[RFC PATCH v2 13/19] heki: Implement a kernel page table walker

[Mickaël Salaün]

From: Madhavan T. Venkataraman <madvenka at linux.microsoft.com>

The Heki feature needs to do the following:

- Find kernel mappings.

- Determine the permissions associated with each mapping.

- Determine the collective permissions for a guest physical page across
  all of its mappings.

This way, a guest physical page can reflect only the required
permissions in the EPT thanks to the KVM_HC_PROTECT_MEMORY hypercall..

Implement a kernel page table walker that walks all of the kernel
mappings and calls a callback function for each mapping.

Cc: Borislav Petkov <bp at alien8.de>
Cc: Dave Hansen <dave.hansen at linux.intel.com>
Cc: H. Peter Anvin <hpa at zytor.com>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: Kees Cook <keescook at chromium.org>
Cc: Madhavan T. Venkataraman <madvenka at linux.microsoft.com>
Cc: Paolo Bonzini <pbonzini at redhat.com>
Cc: Sean Christopherson <seanjc at google.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Vitaly Kuznetsov <vkuznets at redhat.com>
Cc: Wanpeng Li <wanpengli at tencent.com>
Co-developed-by: Mickaël Salaün <mic at digikod.net>
Signed-off-by: Mickaël Salaün <mic at digikod.net>
Signed-off-by: Madhavan T. Venkataraman <madvenka at linux.microsoft.com>
---

Change since v1:
* New patch and new file: virt/heki/walk.c
---
 include/linux/heki.h |  16 +++++
 virt/heki/Makefile   |   1 +
 virt/heki/walk.c     | 140 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 157 insertions(+)
 create mode 100644 virt/heki/walk.c

diff --git a/include/linux/heki.h b/include/linux/heki.h
index 9b0c966c50d1..a7ae0b387dfe 100644
--- a/include/linux/heki.h
+++ b/include/linux/heki.h
@@ -61,6 +61,22 @@ struct heki {
 	struct heki_hypervisor *hypervisor;
 };
 
+/*
+ * The kernel page table is walked to locate kernel mappings. For each
+ * mapping, a callback function is called. The table walker passes information
+ * about the mapping to the callback using this structure.
+ */
+struct heki_args {
+	/* Information passed by the table walker to the callback. */
+	unsigned long va;
+	phys_addr_t pa;
+	size_t size;
+	unsigned long flags;
+};
+
+/* Callback function called by the table walker. */
+typedef void (*heki_func_t)(struct heki_args *args);
+
 extern struct heki heki;
 extern bool heki_enabled;
 
diff --git a/virt/heki/Makefile b/virt/heki/Makefile
index 354e567df71c..a5daa4ff7a4f 100644
--- a/virt/heki/Makefile
+++ b/virt/heki/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 obj-y += main.o
+obj-y += walk.o
diff --git a/virt/heki/walk.c b/virt/heki/walk.c
new file mode 100644
index 000000000000..e10b54226fcc
--- /dev/null
+++ b/virt/heki/walk.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Hypervisor Enforced Kernel Integrity (Heki) - Kernel page table walker.
+ *
+ * Copyright © 2023 Microsoft Corporation
+ *
+ * Cf. arch/x86/mm/init_64.c
+ */
+
+#include <linux/heki.h>
+#include <linux/pgtable.h>
+
+static void heki_walk_pte(pmd_t *pmd, unsigned long va, unsigned long va_end,
+			  heki_func_t func, struct heki_args *args)
+{
+	pte_t *pte;
+	unsigned long next_va;
+
+	for (pte = pte_offset_kernel(pmd, va); va < va_end;
+	     va = next_va, pte++) {
+		next_va = (va + PAGE_SIZE) & PAGE_MASK;
+
+		if (next_va > va_end)
+			next_va = va_end;
+
+		if (!pte_present(*pte))
+			continue;
+
+		args->va = va;
+		args->pa = pte_pfn(*pte) << PAGE_SHIFT;
+		args->size = PAGE_SIZE;
+		args->flags = pte_flags(*pte);
+
+		func(args);
+	}
+}
+
+static void heki_walk_pmd(pud_t *pud, unsigned long va, unsigned long va_end,
+			  heki_func_t func, struct heki_args *args)
+{
+	pmd_t *pmd;
+	unsigned long next_va;
+
+	for (pmd = pmd_offset(pud, va); va < va_end; va = next_va, pmd++) {
+		next_va = pmd_addr_end(va, va_end);
+
+		if (!pmd_present(*pmd))
+			continue;
+
+		if (pmd_large(*pmd)) {
+			args->va = va;
+			args->pa = pmd_pfn(*pmd) << PAGE_SHIFT;
+			args->pa += va & (PMD_SIZE - 1);
+			args->size = next_va - va;
+			args->flags = pmd_flags(*pmd);
+
+			func(args);
+		} else {
+			heki_walk_pte(pmd, va, next_va, func, args);
+		}
+	}
+}
+
+static void heki_walk_pud(p4d_t *p4d, unsigned long va, unsigned long va_end,
+			  heki_func_t func, struct heki_args *args)
+{
+	pud_t *pud;
+	unsigned long next_va;
+
+	for (pud = pud_offset(p4d, va); va < va_end; va = next_va, pud++) {
+		next_va = pud_addr_end(va, va_end);
+
+		if (!pud_present(*pud))
+			continue;
+
+		if (pud_large(*pud)) {
+			args->va = va;
+			args->pa = pud_pfn(*pud) << PAGE_SHIFT;
+			args->pa += va & (PUD_SIZE - 1);
+			args->size = next_va - va;
+			args->flags = pud_flags(*pud);
+
+			func(args);
+		} else {
+			heki_walk_pmd(pud, va, next_va, func, args);
+		}
+	}
+}
+
+static void heki_walk_p4d(pgd_t *pgd, unsigned long va, unsigned long va_end,
+			  heki_func_t func, struct heki_args *args)
+{
+	p4d_t *p4d;
+	unsigned long next_va;
+
+	for (p4d = p4d_offset(pgd, va); va < va_end; va = next_va, p4d++) {
+		next_va = p4d_addr_end(va, va_end);
+
+		if (!p4d_present(*p4d))
+			continue;
+
+		if (p4d_large(*p4d)) {
+			args->va = va;
+			args->pa = p4d_pfn(*p4d) << PAGE_SHIFT;
+			args->pa += va & (P4D_SIZE - 1);
+			args->size = next_va - va;
+			args->flags = p4d_flags(*p4d);
+
+			func(args);
+		} else {
+			heki_walk_pud(p4d, va, next_va, func, args);
+		}
+	}
+}
+
+void heki_walk(unsigned long va, unsigned long va_end, heki_func_t func,
+	       struct heki_args *args)
+{
+	pgd_t *pgd;
+	unsigned long next_va;
+
+	for (pgd = pgd_offset_k(va); va < va_end; va = next_va, pgd++) {
+		next_va = pgd_addr_end(va, va_end);
+
+		if (!pgd_present(*pgd))
+			continue;
+
+		if (pgd_large(*pgd)) {
+			args->va = va;
+			args->pa = pgd_pfn(*pgd) << PAGE_SHIFT;
+			args->pa += va & (PGDIR_SIZE - 1);
+			args->size = next_va - va;
+			args->flags = pgd_flags(*pgd);
+
+			func(args);
+		} else {
+			heki_walk_p4d(pgd, va, next_va, func, args);
+		}
+	}
+}
-- 
2.42.1