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, 178 insertions, 0 deletions

diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
new file mode 100644
index 000000000..3167cab62
--- /dev/null
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013, 2014 Linaro Ltd.
+ */
+
+#include <linux/dmi.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/mm_types.h>
+#include <linux/pgalloc.h>
+#include <linux/pgtable.h>
+#include <linux/preempt.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <asm/cacheflush.h>
+#include <asm/efi.h>
+#include <asm/mmu.h>
+
+#if defined(CONFIG_PTDUMP_DEBUGFS) || defined(CONFIG_ARM_PTDUMP_DEBUGFS)
+#include <asm/ptdump.h>
+
+static struct ptdump_info efi_ptdump_info = {
+	.mm		= &efi_mm,
+	.markers	= (struct addr_marker[]){
+		{ 0,				"UEFI runtime start" },
+		{ EFI_RUNTIME_MAP_END,		"UEFI runtime end" },
+		{ -1,				NULL }
+	},
+	.base_addr	= 0,
+};
+
+static int __init ptdump_init(void)
+{
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		ptdump_debugfs_register(&efi_ptdump_info, "efi_page_tables");
+
+	return 0;
+}
+device_initcall(ptdump_init);
+
+#endif
+
+static bool __init efi_virtmap_init(void)
+{
+	efi_memory_desc_t *md;
+
+	efi_mm.pgd = pgd_alloc(&efi_mm);
+	mm_init_cpumask(&efi_mm);
+	init_new_context(NULL, &efi_mm);
+
+	for_each_efi_memory_desc(md) {
+		phys_addr_t phys = md->phys_addr;
+		int ret;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME))
+			continue;
+		if (md->virt_addr == U64_MAX)
+			return false;
+
+		ret = efi_create_mapping(&efi_mm, md);
+		if (ret) {
+			pr_warn("  EFI remap %pa: failed to create mapping (%d)\n",
+				&phys, ret);
+			return false;
+		}
+	}
+
+	if (efi_memattr_apply_permissions(&efi_mm, efi_set_mapping_permissions))
+		return false;
+
+	return true;
+}
+
+/*
+ * Enable the UEFI Runtime Services if all prerequisites are in place, i.e.,
+ * non-early mapping of the UEFI system table and virtual mappings for all
+ * EFI_MEMORY_RUNTIME regions.
+ */
+static int __init arm_enable_runtime_services(void)
+{
+	u64 mapsize;
+
+	if (!efi_enabled(EFI_BOOT)) {
+		pr_info("EFI services will not be available.\n");
+		return 0;
+	}
+
+	efi_memmap_unmap();
+
+	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
+
+	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
+		pr_err("Failed to remap EFI memory map\n");
+		return 0;
+	}
+
+	if (efi_soft_reserve_enabled()) {
+		efi_memory_desc_t *md;
+
+		for_each_efi_memory_desc(md) {
+			u64 md_size = md->num_pages << EFI_PAGE_SHIFT;
+			struct resource *res;
+
+			if (!(md->attribute & EFI_MEMORY_SP))
+				continue;
+
+			res = kzalloc_obj(*res);
+			if (WARN_ON(!res))
+				break;
+
+			res->start	= md->phys_addr;
+			res->end	= md->phys_addr + md_size - 1;
+			res->name	= "Soft Reserved";
+			res->flags	= IORESOURCE_MEM;
+			res->desc	= IORES_DESC_SOFT_RESERVED;
+
+			insert_resource(&iomem_resource, res);
+		}
+	}
+
+	if (efi_runtime_disabled()) {
+		pr_info("EFI runtime services will be disabled.\n");
+		return 0;
+	}
+
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
+		pr_info("EFI runtime services access via paravirt.\n");
+		return 0;
+	}
+
+	pr_info("Remapping and enabling EFI services.\n");
+
+	if (!efi_virtmap_init()) {
+		pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n");
+		return -ENOMEM;
+	}
+
+	/* Set up runtime services function pointers */
+	efi_native_runtime_setup();
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+	return 0;
+}
+early_initcall(arm_enable_runtime_services);
+
+void efi_virtmap_load(void)
+{
+	preempt_disable();
+	efi_set_pgd(&efi_mm);
+}
+
+void efi_virtmap_unload(void)
+{
+	efi_set_pgd(current->active_mm);
+	preempt_enable();
+}
+
+
+static int __init arm_dmi_init(void)
+{
+	/*
+	 * On arm64/ARM, DMI depends on UEFI, and dmi_setup() needs to
+	 * be called early because dmi_id_init(), which is an arch_initcall
+	 * itself, depends on dmi_scan_machine() having been called already.
+	 */
+	dmi_setup();
+	return 0;
+}
+core_initcall(arm_dmi_init);