP_M3_RPROC
+	depends on OMAP2PLUS_MBOX
+	help
+	  TI AM33XX and AM43XX have a Cortex M3, the Wakeup M3, to handle
+	  low power transitions. This IPC driver provides the necessary API
+	  to communicate and use the Wakeup M3 for PM features like suspend
+	  resume and boots it using wkup_m3_rproc driver.
+
+config TI_K3_RINGACC
+	tristate "K3 Ring accelerator Sub System"
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_SCI_INTA_IRQCHIP
+	help
+	  Say y here to support the K3 Ring accelerator module.
+	  The Ring Accelerator (RINGACC or RA)  provides hardware acceleration
+	  to enable straightforward passing of work between a producer
+	  and a consumer. There is one RINGACC module per NAVSS on TI AM65x SoCs
+	  If unsure, say N.
+
+config TI_K3_SOCINFO
+	bool "K3 SoC Information driver" if COMPILE_TEST
+	depends on ARCH_K3 || COMPILE_TEST
+	select SOC_BUS
+	select MFD_SYSCON
+	help
+	  Include support for the SoC bus socinfo for the TI K3 Multicore SoC
+	  platforms to provide information about the SoC family and
+	  variant to user space.
+
+config TI_PRUSS
+	tristate "TI PRU-ICSS Subsystem Platform drivers"
+	depends on SOC_AM33XX || SOC_AM43XX || SOC_DRA7XX || ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST
+	select MFD_SYSCON
+	help
+	  TI PRU-ICSS Subsystem platform specific support.
+
+	  Say Y or M here to support the Programmable Realtime Unit (PRU)
+	  processors on various TI SoCs. It's safe to say N here if you're
+	  not interested in the PRU or if you are unsure.
+
+endif # SOC_TI
+
+config TI_SCI_INTA_MSI_DOMAIN
+	bool
+	select GENERIC_MSI_IRQ
+	help
+	  Driver to enable Interrupt Aggregator specific MSI Domain.