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, 149 insertions, 0 deletions

diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
new file mode 100644
index 000000000..137abbc65
--- /dev/null
+++ b/arch/mips/ath79/common.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Atheros AR71XX/AR724X/AR913X common routines
+ *
+ *  Copyright (C) 2010-2011 Jaiganesh Narayanan <jnarayanan@atheros.com>
+ *  Copyright (C) 2008-2011 Gabor Juhos <juhosg@openwrt.org>
+ *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
+#include <asm/mach-ath79/ath79.h>
+#include <asm/mach-ath79/ar71xx_regs.h>
+#include "common.h"
+
+static DEFINE_SPINLOCK(ath79_device_reset_lock);
+
+u32 ath79_cpu_freq;
+EXPORT_SYMBOL_GPL(ath79_cpu_freq);
+
+u32 ath79_ahb_freq;
+EXPORT_SYMBOL_GPL(ath79_ahb_freq);
+
+u32 ath79_ddr_freq;
+EXPORT_SYMBOL_GPL(ath79_ddr_freq);
+
+enum ath79_soc_type ath79_soc;
+unsigned int ath79_soc_rev;
+
+void __iomem *ath79_pll_base;
+void __iomem *ath79_reset_base;
+EXPORT_SYMBOL_GPL(ath79_reset_base);
+static void __iomem *ath79_ddr_base;
+static void __iomem *ath79_ddr_wb_flush_base;
+static void __iomem *ath79_ddr_pci_win_base;
+
+void ath79_ddr_ctrl_init(void)
+{
+	ath79_ddr_base = ioremap(AR71XX_DDR_CTRL_BASE,
+					 AR71XX_DDR_CTRL_SIZE);
+	if (soc_is_ar913x() || soc_is_ar724x() || soc_is_ar933x()) {
+		ath79_ddr_wb_flush_base = ath79_ddr_base + 0x7c;
+		ath79_ddr_pci_win_base = 0;
+	} else {
+		ath79_ddr_wb_flush_base = ath79_ddr_base + 0x9c;
+		ath79_ddr_pci_win_base = ath79_ddr_base + 0x7c;
+	}
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
+
+void ath79_ddr_wb_flush(u32 reg)
+{
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
+
+	/* Flush the DDR write buffer. */
+	__raw_writel(0x1, flush_reg);
+	while (__raw_readl(flush_reg) & 0x1)
+		;
+
+	/* It must be run twice. */
+	__raw_writel(0x1, flush_reg);
+	while (__raw_readl(flush_reg) & 0x1)
+		;
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_wb_flush);
+
+void ath79_ddr_set_pci_windows(void)
+{
+	BUG_ON(!ath79_ddr_pci_win_base);
+
+	__raw_writel(AR71XX_PCI_WIN0_OFFS, ath79_ddr_pci_win_base + 0x0);
+	__raw_writel(AR71XX_PCI_WIN1_OFFS, ath79_ddr_pci_win_base + 0x4);
+	__raw_writel(AR71XX_PCI_WIN2_OFFS, ath79_ddr_pci_win_base + 0x8);
+	__raw_writel(AR71XX_PCI_WIN3_OFFS, ath79_ddr_pci_win_base + 0xc);
+	__raw_writel(AR71XX_PCI_WIN4_OFFS, ath79_ddr_pci_win_base + 0x10);
+	__raw_writel(AR71XX_PCI_WIN5_OFFS, ath79_ddr_pci_win_base + 0x14);
+	__raw_writel(AR71XX_PCI_WIN6_OFFS, ath79_ddr_pci_win_base + 0x18);
+	__raw_writel(AR71XX_PCI_WIN7_OFFS, ath79_ddr_pci_win_base + 0x1c);
+}
+EXPORT_SYMBOL_GPL(ath79_ddr_set_pci_windows);
+
+void ath79_device_reset_set(u32 mask)
+{
+	unsigned long flags;
+	u32 reg;
+	u32 t;
+
+	if (soc_is_ar71xx())
+		reg = AR71XX_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar724x())
+		reg = AR724X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar913x())
+		reg = AR913X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar933x())
+		reg = AR933X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar934x())
+		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca955x())
+		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
+	else
+		BUG();
+
+	spin_lock_irqsave(&ath79_device_reset_lock, flags);
+	t = ath79_reset_rr(reg);
+	ath79_reset_wr(reg, t | mask);
+	spin_unlock_irqrestore(&ath79_device_reset_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ath79_device_reset_set);
+
+void ath79_device_reset_clear(u32 mask)
+{
+	unsigned long flags;
+	u32 reg;
+	u32 t;
+
+	if (soc_is_ar71xx())
+		reg = AR71XX_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar724x())
+		reg = AR724X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar913x())
+		reg = AR913X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar933x())
+		reg = AR933X_RESET_REG_RESET_MODULE;
+	else if (soc_is_ar934x())
+		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca955x())
+		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
+	else
+		BUG();
+
+	spin_lock_irqsave(&ath79_device_reset_lock, flags);
+	t = ath79_reset_rr(reg);
+	ath79_reset_wr(reg, t & ~mask);
+	spin_unlock_irqrestore(&ath79_device_reset_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ath79_device_reset_clear);