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/arch/arc/mm/init.c b/arch/arc/mm/init.c
new file mode 100644
index 000000000..d6b5c27a0
--- /dev/null
+++ b/arch/arc/mm/init.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#ifdef CONFIG_BLK_DEV_INITRD
+#include <linux/initrd.h>
+#endif
+#include <linux/of_fdt.h>
+#include <linux/swap.h>
+#include <linux/module.h>
+#include <linux/highmem.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/arcregs.h>
+
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE);
+
+static const unsigned long low_mem_start = CONFIG_LINUX_RAM_BASE;
+static unsigned long low_mem_sz;
+
+#ifdef CONFIG_HIGHMEM
+static unsigned long min_high_pfn, max_high_pfn;
+static phys_addr_t high_mem_start;
+static phys_addr_t high_mem_sz;
+unsigned long arch_pfn_offset;
+EXPORT_SYMBOL(arch_pfn_offset);
+#endif
+
+long __init arc_get_mem_sz(void)
+{
+	return low_mem_sz;
+}
+
+/* User can over-ride above with "mem=nnn[KkMm]" in cmdline */
+static int __init setup_mem_sz(char *str)
+{
+	low_mem_sz = memparse(str, NULL) & PAGE_MASK;
+
+	/* early console might not be setup yet - it will show up later */
+	pr_info("\"mem=%s\": mem sz set to %ldM\n", str, TO_MB(low_mem_sz));
+
+	return 0;
+}
+early_param("mem", setup_mem_sz);
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+	int in_use = 0;
+
+	if (!low_mem_sz) {
+		if (base != low_mem_start)
+			panic("CONFIG_LINUX_RAM_BASE != DT memory { }");
+
+		low_mem_sz = size;
+		in_use = 1;
+		memblock_add_node(base, size, 0, MEMBLOCK_NONE);
+	} else {
+#ifdef CONFIG_HIGHMEM
+		high_mem_start = base;
+		high_mem_sz = size;
+		in_use = 1;
+		memblock_add_node(base, size, 1, MEMBLOCK_NONE);
+		memblock_reserve(base, size);
+#endif
+	}
+
+	pr_info("Memory @ %llx [%lldM] %s\n",
+		base, TO_MB(size), !in_use ? "Not used":"");
+}
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfn)
+{
+	/*----------------- node/zones setup --------------------------*/
+	max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * max_high_pfn should be ok here for both HIGHMEM and HIGHMEM+PAE.
+	 * For HIGHMEM without PAE max_high_pfn should be less than
+	 * min_low_pfn to guarantee that these two regions don't overlap.
+	 * For PAE case highmem is greater than lowmem, so it is natural
+	 * to use max_high_pfn.
+	 *
+	 * In both cases, holes should be handled by pfn_valid().
+	 */
+	max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn;
+#endif
+}
+
+/*
+ * First memory setup routine called from setup_arch()
+ * 1. setup swapper's mm @init_mm
+ * 2. Count the pages we have and setup bootmem allocator
+ * 3. zone setup
+ */
+void __init setup_arch_memory(void)
+{
+	setup_initial_init_mm(_text, _etext, _edata, _end);
+
+	/* first page of system - kernel .vector starts here */
+	min_low_pfn = virt_to_pfn((void *)CONFIG_LINUX_RAM_BASE);
+
+	/* Last usable page of low mem */
+	max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz);
+
+	/*------------- bootmem allocator setup -----------------------*/
+
+	/*
+	 * seed the bootmem allocator after any DT memory node parsing or
+	 * "mem=xxx" cmdline overrides have potentially updated @arc_mem_sz
+	 *
+	 * Only low mem is added, otherwise we have crashes when allocating
+	 * mem_map[] itself. NO_BOOTMEM allocates mem_map[] at the end of
+	 * avail memory, ending in highmem with a > 32-bit address. However
+	 * it then tries to memset it with a truncaed 32-bit handle, causing
+	 * the crash
+	 */
+
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
+
+#ifdef CONFIG_BLK_DEV_INITRD
+	if (phys_initrd_size) {
+		memblock_reserve(phys_initrd_start, phys_initrd_size);
+		initrd_start = (unsigned long)__va(phys_initrd_start);
+		initrd_end = initrd_start + phys_initrd_size;
+	}
+#endif
+
+	early_init_fdt_reserve_self();
+	early_init_fdt_scan_reserved_mem();
+
+	memblock_dump_all();
+
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based)
+	 * than addresses in normal aka low memory (0x8000_0000 based).
+	 * Even with PAE, the huge peripheral space hole would waste a lot of
+	 * mem with single contiguous mem_map[].
+	 * Thus when HIGHMEM on ARC is enabled the memory map corresponding
+	 * to the hole is freed and ARC specific version of pfn_valid()
+	 * handles the hole in the memory map.
+	 */
+
+	min_high_pfn = PFN_DOWN(high_mem_start);
+	max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz);
+
+	arch_pfn_offset = min(min_low_pfn, min_high_pfn);
+	kmap_init();
+#endif /* CONFIG_HIGHMEM */
+}
+
+void __init arch_mm_preinit(void)
+{
+#ifdef CONFIG_HIGHMEM
+	memblock_phys_free(high_mem_start, high_mem_sz);
+#endif
+
+	BUILD_BUG_ON((PTRS_PER_PGD * sizeof(pgd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PUD * sizeof(pud_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PMD * sizeof(pmd_t)) > PAGE_SIZE);
+	BUILD_BUG_ON((PTRS_PER_PTE * sizeof(pte_t)) > PAGE_SIZE);
+}
+
+#ifdef CONFIG_HIGHMEM
+int pfn_valid(unsigned long pfn)
+{
+	return (pfn >= min_high_pfn && pfn <= max_high_pfn) ||
+		(pfn >= min_low_pfn && pfn <= max_low_pfn);
+}
+EXPORT_SYMBOL(pfn_valid);
+#endif