1 files changed, 14 insertions, 123 deletions

diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 2c7e801ab20..c695943a513 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -24,119 +24,13 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/hugetlb.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 
-#include "mmu_decl.h"
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-#ifdef CONFIG_SMP
-
-/*
- * Handle batching of page table freeing on SMP. Page tables are
- * queued up and send to be freed later by RCU in order to avoid
- * freeing a page table page that is being walked without locks
- */
-
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-	struct rcu_head	rcu;
-	unsigned int	index;
-	unsigned long	tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-	  / sizeof(unsigned long))
-
-static void pte_free_smp_sync(void *arg)
-{
-	/* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(void *table, unsigned shift)
-{
-	pte_freelist_forced_free++;
-
-	smp_call_function(pte_free_smp_sync, NULL, 1);
-
-	pgtable_free(table, shift);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-	struct pte_freelist_batch *batch =
-		container_of(head, struct pte_freelist_batch, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++) {
-		void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
-		unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
-
-		pgtable_free(table, shift);
-	}
-
-	free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-	call_rcu(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-	unsigned long pgf;
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-		pgtable_free(table, shift);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-		if (*batchp == NULL) {
-			pgtable_free_now(table, shift);
-			return;
-		}
-		(*batchp)->index = 0;
-	}
-	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
-	pgf = (unsigned long)table | shift;
-	(*batchp)->tables[(*batchp)->index++] = pgf;
-	if ((*batchp)->index == PTE_FREELIST_SIZE) {
-		pte_free_submit(*batchp);
-		*batchp = NULL;
-	}
-}
-
-void pte_free_finish(void)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-	if (*batchp == NULL)
-		return;
-	pte_free_submit(*batchp);
-	*batchp = NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 static inline int is_exec_fault(void)
 {
 	return current->thread.regs && TRAP(current->thread.regs) == 0x400;
@@ -175,7 +69,7 @@ struct page * maybe_pte_to_page(pte_t pte)
  * support falls into the same category.
  */
 
-static pte_t set_pte_filter(pte_t pte, unsigned long addr)
+static pte_t set_pte_filter(pte_t pte)
 {
 	pte = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
 	if (pte_looks_normal(pte) && !(cpu_has_feature(CPU_FTR_COHERENT_ICACHE) ||
@@ -184,17 +78,6 @@ static pte_t set_pte_filter(pte_t pte, unsigned long addr)
 		if (!pg)
 			return pte;
 		if (!test_bit(PG_arch_1, &pg->flags)) {
-#ifdef CONFIG_8xx
-			/* On 8xx, cache control instructions (particularly
-			 * "dcbst" from flush_dcache_icache) fault as write
-			 * operation if there is an unpopulated TLB entry
-			 * for the address in question. To workaround that,
-			 * we invalidate the TLB here, thus avoiding dcbst
-			 * misbehaviour.
-			 */
-			/* 8xx doesn't care about PID, size or ind args */
-			_tlbil_va(addr, 0, 0, 0);
-#endif /* CONFIG_8xx */
 			flush_dcache_icache_page(pg);
 			set_bit(PG_arch_1, &pg->flags);
 		}
@@ -214,7 +97,7 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
  * as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
  * instead we "filter out" the exec permission for non clean pages.
  */
-static pte_t set_pte_filter(pte_t pte, unsigned long addr)
+static pte_t set_pte_filter(pte_t pte)
 {
 	struct page *pg;
 
@@ -290,13 +173,13 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		pte_t pte)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_present(*ptep));
+	WARN_ON(pte_val(*ptep) & _PAGE_PRESENT);
 #endif
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
 	 * is called.
 	 */
-	pte = set_pte_filter(pte, addr);
+	pte = set_pte_filter(pte);
 
 	/* Perform the setting of the PTE */
 	__set_pte_at(mm, addr, ptep, pte, 0);
@@ -316,7 +199,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	entry = set_access_flags_filter(entry, vma, dirty);
 	changed = !pte_same(*(ptep), entry);
 	if (changed) {
-		if (!(vma->vm_flags & VM_HUGETLB))
+		if (!is_vm_hugetlb_page(vma))
 			assert_pte_locked(vma->vm_mm, address);
 		__ptep_set_access_flags(ptep, entry);
 		flush_tlb_page_nohash(vma, address);
@@ -338,6 +221,14 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 	pud = pud_offset(pgd, addr);
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, addr);
+	/*
+	 * khugepaged to collapse normal pages to hugepage, first set
+	 * pmd to none to force page fault/gup to take mmap_sem. After
+	 * pmd is set to none, we do a pte_clear which does this assertion
+	 * so if we find pmd none, return.
+	 */
+	if (pmd_none(*pmd))
+		return;
 	BUG_ON(!pmd_present(*pmd));
 	assert_spin_locked(pte_lockptr(mm, pmd));
 }