Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Honestly all the conflicts were simple overlapping changes,
nothing really interesting to report.

Signed-off-by: David S. Miller <davem@davemloft.net>

17 files changed, 78 insertions, 90 deletions

diff --git a/mm/dmapool.c b/mm/dmapool.c
index 76a160083506..8c94c89a6f7e 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * DMA Pool allocator
  *
@@ -5,10 +6,6 @@
  * Copyright 2007 Intel Corporation
  *   Author: Matthew Wilcox <willy@linux.intel.com>
  *
- * This software may be redistributed and/or modified under the terms of
- * the GNU General Public License ("GPL") version 2 as published by the
- * Free Software Foundation.
- *
  * This allocator returns small blocks of a given size which are DMA-able by
  * the given device.  It uses the dma_alloc_coherent page allocator to get
  * new pages, then splits them up into blocks of the required size.
diff --git a/mm/hmm.c b/mm/hmm.c
index c5d840e34b28..f702a3895d05 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1354,9 +1354,8 @@ static void hmm_devmem_ref_release(struct percpu_ref *ref)
 	complete(&devmem->completion);
 }
 
-static void hmm_devmem_ref_exit(void *data)
+static void hmm_devmem_ref_exit(struct percpu_ref *ref)
 {
-	struct percpu_ref *ref = data;
 	struct hmm_devmem *devmem;
 
 	devmem = container_of(ref, struct hmm_devmem, ref);
@@ -1433,10 +1432,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	if (ret)
 		return ERR_PTR(ret);
 
-	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit, &devmem->ref);
-	if (ret)
-		return ERR_PTR(ret);
-
 	size = ALIGN(size, PA_SECTION_SIZE);
 	addr = min((unsigned long)iomem_resource.end,
 		   (1UL << MAX_PHYSMEM_BITS) - 1);
@@ -1475,6 +1470,7 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	devmem->pagemap.ref = &devmem->ref;
 	devmem->pagemap.data = devmem;
 	devmem->pagemap.kill = hmm_devmem_ref_kill;
+	devmem->pagemap.cleanup = hmm_devmem_ref_exit;
 
 	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
 	if (IS_ERR(result))
@@ -1512,11 +1508,6 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 	if (ret)
 		return ERR_PTR(ret);
 
-	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit,
-			&devmem->ref);
-	if (ret)
-		return ERR_PTR(ret);
-
 	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
 	devmem->pfn_last = devmem->pfn_first +
 			   (resource_size(devmem->resource) >> PAGE_SHIFT);
@@ -1529,6 +1520,7 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 	devmem->pagemap.ref = &devmem->ref;
 	devmem->pagemap.data = devmem;
 	devmem->pagemap.kill = hmm_devmem_ref_kill;
+	devmem->pagemap.cleanup = hmm_devmem_ref_exit;
 
 	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
 	if (IS_ERR(result))
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a335f7c1fac4..0f7419938008 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1004,6 +1004,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
+	result = SCAN_ANY_PROCESS;
+	if (!mmget_still_valid(mm))
+		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c
index dd3c23a801b1..e19279ff6aa3 100644
--- a/mm/kmemleak-test.c
+++ b/mm/kmemleak-test.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/kmemleak-test.c
  *
  * Copyright (C) 2008 ARM Limited
  * Written by Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #define pr_fmt(fmt) "kmemleak: " fmt
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index e57bf810f798..9dd581d11565 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/kmemleak.c
  *
  * Copyright (C) 2008 ARM Limited
  * Written by Catalin Marinas <catalin.marinas@arm.com>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- *
  * For more information on the algorithm and kmemleak usage, please see
  * Documentation/dev-tools/kmemleak.rst.
  *
diff --git a/mm/list_lru.c b/mm/list_lru.c
index e4709fdaa8e6..927d85be32f6 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -354,7 +354,7 @@ static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
 	}
 	return 0;
 fail:
-	__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
+	__memcg_destroy_list_lru_node(memcg_lrus, begin, i);
 	return -ENOMEM;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ca0bc6e6be13..ba9138a4a1de 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -691,11 +691,12 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->stat[idx], val);
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmstats_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmstats[idx]);
 		x = 0;
@@ -745,11 +746,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__mod_memcg_state(memcg, idx, val);
 
 	/* Update lruvec */
+	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup_per_node *pi;
 
-		atomic_long_add(x, &pn->lruvec_stat_local[idx]);
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
 			atomic_long_add(x, &pi->lruvec_stat[idx]);
 		x = 0;
@@ -771,11 +773,12 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->events[idx], count);
+
 	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
 	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmevents_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmevents[idx]);
 		x = 0;
@@ -790,7 +793,12 @@ static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
 
 static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 {
-	return atomic_long_read(&memcg->vmevents_local[event]);
+	long x = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		x += per_cpu(memcg->vmstats_local->events[event], cpu);
+	return x;
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -2191,11 +2199,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmstats_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmstats[i]);
-			}
 
 			if (i >= NR_VM_NODE_STAT_ITEMS)
 				continue;
@@ -2205,12 +2211,10 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 
 				pn = mem_cgroup_nodeinfo(memcg, nid);
 				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
-				if (x) {
-					atomic_long_add(x, &pn->lruvec_stat_local[i]);
+				if (x)
 					do {
 						atomic_long_add(x, &pn->lruvec_stat[i]);
 					} while ((pn = parent_nodeinfo(pn, nid)));
-				}
 			}
 		}
 
@@ -2218,11 +2222,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmevents_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmevents[i]);
-			}
 		}
 	}
 
@@ -4483,8 +4485,15 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
+	pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat);
+	if (!pn->lruvec_stat_local) {
+		kfree(pn);
+		return 1;
+	}
+
 	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
 	if (!pn->lruvec_stat_cpu) {
+		free_percpu(pn->lruvec_stat_local);
 		kfree(pn);
 		return 1;
 	}
@@ -4506,6 +4515,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 		return;
 
 	free_percpu(pn->lruvec_stat_cpu);
+	free_percpu(pn->lruvec_stat_local);
 	kfree(pn);
 }
 
@@ -4516,6 +4526,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
+	free_percpu(memcg->vmstats_local);
 	kfree(memcg);
 }
 
@@ -4544,6 +4555,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg->id.id < 0)
 		goto fail;
 
+	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
+	if (!memcg->vmstats_local)
+		goto fail;
+
 	memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_percpu)
 		goto fail;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fc8b51744579..8da0334b9ca0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008, 2009 Intel Corporation
  * Authors: Andi Kleen, Fengguang Wu
  *
- * This software may be redistributed and/or modified under the terms of
- * the GNU General Public License ("GPL") version 2 only as published by the
- * Free Software Foundation.
- *
  * High level machine check handler. Handles pages reported by the
  * hardware as being corrupted usually due to a multi-bit ECC memory or cache
  * failure.
diff --git a/mm/mlock.c b/mm/mlock.c
index 080f3b36415b..a90099da4fb4 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -636,11 +636,11 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
  * is also counted.
  * Return value: previously mlocked page counts
  */
-static int count_mm_mlocked_page_nr(struct mm_struct *mm,
+static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
 		unsigned long start, size_t len)
 {
 	struct vm_area_struct *vma;
-	int count = 0;
+	unsigned long count = 0;
 
 	if (mm == NULL)
 		mm = current->mm;
@@ -797,7 +797,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	unsigned long lock_limit;
 	int ret;
 
-	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
+	    flags == MCL_ONFAULT)
 		return -EINVAL;
 
 	if (!can_do_mlock())
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 99740e1dd273..8c943a6e1696 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -245,14 +245,28 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 {
 	/*
 	 * 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.
+	 * under non-exclusive lock (e.g., mmap_sem read-side) but defer TLB
+	 * flush by batching, one thread may end up seeing inconsistent PTEs
+	 * and result in having stale TLB entries.  So flush TLB forcefully
+	 * if we detect parallel PTE batching threads.
+	 *
+	 * However, some syscalls, e.g. munmap(), may free page tables, this
+	 * needs force flush everything in the given range. Otherwise this
+	 * may result in having stale TLB entries for some architectures,
+	 * e.g. aarch64, that could specify flush what level TLB.
 	 */
 	if (mm_tlb_flush_nested(tlb->mm)) {
+		/*
+		 * The aarch64 yields better performance with fullmm by
+		 * avoiding multiple CPUs spamming TLBI messages at the
+		 * same time.
+		 *
+		 * On x86 non-fullmm doesn't yield significant difference
+		 * against fullmm.
+		 */
+		tlb->fullmm = 1;
 		__tlb_reset_range(tlb);
-		__tlb_adjust_range(tlb, start, end - start);
+		tlb->freed_tables = 1;
 	}
 
 	tlb_flush_mmu(tlb);
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 3a2ff5c9192c..20d2b69a13b0 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/percpu-km.c - kernel memory based chunk allocation
  *
  * Copyright (C) 2010		SUSE Linux Products GmbH
  * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  *
- * This file is released under the GPLv2.
- *
  * Chunks are allocated as a contiguous kernel memory using gfp
  * allocation.  This is to be used on nommu architectures.
  *
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index ef5034a0464e..a5a8b22816ff 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/percpu-debug.c
  *
  * Copyright (C) 2017		Facebook Inc.
  * Copyright (C) 2017		Dennis Zhou <dennisz@fb.com>
  *
- * This file is released under the GPLv2.
- *
  * Prints statistics about the percpu allocator and backing chunks.
  */
 #include <linux/debugfs.h>
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index d8078de912de..a2b395acef89 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/percpu-vm.c - vmalloc area based chunk allocation
  *
  * Copyright (C) 2010		SUSE Linux Products GmbH
  * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  *
- * This file is released under the GPLv2.
- *
  * Chunks are mapped into vmalloc areas and populated page by page.
  * This is the default chunk allocator.
  */
diff --git a/mm/percpu.c b/mm/percpu.c
index 2df0ee680ea6..9821241fdede 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/percpu.c - percpu memory allocator
  *
@@ -7,8 +8,6 @@
  * Copyright (C) 2017		Facebook Inc.
  * Copyright (C) 2017		Dennis Zhou <dennisszhou@gmail.com>
  *
- * This file is released under the GPLv2 license.
- *
  * The percpu allocator handles both static and dynamic areas.  Percpu
  * areas are allocated in chunks which are divided into units.  There is
  * a 1-to-1 mapping for units to possible cpus.  These units are grouped
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index d908c8769b48..5e313fa93276 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * rodata_test.c: functional test for mark_rodata_ro function
  *
  * (C) Copyright 2008 Intel Corporation
  * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #define pr_fmt(fmt) "rodata_test: " fmt
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 7350a124524b..4c9e150e5ad3 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2123,9 +2123,9 @@ static inline void set_area_direct_map(const struct vm_struct *area,
 /* Handle removing and resetting vm mappings related to the vm_struct. */
 static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 {
-	unsigned long addr = (unsigned long)area->addr;
 	unsigned long start = ULONG_MAX, end = 0;
 	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+	int flush_dmap = 0;
 	int i;
 
 	/*
@@ -2135,8 +2135,8 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 	 * execute permissions, without leaving a RW+X window.
 	 */
 	if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
-		set_memory_nx(addr, area->nr_pages);
-		set_memory_rw(addr, area->nr_pages);
+		set_memory_nx((unsigned long)area->addr, area->nr_pages);
+		set_memory_rw((unsigned long)area->addr, area->nr_pages);
 	}
 
 	remove_vm_area(area->addr);
@@ -2160,9 +2160,11 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 	 * the vm_unmap_aliases() flush includes the direct map.
 	 */
 	for (i = 0; i < area->nr_pages; i++) {
-		if (page_address(area->pages[i])) {
+		unsigned long addr = (unsigned long)page_address(area->pages[i]);
+		if (addr) {
 			start = min(addr, start);
-			end = max(addr, end);
+			end = max(addr + PAGE_SIZE, end);
+			flush_dmap = 1;
 		}
 	}
 
@@ -2172,7 +2174,7 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 	 * reset the direct map permissions to the default.
 	 */
 	set_area_direct_map(area, set_direct_map_invalid_noflush);
-	_vm_unmap_aliases(start, end, 1);
+	_vm_unmap_aliases(start, end, flush_dmap);
 	set_area_direct_map(area, set_direct_map_default_noflush);
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7acd0afdfc2a..7889f583ced9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1505,7 +1505,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
 		if (page_is_file_cache(page) && !PageDirty(page) &&
-		    !__PageMovable(page)) {
+		    !__PageMovable(page) && !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -1953,8 +1953,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (global_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
-	reclaim_stat->recent_rotated[0] = stat.nr_activate[0];
-	reclaim_stat->recent_rotated[1] = stat.nr_activate[1];
+	reclaim_stat->recent_rotated[0] += stat.nr_activate[0];
+	reclaim_stat->recent_rotated[1] += stat.nr_activate[1];
 
 	move_pages_to_lru(lruvec, &page_list);