1 files changed, 171 insertions, 65 deletions

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d3b538be1500..5285757ee0c1 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -40,6 +40,85 @@
 #include <linux/sched.h>
 #include <linux/page_table_check.h>
 
+static inline void emit_pte_barriers(void)
+{
+	/*
+	 * These barriers are emitted under certain conditions after a pte entry
+	 * was modified (see e.g. __set_pte_complete()). The dsb makes the store
+	 * visible to the table walker. The isb ensures that any previous
+	 * speculative "invalid translation" marker that is in the CPU's
+	 * pipeline gets cleared, so that any access to that address after
+	 * setting the pte to valid won't cause a spurious fault. If the thread
+	 * gets preempted after storing to the pgtable but before emitting these
+	 * barriers, __switch_to() emits a dsb which ensure the walker gets to
+	 * see the store. There is no guarantee of an isb being issued though.
+	 * This is safe because it will still get issued (albeit on a
+	 * potentially different CPU) when the thread starts running again,
+	 * before any access to the address.
+	 */
+	dsb(ishst);
+	isb();
+}
+
+static inline void queue_pte_barriers(void)
+{
+	unsigned long flags;
+
+	if (in_interrupt()) {
+		emit_pte_barriers();
+		return;
+	}
+
+	flags = read_thread_flags();
+
+	if (flags & BIT(TIF_LAZY_MMU)) {
+		/* Avoid the atomic op if already set. */
+		if (!(flags & BIT(TIF_LAZY_MMU_PENDING)))
+			set_thread_flag(TIF_LAZY_MMU_PENDING);
+	} else {
+		emit_pte_barriers();
+	}
+}
+
+#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+	/*
+	 * lazy_mmu_mode is not supposed to permit nesting. But in practice this
+	 * does happen with CONFIG_DEBUG_PAGEALLOC, where a page allocation
+	 * inside a lazy_mmu_mode section (such as zap_pte_range()) will change
+	 * permissions on the linear map with apply_to_page_range(), which
+	 * re-enters lazy_mmu_mode. So we tolerate nesting in our
+	 * implementation. The first call to arch_leave_lazy_mmu_mode() will
+	 * flush and clear the flag such that the remainder of the work in the
+	 * outer nest behaves as if outside of lazy mmu mode. This is safe and
+	 * keeps tracking simple.
+	 */
+
+	if (in_interrupt())
+		return;
+
+	set_thread_flag(TIF_LAZY_MMU);
+}
+
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	if (in_interrupt())
+		return;
+
+	if (test_and_clear_thread_flag(TIF_LAZY_MMU_PENDING))
+		emit_pte_barriers();
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+	if (in_interrupt())
+		return;
+
+	arch_flush_lazy_mmu_mode();
+	clear_thread_flag(TIF_LAZY_MMU);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 
@@ -320,18 +399,20 @@ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 	WRITE_ONCE(*ptep, pte);
 }
 
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_complete(pte_t pte)
 {
-	__set_pte_nosync(ptep, pte);
-
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
-	 * or update_mmu_cache() have the necessary barriers.
+	 * has the necessary barriers.
 	 */
-	if (pte_valid_not_user(pte)) {
-		dsb(ishst);
-		isb();
-	}
+	if (pte_valid_not_user(pte))
+		queue_pte_barriers();
+}
+
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+	__set_pte_nosync(ptep, pte);
+	__set_pte_complete(pte);
 }
 
 static inline pte_t __ptep_get(pte_t *ptep)
@@ -423,23 +504,6 @@ static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
 	return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte));
 }
 
-static inline void __set_ptes(struct mm_struct *mm,
-			      unsigned long __always_unused addr,
-			      pte_t *ptep, pte_t pte, unsigned int nr)
-{
-	page_table_check_ptes_set(mm, ptep, pte, nr);
-	__sync_cache_and_tags(pte, nr);
-
-	for (;;) {
-		__check_safe_pte_update(mm, ptep, pte);
-		__set_pte(ptep, pte);
-		if (--nr == 0)
-			break;
-		ptep++;
-		pte = pte_advance_pfn(pte, 1);
-	}
-}
-
 /*
  * Hugetlb definitions.
  */
@@ -649,30 +713,64 @@ static inline pgprot_t pud_pgprot(pud_t pud)
 	return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud));
 }
 
-static inline void __set_pte_at(struct mm_struct *mm,
-				unsigned long __always_unused addr,
-				pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void __set_ptes_anysz(struct mm_struct *mm, pte_t *ptep,
+				    pte_t pte, unsigned int nr,
+				    unsigned long pgsize)
 {
-	__sync_cache_and_tags(pte, nr);
-	__check_safe_pte_update(mm, ptep, pte);
-	__set_pte(ptep, pte);
+	unsigned long stride = pgsize >> PAGE_SHIFT;
+
+	switch (pgsize) {
+	case PAGE_SIZE:
+		page_table_check_ptes_set(mm, ptep, pte, nr);
+		break;
+	case PMD_SIZE:
+		page_table_check_pmds_set(mm, (pmd_t *)ptep, pte_pmd(pte), nr);
+		break;
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		page_table_check_puds_set(mm, (pud_t *)ptep, pte_pud(pte), nr);
+		break;
+#endif
+	default:
+		VM_WARN_ON(1);
+	}
+
+	__sync_cache_and_tags(pte, nr * stride);
+
+	for (;;) {
+		__check_safe_pte_update(mm, ptep, pte);
+		__set_pte_nosync(ptep, pte);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte = pte_advance_pfn(pte, stride);
+	}
+
+	__set_pte_complete(pte);
 }
 
-static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-			      pmd_t *pmdp, pmd_t pmd)
+static inline void __set_ptes(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pte_t *ptep, pte_t pte, unsigned int nr)
 {
-	page_table_check_pmd_set(mm, pmdp, pmd);
-	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
-						PMD_SIZE >> PAGE_SHIFT);
+	__set_ptes_anysz(mm, ptep, pte, nr, PAGE_SIZE);
 }
 
-static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
-			      pud_t *pudp, pud_t pud)
+static inline void __set_pmds(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pmd_t *pmdp, pmd_t pmd, unsigned int nr)
+{
+	__set_ptes_anysz(mm, (pte_t *)pmdp, pmd_pte(pmd), nr, PMD_SIZE);
+}
+#define set_pmd_at(mm, addr, pmdp, pmd) __set_pmds(mm, addr, pmdp, pmd, 1)
+
+static inline void __set_puds(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pud_t *pudp, pud_t pud, unsigned int nr)
 {
-	page_table_check_pud_set(mm, pudp, pud);
-	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
-						PUD_SIZE >> PAGE_SHIFT);
+	__set_ptes_anysz(mm, (pte_t *)pudp, pud_pte(pud), nr, PUD_SIZE);
 }
+#define set_pud_at(mm, addr, pudp, pud) __set_puds(mm, addr, pudp, pud, 1)
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
 #define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
@@ -739,8 +837,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	 * If pmd is present-invalid, pmd_table() won't detect it
 	 * as a table, so force the valid bit for the comparison.
 	 */
-	return pmd_val(pmd) && pmd_present(pmd) &&
-	       !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
+	return pmd_present(pmd) && !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -754,8 +851,6 @@ static inline bool pud_table(pud_t pud) { return true; }
 				 PUD_TYPE_TABLE)
 #endif
 
-extern pgd_t init_pg_dir[];
-extern pgd_t init_pg_end[];
 extern pgd_t swapper_pg_dir[];
 extern pgd_t idmap_pg_dir[];
 extern pgd_t tramp_pg_dir[];
@@ -780,10 +875,8 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 	WRITE_ONCE(*pmdp, pmd);
 
-	if (pmd_valid(pmd)) {
-		dsb(ishst);
-		isb();
-	}
+	if (pmd_valid(pmd))
+		queue_pte_barriers();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -848,10 +941,8 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 
 	WRITE_ONCE(*pudp, pud);
 
-	if (pud_valid(pud)) {
-		dsb(ishst);
-		isb();
-	}
+	if (pud_valid(pud))
+		queue_pte_barriers();
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -930,8 +1021,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 	}
 
 	WRITE_ONCE(*p4dp, p4d);
-	dsb(ishst);
-	isb();
+	queue_pte_barriers();
 }
 
 static inline void p4d_clear(p4d_t *p4dp)
@@ -1059,8 +1149,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 	}
 
 	WRITE_ONCE(*pgdp, pgd);
-	dsb(ishst);
-	isb();
+	queue_pte_barriers();
 }
 
 static inline void pgd_clear(pgd_t *pgdp)
@@ -1301,16 +1390,37 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
 
-static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pte_t *ptep)
+static inline pte_t __ptep_get_and_clear_anysz(struct mm_struct *mm,
+					       pte_t *ptep,
+					       unsigned long pgsize)
 {
 	pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
 
-	page_table_check_pte_clear(mm, pte);
+	switch (pgsize) {
+	case PAGE_SIZE:
+		page_table_check_pte_clear(mm, pte);
+		break;
+	case PMD_SIZE:
+		page_table_check_pmd_clear(mm, pte_pmd(pte));
+		break;
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		page_table_check_pud_clear(mm, pte_pud(pte));
+		break;
+#endif
+	default:
+		VM_WARN_ON(1);
+	}
 
 	return pte;
 }
 
+static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	return __ptep_get_and_clear_anysz(mm, ptep, PAGE_SIZE);
+}
+
 static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, unsigned int nr, int full)
 {
@@ -1347,11 +1457,7 @@ static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm,
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp)
 {
-	pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
-
-	page_table_check_pmd_clear(mm, pmd);
-
-	return pmd;
+	return pte_pmd(__ptep_get_and_clear_anysz(mm, (pte_t *)pmdp, PMD_SIZE));
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */