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, 167 insertions, 0 deletions

diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
new file mode 100644
index 000000000..745097554
--- /dev/null
+++ b/arch/powerpc/mm/init-common.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Dave Engebretsen <engebret@us.ibm.com>
+ *      Rework for PPC64 port.
+ */
+
+#undef DEBUG
+
+#include <linux/string.h>
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/kup.h>
+#include <asm/smp.h>
+
+phys_addr_t memstart_addr __ro_after_init = (phys_addr_t)~0ull;
+EXPORT_SYMBOL_GPL(memstart_addr);
+phys_addr_t kernstart_addr __ro_after_init;
+EXPORT_SYMBOL_GPL(kernstart_addr);
+unsigned long kernstart_virt_addr __ro_after_init = KERNELBASE;
+EXPORT_SYMBOL_GPL(kernstart_virt_addr);
+
+bool disable_kuep = !IS_ENABLED(CONFIG_PPC_KUEP);
+bool disable_kuap = !IS_ENABLED(CONFIG_PPC_KUAP);
+#ifdef CONFIG_KFENCE
+bool __ro_after_init kfence_disabled;
+bool __ro_after_init kfence_early_init = !!CONFIG_KFENCE_SAMPLE_INTERVAL;
+#endif
+
+static int __init parse_nosmep(char *p)
+{
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+		return 0;
+
+	disable_kuep = true;
+	pr_warn("Disabling Kernel Userspace Execution Prevention\n");
+	return 0;
+}
+early_param("nosmep", parse_nosmep);
+
+static int __init parse_nosmap(char *p)
+{
+	disable_kuap = true;
+	pr_warn("Disabling Kernel Userspace Access Protection\n");
+	return 0;
+}
+early_param("nosmap", parse_nosmap);
+
+void __weak setup_kuep(bool disabled)
+{
+	if (!IS_ENABLED(CONFIG_PPC_KUEP) || disabled)
+		return;
+
+	if (smp_processor_id() != boot_cpuid)
+		return;
+
+	pr_info("Activating Kernel Userspace Execution Prevention\n");
+}
+
+void setup_kup(void)
+{
+	setup_kuap(disable_kuap);
+	setup_kuep(disable_kuep);
+}
+
+#define CTOR(shift) static void ctor_##shift(void *addr) \
+{							\
+	memset(addr, 0, sizeof(pgd_t) << (shift));	\
+}
+
+CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7);
+CTOR(8); CTOR(9); CTOR(10); CTOR(11); CTOR(12); CTOR(13); CTOR(14); CTOR(15);
+
+static inline void (*ctor(int shift))(void *)
+{
+	BUILD_BUG_ON(MAX_PGTABLE_INDEX_SIZE != 15);
+
+	switch (shift) {
+	case 0: return ctor_0;
+	case 1: return ctor_1;
+	case 2: return ctor_2;
+	case 3: return ctor_3;
+	case 4: return ctor_4;
+	case 5: return ctor_5;
+	case 6: return ctor_6;
+	case 7: return ctor_7;
+	case 8: return ctor_8;
+	case 9: return ctor_9;
+	case 10: return ctor_10;
+	case 11: return ctor_11;
+	case 12: return ctor_12;
+	case 13: return ctor_13;
+	case 14: return ctor_14;
+	case 15: return ctor_15;
+	}
+	return NULL;
+}
+
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE + 1];
+EXPORT_SYMBOL_GPL(pgtable_cache);	/* used by kvm_hv module */
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned int shift)
+{
+	char *name;
+	unsigned long table_size = sizeof(pgd_t) << shift;
+	unsigned long align = table_size;
+
+	/* When batching pgtable pointers for RCU freeing, we store
+	 * the index size in the low bits.  Table alignment must be
+	 * big enough to fit it.
+	 */
+	unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
+	struct kmem_cache *new = NULL;
+
+	/* It would be nice if this was a BUILD_BUG_ON(), but at the
+	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
+	 * constant expression, so so much for that. */
+	BUG_ON(!is_power_of_2(minalign));
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+
+	if (PGT_CACHE(shift))
+		return; /* Already have a cache of this size */
+
+	align = max_t(unsigned long, align, minalign);
+	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+	if (name)
+		new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
+	if (!new)
+		panic("Could not allocate pgtable cache for order %d", shift);
+
+	kfree(name);
+	pgtable_cache[shift] = new;
+
+	pr_debug("Allocated pgtable cache for order %d\n", shift);
+}
+EXPORT_SYMBOL_GPL(pgtable_cache_add);	/* used by kvm_hv module */
+
+void pgtable_cache_init(void)
+{
+	pgtable_cache_add(PGD_INDEX_SIZE);
+
+	if (PMD_CACHE_INDEX)
+		pgtable_cache_add(PMD_CACHE_INDEX);
+	/*
+	 * In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index except with THP enabled
+	 * on book3s 64
+	 */
+	if (PUD_CACHE_INDEX)
+		pgtable_cache_add(PUD_CACHE_INDEX);
+}