Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "24 patches, based on 4a09d38.

  Subsystems affected by this patch series: mm (thp, vmalloc, hugetlb,
  memory-failure, and pagealloc), nilfs2, kthread, MAINTAINERS, and
  mailmap"

* emailed patches from Andrew Morton <[email protected]>: (24 commits)
  mailmap: add Marek's other e-mail address and identity without diacritics
  MAINTAINERS: fix Marek's identity again
  mm/page_alloc: do bulk array bounds check after checking populated elements
  mm/page_alloc: __alloc_pages_bulk(): do bounds check before accessing array
  mm/hwpoison: do not lock page again when me_huge_page() successfully recovers
  mm,hwpoison: return -EHWPOISON to denote that the page has already been poisoned
  mm/memory-failure: use a mutex to avoid memory_failure() races
  mm, futex: fix shared futex pgoff on shmem huge page
  kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync()
  kthread_worker: split code for canceling the delayed work timer
  mm/vmalloc: unbreak kasan vmalloc support
  KVM: s390: prepare for hugepage vmalloc
  mm/vmalloc: add vmalloc_no_huge
  nilfs2: fix memory leak in nilfs_sysfs_delete_device_group
  mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()
  mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes
  mm: page_vma_mapped_walk(): get vma_address_end() earlier
  mm: page_vma_mapped_walk(): use goto instead of while (1)
  mm: page_vma_mapped_walk(): add a level of indentation
  mm: page_vma_mapped_walk(): crossing page table boundary
  ...

Author: torvalds

.mailmap

@@ -212,6 +212,8 @@ Manivannan Sadhasivam <[email protected]> <[email protected]>
 Manivannan Sadhasivam <[email protected]> <[email protected]>
 Marcin Nowakowski <[email protected]> <[email protected]>
 Marc Zyngier <[email protected]> <[email protected]>
+Marek Behún <[email protected]> <[email protected]>
+Marek Behún <[email protected]> Marek Behun <[email protected]>
 Mark Brown <[email protected]>
 Mark Starovoytov <[email protected]> <[email protected]>
 Mark Yao <[email protected]> <[email protected]>

MAINTAINERS

@@ -1816,7 +1816,7 @@ F:	drivers/pinctrl/pinctrl-gemini.c
 F:	drivers/rtc/rtc-ftrtc010.c
 
 ARM/CZ.NIC TURRIS SUPPORT
-M:	Marek Behun <[email protected]>
+M:	Marek Behún <[email protected]>
 S:	Maintained
 W:	https://www.turris.cz/
 F:	Documentation/ABI/testing/debugfs-moxtet
@@ -10945,7 +10945,7 @@ F:	include/linux/mv643xx.h
 
 MARVELL MV88X3310 PHY DRIVER
 M:	Russell King <[email protected]>
-M:	Marek Behun <[email protected]>
+M:	Marek Behún <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/net/phy/marvell10g.c

arch/s390/kvm/pv.c

@@ -140,7 +140,12 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm)
 	/* Allocate variable storage */
 	vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE);
 	vlen += uv_info.guest_virt_base_stor_len;
-	kvm->arch.pv.stor_var = vzalloc(vlen);
+	/*
+	 * The Create Secure Configuration Ultravisor Call does not support
+	 * using large pages for the virtual memory area.
+	 * This is a hardware limitation.
+	 */
+	kvm->arch.pv.stor_var = vmalloc_no_huge(vlen);
 	if (!kvm->arch.pv.stor_var)
 		goto out_err;
 	return 0;

fs/nilfs2/sysfs.c

@@ -1053,6 +1053,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs)
 	nilfs_sysfs_delete_superblock_group(nilfs);
 	nilfs_sysfs_delete_segctor_group(nilfs);
 	kobject_del(&nilfs->ns_dev_kobj);
+	kobject_put(&nilfs->ns_dev_kobj);
 	kfree(nilfs->ns_dev_subgroups);
 }
 

include/linux/hugetlb.h

@@ -741,17 +741,6 @@ static inline int hstate_index(struct hstate *h)
 	return h - hstates;
 }
 
-pgoff_t __basepage_index(struct page *page);
-
-/* Return page->index in PAGE_SIZE units */
-static inline pgoff_t basepage_index(struct page *page)
-{
-	if (!PageCompound(page))
-		return page->index;
-
-	return __basepage_index(page);
-}
-
 extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
 				    unsigned long end_pfn);
@@ -988,11 +977,6 @@ static inline int hstate_index(struct hstate *h)
 	return 0;
 }
 
-static inline pgoff_t basepage_index(struct page *page)
-{
-	return page->index;
-}
-
 static inline int dissolve_free_huge_page(struct page *page)
 {
 	return 0;

include/linux/pagemap.h

@@ -516,7 +516,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
 }
 
 /*
- * Get index of the page with in radix-tree
+ * Get index of the page within radix-tree (but not for hugetlb pages).
  * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_index(struct page *page)
@@ -535,15 +535,16 @@ static inline pgoff_t page_to_index(struct page *page)
 	return pgoff;
 }
 
+extern pgoff_t hugetlb_basepage_index(struct page *page);
+
 /*
- * Get the offset in PAGE_SIZE.
- * (TODO: hugepage should have ->index in PAGE_SIZE)
+ * Get the offset in PAGE_SIZE (even for hugetlb pages).
+ * (TODO: hugetlb pages should have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_pgoff(struct page *page)
 {
-	if (unlikely(PageHeadHuge(page)))
-		return page->index << compound_order(page);
-
+	if (unlikely(PageHuge(page)))
+		return hugetlb_basepage_index(page);
 	return page_to_index(page);
 }
 

include/linux/vmalloc.h

@@ -135,6 +135,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			const void *caller);
 void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
 		int node, const void *caller);
+void *vmalloc_no_huge(unsigned long size);
 
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);

kernel/futex.c

@@ -35,7 +35,6 @@
 #include <linux/jhash.h>
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
-#include <linux/hugetlb.h>
 #include <linux/freezer.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
@@ -650,7 +649,7 @@ static int get_futex_key(u32 __user *uaddr, bool fshared, union futex_key *key,
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.i_seq = get_inode_sequence_number(inode);
-		key->shared.pgoff = basepage_index(tail);
+		key->shared.pgoff = page_to_pgoff(tail);
 		rcu_read_unlock();
 	}
 

kernel/kthread.c

@@ -1093,37 +1093,47 @@ void kthread_flush_work(struct kthread_work *work)
 EXPORT_SYMBOL_GPL(kthread_flush_work);
 
 /*
- * This function removes the work from the worker queue. Also it makes sure
- * that it won't get queued later via the delayed work's timer.
+ * Make sure that the timer is neither set nor running and could
+ * not manipulate the work list_head any longer.
+ *
+ * The function is called under worker->lock. The lock is temporary
+ * released but the timer can't be set again in the meantime.
+ */
+static void kthread_cancel_delayed_work_timer(struct kthread_work *work,
+					      unsigned long *flags)
+{
+	struct kthread_delayed_work *dwork =
+		container_of(work, struct kthread_delayed_work, work);
+	struct kthread_worker *worker = work->worker;
+
+	/*
+	 * del_timer_sync() must be called to make sure that the timer
+	 * callback is not running. The lock must be temporary released
+	 * to avoid a deadlock with the callback. In the meantime,
+	 * any queuing is blocked by setting the canceling counter.
+	 */
+	work->canceling++;
+	raw_spin_unlock_irqrestore(&worker->lock, *flags);
+	del_timer_sync(&dwork->timer);
+	raw_spin_lock_irqsave(&worker->lock, *flags);
+	work->canceling--;
+}
+
+/*
+ * This function removes the work from the worker queue.
+ *
+ * It is called under worker->lock. The caller must make sure that
+ * the timer used by delayed work is not running, e.g. by calling
+ * kthread_cancel_delayed_work_timer().
  *
  * The work might still be in use when this function finishes. See the
  * current_work proceed by the worker.
  *
  * Return: %true if @work was pending and successfully canceled,
  *	%false if @work was not pending
  */
-static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork,
-				  unsigned long *flags)
+static bool __kthread_cancel_work(struct kthread_work *work)
 {
-	/* Try to cancel the timer if exists. */
-	if (is_dwork) {
-		struct kthread_delayed_work *dwork =
-			container_of(work, struct kthread_delayed_work, work);
-		struct kthread_worker *worker = work->worker;
-
-		/*
-		 * del_timer_sync() must be called to make sure that the timer
-		 * callback is not running. The lock must be temporary released
-		 * to avoid a deadlock with the callback. In the meantime,
-		 * any queuing is blocked by setting the canceling counter.
-		 */
-		work->canceling++;
-		raw_spin_unlock_irqrestore(&worker->lock, *flags);
-		del_timer_sync(&dwork->timer);
-		raw_spin_lock_irqsave(&worker->lock, *flags);
-		work->canceling--;
-	}
-
 	/*
 	 * Try to remove the work from a worker list. It might either
 	 * be from worker->work_list or from worker->delayed_work_list.
@@ -1176,11 +1186,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker,
 	/* Work must not be used with >1 worker, see kthread_queue_work() */
 	WARN_ON_ONCE(work->worker != worker);
 
-	/* Do not fight with another command that is canceling this work. */
+	/*
+	 * Temporary cancel the work but do not fight with another command
+	 * that is canceling the work as well.
+	 *
+	 * It is a bit tricky because of possible races with another
+	 * mod_delayed_work() and cancel_delayed_work() callers.
+	 *
+	 * The timer must be canceled first because worker->lock is released
+	 * when doing so. But the work can be removed from the queue (list)
+	 * only when it can be queued again so that the return value can
+	 * be used for reference counting.
+	 */
+	kthread_cancel_delayed_work_timer(work, &flags);
 	if (work->canceling)
 		goto out;
+	ret = __kthread_cancel_work(work);
 
-	ret = __kthread_cancel_work(work, true, &flags);
 fast_queue:
 	__kthread_queue_delayed_work(worker, dwork, delay);
 out:
@@ -1202,7 +1224,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork)
 	/* Work must not be used with >1 worker, see kthread_queue_work(). */
 	WARN_ON_ONCE(work->worker != worker);
 
-	ret = __kthread_cancel_work(work, is_dwork, &flags);
+	if (is_dwork)
+		kthread_cancel_delayed_work_timer(work, &flags);
+
+	ret = __kthread_cancel_work(work);
 
 	if (worker->current_work != work)
 		goto out_fast;

mm/hugetlb.c

@@ -1588,15 +1588,12 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
 	return NULL;
 }
 
-pgoff_t __basepage_index(struct page *page)
+pgoff_t hugetlb_basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
 	pgoff_t index = page_index(page_head);
 	unsigned long compound_idx;
 
-	if (!PageHuge(page_head))
-		return page_index(page);
-
 	if (compound_order(page_head) >= MAX_ORDER)
 		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
 	else