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, 201 insertions, 0 deletions

diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
new file mode 100644
index 000000000..bc275968f
--- /dev/null
+++ b/drivers/ssb/driver_extif.c
@@ -0,0 +1,201 @@
+/*
+ * Sonics Silicon Backplane
+ * Broadcom EXTIF core driver
+ *
+ * Copyright 2005, Broadcom Corporation
+ * Copyright 2006, 2007, Michael Buesch <m@bues.ch>
+ * Copyright 2006, 2007, Felix Fietkau <nbd@openwrt.org>
+ * Copyright 2007, Aurelien Jarno <aurelien@aurel32.net>
+ *
+ * Licensed under the GNU/GPL. See COPYING for details.
+ */
+
+#include "ssb_private.h"
+
+#include <linux/serial.h>
+#include <linux/serial_core.h>
+#include <linux/serial_reg.h>
+
+
+static inline u32 extif_read32(struct ssb_extif *extif, u16 offset)
+{
+	return ssb_read32(extif->dev, offset);
+}
+
+static inline void extif_write32(struct ssb_extif *extif, u16 offset, u32 value)
+{
+	ssb_write32(extif->dev, offset, value);
+}
+
+static inline u32 extif_write32_masked(struct ssb_extif *extif, u16 offset,
+				       u32 mask, u32 value)
+{
+	value &= mask;
+	value |= extif_read32(extif, offset) & ~mask;
+	extif_write32(extif, offset, value);
+
+	return value;
+}
+
+#ifdef CONFIG_SSB_SERIAL
+static bool serial_exists(u8 *regs)
+{
+	u8 save_mcr, msr = 0;
+
+	if (regs) {
+		save_mcr = regs[UART_MCR];
+		regs[UART_MCR] = (UART_MCR_LOOP | UART_MCR_OUT2 | UART_MCR_RTS);
+		msr = regs[UART_MSR] & (UART_MSR_DCD | UART_MSR_RI
+					| UART_MSR_CTS | UART_MSR_DSR);
+		regs[UART_MCR] = save_mcr;
+	}
+	return (msr == (UART_MSR_DCD | UART_MSR_CTS));
+}
+
+int ssb_extif_serial_init(struct ssb_extif *extif, struct ssb_serial_port *ports)
+{
+	u32 i, nr_ports = 0;
+
+	/* Disable GPIO interrupt initially */
+	extif_write32(extif, SSB_EXTIF_GPIO_INTPOL, 0);
+	extif_write32(extif, SSB_EXTIF_GPIO_INTMASK, 0);
+
+	for (i = 0; i < 2; i++) {
+		void __iomem *uart_regs;
+
+		uart_regs = ioremap(SSB_EUART, 16);
+		if (uart_regs) {
+			uart_regs += (i * 8);
+
+			if (serial_exists(uart_regs) && ports) {
+				extif_write32(extif, SSB_EXTIF_GPIO_INTMASK, 2);
+
+				nr_ports++;
+				ports[i].regs = uart_regs;
+				ports[i].irq = 2;
+				ports[i].baud_base = 13500000;
+				ports[i].reg_shift = 0;
+			}
+			iounmap(uart_regs);
+		}
+	}
+	return nr_ports;
+}
+#endif /* CONFIG_SSB_SERIAL */
+
+void ssb_extif_timing_init(struct ssb_extif *extif, unsigned long ns)
+{
+	u32 tmp;
+
+	/* Initialize extif so we can get to the LEDs and external UART */
+	extif_write32(extif, SSB_EXTIF_PROG_CFG, SSB_EXTCFG_EN);
+
+	/* Set timing for the flash */
+	tmp  = DIV_ROUND_UP(10, ns) << SSB_PROG_WCNT_3_SHIFT;
+	tmp |= DIV_ROUND_UP(40, ns) << SSB_PROG_WCNT_1_SHIFT;
+	tmp |= DIV_ROUND_UP(120, ns);
+	extif_write32(extif, SSB_EXTIF_PROG_WAITCNT, tmp);
+
+	/* Set programmable interface timing for external uart */
+	tmp  = DIV_ROUND_UP(10, ns) << SSB_PROG_WCNT_3_SHIFT;
+	tmp |= DIV_ROUND_UP(20, ns) << SSB_PROG_WCNT_2_SHIFT;
+	tmp |= DIV_ROUND_UP(100, ns) << SSB_PROG_WCNT_1_SHIFT;
+	tmp |= DIV_ROUND_UP(120, ns);
+	extif_write32(extif, SSB_EXTIF_PROG_WAITCNT, tmp);
+}
+
+void ssb_extif_get_clockcontrol(struct ssb_extif *extif,
+				u32 *pll_type, u32 *n, u32 *m)
+{
+	*pll_type = SSB_PLLTYPE_1;
+	*n = extif_read32(extif, SSB_EXTIF_CLOCK_N);
+	*m = extif_read32(extif, SSB_EXTIF_CLOCK_SB);
+}
+
+u32 ssb_extif_watchdog_timer_set_wdt(struct bcm47xx_wdt *wdt, u32 ticks)
+{
+	struct ssb_extif *extif = bcm47xx_wdt_get_drvdata(wdt);
+
+	return ssb_extif_watchdog_timer_set(extif, ticks);
+}
+
+u32 ssb_extif_watchdog_timer_set_ms(struct bcm47xx_wdt *wdt, u32 ms)
+{
+	struct ssb_extif *extif = bcm47xx_wdt_get_drvdata(wdt);
+	u32 ticks = (SSB_EXTIF_WATCHDOG_CLK / 1000) * ms;
+
+	ticks = ssb_extif_watchdog_timer_set(extif, ticks);
+
+	return (ticks * 1000) / SSB_EXTIF_WATCHDOG_CLK;
+}
+
+u32 ssb_extif_watchdog_timer_set(struct ssb_extif *extif, u32 ticks)
+{
+	if (ticks > SSB_EXTIF_WATCHDOG_MAX_TIMER)
+		ticks = SSB_EXTIF_WATCHDOG_MAX_TIMER;
+	extif_write32(extif, SSB_EXTIF_WATCHDOG, ticks);
+
+	return ticks;
+}
+
+void ssb_extif_init(struct ssb_extif *extif)
+{
+	if (!extif->dev)
+		return; /* We don't have a Extif core */
+	spin_lock_init(&extif->gpio_lock);
+}
+
+u32 ssb_extif_gpio_in(struct ssb_extif *extif, u32 mask)
+{
+	return extif_read32(extif, SSB_EXTIF_GPIO_IN) & mask;
+}
+
+u32 ssb_extif_gpio_out(struct ssb_extif *extif, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_OUT(0),
+				   mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
+}
+
+u32 ssb_extif_gpio_outen(struct ssb_extif *extif, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_OUTEN(0),
+				   mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
+}
+
+u32 ssb_extif_gpio_polarity(struct ssb_extif *extif, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_INTPOL, mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
+}
+
+u32 ssb_extif_gpio_intmask(struct ssb_extif *extif, u32 mask, u32 value)
+{
+	unsigned long flags;
+	u32 res = 0;
+
+	spin_lock_irqsave(&extif->gpio_lock, flags);
+	res = extif_write32_masked(extif, SSB_EXTIF_GPIO_INTMASK, mask, value);
+	spin_unlock_irqrestore(&extif->gpio_lock, flags);
+
+	return res;
+}