Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:

 - Yosry Ahmed brought back some cgroup v1 stats in OOM logs

 - Yosry has also eliminated cgroup's atomic rstat flushing

 - Nhat Pham adds the new cachestat() syscall. It provides userspace
   with the ability to query pagecache status - a similar concept to
   mincore() but more powerful and with improved usability

 - Mel Gorman provides more optimizations for compaction, reducing the
   prevalence of page rescanning

 - Lorenzo Stoakes has done some maintanance work on the
   get_user_pages() interface

 - Liam Howlett continues with cleanups and maintenance work to the
   maple tree code. Peng Zhang also does some work on maple tree

 - Johannes Weiner has done some cleanup work on the compaction code

 - David Hildenbrand has contributed additional selftests for
   get_user_pages()

 - Thomas Gleixner has contributed some maintenance and optimization
   work for the vmalloc code

 - Baolin Wang has provided some compaction cleanups,

 - SeongJae Park continues maintenance work on the DAMON code

 - Huang Ying has done some maintenance on the swap code's usage of
   device refcounting

 - Christoph Hellwig has some cleanups for the filemap/directio code

 - Ryan Roberts provides two patch series which yield some
   rationalization of the kernel's access to pte entries - use the
   provided APIs rather than open-coding accesses

 - Lorenzo Stoakes has some fixes to the interaction between pagecache
   and directio access to file mappings

 - John Hubbard has a series of fixes to the MM selftesting code

 - ZhangPeng continues the folio conversion campaign

 - Hugh Dickins has been working on the pagetable handling code, mainly
   with a view to reducing the load on the mmap_lock

 - Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
   from 128 to 8

 - Domenico Cerasuolo has improved the zswap reclaim mechanism by
   reorganizing the LRU management

 - Matthew Wilcox provides some fixups to make gfs2 work better with the
   buffer_head code

 - Vishal Moola also has done some folio conversion work

 - Matthew Wilcox has removed the remnants of the pagevec code - their
   functionality is migrated over to struct folio_batch

* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
  mm/hugetlb: remove hugetlb_set_page_subpool()
  mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
  hugetlb: revert use of page_cache_next_miss()
  Revert "page cache: fix page_cache_next/prev_miss off by one"
  mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
  mm: memcg: rename and document global_reclaim()
  mm: kill [add|del]_page_to_lru_list()
  mm: compaction: convert to use a folio in isolate_migratepages_block()
  mm: zswap: fix double invalidate with exclusive loads
  mm: remove unnecessary pagevec includes
  mm: remove references to pagevec
  mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
  mm: remove struct pagevec
  net: convert sunrpc from pagevec to folio_batch
  i915: convert i915_gpu_error to use a folio_batch
  pagevec: rename fbatch_count()
  mm: remove check_move_unevictable_pages()
  drm: convert drm_gem_put_pages() to use a folio_batch
  i915: convert shmem_sg_free_table() to use a folio_batch
  scatterlist: add sg_set_folio()
  ...

42 files changed, 618 insertions, 640 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 1520793c72da..c794ea7096ba 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -263,7 +263,7 @@ extern int buffer_heads_over_limit;
 void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
-int __block_write_full_page(struct inode *inode, struct page *page,
+int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			get_block_t *get_block, struct writeback_control *wbc,
 			bh_end_io_t *handler);
 int block_read_full_folio(struct folio *, get_block_t *);
@@ -278,7 +278,7 @@ int block_write_end(struct file *, struct address_space *,
 int generic_write_end(struct file *, struct address_space *,
 				loff_t, unsigned, unsigned,
 				struct page *, void *);
-void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
+void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
 void clean_page_buffers(struct page *page);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
 			unsigned, struct page **, void **,
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 5da1bbd96154..9900d20b76c2 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -98,4 +98,10 @@ struct cacheline_padding {
 #define CACHELINE_PADDING(name)
 #endif
 
+#ifdef ARCH_DMA_MINALIGN
+#define ARCH_HAS_DMA_MINALIGN
+#else
+#define ARCH_DMA_MINALIGN __alignof__(unsigned long long)
+#endif
+
 #endif /* __LINUX_CACHE_H */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1261a47932a6..b307013b9c6c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -691,7 +691,6 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
  */
 void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
 void cgroup_rstat_flush(struct cgroup *cgrp);
-void cgroup_rstat_flush_atomic(struct cgroup *cgrp);
 void cgroup_rstat_flush_hold(struct cgroup *cgrp);
 void cgroup_rstat_flush_release(void);
 
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index a6e512cfb670..e94776496049 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -89,89 +89,17 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		const struct alloc_context *ac, enum compact_priority prio,
 		struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern enum compact_result compaction_suitable(struct zone *zone, int order,
-		unsigned int alloc_flags, int highest_zoneidx);
+extern bool compaction_suitable(struct zone *zone, int order,
+					       int highest_zoneidx);
 
 extern void compaction_defer_reset(struct zone *zone, int order,
 				bool alloc_success);
 
-/* Compaction has made some progress and retrying makes sense */
-static inline bool compaction_made_progress(enum compact_result result)
-{
-	/*
-	 * Even though this might sound confusing this in fact tells us
-	 * that the compaction successfully isolated and migrated some
-	 * pageblocks.
-	 */
-	if (result == COMPACT_SUCCESS)
-		return true;
-
-	return false;
-}
-
-/* Compaction has failed and it doesn't make much sense to keep retrying. */
-static inline bool compaction_failed(enum compact_result result)
-{
-	/* All zones were scanned completely and still not result. */
-	if (result == COMPACT_COMPLETE)
-		return true;
-
-	return false;
-}
-
-/* Compaction needs reclaim to be performed first, so it can continue. */
-static inline bool compaction_needs_reclaim(enum compact_result result)
-{
-	/*
-	 * Compaction backed off due to watermark checks for order-0
-	 * so the regular reclaim has to try harder and reclaim something.
-	 */
-	if (result == COMPACT_SKIPPED)
-		return true;
-
-	return false;
-}
-
-/*
- * Compaction has backed off for some reason after doing some work or none
- * at all. It might be throttling or lock contention. Retrying might be still
- * worthwhile, but with a higher priority if allowed.
- */
-static inline bool compaction_withdrawn(enum compact_result result)
-{
-	/*
-	 * If compaction is deferred for high-order allocations, it is
-	 * because sync compaction recently failed. If this is the case
-	 * and the caller requested a THP allocation, we do not want
-	 * to heavily disrupt the system, so we fail the allocation
-	 * instead of entering direct reclaim.
-	 */
-	if (result == COMPACT_DEFERRED)
-		return true;
-
-	/*
-	 * If compaction in async mode encounters contention or blocks higher
-	 * priority task we back off early rather than cause stalls.
-	 */
-	if (result == COMPACT_CONTENDED)
-		return true;
-
-	/*
-	 * Page scanners have met but we haven't scanned full zones so this
-	 * is a back off in fact.
-	 */
-	if (result == COMPACT_PARTIAL_SKIPPED)
-		return true;
-
-	return false;
-}
-
-
 bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 					int alloc_flags);
 
-extern void kcompactd_run(int nid);
-extern void kcompactd_stop(int nid);
+extern void __meminit kcompactd_run(int nid);
+extern void __meminit kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
 
 #else
@@ -179,32 +107,12 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline enum compact_result compaction_suitable(struct zone *zone, int order,
-					int alloc_flags, int highest_zoneidx)
-{
-	return COMPACT_SKIPPED;
-}
-
-static inline bool compaction_made_progress(enum compact_result result)
-{
-	return false;
-}
-
-static inline bool compaction_failed(enum compact_result result)
-{
-	return false;
-}
-
-static inline bool compaction_needs_reclaim(enum compact_result result)
+static inline bool compaction_suitable(struct zone *zone, int order,
+						      int highest_zoneidx)
 {
 	return false;
 }
 
-static inline bool compaction_withdrawn(enum compact_result result)
-{
-	return true;
-}
-
 static inline void kcompactd_run(int nid)
 {
 }
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 31f114f486c4..9bf19b5bf755 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pgtable.h>
+#include <linux/slab.h>
 
 struct cma;
 
@@ -277,6 +278,66 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
+/*
+ * Check whether potential kmalloc() buffers are safe for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_safe(struct device *dev,
+				    enum dma_data_direction dir)
+{
+	/*
+	 * If DMA bouncing of kmalloc() buffers is disabled, the kmalloc()
+	 * caches have already been aligned to a DMA-safe size.
+	 */
+	if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+		return true;
+
+	/*
+	 * kmalloc() buffers are DMA-safe irrespective of size if the device
+	 * is coherent or the direction is DMA_TO_DEVICE (non-desctructive
+	 * cache maintenance and benign cache line evictions).
+	 */
+	if (dev_is_dma_coherent(dev) || dir == DMA_TO_DEVICE)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given size, assuming it is for a kmalloc()'ed buffer, is
+ * sufficiently aligned for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_size_aligned(size_t size)
+{
+	/*
+	 * Larger kmalloc() sizes are guaranteed to be aligned to
+	 * ARCH_DMA_MINALIGN.
+	 */
+	if (size >= 2 * ARCH_DMA_MINALIGN ||
+	    IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment()))
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given object size may have originated from a kmalloc()
+ * buffer with a slab alignment below the DMA-safe alignment and needs
+ * bouncing for non-coherent DMA. The pointer alignment is not considered and
+ * in-structure DMA-safe offsets are the responsibility of the caller. Such
+ * code should use the static ARCH_DMA_MINALIGN for compiler annotations.
+ *
+ * The heuristics can have false positives, bouncing unnecessarily, though the
+ * buffers would be small. False negatives are theoretically possible if, for
+ * example, multiple small kmalloc() buffers are coalesced into a larger
+ * buffer that passes the alignment check. There are no such known constructs
+ * in the kernel.
+ */
+static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size,
+					    enum dma_data_direction dir)
+{
+	return !dma_kmalloc_safe(dev, dir) && !dma_kmalloc_size_aligned(size);
+}
+
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 0ee20b764000..e13050eb9777 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_DMA_MAPPING_H
 #define _LINUX_DMA_MAPPING_H
 
+#include <linux/cache.h>
 #include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/device.h>
@@ -543,13 +544,15 @@ static inline int dma_set_min_align_mask(struct device *dev,
 	return 0;
 }
 
+#ifndef dma_get_cache_alignment
 static inline int dma_get_cache_alignment(void)
 {
-#ifdef ARCH_DMA_MINALIGN
+#ifdef ARCH_HAS_DMA_MINALIGN
 	return ARCH_DMA_MINALIGN;
 #endif
 	return 1;
 }
+#endif
 
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 481abf530b3c..6d5edef09d45 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -93,6 +93,15 @@ struct kmem_cache;
 
 bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
 
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
+#else
+static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+	return false;
+}
+#endif /* CONFIG_FAIL_PAGE_ALLOC */
+
 int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #ifdef CONFIG_FAILSLAB
 extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags);
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index a631bac12220..eaa0ac5f9003 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -10,7 +10,7 @@
 struct frontswap_ops {
 	void (*init)(unsigned); /* this swap type was just swapon'ed */
 	int (*store)(unsigned, pgoff_t, struct page *); /* store a page */
-	int (*load)(unsigned, pgoff_t, struct page *); /* load a page */
+	int (*load)(unsigned, pgoff_t, struct page *, bool *); /* load a page */
 	void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */
 	void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed5b32dc2625..122b218b66c9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2763,6 +2763,8 @@ extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
 ssize_t generic_perform_write(struct kiocb *, struct iov_iter *);
+ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
+		ssize_t direct_written, ssize_t buffered_written);
 
 ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags);
@@ -2860,11 +2862,6 @@ static inline void inode_dio_end(struct inode *inode)
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 
-/*
- * Warn about a page cache invalidation failure diring a direct I/O write.
- */
-void dio_warn_stale_pagecache(struct file *filp);
-
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
 			    unsigned int mask);
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index ed8cb537c6a7..665f06675c83 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -338,19 +338,12 @@ extern gfp_t gfp_allowed_mask;
 /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
 bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
 
-extern void pm_restrict_gfp_mask(void);
-extern void pm_restore_gfp_mask(void);
-
-extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
-
-#ifdef CONFIG_PM_SLEEP
-extern bool pm_suspended_storage(void);
-#else
-static inline bool pm_suspended_storage(void)
+static inline bool gfp_has_io_fs(gfp_t gfp)
 {
-	return false;
+	return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
 }
-#endif /* CONFIG_PM_SLEEP */
+
+extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_CONTIG_ALLOC
 /* The below functions must be run on a range from a single zone. */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6d041aa9f0fe..ca3c8e10f24a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -133,9 +133,8 @@ int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
 struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 				unsigned long address, unsigned int flags);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
-			 struct page **, struct vm_area_struct **,
-			 unsigned long *, unsigned long *, long, unsigned int,
-			 int *);
+			 struct page **, unsigned long *, unsigned long *,
+			 long, unsigned int, int *);
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *,
 			  zap_flags_t);
@@ -306,9 +305,8 @@ static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
 
 static inline long follow_hugetlb_page(struct mm_struct *mm,
 			struct vm_area_struct *vma, struct page **pages,
-			struct vm_area_struct **vmas, unsigned long *position,
-			unsigned long *nr_pages, long i, unsigned int flags,
-			int *nonblocking)
+			unsigned long *position, unsigned long *nr_pages,
+			long i, unsigned int flags, int *nonblocking)
 {
 	BUG();
 	return 0;
@@ -757,26 +755,12 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio
 	return folio->_hugetlb_subpool;
 }
 
-/*
- * hugetlb page subpool pointer located in hpage[2].hugetlb_subpool
- */
-static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
-{
-	return hugetlb_folio_subpool(page_folio(hpage));
-}
-
 static inline void hugetlb_set_folio_subpool(struct folio *folio,
 					struct hugepage_subpool *subpool)
 {
 	folio->_hugetlb_subpool = subpool;
 }
 
-static inline void hugetlb_set_page_subpool(struct page *hpage,
-					struct hugepage_subpool *subpool)
-{
-	hugetlb_set_folio_subpool(page_folio(hpage), subpool);
-}
-
 static inline struct hstate *hstate_file(struct file *f)
 {
 	return hstate_inode(file_inode(f));
@@ -1031,11 +1015,6 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio
 	return NULL;
 }
 
-static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
-{
-	return NULL;
-}
-
 static inline int isolate_or_dissolve_huge_page(struct page *page,
 						struct list_head *list)
 {
@@ -1200,7 +1179,11 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
+#ifdef CONFIG_MMU
+	return ptep_get(ptep);
+#else
 	return *ptep;
+#endif
 }
 
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 81413cd3a3e7..d28a5e8097e4 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -722,7 +722,7 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
  * must not share  cachelines with the rest of the structure, thus making
  * them safe for use with non-coherent DMA.
  */
-#define IIO_DMA_MINALIGN ARCH_KMALLOC_MINALIGN
+#define IIO_DMA_MINALIGN ARCH_DMA_MINALIGN
 struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv);
 
 /* The information at the returned address is guaranteed to be cacheline aligned */
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index f7ef70661ce2..819b6bc8ac08 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -343,7 +343,7 @@ static inline void *kasan_reset_tag(const void *addr)
  * @is_write: whether the bad access is a write or a read
  * @ip: instruction pointer for the accessibility check or the bad access itself
  */
-bool kasan_report(unsigned long addr, size_t size,
+bool kasan_report(const void *addr, size_t size,
 		bool is_write, unsigned long ip);
 
 #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 1fadb5f5978b..295548cca8b3 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -455,7 +455,9 @@ void *mas_erase(struct ma_state *mas);
 int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp);
 void mas_store_prealloc(struct ma_state *mas, void *entry);
 void *mas_find(struct ma_state *mas, unsigned long max);
+void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
+void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
 int mas_preallocate(struct ma_state *mas, gfp_t gfp);
 bool mas_is_err(struct ma_state *mas);
 
@@ -466,10 +468,18 @@ void mas_destroy(struct ma_state *mas);
 int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries);
 
 void *mas_prev(struct ma_state *mas, unsigned long min);
+void *mas_prev_range(struct ma_state *mas, unsigned long max);
 void *mas_next(struct ma_state *mas, unsigned long max);
+void *mas_next_range(struct ma_state *mas, unsigned long max);
 
 int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max,
 		   unsigned long size);
+/*
+ * This finds an empty area from the highest address to the lowest.
+ * AKA "Topdown" version,
+ */
+int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
+		       unsigned long max, unsigned long size);
 
 static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
 			    unsigned long addr)
@@ -482,23 +492,17 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
 }
 
 /* Checks if a mas has not found anything */
-static inline bool mas_is_none(struct ma_state *mas)
+static inline bool mas_is_none(const struct ma_state *mas)
 {
 	return mas->node == MAS_NONE;
 }
 
 /* Checks if a mas has been paused */
-static inline bool mas_is_paused(struct ma_state *mas)
+static inline bool mas_is_paused(const struct ma_state *mas)
 {
 	return mas->node == MAS_PAUSE;
 }
 
-/*
- * This finds an empty area from the highest address to the lowest.
- * AKA "Topdown" version,
- */
-int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
-		       unsigned long max, unsigned long size);
 /**
  * mas_reset() - Reset a Maple Tree operation state.
  * @mas: Maple Tree operation state.
@@ -528,7 +532,6 @@ static inline void mas_reset(struct ma_state *mas)
 #define mas_for_each(__mas, __entry, __max) \
 	while (((__entry) = mas_find((__mas), (__max))) != NULL)
 
-
 /**
  * mas_set_range() - Set up Maple Tree operation state for a different index.
  * @mas: Maple Tree operation state.
@@ -616,7 +619,7 @@ static inline void mt_clear_in_rcu(struct maple_tree *mt)
 		return;
 
 	if (mt_external_lock(mt)) {
-		BUG_ON(!mt_lock_is_held(mt));
+		WARN_ON(!mt_lock_is_held(mt));
 		mt->ma_flags &= ~MT_FLAGS_USE_RCU;
 	} else {
 		mtree_lock(mt);
@@ -635,7 +638,7 @@ static inline void mt_set_in_rcu(struct maple_tree *mt)
 		return;
 
 	if (mt_external_lock(mt)) {
-		BUG_ON(!mt_lock_is_held(mt));
+		WARN_ON(!mt_lock_is_held(mt));
 		mt->ma_flags |= MT_FLAGS_USE_RCU;
 	} else {
 		mtree_lock(mt);
@@ -670,10 +673,17 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max);
 
 
 #ifdef CONFIG_DEBUG_MAPLE_TREE
+enum mt_dump_format {
+	mt_dump_dec,
+	mt_dump_hex,
+};
+
 extern atomic_t maple_tree_tests_run;
 extern atomic_t maple_tree_tests_passed;
 
-void mt_dump(const struct maple_tree *mt);
+void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
+void mas_dump(const struct ma_state *mas);
+void mas_wr_dump(const struct ma_wr_state *wr_mas);
 void mt_validate(struct maple_tree *mt);
 void mt_cache_shrink(void);
 #define MT_BUG_ON(__tree, __x) do {					\
@@ -681,7 +691,23 @@ void mt_cache_shrink(void);
 	if (__x) {							\
 		pr_info("BUG at %s:%d (%u)\n",				\
 		__func__, __LINE__, __x);				\
-		mt_dump(__tree);					\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_BUG_ON(__mas, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
 		pr_info("Pass: %u Run:%u\n",				\
 			atomic_read(&maple_tree_tests_passed),		\
 			atomic_read(&maple_tree_tests_run));		\
@@ -690,8 +716,84 @@ void mt_cache_shrink(void);
 		atomic_inc(&maple_tree_tests_passed);