Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - various misc bits

 - DAX updates

 - OCFS2

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (119 commits)
  mm,fork: introduce MADV_WIPEONFORK
  x86,mpx: make mpx depend on x86-64 to free up VMA flag
  mm: add /proc/pid/smaps_rollup
  mm: hugetlb: clear target sub-page last when clearing huge page
  mm: oom: let oom_reap_task and exit_mmap run concurrently
  swap: choose swap device according to numa node
  mm: replace TIF_MEMDIE checks by tsk_is_oom_victim
  mm, oom: do not rely on TIF_MEMDIE for memory reserves access
  z3fold: use per-cpu unbuddied lists
  mm, swap: don't use VMA based swap readahead if HDD is used as swap
  mm, swap: add sysfs interface for VMA based swap readahead
  mm, swap: VMA based swap readahead
  mm, swap: fix swap readahead marking
  mm, swap: add swap readahead hit statistics
  mm/vmalloc.c: don't reinvent the wheel but use existing llist API
  mm/vmstat.c: fix wrong comment
  selftests/memfd: add memfd_create hugetlbfs selftest
  mm/shmem: add hugetlbfs support to memfd_create()
  mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups
  mm/vmalloc.c: halve the number of comparisons performed in pcpu_get_vm_areas()
  ...

4 files changed, 51 insertions, 40 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index df2e0f14a95d..f64fc967a9ef 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4100,9 +4100,6 @@ static void offline_css(struct cgroup_subsys_state *css)
 	if (!(css->flags & CSS_ONLINE))
 		return;
 
-	if (ss->css_reset)
-		ss->css_reset(css);
-
 	if (ss->css_offline)
 		ss->css_offline(css);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2f4039bafebb..e7485786db9b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -56,6 +56,7 @@
 #include <linux/time64.h>
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
+#include <linux/oom.h>
 
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
@@ -2500,12 +2501,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * If we're in interrupt, yes, we can always allocate.  If @node is set in
  * current's mems_allowed, yes.  If it's not a __GFP_HARDWALL request and this
  * node is set in the nearest hardwalled cpuset ancestor to current's cpuset,
- * yes.  If current has access to memory reserves due to TIF_MEMDIE, yes.
+ * yes.  If current has access to memory reserves as an oom victim, yes.
  * Otherwise, no.
  *
  * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
  * and do not allow allocations outside the current tasks cpuset
- * unless the task has been OOM killed as is marked TIF_MEMDIE.
+ * unless the task has been OOM killed.
  * GFP_KERNEL allocations are not so marked, so can escape to the
  * nearest enclosing hardwalled ancestor cpuset.
  *
@@ -2528,7 +2529,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
  * affect that:
  *	in_interrupt - any node ok (current task context irrelevant)
  *	GFP_ATOMIC   - any node ok
- *	TIF_MEMDIE   - any node ok
+ *	tsk_is_oom_victim   - any node ok
  *	GFP_KERNEL   - any node in enclosing hardwalled cpuset ok
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  */
@@ -2546,7 +2547,7 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+	if (unlikely(tsk_is_oom_victim(current)))
 		return true;
 	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
 		return false;
diff --git a/kernel/fork.c b/kernel/fork.c
index 4e5345c07344..24a4c0be80d5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -657,7 +657,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		retval = dup_userfaultfd(tmp, &uf);
 		if (retval)
 			goto fail_nomem_anon_vma_fork;
-		if (anon_vma_fork(tmp, mpnt))
+		if (tmp->vm_flags & VM_WIPEONFORK) {
+			/* VM_WIPEONFORK gets a clean slate in the child. */
+			tmp->anon_vma = NULL;
+			if (anon_vma_prepare(tmp))
+				goto fail_nomem_anon_vma_fork;
+		} else if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
 		tmp->vm_next = tmp->vm_prev = NULL;
@@ -701,7 +706,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		rb_parent = &tmp->vm_rb;
 
 		mm->map_count++;
-		retval = copy_page_range(mm, oldmm, mpnt);
+		if (!(tmp->vm_flags & VM_WIPEONFORK))
+			retval = copy_page_range(mm, oldmm, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
@@ -922,7 +928,6 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
-	set_bit(MMF_OOM_SKIP, &mm->flags);
 	mmdrop(mm);
 }
 
@@ -938,22 +943,6 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
-#ifdef CONFIG_MMU
-static void mmput_async_fn(struct work_struct *work)
-{
-	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
-	__mmput(mm);
-}
-
-void mmput_async(struct mm_struct *mm)
-{
-	if (atomic_dec_and_test(&mm->mm_users)) {
-		INIT_WORK(&mm->async_put_work, mmput_async_fn);
-		schedule_work(&mm->async_put_work);
-	}
-}
-#endif
-
 /**
  * set_mm_exe_file - change a reference to the mm's executable file
  *
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 9afdc434fb49..066e73c2fcc9 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -194,18 +194,41 @@ struct page_map {
 	struct vmem_altmap altmap;
 };
 
-static void pgmap_radix_release(struct resource *res)
+static unsigned long order_at(struct resource *res, unsigned long pgoff)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
+	unsigned long nr_pages, mask;
 
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
-	align_end = align_start + align_size - 1;
+	nr_pages = PHYS_PFN(resource_size(res));
+	if (nr_pages == pgoff)
+		return ULONG_MAX;
+
+	/*
+	 * What is the largest aligned power-of-2 range available from
+	 * this resource pgoff to the end of the resource range,
+	 * considering the alignment of the current pgoff?
+	 */
+	mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
+	if (!mask)
+		return ULONG_MAX;
+
+	return find_first_bit(&mask, BITS_PER_LONG);
+}
+
+#define foreach_order_pgoff(res, order, pgoff) \
+	for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
+			pgoff += 1UL << order, order = order_at((res), pgoff))
+
+static void pgmap_radix_release(struct resource *res)
+{
+	unsigned long pgoff, order;
 
 	mutex_lock(&pgmap_lock);
-	for (key = res->start; key <= res->end; key += SECTION_SIZE)
-		radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT);
+	foreach_order_pgoff(res, order, pgoff)
+		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
 	mutex_unlock(&pgmap_lock);
+
+	synchronize_rcu();
 }
 
 static unsigned long pfn_first(struct page_map *page_map)
@@ -268,7 +291,7 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT);
+	page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
 	return page_map ? &page_map->pgmap : NULL;
 }
 
@@ -293,12 +316,12 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
-	resource_size_t key, align_start, align_size, align_end;
+	resource_size_t align_start, align_size, align_end;
+	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
 	int error, nid, is_ram;
-	unsigned long pfn;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -337,11 +360,12 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	mutex_lock(&pgmap_lock);
 	error = 0;
 	align_end = align_start + align_size - 1;
-	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
+
+	foreach_order_pgoff(res, order, pgoff) {
 		struct dev_pagemap *dup;
 
 		rcu_read_lock();
-		dup = find_dev_pagemap(key);
+		dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff));
 		rcu_read_unlock();
 		if (dup) {
 			dev_err(dev, "%s: %pr collides with mapping for %s\n",
@@ -349,8 +373,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 			error = -EBUSY;
 			break;
 		}
-		error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT,
-				page_map);
+		error = __radix_tree_insert(&pgmap_radix,
+				PHYS_PFN(res->start) + pgoff, order, page_map);
 		if (error) {
 			dev_err(dev, "%s: failed: %d\n", __func__, error);
 			break;