Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Am experimenting with splitting MM up into identifiable subsystems
  perhaps with a view to gitifying it in complex ways. Also with more
  verbose "incoming" emails.

  Most of MM is here and a few other trees.

  Subsystems affected by this patch series:
   - hotfixes
   - iommu
   - scripts
   - arch/sh
   - ocfs2
   - mm:slab-generic
   - mm:slub
   - mm:kmemleak
   - mm:kasan
   - mm:cleanups
   - mm:debug
   - mm:pagecache
   - mm:swap
   - mm:memcg
   - mm:gup
   - mm:pagemap
   - mm:infrastructure
   - mm:vmalloc
   - mm:initialization
   - mm:pagealloc
   - mm:vmscan
   - mm:tools
   - mm:proc
   - mm:ras
   - mm:oom-kill

  hotfixes:
      mm: vmscan: scan anonymous pages on file refaults
      mm/nvdimm: add is_ioremap_addr and use that to check ioremap address
      mm/memcontrol: fix wrong statistics in memory.stat
      mm/z3fold.c: lock z3fold page before  __SetPageMovable()
      nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header
      MAINTAINERS: nilfs2: update email address

  iommu:
      include/linux/dmar.h: replace single-char identifiers in macros

  scripts:
      scripts/decode_stacktrace: match basepath using shell prefix operator, not regex
      scripts/decode_stacktrace: look for modules with .ko.debug extension
      scripts/spelling.txt: drop "sepc" from the misspelling list
      scripts/spelling.txt: add spelling fix for prohibited
      scripts/decode_stacktrace: Accept dash/underscore in modules
      scripts/spelling.txt: add more spellings to spelling.txt

  arch/sh:
      arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS
      sh: config: remove left-over BACKLIGHT_LCD_SUPPORT
      sh: prevent warnings when using iounmap

  ocfs2:
      fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat"
      ocfs2/dlm: use struct_size() helper
      ocfs2: add last unlock times in locking_state
      ocfs2: add locking filter debugfs file
      ocfs2: add first lock wait time in locking_state
      ocfs: no need to check return value of debugfs_create functions
      fs/ocfs2/dlmglue.c: unneeded variable: "status"
      ocfs2: use kmemdup rather than duplicating its implementation

  mm:slab-generic:
    Patch series "mm/slab: Improved sanity checking":
      mm/slab: validate cache membership under freelist hardening
      mm/slab: sanity-check page type when looking up cache
      lkdtm/heap: add tests for freelist hardening

  mm:slub:
      mm/slub.c: avoid double string traverse in kmem_cache_flags()
      slub: don't panic for memcg kmem cache creation failure

  mm:kmemleak:
      mm/kmemleak.c: fix check for softirq context
      mm/kmemleak.c: change error at _write when kmemleak is disabled
      docs: kmemleak: add more documentation details

  mm:kasan:
      mm/kasan: print frame description for stack bugs
      Patch series "Bitops instrumentation for KASAN", v5:
        lib/test_kasan: add bitops tests
        x86: use static_cpu_has in uaccess region to avoid instrumentation
        asm-generic, x86: add bitops instrumentation for KASAN
      Patch series "mm/kasan: Add object validation in ksize()", v3:
        mm/kasan: introduce __kasan_check_{read,write}
        mm/kasan: change kasan_check_{read,write} to return boolean
        lib/test_kasan: Add test for double-kzfree detection
        mm/slab: refactor common ksize KASAN logic into slab_common.c
        mm/kasan: add object validation in ksize()

  mm:cleanups:
      include/linux/pfn_t.h: remove pfn_t_to_virt()
      Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect":
        arm: remove ARCH_SELECT_MEMORY_MODEL
        s390: remove ARCH_SELECT_MEMORY_MODEL
        sparc: remove ARCH_SELECT_MEMORY_MODEL
      mm/gup.c: make follow_page_mask() static
      mm/memory.c: trivial clean up in insert_page()
      mm: make !CONFIG_HUGE_PAGE wrappers into static inlines
      include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info
      mm: remove the account_page_dirtied export
      mm/page_isolation.c: change the prototype of undo_isolate_page_range()
      include/linux/vmpressure.h: use spinlock_t instead of struct spinlock
      mm: remove the exporting of totalram_pages
      include/linux/pagemap.h: document trylock_page() return value

  mm:debug:
      mm/failslab.c: by default, do not fail allocations with direct reclaim only
      Patch series "debug_pagealloc improvements":
        mm, debug_pagelloc: use static keys to enable debugging
        mm, page_alloc: more extensive free page checking with debug_pagealloc
        mm, debug_pagealloc: use a page type instead of page_ext flag

  mm:pagecache:
      Patch series "fix filler_t callback type mismatches", v2:
        mm/filemap.c: fix an overly long line in read_cache_page
        mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page
        jffs2: pass the correct prototype to read_cache_page
        9p: pass the correct prototype to read_cache_page
      mm/filemap.c: correct the comment about VM_FAULT_RETRY

  mm:swap:
      mm, swap: fix race between swapoff and some swap operations
      mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device()
      mm, swap: use rbtree for swap_extent
      mm/mincore.c: fix race between swapoff and mincore

  mm:memcg:
      memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL
      memcg, fsnotify: no oom-kill for remote memcg charging
      mm, memcg: introduce memory.events.local
      mm: memcontrol: dump memory.stat during cgroup OOM
      Patch series "mm: reparent slab memory on cgroup removal", v7:
        mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache()
        mm: memcg/slab: rename slab delayed deactivation functions and fields
        mm: memcg/slab: generalize postponed non-root kmem_cache deactivation
        mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg()
        mm: memcg/slab: unify SLAB and SLUB page accounting
        mm: memcg/slab: don't check the dying flag on kmem_cache creation
        mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock
        mm: memcg/slab: rework non-root kmem_cache lifecycle management
        mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages
        mm: memcg/slab: reparent memcg kmem_caches on cgroup removal
      mm, memcg: add a memcg_slabinfo debugfs file

  mm:gup:
      Patch series "switch the remaining architectures to use generic GUP", v4:
        mm: use untagged_addr() for get_user_pages_fast addresses
        mm: simplify gup_fast_permitted
        mm: lift the x86_32 PAE version of gup_get_pte to common code
        MIPS: use the generic get_user_pages_fast code
        sh: add the missing pud_page definition
        sh: use the generic get_user_pages_fast code
        sparc64: add the missing pgd_page definition
        sparc64: define untagged_addr()
        sparc64: use the generic get_user_pages_fast code
        mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
        mm: reorder code blocks in gup.c
        mm: consolidate the get_user_pages* implementations
        mm: validate get_user_pages_fast flags
        mm: move the powerpc hugepd code to mm/gup.c
        mm: switch gup_hugepte to use try_get_compound_head
        mm: mark the page referenced in gup_hugepte
      mm/gup: speed up check_and_migrate_cma_pages() on huge page
      mm/gup.c: remove some BUG_ONs from get_gate_page()
      mm/gup.c: mark undo_dev_pagemap as __maybe_unused

  mm:pagemap:
      asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel]
      alpha: switch to generic version of pte allocation
      arm: switch to generic version of pte allocation
      arm64: switch to generic version of pte allocation
      csky: switch to generic version of pte allocation
      m68k: sun3: switch to generic version of pte allocation
      mips: switch to generic version of pte allocation
      nds32: switch to generic version of pte allocation
      nios2: switch to generic version of pte allocation
      parisc: switch to generic version of pte allocation
      riscv: switch to generic version of pte allocation
      um: switch to generic version of pte allocation
      unicore32: switch to generic version of pte allocation
      mm/pgtable: drop pgtable_t variable from pte_fn_t functions
      mm/memory.c: fail when offset == num in first check of __vm_map_pages()

  mm:infrastructure:
      mm/mmu_notifier: use hlist_add_head_rcu()

  mm:vmalloc:
      Patch series "Some cleanups for the KVA/vmalloc", v5:
        mm/vmalloc.c: remove "node" argument
        mm/vmalloc.c: preload a CPU with one object for split purpose
        mm/vmalloc.c: get rid of one single unlink_va() when merge
        mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va()
      mm/vmalloc.c: spelling> s/informaion/information/

  mm:initialization:
      mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist
      mm/large system hash: clear hashdist when only one node with memory is booted

  mm:pagealloc:
      arm64: move jump_label_init() before parse_early_param()
      Patch series "add init_on_alloc/init_on_free boot options", v10:
        mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
        mm: init: report memory auto-initialization features at boot time

  mm:vmscan:
      mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
      mm: vmscan: correct some vmscan counters for THP swapout

  mm:tools:
      tools/vm/slabinfo: order command line options
      tools/vm/slabinfo: add partial slab listing to -X
      tools/vm/slabinfo: add option to sort by partial slabs
      tools/vm/slabinfo: add sorting info to help menu

  mm:proc:
      proc: use down_read_killable mmap_sem for /proc/pid/maps
      proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
      proc: use down_read_killable mmap_sem for /proc/pid/pagemap
      proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
      proc: use down_read_killable mmap_sem for /proc/pid/map_files
      mm: use down_read_killable for locking mmap_sem in access_remote_vm
      mm: smaps: split PSS into components
      mm: vmalloc: show number of vmalloc pages in /proc/meminfo

  mm:ras:
      mm/memory-failure.c: clarify error message

  mm:oom-kill:
      mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
      mm, oom: refactor dump_tasks for memcg OOMs
      mm, oom: remove redundant task_in_mem_cgroup() check
      oom: decouple mems_allowed from oom_unkillable_task
      mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()"

* akpm: (147 commits)
  mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()
  oom: decouple mems_allowed from oom_unkillable_task
  mm, oom: remove redundant task_in_mem_cgroup() check
  mm, oom: refactor dump_tasks for memcg OOMs
  mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
  mm/memory-failure.c: clarify error message
  mm: vmalloc: show number of vmalloc pages in /proc/meminfo
  mm: smaps: split PSS into components
  mm: use down_read_killable for locking mmap_sem in access_remote_vm
  proc: use down_read_killable mmap_sem for /proc/pid/map_files
  proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
  proc: use down_read_killable mmap_sem for /proc/pid/pagemap
  proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
  proc: use down_read_killable mmap_sem for /proc/pid/maps
  tools/vm/slabinfo: add sorting info to help menu
  tools/vm/slabinfo: add option to sort by partial slabs
  tools/vm/slabinfo: add partial slab listing to -X
  tools/vm/slabinfo: order command line options
  mm: vmscan: correct some vmscan counters for THP swapout
  mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
  ...

1 files changed, 75 insertions, 21 deletions

diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b5fc5d3c7525..14207234fa3d 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -426,6 +426,7 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res)
 static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
 {
 	res->l_lock_refresh = 0;
+	res->l_lock_wait = 0;
 	memset(&res->l_lock_prmode, 0, sizeof(struct ocfs2_lock_stats));
 	memset(&res->l_lock_exmode, 0, sizeof(struct ocfs2_lock_stats));
 }
@@ -460,6 +461,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
 
 	if (ret)
 		stats->ls_fail++;
+
+	stats->ls_last = ktime_to_us(ktime_get_real());
 }
 
 static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
@@ -467,6 +470,21 @@ static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
 	lockres->l_lock_refresh++;
 }
 
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+	struct ocfs2_mask_waiter *mw;
+
+	if (list_empty(&lockres->l_mask_waiters)) {
+		lockres->l_lock_wait = 0;
+		return;
+	}
+
+	mw = list_first_entry(&lockres->l_mask_waiters,
+				struct ocfs2_mask_waiter, mw_item);
+	lockres->l_lock_wait =
+			ktime_to_us(ktime_mono_to_real(mw->mw_lock_start));
+}
+
 static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
 {
 	mw->mw_lock_start = ktime_get();
@@ -482,6 +500,9 @@ static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
 static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
 {
 }
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+}
 static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
 {
 }
@@ -875,6 +896,7 @@ static void lockres_set_flags(struct ocfs2_lock_res *lockres,
 		list_del_init(&mw->mw_item);
 		mw->mw_status = 0;
 		complete(&mw->mw_complete);
+		ocfs2_track_lock_wait(lockres);
 	}
 }
 static void lockres_or_flags(struct ocfs2_lock_res *lockres, unsigned long or)
@@ -1386,6 +1408,7 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres,
 	list_add_tail(&mw->mw_item, &lockres->l_mask_waiters);
 	mw->mw_mask = mask;
 	mw->mw_goal = goal;
+	ocfs2_track_lock_wait(lockres);
 }
 
 /* returns 0 if the mw that was removed was already satisfied, -EBUSY
@@ -1402,6 +1425,7 @@ static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
 
 		list_del_init(&mw->mw_item);
 		init_completion(&mw->mw_complete);
+		ocfs2_track_lock_wait(lockres);
 	}
 
 	return ret;
@@ -2989,6 +3013,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void)
 	kref_init(&dlm_debug->d_refcnt);
 	INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking);
 	dlm_debug->d_locking_state = NULL;
+	dlm_debug->d_locking_filter = NULL;
+	dlm_debug->d_filter_secs = 0;
 out:
 	return dlm_debug;
 }
@@ -3079,17 +3105,43 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
  *	- Lock stats printed
  * New in version 3
  *	- Max time in lock stats is in usecs (instead of nsecs)
+ * New in version 4
+ *	- Add last pr/ex unlock times and first lock wait time in usecs
  */
-#define OCFS2_DLM_DEBUG_STR_VERSION 3
+#define OCFS2_DLM_DEBUG_STR_VERSION 4
 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 {
 	int i;
 	char *lvb;
 	struct ocfs2_lock_res *lockres = v;
+#ifdef CONFIG_OCFS2_FS_STATS
+	u64 now, last;
+	struct ocfs2_dlm_debug *dlm_debug =
+			((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug;
+#endif
 
 	if (!lockres)
 		return -EINVAL;
 
+#ifdef CONFIG_OCFS2_FS_STATS
+	if (!lockres->l_lock_wait && dlm_debug->d_filter_secs) {
+		now = ktime_to_us(ktime_get_real());
+		if (lockres->l_lock_prmode.ls_last >
+		    lockres->l_lock_exmode.ls_last)
+			last = lockres->l_lock_prmode.ls_last;
+		else
+			last = lockres->l_lock_exmode.ls_last;
+		/*
+		 * Use d_filter_secs field to filter lock resources dump,
+		 * the default d_filter_secs(0) value filters nothing,
+		 * otherwise, only dump the last N seconds active lock
+		 * resources.
+		 */
+		if (div_u64(now - last, 1000000) > dlm_debug->d_filter_secs)
+			return 0;
+	}
+#endif
+
 	seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION);
 
 	if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY)
@@ -3131,6 +3183,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 # define lock_max_prmode(_l)		((_l)->l_lock_prmode.ls_max)
 # define lock_max_exmode(_l)		((_l)->l_lock_exmode.ls_max)
 # define lock_refresh(_l)		((_l)->l_lock_refresh)
+# define lock_last_prmode(_l)		((_l)->l_lock_prmode.ls_last)
+# define lock_last_exmode(_l)		((_l)->l_lock_exmode.ls_last)
+# define lock_wait(_l)			((_l)->l_lock_wait)
 #else
 # define lock_num_prmode(_l)		(0)
 # define lock_num_exmode(_l)		(0)
@@ -3141,6 +3196,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 # define lock_max_prmode(_l)		(0)
 # define lock_max_exmode(_l)		(0)
 # define lock_refresh(_l)		(0)
+# define lock_last_prmode(_l)		(0ULL)
+# define lock_last_exmode(_l)		(0ULL)
+# define lock_wait(_l)			(0ULL)
 #endif
 	/* The following seq_print was added in version 2 of this output */
 	seq_printf(m, "%u\t"
@@ -3151,7 +3209,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 		   "%llu\t"
 		   "%u\t"
 		   "%u\t"
-		   "%u\t",
+		   "%u\t"
+		   "%llu\t"
+		   "%llu\t"
+		   "%llu\t",
 		   lock_num_prmode(lockres),
 		   lock_num_exmode(lockres),
 		   lock_num_prmode_failed(lockres),
@@ -3160,7 +3221,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 		   lock_total_exmode(lockres),
 		   lock_max_prmode(lockres),
 		   lock_max_exmode(lockres),
-		   lock_refresh(lockres));
+		   lock_refresh(lockres),
+		   lock_last_prmode(lockres),
+		   lock_last_exmode(lockres),
+		   lock_wait(lockres));
 
 	/* End the line */
 	seq_printf(m, "\n");
@@ -3214,9 +3278,8 @@ static const struct file_operations ocfs2_dlm_debug_fops = {
 	.llseek =	seq_lseek,
 };
 
-static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
+static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
 {
-	int ret = 0;
 	struct ocfs2_dlm_debug *dlm_debug = osb->osb_dlm_debug;
 
 	dlm_debug->d_locking_state = debugfs_create_file("locking_state",
@@ -3224,16 +3287,11 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
 							 osb->osb_debug_root,
 							 osb,
 							 &ocfs2_dlm_debug_fops);
-	if (!dlm_debug->d_locking_state) {
-		ret = -EINVAL;
-		mlog(ML_ERROR,
-		     "Unable to create locking state debugfs file.\n");
-		goto out;
-	}
 
-	ocfs2_get_dlm_debug(dlm_debug);
-out:
-	return ret;
+	dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter",
+						0600,
+						osb->osb_debug_root,
+						&dlm_debug->d_filter_secs);
 }
 
 static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
@@ -3242,6 +3300,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
 
 	if (dlm_debug) {
 		debugfs_remove(dlm_debug->d_locking_state);
+		debugfs_remove(dlm_debug->d_locking_filter);
 		ocfs2_put_dlm_debug(dlm_debug);
 	}
 }
@@ -3256,11 +3315,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 		goto local;
 	}
 
-	status = ocfs2_dlm_init_debug(osb);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-	}
+	ocfs2_dlm_init_debug(osb);
 
 	/* launch downconvert thread */
 	osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s",
@@ -4352,7 +4407,6 @@ static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb)
 
 static int ocfs2_downconvert_thread(void *arg)
 {
-	int status = 0;
 	struct ocfs2_super *osb = arg;
 
 	/* only quit once we've been asked to stop and there is no more
@@ -4370,7 +4424,7 @@ static int ocfs2_downconvert_thread(void *arg)
 	}
 
 	osb->dc_task = NULL;
-	return status;
+	return 0;
 }
 
 void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb)