Merge branch 'akpm' (Andrew's patch-bomb)

Merge patches from Andrew Morton:
 "A few misc things and very nearly all of the MM tree.  A tremendous
  amount of stuff (again), including a significant rbtree library
  rework."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (160 commits)
  sparc64: Support transparent huge pages.
  mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd().
  mm: Add and use update_mmu_cache_pmd() in transparent huge page code.
  sparc64: Document PGD and PMD layout.
  sparc64: Eliminate PTE table memory wastage.
  sparc64: Halve the size of PTE tables
  sparc64: Only support 4MB huge pages and 8KB base pages.
  memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning
  mm: memcg: clean up mm_match_cgroup() signature
  mm: document PageHuge somewhat
  mm: use %pK for /proc/vmallocinfo
  mm, thp: fix mlock statistics
  mm, thp: fix mapped pages avoiding unevictable list on mlock
  memory-hotplug: update memory block's state and notify userspace
  memory-hotplug: preparation to notify memory block's state at memory hot remove
  mm: avoid section mismatch warning for memblock_type_name
  make GFP_NOTRACK definition unconditional
  cma: decrease cc.nr_migratepages after reclaiming pagelist
  CMA: migrate mlocked pages
  kpageflags: fix wrong KPF_THP on non-huge compound pages
  ...

6 files changed, 21 insertions, 41 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 29e090c..f4a7756 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1151,7 +1151,6 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 	const struct cred *cred;
 	char name[sizeof(tsk->comm)];
 	struct mm_struct *mm = tsk->mm;
-	struct vm_area_struct *vma;
 	char *tty;
 
 	if (!ab)
@@ -1191,16 +1190,8 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 
 	if (mm) {
 		down_read(&mm->mmap_sem);
-		vma = mm->mmap;
-		while (vma) {
-			if ((vma->vm_flags & VM_EXECUTABLE) &&
-			    vma->vm_file) {
-				audit_log_d_path(ab, " exe=",
-						 &vma->vm_file->f_path);
-				break;
-			}
-			vma = vma->vm_next;
-		}
+		if (mm->exe_file)
+			audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
 		up_read(&mm->mmap_sem);
 	}
 	audit_log_task_context(ab);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f560598..42bd331 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -80,6 +80,10 @@ void put_online_cpus(void)
 	if (cpu_hotplug.active_writer == current)
 		return;
 	mutex_lock(&cpu_hotplug.lock);
+
+	if (WARN_ON(!cpu_hotplug.refcount))
+		cpu_hotplug.refcount++; /* try to fix things up */
+
 	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
 		wake_up_process(cpu_hotplug.active_writer);
 	mutex_unlock(&cpu_hotplug.lock);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f16f3c5..cda3ebd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3671,7 +3671,7 @@ unlock:
 		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = &perf_mmap_vmops;
 
 	return ret;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 912ef48..98256bc 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -141,10 +141,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	spinlock_t *ptl;
 	pte_t *ptep;
 	int err;
+	/* For mmu_notifiers */
+	const unsigned long mmun_start = addr;
+	const unsigned long mmun_end   = addr + PAGE_SIZE;
 
 	/* For try_to_free_swap() and munlock_vma_page() below */
 	lock_page(page);
 
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
 	if (!ptep)
@@ -173,6 +177,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;
 }
@@ -735,7 +740,6 @@ static struct map_info *
 build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 {
 	unsigned long pgoff = offset >> PAGE_SHIFT;
-	struct prio_tree_iter iter;
 	struct vm_area_struct *vma;
 	struct map_info *curr = NULL;
 	struct map_info *prev = NULL;
@@ -744,7 +748,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 
  again:
 	mutex_lock(&mapping->i_mmap_mutex);
-	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		if (!valid_vma(vma, is_register))
 			continue;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a2b1efc..1cd7d581 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -423,7 +423,12 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 				mapping->i_mmap_writable++;
 			flush_dcache_mmap_lock(mapping);
 			/* insert tmp into the share list, just after mpnt */
-			vma_prio_tree_add(tmp, mpnt);
+			if (unlikely(tmp->vm_flags & VM_NONLINEAR))
+				vma_nonlinear_insert(tmp,
+						&mapping->i_mmap_nonlinear);
+			else
+				vma_interval_tree_insert_after(tmp, mpnt,
+							&mapping->i_mmap);
 			flush_dcache_mmap_unlock(mapping);
 			mutex_unlock(&mapping->i_mmap_mutex);
 		}
@@ -622,26 +627,6 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
-/*
- * We added or removed a vma mapping the executable. The vmas are only mapped
- * during exec and are not mapped with the mmap system call.
- * Callers must hold down_write() on the mm's mmap_sem for these
- */
-void added_exe_file_vma(struct mm_struct *mm)
-{
-	mm->num_exe_file_vmas++;
-}
-
-void removed_exe_file_vma(struct mm_struct *mm)
-{
-	mm->num_exe_file_vmas--;
-	if ((mm->num_exe_file_vmas == 0) && mm->exe_file) {
-		fput(mm->exe_file);
-		mm->exe_file = NULL;
-	}
-
-}
-
 void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
 	if (new_exe_file)
@@ -649,15 +634,13 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 	if (mm->exe_file)
 		fput(mm->exe_file);
 	mm->exe_file = new_exe_file;
-	mm->num_exe_file_vmas = 0;
 }
 
 struct file *get_mm_exe_file(struct mm_struct *mm)
 {
 	struct file *exe_file;
 
-	/* We need mmap_sem to protect against races with removal of
-	 * VM_EXECUTABLE vmas */
+	/* We need mmap_sem to protect against races with removal of exe_file */
 	down_read(&mm->mmap_sem);
 	exe_file = mm->exe_file;
 	if (exe_file)
@@ -1078,7 +1061,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	init_rwsem(&sig->group_rwsem);
 #endif
 
-	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c2a2f80..26f65ea 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1549,8 +1549,7 @@ static struct ctl_table fs_table[] = {
 };
 
 static struct ctl_table debug_table[] = {
-#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \
-    defined(CONFIG_S390) || defined(CONFIG_TILE) || defined(CONFIG_ARM64)
+#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
 	{
 		.procname	= "exception-trace",
 		.data		= &show_unhandled_signals,