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, 202 insertions, 0 deletions

diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
new file mode 100644
index 000000000..fe83a6833
--- /dev/null
+++ b/arch/xtensa/mm/init.c
@@ -0,0 +1,202 @@
+/*
+ * arch/xtensa/mm/init.c
+ *
+ * Derived from MIPS, PPC.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2005 Tensilica Inc.
+ * Copyright (C) 2014 - 2016 Cadence Design Systems Inc.
+ *
+ * Chris Zankel	<chris@zankel.net>
+ * Joe Taylor	<joe@tensilica.com, joetylr@yahoo.com>
+ * Marc Gauthier
+ * Kevin Chea
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/memblock.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
+#include <linux/mman.h>
+#include <linux/nodemask.h>
+#include <linux/mm.h>
+#include <linux/of_fdt.h>
+#include <linux/dma-map-ops.h>
+
+#include <asm/bootparam.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <asm/sysmem.h>
+
+/*
+ * Initialize the bootmem system and give it all low memory we have available.
+ */
+
+void __init bootmem_init(void)
+{
+	/* Reserve all memory below PHYS_OFFSET, as memory
+	 * accounting doesn't work for pages below that address.
+	 *
+	 * If PHYS_OFFSET is zero reserve page at address 0:
+	 * successfull allocations should never return NULL.
+	 */
+	memblock_reserve(0, PHYS_OFFSET ? PHYS_OFFSET : 1);
+
+	early_init_fdt_scan_reserved_mem();
+
+	if (!memblock_phys_mem_size())
+		panic("No memory found!\n");
+
+	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
+	min_low_pfn = max(min_low_pfn, PFN_UP(PHYS_OFFSET));
+	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	max_low_pfn = min(max_pfn, MAX_LOW_PFN);
+
+	early_memtest((phys_addr_t)min_low_pfn << PAGE_SHIFT,
+		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
+
+	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
+	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
+
+	memblock_dump_all();
+}
+
+static void __init print_vm_layout(void)
+{
+	pr_info("virtual kernel memory layout:\n"
+#ifdef CONFIG_KASAN
+		"    kasan   : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+#endif
+#ifdef CONFIG_MMU
+		"    vmalloc : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+#endif
+#ifdef CONFIG_HIGHMEM
+		"    pkmap   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    fixmap  : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+#endif
+		"    lowmem  : 0x%08lx - 0x%08lx  (%5lu MB)\n"
+		"    .text   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .rodata : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .data   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .init   : 0x%08lx - 0x%08lx  (%5lu kB)\n"
+		"    .bss    : 0x%08lx - 0x%08lx  (%5lu kB)\n",
+#ifdef CONFIG_KASAN
+		KASAN_SHADOW_START, KASAN_SHADOW_START + KASAN_SHADOW_SIZE,
+		KASAN_SHADOW_SIZE >> 20,
+#endif
+#ifdef CONFIG_MMU
+		VMALLOC_START, VMALLOC_END,
+		(VMALLOC_END - VMALLOC_START) >> 20,
+#ifdef CONFIG_HIGHMEM
+		PKMAP_BASE, PKMAP_BASE + LAST_PKMAP * PAGE_SIZE,
+		(LAST_PKMAP*PAGE_SIZE) >> 10,
+		FIXADDR_START, FIXADDR_END,
+		(FIXADDR_END - FIXADDR_START) >> 10,
+#endif
+		PAGE_OFFSET, PAGE_OFFSET +
+		(max_low_pfn - min_low_pfn) * PAGE_SIZE,
+#else
+		min_low_pfn * PAGE_SIZE, max_low_pfn * PAGE_SIZE,
+#endif
+		((max_low_pfn - min_low_pfn) * PAGE_SIZE) >> 20,
+		(unsigned long)_text, (unsigned long)_etext,
+		(unsigned long)(_etext - _text) >> 10,
+		(unsigned long)__start_rodata, (unsigned long)__end_rodata,
+		(unsigned long)(__end_rodata - __start_rodata) >> 10,
+		(unsigned long)_sdata, (unsigned long)_edata,
+		(unsigned long)(_edata - _sdata) >> 10,
+		(unsigned long)__init_begin, (unsigned long)__init_end,
+		(unsigned long)(__init_end - __init_begin) >> 10,
+		(unsigned long)__bss_start, (unsigned long)__bss_stop,
+		(unsigned long)(__bss_stop - __bss_start) >> 10);
+}
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfns)
+{
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfns[ZONE_HIGHMEM] = max_pfn;
+#endif
+}
+
+void __init zones_init(void)
+{
+	print_vm_layout();
+}
+
+static void __init parse_memmap_one(char *p)
+{
+	char *oldp;
+	unsigned long start_at, mem_size;
+
+	if (!p)
+		return;
+
+	oldp = p;
+	mem_size = memparse(p, &p);
+	if (p == oldp)
+		return;
+
+	switch (*p) {
+	case '@':
+		start_at = memparse(p + 1, &p);
+		memblock_add(start_at, mem_size);
+		break;
+
+	case '$':
+		start_at = memparse(p + 1, &p);
+		memblock_reserve(start_at, mem_size);
+		break;
+
+	case 0:
+		memblock_reserve(mem_size, -mem_size);
+		break;
+
+	default:
+		pr_warn("Unrecognized memmap syntax: %s\n", p);
+		break;
+	}
+}
+
+static int __init parse_memmap_opt(char *str)
+{
+	while (str) {
+		char *k = strchr(str, ',');
+
+		if (k)
+			*k++ = 0;
+
+		parse_memmap_one(str);
+		str = k;
+	}
+
+	return 0;
+}
+early_param("memmap", parse_memmap_opt);
+
+#ifdef CONFIG_MMU
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READONLY,
+	[VM_WRITE]					= PAGE_COPY,
+	[VM_WRITE | VM_READ]				= PAGE_COPY,
+	[VM_EXEC]					= PAGE_READONLY_EXEC,
+	[VM_EXEC | VM_READ]				= PAGE_READONLY_EXEC,
+	[VM_EXEC | VM_WRITE]				= PAGE_COPY_EXEC,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_EXEC,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READONLY,
+	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC]				= PAGE_READONLY_EXEC,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READONLY_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
+};
+DECLARE_VM_GET_PAGE_PROT
+#endif