Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "16 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  kasan: fix memory hotplug during boot
  kasan: free allocated shadow memory on MEM_CANCEL_ONLINE
  checkpatch: fix macro argument precedence test
  init/main.c: include <linux/mem_encrypt.h>
  kernel/sys.c: fix potential Spectre v1 issue
  mm/memory_hotplug: fix leftover use of struct page during hotplug
  proc: fix smaps and meminfo alignment
  mm: do not warn on offline nodes unless the specific node is explicitly requested
  mm, memory_hotplug: make has_unmovable_pages more robust
  mm/kasan: don't vfree() nonexistent vm_area
  MAINTAINERS: change hugetlbfs maintainer and update files
  ipc/shm: fix shmat() nil address after round-down when remapping
  Revert "ipc/shm: Fix shmat mmap nil-page protection"
  idr: fix invalid ptr dereference on item delete
  ocfs2: revert "ocfs2/o2hb: check len for bio_add_page() to avoid getting incorrect bio"
  mm: fix nr_rotate_swap leak in swapon() error case

MAINTAINERS

@@ -6503,9 +6503,15 @@ F:	Documentation/networking/hinic.txt
 F:	drivers/net/ethernet/huawei/hinic/
 
 HUGETLB FILESYSTEM
-M:	Nadia Yvette Chambers <nyc@holomorphy.com>
+M:	Mike Kravetz <mike.kravetz@oracle.com>
+L:	linux-mm@kvack.org
 S:	Maintained
 F:	fs/hugetlbfs/
+F:	mm/hugetlb.c
+F:	include/linux/hugetlb.h
+F:	Documentation/admin-guide/mm/hugetlbpage.rst
+F:	Documentation/vm/hugetlbfs_reserv.rst
+F:	Documentation/ABI/testing/sysfs-kernel-mm-hugepages
 
 HVA ST MEDIA DRIVER
 M:	Jean-Christophe Trotin <jean-christophe.trotin@st.com>

drivers/base/node.c

@@ -490,7 +490,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 	return 0;
 }
 
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages,
+		      bool check_nid)
 {
 	unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn;
@@ -514,7 +515,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 
 		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
 
-		ret = register_mem_sect_under_node(mem_blk, nid, true);
+		ret = register_mem_sect_under_node(mem_blk, nid, check_nid);
 		if (!err)
 			err = ret;
 

fs/ocfs2/cluster/heartbeat.c

@@ -570,16 +570,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) {
-			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
-			     "page %p, len %d, vec_len %u, vec_start %u, "
-			     "bi_sector %llu\n", current_page, page, len,
-			     vec_len, vec_start,
-			     (unsigned long long)bio->bi_iter.bi_sector);
-			bio_put(bio);
-			bio = ERR_PTR(-EIO);
-			return bio;
-		}
+		if (len != vec_len) break;
 
 		cs += vec_len / (PAGE_SIZE/spp);
 		vec_start = 0;

fs/seq_file.c

@@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
 	if (m->count + width >= m->size)
 		goto overflow;
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
 	len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
 	if (!len)
 		goto overflow;

include/linux/gfp.h

@@ -464,7 +464,7 @@ static inline struct page *
 __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON(!node_online(nid));
+	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
 
 	return __alloc_pages(gfp_mask, order, nid);
 }

include/linux/node.h

@@ -32,9 +32,11 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages);
+extern int link_mem_sections(int nid, unsigned long start_pfn,
+			     unsigned long nr_pages, bool check_nid);
 #else
-static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+static inline int link_mem_sections(int nid, unsigned long start_pfn,
+				    unsigned long nr_pages, bool check_nid)
 {
 	return 0;
 }
@@ -57,7 +59,7 @@ static inline int register_one_node(int nid)
 		if (error)
 			return error;
 		/* link memory sections under this node */
-		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages);
+		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true);
 	}
 
 	return error;

init/main.c

@@ -91,6 +91,7 @@
 #include <linux/cache.h>
 #include <linux/rodata_test.h>
 #include <linux/jump_label.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>

ipc/shm.c

@@ -1363,14 +1363,17 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 
 	if (addr) {
 		if (addr & (shmlba - 1)) {
-			/*
-			 * Round down to the nearest multiple of shmlba.
-			 * For sane do_mmap_pgoff() parameters, avoid
-			 * round downs that trigger nil-page and MAP_FIXED.
-			 */
-			if ((shmflg & SHM_RND) && addr >= shmlba)
-				addr &= ~(shmlba - 1);
-			else
+			if (shmflg & SHM_RND) {
+				addr &= ~(shmlba - 1);  /* round down */
+
+				/*
+				 * Ensure that the round-down is non-nil
+				 * when remapping. This can happen for
+				 * cases when addr < shmlba.
+				 */
+				if (!addr && (shmflg & SHM_REMAP))
+					goto out;
+			} else
 #ifndef __ARCH_FORCE_SHMLBA
 				if (addr & ~PAGE_MASK)
 #endif

kernel/sys.c

@@ -71,6 +71,9 @@
 #include <asm/io.h>
 #include <asm/unistd.h>
 
+/* Hardening for Spectre-v1 */
+#include <linux/nospec.h>
+
 #include "uid16.h"
 
 #ifndef SET_UNALIGN_CTL
@@ -1453,6 +1456,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
 
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
 	task_lock(current->group_leader);
 	x = current->signal->rlim[resource];
 	task_unlock(current->group_leader);
@@ -1472,6 +1476,7 @@ COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
 
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
 	task_lock(current->group_leader);
 	r = current->signal->rlim[resource];
 	task_unlock(current->group_leader);

lib/radix-tree.c

@@ -2034,10 +2034,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
 			     unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL;
-	void __rcu **slot;
+	void __rcu **slot = NULL;
 	void *entry;
 
 	entry = __radix_tree_lookup(root, index, &node, &slot);
+	if (!slot)
+		return NULL;
 	if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE,
 						get_slot_offset(node, slot))))
 		return NULL;

mm/kasan/kasan.c

@@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5);
 DEFINE_ASAN_SET_SHADOW(f8);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (pgd_none(*pgd))
+		return false;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return false;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return false;
+
+	/*
+	 * We can't use pud_large() or pud_huge(), the first one is
+	 * arch-specific, the last one depends on HUGETLB_PAGE.  So let's abuse
+	 * pud_bad(), if pud is bad then it's bad because it's huge.
+	 */
+	if (pud_bad(*pud))
+		return true;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+
+	if (pmd_bad(*pmd))
+		return true;
+	pte = pte_offset_kernel(pmd, addr);
+	return !pte_none(*pte);
+}
+
 static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 			unsigned long action, void *data)
 {
@@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 	case MEM_GOING_ONLINE: {
 		void *ret;
 
+		/*
+		 * If shadow is mapped already than it must have been mapped
+		 * during the boot. This could happen if we onlining previously
+		 * offlined memory.
+		 */
+		if (shadow_mapped(shadow_start))
+			return NOTIFY_OK;
+
 		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
 					shadow_end, GFP_KERNEL,
 					PAGE_KERNEL, VM_NO_GUARD,
@@ -824,8 +866,26 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 		kmemleak_ignore(ret);
 		return NOTIFY_OK;
 	}
-	case MEM_OFFLINE:
-		vfree((void *)shadow_start);
+	case MEM_CANCEL_ONLINE:
+	case MEM_OFFLINE: {
+		struct vm_struct *vm;
+
+		/*
+		 * shadow_start was either mapped during boot by kasan_init()
+		 * or during memory online by __vmalloc_node_range().
+		 * In the latter case we can use vfree() to free shadow.
+		 * Non-NULL result of the find_vm_area() will tell us if
+		 * that was the second case.
+		 *
+		 * Currently it's not possible to free shadow mapped
+		 * during boot by kasan_init(). It's because the code
+		 * to do that hasn't been written yet. So we'll just
+		 * leak the memory.
+		 */
+		vm = find_vm_area((void *)shadow_start);
+		if (vm)
+			vfree((void *)shadow_start);
+	}
 	}
 
 	return NOTIFY_OK;
@@ -838,5 +898,5 @@ static int __init kasan_memhotplug_init(void)
 	return 0;
 }
 
-module_init(kasan_memhotplug_init);
+core_initcall(kasan_memhotplug_init);
 #endif

mm/memory_hotplug.c

@@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
 		 * nodes have to go through register_node.
 		 * TODO clean up this mess.
 		 */
-		ret = link_mem_sections(nid, start_pfn, nr_pages);
+		ret = link_mem_sections(nid, start_pfn, nr_pages, false);
 register_fail:
 		/*
 		 * If sysfs file of new node can't create, cpu on the node

mm/page_alloc.c

@@ -7598,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 	unsigned long pfn, iter, found;
 
 	/*
-	 * For avoiding noise data, lru_add_drain_all() should be called
-	 * If ZONE_MOVABLE, the zone never contains unmovable pages
+	 * TODO we could make this much more efficient by not checking every
+	 * page in the range if we know all of them are in MOVABLE_ZONE and
+	 * that the movable zone guarantees that pages are migratable but
+	 * the later is not the case right now unfortunatelly. E.g. movablecore
+	 * can still lead to having bootmem allocations in zone_movable.
 	 */
-	if (zone_idx(zone) == ZONE_MOVABLE)
-		return false;
 
 	/*
 	 * CMA allocations (alloc_contig_range) really need to mark isolate
@@ -7623,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		page = pfn_to_page(check);
 
 		if (PageReserved(page))
-			return true;
+			goto unmovable;
 
 		/*
 		 * Hugepages are not in LRU lists, but they're movable.
@@ -7673,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * page at boot.
 		 */
 		if (found > count)
-			return true;
+			goto unmovable;
 	}
 	return false;
+unmovable:
+	WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+	return true;
 }
 
 bool is_pageblock_removable_nolock(struct page *page)

mm/swapfile.c

@@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	unsigned long *frontswap_map = NULL;
 	struct page *page = NULL;
 	struct inode *inode = NULL;
+	bool inced_nr_rotate_swap = false;
 
 	if (swap_flags & ~SWAP_FLAGS_VALID)
 		return -EINVAL;
@@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
 			cluster_set_null(&cluster->index);
 		}
-	} else
+	} else {
 		atomic_inc(&nr_rotate_swap);
+		inced_nr_rotate_swap = true;
+	}
 
 	error = swap_cgroup_swapon(p->type, maxpages);
 	if (error)
@@ -3307,6 +3310,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	vfree(swap_map);
 	kvfree(cluster_info);
 	kvfree(frontswap_map);
+	if (inced_nr_rotate_swap)
+		atomic_dec(&nr_rotate_swap);
 	if (swap_file) {
 		if (inode && S_ISREG(inode->i_mode)) {
 			inode_unlock(inode);

scripts/checkpatch.pl

@@ -5041,7 +5041,7 @@ sub process {
 				$tmp_stmt =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g;
 				$tmp_stmt =~ s/\#+\s*$arg\b//g;
 				$tmp_stmt =~ s/\b$arg\s*\#\#//g;
-				my $use_cnt = $tmp_stmt =~ s/\b$arg\b//g;
+				my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g;
 				if ($use_cnt > 1) {
 					CHK("MACRO_ARG_REUSE",
 					    "Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx");

tools/testing/radix-tree/idr-test.c

@@ -252,6 +252,13 @@ void idr_checks(void)
 	idr_remove(&idr, 3);
 	idr_remove(&idr, 0);
 
+	assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == 0);
+	idr_remove(&idr, 1);
+	for (i = 1; i < RADIX_TREE_MAP_SIZE; i++)
+		assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == i);
+	idr_remove(&idr, 1 << 30);
+	idr_destroy(&idr);
+
 	for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) {
 		struct item *item = item_create(i, 0);
 		assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);