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, 235 insertions, 0 deletions

diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
new file mode 100644
index 000000000..c7cc5a3d7
--- /dev/null
+++ b/arch/mips/loongson64/init.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Lemote Inc.
+ * Author: Wu Zhangjin, wuzhangjin@gmail.com
+ */
+
+#include <linux/irqchip.h>
+#include <linux/logic_pio.h>
+#include <linux/memblock.h>
+#include <linux/minmax.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <asm/bootinfo.h>
+#include <asm/traps.h>
+#include <asm/smp-ops.h>
+#include <asm/cacheflush.h>
+#include <asm/fw/fw.h>
+
+#include <loongson.h>
+#include <boot_param.h>
+
+#define NODE_ID_OFFSET_ADDR	((void __iomem *)TO_UNCAC(0x1001041c))
+
+u32 node_id_offset;
+
+static void __init mips_nmi_setup(void)
+{
+	void *base;
+
+	base = (void *)(CAC_BASE + 0x380);
+	memcpy(base, except_vec_nmi, 0x80);
+	flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
+}
+
+void ls7a_early_config(void)
+{
+	node_id_offset = ((readl(NODE_ID_OFFSET_ADDR) >> 8) & 0x1f) + 36;
+}
+
+void rs780e_early_config(void)
+{
+	node_id_offset = 37;
+}
+
+void virtual_early_config(void)
+{
+	node_id_offset = 44;
+}
+
+void __init szmem(unsigned int node)
+{
+	u32 i, mem_type;
+	phys_addr_t node_id, mem_start, mem_size;
+
+	/* Otherwise come from DTB */
+	if (loongson_sysconf.fw_interface != LOONGSON_LEFI)
+		return;
+
+	/* Parse memory information and activate */
+	for (i = 0; i < loongson_memmap->nr_map; i++) {
+		node_id = loongson_memmap->map[i].node_id;
+		if (node_id != node)
+			continue;
+
+		mem_type = loongson_memmap->map[i].mem_type;
+		mem_size = loongson_memmap->map[i].mem_size;
+
+		/* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */
+		if (mem_size & MEM_SIZE_IS_IN_BYTES)
+			mem_size &= ~MEM_SIZE_IS_IN_BYTES;
+		else
+			mem_size = mem_size << 20;
+
+		mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start;
+
+		switch (mem_type) {
+		case SYSTEM_RAM_LOW:
+		case SYSTEM_RAM_HIGH:
+		case UMA_VIDEO_RAM:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_add_node(mem_start, mem_size, node,
+					  MEMBLOCK_NONE);
+			break;
+		case SYSTEM_RAM_RESERVED:
+		case VIDEO_ROM:
+		case ADAPTER_ROM:
+		case ACPI_TABLE:
+		case SMBIOS_TABLE:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_reserve(mem_start, mem_size);
+			break;
+		/* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */
+		case VUMA_VIDEO_RAM:
+		default:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			break;
+		}
+	}
+
+	/* Reserve vgabios if it comes from firmware */
+	if (loongson_sysconf.vgabios_addr)
+		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
+				SZ_256K);
+	/* set nid for reserved memory */
+	memblock_set_node((u64)node << 44, (u64)(node + 1) << 44,
+			&memblock.reserved, node);
+}
+
+#ifndef CONFIG_NUMA
+static void __init prom_init_memory(void)
+{
+	szmem(0);
+}
+#endif
+
+void __init prom_init(void)
+{
+	fw_init_cmdline();
+
+	if (fw_arg2 == 0 || (fdt_magic(fw_arg2) == FDT_MAGIC)) {
+		loongson_sysconf.fw_interface = LOONGSON_DTB;
+		prom_dtb_init_env();
+	} else {
+		loongson_sysconf.fw_interface = LOONGSON_LEFI;
+		prom_lefi_init_env();
+	}
+
+	/* init base address of io space */
+	set_io_port_base((unsigned long)PCI_IOBASE);
+
+	if (loongson_sysconf.early_config)
+		loongson_sysconf.early_config();
+
+#ifdef CONFIG_NUMA
+	prom_init_numa_memory();
+#else
+	prom_init_memory();
+#endif
+
+	/* Hardcode to CPU UART 0 */
+	if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64R)
+		setup_8250_early_printk_port(TO_UNCAC(LOONGSON_REG_BASE), 0, 1024);
+	else
+		setup_8250_early_printk_port(TO_UNCAC(LOONGSON_REG_BASE + 0x1e0), 0, 1024);
+
+	register_smp_ops(&loongson3_smp_ops);
+	board_nmi_handler_setup = mips_nmi_setup;
+}
+
+static int __init add_legacy_isa_io(struct fwnode_handle *fwnode, resource_size_t hw_start,
+				    resource_size_t size)
+{
+	int ret = 0;
+	struct logic_pio_hwaddr *range;
+	unsigned long vaddr;
+
+	range = kzalloc_obj(*range, GFP_ATOMIC);
+	if (!range)
+		return -ENOMEM;
+
+	range->fwnode = fwnode;
+	range->size = size = round_up(size, PAGE_SIZE);
+	range->hw_start = hw_start;
+	range->flags = LOGIC_PIO_CPU_MMIO;
+
+	ret = logic_pio_register_range(range);
+	if (ret) {
+		kfree(range);
+		return ret;
+	}
+
+	/* Legacy ISA must placed at the start of PCI_IOBASE */
+	if (range->io_start != 0) {
+		logic_pio_unregister_range(range);
+		kfree(range);
+		return -EINVAL;
+	}
+
+	vaddr = (unsigned long)PCI_IOBASE + range->io_start;
+
+	vmap_page_range(vaddr, vaddr + size, hw_start, pgprot_device(PAGE_KERNEL));
+
+	return 0;
+}
+
+static __init void reserve_pio_range(void)
+{
+	struct device_node *np;
+
+	for_each_node_by_name(np, "isa") {
+		struct of_range range;
+		struct of_range_parser parser;
+
+		pr_info("ISA Bridge: %pOF\n", np);
+
+		if (of_range_parser_init(&parser, np)) {
+			pr_info("Failed to parse resources.\n");
+			of_node_put(np);
+			break;
+		}
+
+		for_each_of_range(&parser, &range) {
+			switch (range.flags & IORESOURCE_TYPE_BITS) {
+			case IORESOURCE_IO:
+				pr_info(" IO 0x%016llx..0x%016llx  ->  0x%016llx\n",
+					range.cpu_addr,
+					range.cpu_addr + range.size - 1,
+					range.bus_addr);
+				if (add_legacy_isa_io(&np->fwnode, range.cpu_addr, range.size))
+					pr_warn("Failed to reserve legacy IO in Logic PIO\n");
+				break;
+			case IORESOURCE_MEM:
+				pr_info(" MEM 0x%016llx..0x%016llx  ->  0x%016llx\n",
+					range.cpu_addr,
+					range.cpu_addr + range.size - 1,
+					range.bus_addr);
+				break;
+			}
+		}
+	}
+}
+
+void __init arch_init_irq(void)
+{
+	reserve_pio_range();
+	irqchip_init();
+}
+
+unsigned int arch_dynirq_lower_bound(unsigned int from)
+{
+	return MAX(from, NR_IRQS_LEGACY);
+}