Merge branch 'xarray' of git://git.infradead.org/users/willy/linux-dax

Pull XArray conversion from Matthew Wilcox:
 "The XArray provides an improved interface to the radix tree data
  structure, providing locking as part of the API, specifying GFP flags
  at allocation time, eliminating preloading, less re-walking the tree,
  more efficient iterations and not exposing RCU-protected pointers to
  its users.

  This patch set

   1. Introduces the XArray implementation

   2. Converts the pagecache to use it

   3. Converts memremap to use it

  The page cache is the most complex and important user of the radix
  tree, so converting it was most important. Converting the memremap
  code removes the only other user of the multiorder code, which allows
  us to remove the radix tree code that supported it.

  I have 40+ followup patches to convert many other users of the radix
  tree over to the XArray, but I'd like to get this part in first. The
  other conversions haven't been in linux-next and aren't suitable for
  applying yet, but you can see them in the xarray-conv branch if you're
  interested"

* 'xarray' of git://git.infradead.org/users/willy/linux-dax: (90 commits)
  radix tree: Remove multiorder support
  radix tree test: Convert multiorder tests to XArray
  radix tree tests: Convert item_delete_rcu to XArray
  radix tree tests: Convert item_kill_tree to XArray
  radix tree tests: Move item_insert_order
  radix tree test suite: Remove multiorder benchmarking
  radix tree test suite: Remove __item_insert
  memremap: Convert to XArray
  xarray: Add range store functionality
  xarray: Move multiorder_check to in-kernel tests
  xarray: Move multiorder_shrink to kernel tests
  xarray: Move multiorder account test in-kernel
  radix tree test suite: Convert iteration test to XArray
  radix tree test suite: Convert tag_tagged_items to XArray
  radix tree: Remove radix_tree_clear_tags
  radix tree: Remove radix_tree_maybe_preload_order
  radix tree: Remove split/join code
  radix tree: Remove radix_tree_update_node_t
  page cache: Finish XArray conversion
  dax: Convert page fault handlers to XArray
  ...

28 files changed, 497 insertions, 1008 deletions

diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 9bce3b56b5e7..5d2ab38965cc 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -27,5 +27,6 @@
 #include <asm-generic/bitops/hweight.h>
 
 #include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
 
 #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 21c41ccd1266..2f6ea28764a7 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -15,13 +15,4 @@ static inline void clear_bit(int nr, unsigned long *addr)
 	addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG));
 }
 
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-	return ((1UL << (nr % __BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0;
-}
-
-#define __set_bit(nr, addr)	set_bit(nr, addr)
-#define __clear_bit(nr, addr)	clear_bit(nr, addr)
-
 #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 000000000000..7e10c4b50c5d
--- /dev/null
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <asm/types.h>
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index e63662db131b..05dca5c203f3 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -15,6 +15,7 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, int bits);
 int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int bits);
+void bitmap_clear(unsigned long *map, unsigned int start, int len);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 0ad884452c5c..6935ef94e77a 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -70,6 +70,7 @@
 #define BUG_ON(cond) assert(!(cond))
 #endif
 #endif
+#define BUG()	BUG_ON(1)
 
 #if __BYTE_ORDER == __BIG_ENDIAN
 #define cpu_to_le16 bswap_16
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 1738c0391da4..c934572d935c 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -8,8 +8,14 @@
 #define spinlock_t		pthread_mutex_t
 #define DEFINE_SPINLOCK(x)	pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
 #define __SPIN_LOCK_UNLOCKED(x)	(pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
-#define spin_lock_init(x)      pthread_mutex_init(x, NULL)
-
+#define spin_lock_init(x)	pthread_mutex_init(x, NULL)
+
+#define spin_lock(x)			pthread_mutex_lock(x)
+#define spin_unlock(x)			pthread_mutex_unlock(x)
+#define spin_lock_bh(x)			pthread_mutex_lock(x)
+#define spin_unlock_bh(x)		pthread_mutex_unlock(x)
+#define spin_lock_irq(x)		pthread_mutex_lock(x)
+#define spin_unlock_irq(x)		pthread_mutex_unlock(x)
 #define spin_lock_irqsave(x, f)		(void)f, pthread_mutex_lock(x)
 #define spin_unlock_irqrestore(x, f)	(void)f, pthread_mutex_unlock(x)
 
@@ -31,4 +37,6 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
+#include <linux/lockdep.h>
+
 #endif
diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore
index d4706c0ffceb..3834899b6693 100644
--- a/tools/testing/radix-tree/.gitignore
+++ b/tools/testing/radix-tree/.gitignore
@@ -4,3 +4,4 @@ idr-test
 main
 multiorder
 radix-tree.c
+xarray
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 37baecc3766f..acf1afa01c5b 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -4,8 +4,8 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \
 	  -fsanitize=undefined
 LDFLAGS += -fsanitize=address -fsanitize=undefined
 LDLIBS+= -lpthread -lurcu
-TARGETS = main idr-test multiorder
-CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
+TARGETS = main idr-test multiorder xarray
+CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
 	 tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o
 
@@ -25,6 +25,8 @@ main:	$(OFILES)
 idr-test.o: ../../../lib/test_ida.c
 idr-test: idr-test.o $(CORE_OFILES)
 
+xarray: $(CORE_OFILES)
+
 multiorder: multiorder.o $(CORE_OFILES)
 
 clean:
@@ -35,6 +37,7 @@ vpath %.c ../../lib
 $(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
+	../../../include/linux/xarray.h \
 	../../../include/linux/radix-tree.h \
 	../../../include/linux/idr.h
 
@@ -44,8 +47,10 @@ radix-tree.c: ../../../lib/radix-tree.c
 idr.c: ../../../lib/idr.c
 	sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
 
+xarray.o: ../../../lib/xarray.c ../../../lib/test_xarray.c
+
 generated/map-shift.h:
 	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
-		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
+		echo "#define XA_CHUNK_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 99c40f3ed133..7e195ed8e92d 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,9 +17,6 @@
 #include <time.h>
 #include "test.h"
 
-#define for_each_index(i, base, order) \
-	        for (i = base; i < base + (1 << order); i++)
-
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -61,7 +58,7 @@ again:
 }
 
 static void benchmark_insert(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -70,19 +67,19 @@ static void benchmark_insert(struct radix_tree_root *root,
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		item_insert_order(root, index, order);
+		item_insert(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, insertion: %15lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_tagging(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
 	unsigned long index;
@@ -98,138 +95,53 @@ static void benchmark_tagging(struct radix_tree_root *root,
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, tagging: %17lld ns\n",
+		size, step, nsec);
 }
 
 static void benchmark_delete(struct radix_tree_root *root,
-			     unsigned long size, unsigned long step, int order)
+			     unsigned long size, unsigned long step)
 {
 	struct timespec start, finish;
-	unsigned long index, i;
+	unsigned long index;
 	long long nsec;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	for (index = 0 ; index < size ; index += step)
-		for_each_index(i, index, order)
-			item_delete(root, i);
+		item_delete(root, index);
 
 	clock_gettime(CLOCK_MONOTONIC, &finish);
 
 	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
 	       (finish.tv_nsec - start.tv_nsec);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
-		size, step, order, nsec);
+	printv(2, "Size: %8ld, step: %8ld, deletion: %16lld ns\n",
+		size, step, nsec);
 }
 
-static void benchmark_size(unsigned long size, unsigned long step, int order)
+static void benchmark_size(unsigned long size, unsigned long step)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
 
-	benchmark_insert(&tree, size, step, order);
-	benchmark_tagging(&tree, size, step, order);
+	benchmark_insert(&tree, size, step);
+	benchmark_tagging(&tree, size, step);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
-		size, step, order, tagged);
-	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
-		size, step, order, normal);
+	printv(2, "Size: %8ld, step: %8ld, tagged iteration: %8lld ns\n",
+		size, step, tagged);
+	printv(2, "Size: %8ld, step: %8ld, normal iteration: %8lld ns\n",
+		size, step, normal);
 
-	benchmark_delete(&tree, size, step, order);
+	benchmark_delete(&tree, size, step);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
 }
 
-static long long  __benchmark_split(unsigned long index,
-				    int old_order, int new_order)
-{
-	struct timespec start, finish;
-	long long nsec;
-	RADIX_TREE(tree, GFP_ATOMIC);
-
-	item_insert_order(&tree, index, old_order);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_split(&tree, index, new_order);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-	       (finish.tv_nsec - start.tv_nsec);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-
-}
-
-static void benchmark_split(unsigned long size, unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-
-	for (idx = 0; idx < size; idx += step) {
-		for (i = 3; i < 11; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_split(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
-			size, step, nsec);
-
-}
-
-static long long  __benchmark_join(unsigned long index,
-			     unsigned order1, unsigned order2)
-{
-	unsigned long loc;
-	struct timespec start, finish;
-	long long nsec;
-	void *item, *item2 = item_create(index + 1, order1);
-	RADIX_TREE(tree, GFP_KERNEL);
-
-	item_insert_order(&tree, index, order2);
-	item = radix_tree_lookup(&tree, index);
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	radix_tree_join(&tree, index + 1, order1, item2);
-	clock_gettime(CLOCK_MONOTONIC, &finish);
-	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
-		(finish.tv_nsec - start.tv_nsec);
-
-	loc = find_item(&tree, item);
-	if (loc == -1)
-		free(item);
-
-	item_kill_tree(&tree);
-
-	return nsec;
-}
-
-static void benchmark_join(unsigned long step)
-{
-	int i, j, idx;
-	long long nsec = 0;
-
-	for (idx = 0; idx < 1 << 10; idx += step) {
-		for (i = 1; i < 15; i++) {
-			for (j = 0; j < i; j++) {
-				nsec += __benchmark_join(idx, i, j);
-			}
-		}
-	}
-
-	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
-			1 << 10, step, nsec);
-}
-
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -242,16 +154,5 @@ void benchmark(void)
 
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s], 0);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_size(size[c], step[s] << 9, 9);
-
-	for (c = 0; size[c]; c++)
-		for (s = 0; step[s]; s++)
-			benchmark_split(size[c], step[s]);
-
-	for (s = 0; step[s]; s++)
-		benchmark_join(step[s]);
+			benchmark_size(size[c], step[s]);
 }
diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c
new file mode 100644
index 000000000000..66ec4a24a203
--- /dev/null
+++ b/tools/testing/radix-tree/bitmap.c
@@ -0,0 +1,23 @@
+/* lib/bitmap.c pulls in at least two other files. */
+
+#include <linux/bitmap.h>
+
+void bitmap_clear(unsigned long *map, unsigned int start, int len)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const unsigned int size = start + len;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (len - bits_to_clear >= 0) {
+		*p &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		*p &= ~mask_to_clear;
+	}
+}
diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h
index cf88dc5b8832..2218b3cc184e 100644
--- a/tools/testing/radix-tree/generated/autoconf.h
+++ b/tools/testing/radix-tree/generated/autoconf.h
@@ -1 +1 @@
-#define CONFIG_RADIX_TREE_MULTIORDER 1
+#define CONFIG_XARRAY_MULTI 1
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 321ba92c70d2..1b63bdb7688f 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -19,7 +19,7 @@
 
 #include "test.h"
 
-#define DUMMY_PTR	((void *)0x12)
+#define DUMMY_PTR	((void *)0x10)
 
 int item_idr_free(int id, void *p, void *data)
 {
@@ -227,6 +227,66 @@ void idr_u32_test(int base)
 	idr_u32_test1(&idr, 0xffffffff);
 }
 
+static void idr_align_test(struct idr *idr)
+{
+	char name[] = "Motorola 68000";
+	int i, id;
+	void *entry;
+
+	for (i = 0; i < 9; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 1; i < 10; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 1);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 2; i < 11; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 2);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 3; i < 12; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != i - 3);
+		idr_for_each_entry(idr, entry, id);
+	}
+	idr_destroy(idr);
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, &name[i + 1], 0, 0, GFP_KERNEL) != 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+		BUG_ON(!idr_is_empty(idr));
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i], 0);
+		idr_for_each_entry(idr, entry, id);
+		BUG_ON(idr_find(idr, 0) != &name[i]);
+		idr_remove(idr, 0);
+	}
+
+	for (i = 0; i < 8; i++) {
+		BUG_ON(idr_alloc(idr, &name[i], 0, 0, GFP_KERNEL) != 0);
+		BUG_ON(idr_alloc(idr, NULL, 0, 0, GFP_KERNEL) != 1);
+		idr_remove(idr, 1);
+		idr_for_each_entry(idr, entry, id);
+		idr_replace(idr, &name[i + 1], 0);
+		idr_for_each_entry(idr, entry, id);
+		idr_remove(idr, 0);
+	}
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -307,6 +367,7 @@ void idr_checks(void)
 	idr_u32_test(4);
 	idr_u32_test(1);
 	idr_u32_test(0);
+	idr_align_test(&idr);
 }
 
 #define module_init(x)
@@ -344,16 +405,16 @@ void ida_check_conv_user(void)
 	DEFINE_IDA(ida);
 	unsigned long i;
 
-	radix_tree_cpu_dead(1);
 	for (i = 0; i < 1000000; i++) {
 		int id = ida_alloc(&ida, GFP_NOWAIT);
 		if (id == -ENOMEM) {
-			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) !=
-					BITS_PER_LONG - 2);
+			IDA_BUG_ON(&ida, ((i % IDA_BITMAP_BITS) !=
+					  BITS_PER_XA_VALUE) &&
+					 ((i % IDA_BITMAP_BITS) != 0));
 			id = ida_alloc(&ida, GFP_KERNEL);
 		} else {
 			IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) ==
-					BITS_PER_LONG - 2);
+					BITS_PER_XA_VALUE);
 		}
 		IDA_BUG_ON(&ida, id != i);
 	}
diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c
index a92bab513701..238db187aa15 100644
--- a/tools/testing/radix-tree/iteration_check.c
+++ b/tools/testing/radix-tree/iteration_check.c
@@ -1,5 +1,5 @@
 /*
- * iteration_check.c: test races having to do with radix tree iteration
+ * iteration_check.c: test races having to do with xarray iteration
  * Copyright (c) 2016 Intel Corporation
  * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
  *
@@ -12,41 +12,54 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  */
-#include <linux/radix-tree.h>
 #include <pthread.h>
 #include "test.h"
 
 #define NUM_THREADS	5
 #define MAX_IDX		100
-#define TAG		0
-#define NEW_TAG		1
+#define TAG		XA_MARK_0
+#define NEW_TAG		XA_MARK_1
 
-static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER;
 static pthread_t threads[NUM_THREADS];
 static unsigned int seeds[3];
-static RADIX_TREE(tree, GFP_KERNEL);
+static DEFINE_XARRAY(array);
 static bool test_complete;
 static int max_order;
 
-/* relentlessly fill the tree with tagged entries */
+void my_item_insert(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	struct item *item = item_create(index, 0);
+	int order;
+
+retry:
+	xas_lock(&xas);
+	for (order = max_order; order >= 0; order--) {
+		xas_set_order(&xas, index, order);
+		item->order = order;
+		if (xas_find_conflict(&xas))
+			continue;
+		xas_store(&xas, item);
+		xas_set_mark(&xas, TAG);
+		break;
+	}
+	xas_unlock(&xas);
+	if (xas_nomem(&xas, GFP_KERNEL))
+		goto retry;
+	if (order < 0)
+		free(item);
+}
+
+/* relentlessly fill the array with tagged entries */
 static void *add_entries_fn(void *arg)
 {
 	rcu_register_thread();
 
 	while (!test_complete) {
 		unsigned long pgoff;
-		int order;
 
 		for (pgoff = 0; pgoff < MAX_IDX; pgoff++) {
-			pthread_mutex_lock(&tree_lock);
-			for (order = max_order; order >= 0; order--) {
-				if (item_insert_order(&tree, pgoff, order)
-						== 0) {
-					item_tag_set(&tree, pgoff, TAG);
-					break;
-				}
-			}
-			pthread_mutex_unlock(&tree_lock);
+			my_item_insert(&array, pgoff);
 		}
 	}
 
@@ -56,33 +69,25 @@ static void *add_entries_fn(void *arg)
 }
 
 /*
- * Iterate over the tagged entries, doing a radix_tree_iter_retry() as we find
- * things that have been removed and randomly resetting our iteration to the
- * next chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over tagged entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *tagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_tagged(slot, &tree, &iter, 0, TAG) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each_marked(&xas, entry, ULONG_MAX, TAG) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[0]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -97,33 +102,25 @@ static void *tagged_iteration_fn(void *arg)
 }
 
 /*
- * Iterate over the entries, doing a radix_tree_iter_retry() as we find things
- * that have been removed and randomly resetting our iteration to the next
- * chunk with radix_tree_iter_resume().  Both radix_tree_iter_retry() and
- * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a
- * NULL 'slot' variable.
+ * Iterate over the entries, retrying when we find ourselves in a deleted
+ * node and randomly pausing the iteration.
  */
 static void *untagged_iteration_fn(void *arg)
 {
-	struct radix_tree_iter iter;
-	void **slot;
+	XA_STATE(xas, &array, 0);
+	void *entry;
 
 	rcu_register_thread();
 
 	while (!test_complete) {
+		xas_set(&xas, 0);
 		rcu_read_lock();
-		radix_tree_for_each_slot(slot, &tree, &iter, 0) {
-			void *entry = radix_tree_deref_slot(slot);
-			if (unlikely(!entry))
+		xas_for_each(&xas, entry, ULONG_MAX) {
+			if (xas_retry(&xas, entry))
 				continue;
 
-			if (radix_tree_deref_retry(entry)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-
 			if (rand_r(&seeds[1]) % 50 == 0) {
-				slot = radix_tree_iter_resume(slot, &iter);
+				xas_pause(&xas);
 				rcu_read_unlock();
 				rcu_barrier();
 				rcu_read_lock();
@@ -138,7 +135,7 @@ static void *untagged_iteration_fn(void *arg)
 }
 
 /*
- * Randomly remove entries to help induce radix_tree_iter_retry() calls in the
+ * Randomly remove entries to help induce retries in the
  * two iteration functions.
  */
 static void *remove_entries_fn(void *arg)
@@ -147,12 +144,13 @@ static void *remove_entries_fn(void *arg)
 
 	while (!test_complete) {
 		int pgoff;
+		struct item *item;
 
 		pgoff = rand_r(&seeds[2]) % MAX_IDX;
 
-		pthread_mutex_lock(&tree_lock);
-		item_delete(&tree, pgoff);
-		pthread_mutex_unlock(&tree_lock);
+		item = xa_erase(&array, pgoff);
+		if (item)
+			item_free(item, pgoff);
 	}
 
 	rcu_unregister_thread();
@@ -165,8 +163,7 @@ static void *tag_entries_fn(void *arg)
 	rcu_register_thread();
 
 	while (!test_complete) {
-		tag_tagged_items(&tree, &tree_lock, 0, MAX_IDX, 10, TAG,
-					NEW_TAG);
+		tag_tagged_items(&array, 0, MAX_IDX, 10, TAG, NEW_TAG);
 	}
 	rcu_unregister_thread();
 	return NULL;
@@ -217,5 +214,5 @@ void iteration_test(unsigned order, unsigned test_duration)
 		}
 	}
 
-	item_kill_tree(&tree);
+	item_kill_tree(&array);
 }
diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h
index 23b8ed52f8c8..03dc8a57eb99 100644
--- a/