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, 178 insertions, 0 deletions

diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
new file mode 100644
index 000000000..81529084b
--- /dev/null
+++ b/arch/mips/bcm63xx/setup.c
@@ -0,0 +1,178 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2008 Maxime Bizon <mbizon@freebox.fr>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/memblock.h>
+#include <linux/ioport.h>
+#include <linux/pm.h>
+#include <asm/bmips.h>
+#include <asm/bootinfo.h>
+#include <asm/time.h>
+#include <asm/reboot.h>
+#include <asm/cacheflush.h>
+#include <bcm63xx_board.h>
+#include <bcm63xx_cpu.h>
+#include <bcm63xx_regs.h>
+#include <bcm63xx_io.h>
+#include <bcm63xx_gpio.h>
+
+/*
+ * CBR addr doesn't change and we can cache it.
+ * For broken SoC/Bootloader CBR addr might also be provided via DT
+ * with "brcm,bmips-cbr-reg" in the "cpus" node.
+ */
+void __iomem *bmips_cbr_addr __read_mostly;
+
+void bcm63xx_machine_halt(void)
+{
+	pr_info("System halted\n");
+	while (1)
+		;
+}
+
+static void bcm6348_a1_reboot(void)
+{
+	u32 reg;
+
+	/* soft reset all blocks */
+	pr_info("soft-resetting all blocks ...\n");
+	reg = bcm_perf_readl(PERF_SOFTRESET_REG);
+	reg &= ~SOFTRESET_6348_ALL;
+	bcm_perf_writel(reg, PERF_SOFTRESET_REG);
+	mdelay(10);
+
+	reg = bcm_perf_readl(PERF_SOFTRESET_REG);
+	reg |= SOFTRESET_6348_ALL;
+	bcm_perf_writel(reg, PERF_SOFTRESET_REG);
+	mdelay(10);
+
+	/* Jump to the power on address. */
+	pr_info("jumping to reset vector.\n");
+	/* set high vectors (base at 0xbfc00000 */
+	set_c0_status(ST0_BEV | ST0_ERL);
+	/* run uncached in kseg0 */
+	change_c0_config(CONF_CM_CMASK, CONF_CM_UNCACHED);
+	__flush_cache_all();
+	/* remove all wired TLB entries */
+	write_c0_wired(0);
+	__asm__ __volatile__(
+		"jr\t%0"
+		:
+		: "r" (0xbfc00000));
+	while (1)
+		;
+}
+
+void bcm63xx_machine_reboot(void)
+{
+	u32 reg, perf_regs[2] = { 0, 0 };
+	unsigned int i;
+
+	/* mask and clear all external irq */
+	switch (bcm63xx_get_cpu_id()) {
+	case BCM3368_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_3368;
+		break;
+	case BCM6328_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6328;
+		break;
+	case BCM6338_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6338;
+		break;
+	case BCM6345_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6345;
+		break;
+	case BCM6348_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6348;
+		break;
+	case BCM6358_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6358;
+		break;
+	case BCM6362_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6362;
+		break;
+	}
+
+	for (i = 0; i < 2; i++) {
+		if (!perf_regs[i])
+			break;
+
+		reg = bcm_perf_readl(perf_regs[i]);
+		if (BCMCPU_IS_6348()) {
+			reg &= ~EXTIRQ_CFG_MASK_ALL_6348;
+			reg |= EXTIRQ_CFG_CLEAR_ALL_6348;
+		} else {
+			reg &= ~EXTIRQ_CFG_MASK_ALL;
+			reg |= EXTIRQ_CFG_CLEAR_ALL;
+		}
+		bcm_perf_writel(reg, perf_regs[i]);
+	}
+
+	if (BCMCPU_IS_6348() && (bcm63xx_get_cpu_rev() == 0xa1))
+		bcm6348_a1_reboot();
+
+	pr_info("triggering watchdog soft-reset...\n");
+	if (BCMCPU_IS_6328()) {
+		bcm_wdt_writel(1, WDT_SOFTRESET_REG);
+	} else {
+		reg = bcm_perf_readl(PERF_SYS_PLL_CTL_REG);
+		reg |= SYS_PLL_SOFT_RESET;
+		bcm_perf_writel(reg, PERF_SYS_PLL_CTL_REG);
+	}
+	while (1)
+		;
+}
+
+static void __bcm63xx_machine_reboot(char *p)
+{
+	bcm63xx_machine_reboot();
+}
+
+/*
+ * return system type in /proc/cpuinfo
+ */
+const char *get_system_type(void)
+{
+	static char buf[128];
+	snprintf(buf, sizeof(buf), "bcm63xx/%s (0x%04x/0x%02X)",
+		 board_get_name(),
+		 bcm63xx_get_cpu_id(), bcm63xx_get_cpu_rev());
+	return buf;
+}
+
+void __init plat_time_init(void)
+{
+	mips_hpt_frequency = bcm63xx_get_cpu_freq() / 2;
+}
+
+void __init plat_mem_setup(void)
+{
+	memblock_add(0, bcm63xx_get_memory_size());
+
+	_machine_halt = bcm63xx_machine_halt;
+	_machine_restart = __bcm63xx_machine_reboot;
+	pm_power_off = bcm63xx_machine_halt;
+
+	set_io_port_base(0);
+	ioport_resource.start = 0;
+	ioport_resource.end = ~0;
+
+	board_setup();
+}
+
+static int __init bcm63xx_register_devices(void)
+{
+	/* register gpiochip */
+	bcm63xx_gpio_init();
+
+	return board_register_devices();
+}
+
+arch_initcall(bcm63xx_register_devices);