Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "19 patches.

  Subsystems affected by this patch series: MAINTAINERS, ipc, fork,
  checkpatch, lib, and mm (memcg, slub, pagemap, madvise, migration,
  hugetlb)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  include/linux/log2.h: add missing () around n in roundup_pow_of_two()
  mm/khugepaged.c: fix khugepaged's request size in collapse_file
  mm/hugetlb: fix a race between hugetlb sysctl handlers
  mm/hugetlb: try preferred node first when alloc gigantic page from cma
  mm/migrate: preserve soft dirty in remove_migration_pte()
  mm/migrate: remove unnecessary is_zone_device_page() check
  mm/rmap: fixup copying of soft dirty and uffd ptes
  mm/migrate: fixup setting UFFD_WP flag
  mm: madvise: fix vma user-after-free
  checkpatch: fix the usage of capture group ( ... )
  fork: adjust sysctl_max_threads definition to match prototype
  ipc: adjust proc_ipc_sem_dointvec definition to match prototype
  mm: track page table modifications in __apply_to_page_range()
  MAINTAINERS: IA64: mark Status as Odd Fixes only
  MAINTAINERS: add LLVM maintainers
  MAINTAINERS: update Cavium/Marvell entries
  mm: slub: fix conversion of freelist_corrupted()
  mm: memcg: fix memcg reclaim soft lockup
  memcg: fix use-after-free in uncharge_batch

9 files changed, 108 insertions, 46 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..67fc6383995b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1250,21 +1250,32 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
 #ifdef CONFIG_CMA
 	{
 		struct page *page;
 		int node;
 
-		for_each_node_mask(node, *nodemask) {
-			if (!hugetlb_cma[node])
-				continue;
-
-			page = cma_alloc(hugetlb_cma[node], nr_pages,
-					 huge_page_order(h), true);
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
 			if (page)
 				return page;
 		}
+
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
+
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
 	}
 #endif
 
@@ -3454,6 +3465,22 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void *buffer, size_t *length, loff_t *ppos)
@@ -3465,9 +3492,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3510,9 +3536,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index e749e568e1ea..cfa0dba5fd3b 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1709,7 +1709,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				page_cache_sync_readahead(mapping, &file->f_ra,
 							  file, index,
-							  PAGE_SIZE);
+							  end - index);
 				/* drain pagevecs to help isolate_lru_page() */
 				lru_add_drain();
 				page = find_lock_page(mapping, index);
diff --git a/mm/madvise.c b/mm/madvise.c
index dd1d43cf026d..d4aa5f776543 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -289,9 +289,9 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	 */
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
-	mmap_read_unlock(current->mm);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	mmap_read_unlock(current->mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
 	mmap_read_lock(current->mm);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..cfa6cbad21d5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6774,6 +6774,9 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
+
+	/* drop reference from uncharge_page */
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6797,6 +6800,9 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 			uncharge_gather_clear(ug);
 		}
 		ug->memcg = page->mem_cgroup;
+
+		/* pairs with css_put in uncharge_batch */
+		css_get(&ug->memcg->css);
 	}
 
 	nr_pages = compound_nr(page);
diff --git a/mm/memory.c b/mm/memory.c
index 148eafb8cbb1..469af373ae76 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -73,6 +73,7 @@
 #include <linux/numa.h>
 #include <linux/perf_event.h>
 #include <linux/ptrace.h>
+#include <linux/vmalloc.h>
 
 #include <trace/events/kmem.h>
 
@@ -83,6 +84,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+#include "pgalloc-track.h"
 #include "internal.h"
 
 #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
@@ -2206,7 +2208,8 @@ EXPORT_SYMBOL(vm_iomap_memory);
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
 	int err = 0;
@@ -2214,7 +2217,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 	if (create) {
 		pte = (mm == &init_mm) ?
-			pte_alloc_kernel(pmd, addr) :
+			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
@@ -2235,6 +2238,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				break;
 		}
 	} while (addr += PAGE_SIZE, addr != end);
+	*mask |= PGTBL_PTE_MODIFIED;
 
 	arch_leave_lazy_mmu_mode();
 
@@ -2245,7 +2249,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -2254,7 +2259,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	BUG_ON(pud_huge(*pud));
 
 	if (create) {
-		pmd = pmd_alloc(mm, pud, addr);
+		pmd = pmd_alloc_track(mm, pud, addr, mask);
 		if (!pmd)
 			return -ENOMEM;
 	} else {
@@ -2264,7 +2269,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (create || !pmd_none_or_clear_bad(pmd)) {
 			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2274,14 +2279,15 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	pud_t *pud;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		pud = pud_alloc(mm, p4d, addr);
+		pud = pud_alloc_track(mm, p4d, addr, mask);
 		if (!pud)
 			return -ENOMEM;
 	} else {
@@ -2291,7 +2297,7 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		next = pud_addr_end(addr, end);
 		if (create || !pud_none_or_clear_bad(pud)) {
 			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2301,14 +2307,15 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data, bool create)
+				     pte_fn_t fn, void *data, bool create,
+				     pgtbl_mod_mask *mask)
 {
 	p4d_t *p4d;
 	unsigned long next;
 	int err = 0;
 
 	if (create) {
-		p4d = p4d_alloc(mm, pgd, addr);
+		p4d = p4d_alloc_track(mm, pgd, addr, mask);
 		if (!p4d)
 			return -ENOMEM;
 	} else {
@@ -2318,7 +2325,7 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		next = p4d_addr_end(addr, end);
 		if (create || !p4d_none_or_clear_bad(p4d)) {
 			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
-						 create);
+						 create, mask);
 			if (err)
 				break;
 		}
@@ -2331,8 +2338,9 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 				 void *data, bool create)
 {
 	pgd_t *pgd;
-	unsigned long next;
+	unsigned long start = addr, next;
 	unsigned long end = addr + size;
+	pgtbl_mod_mask mask = 0;
 	int err = 0;
 
 	if (WARN_ON(addr >= end))
@@ -2343,11 +2351,14 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (!create && pgd_none_or_clear_bad(pgd))
 			continue;
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, start + size);
+
 	return err;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..941b89383cf3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -246,13 +246,13 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		else if (pte_swp_uffd_wp(*pvmw.pte))
 			pte = pte_mkuffd_wp(pte);
 
-		if (unlikely(is_zone_device_page(new))) {
-			if (is_device_private_page(new)) {
-				entry = make_device_private_entry(new, pte_write(pte));
-				pte = swp_entry_to_pte(entry);
-				if (pte_swp_uffd_wp(*pvmw.pte))
-					pte = pte_mkuffd_wp(pte);
-			}
+		if (unlikely(is_device_private_page(new))) {
+			entry = make_device_private_entry(new, pte_write(pte));
+			pte = swp_entry_to_pte(entry);
+			if (pte_swp_soft_dirty(*pvmw.pte))
+				pte = pte_swp_mksoft_dirty(pte);
+			if (pte_swp_uffd_wp(*pvmw.pte))
+				pte = pte_swp_mkuffd_wp(pte);
 		}
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -2427,10 +2427,17 @@ again:
 			entry = make_migration_entry(page, mpfn &
 						     MIGRATE_PFN_WRITE);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pte))
-				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pte))
-				swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			if (pte_present(pte)) {
+				if (pte_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			} else {
+				if (pte_swp_soft_dirty(pte))
+					swp_pte = pte_swp_mksoft_dirty(swp_pte);
+				if (pte_swp_uffd_wp(pte))
+					swp_pte = pte_swp_mkuffd_wp(swp_pte);
+			}
 			set_pte_at(mm, addr, ptep, swp_pte);
 
 			/*
diff --git a/mm/rmap.c b/mm/rmap.c
index 83cc459edc40..9425260774a1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1511,9 +1511,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 */
 			entry = make_migration_entry(page, 0);
 			swp_pte = swp_entry_to_pte(entry);
-			if (pte_soft_dirty(pteval))
+
+			/*
+			 * pteval maps a zone device page and is therefore
+			 * a swap pte.
+			 */
+			if (pte_swp_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			if (pte_uffd_wp(pteval))
+			if (pte_swp_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 			/*
diff --git a/mm/slub.c b/mm/slub.c
index 68c02b2eecd9..d4177aecedf6 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -672,12 +672,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 }
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
-	    !check_valid_pointer(s, page, nextfree)) {
-		object_err(s, page, freelist, "Freechain corrupt");
-		freelist = NULL;
+	    !check_valid_pointer(s, page, nextfree) && freelist) {
+		object_err(s, page, *freelist, "Freechain corrupt");
+		*freelist = NULL;
 		slab_fix(s, "Isolate corrupted freechain");
 		return true;
 	}
@@ -1494,7 +1494,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
 static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
-			       void *freelist, void *nextfree)
+			       void **freelist, void *nextfree)
 {
 	return false;
 }
@@ -2184,7 +2184,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 		 * 'freelist' is already corrupted.  So isolate all objects
 		 * starting at 'freelist'.
 		 */
-		if (freelist_corrupted(s, page, freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist, nextfree))
 			break;
 
 		do {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 99e1796eb833..9727dd8e2581 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2615,6 +2615,14 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long reclaimed;
 		unsigned long scanned;
 
+		/*
+		 * This loop can become CPU-bound when target memcgs
+		 * aren't eligible for reclaim - either because they
+		 * don't have any reclaimable pages, or because their
+		 * memory is explicitly protected. Avoid soft lockups.
+		 */
+		cond_resched();
+
 		mem_cgroup_calculate_protection(target_memcg, memcg);
 
 		if (mem_cgroup_below_min(memcg)) {