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, 129 insertions, 0 deletions

diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h
new file mode 100644
index 000000000..bba94ce96
--- /dev/null
+++ b/drivers/net/phy/bcm-phy-lib.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ */
+
+#ifndef _LINUX_BCM_PHY_LIB_H
+#define _LINUX_BCM_PHY_LIB_H
+
+#include <linux/brcmphy.h>
+#include <linux/phy.h>
+#include <linux/interrupt.h>
+
+struct ethtool_wolinfo;
+
+/* 28nm only register definitions */
+#define MISC_ADDR(base, channel)	base, channel
+
+#define DSP_TAP10			MISC_ADDR(0x0a, 0)
+#define PLL_PLLCTRL_1			MISC_ADDR(0x32, 1)
+#define PLL_PLLCTRL_2			MISC_ADDR(0x32, 2)
+#define PLL_PLLCTRL_4			MISC_ADDR(0x33, 0)
+
+#define AFE_RXCONFIG_0			MISC_ADDR(0x38, 0)
+#define AFE_RXCONFIG_1			MISC_ADDR(0x38, 1)
+#define AFE_RXCONFIG_2			MISC_ADDR(0x38, 2)
+#define AFE_RX_LP_COUNTER		MISC_ADDR(0x38, 3)
+#define AFE_TX_CONFIG			MISC_ADDR(0x39, 0)
+#define AFE_VDCA_ICTRL_0		MISC_ADDR(0x39, 1)
+#define AFE_VDAC_OTHERS_0		MISC_ADDR(0x39, 3)
+#define AFE_HPF_TRIM_OTHERS		MISC_ADDR(0x3a, 0)
+
+
+int __bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val);
+int __bcm_phy_read_exp(struct phy_device *phydev, u16 reg);
+int __bcm_phy_modify_exp(struct phy_device *phydev, u16 reg, u16 mask, u16 set);
+int bcm_phy_write_exp(struct phy_device *phydev, u16 reg, u16 val);
+int bcm_phy_read_exp(struct phy_device *phydev, u16 reg);
+int bcm_phy_modify_exp(struct phy_device *phydev, u16 reg, u16 mask, u16 set);
+
+static inline int bcm_phy_write_exp_sel(struct phy_device *phydev,
+					u16 reg, u16 val)
+{
+	return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val);
+}
+
+static inline int bcm_phy_read_exp_sel(struct phy_device *phydev, u16 reg)
+{
+	return bcm_phy_read_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER);
+}
+
+int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val);
+int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum);
+
+int bcm_phy_write_misc(struct phy_device *phydev,
+		       u16 reg, u16 chl, u16 value);
+int bcm_phy_read_misc(struct phy_device *phydev,
+		      u16 reg, u16 chl);
+
+int bcm_phy_write_shadow(struct phy_device *phydev, u16 shadow,
+			 u16 val);
+int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow);
+
+int __bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val);
+int bcm_phy_write_rdb(struct phy_device *phydev, u16 rdb, u16 val);
+int __bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb);
+int bcm_phy_read_rdb(struct phy_device *phydev, u16 rdb);
+int __bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask,
+			 u16 set);
+int bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask,
+		       u16 set);
+
+int bcm_phy_ack_intr(struct phy_device *phydev);
+int bcm_phy_config_intr(struct phy_device *phydev);
+irqreturn_t bcm_phy_handle_interrupt(struct phy_device *phydev);
+
+int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down);
+
+int bcm_phy_set_eee(struct phy_device *phydev, bool enable);
+
+int bcm_phy_downshift_get(struct phy_device *phydev, u8 *count);
+
+int bcm_phy_downshift_set(struct phy_device *phydev, u8 count);
+
+int bcm_phy_get_sset_count(struct phy_device *phydev);
+void bcm_phy_get_strings(struct phy_device *phydev, u8 *data);
+void bcm_phy_get_stats(struct phy_device *phydev, u64 *shadow,
+		       struct ethtool_stats *stats, u64 *data);
+void bcm_phy_update_stats_shadow(struct phy_device *phydev, u64 *shadow);
+void bcm_phy_r_rc_cal_reset(struct phy_device *phydev);
+int bcm_phy_28nm_a0b0_afe_config_init(struct phy_device *phydev);
+int bcm_phy_enable_jumbo(struct phy_device *phydev);
+
+int bcm_phy_cable_test_get_status_rdb(struct phy_device *phydev,
+				      bool *finished);
+int bcm_phy_cable_test_start_rdb(struct phy_device *phydev);
+int bcm_phy_cable_test_start(struct phy_device *phydev);
+int bcm_phy_cable_test_get_status(struct phy_device *phydev, bool *finished);
+
+#if IS_ENABLED(CONFIG_BCM_NET_PHYPTP)
+struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev);
+void bcm_ptp_config_init(struct phy_device *phydev);
+void bcm_ptp_stop(struct bcm_ptp_private *priv);
+#else
+static inline struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev)
+{
+	return NULL;
+}
+
+static inline void bcm_ptp_config_init(struct phy_device *phydev)
+{
+}
+
+static inline void bcm_ptp_stop(struct bcm_ptp_private *priv)
+{
+}
+#endif
+
+int bcm_phy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol);
+void bcm_phy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol);
+irqreturn_t bcm_phy_wol_isr(int irq, void *dev_id);
+
+int bcm_phy_led_brightness_set(struct phy_device *phydev,
+			       u8 index, enum led_brightness value);
+
+int bcm_setup_lre_master_slave(struct phy_device *phydev);
+int bcm_config_lre_aneg(struct phy_device *phydev, bool changed);
+int bcm_config_lre_advert(struct phy_device *phydev);
+
+#endif /* _LINUX_BCM_PHY_LIB_H */