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, 95 insertions, 0 deletions

diff --git a/arch/powerpc/boot/ppcboot.h b/arch/powerpc/boot/ppcboot.h
new file mode 100644
index 000000000..90c8f452f
--- /dev/null
+++ b/arch/powerpc/boot/ppcboot.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This interface is used for compatibility with old U-boots *ONLY*.
+ * Please do not imitate or extend this.
+ */
+
+/*
+ * (C) Copyright 2000, 2001
+ * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
+ */
+
+#ifndef __PPCBOOT_H__
+#define __PPCBOOT_H__
+
+/*
+ * Board information passed to kernel from PPCBoot
+ *
+ * include/asm-ppc/ppcboot.h
+ */
+
+#include "types.h"
+
+typedef struct bd_info {
+	unsigned long	bi_memstart;	/* start of DRAM memory */
+	unsigned long	bi_memsize;	/* size	 of DRAM memory in bytes */
+	unsigned long	bi_flashstart;	/* start of FLASH memory */
+	unsigned long	bi_flashsize;	/* size	 of FLASH memory */
+	unsigned long	bi_flashoffset; /* reserved area for startup monitor */
+	unsigned long	bi_sramstart;	/* start of SRAM memory */
+	unsigned long	bi_sramsize;	/* size	 of SRAM memory */
+#if defined(TARGET_8xx) || defined(TARGET_CPM2) || defined(TARGET_85xx) ||\
+	defined(TARGET_83xx) || defined(TARGET_86xx)
+	unsigned long	bi_immr_base;	/* base of IMMR register */
+#endif
+#if defined(TARGET_PPC_MPC52xx)
+	unsigned long   bi_mbar_base;   /* base of internal registers */
+#endif
+	unsigned long	bi_bootflags;	/* boot / reboot flag (for LynxOS) */
+	unsigned long	bi_ip_addr;	/* IP Address */
+	unsigned char	bi_enetaddr[6];	/* Ethernet address */
+	unsigned short	bi_ethspeed;	/* Ethernet speed in Mbps */
+	unsigned long	bi_intfreq;	/* Internal Freq, in MHz */
+	unsigned long	bi_busfreq;	/* Bus Freq, in MHz */
+#if defined(TARGET_CPM2)
+	unsigned long	bi_cpmfreq;	/* CPM_CLK Freq, in MHz */
+	unsigned long	bi_brgfreq;	/* BRG_CLK Freq, in MHz */
+	unsigned long	bi_sccfreq;	/* SCC_CLK Freq, in MHz */
+	unsigned long	bi_vco;		/* VCO Out from PLL, in MHz */
+#endif
+#if defined(TARGET_PPC_MPC52xx)
+	unsigned long   bi_ipbfreq;     /* IPB Bus Freq, in MHz */
+	unsigned long   bi_pcifreq;     /* PCI Bus Freq, in MHz */
+#endif
+	unsigned long	bi_baudrate;	/* Console Baudrate */
+#if defined(TARGET_4xx)
+	unsigned char	bi_s_version[4];	/* Version of this structure */
+	unsigned char	bi_r_version[32];	/* Version of the ROM (IBM) */
+	unsigned int	bi_procfreq;	/* CPU (Internal) Freq, in Hz */
+	unsigned int	bi_plb_busfreq;	/* PLB Bus speed, in Hz */
+	unsigned int	bi_pci_busfreq;	/* PCI Bus speed, in Hz */
+	unsigned char	bi_pci_enetaddr[6];	/* PCI Ethernet MAC address */
+#endif
+#if defined(TARGET_HYMOD)
+	hymod_conf_t	bi_hymod_conf;	/* hymod configuration information */
+#endif
+#if defined(TARGET_EVB64260) || defined(TARGET_44x) || \
+	defined(TARGET_85xx) ||	defined(TARGET_83xx) || defined(TARGET_HAS_ETH1)
+	/* second onboard ethernet port */
+	unsigned char	bi_enet1addr[6];
+#define HAVE_ENET1ADDR
+#endif
+#if defined(TARGET_EVB64260) || defined(TARGET_440GX) || \
+    defined(TARGET_85xx) || defined(TARGET_HAS_ETH2)
+	/* third onboard ethernet ports */
+	unsigned char	bi_enet2addr[6];
+#define HAVE_ENET2ADDR
+#endif
+#if defined(TARGET_440GX) || defined(TARGET_HAS_ETH3)
+	/* fourth onboard ethernet ports */
+	unsigned char	bi_enet3addr[6];
+#define HAVE_ENET3ADDR
+#endif
+#if defined(TARGET_4xx)
+	unsigned int	bi_opbfreq;		/* OB clock in Hz */
+	int		bi_iic_fast[2];		/* Use fast i2c mode */
+#endif
+#if defined(TARGET_440GX)
+	int		bi_phynum[4];		/* phy mapping */
+	int		bi_phymode[4];		/* phy mode */
+#endif
+} bd_t;
+
+#define bi_tbfreq	bi_intfreq
+
+#endif	/* __PPCBOOT_H__ */