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, 204 insertions, 0 deletions

diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
new file mode 100644
index 000000000..1d712eac1
--- /dev/null
+++ b/arch/mips/generic/init.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@mips.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/irqchip.h>
+#include <linux/of_clk.h>
+#include <linux/of_fdt.h>
+
+#include <asm/bootinfo.h>
+#include <asm/fw/fw.h>
+#include <asm/irq_cpu.h>
+#include <asm/machine.h>
+#include <asm/mips-cps.h>
+#include <asm/prom.h>
+#include <asm/smp-ops.h>
+#include <asm/time.h>
+
+static __initconst const void *fdt;
+static __initconst const struct mips_machine *mach;
+static __initconst const void *mach_match_data;
+
+void __init prom_init(void)
+{
+	plat_get_fdt();
+	BUG_ON(!fdt);
+}
+
+void __init *plat_get_fdt(void)
+{
+	const struct mips_machine *check_mach;
+	const struct of_device_id *match;
+
+	if (fdt)
+		/* Already set up */
+		return (void *)fdt;
+
+	fdt = (void *)get_fdt();
+	if (fdt && !fdt_check_header(fdt)) {
+		/*
+		 * We have been provided with the appropriate device tree for
+		 * the board. Make use of it & search for any machine struct
+		 * based upon the root compatible string.
+		 */
+		for_each_mips_machine(check_mach) {
+			match = mips_machine_is_compatible(check_mach, fdt);
+			if (match) {
+				mach = check_mach;
+				mach_match_data = match->data;
+				break;
+			}
+		}
+	} else if (IS_ENABLED(CONFIG_LEGACY_BOARDS)) {
+		/*
+		 * We weren't booted using the UHI boot protocol, but do
+		 * support some number of boards with legacy boot protocols.
+		 * Attempt to find the right one.
+		 */
+		for_each_mips_machine(check_mach) {
+			if (!check_mach->detect)
+				continue;
+
+			if (!check_mach->detect())
+				continue;
+
+			mach = check_mach;
+		}
+
+		/*
+		 * If we don't recognise the machine then we can't continue, so
+		 * die here.
+		 */
+		BUG_ON(!mach);
+
+		/* Retrieve the machine's FDT */
+		fdt = mach->fdt;
+	}
+	return (void *)fdt;
+}
+
+#ifdef CONFIG_RELOCATABLE
+
+void __init plat_fdt_relocated(void *new_location)
+{
+	/*
+	 * reset fdt as the cached value would point to the location
+	 * before relocations happened and update the location argument
+	 * if it was passed using UHI
+	 */
+	fdt = NULL;
+
+	if (fw_arg0 == -2)
+		fw_arg1 = (unsigned long)new_location;
+}
+
+#endif /* CONFIG_RELOCATABLE */
+
+void __init plat_mem_setup(void)
+{
+	if (mach && mach->fixup_fdt)
+		fdt = mach->fixup_fdt(fdt, mach_match_data);
+
+	fw_init_cmdline();
+	__dt_setup_arch((void *)fdt);
+}
+
+void __init device_tree_init(void)
+{
+	unflatten_and_copy_device_tree();
+	mips_cpc_probe();
+
+	if (!register_cps_smp_ops())
+		return;
+	if (!register_vsmp_smp_ops())
+		return;
+
+	register_up_smp_ops();
+}
+
+int __init apply_mips_fdt_fixups(void *fdt_out, size_t fdt_out_size,
+				 const void *fdt_in,
+				 const struct mips_fdt_fixup *fixups)
+{
+	int err;
+
+	err = fdt_open_into(fdt_in, fdt_out, fdt_out_size);
+	if (err) {
+		pr_err("Failed to open FDT\n");
+		return err;
+	}
+
+	for (; fixups->apply; fixups++) {
+		err = fixups->apply(fdt_out);
+		if (err) {
+			pr_err("Failed to apply FDT fixup \"%s\"\n",
+			       fixups->description);
+			return err;
+		}
+	}
+
+	err = fdt_pack(fdt_out);
+	if (err)
+		pr_err("Failed to pack FDT\n");
+	return err;
+}
+
+void __init plat_time_init(void)
+{
+	struct device_node *np;
+	struct clk *clk;
+
+	of_clk_init(NULL);
+
+	if (!cpu_has_counter) {
+		mips_hpt_frequency = 0;
+	} else if (mach && mach->measure_hpt_freq) {
+		mips_hpt_frequency = mach->measure_hpt_freq();
+	} else {
+		np = of_get_cpu_node(0, NULL);
+		if (!np) {
+			pr_err("Failed to get CPU node\n");
+			return;
+		}
+
+		clk = of_clk_get(np, 0);
+		if (IS_ERR(clk)) {
+			pr_err("Failed to get CPU clock: %ld\n", PTR_ERR(clk));
+			return;
+		}
+
+		mips_hpt_frequency = clk_get_rate(clk);
+		clk_put(clk);
+
+		switch (boot_cpu_type()) {
+		case CPU_20KC:
+		case CPU_25KF:
+			/* The counter runs at the CPU clock rate */
+			break;
+		default:
+			/* The counter runs at half the CPU clock rate */
+			mips_hpt_frequency /= 2;
+			break;
+		}
+	}
+
+	timer_probe();
+}
+
+void __init arch_init_irq(void)
+{
+	struct device_node *intc_node;
+
+	intc_node = of_find_compatible_node(NULL, NULL,
+					    "mti,cpu-interrupt-controller");
+	if (!cpu_has_veic && !intc_node)
+		mips_cpu_irq_init();
+	of_node_put(intc_node);
+
+	irqchip_init();
+}