- In the series "treewide: Refactor heap related implementation",

Kuan-Wei Chiu has significantly reworked the min_heap library code and
   has taught bcachefs to use the new more generic implementation.
 
 - Yury Norov's series "Cleanup cpumask.h inclusion in core headers"
   reworks the cpumask and nodemask headers to make things generally more
   rational.
 
 - Kuan-Wei Chiu has sent along some maintenance work against our sorting
   library code in the series "lib/sort: Optimizations and cleanups".
 
 - More library maintainance work from Christophe Jaillet in the series
   "Remove usage of the deprecated ida_simple_xx() API".
 
 - Ryusuke Konishi continues with the nilfs2 fixes and clanups in the
   series "nilfs2: eliminate the call to inode_attach_wb()".
 
 - Kuan-Ying Lee has some fixes to the gdb scripts in the series "Fix GDB
   command error".
 
 - Plus the usual shower of singleton patches all over the place.  Please
   see the relevant changelogs for details.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZp2GvwAKCRDdBJ7gKXxA
 jlf/AP48xP5ilIHbtpAKm2z+MvGuTxJQ5VSC0UXFacuCbc93lAEA+Yo+vOVRmh6j
 fQF2nVKyKLYfSz7yqmCyAaHWohIYLgg=
 =Stxz
 -----END PGP SIGNATURE-----

Merge tag 'mm-nonmm-stable-2024-07-21-15-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - In the series "treewide: Refactor heap related implementation",
   Kuan-Wei Chiu has significantly reworked the min_heap library code
   and has taught bcachefs to use the new more generic implementation.

 - Yury Norov's series "Cleanup cpumask.h inclusion in core headers"
   reworks the cpumask and nodemask headers to make things generally
   more rational.

 - Kuan-Wei Chiu has sent along some maintenance work against our
   sorting library code in the series "lib/sort: Optimizations and
   cleanups".

 - More library maintainance work from Christophe Jaillet in the series
   "Remove usage of the deprecated ida_simple_xx() API".

 - Ryusuke Konishi continues with the nilfs2 fixes and clanups in the
   series "nilfs2: eliminate the call to inode_attach_wb()".

 - Kuan-Ying Lee has some fixes to the gdb scripts in the series "Fix
   GDB command error".

 - Plus the usual shower of singleton patches all over the place. Please
   see the relevant changelogs for details.

* tag 'mm-nonmm-stable-2024-07-21-15-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (98 commits)
  ia64: scrub ia64 from poison.h
  watchdog/perf: properly initialize the turbo mode timestamp and rearm counter
  tsacct: replace strncpy() with strscpy()
  lib/bch.c: use swap() to improve code
  test_bpf: convert comma to semicolon
  init/modpost: conditionally check section mismatch to __meminit*
  init: remove unused __MEMINIT* macros
  nilfs2: Constify struct kobj_type
  nilfs2: avoid undefined behavior in nilfs_cnt32_ge macro
  math: rational: add missing MODULE_DESCRIPTION() macro
  lib/zlib: add missing MODULE_DESCRIPTION() macro
  fs: ufs: add MODULE_DESCRIPTION()
  lib/rbtree.c: fix the example typo
  ocfs2: add bounds checking to ocfs2_check_dir_entry()
  fs: add kernel-doc comments to ocfs2_prepare_orphan_dir()
  coredump: simplify zap_process()
  selftests/fpu: add missing MODULE_DESCRIPTION() macro
  compiler.h: simplify data_race() macro
  build-id: require program headers to be right after ELF header
  resource: add missing MODULE_DESCRIPTION()
  ...

MAINTAINERS

@@ -3801,8 +3801,10 @@ F:	include/linux/bitmap-str.h
 F:	include/linux/bitmap.h
 F:	include/linux/bits.h
 F:	include/linux/cpumask.h
+F:	include/linux/cpumask_types.h
 F:	include/linux/find.h
 F:	include/linux/nodemask.h
+F:	include/linux/nodemask_types.h
 F:	include/vdso/bits.h
 F:	lib/bitmap-str.c
 F:	lib/bitmap.c

arch/powerpc/kernel/vmlinux.lds.S

@@ -123,8 +123,6 @@ SECTIONS
 		 */
 		*(.sfpr);
 		*(.text.asan.* .text.tsan.*)
-		MEM_KEEP(init.text)
-		MEM_KEEP(exit.text)
 	} :text
 
 	. = ALIGN(PAGE_SIZE);

drivers/fsi/fsi-occ.c

@@ -656,17 +656,16 @@ static int occ_probe(struct platform_device *pdev)
 		rc = of_property_read_u32(dev->of_node, "reg", &reg);
 		if (!rc) {
 			/* make sure we don't have a duplicate from dts */
-			occ->idx = ida_simple_get(&occ_ida, reg, reg + 1,
+			occ->idx = ida_alloc_range(&occ_ida, reg, reg,
-						  GFP_KERNEL);
+						   GFP_KERNEL);
 			if (occ->idx < 0)
-				occ->idx = ida_simple_get(&occ_ida, 1, INT_MAX,
+				occ->idx = ida_alloc_min(&occ_ida, 1,
-							  GFP_KERNEL);
+							 GFP_KERNEL);
 		} else {
-			occ->idx = ida_simple_get(&occ_ida, 1, INT_MAX,
+			occ->idx = ida_alloc_min(&occ_ida, 1, GFP_KERNEL);
-						  GFP_KERNEL);
 		}
 	} else {
-		occ->idx = ida_simple_get(&occ_ida, 1, INT_MAX, GFP_KERNEL);
+		occ->idx = ida_alloc_min(&occ_ida, 1, GFP_KERNEL);
 	}
 
 	platform_set_drvdata(pdev, occ);
@@ -680,7 +679,7 @@ static int occ_probe(struct platform_device *pdev)
 	rc = misc_register(&occ->mdev);
 	if (rc) {
 		dev_err(dev, "failed to register miscdevice: %d\n", rc);
-		ida_simple_remove(&occ_ida, occ->idx);
+		ida_free(&occ_ida, occ->idx);
 		kvfree(occ->buffer);
 		return rc;
 	}
@@ -719,7 +718,7 @@ static int occ_remove(struct platform_device *pdev)
 	else
 		device_for_each_child(&pdev->dev, NULL, occ_unregister_of_child);
 
-	ida_simple_remove(&occ_ida, occ->idx);
+	ida_free(&occ_ida, occ->idx);
 
 	return 0;
 }

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -340,7 +340,7 @@ static int eb_create(struct i915_execbuffer *eb)
 		 * Without a 1:1 association between relocation handles and
 		 * the execobject[] index, we instead create a hashtable.
 		 * We size it dynamically based on available memory, starting
-		 * first with 1:1 assocative hash and scaling back until
+		 * first with 1:1 associative hash and scaling back until
 		 * the allocation succeeds.
 		 *
 		 * Later on we use a positive lut_size to indicate we are

drivers/md/bcache/alloc.c

@@ -164,40 +164,68 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
  * prio is worth 1/8th of what INITIAL_PRIO is worth.
  */
 
-#define bucket_prio(b)							\
+static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b)
-({									\
+{
-	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;	\
+	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;
-									\
-	(b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);	\
-})
 
-#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
+	return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);
-#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))
+}
+
+static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args)
+{
+	struct bucket **lhs = (struct bucket **)l;
+	struct bucket **rhs = (struct bucket **)r;
+	struct cache *ca = args;
+
+	return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs);
+}
+
+static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
+{
+	struct bucket **lhs = (struct bucket **)l;
+	struct bucket **rhs = (struct bucket **)r;
+	struct cache *ca = args;
+
+	return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
+}
+
+static inline void new_bucket_swap(void *l, void *r, void __always_unused *args)
+{
+	struct bucket **lhs = l, **rhs = r;
+
+	swap(*lhs, *rhs);
+}
 
 static void invalidate_buckets_lru(struct cache *ca)
 {
 	struct bucket *b;
-	ssize_t i;
+	const struct min_heap_callbacks bucket_max_cmp_callback = {
+		.less = new_bucket_max_cmp,
+		.swp = new_bucket_swap,
+	};
+	const struct min_heap_callbacks bucket_min_cmp_callback = {
+		.less = new_bucket_min_cmp,
+		.swp = new_bucket_swap,
+	};
 
-	ca->heap.used = 0;
+	ca->heap.nr = 0;
 
 	for_each_bucket(b, ca) {
 		if (!bch_can_invalidate_bucket(ca, b))
 			continue;
 
-		if (!heap_full(&ca->heap))
+		if (!min_heap_full(&ca->heap))
-			heap_add(&ca->heap, b, bucket_max_cmp);
+			min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca);
-		else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
+		else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) {
 			ca->heap.data[0] = b;
-			heap_sift(&ca->heap, 0, bucket_max_cmp);
+			min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca);
 		}
 	}
 
-	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+	min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca);
-		heap_sift(&ca->heap, i, bucket_min_cmp);
 
 	while (!fifo_full(&ca->free_inc)) {
-		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
+		if (!ca->heap.nr) {
 			/*
 			 * We don't want to be calling invalidate_buckets()
 			 * multiple times when it can't do anything
@@ -206,6 +234,8 @@ static void invalidate_buckets_lru(struct cache *ca)
 			wake_up_gc(ca->set);
 			return;
 		}
+		b = min_heap_peek(&ca->heap)[0];
+		min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca);
 
 		bch_invalidate_one_bucket(ca, b);
 	}

drivers/md/bcache/bcache.h

@@ -458,7 +458,7 @@ struct cache {
 	/* Allocation stuff: */
 	struct bucket		*buckets;
 
-	DECLARE_HEAP(struct bucket *, heap);
+	DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap;
 
 	/*
 	 * If nonzero, we know we aren't going to find any buckets to invalidate

drivers/md/bcache/bset.c

@@ -54,9 +54,11 @@ void bch_dump_bucket(struct btree_keys *b)
 int __bch_count_data(struct btree_keys *b)
 {
 	unsigned int ret = 0;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct bkey *k;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	if (b->ops->is_extents)
 		for_each_key(b, k, &iter)
 			ret += KEY_SIZE(k);
@@ -67,9 +69,11 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
 {
 	va_list args;
 	struct bkey *k, *p = NULL;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	const char *err;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	for_each_key(b, k, &iter) {
 		if (b->ops->is_extents) {
 			err = "Keys out of order";
@@ -110,9 +114,9 @@ bug:
 
 static void bch_btree_iter_next_check(struct btree_iter *iter)
 {
-	struct bkey *k = iter->data->k, *next = bkey_next(k);
+	struct bkey *k = iter->heap.data->k, *next = bkey_next(k);
 
-	if (next < iter->data->end &&
+	if (next < iter->heap.data->end &&
 	    bkey_cmp(k, iter->b->ops->is_extents ?
 		     &START_KEY(next) : next) > 0) {
 		bch_dump_bucket(iter->b);
@@ -879,12 +883,14 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
 	struct bset *i = bset_tree_last(b)->data;
 	struct bkey *m, *prev = NULL;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct bkey preceding_key_on_stack = ZERO_KEY;
 	struct bkey *preceding_key_p = &preceding_key_on_stack;
 
 	BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	/*
 	 * If k has preceding key, preceding_key_p will be set to address
 	 *  of k's preceding key; otherwise preceding_key_p will be set
@@ -895,9 +901,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	else
 		preceding_key(k, &preceding_key_p);
 
-	m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
+	m = bch_btree_iter_init(b, &iter, preceding_key_p);
 
-	if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
+	if (b->ops->insert_fixup(b, k, &iter, replace_key))
 		return status;
 
 	status = BTREE_INSERT_STATUS_INSERT;
@@ -1077,79 +1083,102 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 /* Btree iterator */
 
-typedef bool (btree_iter_cmp_fn)(struct btree_iter_set,
+typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *);
-				 struct btree_iter_set);
 
-static inline bool btree_iter_cmp(struct btree_iter_set l,
+static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args)
-				  struct btree_iter_set r)
 {
-	return bkey_cmp(l.k, r.k) > 0;
+	const struct btree_iter_set *_l = l;
+	const struct btree_iter_set *_r = r;
+
+	return bkey_cmp(_l->k, _r->k) <= 0;
+}
+
+static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+{
+	struct btree_iter_set *_iter1 = iter1;
+	struct btree_iter_set *_iter2 = iter2;
+
+	swap(*_iter1, *_iter2);
 }
 
 static inline bool btree_iter_end(struct btree_iter *iter)
 {
-	return !iter->used;
+	return !iter->heap.nr;
 }
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end)
 {
+	const struct min_heap_callbacks callbacks = {
+		.less = new_btree_iter_cmp,
+		.swp = new_btree_iter_swap,
+	};
+
 	if (k != end)
-		BUG_ON(!heap_add(iter,
+		BUG_ON(!min_heap_push(&iter->heap,
-				 ((struct btree_iter_set) { k, end }),
+				 &((struct btree_iter_set) { k, end }),
-				 btree_iter_cmp));
+				 &callbacks,
+				 NULL));
 }
 
-static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
+static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
-						struct btree_iter_stack *iter,
+					  struct btree_iter *iter,
-						struct bkey *search,
+					  struct bkey *search,
-						struct bset_tree *start)
+					  struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 
-	iter->iter.size = ARRAY_SIZE(iter->stack_data);
+	iter->heap.size = ARRAY_SIZE(iter->heap.preallocated);
-	iter->iter.used = 0;
+	iter->heap.nr = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->iter.b = b;
+	iter->b = b;
 #endif
 
 	for (; start <= bset_tree_last(b); start++) {
 		ret = bch_bset_search(b, start, search);
-		bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
+		bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
 	}
 
 	return ret;
 }
 
-struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter_stack *iter,
+				 struct btree_iter *iter,
 				 struct bkey *search)
 {
-	return __bch_btree_iter_stack_init(b, iter, search, b->set);
+	return __bch_btree_iter_init(b, iter, search, b->set);
 }
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
-						 btree_iter_cmp_fn *cmp)
+						 new_btree_iter_cmp_fn *cmp)
 {
 	struct btree_iter_set b __maybe_unused;
 	struct bkey *ret = NULL;
+	const struct min_heap_callbacks callbacks = {
+		.less = cmp,
+		.swp = new_btree_iter_swap,
+	};
 
 	if (!btree_iter_end(iter)) {
 		bch_btree_iter_next_check(iter);
 
-		ret = iter->data->k;
+		ret = iter->heap.data->k;
-		iter->data->k = bkey_next(iter->data->k);
+		iter->heap.data->k = bkey_next(iter->heap.data->k);
 
-		if (iter->data->k > iter->data->end) {
+		if (iter->heap.data->k > iter->heap.data->end) {
 			WARN_ONCE(1, "bset was corrupt!\n");
-			iter->data->k = iter->data->end;
+			iter->heap.data->k = iter->heap.data->end;
 		}
 
-		if (iter->data->k == iter->data->end)
+		if (iter->heap.data->k == iter->heap.data->end) {
-			heap_pop(iter, b, cmp);
+			if (iter->heap.nr) {
+				b = min_heap_peek(&iter->heap)[0];
+				min_heap_pop(&iter->heap, &callbacks, NULL);
+			}
+		}
 		else
-			heap_sift(iter, 0, cmp);
+			min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
 	}
 
 	return ret;
@@ -1157,7 +1186,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 
 struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 {
-	return __bch_btree_iter_next(iter, btree_iter_cmp);
+	return __bch_btree_iter_next(iter, new_btree_iter_cmp);
 
 }
 
@@ -1195,16 +1224,18 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
 			    bool fixup, bool remove_stale)
 {
-	int i;
 	struct bkey *k, *last = NULL;
 	BKEY_PADDED(k) tmp;
 	bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale
 		? bch_ptr_bad
 		: bch_ptr_invalid;
+	const struct min_heap_callbacks callbacks = {
+		.less = b->ops->sort_cmp,
+		.swp = new_btree_iter_swap,
+	};
 
 	/* Heapify the iterator, using our comparison function */
-	for (i = iter->used / 2 - 1; i >= 0; --i)
+	min_heapify_all(&iter->heap, &callbacks, NULL);
-		heap_sift(iter, i, b->ops->sort_cmp);
 
 	while (!btree_iter_end(iter)) {
 		if (b->ops->sort_fixup && fixup)
@@ -1293,10 +1324,11 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 			    struct bset_sort_state *state)
 {
 	size_t order = b->page_order, keys = 0;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	int oldsize = bch_count_data(b);
 
-	__bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
 
 	if (start) {
 		unsigned int i;
@@ -1307,7 +1339,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 		order = get_order(__set_bytes(b->set->data, keys));
 	}
 
-	__btree_sort(b, &iter.iter, start, order, false, state);
+	__btree_sort(b, &iter, start, order, false, state);
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
@@ -1323,11 +1355,13 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
 			 struct bset_sort_state *state)
 {
 	uint64_t start_time = local_clock();
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 
-	bch_btree_iter_stack_init(b, &iter, NULL);
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
 
-	btree_mergesort(b, new->set->data, &iter.iter, false, true);
+	bch_btree_iter_init(b, &iter, NULL);
+
+	btree_mergesort(b, new->set->data, &iter, false, true);
 
 	bch_time_stats_update(&state->time, start_time);
 

drivers/md/bcache/bset.h

@@ -187,8 +187,9 @@ struct bset_tree {
 };
 
 struct btree_keys_ops {
-	bool		(*sort_cmp)(struct btree_iter_set l,
+	bool		(*sort_cmp)(const void *l,
-				    struct btree_iter_set r);
+				    const void *r,
+					void *args);
 	struct bkey	*(*sort_fixup)(struct btree_iter *iter,
 				       struct bkey *tmp);
 	bool		(*insert_fixup)(struct btree_keys *b,
@@ -312,23 +313,17 @@ enum {
 	BTREE_INSERT_STATUS_FRONT_MERGE,
 };
 
+struct btree_iter_set {
+	struct bkey *k, *end;
+};
+
 /* Btree key iteration */
 
 struct btree_iter {
-	size_t size, used;
 #ifdef CONFIG_BCACHE_DEBUG
 	struct btree_keys *b;
 #endif
-	struct btree_iter_set {
+	MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap;
-		struct bkey *k, *end;
-	} data[];
-};
-
-/* Fixed-size btree_iter that can be allocated on the stack */
-
-struct btree_iter_stack {
-	struct btree_iter iter;
-	struct btree_iter_set stack_data[MAX_BSETS];
 };
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -340,9 +335,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end);
-struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				       struct btree_iter_stack *iter,
+				 struct btree_iter *iter,
-				       struct bkey *search);
+				 struct bkey *search);
 
 struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 			       const struct bkey *search);
@@ -357,14 +352,13 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
-#define for_each_key_filter(b, k, stack_iter, filter)                      \
+#define for_each_key_filter(b, k, iter, filter)				\
-	for (bch_btree_iter_stack_init((b), (stack_iter), NULL);           \
+	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
-					       filter));)
 
-#define for_each_key(b, k, stack_iter)                           \
+#define for_each_key(b, k, iter)					\
-	for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
+	     ((k) = bch_btree_iter_next(iter));)
 
 /* Sorting */
 

drivers/md/bcache/btree.c

@@ -149,19 +149,19 @@ void bch_btree_node_read_done(struct btree *b)
 {
 	const char *err = "bad btree header";
 	struct bset *i = btree_bset_first(b);
-	struct btree_iter *iter;
+	struct btree_iter iter;
 
 	/*
 	 * c->fill_iter can allocate an iterator with more memory space
 	 * than static MAX_BSETS.
 	 * See the comment arount cache_set->fill_iter.
 	 */
-	iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
+	iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
-	iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
+	iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
-	iter->used = 0;
+	iter.heap.nr = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->b = &b->keys;
+	iter.b = &b->keys;
 #endif
 
 	if (!i->seq)
@@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i != b->keys.set[0].data && !i->keys)
 			goto err;
 
-		bch_btree_iter_push(iter, i->start, bset_bkey_last(i));
+		bch_btree_iter_push(&iter, i->start, bset_bkey_last(i));
 
 		b->written += set_blocks(i, block_bytes(b->c->cache));
 	}
@@ -211,7 +211,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i->seq == b->keys.set[0].data->seq)
 			goto err;
 
-	bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort);
+	bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort);
 
 	i = b->keys.set[0].data;
 	err = "short btree key";
@@ -223,7 +223,7 @@ void bch_btree_node_read_done(struct btree *b)
 		bch_bset_init_next(&b->keys, write_block(b),
 				   bset_magic(&b->c->cache->sb));
 out:
-	mempool_free(iter, &b->c->fill_iter);
+	mempool_free(iter.heap.data, &b->c->fill_iter);
 	return;
 err:
 	set_btree_node_io_error(b);
@@ -1309,9 +1309,11 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct bset_tree *t;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	gc->nodes++;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) {
@@ -1570,9 +1572,11 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	unsigned int ret = 0;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
 		ret += bkey_u64s(k);
 
@@ -1611,18 +1615,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
-					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1917,7 +1921,9 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
+
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1925,10 +1931,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
+		bch_btree_iter_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1956,7 +1962,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1964,9 +1970,11 @@ static int bch_btree_check_thread(void *arg)
 	cur_idx = prev_idx = 0;
 	ret = 0;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	/* root node keys are checked before thread created */
-	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
+	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1984,7 +1992,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter.iter,
+			k = bch_btree_iter_next_filter(&iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2057,9 +2065,11 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct btree_check_state check_state;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 	/* check and mark root node keys */
 	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(c, c->root->level, k);
@@ -2553,11 +2563,12 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter_stack iter;
+		struct btree_iter iter;
 
-		bch_btree_iter_stack_init(&b->keys, &iter, from);
+		min_heap_init(&iter.heap, NULL, MAX_BSETS);
+		bch_btree_iter_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2586,12 +2597,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 
-	bch_btree_iter_stack_init(&b->keys, &iter, from);
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	bch_btree_iter_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
-					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,

drivers/md/bcache/extents.c

@@ -33,15 +33,16 @@ static void sort_key_next(struct btree_iter *iter,
 	i->k = bkey_next(i->k);
 
 	if (i->k == i->end)
-		*i = iter->data[--iter->used];
+		*i = iter->heap.data[--iter->heap.nr];
 }
 
-static bool bch_key_sort_cmp(struct btree_iter_set l,
+static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args)
-			     struct btree_iter_set r)
 {
-	int64_t c = bkey_cmp(l.k, r.k);
+	struct btree_iter_set *_l = (struct btree_iter_set *)l;
+	struct btree_iter_set *_r = (struct btree_iter_set *)r;
+	int64_t c = bkey_cmp(_l->k, _r->k);
 
-	return c ? c > 0 : l.k < r.k;
+	return !(c ? c > 0 : _l->k < _r->k);
 }
 
 static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
@@ -238,7 +239,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_btree_keys_ops = {
-	.sort_cmp	= bch_key_sort_cmp,
+	.sort_cmp	= new_bch_key_sort_cmp,
 	.insert_fixup	= bch_btree_ptr_insert_fixup,
 	.key_invalid	= bch_btree_ptr_invalid,
 	.key_bad	= bch_btree_ptr_bad,
@@ -255,22 +256,36 @@ const struct btree_keys_ops bch_btree_keys_ops = {
  * Necessary for btree_sort_fixup() - if there are multiple keys that compare
  * equal in different sets, we have to process them newest to oldest.
  */
-static bool bch_extent_sort_cmp(struct btree_iter_set l,
-				struct btree_iter_set r)
-{
-	int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k));
 
-	return c ? c > 0 : l.k < r.k;
+static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args)
+{
+	struct btree_iter_set *_l = (struct btree_iter_set *)l;
+	struct btree_iter_set *_r = (struct btree_iter_set *)r;
+	int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k));
+
+	return !(c ? c > 0 : _l->k < _r->k);
+}
+
+static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+{
+	struct btree_iter_set *_iter1 = iter1;
+	struct btree_iter_set *_iter2 = iter2;
+
+	swap(*_iter1, *_iter2);
 }
 
 static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 					  struct bkey *tmp)
 {
-	while (iter->used > 1) {
+	const struct min_heap_callbacks callbacks = {
-		struct btree_iter_set *top = iter->data, *i = top + 1;
+		.less = new_bch_extent_sort_cmp,
+		.swp = new_btree_iter_swap,
+	};
+	while (iter->heap.nr > 1) {
+		struct btree_iter_set *top = iter->heap.data, *i = top + 1;
 
-		if (iter->used > 2 &&
+		if (iter->heap.nr > 2 &&
-		    bch_extent_sort_cmp(i[0], i[1]))
+		    !new_bch_extent_sort_cmp(&i[0], &i[1], NULL))
 			i++;
 
 		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
@@ -278,7 +293,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 		if (!KEY_SIZE(i->k)) {
 			sort_key_next(iter, i);
-			heap_sift(iter, i - top, bch_extent_sort_cmp);
+			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
 			continue;
 		}
 
@@ -288,7 +303,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 			else
 				bch_cut_front(top->k, i->k);
 
-			heap_sift(iter, i - top, bch_extent_sort_cmp);
+			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
 		} else {
 			/* can't happen because of comparison func */
 			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
@@ -298,7 +313,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 				bch_cut_back(&START_KEY(i->k), tmp);
 				bch_cut_front(i->k, top->k);
-				heap_sift(iter, 0, bch_extent_sort_cmp);
+				min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
 
 				return tmp;
 			} else {
@@ -618,7 +633,7 @@ static bool bch_extent_merge(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_extent_keys_ops = {
-	.sort_cmp	= bch_extent_sort_cmp,
+	.sort_cmp	= new_bch_extent_sort_cmp,
 	.sort_fixup	= bch_extent_sort_fixup,
 	.insert_fixup	= bch_extent_insert_fixup,
 	.key_invalid	= bch_extent_invalid,

drivers/md/bcache/movinggc.c

@@ -182,16 +182,27 @@ err:		if (!IS_ERR_OR_NULL(w->private))
 	closure_sync(&cl);
 }
 
-static bool bucket_cmp(struct bucket *l, struct bucket *r)
+static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args)
 {
-	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
+	struct bucket **_l = (struct bucket **)l;
+	struct bucket **_r = (struct bucket **)r;
+
+	return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
+}
+
+static void new_bucket_swap(void *l, void *r, void __always_unused *args)
+{
+	struct bucket **_l = l;
+	struct bucket **_r = r;
+
+	swap(*_l, *_r);
 }
 
 static unsigned int bucket_heap_top(struct cache *ca)
 {
 	struct bucket *b;
 
-	return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
+	return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0;
 }
 
 void bch_moving_gc(struct cache_set *c)
@@ -199,6 +210,10 @@ void bch_moving_gc(struct cache_set *c)
 	struct cache *ca = c->cache;
 	struct bucket *b;
 	unsigned long sectors_to_move, reserve_sectors;
+	const struct min_heap_callbacks callbacks = {
+		.less = new_bucket_cmp,
+		.swp = new_bucket_swap,
+	};
 
 	if (!c->copy_gc_enabled)
 		return;
@@ -209,7 +224,7 @@ void bch_moving_gc(struct cache_set *c)
 	reserve_sectors = ca->sb.bucket_size *
 			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
-	ca->heap.used = 0;
+	ca->heap.nr = 0;
 
 	for_each_bucket(b, ca) {
 		if (GC_MARK(b) == GC_MARK_METADATA ||
@@ -218,25 +233,31 @@ void bch_moving_gc(struct cache_set *c)
 		    atomic_read(&b->pin))
 			continue;
 
-		if (!heap_full(&ca->heap)) {
+		if (!min_heap_full(&ca->heap)) {
 			sectors_to_move += GC_SECTORS_USED(b);
-			heap_add(&ca->heap, b, bucket_cmp);
+			min_heap_push(&ca->heap, &b, &callbacks, NULL);
-		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
+		} else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) {
 			sectors_to_move -= bucket_heap_top(ca);
 			sectors_to_move += GC_SECTORS_USED(b);
 
 			ca->heap.data[0] = b;
-			heap_sift(&ca->heap, 0, bucket_cmp);
+			min_heap_sift_down(&ca->heap, 0, &callbacks, NULL);
 		}
 	}
 
 	while (sectors_to_move > reserve_sectors) {
-		heap_pop(&ca->heap, b, bucket_cmp);
+		if (ca->heap.nr) {
+			b = min_heap_peek(&ca->heap)[0];
+			min_heap_pop(&ca->heap, &callbacks, NULL);
+		}
 		sectors_to_move -= GC_SECTORS_USED(b);
 	}
 
-	while (heap_pop(&ca->heap, b, bucket_cmp))
+	while (ca->heap.nr) {
+		b = min_heap_peek(&ca->heap)[0];
+		min_heap_pop(&ca->heap, &callbacks, NULL);
 		SET_GC_MOVE(b, 1);
+	}
 
 	mutex_unlock(&c->bucket_lock);
 

drivers/md/bcache/super.c

@@ -1907,8 +1907,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = sizeof(struct btree_iter) +
+	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
-		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
 			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);

drivers/md/bcache/sysfs.c

@@ -660,7 +660,9 @@ static unsigned int bch_root_usage(struct cache_set *c)
 	unsigned int bytes = 0;
 	struct bkey *k;
 	struct btree *b;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
+
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
 
 	goto lock_root;
 

drivers/md/bcache/util.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * random utiility code, for bcache but in theory not specific to bcache
+ * random utility code, for bcache but in theory not specific to bcache
  *
  * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
  * Copyright 2012 Google, Inc.

drivers/md/bcache/util.h

@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
+#include <linux/min_heap.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
@@ -30,16 +31,10 @@ struct closure;
 
 #endif
 
-#define DECLARE_HEAP(type, name)					\
-	struct {							\
-		size_t size, used;					\
-		type *data;						\
-	} name
-
 #define init_heap(heap, _size, gfp)					\
 ({									\
 	size_t _bytes;							\
-	(heap)->used = 0;						\
+	(heap)->nr = 0;						\
 	(heap)->size = (_size);						\
 	_bytes = (heap)->size * sizeof(*(heap)->data);			\
 	(heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL);		\
@@ -52,64 +47,6 @@ do {									\
 	(heap)->data = NULL;						\
 } while (0)
 
-#define heap_swap(h, i, j)	swap((h)->data[i], (h)->data[j])
-
-#define heap_sift(h, i, cmp)						\
-do {									\
-	size_t _r, _j = i;						\
-									\
-	for (; _j * 2 + 1 < (h)->used; _j = _r) {			\
-		_r = _j * 2 + 1;					\
-		if (_r + 1 < (h)->used &&				\
-		    cmp((h)->data[_r], (h)->data[_r + 1]))		\
-			_r++;						\
-									\
-		if (cmp((h)->data[_r], (h)->data[_j]))			\
-			break;						\
-		heap_swap(h, _r, _j);					\
-	}								\
-} while (0)
-
-#define heap_sift_down(h, i, cmp)					\
-do {									\
-	while (i) {							\
-		size_t p = (i - 1) / 2;					\
-		if (cmp((h)->data[i], (h)->data[p]))			\
-			break;						\
-		heap_swap(h, i, p);					\
-		i = p;							\
-	}								\
-} while (0)
-
-#define heap_add(h, d, cmp)						\
-({									\
-	bool _r = !heap_full(h);					\
-	if (_r) {							\
-		size_t _i = (h)->used++;				\
-		(h)->data[_i] = d;					\
-									\
-		heap_sift_down(h, _i, cmp);				\
-		heap_sift(h, _i, cmp);					\
-	}								\
-	_r;								\
-})
-
-#define heap_pop(h, d, cmp)						\
-({									\
-	bool _r = (h)->used;						\
-	if (_r) {							\
-		(d) = (h)->data[0];					\
-		(h)->used--;						\
-		heap_swap(h, 0, (h)->used);				\
-		heap_sift(h, 0, cmp);					\
-	}								\
-	_r;								\
-})
-
-#define heap_peek(h)	((h)->used ? (h)->data[0] : NULL)
-
-#define heap_full(h)	((h)->used == (h)->size)
-
 #define DECLARE_FIFO(type, name)					\
 	struct {							\
 		size_t front, back, size, mask;				\

drivers/md/bcache/writeback.c

@@ -908,15 +908,16 @@ static int bch_dirty_init_thread(void *arg)
 	struct dirty_init_thrd_info *info = arg;
 	struct bch_dirty_init_state *state = info->state;
 	struct cache_set *c = state->c;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
 	prev_idx = 0;
 
-	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -930,7 +931,7 @@ static int bch_dirty_init_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter.iter,
+			k = bch_btree_iter_next_filter(&iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -979,11 +980,13 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	int i;
 	struct btree *b = NULL;
 	struct bkey *k = NULL;
-	struct btree_iter_stack iter;
+	struct btree_iter iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
 
+	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+
 retry_lock:
 	b = c->root;
 	rw_lock(0, b, b->level);

drivers/md/dm-vdo/repair.c

@@ -51,6 +51,8 @@ struct recovery_point {
 	bool increment_applied;
 };
 
+DEFINE_MIN_HEAP(struct numbered_block_mapping, replay_heap);
+
 struct repair_completion {
 	/* The completion header */
 	struct vdo_completion completion;
@@ -97,7 +99,7 @@ struct repair_completion {
 	 * order, then original journal order. This permits efficient iteration over the journal
 	 * entries in order.
 	 */
-	struct min_heap replay_heap;
+	struct replay_heap replay_heap;
 	/* Fields tracking progress through the journal entries. */
 	struct numbered_block_mapping *current_entry;
 	struct numbered_block_mapping *current_unfetched_entry;
@@ -135,7 +137,7 @@ struct repair_completion {
  * to sort by slot while still ensuring we replay all entries with the same slot in the exact order
  * as they appeared in the journal.
  */
-static bool mapping_is_less_than(const void *item1, const void *item2)
+static bool mapping_is_less_than(const void *item1, const void *item2, void __always_unused *args)
 {
 	const struct numbered_block_mapping *mapping1 =
 		(const struct numbered_block_mapping *) item1;
@@ -154,7 +156,7 @@ static bool mapping_is_less_than(const void *item1, const void *item2)
 	return 0;
 }
 
-static void swap_mappings(void *item1, void *item2)
+static void swap_mappings(void *item1, void *item2, void __always_unused *args)
 {
 	struct numbered_block_mapping *mapping1 = item1;
 	struct numbered_block_mapping *mapping2 = item2;
@@ -163,14 +165,13 @@ static void swap_mappings(void *item1, void *item2)
 }
 
 static const struct min_heap_callbacks repair_min_heap = {
-	.elem_size = sizeof(struct numbered_block_mapping),
 	.less = mapping_is_less_than,
 	.swp = swap_mappings,
 };
 
 static struct numbered_block_mapping *sort_next_heap_element(struct repair_completion *repair)
 {
-	struct min_heap *heap = &repair->replay_heap;
+	struct replay_heap *heap = &repair->replay_heap;
 	struct numbered_block_mapping *last;
 
 	if (heap->nr == 0)
@@ -181,8 +182,8 @@ static struct numbered_block_mapping *sort_next_heap_element(struct repair_compl
 	 * restore the heap invariant, and return a pointer to the popped element.
 	 */
 	last = &repair->entries[--heap->nr];
-	swap_mappings(heap->data, last);
+	swap_mappings(heap->data, last, NULL);
-	min_heapify(heap, 0, &repair_min_heap);
+	min_heap_sift_down(heap, 0, &repair_min_heap, NULL);
 	return last;
 }
 
@@ -1116,12 +1117,12 @@ static void recover_block_map(struct vdo_completion *completion)
 	 * Organize the journal entries into a binary heap so we can iterate over them in sorted
 	 * order incrementally, avoiding an expensive sort call.
 	 */
-	repair->replay_heap = (struct min_heap) {
+	repair->replay_heap = (struct replay_heap) {
 		.data = repair->entries,
 		.nr = repair->block_map_entry_count,
 		.size = repair->block_map_entry_count,
 	};
-	min_heapify_all(&repair->replay_heap, &repair_min_heap);
+	min_heapify_all(&repair->replay_heap, &repair_min_heap, NULL);
 
 	vdo_log_info("Replaying %zu recovery entries into block map",
 		     repair->block_map_entry_count);

drivers/md/dm-vdo/slab-depot.c

@@ -3288,7 +3288,8 @@ int vdo_release_block_reference(struct block_allocator *allocator,
  * Thus, the ordering is reversed from the usual sense since min_heap returns smaller elements
  * before larger ones.
  */
-static bool slab_status_is_less_than(const void *item1, const void *item2)
+static bool slab_status_is_less_than(const void *item1, const void *item2,
+					void __always_unused *args)
 {
 	const struct slab_status *info1 = item1;
 	const struct slab_status *info2 = item2;
@@ -3300,7 +3301,7 @@ static bool slab_status_is_less_than(const void *item1, const void *item2)
 	return info1->slab_number < info2->slab_number;
 }
 
-static void swap_slab_statuses(void *item1, void *item2)
+static void swap_slab_statuses(void *item1, void *item2, void __always_unused *args)
 {
 	struct slab_status *info1 = item1;
 	struct slab_status *info2 = item2;
@@ -3309,7 +3310,6 @@ static void swap_slab_statuses(void *item1, void *item2)
 }
 
 static const struct min_heap_callbacks slab_status_min_heap = {
-	.elem_size = sizeof(struct slab_status),
 	.less = slab_status_is_less_than,
 	.swp = swap_slab_statuses,
 };
@@ -3509,7 +3509,7 @@ static int get_slab_statuses(struct block_allocator *allocator,
 static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator *allocator)
 {
 	struct slab_status current_slab_status;
-	struct min_heap heap;
+	DEFINE_MIN_HEAP(struct slab_status, heap) heap;
 	int result;
 	struct slab_status *slab_statuses;
 	struct slab_depot *depot = allocator->depot;
@@ -3521,12 +3521,12 @@ static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator
 		return result;
 
 	/* Sort the slabs by cleanliness, then by emptiness hint. */
-	heap = (struct min_heap) {
+	heap = (struct heap) {
 		.data = slab_statuses,
 		.nr = allocator->slab_count,
 		.size = allocator->slab_count,
 	};
-	min_heapify_all(&heap, &slab_status_min_heap);
+	min_heapify_all(&heap, &slab_status_min_heap, NULL);
 
 	while (heap.nr > 0) {
 		bool high_priority;
@@ -3534,7 +3534,7 @@ static int __must_check vdo_prepare_slabs_for_allocation(struct block_allocator
 		struct slab_journal *journal;
 
 		current_slab_status = slab_statuses[0];
-		min_heap_pop(&heap, &slab_status_min_heap);
+		min_heap_pop(&heap, &slab_status_min_heap, NULL);
 		slab = depot->slabs[current_slab_status.slab_number];
 
 		if ((depot->load_type == VDO_SLAB_DEPOT_REBUILD_LOAD) ||

drivers/most/core.c

@@ -1286,7 +1286,7 @@ int most_register_interface(struct most_interface *iface)
 	    !iface->poison_channel || (iface->num_channels > MAX_CHANNELS))
 		return -EINVAL;
 
-	id = ida_simple_get(&mdev_id, 0, 0, GFP_KERNEL);
+	id = ida_alloc(&mdev_id, GFP_KERNEL);
 	if (id < 0) {
 		dev_err(iface->dev, "Failed to allocate device ID\n");
 		return id;
@@ -1294,7 +1294,7 @@ int most_register_interface(struct most_interface *iface)
 
 	iface->p = kzalloc(sizeof(*iface->p), GFP_KERNEL);
 	if (!iface->p) {
-		ida_simple_remove(&mdev_id, id);
+		ida_free(&mdev_id, id);
 		return -ENOMEM;
 	}
 
@@ -1308,7 +1308,7 @@ int most_register_interface(struct most_interface *iface)
 		dev_err(iface->dev, "Failed to register interface device\n");
 		kfree(iface->p);
 		put_device(iface->dev);
-		ida_simple_remove(&mdev_id, id);
+		ida_free(&mdev_id, id);
 		return -ENOMEM;
 	}
 
@@ -1366,7 +1366,7 @@ err_free_resources:
 	}
 	kfree(iface->p);
 	device_unregister(iface->dev);
-	ida_simple_remove(&mdev_id, id);
+	ida_free(&mdev_id, id);
 	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(most_register_interface);
@@ -1397,7 +1397,7 @@ void most_deregister_interface(struct most_interface *iface)
 		device_unregister(&c->dev);
 	}
 
-	ida_simple_remove(&mdev_id, iface->p->dev_id);
+	ida_free(&mdev_id, iface->p->dev_id);
 	kfree(iface->p);
 	device_unregister(iface->dev);
 }

drivers/most/most_cdev.c

@@ -100,7 +100,7 @@ static void destroy_cdev(struct comp_channel *c)
 
 static void destroy_channel(struct comp_channel *c)
 {
-	ida_simple_remove(&comp.minor_id, MINOR(c->devno));
+	ida_free(&comp.minor_id, MINOR(c->devno));
 	kfifo_free(&c->fifo);
 	kfree(c);
 }
@@ -425,7 +425,7 @@ static int comp_probe(struct most_interface *iface, int channel_id,
 	if (c)
 		return -EEXIST;
 
-	current_minor = ida_simple_get(&comp.minor_id, 0, 0, GFP_KERNEL);
+	current_minor = ida_alloc(&comp.minor_id, GFP_KERNEL);
 	if (current_minor < 0)
 		return current_minor;
 
@@ -472,7 +472,7 @@ err_del_cdev_and_free_channel:
 err_free_c:
 	kfree(c);
 err_remove_ida:
-	ida_simple_remove(&comp.minor_id, current_minor);
+	ida_free(&comp.minor_id, current_minor);
 	return retval;
 }
 

drivers/net/wireless/ti/wl1251/acx.h

@@ -229,7 +229,7 @@ struct acx_rx_msdu_lifetime {
  * ===		==========
  * 31:12		Reserved - Always equal to 0.
  * 11		Association - When set, the WiLink receives all association
- * 	 	related frames (association request/response, reassocation
+ *		related frames (association request/response, reassociation
  *		request/response, and disassociation). When clear, these frames
  *		are discarded.
  * 10		Auth/De auth - When set, the WiLink receives all authentication

drivers/scsi/qedf/qedf_main.c

@@ -2286,7 +2286,7 @@ static bool qedf_process_completions(struct qedf_fastpath *fp)
 		 * on.
 		 */
 		if (!io_req)
-			/* If there is not io_req assocated with this CQE
+			/* If there is not io_req associated with this CQE
 			 * just queue it on CPU 0
 			 */
 			cpu = 0;

drivers/staging/rtl8723bs/core/rtw_mlme_ext.c

@@ -979,7 +979,7 @@ unsigned int OnAssocReq(struct adapter *padapter, union recv_frame *precv_frame)
 	left = pkt_len - (sizeof(struct ieee80211_hdr_3addr) + ie_offset);
 	pos = pframe + (sizeof(struct ieee80211_hdr_3addr) + ie_offset);
 
-	/*  check if this stat has been successfully authenticated/assocated */
+	/*  check if this stat has been successfully authenticated/associated */
 	if (!((pstat->state) & WIFI_FW_AUTH_SUCCESS)) {
 		if (!((pstat->state) & WIFI_FW_ASSOC_SUCCESS)) {
 			status = WLAN_REASON_CLASS2_FRAME_FROM_NONAUTH_STA;

drivers/staging/rtl8723bs/core/rtw_pwrctrl.c

@@ -452,7 +452,7 @@ void LPS_Enter(struct adapter *padapter, const char *msg)
 	if (hal_btcoex_IsBtControlLps(padapter))
 		return;
 
-	/* Skip lps enter request if number of assocated adapters is not 1 */
+	/* Skip lps enter request if number of associated adapters is not 1 */
 	if (check_fwstate(&(dvobj->padapters->mlmepriv), WIFI_ASOC_STATE))
 		n_assoc_iface++;
 	if (n_assoc_iface != 1)

fs/bcachefs/clock.c

@@ -6,15 +6,29 @@
 #include <linux/kthread.h>
 #include <linux/preempt.h>
 
-static inline long io_timer_cmp(io_timer_heap *h,
+static inline bool io_timer_cmp(const void *l, const void *r, void __always_unused *args)
-				struct io_timer *l,
-				struct io_timer *r)
 {
-	return l->expire - r->expire;
+	struct io_timer **_l = (struct io_timer **)l;
+	struct io_timer **_r = (struct io_timer **)r;
+
+	return (*_l)->expire < (*_r)->expire;
+}
+
+static inline void io_timer_swp(void *l, void *r, void __always_unused *args)
+{
+	struct io_timer **_l = (struct io_timer **)l;
+	struct io_timer **_r = (struct io_timer **)r;
+
+	swap(*_l, *_r);
 }
 
 void bch2_io_timer_add(struct io_clock *clock, struct io_timer *timer)
 {
+	const struct min_heap_callbacks callbacks = {
+		.less = io_timer_cmp,
+		.swp = io_timer_swp,
+	};
+
 	spin_lock(&clock->timer_lock);
 
 	if (time_after_eq64((u64) atomic64_read(&clock->now), timer->expire)) {
@@ -23,22 +37,27 @@ void bch2_io_timer_add(struct io_clock *clock, struct io_timer *timer)
 		return;
 	}
 
-	for (size_t i = 0; i < clock->timers.used; i++)
+	for (size_t i = 0; i < clock->timers.nr; i++)
 		if (clock->timers.data[i] == timer)
 			goto out;
 
-	BUG_ON(!heap_add(&clock->timers, timer, io_timer_cmp, NULL));
+	BUG_ON(!min_heap_push(&clock->timers, &timer, &callbacks, NULL));
 out:
 	spin_unlock(&clock->timer_lock);
 }
 
 void bch2_io_timer_del(struct io_clock *clock, struct io_timer *timer)
 {
+	const struct min_heap_callbacks callbacks = {
+		.less = io_timer_cmp,
+		.swp = io_timer_swp,
+	};
+
 	spin_lock(&clock->timer_lock);
 
-	for (size_t i = 0; i < clock->timers.used; i++)
+	for (size_t i = 0; i < clock->timers.nr; i++)
 		if (clock->timers.data[i] == timer) {
-			heap_del(&clock->timers, i, io_timer_cmp, NULL);
+			min_heap_del(&clock->timers, i, &callbacks, NULL);
 			break;
 		}
 
@@ -123,10 +142,17 @@ void bch2_kthread_io_clock_wait(struct io_clock *clock,
 static struct io_timer *get_expired_timer(struct io_clock *clock, u64 now)
 {
 	struct io_timer *ret = NULL;
+	const struct min_heap_callbacks callbacks = {
+		.less = io_timer_cmp,
+		.swp = io_timer_swp,
+	};
+
+	if (clock->timers.nr &&
+	    time_after_eq64(now, clock->timers.data[0]->expire)) {
+		ret = *min_heap_peek(&clock->timers);
+		min_heap_pop(&clock->timers, &callbacks, NULL);
+	}
 
-	if (clock->timers.used &&
-	    time_after_eq64(now, clock->timers.data[0]->expire))
-		heap_pop(&clock->timers, ret, io_timer_cmp, NULL);
 	return ret;
 }
 
@@ -150,7 +176,7 @@ void bch2_io_timers_to_text(struct printbuf *out, struct io_clock *clock)
 	printbuf_tabstop_push(out, 40);
 	prt_printf(out, "current time:\t%llu\n", now);
 
-	for (unsigned i = 0; i < clock->timers.used; i++)
+	for (unsigned i = 0; i < clock->timers.nr; i++)
 		prt_printf(out, "%ps %ps:\t%llu\n",
 		       clock->timers.data[i]->fn,
 		       clock->timers.data[i]->fn2,

fs/bcachefs/clock_types.h

@@ -24,7 +24,7 @@ struct io_timer {
 /* Amount to buffer up on a percpu counter */
 #define IO_CLOCK_PCPU_SECTORS	128
 
-typedef HEAP(struct io_timer *)	io_timer_heap;
+typedef DEFINE_MIN_HEAP(struct io_timer *, io_timer_heap)	io_timer_heap;
 
 struct io_clock {
 	atomic64_t		now;

fs/bcachefs/ec.c

@@ -901,8 +901,8 @@ static int __ec_stripe_mem_alloc(struct bch_fs *c, size_t idx, gfp_t gfp)
 
 		mutex_lock(&c->ec_stripes_heap_lock);
 		if (n.size > h->size) {
-			memcpy(n.data, h->data, h->used * sizeof(h->data[0]));
+			memcpy(n.data, h->data, h->nr * sizeof(h->data[0]));
-			n.used = h->used;
+			n.nr = h->nr;
 			swap(*h, n);
 		}
 		mutex_unlock(&c->ec_stripes_heap_lock);
@@ -993,7 +993,7 @@ static u64 stripe_idx_to_delete(struct bch_fs *c)
 
 	lockdep_assert_held(&c->ec_stripes_heap_lock);
 
-	if (h->used &&
+	if (h->nr &&
 	    h->data[0].blocks_nonempty == 0 &&
 	    !bch2_stripe_is_open(c, h->data[0].idx))
 		return h->data[0].idx;
@@ -1001,14 +1001,6 @@ static u64 stripe_idx_to_delete(struct bch_fs *c)
 	return 0;
 }
 
-static inline int ec_stripes_heap_cmp(ec_stripes_heap *h,
-				      struct ec_stripe_heap_entry l,
-				      struct ec_stripe_heap_entry r)
-{
-	return ((l.blocks_nonempty > r.blocks_nonempty) -
-		(l.blocks_nonempty < r.blocks_nonempty));
-}
-
 static inline void ec_stripes_heap_set_backpointer(ec_stripes_heap *h,
 						   size_t i)
 {
@@ -1017,39 +1009,71 @@ static inline void ec_stripes_heap_set_backpointer(ec_stripes_heap *h,
 	genradix_ptr(&c->stripes, h->data[i].idx)->heap_idx = i;
 }
 
+static inline bool ec_stripes_heap_cmp(const void *l, const void *r, void __always_unused *args)
+{
+	struct ec_stripe_heap_entry *_l = (struct ec_stripe_heap_entry *)l;
+	struct ec_stripe_heap_entry *_r = (struct ec_stripe_heap_entry *)r;
+
+	return ((_l->blocks_nonempty > _r->blocks_nonempty) <
+		(_l->blocks_nonempty < _r->blocks_nonempty));
+}
+
+static inline void ec_stripes_heap_swap(void *l, void *r, void *h)
+{
+	struct ec_stripe_heap_entry *_l = (struct ec_stripe_heap_entry *)l;
+	struct ec_stripe_heap_entry *_r = (struct ec_stripe_heap_entry *)r;
+	ec_stripes_heap *_h = (ec_stripes_heap *)h;
+	size_t i = _l - _h->data;
+	size_t j = _r - _h->data;
+
+	swap(*_l, *_r);
+
+	ec_stripes_heap_set_backpointer(_h, i);
+	ec_stripes_heap_set_backpointer(_h, j);
+}
+
 static void heap_verify_backpointer(struct bch_fs *c, size_t idx)
 {
 	ec_stripes_heap *h = &c->ec_stripes_heap;
 	struct stripe *m = genradix_ptr(&c->stripes, idx);
 
-	BUG_ON(m->heap_idx >= h->used);
+	BUG_ON(m->heap_idx >= h->nr);
 	BUG_ON(h->data[m->heap_idx].idx != idx);
 }
 
 void bch2_stripes_heap_del(struct bch_fs *c,
 			   struct stripe *m, size_t idx)
 {
+	const struct min_heap_callbacks callbacks = {
+		.less = ec_stripes_heap_cmp,
+		.swp = ec_stripes_heap_swap,
+	};
+
 	mutex_lock(&c->ec_stripes_heap_lock);
 	heap_verify_backpointer(c, idx);
 
-	heap_del(&c->ec_stripes_heap, m->heap_idx,
+	min_heap_del(&c->ec_stripes_heap, m->heap_idx, &callbacks, &c->ec_stripes_heap);
-		 ec_stripes_heap_cmp,
-		 ec_stripes_heap_set_backpointer);
 	mutex_unlock(&c->ec_stripes_heap_lock);
 }
 
 void bch2_stripes_heap_insert(struct bch_fs *c,
 			      struct stripe *m, size_t idx)
 {
-	mutex_lock(&c->ec_stripes_heap_lock);
+	const struct min_heap_callbacks callbacks = {
-	BUG_ON(heap_full(&c->ec_stripes_heap));
+		.less = ec_stripes_heap_cmp,
+		.swp = ec_stripes_heap_swap,
+	};
 
-	heap_add(&c->ec_stripes_heap, ((struct ec_stripe_heap_entry) {
+	mutex_lock(&c->ec_stripes_heap_lock);
+	BUG_ON(min_heap_full(&c->ec_stripes_heap));
+
+	genradix_ptr(&c->stripes, idx)->heap_idx = c->ec_stripes_heap.nr;
+	min_heap_push(&c->ec_stripes_heap, &((struct ec_stripe_heap_entry) {
 			.idx = idx,
 			.blocks_nonempty = m->blocks_nonempty,
 		}),
-		 ec_stripes_heap_cmp,
+		&callbacks,
-		 ec_stripes_heap_set_backpointer);
+		&c->ec_stripes_heap);
 
 	heap_verify_backpointer(c, idx);
 	mutex_unlock(&c->ec_stripes_heap_lock);
@@ -1058,6 +1082,10 @@ void bch2_stripes_heap_insert(struct bch_fs *c,
 void bch2_stripes_heap_update(struct bch_fs *c,
 			      struct stripe *m, size_t idx)
 {
+	const struct min_heap_callbacks callbacks = {
+		.less = ec_stripes_heap_cmp,
+		.swp = ec_stripes_heap_swap,
+	};
 	ec_stripes_heap *h = &c->ec_stripes_heap;
 	bool do_deletes;
 	size_t i;
@@ -1068,10 +1096,8 @@ void bch2_stripes_heap_update(struct bch_fs *c,
 	h->data[m->heap_idx].blocks_nonempty = m->blocks_nonempty;
 
 	i = m->heap_idx;
-	heap_sift_up(h,	  i, ec_stripes_heap_cmp,
+	min_heap_sift_up(h,	i, &callbacks, &c->ec_stripes_heap);
-		     ec_stripes_heap_set_backpointer);
+	min_heap_sift_down(h, i, &callbacks, &c->ec_stripes_heap);
-	heap_sift_down(h, i, ec_stripes_heap_cmp,
-		       ec_stripes_heap_set_backpointer);
 
 	heap_verify_backpointer(c, idx);
 
@@ -1864,7 +1890,7 @@ static s64 get_existing_stripe(struct bch_fs *c,
 		return -1;
 
 	mutex_lock(&c->ec_stripes_heap_lock);
-	for (heap_idx = 0; heap_idx < h->used; heap_idx++) {
+	for (heap_idx = 0; heap_idx < h->nr; heap_idx++) {
 		/* No blocks worth reusing, stripe will just be deleted: */
 		if (!h->data[heap_idx].blocks_nonempty)
 			continue;
@@ -2195,7 +2221,7 @@ void bch2_stripes_heap_to_text(struct printbuf *out, struct bch_fs *c)
 	size_t i;
 
 	mutex_lock(&c->ec_stripes_heap_lock);
-	for (i = 0; i < min_t(size_t, h->used, 50); i++) {
+	for (i = 0; i < min_t(size_t, h->nr, 50); i++) {
 		m = genradix_ptr(&c->stripes, h->data[i].idx);
 
 		prt_printf(out, "%zu %u/%u+%u", h->data[i].idx,

fs/bcachefs/ec_types.h

@@ -36,6 +36,6 @@ struct ec_stripe_heap_entry {
 	unsigned		blocks_nonempty;
 };
 
-typedef HEAP(struct ec_stripe_heap_entry) ec_stripes_heap;
+typedef DEFINE_MIN_HEAP(struct ec_stripe_heap_entry, ec_stripes_heap) ec_stripes_heap;
 
 #endif /* _BCACHEFS_EC_TYPES_H */

fs/bcachefs/util.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * random utiility code, for bcache but in theory not specific to bcache
+ * random utility code, for bcache but in theory not specific to bcache
  *
  * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
  * Copyright 2012 Google, Inc.

fs/bcachefs/util.h

@@ -8,6 +8,7 @@
 #include <linux/errno.h>
 #include <linux/freezer.h>
 #include <linux/kernel.h>
+#include <linux/min_heap.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
 #include <linux/log2.h>
@@ -54,17 +55,9 @@ static inline size_t buf_pages(void *p, size_t len)
 			    PAGE_SIZE);
 }
 
-#define HEAP(type)							\
-struct {								\
-	size_t size, used;						\
-	type *data;							\
-}
-
-#define DECLARE_HEAP(type, name) HEAP(type) name
-
 #define init_heap(heap, _size, gfp)					\
 ({									\
-	(heap)->used = 0;						\
+	(heap)->nr = 0;						\
 	(heap)->size = (_size);						\
 	(heap)->data = kvmalloc((heap)->size * sizeof((heap)->data[0]),\
 				 (gfp));				\
@@ -76,113 +69,6 @@ do {									\
 	(heap)->data = NULL;						\
 } while (0)
 
-#define heap_set_backpointer(h, i, _fn)					\
-do {									\
-	void (*fn)(typeof(h), size_t) = _fn;				\
-	if (fn)								\
-		fn(h, i);						\
-} while (0)
-
-#define heap_swap(h, i, j, set_backpointer)				\
-do {									\
-	swap((h)->data[i], (h)->data[j]);				\
-	heap_set_backpointer(h, i, set_backpointer);			\
-	heap_set_backpointer(h, j, set_backpointer);			\
-} while (0)
-
-#define heap_peek(h)							\
-({									\
-	EBUG_ON(!(h)->used);						\
-	(h)->data[0];							\
-})
-
-#define heap_full(h)	((h)->used == (h)->size)
-
-#define heap_sift_down(h, i, cmp, set_backpointer)			\
-do {									\
-	size_t _c, _j = i;						\
-									\
-	for (; _j * 2 + 1 < (h)->used; _j = _c) {			\
-		_c = _j * 2 + 1;					\
-		if (_c + 1 < (h)->used &&				\
-		    cmp(h, (h)->data[_c], (h)->data[_c + 1]) >= 0)	\
-			_c++;						\
-									\
-		if (cmp(h, (h)->data[_c], (h)->data[_j]) >= 0)		\
-			break;						\
-		heap_swap(h, _c, _j, set_backpointer);			\
-	}								\
-} while (0)
-
-#define heap_sift_up(h, i, cmp, set_backpointer)			\
-do {									\
-	while (i) {							\
-		size_t p = (i - 1) / 2;					\
-		if (cmp(h, (h)->data[i], (h)->data[p]) >= 0)		\
-			break;						\
-		heap_swap(h, i, p, set_backpointer);			\
-		i = p;							\
-	}								\
-} while (0)
-
-#define __heap_add(h, d, cmp, set_backpointer)				\
-({									\
-	size_t _i = (h)->used++;					\
-	(h)->data[_i] = d;						\
-	heap_set_backpointer(h, _i, set_backpointer);			\
-									\
-	heap_sift_up(h, _i, cmp, set_backpointer);			\
-	_i;								\
-})
-
-#define heap_add(h, d, cmp, set_backpointer)				\
-({									\
-	bool _r = !heap_full(h);					\
-	if (_r)								\
-		__heap_add(h, d, cmp, set_backpointer);			\
-	_r;								\
-})
-
-#define heap_add_or_replace(h, new, cmp, set_backpointer)		\
-do {									\
-	if (!heap_add(h, new, cmp, set_backpointer) &&			\
-	    cmp(h, new, heap_peek(h)) >= 0) {				\
-		(h)->data[0] = new;					\
-		heap_set_backpointer(h, 0, set_backpointer);		\
-		heap_sift_down(h, 0, cmp, set_backpointer);		\
-	}								\
-} while (0)
-
-#define heap_del(h, i, cmp, set_backpointer)				\
-do {									\
-	size_t _i = (i);						\
-									\
-	BUG_ON(_i >= (h)->used);					\
-	(h)->used--;							\
-	if ((_i) < (h)->used) {						\
-		heap_swap(h, _i, (h)->used, set_backpointer);		\
-		heap_sift_up(h, _i, cmp, set_backpointer);		\
-		heap_sift_down(h, _i, cmp, set_backpointer);		\
-	}								\
-} while (0)
-
-#define heap_pop(h, d, cmp, set_backpointer)				\
-({									\
-	bool _r = (h)->used;						\
-	if (_r) {							\
-		(d) = (h)->data[0];					\
-		heap_del(h, 0, cmp, set_backpointer);			\
-	}								\
-	_r;								\
-})
-
-#define heap_resort(heap, cmp, set_backpointer)				\
-do {									\
-	ssize_t _i;							\
-	for (_i = (ssize_t) (heap)->used / 2 -  1; _i >= 0; --_i)	\
-		heap_sift_down(heap, _i, cmp, set_backpointer);		\
-} while (0)
-
 #define ANYSINT_MAX(t)							\
 	((((t) 1 << (sizeof(t) * 8 - 2)) - (t) 1) * (t) 2 + (t) 1)
 

fs/coredump.c

@@ -361,17 +361,16 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start, int exit_code)
+static int zap_process(struct signal_struct *signal, int exit_code)
 {
 	struct task_struct *t;
 	int nr = 0;
 
-	/* Allow SIGKILL, see prepare_signal() */
+	signal->flags = SIGNAL_GROUP_EXIT;
-	start->signal->flags = SIGNAL_GROUP_EXIT;
+	signal->group_exit_code = exit_code;
-	start->signal->group_exit_code = exit_code;
+	signal->group_stop_count = 0;
-	start->signal->group_stop_count = 0;
 
-	for_each_thread(start, t) {
+	__for_each_thread(signal, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		if (t != current && !(t->flags & PF_POSTCOREDUMP)) {
 			sigaddset(&t->pending.signal, SIGKILL);
@@ -391,8 +390,9 @@ static int zap_threads(struct task_struct *tsk,
 
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) {
+		/* Allow SIGKILL, see prepare_signal() */
 		signal->core_state = core_state;
-		nr = zap_process(tsk, exit_code);
+		nr = zap_process(signal, exit_code);
 		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 		tsk->flags |= PF_DUMPCORE;
 		atomic_set(&core_state->nr_threads, nr);

fs/nilfs2/segment.c

@@ -136,7 +136,7 @@ static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
 
 #define nilfs_cnt32_ge(a, b)   \
 	(typecheck(__u32, a) && typecheck(__u32, b) && \
-	 ((__s32)(a) - (__s32)(b) >= 0))
+	 ((__s32)((a) - (b)) >= 0))
 
 static int nilfs_prepare_segment_lock(struct super_block *sb,
 				      struct nilfs_transaction_info *ti)
@@ -1639,41 +1639,30 @@ static void nilfs_begin_folio_io(struct folio *folio)
 	folio_unlock(folio);
 }
 
-static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
+/**
+ * nilfs_prepare_write_logs - prepare to write logs
+ * @logs: logs to prepare for writing
+ * @seed: checksum seed value
+ *
+ * nilfs_prepare_write_logs() adds checksums and prepares the block
+ * buffers/folios for writing logs.  In order to stabilize folios of
+ * memory-mapped file blocks by putting them in writeback state before
+ * calculating the checksums, first prepare to write payload blocks other
+ * than segment summary and super root blocks in which the checksums will
+ * be embedded.
+ */
+static void nilfs_prepare_write_logs(struct list_head *logs, u32 seed)
 {
 	struct nilfs_segment_buffer *segbuf;
 	struct folio *bd_folio = NULL, *fs_folio = NULL;
+	struct buffer_head *bh;
 
-	list_for_each_entry(segbuf, &sci->sc_segbufs, sb_list) {
+	/* Prepare to write payload blocks */
-		struct buffer_head *bh;
+	list_for_each_entry(segbuf, logs, sb_list) {
-
-		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
-				    b_assoc_buffers) {
-			if (bh->b_folio != bd_folio) {
-				if (bd_folio) {
-					folio_lock(bd_folio);
-					folio_wait_writeback(bd_folio);
-					folio_clear_dirty_for_io(bd_folio);
-					folio_start_writeback(bd_folio);
-					folio_unlock(bd_folio);
-				}
-				bd_folio = bh->b_folio;
-			}
-		}
-
 		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
 				    b_assoc_buffers) {
-			if (bh == segbuf->sb_super_root) {
+			if (bh == segbuf->sb_super_root)
-				if (bh->b_folio != bd_folio) {
-					folio_lock(bd_folio);
-					folio_wait_writeback(bd_folio);
-					folio_clear_dirty_for_io(bd_folio);
-					folio_start_writeback(bd_folio);
-					folio_unlock(bd_folio);
-					bd_folio = bh->b_folio;
-				}
 				break;
-			}
 			set_buffer_async_write(bh);
 			if (bh->b_folio != fs_folio) {
 				nilfs_begin_folio_io(fs_folio);
@@ -1681,6 +1670,42 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 			}
 		}
 	}
+	nilfs_begin_folio_io(fs_folio);
+
+	nilfs_add_checksums_on_logs(logs, seed);
+
+	/* Prepare to write segment summary blocks */
+	list_for_each_entry(segbuf, logs, sb_list) {
+		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
+				    b_assoc_buffers) {
+			mark_buffer_dirty(bh);
+			if (bh->b_folio == bd_folio)
+				continue;
+			if (bd_folio) {
+				folio_lock(bd_folio);
+				folio_wait_writeback(bd_folio);
+				folio_clear_dirty_for_io(bd_folio);
+				folio_start_writeback(bd_folio);
+				folio_unlock(bd_folio);
+			}
+			bd_folio = bh->b_folio;
+		}
+	}
+
+	/* Prepare to write super root block */
+	bh = NILFS_LAST_SEGBUF(logs)->sb_super_root;
+	if (bh) {
+		mark_buffer_dirty(bh);
+		if (bh->b_folio != bd_folio) {
+			folio_lock(bd_folio);
+			folio_wait_writeback(bd_folio);
+			folio_clear_dirty_for_io(bd_folio);
+			folio_start_writeback(bd_folio);
+			folio_unlock(bd_folio);
+			bd_folio = bh->b_folio;
+		}
+	}
+
 	if (bd_folio) {
 		folio_lock(bd_folio);
 		folio_wait_writeback(bd_folio);
@@ -1688,7 +1713,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 		folio_start_writeback(bd_folio);
 		folio_unlock(bd_folio);
 	}
-	nilfs_begin_folio_io(fs_folio);
 }
 
 static int nilfs_segctor_write(struct nilfs_sc_info *sci,
@@ -2070,10 +2094,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 		nilfs_segctor_update_segusage(sci, nilfs->ns_sufile);
 
 		/* Write partial segments */
-		nilfs_segctor_prepare_write(sci);
+		nilfs_prepare_write_logs(&sci->sc_segbufs, nilfs->ns_crc_seed);
-
-		nilfs_add_checksums_on_logs(&sci->sc_segbufs,
-					    nilfs->ns_crc_seed);
 
 		err = nilfs_segctor_write(sci, nilfs);
 		if (unlikely(err))
@@ -2824,8 +2845,6 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
 	if (!nilfs->ns_writer)
 		return -ENOMEM;
 
-	inode_attach_wb(nilfs->ns_bdev->bd_mapping->host, NULL);
-
 	err = nilfs_segctor_start_thread(nilfs->ns_writer);
 	if (unlikely(err))
 		nilfs_detach_log_writer(sb);

fs/nilfs2/sysfs.c

@@ -56,7 +56,7 @@ static void nilfs_##name##_attr_release(struct kobject *kobj) \
 						sg_##name##_kobj); \
 	complete(&subgroups->sg_##name##_kobj_unregister); \
 } \
-static struct kobj_type nilfs_##name##_ktype = { \
+static const struct kobj_type nilfs_##name##_ktype = { \
 	.default_groups	= nilfs_##name##_groups, \
 	.sysfs_ops	= &nilfs_##name##_attr_ops, \
 	.release	= nilfs_##name##_attr_release, \
@@ -166,7 +166,7 @@ static const struct sysfs_ops nilfs_snapshot_attr_ops = {
 	.store	= nilfs_snapshot_attr_store,
 };
 
-static struct kobj_type nilfs_snapshot_ktype = {
+static const struct kobj_type nilfs_snapshot_ktype = {
 	.default_groups	= nilfs_snapshot_groups,
 	.sysfs_ops	= &nilfs_snapshot_attr_ops,
 	.release	= nilfs_snapshot_attr_release,
@@ -967,7 +967,7 @@ static const struct sysfs_ops nilfs_dev_attr_ops = {
 	.store	= nilfs_dev_attr_store,
 };
 
-static struct kobj_type nilfs_dev_ktype = {
+static const struct kobj_type nilfs_dev_ktype = {
 	.default_groups	= nilfs_dev_groups,
 	.sysfs_ops	= &nilfs_dev_attr_ops,
 	.release	= nilfs_dev_attr_release,

fs/ocfs2/dir.c

@@ -294,13 +294,16 @@ out:
  * bh passed here can be an inode block or a dir data block, depending
  * on the inode inline data flag.
  */
-static int ocfs2_check_dir_entry(struct inode * dir,
+static int ocfs2_check_dir_entry(struct inode *dir,
-				 struct ocfs2_dir_entry * de,
+				 struct ocfs2_dir_entry *de,
-				 struct buffer_head * bh,
+				 struct buffer_head *bh,
+				 char *buf,
+				 unsigned int size,
 				 unsigned long offset)
 {
 	const char *error_msg = NULL;
 	const int rlen = le16_to_cpu(de->rec_len);
+	const unsigned long next_offset = ((char *) de - buf) + rlen;
 
 	if (unlikely(rlen < OCFS2_DIR_REC_LEN(1)))
 		error_msg = "rec_len is smaller than minimal";
@@ -308,9 +311,11 @@ static int ocfs2_check_dir_entry(struct inode * dir,
 		error_msg = "rec_len % 4 != 0";
 	else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len)))
 		error_msg = "rec_len is too small for name_len";
-	else if (unlikely(
+	else if (unlikely(next_offset > size))
-		 ((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize))
+		error_msg = "directory entry overrun";
-		error_msg = "directory entry across blocks";
+	else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) &&
+		 next_offset != size)
+		error_msg = "directory entry too close to end";
 
 	if (unlikely(error_msg != NULL))
 		mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
@@ -352,16 +357,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh,
 	de_buf = first_de;
 	dlimit = de_buf + bytes;
 
-	while (de_buf < dlimit) {
+	while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) {
 		/* this code is executed quadratically often */
 		/* do minimal checking `by hand' */
 
 		de = (struct ocfs2_dir_entry *) de_buf;
 
-		if (de_buf + namelen <= dlimit &&
+		if (de->name + namelen <= dlimit &&
 		    ocfs2_match(namelen, name, de)) {
 			/* found a match - just to be sure, do a full check */
-			if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+			if (!ocfs2_check_dir_entry(dir, de, bh, first_de,
+						   bytes, offset)) {
 				ret = -1;
 				goto bail;
 			}
@@ -1138,7 +1144,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
 	pde = NULL;
 	de = (struct ocfs2_dir_entry *) first_de;
 	while (i < bytes) {
-		if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
+		if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) {
 			status = -EIO;
 			mlog_errno(status);
 			goto bail;
@@ -1635,7 +1641,8 @@ int __ocfs2_add_entry(handle_t *handle,
 		/* These checks should've already been passed by the
 		 * prepare function, but I guess we can leave them
 		 * here anyway. */
-		if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start,
+					   size, offset)) {
 			retval = -ENOENT;
 			goto bail;
 		}
@@ -1774,7 +1781,8 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
 		}
 
 		de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
-		if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) {
+		if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data,
+					   i_size_read(inode), ctx->pos)) {
 			/* On error, skip the f_pos to the end. */
 			ctx->pos = i_size_read(inode);
 			break;
@@ -1867,7 +1875,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 		while (ctx->pos < i_size_read(inode)
 		       && offset < sb->s_blocksize) {
 			de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
-			if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
+			if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data,
+						   sb->s_blocksize, offset)) {
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
@@ -3339,7 +3348,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
 	struct super_block *sb = dir->i_sb;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_dir_entry *de, *last_de = NULL;
-	char *de_buf, *limit;
+	char *first_de, *de_buf, *limit;
 	unsigned long offset = 0;
 	unsigned int rec_len, new_rec_len, free_space;
 
@@ -3352,14 +3361,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
 	else
 		free_space = dir->i_sb->s_blocksize - i_size_read(dir);
 
-	de_buf = di->id2.i_data.id_data;
+	first_de = di->id2.i_data.id_data;
+	de_buf = first_de;
 	limit = de_buf + i_size_read(dir);
 	rec_len = OCFS2_DIR_REC_LEN(namelen);
 
 	while (de_buf < limit) {
 		de = (struct ocfs2_dir_entry *)de_buf;
 
-		if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de,
+					   i_size_read(dir), offset)) {
 			ret = -ENOENT;
 			goto out;
 		}
@@ -3441,7 +3452,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
 			/* move to next block */
 			de = (struct ocfs2_dir_entry *) bh->b_data;
 		}
-		if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize,
+					   offset)) {
 			status = -ENOENT;
 			goto bail;
 		}

fs/ocfs2/dlmglue.c

@@ -221,12 +221,12 @@ struct ocfs2_lock_res_ops {
  */
 #define LOCK_TYPE_USES_LVB		0x2
 
-static struct ocfs2_lock_res_ops ocfs2_inode_rw_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_inode_rw_lops = {
 	.get_osb	= ocfs2_get_inode_osb,
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_inode_inode_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_inode_inode_lops = {
 	.get_osb	= ocfs2_get_inode_osb,
 	.check_downconvert = ocfs2_check_meta_downconvert,
 	.set_lvb	= ocfs2_set_meta_lvb,
@@ -234,50 +234,50 @@ static struct ocfs2_lock_res_ops ocfs2_inode_inode_lops = {
 	.flags		= LOCK_TYPE_REQUIRES_REFRESH|LOCK_TYPE_USES_LVB,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_super_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_super_lops = {
 	.flags		= LOCK_TYPE_REQUIRES_REFRESH,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_rename_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_rename_lops = {
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_nfs_sync_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_nfs_sync_lops = {
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_trim_fs_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_trim_fs_lops = {
 	.flags		= LOCK_TYPE_REQUIRES_REFRESH|LOCK_TYPE_USES_LVB,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_orphan_scan_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_orphan_scan_lops = {
 	.flags		= LOCK_TYPE_REQUIRES_REFRESH|LOCK_TYPE_USES_LVB,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_dentry_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_dentry_lops = {
 	.get_osb	= ocfs2_get_dentry_osb,
 	.post_unlock	= ocfs2_dentry_post_unlock,
 	.downconvert_worker = ocfs2_dentry_convert_worker,
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_inode_open_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_inode_open_lops = {
 	.get_osb	= ocfs2_get_inode_osb,
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_flock_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_flock_lops = {
 	.get_osb	= ocfs2_get_file_osb,
 	.flags		= 0,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_qinfo_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_qinfo_lops = {
 	.set_lvb	= ocfs2_set_qinfo_lvb,
 	.get_osb	= ocfs2_get_qinfo_osb,
 	.flags		= LOCK_TYPE_REQUIRES_REFRESH | LOCK_TYPE_USES_LVB,
 };
 
-static struct ocfs2_lock_res_ops ocfs2_refcount_block_lops = {
+static const struct ocfs2_lock_res_ops ocfs2_refcount_block_lops = {
 	.check_downconvert = ocfs2_check_refcount_downconvert,
 	.downconvert_worker = ocfs2_refcount_convert_worker,
 	.flags		= 0,
@@ -510,7 +510,7 @@ static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
 static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
 				       struct ocfs2_lock_res *res,
 				       enum ocfs2_lock_type type,
-				       struct ocfs2_lock_res_ops *ops,
+				       const struct ocfs2_lock_res_ops *ops,
 				       void *priv)
 {
 	res->l_type          = type;
@@ -553,7 +553,7 @@ void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
 			       unsigned int generation,
 			       struct inode *inode)
 {
-	struct ocfs2_lock_res_ops *ops;
+	const struct ocfs2_lock_res_ops *ops;
 
 	switch(type) {
 		case OCFS2_LOCK_TYPE_RW:

fs/ocfs2/namei.c

@@ -2189,8 +2189,10 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
  * @osb: ocfs2 file system
  * @ret_orphan_dir: Orphan dir inode - returned locked!
  * @blkno: Actual block number of the inode to be inserted into orphan dir.
+ * @name: Buffer to store the name of the orphan.
  * @lookup: dir lookup result, to be passed back into functions like
  *          ocfs2_orphan_add
+ * @dio: Flag indicating if direct IO is being used or not.
  *
  * Returns zero on success and the ret_orphan_dir, name and lookup
  * fields will be populated.

fs/ocfs2/ocfs2.h

@@ -154,7 +154,7 @@ struct ocfs2_lock_stats {
 
 struct ocfs2_lock_res {
 	void                    *l_priv;
-	struct ocfs2_lock_res_ops *l_ops;
+	const struct ocfs2_lock_res_ops *l_ops;
 
 
 	struct list_head         l_blocked_list;

fs/ocfs2/stack_o2cb.c

@@ -404,7 +404,7 @@ static int o2cb_cluster_this_node(struct ocfs2_cluster_connection *conn,
 	return 0;
 }
 
-static struct ocfs2_stack_operations o2cb_stack_ops = {
+static const struct ocfs2_stack_operations o2cb_stack_ops = {
 	.connect	= o2cb_cluster_connect,
 	.disconnect	= o2cb_cluster_disconnect,
 	.this_node	= o2cb_cluster_this_node,

fs/ocfs2/stack_user.c

@@ -1065,7 +1065,7 @@ static int user_cluster_this_node(struct ocfs2_cluster_connection *conn,
 	return 0;
 }
 
-static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
+static const struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
 	.connect	= user_cluster_connect,
 	.disconnect	= user_cluster_disconnect,
 	.this_node	= user_cluster_this_node,

fs/ocfs2/stackglue.h

@@ -223,7 +223,7 @@ struct ocfs2_stack_operations {
  */
 struct ocfs2_stack_plugin {
 	char *sp_name;
-	struct ocfs2_stack_operations *sp_ops;
+	const struct ocfs2_stack_operations *sp_ops;
 	struct module *sp_owner;
 
 	/* These are managed by the stackglue code. */

fs/ocfs2/xattr.c

@@ -1062,13 +1062,13 @@ ssize_t ocfs2_listxattr(struct dentry *dentry,
 	return i_ret + b_ret;
 }
 
-static int ocfs2_xattr_find_entry(int name_index,
+static int ocfs2_xattr_find_entry(struct inode *inode, int name_index,
 				  const char *name,
 				  struct ocfs2_xattr_search *xs)
 {
 	struct ocfs2_xattr_entry *entry;
 	size_t name_len;
-	int i, cmp = 1;
+	int i, name_offset, cmp = 1;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -1076,13 +1076,22 @@ static int ocfs2_xattr_find_entry(int name_index,
 	name_len = strlen(name);
 	entry = xs->here;
 	for (i = 0; i < le16_to_cpu(xs->header->xh_count); i++) {
+		if ((void *)entry >= xs->end) {
+			ocfs2_error(inode->i_sb, "corrupted xattr entries");
+			return -EFSCORRUPTED;
+		}
 		cmp = name_index - ocfs2_xattr_get_type(entry);
 		if (!cmp)
 			cmp = name_len - entry->xe_name_len;
-		if (!cmp)
+		if (!cmp) {
-			cmp = memcmp(name, (xs->base +
+			name_offset = le16_to_cpu(entry->xe_name_offset);
-				     le16_to_cpu(entry->xe_name_offset)),
+			if ((xs->base + name_offset + name_len) > xs->end) {
-				     name_len);
+				ocfs2_error(inode->i_sb,
+					    "corrupted xattr entries");
+				return -EFSCORRUPTED;
+			}
+			cmp = memcmp(name, (xs->base + name_offset), name_len);
+		}
 		if (cmp == 0)
 			break;
 		entry += 1;
@@ -1166,7 +1175,7 @@ static int ocfs2_xattr_ibody_get(struct inode *inode,
 	xs->base = (void *)xs->header;
 	xs->here = xs->header->xh_entries;
 
-	ret = ocfs2_xattr_find_entry(name_index, name, xs);
+	ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
 	if (ret)
 		return ret;
 	size = le64_to_cpu(xs->here->xe_value_size);
@@ -2698,7 +2707,7 @@ static int ocfs2_xattr_ibody_find(struct inode *inode,
 
 	/* Find the named attribute. */
 	if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
-		ret = ocfs2_xattr_find_entry(name_index, name, xs);
+		ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
 		if (ret && ret != -ENODATA)
 			return ret;
 		xs->not_found = ret;
@@ -2833,7 +2842,7 @@ static int ocfs2_xattr_block_find(struct inode *inode,
 		xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
 		xs->here = xs->header->xh_entries;
 
-		ret = ocfs2_xattr_find_entry(name_index, name, xs);
+		ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
 	} else
 		ret = ocfs2_xattr_index_block_find(inode, blk_bh,
 						   name_index,

fs/ufs/super.c

@@ -1540,4 +1540,5 @@ static void __exit exit_ufs_fs(void)
 
 module_init(init_ufs_fs)
 module_exit(exit_ufs_fs)
+MODULE_DESCRIPTION("UFS Filesystem");
 MODULE_LICENSE("GPL");

include/asm-generic/vmlinux.lds.h

@@ -141,14 +141,6 @@
  * often happens at runtime)
  */
 
-#if defined(CONFIG_MEMORY_HOTPLUG)
-#define MEM_KEEP(sec)    *(.mem##sec)
-#define MEM_DISCARD(sec)
-#else
-#define MEM_KEEP(sec)
-#define MEM_DISCARD(sec) *(.mem##sec)
-#endif
-
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 #define KEEP_PATCHABLE		KEEP(*(__patchable_function_entries))
 #define PATCHABLE_DISCARDS
@@ -357,7 +349,6 @@
 	*(.data..decrypted)						\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
-	MEM_KEEP(init.data*)						\
 	*(.data.unlikely)						\
 	__start_once = .;						\
 	*(.data.once)							\
@@ -542,7 +533,6 @@
 	/* __*init sections */						\
 	__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) {		\
 		*(.ref.rodata)						\
-		MEM_KEEP(init.rodata)					\
 	}								\
 									\
 	/* Built-in module parameters. */				\
@@ -593,8 +583,7 @@
 		*(.text.unknown .text.unknown.*)			\
 		NOINSTR_TEXT						\
 		*(.ref.text)						\
-		*(.text.asan.* .text.tsan.*)				\
+		*(.text.asan.* .text.tsan.*)
-	MEM_KEEP(init.text*)						\
 
 
 /* sched.text is aling to function alignment to secure we have same
@@ -701,7 +690,6 @@
 #define INIT_DATA							\
 	KEEP(*(SORT(___kentry+*)))					\
 	*(.init.data .init.data.*)					\
-	MEM_DISCARD(init.data*)						\
 	KERNEL_CTORS()							\
 	MCOUNT_REC()							\
 	*(.init.rodata .init.rodata.*)					\
@@ -709,7 +697,6 @@
 	TRACE_SYSCALLS()						\
 	KPROBE_BLACKLIST()						\
 	ERROR_INJECT_WHITELIST()					\
-	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
 	TIMER_OF_TABLES()						\
@@ -727,8 +714,7 @@
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
-	*(.text.startup)						\
+	*(.text.startup)
-	MEM_DISCARD(init.text*)
 
 #define EXIT_DATA							\
 	*(.exit.data .exit.data.*)					\

include/linux/cacheinfo.h

@@ -4,7 +4,7 @@
 
 #include <linux/bitops.h>
 #include <linux/cpuhplock.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/smp.h>
 
 struct device_node;

include/linux/cgroup.h

@@ -10,7 +10,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/rculist.h>
 #include <linux/cgroupstats.h>

include/linux/clockchips.h

@@ -12,7 +12,7 @@
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 # include <linux/clocksource.h>
-# include <linux/cpumask.h>
+# include <linux/cpumask_types.h>
 # include <linux/ktime.h>
 # include <linux/notifier.h>
 

include/linux/compiler.h

@@ -208,10 +208,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define data_race(expr)							\
 ({									\
-	__unqual_scalar_typeof(({ expr; })) __v = ({			\
+	__kcsan_disable_current();					\
-		__kcsan_disable_current();				\
+	__auto_type __v = (expr);					\
-		expr;							\
-	});								\
 	__kcsan_enable_current();					\
 	__v;								\
 })

include/linux/cpu.h

@@ -16,7 +16,6 @@
 
 #include <linux/node.h>
 #include <linux/compiler.h>
-#include <linux/cpumask.h>
 #include <linux/cpuhotplug.h>
 #include <linux/cpuhplock.h>
 #include <linux/cpu_smt.h>

include/linux/cpu_cooling.h

@@ -15,7 +15,6 @@
 
 #include <linux/of.h>
 #include <linux/thermal.h>
-#include <linux/cpumask.h>
 
 struct cpufreq_policy;
 

include/linux/cpu_rmap.h

@@ -7,7 +7,7 @@
  * Copyright 2011 Solarflare Communications Inc.
  */
 
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/kref.h>

include/linux/cpumask.h

@@ -9,25 +9,13 @@
  */
 #include <linux/cleanup.h>
 #include <linux/kernel.h>
-#include <linux/threads.h>
 #include <linux/bitmap.h>
+#include <linux/cpumask_types.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
 #include <linux/gfp_types.h>
 #include <linux/numa.h>
 
-/* Don't assign or return these: may not be this big! */
-typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
-
-/**
- * cpumask_bits - get the bits in a cpumask
- * @maskp: the struct cpumask *
- *
- * You should only assume nr_cpu_ids bits of this mask are valid.  This is
- * a macro so it's const-correct.
- */
-#define cpumask_bits(maskp) ((maskp)->bits)
-
 /**
  * cpumask_pr_args - printf args to output a cpumask
  * @maskp: cpumask to be printed
@@ -925,48 +913,7 @@ static inline unsigned int cpumask_size(void)
 	return bitmap_size(large_cpumask_bits);
 }
 
-/*
- * cpumask_var_t: struct cpumask for stack usage.
- *
- * Oh, the wicked games we play!  In order to make kernel coding a
- * little more difficult, we typedef cpumask_var_t to an array or a
- * pointer: doing &mask on an array is a noop, so it still works.
- *
- * i.e.
- *	cpumask_var_t tmpmask;
- *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- *		return -ENOMEM;
- *
- *	  ... use 'tmpmask' like a normal struct cpumask * ...
- *
- *	free_cpumask_var(tmpmask);
- *
- *
- * However, one notable exception is there. alloc_cpumask_var() allocates
- * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has
- * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t.
- *
- *	cpumask_var_t tmpmask;
- *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- *		return -ENOMEM;
- *
- *	var = *tmpmask;
- *
- * This code makes NR_CPUS length memcopy and brings to a memory corruption.
- * cpumask_copy() provide safe copy functionality.
- *
- * Note that there is another evil here: If you define a cpumask_var_t
- * as a percpu variable then the way to obtain the address of the cpumask
- * structure differently influences what this_cpu_* operation needs to be
- * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
- * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
- * other type of cpumask_var_t implementation is configured.
- *
- * Please also note that __cpumask_var_read_mostly can be used to declare
- * a cpumask_var_t variable itself (not its content) as read mostly.
- */
 #ifdef CONFIG_CPUMASK_OFFSTACK
-typedef struct cpumask *cpumask_var_t;
 
 #define this_cpu_cpumask_var_ptr(x)	this_cpu_read(x)
 #define __cpumask_var_read_mostly	__read_mostly
@@ -1013,7 +960,6 @@ static inline bool cpumask_available(cpumask_var_t mask)
 }
 
 #else
-typedef struct cpumask cpumask_var_t[1];
 
 #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
 #define __cpumask_var_read_mostly

include/linux/cpumask_types.h

@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_CPUMASK_TYPES_H
+#define __LINUX_CPUMASK_TYPES_H
+
+#include <linux/bitops.h>
+#include <linux/threads.h>
+
+/* Don't assign or return these: may not be this big! */
+typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
+
+/**
+ * cpumask_bits - get the bits in a cpumask
+ * @maskp: the struct cpumask *
+ *
+ * You should only assume nr_cpu_ids bits of this mask are valid.  This is
+ * a macro so it's const-correct.
+ */
+#define cpumask_bits(maskp) ((maskp)->bits)
+
+/*
+ * cpumask_var_t: struct cpumask for stack usage.
+ *
+ * Oh, the wicked games we play!  In order to make kernel coding a
+ * little more difficult, we typedef cpumask_var_t to an array or a
+ * pointer: doing &mask on an array is a noop, so it still works.
+ *
+ * i.e.
+ *	cpumask_var_t tmpmask;
+ *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ *		return -ENOMEM;
+ *
+ *	  ... use 'tmpmask' like a normal struct cpumask * ...
+ *
+ *	free_cpumask_var(tmpmask);
+ *
+ *
+ * However, one notable exception is there. alloc_cpumask_var() allocates
+ * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has
+ * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t.
+ *
+ *	cpumask_var_t tmpmask;
+ *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ *		return -ENOMEM;
+ *
+ *	var = *tmpmask;
+ *
+ * This code makes NR_CPUS length memcopy and brings to a memory corruption.
+ * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
+ *
+ * Please also note that __cpumask_var_read_mostly can be used to declare
+ * a cpumask_var_t variable itself (not its content) as read mostly.
+ */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+typedef struct cpumask *cpumask_var_t;
+#else
+typedef struct cpumask cpumask_var_t[1];
+#endif /* CONFIG_CPUMASK_OFFSTACK */
+
+#endif /* __LINUX_CPUMASK_TYPES_H */

include/linux/init.h

@@ -84,11 +84,15 @@
 
 #define __exit          __section(".exit.text") __exitused __cold notrace
 
-/* Used for MEMORY_HOTPLUG */
+#ifdef CONFIG_MEMORY_HOTPLUG
-#define __meminit        __section(".meminit.text") __cold notrace \
+#define __meminit
-						  __latent_entropy
+#define __meminitdata
-#define __meminitdata    __section(".meminit.data")
+#define __meminitconst
-#define __meminitconst   __section(".meminit.rodata")
+#else
+#define __meminit	__init
+#define __meminitdata	__initdata
+#define __meminitconst	__initconst
+#endif
 
 /* For assembly routines */
 #define __HEAD		.section	".head.text","ax"
@@ -99,10 +103,6 @@
 #define __INITRODATA	.section	".init.rodata","a",%progbits
 #define __FINITDATA	.previous
 
-#define __MEMINIT        .section	".meminit.text", "ax"
-#define __MEMINITDATA    .section	".meminit.data", "aw"
-#define __MEMINITRODATA  .section	".meminit.rodata", "a"
-
 /* silence warnings when references are OK */
 #define __REF            .section       ".ref.text", "ax"
 #define __REFDATA        .section       ".ref.data", "aw"

include/linux/interrupt.h

@@ -6,13 +6,13 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/cleanup.h>
-#include <linux/cpumask.h>
 #include <linux/irqreturn.h>
 #include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
+#include <linux/cpumask_types.h>
 #include <linux/workqueue.h>
 #include <linux/jump_label.h>
 

include/linux/irqchip/irq-partition-percpu.h

@@ -8,7 +8,7 @@
 #define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H
 
 #include <linux/fwnode.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/irqdomain.h>
 
 struct partition_affinity {

include/linux/jhash.h

@@ -31,7 +31,7 @@
 /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */
 #define jhash_mask(n)   (jhash_size(n)-1)
 
-/* __jhash_mix -- mix 3 32-bit values reversibly. */
+/* __jhash_mix - mix 3 32-bit values reversibly. */
 #define __jhash_mix(a, b, c)			\
 {						\
 	a -= c;  a ^= rol32(c, 4);  c += b;	\
@@ -60,7 +60,7 @@
 /* jhash - hash an arbitrary key
  * @k: sequence of bytes as key
  * @length: the length of the key
- * @initval: the previous hash, or an arbitray value
+ * @initval: the previous hash, or an arbitrary value
  *
  * The generic version, hashes an arbitrary sequence of bytes.
  * No alignment or length assumptions are made about the input key.
@@ -110,7 +110,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 /* jhash2 - hash an array of u32's
  * @k: the key which must be an array of u32's
  * @length: the number of u32's in the key
- * @initval: the previous hash, or an arbitray value
+ * @initval: the previous hash, or an arbitrary value
  *
  * Returns the hash value of the key.
  */

include/linux/kernel_stat.h

@@ -5,7 +5,6 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
-#include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/vtime.h>

include/linux/min_heap.h

@@ -7,46 +7,89 @@
 #include <linux/types.h>
 
 /**
- * struct min_heap - Data structure to hold a min-heap.
+ * Data structure to hold a min-heap.
- * @data: Start of array holding the heap elements.
  * @nr: Number of elements currently in the heap.
  * @size: Maximum number of elements that can be held in current storage.
+ * @data: Pointer to the start of array holding the heap elements.
+ * @preallocated: Start of the static preallocated array holding the heap elements.
  */
-struct min_heap {
+#define MIN_HEAP_PREALLOCATED(_type, _name, _nr)	\
-	void *data;
+struct _name {	\
-	int nr;
+	int nr;	\
-	int size;
+	int size;	\
-};
+	_type *data;	\
+	_type preallocated[_nr];	\
+}
+
+#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0)
+
+typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char;
+
+#define __minheap_cast(_heap)		(typeof((_heap)->data[0]) *)
+#define __minheap_obj_size(_heap)	sizeof((_heap)->data[0])
 
 /**
  * struct min_heap_callbacks - Data/functions to customise the min_heap.
- * @elem_size: The nr of each element in bytes.
  * @less: Partial order function for this heap.
  * @swp: Swap elements function.
  */
 struct min_heap_callbacks {
-	int elem_size;
+	bool (*less)(const void *lhs, const void *rhs, void *args);
-	bool (*less)(const void *lhs, const void *rhs);
+	void (*swp)(void *lhs, void *rhs, void *args);
-	void (*swp)(void *lhs, void *rhs);
 };
 
+/* Initialize a min-heap. */
+static __always_inline
+void __min_heap_init(min_heap_char *heap, void *data, int size)
+{
+	heap->nr = 0;
+	heap->size = size;
+	if (data)
+		heap->data = data;
+	else
+		heap->data = heap->preallocated;
+}
+
+#define min_heap_init(_heap, _data, _size)	\
+	__min_heap_init((min_heap_char *)_heap, _data, _size)
+
+/* Get the minimum element from the heap. */
+static __always_inline
+void *__min_heap_peek(struct min_heap_char *heap)
+{
+	return heap->nr ? heap->data : NULL;
+}
+
+#define min_heap_peek(_heap)	\
+	(__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap))
+
+/* Check if the heap is full. */
+static __always_inline
+bool __min_heap_full(min_heap_char *heap)
+{
+	return heap->nr == heap->size;
+}
+
+#define min_heap_full(_heap)	\
+	__min_heap_full((min_heap_char *)_heap)
+
 /* Sift the element at pos down the heap. */
 static __always_inline
-void min_heapify(struct min_heap *heap, int pos,
+void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size,
-		const struct min_heap_callbacks *func)
+		const struct min_heap_callbacks *func, void *args)
 {
 	void *left, *right;
 	void *data = heap->data;
-	void *root = data + pos * func->elem_size;
+	void *root = data + pos * elem_size;
 	int i = pos, j;
 
 	/* Find the sift-down path all the way to the leaves. */
 	for (;;) {
 		if (i * 2 + 2 >= heap->nr)
 			break;
-		left = data + (i * 2 + 1) * func->elem_size;
+		left = data + (i * 2 + 1) * elem_size;
-		right = data + (i * 2 + 2) * func->elem_size;
+		right = data + (i * 2 + 2) * elem_size;
-		i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2;
+		i = func->less(left, right, args) ? i * 2 + 1 : i * 2 + 2;
 	}
 
 	/* Special case for the last leaf with no sibling. */
@@ -54,83 +97,140 @@ void min_heapify(struct min_heap *heap, int pos,
 		i = i * 2 + 1;
 
 	/* Backtrack to the correct location. */
-	while (i != pos && func->less(root, data + i * func->elem_size))
+	while (i != pos && func->less(root, data + i * elem_size, args))
 		i = (i - 1) / 2;
 
 	/* Shift the element into its correct place. */
 	j = i;
 	while (i != pos) {
 		i = (i - 1) / 2;
-		func->swp(data + i * func->elem_size, data + j * func->elem_size);
+		func->swp(data + i * elem_size, data + j * elem_size, args);
 	}
 }
 
+#define min_heap_sift_down(_heap, _pos, _func, _args)	\
+	__min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args)
+
+/* Sift up ith element from the heap, O(log2(nr)). */
+static __always_inline
+void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
+		const struct min_heap_callbacks *func, void *args)
+{
+	void *data = heap->data;
+	size_t parent;
+
+	while (idx) {
+		parent = (idx - 1) / 2;
+		if (func->less(data + parent * elem_size, data + idx * elem_size, args))
+			break;
+		func->swp(data + parent * elem_size, data + idx * elem_size, args);
+		idx = parent;
+	}
+}
+
+#define min_heap_sift_up(_heap, _idx, _func, _args)	\
+	__min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+
 /* Floyd's approach to heapification that is O(nr). */
 static __always_inline
-void min_heapify_all(struct min_heap *heap,
+void __min_heapify_all(min_heap_char *heap, size_t elem_size,
-		const struct min_heap_callbacks *func)
+		const struct min_heap_callbacks *func, void *args)
 {
 	int i;
 
 	for (i = heap->nr / 2 - 1; i >= 0; i--)
-		min_heapify(heap, i, func);
+		__min_heap_sift_down(heap, i, elem_size, func, args);
 }
 
+#define min_heapify_all(_heap, _func, _args)	\
+	__min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+
 /* Remove minimum element from the heap, O(log2(nr)). */
 static __always_inline
-void min_heap_pop(struct min_heap *heap,
+bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
-		const struct min_heap_callbacks *func)
+		const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 
 	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
-		return;
+		return false;
 
 	/* Place last element at the root (position 0) and then sift down. */
 	heap->nr--;
-	memcpy(data, data + (heap->nr * func->elem_size), func->elem_size);
+	memcpy(data, data + (heap->nr * elem_size), elem_size);
-	min_heapify(heap, 0, func);
+	__min_heap_sift_down(heap, 0, elem_size, func, args);
+
+	return true;
 }
 
+#define min_heap_pop(_heap, _func, _args)	\
+	__min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+
 /*
  * Remove the minimum element and then push the given element. The
  * implementation performs 1 sift (O(log2(nr))) and is therefore more
  * efficient than a pop followed by a push that does 2.
  */
 static __always_inline
-void min_heap_pop_push(struct min_heap *heap,
+void __min_heap_pop_push(min_heap_char *heap,
-		const void *element,
+		const void *element, size_t elem_size,
-		const struct min_heap_callbacks *func)
+		const struct min_heap_callbacks *func,
+		void *args)
 {
-	memcpy(heap->data, element, func->elem_size);
+	memcpy(heap->data, element, elem_size);
-	min_heapify(heap, 0, func);
+	__min_heap_sift_down(heap, 0, elem_size, func, args);
 }
 
+#define min_heap_pop_push(_heap, _element, _func, _args)	\
+	__min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
+
 /* Push an element on to the heap, O(log2(nr)). */
 static __always_inline
-void min_heap_push(struct min_heap *heap, const void *element,
+bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
-		const struct min_heap_callbacks *func)
+		const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
-	void *child, *parent;
 	int pos;
 
 	if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap"))
-		return;
+		return false;
 
 	/* Place at the end of data. */
 	pos = heap->nr;
-	memcpy(data + (pos * func->elem_size), element, func->elem_size);
+	memcpy(data + (pos * elem_size), element, elem_size);
 	heap->nr++;
 
 	/* Sift child at pos up. */
-	for (; pos > 0; pos = (pos - 1) / 2) {
+	__min_heap_sift_up(heap, elem_size, pos, func, args);
-		child = data + (pos * func->elem_size);
+
-		parent = data + ((pos - 1) / 2) * func->elem_size;
+	return true;
-		if (func->less(parent, child))
-			break;
-		func->swp(parent, child);
-	}
 }
 
+#define min_heap_push(_heap, _element, _func, _args)	\
+	__min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
+
+/* Remove ith element from the heap, O(log2(nr)). */
+static __always_inline
+bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
+		const struct min_heap_callbacks *func, void *args)
+{
+	void *data = heap->data;
+
+	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
+		return false;
+
+	/* Place last element at the root (position 0) and then sift down. */
+	heap->nr--;
+	if (idx == heap->nr)
+		return true;
+	func->swp(data + (idx * elem_size), data + (heap->nr * elem_size), args);
+	__min_heap_sift_up(heap, elem_size, idx, func, args);
+	__min_heap_sift_down(heap, idx, elem_size, func, args);
+
+	return true;
+}
+
+#define min_heap_del(_heap, _idx, _func, _args)	\
+	__min_heap_del((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+
 #endif /* _LINUX_MIN_HEAP_H */

include/linux/msi.h

@@ -19,7 +19,7 @@
  */
 
 #include <linux/irqdomain_defs.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/msi_api.h>
 #include <linux/xarray.h>
 #include <linux/mutex.h>

include/linux/node.h

@@ -16,7 +16,6 @@
 #define _LINUX_NODE_H_
 
 #include <linux/device.h>
-#include <linux/cpumask.h>
 #include <linux/list.h>
 
 /**

include/linux/nvme-fc-driver.h

@@ -620,7 +620,7 @@ enum {
  *
  * Structure used between LLDD and nvmet-fc layer to represent the exchange
  * context for a FC-NVME FCP I/O operation (e.g. a nvme sqe, the sqe-related
- * memory transfers, and its assocated cqe transfer).
+ * memory transfers, and its associated cqe transfer).
  *
  * The structure is allocated by the LLDD whenever a FCP CMD IU is received
  * from the FC link. The address of the structure is passed to the nvmet-fc

include/linux/panic.h

@@ -77,9 +77,10 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
 #define TAINT_FLAGS_MAX			((1UL << TAINT_FLAGS_COUNT) - 1)
 
 struct taint_flag {
-	char c_true;	/* character printed when tainted */
+	char c_true;		/* character printed when tainted */
-	char c_false;	/* character printed when not tainted */
+	char c_false;		/* character printed when not tainted */
-	bool module;	/* also show as a per-module taint flag */
+	bool module;		/* also show as a per-module taint flag */
+	const char *desc;	/* verbose description of the set taint flag */
 };
 
 extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT];
@@ -90,6 +91,7 @@ enum lockdep_ok {
 };
 
 extern const char *print_tainted(void);
+extern const char *print_tainted_verbose(void);
 extern void add_taint(unsigned flag, enum lockdep_ok);
 extern int test_taint(unsigned flag);
 extern unsigned long get_taint(void);

include/linux/percpu.h

@@ -6,7 +6,6 @@
 #include <linux/mmdebug.h>
 #include <linux/preempt.h>
 #include <linux/smp.h>
-#include <linux/cpumask.h>
 #include <linux/pfn.h>
 #include <linux/init.h>
 #include <linux/cleanup.h>

include/linux/pm_domain.h

@@ -16,7 +16,7 @@
 #include <linux/of.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/time64.h>
 
 /*

include/linux/poison.h

@@ -49,12 +49,6 @@
 /********** arch/$ARCH/mm/init.c **********/
 #define POISON_FREE_INITMEM	0xcc
 
-/********** arch/ia64/hp/common/sba_iommu.c **********/
-/*
- * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
- * value of "SBAIOMMU POISON\0" for spill-over poisoning.
- */
-
 /********** fs/jbd/journal.c **********/
 #define JBD_POISON_FREE		0x5b
 #define JBD2_POISON_FREE	0x5c

include/linux/profile.h

@@ -4,7 +4,6 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/cpumask.h>
 #include <linux/cache.h>
 
 #include <asm/errno.h>

include/linux/rcupdate.h

@@ -29,7 +29,6 @@
 #include <linux/lockdep.h>
 #include <linux/cleanup.h>
 #include <asm/processor.h>
-#include <linux/cpumask.h>
 #include <linux/context_tracking_irq.h>
 
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))

include/linux/sched.h

@@ -13,7 +13,7 @@
 #include <asm/processor.h>
 #include <linux/thread_info.h>
 #include <linux/preempt.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 
 #include <linux/cache.h>
 #include <linux/irqflags_types.h>
@@ -1618,7 +1618,7 @@ static inline char task_index_to_char(unsigned int state)
 {
 	static const char state_char[] = "RSDTtXZPI";
 
-	BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
+	BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1));
 
 	return state_char[state];
 }
@@ -1792,7 +1792,8 @@ static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpuma
 }
 static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-	if (!cpumask_test_cpu(0, new_mask))
+	/* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */
+	if ((*cpumask_bits(new_mask) & 1) == 0)
 		return -EINVAL;
 	return 0;
 }

include/linux/seq_file.h

@@ -7,7 +7,6 @@
 #include <linux/string_helpers.h>
 #include <linux/bug.h>
 #include <linux/mutex.h>
-#include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/fs.h>
 #include <linux/cred.h>

include/linux/soc/apple/rtkit.h

@@ -69,7 +69,7 @@ struct apple_rtkit;
  * Initializes the internal state required to handle RTKit. This
  * should usually be called within _probe.
  *
- * @dev:         Pointer to the device node this coprocessor is assocated with
+ * @dev:         Pointer to the device node this coprocessor is associated with
  * @cookie:      opaque cookie passed to all functions defined in rtkit_ops
  * @mbox_name:   mailbox name used to communicate with the co-processor
  * @mbox_idx:    mailbox index to be used if mbox_name is NULL
@@ -83,7 +83,7 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie,
  * Non-devm version of devm_apple_rtkit_init. Must be freed with
  * apple_rtkit_free.
  *
- * @dev:         Pointer to the device node this coprocessor is assocated with
+ * @dev:         Pointer to the device node this coprocessor is associated with
  * @cookie:      opaque cookie passed to all functions defined in rtkit_ops
  * @mbox_name:   mailbox name used to communicate with the co-processor
  * @mbox_idx:    mailbox index to be used if mbox_name is NULL

include/linux/stop_machine.h

@@ -3,7 +3,7 @@
 #define _LINUX_STOP_MACHINE
 
 #include <linux/cpu.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/smp.h>
 #include <linux/list.h>
 

include/linux/torture.h

@@ -14,7 +14,7 @@
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/threads.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
 #include <linux/completion.h>

include/linux/tracepoint.h

@@ -16,7 +16,6 @@
 #include <linux/srcu.h>
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/static_call.h>

include/linux/workqueue.h

@@ -12,7 +12,7 @@
 #include <linux/lockdep.h>
 #include <linux/threads.h>
 #include <linux/atomic.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/rcupdate.h>
 #include <linux/workqueue_types.h>
 

kernel/backtracetest.c

@@ -74,5 +74,6 @@ static void exitf(void)
 
 module_init(backtrace_regression_test);
 module_exit(exitf);
+MODULE_DESCRIPTION("Simple stack backtrace regression test module");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");

kernel/crash_reserve.c

@@ -13,7 +13,6 @@
 #include <linux/memory.h>
 #include <linux/cpuhotplug.h>
 #include <linux/memblock.h>
-#include <linux/kexec.h>
 #include <linux/kmemleak.h>
 
 #include <asm/page.h>

kernel/events/core.c

@@ -534,7 +534,7 @@ void perf_sample_event_took(u64 sample_len_ns)
 	__this_cpu_write(running_sample_length, running_len);
 
 	/*
-	 * Note: this will be biased artifically low until we have
+	 * Note: this will be biased artificially low until we have
 	 * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us
 	 * from having to maintain a count.
 	 */
@@ -596,10 +596,10 @@ static inline u64 perf_event_clock(struct perf_event *event)
  *
  * Event groups make things a little more complicated, but not terribly so. The
  * rules for a group are that if the group leader is OFF the entire group is
- * OFF, irrespecive of what the group member states are. This results in
+ * OFF, irrespective of what the group member states are. This results in
  * __perf_effective_state().
  *
- * A futher ramification is that when a group leader flips between OFF and
+ * A further ramification is that when a group leader flips between OFF and
  * !OFF, we need to update all group member times.
  *
  *
@@ -891,7 +891,7 @@ static int perf_cgroup_ensure_storage(struct perf_event *event,
 	int cpu, heap_size, ret = 0;
 
 	/*
-	 * Allow storage to have sufficent space for an iterator for each
+	 * Allow storage to have sufficient space for an iterator for each
 	 * possibly nested cgroup plus an iterator for events with no cgroup.
 	 */
 	for (heap_size = 1; css; css = css->parent)
@@ -3671,7 +3671,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	perf_cgroup_switch(next);
 }
 
-static bool perf_less_group_idx(const void *l, const void *r)
+static bool perf_less_group_idx(const void *l, const void *r, void __always_unused *args)
 {
 	const struct perf_event *le = *(const struct perf_event **)l;
 	const struct perf_event *re = *(const struct perf_event **)r;
@@ -3679,20 +3679,21 @@ static bool perf_less_group_idx(const void *l, const void *r)
 	return le->group_index < re->group_index;
 }
 
-static void swap_ptr(void *l, void *r)
+static void swap_ptr(void *l, void *r, void __always_unused *args)
 {
 	void **lp = l, **rp = r;
 
 	swap(*lp, *rp);
 }
 
+DEFINE_MIN_HEAP(struct perf_event *, perf_event_min_heap);
+
 static const struct min_heap_callbacks perf_min_heap = {
-	.elem_size = sizeof(struct perf_event *),
 	.less = perf_less_group_idx,
 	.swp = swap_ptr,
 };
 
-static void __heap_add(struct min_heap *heap, struct perf_event *event)
+static void __heap_add(struct perf_event_min_heap *heap, struct perf_event *event)
 {
 	struct perf_event **itrs = heap->data;
 
@@ -3726,7 +3727,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 	struct perf_cpu_context *cpuctx = NULL;
 	/* Space for per CPU and/or any CPU event iterators. */
 	struct perf_event *itrs[2];
-	struct min_heap event_heap;
+	struct perf_event_min_heap event_heap;
 	struct perf_event **evt;
 	int ret;
 
@@ -3735,7 +3736,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 
 	if (!ctx->task) {
 		cpuctx = this_cpu_ptr(&perf_cpu_context);
-		event_heap = (struct min_heap){
+		event_heap = (struct perf_event_min_heap){
 			.data = cpuctx->heap,
 			.nr = 0,
 			.size = cpuctx->heap_size,
@@ -3748,7 +3749,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 			css = &cpuctx->cgrp->css;
 #endif
 	} else {
-		event_heap = (struct min_heap){
+		event_heap = (struct perf_event_min_heap){
 			.data = itrs,
 			.nr = 0,
 			.size = ARRAY_SIZE(itrs),
@@ -3770,7 +3771,7 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 		perf_assert_pmu_disabled((*evt)->pmu_ctx->pmu);
 	}
 
-	min_heapify_all(&event_heap, &perf_min_heap);
+	min_heapify_all(&event_heap, &perf_min_heap, NULL);
 
 	while (event_heap.nr) {
 		ret = func(*evt, data);
@@ -3779,9 +3780,9 @@ static noinline int visit_groups_merge(struct perf_event_context *ctx,
 
 		*evt = perf_event_groups_next(*evt, pmu);
 		if (*evt)
-			min_heapify(&event_heap, 0, &perf_min_heap);
+			min_heap_sift_down(&event_heap, 0, &perf_min_heap, NULL);
 		else
-			min_heap_pop(&event_heap, &perf_min_heap);
+			min_heap_pop(&event_heap, &perf_min_heap, NULL);
 	}
 
 	return 0;

kernel/fork.c

@@ -208,9 +208,10 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
 	unsigned int i;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
-		if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL)
+		struct vm_struct *tmp = NULL;
-			continue;
+
-		return true;
+		if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm))
+			return true;
 	}
 	return false;
 }

kernel/hung_task.c

@@ -127,7 +127,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	 * Ok, the task did not get scheduled for more than 2 minutes,
 	 * complain:
 	 */
-	if (sysctl_hung_task_warnings) {
+	if (sysctl_hung_task_warnings || hung_task_call_panic) {
 		if (sysctl_hung_task_warnings > 0)
 			sysctl_hung_task_warnings--;
 		pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",

kernel/panic.c

@@ -35,6 +35,7 @@
 #include <linux/debugfs.h>
 #include <linux/sysfs.h>
 #include <linux/context_tracking.h>
+#include <linux/seq_buf.h>
 #include <trace/events/error_report.h>
 #include <asm/sections.h>
 
@@ -470,32 +471,83 @@ void panic(const char *fmt, ...)
 
 EXPORT_SYMBOL(panic);
 
+#define TAINT_FLAG(taint, _c_true, _c_false, _module)			\
+	[ TAINT_##taint ] = {						\
+		.c_true = _c_true, .c_false = _c_false,			\
+		.module = _module,					\
+		.desc = #taint,						\
+	}
+
 /*
  * TAINT_FORCED_RMMOD could be a per-module flag but the module
  * is being removed anyway.
  */
 const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
-	[ TAINT_PROPRIETARY_MODULE ]	= { 'P', 'G', true },
+	TAINT_FLAG(PROPRIETARY_MODULE,		'P', 'G', true),
-	[ TAINT_FORCED_MODULE ]		= { 'F', ' ', true },
+	TAINT_FLAG(FORCED_MODULE,		'F', ' ', true),
-	[ TAINT_CPU_OUT_OF_SPEC ]	= { 'S', ' ', false },
+	TAINT_FLAG(CPU_OUT_OF_SPEC,		'S', ' ', false),
-	[ TAINT_FORCED_RMMOD ]		= { 'R', ' ', false },
+	TAINT_FLAG(FORCED_RMMOD,		'R', ' ', false),
-	[ TAINT_MACHINE_CHECK ]		= { 'M', ' ', false },
+	TAINT_FLAG(MACHINE_CHECK,		'M', ' ', false),
-	[ TAINT_BAD_PAGE ]		= { 'B', ' ', false },
+	TAINT_FLAG(BAD_PAGE,			'B', ' ', false),
-	[ TAINT_USER ]			= { 'U', ' ', false },
+	TAINT_FLAG(USER,			'U', ' ', false),
-	[ TAINT_DIE ]			= { 'D', ' ', false },
+	TAINT_FLAG(DIE,				'D', ' ', false),
-	[ TAINT_OVERRIDDEN_ACPI_TABLE ]	= { 'A', ' ', false },
+	TAINT_FLAG(OVERRIDDEN_ACPI_TABLE,	'A', ' ', false),
-	[ TAINT_WARN ]			= { 'W', ' ', false },
+	TAINT_FLAG(WARN,			'W', ' ', false),
-	[ TAINT_CRAP ]			= { 'C', ' ', true },
+	TAINT_FLAG(CRAP,			'C', ' ', true),
-	[ TAINT_FIRMWARE_WORKAROUND ]	= { 'I', ' ', false },
+	TAINT_FLAG(FIRMWARE_WORKAROUND,		'I', ' ', false),
-	[ TAINT_OOT_MODULE ]		= { 'O', ' ', true },
+	TAINT_FLAG(OOT_MODULE,			'O', ' ', true),
-	[ TAINT_UNSIGNED_MODULE ]	= { 'E', ' ', true },
+	TAINT_FLAG(UNSIGNED_MODULE,		'E', ' ', true),
-	[ TAINT_SOFTLOCKUP ]		= { 'L', ' ', false },
+	TAINT_FLAG(SOFTLOCKUP,			'L', ' ', false),
-	[ TAINT_LIVEPATCH ]		= { 'K', ' ', true },
+	TAINT_FLAG(LIVEPATCH,			'K', ' ', true),
-	[ TAINT_AUX ]			= { 'X', ' ', true },
+	TAINT_FLAG(AUX,				'X', ' ', true),
-	[ TAINT_RANDSTRUCT ]		= { 'T', ' ', true },
+	TAINT_FLAG(RANDSTRUCT,			'T', ' ', true),
-	[ TAINT_TEST ]			= { 'N', ' ', true },
+	TAINT_FLAG(TEST,			'N', ' ', true),
 };
 
+#undef TAINT_FLAG
+
+static void print_tainted_seq(struct seq_buf *s, bool verbose)
+{
+	const char *sep = "";
+	int i;
+
+	if (!tainted_mask) {
+		seq_buf_puts(s, "Not tainted");
+		return;
+	}
+
+	seq_buf_printf(s, "Tainted: ");
+	for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
+		const struct taint_flag *t = &taint_flags[i];
+		bool is_set = test_bit(i, &tainted_mask);
+		char c = is_set ? t->c_true : t->c_false;
+
+		if (verbose) {
+			if (is_set) {
+				seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc);
+				sep = ", ";
+			}
+		} else {
+			seq_buf_putc(s, c);
+		}
+	}
+}
+
+static const char *_print_tainted(bool verbose)
+{
+	/* FIXME: what should the size be? */
+	static char buf[sizeof(taint_flags)];
+	struct seq_buf s;
+
+	BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT);
+
+	seq_buf_init(&s, buf, sizeof(buf));
+
+	print_tainted_seq(&s, verbose);
+
+	return seq_buf_str(&s);
+}
+
 /**
  * print_tainted - return a string to represent the kernel taint state.
  *
@@ -506,25 +558,15 @@ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
  */
 const char *print_tainted(void)
 {
-	static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")];
+	return _print_tainted(false);
+}
 
-	BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT);
+/**
-
+ * print_tainted_verbose - A more verbose version of print_tainted()
-	if (tainted_mask) {
+ */
-		char *s;
+const char *print_tainted_verbose(void)
-		int i;
+{
-
+	return _print_tainted(true);
-		s = buf + sprintf(buf, "Tainted: ");
-		for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
-			const struct taint_flag *t = &taint_flags[i];
-			*s++ = test_bit(i, &tainted_mask) ?
-					t->c_true : t->c_false;
-		}
-		*s = 0;
-	} else
-		snprintf(buf, sizeof(buf), "Not tainted");
-
-	return buf;
 }
 
 int test_taint(unsigned flag)

kernel/resource_kunit.c

@@ -149,4 +149,5 @@ static struct kunit_suite resource_test_suite = {
 };
 kunit_test_suite(resource_test_suite);
 
+MODULE_DESCRIPTION("I/O Port & Memory Resource manager unit tests");
 MODULE_LICENSE("GPL");

kernel/tsacct.c

@@ -76,7 +76,7 @@ void bacct_add_tsk(struct user_namespace *user_ns,
 	stats->ac_minflt = tsk->min_flt;
 	stats->ac_majflt = tsk->maj_flt;
 
-	strncpy(stats->ac_comm, tsk->comm, sizeof(stats->ac_comm));
+	strscpy_pad(stats->ac_comm, tsk->comm);
 }
 
 

kernel/watchdog_perf.c

@@ -75,11 +75,15 @@ static bool watchdog_check_timestamp(void)
 	__this_cpu_write(last_timestamp, now);
 	return true;
 }
-#else
+
-static inline bool watchdog_check_timestamp(void)
+static void watchdog_init_timestamp(void)
 {
-	return true;
+	__this_cpu_write(nmi_rearmed, 0);
+	__this_cpu_write(last_timestamp, ktime_get_mono_fast_ns());
 }
+#else
+static inline bool watchdog_check_timestamp(void) { return true; }
+static inline void watchdog_init_timestamp(void) { }
 #endif
 
 static struct perf_event_attr wd_hw_attr = {
@@ -161,6 +165,7 @@ void watchdog_hardlockup_enable(unsigned int cpu)
 	if (!atomic_fetch_inc(&watchdog_cpus))
 		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
 
+	watchdog_init_timestamp();
 	perf_event_enable(this_cpu_read(watchdog_ev));
 }
 

lib/Kconfig.debug

@@ -1043,7 +1043,9 @@ config PANIC_TIMEOUT
 	  Set the timeout value (in seconds) until a reboot occurs when
 	  the kernel panics. If n = 0, then we wait forever. A timeout
 	  value n > 0 will wait n seconds before rebooting, while a timeout
-	  value n < 0 will reboot immediately.
+	  value n < 0 will reboot immediately. This setting can be overridden
+	  with the kernel command line option panic=, and from userspace via
+	  /proc/sys/kernel/panic.
 
 config LOCKUP_DETECTOR
 	bool

lib/asn1_encoder.c

@@ -449,4 +449,5 @@ asn1_encode_boolean(unsigned char *data, const unsigned char *end_data,
 }
 EXPORT_SYMBOL_GPL(asn1_encode_boolean);
 
+MODULE_DESCRIPTION("Simple encoder primitives for ASN.1 BER/DER/CER");
 MODULE_LICENSE("GPL");

lib/atomic64_test.c

@@ -273,4 +273,5 @@ static __exit void test_atomics_exit(void) {}
 module_init(test_atomics_init);
 module_exit(test_atomics_exit);
 
+MODULE_DESCRIPTION("Testsuite for atomic64_t functions");
 MODULE_LICENSE("GPL");

lib/bch.c

@@ -479,11 +479,8 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
 		/* find suitable row for elimination */
 		for (r = p; r < m; r++) {
 			if (rows[r] & mask) {
-				if (r != p) {
+				if (r != p)
-					tmp = rows[r];
+					swap(rows[r], rows[p]);
-					rows[r] = rows[p];
-					rows[p] = tmp;
-				}
 				rem = r+1;
 				break;
 			}
@@ -799,21 +796,14 @@ static void gf_poly_div(struct bch_control *bch, struct gf_poly *a,
 static struct gf_poly *gf_poly_gcd(struct bch_control *bch, struct gf_poly *a,
 				   struct gf_poly *b)
 {
-	struct gf_poly *tmp;
-
 	dbg("gcd(%s,%s)=", gf_poly_str(a), gf_poly_str(b));
 
-	if (a->deg < b->deg) {
+	if (a->deg < b->deg)
-		tmp = b;
+		swap(a, b);
-		b = a;
-		a = tmp;
-	}
 
 	while (b->deg > 0) {
 		gf_poly_mod(bch, a, b, NULL);
-		tmp = b;
+		swap(a, b);
-		b = a;
-		a = tmp;
 	}
 
 	dbg("%s\n", gf_poly_str(a));

lib/bitfield_kunit.c

@@ -151,4 +151,5 @@ static struct kunit_suite bitfields_test_suite = {
 kunit_test_suites(&bitfields_test_suite);
 
 MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>");
+MODULE_DESCRIPTION("Test cases for bitfield helpers");
 MODULE_LICENSE("GPL");

lib/buildid.c

@@ -73,6 +73,13 @@ static int get_build_id_32(const void *page_addr, unsigned char *build_id,
 	Elf32_Phdr *phdr;
 	int i;
 
+	/*
+	 * FIXME
+	 * Neither ELF spec nor ELF loader require that program headers
+	 * start immediately after ELF header.
+	 */
+	if (ehdr->e_phoff != sizeof(Elf32_Ehdr))
+		return -EINVAL;
 	/* only supports phdr that fits in one page */
 	if (ehdr->e_phnum >
 	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
@@ -98,6 +105,13 @@ static int get_build_id_64(const void *page_addr, unsigned char *build_id,
 	Elf64_Phdr *phdr;
 	int i;
 
+	/*
+	 * FIXME
+	 * Neither ELF spec nor ELF loader require that program headers
+	 * start immediately after ELF header.
+	 */
+	if (ehdr->e_phoff != sizeof(Elf64_Ehdr))
+		return -EINVAL;
 	/* only supports phdr that fits in one page */
 	if (ehdr->e_phnum >
 	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))

lib/checksum_kunit.c

@@ -639,4 +639,5 @@ static struct kunit_suite checksum_test_suite = {
 kunit_test_suites(&checksum_test_suite);
 
 MODULE_AUTHOR("Noah Goldstein <goldstein.w.n@gmail.com>");
+MODULE_DESCRIPTION("Test cases csum_* APIs");
 MODULE_LICENSE("GPL");

lib/cmdline_kunit.c

@@ -153,4 +153,5 @@ static struct kunit_suite cmdline_test_suite = {
 };
 kunit_test_suite(cmdline_test_suite);
 
+MODULE_DESCRIPTION("Test cases for API provided by cmdline.c");
 MODULE_LICENSE("GPL");

lib/dhry_run.c

@@ -83,4 +83,5 @@ static int __init dhry_init(void)
 module_init(dhry_init);
 
 MODULE_AUTHOR("Geert Uytterhoeven <geert+renesas@glider.be>");
+MODULE_DESCRIPTION("Dhrystone benchmark test module");
 MODULE_LICENSE("GPL");

lib/dump_stack.c

@@ -54,14 +54,19 @@ void __init dump_stack_set_arch_desc(const char *fmt, ...)
  */
 void dump_stack_print_info(const char *log_lvl)
 {
-	printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n",
+	printk("%sCPU: %d UID: %u PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n",
-	       log_lvl, raw_smp_processor_id(), current->pid, current->comm,
+	       log_lvl, raw_smp_processor_id(),
+	       __kuid_val(current_real_cred()->euid),
+	       current->pid, current->comm,
 	       kexec_crash_loaded() ? "Kdump: loaded " : "",
 	       print_tainted(),
 	       init_utsname()->release,
 	       (int)strcspn(init_utsname()->version, " "),
 	       init_utsname()->version, BUILD_ID_VAL);
 
+	if (get_taint())
+		printk("%s%s\n", log_lvl, print_tainted_verbose());
+
 	if (dump_stack_arch_desc_str[0] != '\0')
 		printk("%sHardware name: %s\n",
 		       log_lvl, dump_stack_arch_desc_str);

lib/fortify_kunit.c

@@ -1093,4 +1093,5 @@ static struct kunit_suite fortify_test_suite = {
 
 kunit_test_suite(fortify_test_suite);
 
+MODULE_DESCRIPTION("Runtime test cases for CONFIG_FORTIFY_SOURCE");
 MODULE_LICENSE("GPL");

lib/hashtable_test.c

@@ -314,4 +314,5 @@ static struct kunit_suite hashtable_test_module = {
 
 kunit_test_suites(&hashtable_test_module);
 
+MODULE_DESCRIPTION("KUnit test for the Kernel Hashtable structures");
 MODULE_LICENSE("GPL");

lib/is_signed_type_kunit.c

@@ -46,4 +46,5 @@ static struct kunit_suite is_signed_type_test_suite = {
 
 kunit_test_suite(is_signed_type_test_suite);
 
+MODULE_DESCRIPTION("is_signed_type() KUnit test suite");
 MODULE_LICENSE("Dual MIT/GPL");

lib/math/rational.c

@@ -108,4 +108,5 @@ void rational_best_approximation(
 
 EXPORT_SYMBOL(rational_best_approximation);
 
+MODULE_DESCRIPTION("Rational fraction support library");
 MODULE_LICENSE("GPL v2");

lib/memcpy_kunit.c

@@ -510,4 +510,5 @@ static struct kunit_suite memcpy_test_suite = {
 
 kunit_test_suite(memcpy_test_suite);
 
+MODULE_DESCRIPTION("test cases for memcpy(), memmove(), and memset()");
 MODULE_LICENSE("GPL");

lib/overflow_kunit.c

@@ -1237,4 +1237,5 @@ static struct kunit_suite overflow_test_suite = {
 
 kunit_test_suite(overflow_test_suite);
 
+MODULE_DESCRIPTION("Test cases for arithmetic overflow checks");
 MODULE_LICENSE("Dual MIT/GPL");

lib/percpu_counter.c

@@ -73,17 +73,50 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 EXPORT_SYMBOL(percpu_counter_set);
 
 /*
- * local_irq_save() is needed to make the function irq safe:
+ * Add to a counter while respecting batch size.
- * - The slow path would be ok as protected by an irq-safe spinlock.
+ *
- * - this_cpu_add would be ok as it is irq-safe by definition.
+ * There are 2 implementations, both dealing with the following problem:
- * But:
+ *
- * The decision slow path/fast path and the actual update must be atomic, too.
+ * The decision slow path/fast path and the actual update must be atomic.
  * Otherwise a call in process context could check the current values and
  * decide that the fast path can be used. If now an interrupt occurs before
  * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters),
  * then the this_cpu_add() that is executed after the interrupt has completed
  * can produce values larger than "batch" or even overflows.
  */
+#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
+/*
+ * Safety against interrupts is achieved in 2 ways:
+ * 1. the fast path uses local cmpxchg (note: no lock prefix)
+ * 2. the slow path operates with interrupts disabled
+ */
+void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
+{
+	s64 count;
+	unsigned long flags;
+
+	count = this_cpu_read(*fbc->counters);
+	do {
+		if (unlikely(abs(count + amount) >= batch)) {
+			raw_spin_lock_irqsave(&fbc->lock, flags);
+			/*
+			 * Note: by now we might have migrated to another CPU
+			 * or the value might have changed.
+			 */
+			count = __this_cpu_read(*fbc->counters);
+			fbc->count += count + amount;
+			__this_cpu_sub(*fbc->counters, count);
+			raw_spin_unlock_irqrestore(&fbc->lock, flags);
+			return;
+		}
+	} while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount));
+}
+#else
+/*
+ * local_irq_save() is used to make the function irq safe:
+ * - The slow path would be ok as protected by an irq-safe spinlock.
+ * - this_cpu_add would be ok as it is irq-safe by definition.
+ */
 void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
 	s64 count;
@@ -101,6 +134,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 	}
 	local_irq_restore(flags);
 }
+#endif
 EXPORT_SYMBOL(percpu_counter_add_batch);
 
 /*