Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - VMAP_STACK support, allowing the kernel stacks to be allocated in the
   vmalloc space with a guard page for trapping stack overflows. One of
   the patches introduces THREAD_ALIGN and changes the generic
   alloc_thread_stack_node() to use this instead of THREAD_SIZE (no
   functional change for other architectures)

 - Contiguous PTE hugetlb support re-enabled (after being reverted a
   couple of times). We now have the semantics agreed in the generic mm
   layer together with API improvements so that the architecture code
   can detect between contiguous and non-contiguous huge PTEs

 - Initial support for persistent memory on ARM: DC CVAP instruction
   exposed to user space (HWCAP) and the in-kernel pmem API implemented

 - raid6 improvements for arm64: faster algorithm for the delta syndrome
   and implementation of the recovery routines using Neon

 - FP/SIMD refactoring and removal of support for Neon in interrupt
   context. This is in preparation for full SVE support

 - PTE accessors converted from inline asm to cmpxchg so that we can use
   LSE atomics if available (ARMv8.1)

 - Perf support for Cortex-A35 and A73

 - Non-urgent fixes and cleanups

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits)
  arm64: cleanup {COMPAT_,}SET_PERSONALITY() macro
  arm64: introduce separated bits for mm_context_t flags
  arm64: hugetlb: Cleanup setup_hugepagesz
  arm64: Re-enable support for contiguous hugepages
  arm64: hugetlb: Override set_huge_swap_pte_at() to support contiguous hugepages
  arm64: hugetlb: Override huge_pte_clear() to support contiguous hugepages
  arm64: hugetlb: Handle swap entries in huge_pte_offset() for contiguous hugepages
  arm64: hugetlb: Add break-before-make logic for contiguous entries
  arm64: hugetlb: Spring clean huge pte accessors
  arm64: hugetlb: Introduce pte_pgprot helper
  arm64: hugetlb: set_huge_pte_at Add WARN_ON on !pte_present
  arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores
  arm64: dma-mapping: Mark atomic_pool as __ro_after_init
  arm64: dma-mapping: Do not pass data to gen_pool_set_algo()
  arm64: Remove the !CONFIG_ARM64_HW_AFDBM alternative code paths
  arm64: Ignore hardware dirty bit updates in ptep_set_wrprotect()
  arm64: Move PTE_RDONLY bit handling out of set_pte_at()
  kvm: arm64: Convert kvm_set_s2pte_readonly() from inline asm to cmpxchg()
  arm64: Convert pte handling from inline asm to using (cmp)xchg
  arm64: neon/efi: Make EFI fpsimd save/restore variables static
  ...

5 files changed, 334 insertions, 114 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 83c27b6e6dca..7f1dbe962cf5 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -109,20 +109,25 @@ ENTRY(__clean_dcache_area_pou)
 ENDPROC(__clean_dcache_area_pou)
 
 /*
- *	__dma_inv_area(start, size)
- *	- start   - virtual start address of region
+ *	__inval_dcache_area(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are invalidated. Any partial lines at the ends of the interval are
+ *	also cleaned to PoC to prevent data loss.
+ *
+ *	- kaddr   - kernel address
  *	- size    - size in question
  */
-__dma_inv_area:
-	add	x1, x1, x0
+ENTRY(__inval_dcache_area)
 	/* FALLTHROUGH */
 
 /*
- *	__inval_cache_range(start, end)
- *	- start   - start address of region
- *	- end     - end address of region
+ *	__dma_inv_area(start, size)
+ *	- start   - virtual start address of region
+ *	- size    - size in question
  */
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+	add	x1, x1, x0
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -140,7 +145,7 @@ ENTRY(__inval_cache_range)
 	b.lo	2b
 	dsb	sy
 	ret
-ENDPIPROC(__inval_cache_range)
+ENDPIPROC(__inval_dcache_area)
 ENDPROC(__dma_inv_area)
 
 /*
@@ -167,6 +172,20 @@ ENDPIPROC(__clean_dcache_area_poc)
 ENDPROC(__dma_clean_area)
 
 /*
+ *	__clean_dcache_area_pop(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoP.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_pop)
+	dcache_by_line_op cvap, sy, x0, x1, x2, x3
+	ret
+ENDPIPROC(__clean_dcache_area_pop)
+
+/*
  *	__dma_flush_area(start, size)
  *
  *	clean & invalidate D / U line
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index f27d4dd04384..614af886b7ef 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -42,7 +42,7 @@ static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
 	return prot;
 }
 
-static struct gen_pool *atomic_pool;
+static struct gen_pool *atomic_pool __ro_after_init;
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
 static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
@@ -425,7 +425,7 @@ static int __init atomic_pool_init(void)
 
 		gen_pool_set_algo(atomic_pool,
 				  gen_pool_first_fit_order_align,
-				  (void *)PAGE_SHIFT);
+				  NULL);
 
 		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
 			atomic_pool_size / 1024);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1f22a41565a3..89993c4be1be 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/hugetlb.h>
 
 #include <asm/bug.h>
+#include <asm/cmpxchg.h>
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
 #include <asm/debug-monitors.h>
@@ -82,6 +83,49 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
 }
 #endif
 
+static void data_abort_decode(unsigned int esr)
+{
+	pr_alert("Data abort info:\n");
+
+	if (esr & ESR_ELx_ISV) {
+		pr_alert("  Access size = %u byte(s)\n",
+			 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+		pr_alert("  SSE = %lu, SRT = %lu\n",
+			 (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+			 (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+		pr_alert("  SF = %lu, AR = %lu\n",
+			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+	} else {
+		pr_alert("  ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+	}
+
+	pr_alert("  CM = %lu, WnR = %lu\n",
+		 (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+		 (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+/*
+ * Decode mem abort information
+ */
+static void mem_abort_decode(unsigned int esr)
+{
+	pr_alert("Mem abort info:\n");
+
+	pr_alert("  Exception class = %s, IL = %u bits\n",
+		 esr_get_class_string(esr),
+		 (esr & ESR_ELx_IL) ? 32 : 16);
+	pr_alert("  SET = %lu, FnV = %lu\n",
+		 (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+		 (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+	pr_alert("  EA = %lu, S1PTW = %lu\n",
+		 (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+		 (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+	if (esr_is_data_abort(esr))
+		data_abort_decode(esr);
+}
+
 /*
  * Dump out the page tables associated with 'addr' in the currently active mm.
  */
@@ -139,7 +183,6 @@ void show_pte(unsigned long addr)
 	pr_cont("\n");
 }
 
-#ifdef CONFIG_ARM64_HW_AFDBM
 /*
  * This function sets the access flags (dirty, accessed), as well as write
  * permission, and only to a more permissive setting.
@@ -154,18 +197,13 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  unsigned long address, pte_t *ptep,
 			  pte_t entry, int dirty)
 {
-	pteval_t old_pteval;
-	unsigned int tmp;
+	pteval_t old_pteval, pteval;
 
 	if (pte_same(*ptep, entry))
 		return 0;
 
 	/* only preserve the access flags and write permission */
-	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
-
-	/* set PTE_RDONLY if actual read-only or clean PTE */
-	if (!pte_write(entry) || !pte_sw_dirty(entry))
-		pte_val(entry) |= PTE_RDONLY;
+	pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
@@ -174,21 +212,18 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
 	pte_val(entry) ^= PTE_RDONLY;
-	asm volatile("//	ptep_set_access_flags\n"
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldxr	%0, %2\n"
-	"	eor	%0, %0, %3		// negate PTE_RDONLY in *ptep\n"
-	"	orr	%0, %0, %4		// set flags\n"
-	"	eor	%0, %0, %3		// negate final PTE_RDONLY\n"
-	"	stxr	%w1, %0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (PTE_RDONLY), "r" (pte_val(entry)));
+	pteval = READ_ONCE(pte_val(*ptep));
+	do {
+		old_pteval = pteval;
+		pteval ^= PTE_RDONLY;
+		pteval |= pte_val(entry);
+		pteval ^= PTE_RDONLY;
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+	} while (pteval != old_pteval);
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
 }
-#endif
 
 static bool is_el1_instruction_abort(unsigned int esr)
 {
@@ -248,6 +283,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
 		 addr);
 
+	mem_abort_decode(esr);
+
 	show_pte(addr);
 	die("Oops", regs, esr);
 	bust_spinlocks(0);
@@ -705,6 +742,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
 		 inf->name, esr, addr);
 
+	mem_abort_decode(esr);
+
 	info.si_signo = inf->sig;
 	info.si_errno = 0;
 	info.si_code  = inf->code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 21a8d828cbf4..e36ed5087b5c 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -83,3 +83,19 @@ EXPORT_SYMBOL(flush_dcache_page);
  * Additional functions defined in assembly.
  */
 EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	/* Ensure order against any prior non-cacheable writes */
+	dmb(osh);
+	__clean_dcache_area_pop(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	__inval_dcache_area(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 656e0ece2289..6cb0fa92a651 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,6 +41,16 @@ int pud_huge(pud_t pud)
 #endif
 }
 
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
@@ -58,15 +68,107 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	return CONT_PTES;
 }
 
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+	int contig_ptes = 0;
+
+	*pgsize = size;
+
+	switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE:
+		contig_ptes = 1;
+		break;
+	case CONT_PMD_SIZE:
+		*pgsize = PMD_SIZE;
+		contig_ptes = CONT_PMDS;
+		break;
+	case CONT_PTE_SIZE:
+		*pgsize = PAGE_SIZE;
+		contig_ptes = CONT_PTES;
+		break;
+	}
+
+	return contig_ptes;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	pte_t orig_pte = huge_ptep_get(ptep);
+	bool valid = pte_valid(orig_pte);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+		/*
+		 * If HW_AFDBM is enabled, then the HW could turn on
+		 * the dirty bit for any page in the set, so check
+		 * them all.  All hugetlb entries are already young.
+		 */
+		if (pte_dirty(pte))
+			orig_pte = pte_mkdirty(orig_pte);
+	}
+
+	if (valid)
+		flush_tlb_range(&vma, saddr, addr);
+	return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte)
 {
 	size_t pgsize;
 	int i;
 	int ncontig;
-	unsigned long pfn;
+	unsigned long pfn, dpfn;
 	pgprot_t hugeprot;
 
+	/*
+	 * Code needs to be expanded to handle huge swap and migration
+	 * entries. Needed for HUGETLB and MEMORY_FAILURE.
+	 */
+	WARN_ON(!pte_present(pte));
+
 	if (!pte_cont(pte)) {
 		set_pte_at(mm, addr, ptep, pte);
 		return;
@@ -74,17 +176,30 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
-	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
-	for (i = 0; i < ncontig; i++) {
+	dpfn = pgsize >> PAGE_SHIFT;
+	hugeprot = pte_pgprot(pte);
+
+	clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-		ptep++;
-		pfn += pgsize >> PAGE_SHIFT;
-		addr += pgsize;
 	}
 }
 
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+			  pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, ptep++)
+		set_pte(ptep, pte);
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
@@ -144,19 +259,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	if (sz != PUD_SIZE && pud_none(*pud))
 		return NULL;
-	/* swap or huge page */
-	if (!pud_present(*pud) || pud_huge(*pud))
+	/* hugepage or swap? */
+	if (pud_huge(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 	/* table; check the next level */
 
+	if (sz == CONT_PMD_SIZE)
+		addr &= CONT_PMD_MASK;
+
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+	    pmd_none(*pmd))
 		return NULL;
-	if (!pmd_present(*pmd) || pmd_huge(*pmd))
+	if (pmd_huge(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	if (sz == CONT_PTE_SIZE) {
+		pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
+		return pte;
+	}
+
 	return NULL;
 }
 
@@ -176,111 +300,133 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 	return entry;
 }
 
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+		    pte_t *ptep, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+}
+
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
-	pte_t pte;
+	int ncontig;
+	size_t pgsize;
+	pte_t orig_pte = huge_ptep_get(ptep);
 
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize;
-		bool is_dirty = false;
-
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		/* save the 1st pte to return */
-		pte = ptep_get_and_clear(mm, addr, ptep);
-		for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
-			/*
-			 * If HW_AFDBM is enabled, then the HW could
-			 * turn on the dirty bit for any of the page
-			 * in the set, so check them all.
-			 */
-			++ptep;
-			if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
-				is_dirty = true;
-		}
-		if (is_dirty)
-			return pte_mkdirty(pte);
-		else
-			return pte;
-	} else {
+	if (!pte_cont(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
-	}
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+
+	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	if (pte_cont(pte)) {
-		int ncontig, i, changed = 0;
-		size_t pgsize = 0;
-		unsigned long pfn = pte_pfn(pte);
-		/* Select all bits except the pfn */
-		pgprot_t hugeprot =
-			__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
-				 pte_val(pte));
-
-		pfn = pte_pfn(pte);
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize) {
-			changed |= ptep_set_access_flags(vma, addr, ptep,
-							pfn_pte(pfn,
-								hugeprot),
-							dirty);
-			pfn += pgsize >> PAGE_SHIFT;
-		}
-		return changed;
-	} else {
+	int ncontig, i, changed = 0;
+	size_t pgsize = 0;
+	unsigned long pfn = pte_pfn(pte), dpfn;
+	pgprot_t hugeprot;
+	pte_t orig_pte;
+
+	if (!pte_cont(pte))
 		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-	}
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	if (!pte_same(orig_pte, pte))
+		changed = 1;
+
+	/* Make sure we don't lose the dirty state */
+	if (pte_dirty(orig_pte))
+		pte = pte_mkdirty(pte);
+
+	hugeprot = pte_pgprot(pte);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+
+	return changed;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
-
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_set_wrprotect(mm, addr, ptep);
-	} else {
+	unsigned long pfn, dpfn;
+	pgprot_t hugeprot;
+	int ncontig, i;
+	size_t pgsize;
+	pte_t pte;
+
+	if (!pte_cont(*ptep)) {
 		ptep_set_wrprotect(mm, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+	pte = pte_wrprotect(pte);
+
+	hugeprot = pte_pgprot(pte);
+	pfn = pte_pfn(pte);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 }
 
 void huge_ptep_clear_flush(struct vm_area_struct *vma,
 			   unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
-
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_clear_flush(vma, addr, ptep);
-	} else {
+	size_t pgsize;
+	int ncontig;
+
+	if (!pte_cont(*ptep)) {
 		ptep_clear_flush(vma, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
 }
 
 static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
 
-	if (ps == PMD_SIZE) {
-		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
-	} else if (ps == PUD_SIZE) {
-		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else {
-		hugetlb_bad_size();
-		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
-		return 0;
+	switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE * CONT_PMDS:
+	case PMD_SIZE:
+	case PAGE_SIZE * CONT_PTES:
+		hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+		return 1;
 	}
-	return 1;
+
+	hugetlb_bad_size();
+	pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+	return 0;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif