[PATCH RFC v7 14/24] mm: kpkeys: Protect vmemmap page tables

[Kevin Brodsky]

When the kpkeys_hardened_pgtables feature is enabled, make sure that
vmemmap page tables are protected by using:

* The standard pagetable_alloc() if the buddy allocator is
  available, as it already allocates protected memory.

* The memblock-based kpkeys allocator for early allocations.

These allocators are not NUMA-aware, so the page tables may be
allocated on any node. This could potentially incur some overhead on
large NUMA systems.

Signed-off-by: Kevin Brodsky <kevin.brodsky at arm.com>
---

This is a minimal patch to protect vmemmmap page tables. More work
may be needed here:

* Restoring NUMA awareness

* General refactoring of how these page tables are allocated: since
  we are not using the standard per-level functions (e.g.
  pmd_alloc()), we are not calling pagetable_*_ctor() or
  ptdesc_set_kernel(). [Maybe that doesn't matter because these page
  tables can only be freed via vmemmap_free()?]
---
 mm/sparse-vmemmap.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 6eadb9d116e4..0c0d3b1e356c 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -184,13 +184,28 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
 	return pte;
 }
 
-static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
+static void * __meminit vmemmap_alloc_pgtable(int node)
 {
-	void *p = vmemmap_alloc_block(size, node);
+	void *p;
+
+	if (slab_is_available()) {
+		struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL, 0);
+
+		return ptdesc ? ptdesc_address(ptdesc) : NULL;
+	}
+
+	if (kpkeys_hardened_pgtables_early_enabled()) {
+		phys_addr_t phys = kpkeys_physmem_pgtable_alloc();
+
+		p = phys ? phys_to_virt(phys) : NULL;
+	} else {
+		p = __earlyonly_bootmem_alloc(node, PAGE_SIZE, PAGE_SIZE,
+					      __pa(MAX_DMA_ADDRESS));
+	}
 
 	if (!p)
 		return NULL;
-	memset(p, 0, size);
+	memset(p, 0, PAGE_SIZE);
 
 	return p;
 }
@@ -199,7 +214,7 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd)) {
-		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_pgtable(node);
 		if (!p)
 			return NULL;
 		kernel_pte_init(p);
@@ -212,7 +227,7 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
 {
 	pud_t *pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
-		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_pgtable(node);
 		if (!p)
 			return NULL;
 		pmd_init(p);
@@ -225,7 +240,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
 {
 	p4d_t *p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d)) {
-		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_pgtable(node);
 		if (!p)
 			return NULL;
 		pud_init(p);
@@ -238,7 +253,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
 	if (pgd_none(*pgd)) {
-		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_pgtable(node);
 		if (!p)
 			return NULL;
 		pgd_populate_kernel(addr, pgd, p);

-- 
2.51.2