arm64: mm: enable per pmd page table lock

Switch from per mm_struct to per pmd page table lock by enabling
ARCH_ENABLE_SPLIT_PMD_PTLOCK. This provides better granularity for
large system.

I'm not sure if there is contention on mm->page_table_lock. Given
the option comes at no cost (apart from initializing more spin
locks), why not enable it now.

We only do so when pmd is not folded, so we don't mistakenly call
pgtable_pmd_page_ctor() on pud or p4d in pgd_pgtable_alloc().
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/Kconfig

@@ -889,6 +889,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	def_bool y if PGTABLE_LEVELS > 2
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---

arch/arm64/include/asm/pgalloc.h

@@ -33,12 +33,22 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)__get_free_page(PGALLOC_GFP);
+	struct page *page;
+
+	page = alloc_page(PGALLOC_GFP);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	return page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
 	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmdp));
 	free_page((unsigned long)pmdp);
 }
 

arch/arm64/include/asm/tlb.h

@@ -62,7 +62,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_remove_table(tlb, virt_to_page(pmdp));
+	struct page *page = virt_to_page(pmdp);
+
+	pgtable_pmd_page_dtor(page);
+	tlb_remove_table(tlb, page);
 }
 #endif