1 files changed, 248 insertions, 192 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 61e66f02656..b73f677f0bb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -182,7 +182,7 @@ void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
 {
 	__sync_task_rss_stat(task, mm);
 }
-#else
+#else /* SPLIT_RSS_COUNTING */
 
 #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member)
 #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member)
@@ -191,8 +191,205 @@ static void check_sync_rss_stat(struct task_struct *task)
 {
 }
 
+#endif /* SPLIT_RSS_COUNTING */
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+
+static int tlb_next_batch(struct mmu_gather *tlb)
+{
+	struct mmu_gather_batch *batch;
+
+	batch = tlb->active;
+	if (batch->next) {
+		tlb->active = batch->next;
+		return 1;
+	}
+
+	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+	if (!batch)
+		return 0;
+
+	batch->next = NULL;
+	batch->nr   = 0;
+	batch->max  = MAX_GATHER_BATCH;
+
+	tlb->active->next = batch;
+	tlb->active = batch;
+
+	return 1;
+}
+
+/* tlb_gather_mmu
+ *	Called to initialize an (on-stack) mmu_gather structure for page-table
+ *	tear-down from @mm. The @fullmm argument is used 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, bool fullmm)
+{
+	tlb->mm = mm;
+
+	tlb->fullmm     = fullmm;
+	tlb->need_flush = 0;
+	tlb->fast_mode  = (num_possible_cpus() == 1);
+	tlb->local.next = NULL;
+	tlb->local.nr   = 0;
+	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+	tlb->active     = &tlb->local;
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	struct mmu_gather_batch *batch;
+
+	if (!tlb->need_flush)
+		return;
+	tlb->need_flush = 0;
+	tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
 #endif
 
+	if (tlb_fast_mode(tlb))
+		return;
+
+	for (batch = &tlb->local; batch; batch = batch->next) {
+		free_pages_and_swap_cache(batch->pages, batch->nr);
+		batch->nr = 0;
+	}
+	tlb->active = &tlb->local;
+}
+
+/* tlb_finish_mmu
+ *	Called at the end of the shootdown operation to free up any resources
+ *	that were required.
+ */
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	struct mmu_gather_batch *batch, *next;
+
+	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().
+ */
+int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	struct mmu_gather_batch *batch;
+
+	tlb->need_flush = 1;
+
+	if (tlb_fast_mode(tlb)) {
+		free_page_and_swap_cache(page);
+		return 1; /* avoid calling tlb_flush_mmu() */
+	}
+
+	batch = tlb->active;
+	batch->pages[batch->nr++] = page;
+	if (batch->nr == batch->max) {
+		if (!tlb_next_batch(tlb))
+			return 0;
+	}
+	VM_BUG_ON(batch->nr > batch->max);
+
+	return batch->max - batch->nr;
+}
+
+#endif /* HAVE_GENERIC_MMU_GATHER */
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+/*
+ * See the comment near struct mmu_table_batch.
+ */
+
+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) {
+		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;
+
+	tlb->need_flush = 1;
+
+	/*
+	 * When there's less then two users of this mm there cannot be a
+	 * concurrent page-table walk.
+	 */
+	if (atomic_read(&tlb->mm->mm_users) < 2) {
+		__tlb_remove_table(table);
+		return;
+	}
+
+	if (*batch == NULL) {
+		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (*batch == NULL) {
+			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 */
+
 /*
  * If a p?d_bad entry is found while walking page tables, report
  * the error, before resetting entry to p?d_none.  Usually (but
@@ -909,26 +1106,24 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	struct mm_struct *mm = tlb->mm;
-	pte_t *pte;
-	spinlock_t *ptl;
+	int force_flush = 0;
 	int rss[NR_MM_COUNTERS];
+	spinlock_t *ptl;
+	pte_t *pte;
 
+again:
 	init_rss_vec(rss);
-
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
 	do {
 		pte_t ptent = *pte;
 		if (pte_none(ptent)) {
-			(*zap_work)--;
 			continue;
 		}
 
-		(*zap_work) -= PAGE_SIZE;
-
 		if (pte_present(ptent)) {
 			struct page *page;
 
@@ -974,7 +1169,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			page_remove_rmap(page);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
-			tlb_remove_page(tlb, page);
+			force_flush = !__tlb_remove_page(tlb, page);
+			if (force_flush)
+				break;
 			continue;
 		}
 		/*
@@ -995,19 +1192,31 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				print_bad_pte(vma, addr, ptent, NULL);
 		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
+	} while (pte++, addr += PAGE_SIZE, addr != end);
 
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
+	/*
+	 * mmu_gather ran out of room to batch pages, we break out of
+	 * the PTE lock to avoid doing the potential expensive TLB invalidate
+	 * and page-free while holding it.
+	 */
+	if (force_flush) {
+		force_flush = 0;
+		tlb_flush_mmu(tlb);
+		if (addr != end)
+			goto again;
+	}
+
 	return addr;
 }
 
 static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pud_t *pud,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -1019,19 +1228,15 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 			if (next-addr != HPAGE_PMD_SIZE) {
 				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
 				split_huge_page_pmd(vma->vm_mm, pmd);
-			} else if (zap_huge_pmd(tlb, vma, pmd)) {
-				(*zap_work)--;
+			} else if (zap_huge_pmd(tlb, vma, pmd))
 				continue;
-			}
 			/* fall through */
 		}
-		if (pmd_none_or_clear_bad(pmd)) {
-			(*zap_work)--;
+		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		}
-		next = zap_pte_range(tlb, vma, pmd, addr, next,
-						zap_work, details);
-	} while (pmd++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
+		cond_resched();
+	} while (pmd++, addr = next, addr != end);
 
 	return addr;
 }
@@ -1039,7 +1244,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pgd_t *pgd,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -1047,13 +1252,10 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud)) {
-			(*zap_work)--;
+		if (pud_none_or_clear_bad(pud))
 			continue;
-		}
-		next = zap_pmd_range(tlb, vma, pud, addr, next,
-						zap_work, details);
-	} while (pud++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+	} while (pud++, addr = next, addr != end);
 
 	return addr;
 }
@@ -1061,7 +1263,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 static unsigned long unmap_page_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma,
 				unsigned long addr, unsigned long end,
-				long *zap_work, struct zap_details *details)
+				struct zap_details *details)
 {
 	pgd_t *pgd;
 	unsigned long next;
@@ -1075,13 +1277,10 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd)) {
-			(*zap_work)--;
+		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		}
-		next = zap_pud_range(tlb, vma, pgd, addr, next,
-						zap_work, details);
-	} while (pgd++, addr = next, (addr != end && *zap_work > 0));
+		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 	mem_cgroup_uncharge_end();
 
@@ -1121,17 +1320,12 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
  * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
  * drops the lock and schedules.
  */
-unsigned long unmap_vmas(struct mmu_gather **tlbp,
+unsigned long unmap_vmas(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, unsigned long start_addr,
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *details)
 {
-	long zap_work = ZAP_BLOCK_SIZE;
-	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
-	int tlb_start_valid = 0;
 	unsigned long start = start_addr;
-	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
-	int fullmm = (*tlbp)->fullmm;
 	struct mm_struct *mm = vma->vm_mm;
 
 	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
@@ -1152,11 +1346,6 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 			untrack_pfn_vma(vma, 0, 0);
 
 		while (start != end) {
-			if (!tlb_start_valid) {
-				tlb_start = start;
-				tlb_start_valid = 1;
-			}
-
 			if (unlikely(is_vm_hugetlb_page(vma))) {
 				/*
 				 * It is undesirable to test vma->vm_file as it
@@ -1169,39 +1358,15 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 				 * Since no pte has actually been setup, it is
 				 * safe to do nothing in this case.
 				 */
-				if (vma->vm_file) {
+				if (vma->vm_file)
 					unmap_hugepage_range(vma, start, end, NULL);
-					zap_work -= (end - start) /
-					pages_per_huge_page(hstate_vma(vma));
-				}
 
 				start = end;
 			} else
-				start = unmap_page_range(*tlbp, vma,
-						start, end, &zap_work, details);
-
-			if (zap_work > 0) {
-				BUG_ON(start != end);
-				break;
-			}
-
-			tlb_finish_mmu(*tlbp, tlb_start, start);
-
-			if (need_resched() ||
-				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-				if (i_mmap_lock) {
-					*tlbp = NULL;
-					goto out;
-				}
-				cond_resched();
-			}
-
-			*tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
-			tlb_start_valid = 0;
-			zap_work = ZAP_BLOCK_SIZE;
+				start = unmap_page_range(tlb, vma, start, end, details);
 		}
 	}
-out:
+
 	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
 	return start;	/* which is now the end (or restart) address */
 }
@@ -1217,16 +1382,15 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size, struct zap_details *details)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	struct mmu_gather *tlb;
+	struct mmu_gather tlb;
 	unsigned long end = address + size;
 	unsigned long nr_accounted = 0;
 
 	lru_add_drain();
-	tlb = tlb_gather_mmu(mm, 0);
+	tlb_gather_mmu(&tlb, mm, 0);
 	update_hiwater_rss(mm);
 	end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details);
-	if (tlb)
-		tlb_finish_mmu(tlb, address, end);
+	tlb_finish_mmu(&tlb, address, end);
 	return end;
 }
 
@@ -2535,96 +2699,11 @@ unwritable_page:
 	return ret;
 }
 
-/*
- * Helper functions for unmap_mapping_range().
- *
- * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
- *
- * We have to restart searching the prio_tree whenever we drop the lock,
- * since the iterator is only valid while the lock is held, and anyway
- * a later vma might be split and reinserted earlier while lock dropped.
- *
- * The list of nonlinear vmas could be handled more efficiently, using
- * a placeholder, but handle it in the same way until a need is shown.
- * It is important to search the prio_tree before nonlinear list: a vma
- * may become nonlinear and be shifted from prio_tree to nonlinear list
- * while the lock is dropped; but never shifted from list to prio_tree.
- *
- * In order to make forward progress despite restarting the search,
- * vm_truncate_count is used to mark a vma as now dealt with, so we can
- * quickly skip it next time around.  Since the prio_tree search only
- * shows us those vmas affected by unmapping the range in question, we
- * can't efficiently keep all vmas in step with mapping->truncate_count:
- * so instead reset them all whenever it wraps back to 0 (then go to 1).
- * mapping->truncate_count and vma->vm_truncate_count are protected by
- * i_mmap_lock.
- *
- * In order to make forward progress despite repeatedly restarting some
- * large vma, note the restart_addr from unmap_vmas when it breaks out:
- * and restart from that address when we reach that vma again.  It might
- * have been split or merged, shrunk or extended, but never shifted: so
- * restart_addr remains valid so long as it remains in the vma's range.
- * unmap_mapping_range forces truncate_count to leap over page-aligned
- * values so we can save vma's restart_addr in its truncate_count field.
- */
-#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
-
-static void reset_vma_truncate_counts(struct address_space *mapping)
-{
-	struct vm_area_struct *vma;
-	struct prio_tree_iter iter;
-
-	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
-		vma->vm_truncate_count = 0;
-	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
-		vma->vm_truncate_count = 0;
-}
-
-static int unmap_mapping_range_vma(struct vm_area_struct *vma,
+static void unmap_mapping_range_vma(struct vm_area_struct *vma,
 		unsigned long start_addr, unsigned long end_addr,
 		struct zap_details *details)
 {
-	unsigned long restart_addr;
-	int need_break;
-
-	/*
-	 * files that support invalidating or truncating portions of the
-	 * file from under mmaped areas must have their ->fault function
-	 * return a locked page (and set VM_FAULT_LOCKED in the return).
-	 * This provides synchronisation against concurrent unmapping here.
-	 */
-
-again:
-	restart_addr = vma->vm_truncate_count;
-	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
-		start_addr = restart_addr;
-		if (start_addr >= end_addr) {
-			/* Top of vma has been split off since last time */
-			vma->vm_truncate_count = details->truncate_count;
-			return 0;
-		}
-	}
-
-	restart_addr = zap_page_range(vma, start_addr,
-					end_addr - start_addr, details);
-	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
-
-	if (restart_addr >= end_addr) {
-		/* We have now completed this vma: mark it so */
-		vma->vm_truncate_count = details->truncate_count;
-		if (!need_break)
-			return 0;
-	} else {
-		/* Note restart_addr in vma's truncate_count field */
-		vma->vm_truncate_count = restart_addr;
-		if (!need_break)
-			goto again;
-	}
-
-	spin_unlock(details->i_mmap_lock);
-	cond_resched();
-	spin_lock(details->i_mmap_lock);
-	return -EINTR;
+	zap_page_range(vma, start_addr, end_addr - start_addr, details);
 }
 
 static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
@@ -2634,12 +2713,8 @@ static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
 	struct prio_tree_iter iter;
 	pgoff_t vba, vea, zba, zea;
 
-restart:
 	vma_prio_tree_foreach(vma, &iter, root,
 			details->first_index, details->last_index) {
-		/* Skip quickly over those we have already dealt with */
-		if (vma->vm_truncate_count == details->truncate_count)
-			continue;
 
 		vba = vma->vm_pgoff;
 		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
@@ -2651,11 +2726,10 @@ restart:
 		if (zea > vea)
 			zea = vea;
 
-		if (unmap_mapping_range_vma(vma,
+		unmap_mapping_range_vma(vma,
 			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
 			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
-				details) < 0)
-			goto restart;
+				details);
 	}
 }
 
@@ -2670,15 +2744,9 @@ static inline void unmap_mapping_range_list(struct list_head *head,
 	 * across *all* the pages in each nonlinear VMA, not just the pages
 	 * whose virtual address lies outside the file truncation point.
 	 */
-restart:
 	list_for_each_entry(vma, head, shared.vm_set.list) {
-		/* Skip quickly over those we have already dealt with */
-		if (vma->vm_truncate_count == details->truncate_count)
-			continue;
 		details->nonlinear_vma = vma;
-		if (unmap_mapping_range_vma(vma, vma->vm_start,
-					vma->vm_end, details) < 0)
-			goto restart;
+		unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
 	}
 }
 
@@ -2717,26 +2785,14 @@ void unmap_mapping_range(struct address_space *mapping,
 	details.last_index = hba + hlen - 1;
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
-	details.i_mmap_lock = &mapping->i_mmap_lock;
 
-	mutex_lock(&mapping->unmap_mutex);
-	spin_lock(&mapping->i_mmap_lock);
-
-	/* Protect against endless unmapping loops */
-	mapping->truncate_count++;
-	if (unlikely(is_restart_addr(mapping->truncate_count))) {
-		if (mapping->truncate_count == 0)
-			reset_vma_truncate_counts(mapping);
-		mapping->truncate_count++;
-	}
-	details.truncate_count = mapping->truncate_count;
 
+	mutex_lock(&mapping->i_mmap_mutex);
 	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-	spin_unlock(&mapping->i_mmap_lock);
-	mutex_unlock(&mapping->unmap_mutex);
+	mutex_unlock(&mapping->i_mmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
@@ -2966,7 +3022,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (prev && prev->vm_end == address)
 			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-		expand_stack(vma, address - PAGE_SIZE);
+		expand_downwards(vma, address - PAGE_SIZE);
 	}
 	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
 		struct vm_area_struct *next = vma->vm_next;