Merge branch 'linus' into x86/core, to pick up fixes

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

16 files changed, 118 insertions, 119 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index a550635ea5c3..de64ea658716 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -637,6 +637,7 @@ config DEFERRED_STRUCT_PAGE_INIT
 	depends on NO_BOOTMEM
 	depends on SPARSEMEM
 	depends on !NEED_PER_CPU_KM
+	depends on 64BIT
 	help
 	  Ordinarily all struct pages are initialised during early boot in a
 	  single thread. On very large machines this can take a considerable
diff --git a/mm/Makefile b/mm/Makefile
index 8716bdabe1e6..26ef77a3883b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH
 mmu-$(CONFIG_MMU)	+= process_vm_access.o
 endif
 
-obj-y			:= filemap.o mempool.o oom_kill.o \
+obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
@@ -49,7 +49,6 @@ else
 	obj-y		+= bootmem.o
 endif
 
-obj-$(CONFIG_ADVISE_SYSCALLS)	+= fadvise.o
 ifdef CONFIG_MMU
 	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
 endif
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f5981e9d6ae2..8a8bb8796c6c 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
+	struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css);
 
 	mutex_lock(&wb->bdi->cgwb_release_mutex);
 	wb_shutdown(wb);
@@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work)
 	css_put(wb->blkcg_css);
 	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
+	/* triggers blkg destruction if cgwb_refcnt becomes zero */
+	blkcg_cgwb_put(blkcg);
+
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
@@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
+			blkcg_cgwb_get(blkcg);
 			css_get(memcg_css);
 			css_get(blkcg_css);
 		}
diff --git a/mm/debug.c b/mm/debug.c
index 38c926520c97..bd10aad8539a 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma);
 
 void dump_mm(const struct mm_struct *mm)
 {
-	pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n"
+	pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
 #ifdef CONFIG_MMU
 		"get_unmapped_area %px\n"
 #endif
@@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm)
 		"tlb_flush_pending %d\n"
 		"def_flags: %#lx(%pGv)\n",
 
-		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+		mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
 #ifdef CONFIG_MMU
 		mm->get_unmapped_area,
 #endif
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2d8376e3c640..467bcd032037 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -27,9 +27,9 @@
  * deactivate the pages and clear PG_Referenced.
  */
 
-int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+static int generic_fadvise(struct file *file, loff_t offset, loff_t len,
+			   int advice)
 {
-	struct fd f = fdget(fd);
 	struct inode *inode;
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
@@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 	pgoff_t start_index;
 	pgoff_t end_index;
 	unsigned long nrpages;
-	int ret = 0;
-
-	if (!f.file)
-		return -EBADF;
 
-	inode = file_inode(f.file);
-	if (S_ISFIFO(inode->i_mode)) {
-		ret = -ESPIPE;
-		goto out;
-	}
+	inode = file_inode(file);
+	if (S_ISFIFO(inode->i_mode))
+		return -ESPIPE;
 
-	mapping = f.file->f_mapping;
-	if (!mapping || len < 0) {
-		ret = -EINVAL;
-		goto out;
-	}
+	mapping = file->f_mapping;
+	if (!mapping || len < 0)
+		return -EINVAL;
 
 	bdi = inode_to_bdi(mapping->host);
 
@@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 			/* no bad return value, but ignore advice */
 			break;
 		default:
-			ret = -EINVAL;
+			return -EINVAL;
 		}
-		goto out;
+		return 0;
 	}
 
 	/*
@@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
-		f.file->f_ra.ra_pages = bdi->ra_pages;
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		file->f_ra.ra_pages = bdi->ra_pages;
+		spin_lock(&file->f_lock);
+		file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_RANDOM:
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode |= FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		spin_lock(&file->f_lock);
+		file->f_mode |= FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_SEQUENTIAL:
-		f.file->f_ra.ra_pages = bdi->ra_pages * 2;
-		spin_lock(&f.file->f_lock);
-		f.file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&f.file->f_lock);
+		file->f_ra.ra_pages = bdi->ra_pages * 2;
+		spin_lock(&file->f_lock);
+		file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&file->f_lock);
 		break;
 	case POSIX_FADV_WILLNEED:
 		/* First and last PARTIAL page! */
@@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		 * Ignore return value because fadvise() shall return
 		 * success even if filesystem can't retrieve a hint,
 		 */
-		force_page_cache_readahead(mapping, f.file, start_index,
-					   nrpages);
+		force_page_cache_readahead(mapping, file, start_index, nrpages);
 		break;
 	case POSIX_FADV_NOREUSE:
 		break;
@@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 		}
 		break;
 	default:
-		ret = -EINVAL;
+		return -EINVAL;
 	}
-out:
+	return 0;
+}
+
+int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+{
+	if (file->f_op->fadvise)
+		return file->f_op->fadvise(file, offset, len, advice);
+
+	return generic_fadvise(file, offset, len, advice);
+}
+EXPORT_SYMBOL(vfs_fadvise);
+
+#ifdef CONFIG_ADVISE_SYSCALLS
+
+int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+{
+	struct fd f = fdget(fd);
+	int ret;
+
+	if (!f.file)
+		return -EBADF;
+
+	ret = vfs_fadvise(f.file, offset, len, advice);
+
 	fdput(f);
 	return ret;
 }
@@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
 }
 
 #endif
+#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c3bc7e9c9a2a..533f9b00147d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -821,11 +821,11 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	 * but we need to be consistent with PTEs and architectures that
 	 * can't support a 'special' bit.
 	 */
-	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+			!pfn_t_devmap(pfn));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
-	BUG_ON(!pfn_t_devmap(pfn));
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 9a085d525bbc..17dd883198ae 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void)
 
 	kmemleak_initialized = 1;
 
+	dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL,
+				     &kmemleak_fops);
+	if (!dentry)
+		pr_warn("Failed to create the debugfs kmemleak file\n");
+
 	if (kmemleak_error) {
 		/*
 		 * Some error occurred and kmemleak was disabled. There is a
@@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void)
 		return -ENOMEM;
 	}
 
-	dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL,
-				     &kmemleak_fops);
-	if (!dentry)
-		pr_warn("Failed to create the debugfs kmemleak file\n");
 	mutex_lock(&scan_mutex);
 	start_scan_thread();
 	mutex_unlock(&scan_mutex);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4ead5a4817de..e79cb59552d9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 	if (mem_cgroup_out_of_memory(memcg, mask, order))
 		return OOM_SUCCESS;
 
-	WARN(1,"Memory cgroup charge failed because of no reclaimable memory! "
-		"This looks like a misconfiguration or a kernel bug.");
 	return OOM_FAILED;
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9eea6e809a4e..38d94b703e9d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 			if (__PageMovable(page))
 				return pfn;
 			if (PageHuge(page)) {
-				if (page_huge_active(page))
+				if (hugepage_migration_supported(page_hstate(page)) &&
+				    page_huge_active(page))
 					return pfn;
 				else
 					pfn = round_up(pfn + 1,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index b5b25e4dcbbb..f10aa5360616 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
 
 			tlb_gather_mmu(&tlb, mm, start, end);
 			if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) {
+				tlb_finish_mmu(&tlb, start, end);
 				ret = false;
 				continue;
 			}
@@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc)
 	}
 
 	select_bad_process(oc);
-	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
+	/* Found nothing?!?! */
+	if (!oc->chosen) {
 		dump_header(oc, NULL);
-		panic("Out of memory and no killable processes...\n");
+		pr_warn("Out of memory and no killable processes...\n");
+		/*
+		 * If we got here due to an actual allocation at the
+		 * system level, we cannot survive this and will enter
+		 * an endless loop in the allocator. Bail out now.
+		 */
+		if (!is_sysrq_oom(oc) && !is_memcg_oom(oc))
+			panic("System is deadlocked on memory\n");
 	}
 	if (oc->chosen && oc->chosen != (void *)-1UL)
 		oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 05e983f42316..89d2a2ab3fe6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7708,6 +7708,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * handle each tail page individually in migration.
 		 */
 		if (PageHuge(page)) {
+
+			if (!hugepage_migration_supported(page_hstate(page)))
+				goto unmovable;
+
 			iter = round_up(iter + 1, 1<<compound_order(page)) - 1;
 			continue;
 		}
diff --git a/mm/readahead.c b/mm/readahead.c
index a59ea70527b9..4e630143a0ba 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -20,6 +20,7 @@
 #include <linux/file.h>
 #include <linux/mm_inline.h>
 #include <linux/blk-cgroup.h>
+#include <linux/fadvise.h>
 
 #include "internal.h"
 
@@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping,
 }
 EXPORT_SYMBOL_GPL(page_cache_async_readahead);
 
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
-	     pgoff_t index, unsigned long nr)
-{
-	if (!mapping || !mapping->a_ops)
-		return -EINVAL;
-
-	/*
-	 * Readahead doesn't make sense for DAX inodes, but we don't want it
-	 * to report a failure either.  Instead, we just return success and
-	 * don't do any work.
-	 */
-	if (dax_mapping(mapping))
-		return 0;
-
-	return force_page_cache_readahead(mapping, filp, index, nr);
-}
-
 ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
@@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 
 	ret = -EBADF;
 	f = fdget(fd);
-	if (f.file) {
-		if (f.file->f_mode & FMODE_READ) {
-			struct address_space *mapping = f.file->f_mapping;
-			pgoff_t start = offset >> PAGE_SHIFT;
-			pgoff_t end = (offset + count - 1) >> PAGE_SHIFT;
-			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, f.file, start, len);
-		}
-		fdput(f);
-	}
+	if (!f.file || !(f.file->f_mode & FMODE_READ))
+		goto out;
+
+	/*
+	 * The readahead() syscall is intended to run only on files
+	 * that can execute readahead. If readahead is not possible
+	 * on this file, then we must return -EINVAL.
+	 */
+	ret = -EINVAL;
+	if (!f.file->f_mapping || !f.file->f_mapping->a_ops ||
+	    !S_ISREG(file_inode(f.file)->i_mode))
+		goto out;
+
+	ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED);
+out:
+	fdput(f);
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 0376c124b043..446942677cd4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2227,6 +2227,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 			mpol_shared_policy_init(&info->policy, NULL);
 			break;
 		}
+
+		lockdep_annotate_inode_mutex_key(inode);
 	} else
 		shmem_free_inode(sb);
 	return inode;
diff --git a/mm/util.c b/mm/util.c
index d2890a407332..9e3ebd2ef65f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 EXPORT_SYMBOL(kvmalloc_node);
 
 /**
- * kvfree - free memory allocated with kvmalloc
- * @addr: pointer returned by kvmalloc
+ * kvfree() - Free memory.
+ * @addr: Pointer to allocated memory.
  *
- * If the memory is allocated from vmalloc area it is freed with vfree().
- * Otherwise kfree() is used.
+ * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc().
+ * It is slightly more efficient to use kfree() or vfree() if you are certain
+ * that you know which one to use.
+ *
+ * Context: Any context except NMI.
  */
 void kvfree(const void *addr)
 {
diff --git a/mm/vmacache.c b/mm/vmacache.c
index ea517bef7dc5..cdc32a3b02fa 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -20,44 +20,6 @@
 #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK)
 
 /*
- * Flush vma caches for threads that share a given mm.
- *
- * The operation is safe because the caller holds the mmap_sem
- * exclusively and other threads accessing the vma cache will
- * have mmap_sem held at least for read, so no extra locking
- * is required to maintain the vma cache.
- */
-void vmacache_flush_all(struct mm_struct *mm)
-{
-	struct task_struct *g, *p;
-
-	count_vm_vmacache_event(VMACACHE_FULL_FLUSHES);
-
-	/*
-	 * Single threaded tasks need not iterate the entire
-	 * list of process. We can avoid the flushing as well
-	 * since the mm's seqnum was increased and don't have
-	 * to worry about other threads' seqnum. Current's
-	 * flush will occur upon the next lookup.
-	 */
-	if (atomic_read(&mm->mm_users) == 1)
-		return;
-
-	rcu_read_lock();
-	for_each_process_thread(g, p) {
-		/*
-		 * Only flush the vmacache pointers as the
-		 * mm seqnum is already set and curr's will
-		 * be set upon invalidation when the next
-		 * lookup is done.
-		 */
-		if (mm == p->mm)
-			vmacache_flush(p);
-	}
-	rcu_read_unlock();
-}
-
-/*
  * This task may be accessing a foreign mm via (for example)
  * get_user_pages()->find_vma().  The vmacache is task-local and this
  * task's vmacache pertains to a different mm (ie, its own).  There is
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7e7d25504651..c7ce2c161225 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -476,6 +476,17 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	delta = freeable >> priority;
 	delta *= 4;
 	do_div(delta, shrinker->seeks);
+
+	/*
+	 * Make sure we apply some minimal pressure on default priority
+	 * even on small cgroups. Stale objects are not only consuming memory
+	 * by themselves, but can also hold a reference to a dying cgroup,
+	 * preventing it from being reclaimed. A dying cgroup with all
+	 * corresponding structures like per-cpu stats and kmem caches
+	 * can be really big, so it may lead to a significant waste of memory.
+	 */
+	delta = max_t(unsigned long long, delta, min(freeable, batch_size));
+
 	total_scan += delta;
 	if (total_scan < 0) {
 		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",