Merge branch 'linus' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 120 insertions, 96 deletions

diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index 595b757bef72..c03ccbc405a0 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -167,7 +167,7 @@ static void cma_debugfs_add_one(struct cma *cma, int idx)
 	char name[16];
 	int u32s;
 
-	sprintf(name, "cma-%s", cma->name);
+	scnprintf(name, sizeof(name), "cma-%s", cma->name);
 
 	tmp = debugfs_create_dir(name, cma_debugfs_root);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 08f6c1993832..3644ff918434 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -32,6 +32,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
 #include <linux/shmem_fs.h>
+#include <linux/oom.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -550,6 +551,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 	struct mem_cgroup *memcg;
 	pgtable_t pgtable;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+	int ret = 0;
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
@@ -561,9 +563,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	pgtable = pte_alloc_one(vma->vm_mm, haddr);
 	if (unlikely(!pgtable)) {
-		mem_cgroup_cancel_charge(page, memcg, true);
-		put_page(page);
-		return VM_FAULT_OOM;
+		ret = VM_FAULT_OOM;
+		goto release;
 	}
 
 	clear_huge_page(page, haddr, HPAGE_PMD_NR);
@@ -576,13 +577,14 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 	if (unlikely(!pmd_none(*vmf->pmd))) {
-		spin_unlock(vmf->ptl);
-		mem_cgroup_cancel_charge(page, memcg, true);
-		put_page(page);
-		pte_free(vma->vm_mm, pgtable);
+		goto unlock_release;
 	} else {
 		pmd_t entry;
 
+		ret = check_stable_address_space(vma->vm_mm);
+		if (ret)
+			goto unlock_release;
+
 		/* Deliver the page fault to userland */
 		if (userfaultfd_missing(vma)) {
 			int ret;
@@ -610,6 +612,15 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 	}
 
 	return 0;
+unlock_release:
+	spin_unlock(vmf->ptl);
+release:
+	if (pgtable)
+		pte_free(vma->vm_mm, pgtable);
+	mem_cgroup_cancel_charge(page, memcg, true);
+	put_page(page);
+	return ret;
+
 }
 
 /*
@@ -688,7 +699,10 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 		ret = 0;
 		set = false;
 		if (pmd_none(*vmf->pmd)) {
-			if (userfaultfd_missing(vma)) {
+			ret = check_stable_address_space(vma->vm_mm);
+			if (ret) {
+				spin_unlock(vmf->ptl);
+			} else if (userfaultfd_missing(vma)) {
 				spin_unlock(vmf->ptl);
 				ret = handle_userfault(vmf, VM_UFFD_MISSING);
 				VM_BUG_ON(ret & VM_FAULT_FALLBACK);
diff --git a/mm/memblock.c b/mm/memblock.c
index 2cb25fe4452c..bf14aea6ab70 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -285,31 +285,27 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 }
 
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
-
-phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
-					phys_addr_t *addr)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	*addr = __pa(memblock.reserved.regions);
-
-	return PAGE_ALIGN(sizeof(struct memblock_region) *
-			  memblock.reserved.max);
-}
-
-phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info(
-					phys_addr_t *addr)
+/**
+ * Discard memory and reserved arrays if they were allocated
+ */
+void __init memblock_discard(void)
 {
-	if (memblock.memory.regions == memblock_memory_init_regions)
-		return 0;
+	phys_addr_t addr, size;
 
-	*addr = __pa(memblock.memory.regions);
+	if (memblock.reserved.regions != memblock_reserved_init_regions) {
+		addr = __pa(memblock.reserved.regions);
+		size = PAGE_ALIGN(sizeof(struct memblock_region) *
+				  memblock.reserved.max);
+		__memblock_free_late(addr, size);
+	}
 
-	return PAGE_ALIGN(sizeof(struct memblock_region) *
-			  memblock.memory.max);
+	if (memblock.memory.regions == memblock_memory_init_regions) {
+		addr = __pa(memblock.memory.regions);
+		size = PAGE_ALIGN(sizeof(struct memblock_region) *
+				  memblock.memory.max);
+		__memblock_free_late(addr, size);
+	}
 }
-
 #endif
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3df3c04d73ab..e09741af816f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1611,9 +1611,13 @@ cleanup:
  * @page: the page
  *
  * This function protects unlocked LRU pages from being moved to
- * another cgroup and stabilizes their page->mem_cgroup binding.
+ * another cgroup.
+ *
+ * It ensures lifetime of the returned memcg. Caller is responsible
+ * for the lifetime of the page; __unlock_page_memcg() is available
+ * when @page might get freed inside the locked section.
  */
-void lock_page_memcg(struct page *page)
+struct mem_cgroup *lock_page_memcg(struct page *page)
 {
 	struct mem_cgroup *memcg;
 	unsigned long flags;
@@ -1622,18 +1626,24 @@ void lock_page_memcg(struct page *page)
 	 * The RCU lock is held throughout the transaction.  The fast
 	 * path can get away without acquiring the memcg->move_lock
 	 * because page moving starts with an RCU grace period.
-	 */
+	 *
+	 * The RCU lock also protects the memcg from being freed when
+	 * the page state that is going to change is the only thing
+	 * preventing the page itself from being freed. E.g. writeback
+	 * doesn't hold a page reference and relies on PG_writeback to
+	 * keep off truncation, migration and so forth.
+         */
 	rcu_read_lock();
 
 	if (mem_cgroup_disabled())
-		return;
+		return NULL;
 again:
 	memcg = page->mem_cgroup;
 	if (unlikely(!memcg))
-		return;
+		return NULL;
 
 	if (atomic_read(&memcg->moving_account) <= 0)
-		return;
+		return memcg;
 
 	spin_lock_irqsave(&memcg->move_lock, flags);
 	if (memcg != page->mem_cgroup) {
@@ -1649,18 +1659,18 @@ again:
 	memcg->move_lock_task = current;
 	memcg->move_lock_flags = flags;
 
-	return;
+	return memcg;
 }
 EXPORT_SYMBOL(lock_page_memcg);
 
 /**
- * unlock_page_memcg - unlock a page->mem_cgroup binding
- * @page: the page
+ * __unlock_page_memcg - unlock and unpin a memcg
+ * @memcg: the memcg
+ *
+ * Unlock and unpin a memcg returned by lock_page_memcg().
  */
-void unlock_page_memcg(struct page *page)
+void __unlock_page_memcg(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
-
 	if (memcg && memcg->move_lock_task == current) {
 		unsigned long flags = memcg->move_lock_flags;
 
@@ -1672,6 +1682,15 @@ void unlock_page_memcg(struct page *page)
 
 	rcu_read_unlock();
 }
+
+/**
+ * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * @page: the page
+ */
+void unlock_page_memcg(struct page *page)
+{
+	__unlock_page_memcg(page->mem_cgroup);
+}
 EXPORT_SYMBOL(unlock_page_memcg);
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index e158f7ac6730..fe2fba27ded2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -68,6 +68,7 @@
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
+#include <linux/oom.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -2893,6 +2894,7 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct mem_cgroup *memcg;
 	struct page *page;
+	int ret = 0;
 	pte_t entry;
 
 	/* File mapping without ->vm_ops ? */
@@ -2925,6 +2927,9 @@ static int do_anonymous_page(struct vm_fault *vmf)
 				vmf->address, &vmf->ptl);
 		if (!pte_none(*vmf->pte))
 			goto unlock;
+		ret = check_stable_address_space(vma->vm_mm);
+		if (ret)
+			goto unlock;
 		/* Deliver the page fault to userland, check inside PT lock */
 		if (userfaultfd_missing(vma)) {
 			pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2959,6 +2964,10 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!pte_none(*vmf->pte))
 		goto release;
 
+	ret = check_stable_address_space(vma->vm_mm);
+	if (ret)
+		goto release;
+
 	/* Deliver the page fault to userland, check inside PT lock */
 	if (userfaultfd_missing(vma)) {
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -2978,7 +2987,7 @@ setpte:
 	update_mmu_cache(vma, vmf->address, vmf->pte);
 unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
-	return 0;
+	return ret;
 release:
 	mem_cgroup_cancel_charge(page, memcg, false);
 	put_page(page);
@@ -3252,7 +3261,7 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
 int finish_fault(struct vm_fault *vmf)
 {
 	struct page *page;
-	int ret;
+	int ret = 0;
 
 	/* Did we COW the page? */
 	if ((vmf->flags & FAULT_FLAG_WRITE) &&
@@ -3260,7 +3269,15 @@ int finish_fault(struct vm_fault *vmf)
 		page = vmf->cow_page;
 	else
 		page = vmf->page;
-	ret = alloc_set_pte(vmf, vmf->memcg, page);
+
+	/*
+	 * check even for read faults because we might have lost our CoWed
+	 * page
+	 */
+	if (!(vmf->vma->vm_flags & VM_SHARED))
+		ret = check_stable_address_space(vmf->vma->vm_mm);
+	if (!ret)
+		ret = alloc_set_pte(vmf, vmf->memcg, page);
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
@@ -3900,19 +3917,6 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 			mem_cgroup_oom_synchronize(false);
 	}
 
-	/*
-	 * This mm has been already reaped by the oom reaper and so the
-	 * refault cannot be trusted in general. Anonymous refaults would
-	 * lose data and give a zero page instead e.g. This is especially
-	 * problem for use_mm() because regular tasks will just die and
-	 * the corrupted data will not be visible anywhere while kthread
-	 * will outlive the oom victim and potentially propagate the date
-	 * further.
-	 */
-	if (unlikely((current->flags & PF_KTHREAD) && !(ret & VM_FAULT_ERROR)
-				&& test_bit(MMF_UNSTABLE, &vma->vm_mm->flags)))
-		ret = VM_FAULT_SIGBUS;
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d911fa5cb2a7..618ab125228b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -861,11 +861,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 		*policy |= (pol->flags & MPOL_MODE_FLAGS);
 	}
 
-	if (vma) {
-		up_read(&current->mm->mmap_sem);
-		vma = NULL;
-	}
-
 	err = 0;
 	if (nmask) {
 		if (mpol_store_user_nodemask(pol)) {
diff --git a/mm/migrate.c b/mm/migrate.c
index d68a41da6abb..e84eeb4e4356 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -41,6 +41,7 @@
 #include <linux/page_idle.h>
 #include <linux/page_owner.h>
 #include <linux/sched/mm.h>
+#include <linux/ptrace.h>
 
 #include <asm/tlbflush.h>
 
@@ -1652,7 +1653,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 		const int __user *, nodes,
 		int __user *, status, int, flags)
 {
-	const struct cred *cred = current_cred(), *tcred;
 	struct task_struct *task;
 	struct mm_struct *mm;
 	int err;
@@ -1676,14 +1676,9 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 
 	/*
 	 * Check if this process has the right to modify the specified
-	 * process. The right exists if the process has administrative
-	 * capabilities, superuser privileges or the same
-	 * userid as the target process.
+	 * process. Use the regular "ptrace_may_access()" checks.
 	 */
-	tcred = __task_cred(task);
-	if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) &&
-	    !uid_eq(cred->uid,  tcred->suid) && !uid_eq(cred->uid,  tcred->uid) &&
-	    !capable(CAP_SYS_NICE)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
 		rcu_read_unlock();
 		err = -EPERM;
 		goto out;
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 36454d0f96ee..3637809a18d0 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -146,22 +146,6 @@ static unsigned long __init free_low_memory_core_early(void)
 				NULL)
 		count += __free_memory_core(start, end);
 
-#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
-	{
-		phys_addr_t size;
-
-		/* Free memblock.reserved array if it was allocated */
-		size = get_allocated_memblock_reserved_regions_info(&start);
-		if (size)
-			count += __free_memory_core(start, start + size);
-
-		/* Free memblock.memory array if it was allocated */
-		size = get_allocated_memblock_memory_regions_info(&start);
-		if (size)
-			count += __free_memory_core(start, start + size);
-	}
-#endif
-
 	return count;
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 96e93b214d31..bf050ab025b7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2724,9 +2724,12 @@ EXPORT_SYMBOL(clear_page_dirty_for_io);
 int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 	int ret;
 
-	lock_page_memcg(page);
+	memcg = lock_page_memcg(page);
+	lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
 	if (mapping && mapping_use_writeback_tags(mapping)) {
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -2754,12 +2757,18 @@ int test_clear_page_writeback(struct page *page)
 	} else {
 		ret = TestClearPageWriteback(page);
 	}
+	/*
+	 * NOTE: Page might be free now! Writeback doesn't hold a page
+	 * reference on its own, it relies on truncation to wait for
+	 * the clearing of PG_writeback. The below can only access
+	 * page state that is static across allocation cycles.
+	 */
 	if (ret) {
-		dec_lruvec_page_state(page, NR_WRITEBACK);
+		dec_lruvec_state(lruvec, NR_WRITEBACK);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		inc_node_page_state(page, NR_WRITTEN);
 	}
-	unlock_page_memcg(page);
+	__unlock_page_memcg(memcg);
 	return ret;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6acf612fdd99..471b0526b876 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1585,6 +1585,10 @@ void __init page_alloc_init_late(void)
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+	/* Discard memblock private memory */
+	memblock_discard();
+#endif
 
 	for_each_populated_zone(zone)
 		set_zone_contiguous(zone);
diff --git a/mm/slub.c b/mm/slub.c
index 1d3f9835f4ea..e8b4e31162ca 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5642,13 +5642,14 @@ static void sysfs_slab_remove_workfn(struct work_struct *work)
 		 * A cache is never shut down before deactivation is
 		 * complete, so no need to worry about synchronization.
 		 */
-		return;
+		goto out;
 
 #ifdef CONFIG_MEMCG
 	kset_unregister(s->memcg_kset);
 #endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
 	kobject_del(&s->kobj);
+out:
 	kobject_put(&s->kobj);
 }
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 8698c1c86c4d..a47e3894c775 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1671,7 +1671,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	struct page **pages;
 	unsigned int nr_pages, array_size, i;
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
-	const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN;
+	const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
+	const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ?
+					0 :
+					__GFP_HIGHMEM;
 
 	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
@@ -1679,7 +1682,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	area->nr_pages = nr_pages;
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
-		pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM,
+		pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,
 				PAGE_KERNEL, node, area->caller);
 	} else {
 		pages = kmalloc_node(array_size, nested_gfp, node);
@@ -1700,9 +1703,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		}
 
 		if (node == NUMA_NO_NODE)
-			page = alloc_page(alloc_mask);
+			page = alloc_page(alloc_mask|highmem_mask);
 		else
-			page = alloc_pages_node(node, alloc_mask, 0);
+			page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
 
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */
@@ -1710,7 +1713,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 			goto fail;
 		}
 		area->pages[i] = page;
-		if (gfpflags_allow_blocking(gfp_mask))
+		if (gfpflags_allow_blocking(gfp_mask|highmem_mask))
 			cond_resched();
 	}