powerpc/64s: Enable KFENCE on book3s64

KFENCE support was added for ppc32 in commit 90cbac0e
("powerpc: Enable KFENCE for PPC32").
Enable KFENCE on ppc64 architecture with hash and radix MMUs.
It uses the same mechanism as debug pagealloc to
protect/unprotect pages. All KFENCE kunit tests pass on both
MMUs.

KFENCE memory is initially allocated using memblock but is
later marked as SLAB allocated. This necessitates the change
to __pud_free to ensure that the KFENCE pages are freed
appropriately.

Based on previous work by Christophe Leroy and Jordan Niethe.
Signed-off-by: Nicholas Miehlbradt <nicholas@linux.ibm.com>
Reviewed-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220926075726.2846-4-nicholas@linux.ibm.com

arch/powerpc/Kconfig

@@ -195,7 +195,7 @@ config PPC
 	select HAVE_ARCH_KASAN			if PPC_RADIX_MMU
 	select HAVE_ARCH_KASAN			if PPC_BOOK3E_64
 	select HAVE_ARCH_KASAN_VMALLOC		if HAVE_ARCH_KASAN
-	select HAVE_ARCH_KFENCE			if PPC_BOOK3S_32 || PPC_8xx || 40x
+	select HAVE_ARCH_KFENCE			if ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS

arch/powerpc/include/asm/book3s/64/pgalloc.h

@@ -113,9 +113,11 @@ static inline void __pud_free(pud_t *pud)
 
 	/*
 	 * Early pud pages allocated via memblock allocator
-	 * can't be directly freed to slab
+	 * can't be directly freed to slab. KFENCE pages have
+	 * both reserved and slab flags set so need to be freed
+	 * kmem_cache_free.
 	 */
-	if (PageReserved(page))
+	if (PageReserved(page) && !PageSlab(page))
 		free_reserved_page(page);
 	else
 		kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1106,7 +1106,7 @@ static inline void vmemmap_remove_mapping(unsigned long start,
 }
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
 static inline void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (radix_enabled())

arch/powerpc/include/asm/kfence.h

@@ -11,11 +11,25 @@
 #include <linux/mm.h>
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+#define ARCH_FUNC_PREFIX "."
+#endif
+
 static inline bool arch_kfence_init_pool(void)
 {
 	return true;
 }
 
+#ifdef CONFIG_PPC64
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	struct page *page = virt_to_page(addr);
+
+	__kernel_map_pages(page, 1, !protect);
+
+	return true;
+}
+#else
 static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *kpte = virt_to_kpte(addr);
@@ -29,5 +43,6 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 
 	return true;
 }
+#endif
 
 #endif /* __ASM_POWERPC_KFENCE_H */

arch/powerpc/mm/book3s64/hash_utils.c

@@ -424,7 +424,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			break;
 
 		cond_resched();
-		if (debug_pagealloc_enabled() &&
+		if (debug_pagealloc_enabled_or_kfence() &&
 			(paddr >> PAGE_SHIFT) < linear_map_hash_count)
 			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
 	}
@@ -773,7 +773,7 @@ static void __init htab_init_page_sizes(void)
 	bool aligned = true;
 	init_hpte_page_sizes();
 
-	if (!debug_pagealloc_enabled()) {
+	if (!debug_pagealloc_enabled_or_kfence()) {
 		/*
 		 * Pick a size for the linear mapping. Currently, we only
 		 * support 16M, 1M and 4K which is the default
@@ -1061,7 +1061,7 @@ static void __init htab_initialize(void)
 
 	prot = pgprot_val(PAGE_KERNEL);
 
-	if (debug_pagealloc_enabled()) {
+	if (debug_pagealloc_enabled_or_kfence()) {
 		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
 		linear_map_hash_slots = memblock_alloc_try_nid(
 				linear_map_hash_count, 1, MEMBLOCK_LOW_LIMIT,
@@ -1980,7 +1980,7 @@ long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
 	return slot;
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
 static DEFINE_SPINLOCK(linear_map_hash_lock);
 
 static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
@@ -2053,7 +2053,7 @@ void hash__kernel_map_pages(struct page *page, int numpages, int enable)
 	}
 	local_irq_restore(flags);
 }
-#endif /* CONFIG_DEBUG_PAGEALLOC */
+#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_KFENCE */
 
 void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 				phys_addr_t first_memblock_size)

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -34,6 +34,8 @@
 
 #include <trace/events/thp.h>
 
+#include <mm/mmu_decl.h>
+
 unsigned int mmu_base_pid;
 unsigned long radix_mem_block_size __ro_after_init;
 
@@ -276,7 +278,7 @@ static int __meminit create_physical_mapping(unsigned long start,
 	int psize;
 	unsigned long max_mapping_size = radix_mem_block_size;
 
-	if (debug_pagealloc_enabled())
+	if (debug_pagealloc_enabled_or_kfence())
 		max_mapping_size = PAGE_SIZE;
 
 	start = ALIGN(start, PAGE_SIZE);
@@ -899,7 +901,7 @@ void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long
 #endif
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
 void radix__kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long addr;