Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "More mm/ work, plenty more to come

  Subsystems affected by this patch series: slub, memcg, gup, kasan,
  pagealloc, hugetlb, vmscan, tools, mempolicy, memblock, hugetlbfs,
  thp, mmap, kconfig"

* akpm: (131 commits)
  arm64: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  x86: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  riscv: support DEBUG_WX
  mm: add DEBUG_WX support
  drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
  mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
  powerpc/mm: drop platform defined pmd_mknotpresent()
  mm: thp: don't need to drain lru cache when splitting and mlocking THP
  hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
  sparc32: register memory occupied by kernel as memblock.memory
  include/linux/memblock.h: fix minor typo and unclear comment
  mm, mempolicy: fix up gup usage in lookup_node
  tools/vm/page_owner_sort.c: filter out unneeded line
  mm: swap: memcg: fix memcg stats for huge pages
  mm: swap: fix vmstats for huge pages
  mm: vmscan: limit the range of LRU type balancing
  mm: vmscan: reclaim writepage is IO cost
  mm: vmscan: determine anon/file pressure balance at the reclaim root
  mm: balance LRU lists based on relative thrashing
  mm: only count actual rotations as LRU reclaim cost
  ...

1 files changed, 36 insertions, 7 deletions

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 693cae9bfe66..7302efff5e65 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -4,6 +4,9 @@
  *
  * Copyright (C) 2008, 2009 secunet Security Networks AG
  * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Copyright (c) 2020 Oracle and/or its affiliates.
+ * Author: Daniel Jordan <daniel.m.jordan@oracle.com>
  */
 
 #ifndef PADATA_H
@@ -24,7 +27,6 @@
  * @list: List entry, to attach to the padata lists.
  * @pd: Pointer to the internal control structure.
  * @cb_cpu: Callback cpu for serializatioon.
- * @cpu: Cpu for parallelization.
  * @seq_nr: Sequence number of the parallelized data object.
  * @info: Used to pass information from the parallel to the serial function.
  * @parallel: Parallel execution function.
@@ -34,7 +36,6 @@ struct padata_priv {
 	struct list_head	list;
 	struct parallel_data	*pd;
 	int			cb_cpu;
-	int			cpu;
 	unsigned int		seq_nr;
 	int			info;
 	void                    (*parallel)(struct padata_priv *padata);
@@ -68,15 +69,11 @@ struct padata_serial_queue {
 /**
  * struct padata_parallel_queue - The percpu padata parallel queue
  *
- * @parallel: List to wait for parallelization.
  * @reorder: List to wait for reordering after parallel processing.
- * @work: work struct for parallelization.
  * @num_obj: Number of objects that are processed by this cpu.
  */
 struct padata_parallel_queue {
-       struct padata_list    parallel;
        struct padata_list    reorder;
-       struct work_struct    work;
        atomic_t              num_obj;
 };
 
@@ -111,7 +108,7 @@ struct parallel_data {
 	struct padata_parallel_queue	__percpu *pqueue;
 	struct padata_serial_queue	__percpu *squeue;
 	atomic_t			refcnt;
-	atomic_t			seq_nr;
+	unsigned int			seq_nr;
 	unsigned int			processed;
 	int				cpu;
 	struct padata_cpumask		cpumask;
@@ -137,6 +134,31 @@ struct padata_shell {
 };
 
 /**
+ * struct padata_mt_job - represents one multithreaded job
+ *
+ * @thread_fn: Called for each chunk of work that a padata thread does.
+ * @fn_arg: The thread function argument.
+ * @start: The start of the job (units are job-specific).
+ * @size: size of this node's work (units are job-specific).
+ * @align: Ranges passed to the thread function fall on this boundary, with the
+ *         possible exceptions of the beginning and end of the job.
+ * @min_chunk: The minimum chunk size in job-specific units.  This allows
+ *             the client to communicate the minimum amount of work that's
+ *             appropriate for one worker thread to do at once.
+ * @max_threads: Max threads to use for the job, actual number may be less
+ *               depending on task size and minimum chunk size.
+ */
+struct padata_mt_job {
+	void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
+	void			*fn_arg;
+	unsigned long		start;
+	unsigned long		size;
+	unsigned long		align;
+	unsigned long		min_chunk;
+	int			max_threads;
+};
+
+/**
  * struct padata_instance - The overall control structure.
  *
  * @cpu_online_node: Linkage for CPU online callback.
@@ -166,6 +188,12 @@ struct padata_instance {
 #define	PADATA_INVALID	4
 };
 
+#ifdef CONFIG_PADATA
+extern void __init padata_init(void);
+#else
+static inline void __init padata_init(void) {}
+#endif
+
 extern struct padata_instance *padata_alloc_possible(const char *name);
 extern void padata_free(struct padata_instance *pinst);
 extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
@@ -173,6 +201,7 @@ extern void padata_free_shell(struct padata_shell *ps);
 extern int padata_do_parallel(struct padata_shell *ps,
 			      struct padata_priv *padata, int *cb_cpu);
 extern void padata_do_serial(struct padata_priv *padata);
+extern void __init padata_do_multithreaded(struct padata_mt_job *job);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
 extern int padata_start(struct padata_instance *pinst);