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, 311 insertions, 0 deletions

diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c
new file mode 100644
index 000000000..69899797d
--- /dev/null
+++ b/arch/arm64/kvm/ptdump.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Debug helper used to dump the stage-2 pagetables of the system and their
+ * associated permissions.
+ *
+ * Copyright (C) Google, 2024
+ * Author: Sebastian Ene <sebastianene@google.com>
+ */
+#include <linux/debugfs.h>
+#include <linux/kvm_host.h>
+#include <linux/seq_file.h>
+
+#include <asm/cpufeature.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_pgtable.h>
+#include <asm/ptdump.h>
+
+#define MARKERS_LEN		2
+#define KVM_PGTABLE_MAX_LEVELS	(KVM_PGTABLE_LAST_LEVEL + 1)
+#define S2FNAMESZ		sizeof("0x0123456789abcdef-0x0123456789abcdef-s2-disabled")
+
+struct kvm_ptdump_guest_state {
+	struct kvm_s2_mmu	*mmu;
+	struct ptdump_pg_state	parser_state;
+	struct addr_marker	ipa_marker[MARKERS_LEN];
+	struct ptdump_pg_level	level[KVM_PGTABLE_MAX_LEVELS];
+};
+
+static const struct ptdump_prot_bits stage2_pte_bits[] = {
+	{
+		.mask	= PTE_VALID,
+		.val	= PTE_VALID,
+		.set	= " ",
+		.clear	= "F",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R,
+		.set	= "R",
+		.clear	= " ",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
+		.set	= "W",
+		.clear	= " ",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.val	= 0b00UL << __bf_shf(KVM_PTE_LEAF_ATTR_HI_S2_XN),
+		.set	= "px ux ",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.val	= 0b01UL << __bf_shf(KVM_PTE_LEAF_ATTR_HI_S2_XN),
+		.set	= "PXNux ",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.val	= 0b10UL << __bf_shf(KVM_PTE_LEAF_ATTR_HI_S2_XN),
+		.set	= "PXNUXN",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_HI_S2_XN,
+		.val	= 0b11UL << __bf_shf(KVM_PTE_LEAF_ATTR_HI_S2_XN),
+		.set	= "px UXN",
+	},
+	{
+		.mask	= KVM_PTE_LEAF_ATTR_LO_S2_AF,
+		.val	= KVM_PTE_LEAF_ATTR_LO_S2_AF,
+		.set	= "AF",
+		.clear	= "  ",
+	},
+	{
+		.mask	= PMD_TYPE_MASK,
+		.val	= PMD_TYPE_SECT,
+		.set	= "BLK",
+		.clear	= "   ",
+	},
+};
+
+static int kvm_ptdump_visitor(const struct kvm_pgtable_visit_ctx *ctx,
+			      enum kvm_pgtable_walk_flags visit)
+{
+	struct ptdump_pg_state *st = ctx->arg;
+	struct ptdump_state *pt_st = &st->ptdump;
+
+	note_page(pt_st, ctx->addr, ctx->level, ctx->old);
+
+	return 0;
+}
+
+static int kvm_ptdump_build_levels(struct ptdump_pg_level *level, u32 start_lvl)
+{
+	u32 i;
+	u64 mask;
+
+	if (WARN_ON_ONCE(start_lvl >= KVM_PGTABLE_LAST_LEVEL))
+		return -EINVAL;
+
+	mask = 0;
+	for (i = 0; i < ARRAY_SIZE(stage2_pte_bits); i++)
+		mask |= stage2_pte_bits[i].mask;
+
+	for (i = start_lvl; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+		snprintf(level[i].name, sizeof(level[i].name), "%u", i);
+
+		level[i].num	= ARRAY_SIZE(stage2_pte_bits);
+		level[i].bits	= stage2_pte_bits;
+		level[i].mask	= mask;
+	}
+
+	return 0;
+}
+
+static struct kvm_ptdump_guest_state *kvm_ptdump_parser_create(struct kvm_s2_mmu *mmu)
+{
+	struct kvm_ptdump_guest_state *st;
+	struct kvm_pgtable *pgtable = mmu->pgt;
+	int ret;
+
+	st = kzalloc_obj(struct kvm_ptdump_guest_state, GFP_KERNEL_ACCOUNT);
+	if (!st)
+		return ERR_PTR(-ENOMEM);
+
+	ret = kvm_ptdump_build_levels(&st->level[0], pgtable->start_level);
+	if (ret) {
+		kfree(st);
+		return ERR_PTR(ret);
+	}
+
+	st->ipa_marker[0].name		= "Guest IPA";
+	st->ipa_marker[1].start_address = ULONG_MAX;
+
+	st->mmu				= mmu;
+	return st;
+}
+
+static int kvm_ptdump_guest_show(struct seq_file *m, void *unused)
+{
+	int ret;
+	struct kvm_ptdump_guest_state *st = m->private;
+	struct kvm_s2_mmu *mmu = st->mmu;
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+	struct kvm_pgtable_walker walker = (struct kvm_pgtable_walker) {
+		.cb	= kvm_ptdump_visitor,
+		.arg	= &st->parser_state,
+		.flags	= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	guard(write_lock)(&kvm->mmu_lock);
+	st->parser_state = (struct ptdump_pg_state) {
+		.marker		= &st->ipa_marker[0],
+		.end_address	= BIT(mmu->pgt->ia_bits),
+		.level		= -1,
+		.pg_level	= &st->level[0],
+		.seq		= m,
+	};
+
+	ret = kvm_pgtable_walk(mmu->pgt, 0, BIT(mmu->pgt->ia_bits), &walker);
+	if (ret)
+		return ret;
+	note_page_flush(&st->parser_state.ptdump);
+
+	return 0;
+}
+
+static int kvm_ptdump_guest_open(struct inode *m, struct file *file)
+{
+	struct kvm_s2_mmu *mmu = m->i_private;
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+	struct kvm_ptdump_guest_state *st;
+	int ret;
+
+	if (!kvm_get_kvm_safe(kvm))
+		return -ENOENT;
+
+	st = kvm_ptdump_parser_create(mmu);
+	if (IS_ERR(st)) {
+		ret = PTR_ERR(st);
+		goto err_with_kvm_ref;
+	}
+
+	ret = single_open(file, kvm_ptdump_guest_show, st);
+	if (!ret)
+		return 0;
+
+	kfree(st);
+err_with_kvm_ref:
+	kvm_put_kvm(kvm);
+	return ret;
+}
+
+static int kvm_ptdump_guest_close(struct inode *m, struct file *file)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(m->i_private);
+	void *st = ((struct seq_file *)file->private_data)->private;
+
+	kfree(st);
+	kvm_put_kvm(kvm);
+
+	return single_release(m, file);
+}
+
+static const struct file_operations kvm_ptdump_guest_fops = {
+	.open		= kvm_ptdump_guest_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= kvm_ptdump_guest_close,
+};
+
+static int kvm_pgtable_range_show(struct seq_file *m, void *unused)
+{
+	struct kvm_pgtable *pgtable = m->private;
+
+	seq_printf(m, "%2u\n", pgtable->ia_bits);
+	return 0;
+}
+
+static int kvm_pgtable_levels_show(struct seq_file *m, void *unused)
+{
+	struct kvm_pgtable *pgtable = m->private;
+
+	seq_printf(m, "%1d\n", KVM_PGTABLE_MAX_LEVELS - pgtable->start_level);
+	return 0;
+}
+
+static int kvm_pgtable_debugfs_open(struct inode *m, struct file *file,
+				    int (*show)(struct seq_file *, void *))
+{
+	struct kvm_s2_mmu *mmu = m->i_private;
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+	struct kvm_pgtable *pgtable;
+	int ret;
+
+	if (!kvm_get_kvm_safe(kvm))
+		return -ENOENT;
+
+	pgtable = mmu->pgt;
+
+	ret = single_open(file, show, pgtable);
+	if (ret < 0)
+		kvm_put_kvm(kvm);
+	return ret;
+}
+
+static int kvm_pgtable_range_open(struct inode *m, struct file *file)
+{
+	return kvm_pgtable_debugfs_open(m, file, kvm_pgtable_range_show);
+}
+
+static int kvm_pgtable_levels_open(struct inode *m, struct file *file)
+{
+	return kvm_pgtable_debugfs_open(m, file, kvm_pgtable_levels_show);
+}
+
+static int kvm_pgtable_debugfs_close(struct inode *m, struct file *file)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(m->i_private);
+
+	kvm_put_kvm(kvm);
+	return single_release(m, file);
+}
+
+static const struct file_operations kvm_pgtable_range_fops = {
+	.open		= kvm_pgtable_range_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= kvm_pgtable_debugfs_close,
+};
+
+static const struct file_operations kvm_pgtable_levels_fops = {
+	.open		= kvm_pgtable_levels_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= kvm_pgtable_debugfs_close,
+};
+
+void kvm_nested_s2_ptdump_create_debugfs(struct kvm_s2_mmu *mmu)
+{
+	struct dentry *dent;
+	char file_name[S2FNAMESZ];
+
+	snprintf(file_name, sizeof(file_name), "0x%016llx-0x%016llx-s2-%sabled",
+		 mmu->tlb_vttbr,
+		 mmu->tlb_vtcr,
+		 mmu->nested_stage2_enabled ? "en" : "dis");
+
+	dent = debugfs_create_file(file_name, 0400,
+				   mmu->arch->debugfs_nv_dentry, mmu,
+				   &kvm_ptdump_guest_fops);
+
+	mmu->shadow_pt_debugfs_dentry = dent;
+}
+
+void kvm_nested_s2_ptdump_remove_debugfs(struct kvm_s2_mmu *mmu)
+{
+	debugfs_remove(mmu->shadow_pt_debugfs_dentry);
+}
+
+void kvm_s2_ptdump_create_debugfs(struct kvm *kvm)
+{
+	debugfs_create_file("stage2_page_tables", 0400, kvm->debugfs_dentry,
+			    &kvm->arch.mmu, &kvm_ptdump_guest_fops);
+	debugfs_create_file("ipa_range", 0400, kvm->debugfs_dentry,
+			    &kvm->arch.mmu, &kvm_pgtable_range_fops);
+	debugfs_create_file("stage2_levels", 0400, kvm->debugfs_dentry,
+			    &kvm->arch.mmu, &kvm_pgtable_levels_fops);
+	if (cpus_have_final_cap(ARM64_HAS_NESTED_VIRT))
+		kvm->arch.debugfs_nv_dentry = debugfs_create_dir("nested", kvm->debugfs_dentry);
+}