Merge tag 'mm-hotfixes-stable-2022-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more hotfixes from Andrew Morton:
 "Seventeen hotfixes.  Mostly memory management things.

  Ten patches are cc:stable, addressing pre-6.0 issues"

* tag 'mm-hotfixes-stable-2022-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  .mailmap: update Luca Ceresoli's e-mail address
  mm/mprotect: only reference swap pfn page if type match
  squashfs: don't call kmalloc in decompressors
  mm/damon/dbgfs: avoid duplicate context directory creation
  mailmap: update email address for Colin King
  asm-generic: sections: refactor memory_intersects
  bootmem: remove the vmemmap pages from kmemleak in put_page_bootmem
  ocfs2: fix freeing uninitialized resource on ocfs2_dlm_shutdown
  Revert "memcg: cleanup racy sum avoidance code"
  mm/zsmalloc: do not attempt to free IS_ERR handle
  binder_alloc: add missing mmap_lock calls when using the VMA
  mm: re-allow pinning of zero pfns (again)
  vmcoreinfo: add kallsyms_num_syms symbol
  mailmap: update Guilherme G. Piccoli's email addresses
  writeback: avoid use-after-free after removing device
  shmem: update folio if shmem_replace_page() updates the page
  mm/hugetlb: avoid corrupting page->mapping in hugetlb_mcopy_atomic_pte

.mailmap

@@ -98,8 +98,7 @@ Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com>
 Christian Marangi <ansuelsmth@gmail.com>
 Christophe Ricard <christophe.ricard@gmail.com>
 Christoph Hellwig <hch@lst.de>
-Colin Ian King <colin.king@intel.com> <colin.king@canonical.com>
-Colin Ian King <colin.king@intel.com> <colin.i.king@gmail.com>
+Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
@@ -150,6 +149,8 @@ Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Guilherme G. Piccoli <kernel@gpiccoli.net> <gpiccoli@linux.vnet.ibm.com>
+Guilherme G. Piccoli <kernel@gpiccoli.net> <gpiccoli@canonical.com>
 Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com>
 Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
@@ -253,6 +254,7 @@ Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
+Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org>

drivers/android/binder_alloc.c

@@ -402,12 +402,15 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	size_t size, data_offsets_size;
 	int ret;
 
+	mmap_read_lock(alloc->vma_vm_mm);
 	if (!binder_alloc_get_vma(alloc)) {
+		mmap_read_unlock(alloc->vma_vm_mm);
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
 				   alloc->pid);
 		return ERR_PTR(-ESRCH);
 	}
+	mmap_read_unlock(alloc->vma_vm_mm);
 
 	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
 		ALIGN(offsets_size, sizeof(void *));
@@ -929,7 +932,14 @@ void binder_alloc_print_pages(struct seq_file *m,
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
+
+	mmap_read_lock(alloc->vma_vm_mm);
+	if (binder_alloc_get_vma(alloc) == NULL) {
+		mmap_read_unlock(alloc->vma_vm_mm);
+		goto uninitialized;
+	}
+
+	mmap_read_unlock(alloc->vma_vm_mm);
 	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
 		page = &alloc->pages[i];
 		if (!page->page_ptr)
@@ -939,7 +949,8 @@ void binder_alloc_print_pages(struct seq_file *m,
 		else
 			lru++;
 	}
-	}
+
+uninitialized:
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);

fs/fs-writeback.c

@@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode,
 
 static void wb_wakeup(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void finish_writeback_work(struct bdi_writeback *wb,
@@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	if (work->done)
 		atomic_inc(&work->done->cnt);
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 
 	if (test_bit(WB_registered, &wb->state)) {
 		list_add_tail(&work->list, &wb->work_list);
@@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	} else
 		finish_writeback_work(wb, work);
 
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 /**
@@ -2082,13 +2082,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!list_empty(&wb->work_list)) {
 		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 	return work;
 }
 

fs/ocfs2/dlmglue.c

@@ -3403,10 +3403,12 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb,
 	ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres);
 	ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres);
 
+	if (osb->cconn) {
 		ocfs2_cluster_disconnect(osb->cconn, hangup_pending);
 		osb->cconn = NULL;
 
 		ocfs2_dlm_shutdown_debug(osb);
+	}
 }
 
 static int ocfs2_drop_lock(struct ocfs2_super *osb,

fs/ocfs2/super.c

@@ -1914,7 +1914,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	    !ocfs2_is_hard_readonly(osb))
 		hangup_needed = 1;
 
-	if (osb->cconn)
 	ocfs2_dlm_shutdown(osb, hangup_needed);
 
 	ocfs2_blockcheck_stats_debugfs_remove(&osb->osb_ecc_stats);

fs/squashfs/file.c

@@ -593,7 +593,7 @@ static void squashfs_readahead(struct readahead_control *ractl)
 
 		res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
 
-		kfree(actor);
+		squashfs_page_actor_free(actor);
 
 		if (res == expected) {
 			int bytes;

fs/squashfs/file_direct.c

@@ -74,7 +74,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
 	/* Decompress directly into the page cache buffers */
 	res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
 
-	kfree(actor);
+	squashfs_page_actor_free(actor);
 
 	if (res < 0)
 		goto mark_errored;

fs/squashfs/page_actor.c

@@ -52,6 +52,7 @@ struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 	actor->buffer = buffer;
 	actor->pages = pages;
 	actor->next_page = 0;
+	actor->tmp_buffer = NULL;
 	actor->squashfs_first_page = cache_first_page;
 	actor->squashfs_next_page = cache_next_page;
 	actor->squashfs_finish_page = cache_finish_page;
@@ -68,20 +69,9 @@ static void *handle_next_page(struct squashfs_page_actor *actor)
 
 	if ((actor->next_page == actor->pages) ||
 			(actor->next_index != actor->page[actor->next_page]->index)) {
-		if (actor->alloc_buffer) {
-			void *tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
-
-			if (tmp_buffer) {
-				actor->tmp_buffer = tmp_buffer;
 		actor->next_index++;
 		actor->returned_pages++;
-				return tmp_buffer;
-			}
-		}
-
-		actor->next_index++;
-		actor->returned_pages++;
-		return ERR_PTR(-ENOMEM);
+		return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM);
 	}
 
 	actor->next_index++;
@@ -96,11 +86,10 @@ static void *direct_first_page(struct squashfs_page_actor *actor)
 
 static void *direct_next_page(struct squashfs_page_actor *actor)
 {
-	if (actor->pageaddr)
+	if (actor->pageaddr) {
 		kunmap_local(actor->pageaddr);
-
-	kfree(actor->tmp_buffer);
-	actor->pageaddr = actor->tmp_buffer = NULL;
+		actor->pageaddr = NULL;
+	}
 
 	return handle_next_page(actor);
 }
@@ -109,8 +98,6 @@ static void direct_finish_page(struct squashfs_page_actor *actor)
 {
 	if (actor->pageaddr)
 		kunmap_local(actor->pageaddr);
-
-	kfree(actor->tmp_buffer);
 }
 
 struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk,
@@ -121,6 +108,16 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
 	if (actor == NULL)
 		return NULL;
 
+	if (msblk->decompressor->alloc_buffer) {
+		actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+
+		if (actor->tmp_buffer == NULL) {
+			kfree(actor);
+			return NULL;
+		}
+	} else
+		actor->tmp_buffer = NULL;
+
 	actor->length = length ? : pages * PAGE_SIZE;
 	actor->page = page;
 	actor->pages = pages;
@@ -128,7 +125,6 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
 	actor->returned_pages = 0;
 	actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1);
 	actor->pageaddr = NULL;
-	actor->tmp_buffer = NULL;
 	actor->alloc_buffer = msblk->decompressor->alloc_buffer;
 	actor->squashfs_first_page = direct_first_page;
 	actor->squashfs_next_page = direct_next_page;

fs/squashfs/page_actor.h

@@ -29,6 +29,11 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
 extern struct squashfs_page_actor *squashfs_page_actor_init_special(
 				struct squashfs_sb_info *msblk,
 				struct page **page, int pages, int length);
+static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor)
+{
+	kfree(actor->tmp_buffer);
+	kfree(actor);
+}
 static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
 {
 	return actor->squashfs_first_page(actor);

include/asm-generic/sections.h

@@ -97,7 +97,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt,
 /**
  * memory_intersects - checks if the region occupied by an object intersects
  *                     with another memory region
- * @begin: virtual address of the beginning of the memory regien
+ * @begin: virtual address of the beginning of the memory region
  * @end: virtual address of the end of the memory region
  * @virt: virtual address of the memory object
  * @size: size of the memory object
@@ -110,7 +110,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt,
 {
 	void *vend = virt + size;
 
-	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+	if (virt < end && vend > begin)
+		return true;
+
+	return false;
 }
 
 /**

include/linux/memcontrol.h

@@ -987,19 +987,30 @@ static inline void mod_memcg_page_state(struct page *page,
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,

include/linux/mm.h

@@ -1544,9 +1544,16 @@ static inline bool is_longterm_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	return !(is_device_coherent_page(page) ||
-		 is_zone_movable_page(page) ||
-		 is_zero_pfn(page_to_pfn(page)));
+	/* The zero page may always be pinned */
+	if (is_zero_pfn(page_to_pfn(page)))
+		return true;
+
+	/* Coherent device memory must always allow eviction. */
+	if (is_device_coherent_page(page))
+		return false;
+
+	/* Otherwise, non-movable zone pages can be pinned. */
+	return !is_zone_movable_page(page);
 }
 #else
 static inline bool is_longterm_pinnable_page(struct page *page)

kernel/crash_core.c

@@ -494,6 +494,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 
 #ifdef CONFIG_KALLSYMS
 	VMCOREINFO_SYMBOL(kallsyms_names);
+	VMCOREINFO_SYMBOL(kallsyms_num_syms);
 	VMCOREINFO_SYMBOL(kallsyms_token_table);
 	VMCOREINFO_SYMBOL(kallsyms_token_index);
 #ifdef CONFIG_KALLSYMS_BASE_RELATIVE

mm/backing-dev.c

@@ -260,10 +260,10 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void wb_update_bandwidth_workfn(struct work_struct *work)
@@ -334,12 +334,12 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
 static void wb_shutdown(struct bdi_writeback *wb)
 {
 	/* Make sure nobody queues further work */
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
-		spin_unlock_bh(&wb->work_lock);
+		spin_unlock_irq(&wb->work_lock);
 		return;
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
 	/*

mm/bootmem_info.c

@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <linux/bootmem_info.h>
 #include <linux/memory_hotplug.h>
+#include <linux/kmemleak.h>
 
 void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
 {
@@ -33,6 +34,7 @@ void put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
+		kmemleak_free_part(page_to_virt(page), PAGE_SIZE);
 		free_reserved_page(page);
 	}
 }

mm/damon/dbgfs.c

@@ -818,6 +818,9 @@ static int dbgfs_mk_context(char *name)
 		return -ENOENT;
 
 	new_dir = debugfs_create_dir(name, root);
+	/* Below check is required for a potential duplicated name case */
+	if (IS_ERR(new_dir))
+		return PTR_ERR(new_dir);
 	dbgfs_dirs[dbgfs_nr_ctxs] = new_dir;
 
 	new_ctx = dbgfs_new_ctx();

mm/hugetlb.c

@@ -6041,7 +6041,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (!huge_pte_none_mostly(huge_ptep_get(dst_pte)))
 		goto out_release_unlock;
 
-	if (vm_shared) {
+	if (page_in_pagecache) {
 		page_dup_file_rmap(page, true);
 	} else {
 		ClearHPageRestoreReserve(page);

mm/mprotect.c

@@ -196,10 +196,11 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 			pages++;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
-			struct page *page = pfn_swap_entry_to_page(entry);
 			pte_t newpte;
 
 			if (is_writable_migration_entry(entry)) {
+				struct page *page = pfn_swap_entry_to_page(entry);
+
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write

mm/page-writeback.c

@@ -2892,6 +2892,7 @@ static void wb_inode_writeback_start(struct bdi_writeback *wb)
 
 static void wb_inode_writeback_end(struct bdi_writeback *wb)
 {
+	unsigned long flags;
 	atomic_dec(&wb->writeback_inodes);
 	/*
 	 * Make sure estimate of writeback throughput gets updated after
@@ -2900,7 +2901,10 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
 	 * that if multiple inodes end writeback at a similar time, they get
 	 * batched into one bandwidth update.
 	 */
+	spin_lock_irqsave(&wb->work_lock, flags);
+	if (test_bit(WB_registered, &wb->state))
 		queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
+	spin_unlock_irqrestore(&wb->work_lock, flags);
 }
 
 bool __folio_end_writeback(struct folio *folio)

mm/shmem.c

@@ -1782,6 +1782,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 
 	if (shmem_should_replace_folio(folio, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
+		folio = page_folio(page);
 		if (error)
 			goto failed;
 	}

mm/zsmalloc.c

@@ -1487,7 +1487,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	struct size_class *class;
 	enum fullness_group fullness;
 
-	if (unlikely(!handle))
+	if (IS_ERR_OR_NULL((void *)handle))
 		return;
 
 	/*