1 files changed, 97 insertions, 315 deletions

diff --git a/mm/memory.c b/mm/memory.c
index c467102a5cbc..4ad2d293ddc2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -186,253 +186,6 @@ static void check_sync_rss_stat(struct task_struct *task)
 
 #endif /* SPLIT_RSS_COUNTING */
 
-#ifdef HAVE_GENERIC_MMU_GATHER
-
-static bool tlb_next_batch(struct mmu_gather *tlb)
-{
-	struct mmu_gather_batch *batch;
-
-	batch = tlb->active;
-	if (batch->next) {
-		tlb->active = batch->next;
-		return true;
-	}
-
-	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
-		return false;
-
-	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-	if (!batch)
-		return false;
-
-	tlb->batch_count++;
-	batch->next = NULL;
-	batch->nr   = 0;
-	batch->max  = MAX_GATHER_BATCH;
-
-	tlb->active->next = batch;
-	tlb->active = batch;
-
-	return true;
-}
-
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-				unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-
-	/* Is it from 0 to ~0? */
-	tlb->fullmm     = !(start | (end+1));
-	tlb->need_flush_all = 0;
-	tlb->local.next = NULL;
-	tlb->local.nr   = 0;
-	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
-	tlb->active     = &tlb->local;
-	tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-	tlb->page_size = 0;
-
-	__tlb_reset_range(tlb);
-}
-
-static void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	struct mmu_gather_batch *batch;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
-	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
-		free_pages_and_swap_cache(batch->pages, batch->nr);
-		batch->nr = 0;
-	}
-	tlb->active = &tlb->local;
-}
-
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	struct mmu_gather_batch *batch, *next;
-
-	if (force)
-		__tlb_adjust_range(tlb, start, end - start);
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	for (batch = tlb->local.next; batch; batch = next) {
-		next = batch->next;
-		free_pages((unsigned long)batch, 0);
-	}
-	tlb->local.next = NULL;
-}
-
-/* __tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *	handling the additional races in SMP caused by other CPUs caching valid
- *	mappings in their TLBs. Returns the number of free page slots left.
- *	When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
-bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
-{
-	struct mmu_gather_batch *batch;
-
-	VM_BUG_ON(!tlb->end);
-	VM_WARN_ON(tlb->page_size != page_size);
-
-	batch = tlb->active;
-	/*
-	 * Add the page and check if we are full. If so
-	 * force a flush.
-	 */
-	batch->pages[batch->nr++] = page;
-	if (batch->nr == batch->max) {
-		if (!tlb_next_batch(tlb))
-			return true;
-		batch = tlb->active;
-	}
-	VM_BUG_ON_PAGE(batch->nr > batch->max, page);
-
-	return false;
-}
-
-#endif /* HAVE_GENERIC_MMU_GATHER */
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
-/*
- * See the comment near struct mmu_table_batch.
- */
-
-/*
- * If we want tlb_remove_table() to imply TLB invalidates.
- */
-static inline void tlb_table_invalidate(struct mmu_gather *tlb)
-{
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
-	/*
-	 * Invalidate page-table caches used by hardware walkers. Then we still
-	 * need to RCU-sched wait while freeing the pages because software
-	 * walkers can still be in-flight.
-	 */
-	tlb_flush_mmu_tlbonly(tlb);
-#endif
-}
-
-static void tlb_remove_table_smp_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
-	/*
-	 * This isn't an RCU grace period and hence the page-tables cannot be
-	 * assumed to be actually RCU-freed.
-	 *
-	 * It is however sufficient for software page-table walkers that rely on
-	 * IRQ disabling. See the comment near struct mmu_table_batch.
-	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
-	struct mmu_table_batch *batch;
-	int i;
-
-	batch = container_of(head, struct mmu_table_batch, rcu);
-
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch) {
-		tlb_table_invalidate(tlb);
-		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
-		*batch = NULL;
-	}
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch == NULL) {
-		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		if (*batch == NULL) {
-			tlb_table_invalidate(tlb);
-			tlb_remove_table_one(table);
-			return;
-		}
-		(*batch)->nr = 0;
-	}
-
-	(*batch)->tables[(*batch)->nr++] = table;
-	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_table_flush(tlb);
-}
-
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/**
- * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
- * @tlb: the mmu_gather structure to initialize
- * @mm: the mm_struct of the target address space
- * @start: start of the region that will be removed from the page-table
- * @end: end of the region that will be removed from the page-table
- *
- * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm. The @start and @end are set to 0 and -1
- * respectively when @mm is without users and we're going to destroy
- * the full address space (exit/execve).
- */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	arch_tlb_gather_mmu(tlb, mm, start, end);
-	inc_tlb_flush_pending(tlb->mm);
-}
-
-void tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end)
-{
-	/*
-	 * If there are parallel threads are doing PTE changes on same range
-	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
-	 * flush by batching, a thread has stable TLB entry can fail to flush
-	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
-	 * forcefully if we detect parallel PTE batching threads.
-	 */
-	bool force = mm_tlb_flush_nested(tlb->mm);
-
-	arch_tlb_finish_mmu(tlb, start, end, force);
-	dec_tlb_flush_pending(tlb->mm);
-}
-
 /*
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
@@ -1767,19 +1520,16 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
-static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn, pgprot_t prot, bool mkwrite)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	int retval;
 	pte_t *pte, entry;
 	spinlock_t *ptl;
 
-	retval = -ENOMEM;
 	pte = get_locked_pte(mm, addr, &ptl);
 	if (!pte)
-		goto out;
-	retval = -EBUSY;
+		return VM_FAULT_OOM;
 	if (!pte_none(*pte)) {
 		if (mkwrite) {
 			/*
@@ -1787,10 +1537,15 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			 * in may not match the PFN we have mapped if the
 			 * mapped PFN is a writeable COW page.  In the mkwrite
 			 * case we are creating a writable PTE for a shared
-			 * mapping and we expect the PFNs to match.
+			 * mapping and we expect the PFNs to match. If they
+			 * don't match, we are likely racing with block
+			 * allocation and mapping invalidation so just skip the
+			 * update.
 			 */
-			if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn)))
+			if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) {
+				WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
 				goto out_unlock;
+			}
 			entry = *pte;
 			goto out_mkwrite;
 		} else
@@ -1812,56 +1567,32 @@ out_mkwrite:
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
-	retval = 0;
 out_unlock:
 	pte_unmap_unlock(pte, ptl);
-out:
-	return retval;
-}
-
-/**
- * vm_insert_pfn - insert single pfn into user vma
- * @vma: user vma to map to
- * @addr: target user address of this page
- * @pfn: source kernel pfn
- *
- * Similar to vm_insert_page, this allows drivers to insert individual pages
- * they've allocated into a user vma. Same comments apply.
- *
- * This function should only be called from a vm_ops->fault handler, and
- * in that case the handler should return NULL.
- *
- * vma cannot be a COW mapping.
- *
- * As this is called only for pages that do not currently exist, we
- * do not need to flush old virtual caches or the TLB.
- */
-int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn)
-{
-	return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+	return VM_FAULT_NOPAGE;
 }
-EXPORT_SYMBOL(vm_insert_pfn);
 
 /**
- * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot
  * @vma: user vma to map to
  * @addr: target user address of this page
  * @pfn: source kernel pfn
  * @pgprot: pgprot flags for the inserted page
  *
- * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * This is exactly like vmf_insert_pfn(), except that it allows drivers to
  * to override pgprot on a per-page basis.
  *
  * This only makes sense for IO mappings, and it makes no sense for
- * cow mappings.  In general, using multiple vmas is preferable;
- * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * COW mappings.  In general, using multiple vmas is preferable;
+ * vmf_insert_pfn_prot should only be used if using multiple VMAs is
  * impractical.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
  */
-int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot)
 {
-	int ret;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1875,19 +1606,44 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
-		return -EFAULT;
+		return VM_FAULT_SIGBUS;
 
 	if (!pfn_modify_allowed(pfn, pgprot))
-		return -EACCES;
+		return VM_FAULT_SIGBUS;
 
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
-	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
+	return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
 			false);
+}
+EXPORT_SYMBOL(vmf_insert_pfn_prot);
 
-	return ret;
+/**
+ * vmf_insert_pfn - insert single pfn into user vma
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ *
+ * Similar to vm_insert_page, this allows drivers to insert individual pages
+ * they've allocated into a user vma. Same comments apply.
+ *
+ * This function should only be called from a vm_ops->fault handler, and
+ * in that case the handler should return the result of this function.
+ *
+ * vma cannot be a COW mapping.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn)
+{
+	return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
 }
-EXPORT_SYMBOL(vm_insert_pfn_prot);
+EXPORT_SYMBOL(vmf_insert_pfn);
 
 static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 {
@@ -1903,20 +1659,21 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 	return false;
 }
 
-static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn, bool mkwrite)
+static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
+		unsigned long addr, pfn_t pfn, bool mkwrite)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
+	int err;
 
 	BUG_ON(!vm_mixed_ok(vma, pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
-		return -EFAULT;
+		return VM_FAULT_SIGBUS;
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
 	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
-		return -EACCES;
+		return VM_FAULT_SIGBUS;
 
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
@@ -1935,36 +1692,35 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		 * result in pfn_t_has_page() == false.
 		 */
 		page = pfn_to_page(pfn_t_to_pfn(pfn));
-		return insert_page(vma, addr, page, pgprot);
+		err = insert_page(vma, addr, page, pgprot);
+	} else {
+		return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
 	}
-	return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
 }
 
-int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn)
+vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+		pfn_t pfn)
 {
 	return __vm_insert_mixed(vma, addr, pfn, false);
-
 }
-EXPORT_SYMBOL(vm_insert_mixed);
+EXPORT_SYMBOL(vmf_insert_mixed);
 
 /*
  *  If the insertion of PTE failed because someone else already added a
  *  different entry in the mean time, we treat that as success as we assume
  *  the same entry was actually inserted.
  */
-
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn)
 {
-	int err;
-
-	err =  __vm_insert_mixed(vma, addr, pfn, true);
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	if (err < 0 && err != -EBUSY)
-		return VM_FAULT_SIGBUS;
-	return VM_FAULT_NOPAGE;
+	return __vm_insert_mixed(vma, addr, pfn, true);
 }
 EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);
 
@@ -3745,10 +3501,36 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret;
 
-	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
-	if (!vma->vm_ops->fault)
-		ret = VM_FAULT_SIGBUS;
-	else if (!(vmf->flags & FAULT_FLAG_WRITE))
+	/*
+	 * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND
+	 */
+	if (!vma->vm_ops->fault) {
+		/*
+		 * If we find a migration pmd entry or a none pmd entry, which
+		 * should never happen, return SIGBUS
+		 */
+		if (unlikely(!pmd_present(*vmf->pmd)))
+			ret = VM_FAULT_SIGBUS;
+		else {
+			vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm,
+						       vmf->pmd,
+						       vmf->address,
+						       &vmf->ptl);
+			/*
+			 * Make sure this is not a temporary clearing of pte
+			 * by holding ptl and checking again. A R/M/W update
+			 * of pte involves: take ptl, clearing the pte so that
+			 * we don't have concurrent modification by hardware
+			 * followed by an update.
+			 */
+			if (unlikely(pte_none(*vmf->pte)))
+				ret = VM_FAULT_SIGBUS;
+			else
+				ret = VM_FAULT_NOPAGE;
+
+			pte_unmap_unlock(vmf->pte, vmf->ptl);
+		}
+	} else if (!(vmf->flags & FAULT_FLAG_WRITE))
 		ret = do_read_fault(vmf);
 	else if (!(vma->vm_flags & VM_SHARED))
 		ret = do_cow_fault(vmf);