June 2025 - Linux-stable-mirror

[merged mm-hotfixes-stable] revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: Revert "bcache: remove heap-related macros and switch to generic min_heap" has been removed from the -mm tree. Its filename was revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kuan-Wei Chiu <visitorckw(a)gmail.com> Subject: Revert "bcache: remove heap-related macros and switch to generic min_heap" Date: Sun, 15 Jun 2025 04:23:52 +0800 This reverts commit 866898efbb25bb44fd42848318e46db9e785973a. The generic bottom-up min_heap implementation causes performance regression in invalidate_buckets_lru(), a hot path in bcache. Before the cache is fully populated, new_bucket_prio() often returns zero, leading to many equal comparisons. In such cases, bottom-up sift_down performs up to 2 * log2(n) comparisons, while the original top-down approach completes with just O() comparisons, resulting in a measurable performance gap. The performance degradation is further worsened by the non-inlined min_heap API functions introduced in commit 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions"), adding function call overhead to this critical path. As reported by Robert, bcache now suffers from latency spikes, with P100 (max) latency increasing from 600 ms to 2.4 seconds every 5 minutes. These regressions degrade bcache's effectiveness as a low-latency cache layer and lead to frequent timeouts and application stalls in production environments. This revert aims to restore bcache's original low-latency behavior. Link: https://lore.kernel.org/lkml/CAJhEC05+0S69z+3+FB2Cd0hD+pCRyWTKLEOsc8BOmH73p… Link: https://lkml.kernel.org/r/20250614202353.1632957-3-visitorckw@gmail.com Fixes: 866898efbb25 ("bcache: remove heap-related macros and switch to generic min_heap") Fixes: 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions") Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Reported-by: Robert Pang <robertpang(a)google.com> Closes: https://lore.kernel.org/linux-bcache/CAJhEC06F_AtrPgw2-7CvCqZgeStgCtitbD-ry… Acked-by: Coly Li <colyli(a)kernel.org> Cc: Ching-Chun (Jim) Huang <jserv(a)ccns.ncku.edu.tw> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- drivers/md/bcache/alloc.c | 64 ++++------------ drivers/md/bcache/bcache.h | 2 drivers/md/bcache/bset.c | 124 +++++++++++--------------------- drivers/md/bcache/bset.h | 42 ++++++---- drivers/md/bcache/btree.c | 69 +++++++---------- drivers/md/bcache/extents.c | 51 ++++--------- drivers/md/bcache/movinggc.c | 41 ++-------- drivers/md/bcache/super.c | 3 drivers/md/bcache/sysfs.c | 4 - drivers/md/bcache/util.h | 67 ++++++++++++++++- drivers/md/bcache/writeback.c | 13 +-- 11 files changed, 217 insertions(+), 263 deletions(-) --- a/drivers/md/bcache/alloc.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/alloc.c @@ -164,68 +164,40 @@ static void bch_invalidate_one_bucket(st * prio is worth 1/8th of what INITIAL_PRIO is worth. */ -static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b) -{ - unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; - - return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); -} - -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; +#define bucket_prio(b) \ +({ \ + unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \ + \ + (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); \ +}) - swap(*lhs, *rhs); -} +#define bucket_max_cmp(l, r) (bucket_prio(l) < bucket_prio(r)) +#define bucket_min_cmp(l, r) (bucket_prio(l) > bucket_prio(r)) static void invalidate_buckets_lru(struct cache *ca) { struct bucket *b; - 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, - }; + ssize_t i; - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (!bch_can_invalidate_bucket(ca, b)) continue; - if (!min_heap_full(&ca->heap)) - min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca); - else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) { + if (!heap_full(&ca->heap)) + heap_add(&ca->heap, b, bucket_max_cmp); + else if (bucket_max_cmp(b, heap_peek(&ca->heap))) { ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca); + heap_sift(&ca->heap, 0, bucket_max_cmp); } } - min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca); + for (i = ca->heap.used / 2 - 1; i >= 0; --i) + heap_sift(&ca->heap, i, bucket_min_cmp); while (!fifo_full(&ca->free_inc)) { - if (!ca->heap.nr) { + if (!heap_pop(&ca->heap, b, bucket_min_cmp)) { /* * We don't want to be calling invalidate_buckets() * multiple times when it can't do anything @@ -234,8 +206,6 @@ static void invalidate_buckets_lru(struc 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); } --- a/drivers/md/bcache/bcache.h~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/bcache.h @@ -458,7 +458,7 @@ struct cache { /* Allocation stuff: */ struct bucket *buckets; - DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap; + DECLARE_HEAP(struct bucket *, heap); /* * If nonzero, we know we aren't going to find any buckets to invalidate --- a/drivers/md/bcache/bset.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/bset.c @@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys * int __bch_count_data(struct btree_keys *b) { unsigned int ret = 0; - struct btree_iter iter; + struct btree_iter_stack 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); @@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys { va_list args; struct bkey *k, *p = NULL; - struct btree_iter iter; + struct btree_iter_stack 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"; @@ -114,9 +110,9 @@ bug: static void bch_btree_iter_next_check(struct btree_iter *iter) { - struct bkey *k = iter->heap.data->k, *next = bkey_next(k); + struct bkey *k = iter->data->k, *next = bkey_next(k); - if (next < iter->heap.data->end && + if (next < iter->data->end && bkey_cmp(k, iter->b->ops->is_extents ? &START_KEY(next) : next) > 0) { bch_dump_bucket(iter->b); @@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct unsigned int status = BTREE_INSERT_STATUS_NO_INSERT; struct bset *i = bset_tree_last(b)->data; struct bkey *m, *prev = NULL; - struct btree_iter iter; + struct btree_iter_stack 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 @@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct else preceding_key(k, &preceding_key_p); - m = bch_btree_iter_init(b, &iter, preceding_key_p); + m = bch_btree_iter_stack_init(b, &iter, preceding_key_p); - if (b->ops->insert_fixup(b, k, &iter, replace_key)) + if (b->ops->insert_fixup(b, k, &iter.iter, replace_key)) return status; status = BTREE_INSERT_STATUS_INSERT; @@ -1083,102 +1077,79 @@ struct bkey *__bch_bset_search(struct bt /* Btree iterator */ -typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *); - -static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args) -{ - const struct btree_iter_set *_l = l; - const struct btree_iter_set *_r = r; - - return bkey_cmp(_l->k, _r->k) <= 0; -} +typedef bool (btree_iter_cmp_fn)(struct btree_iter_set, + struct btree_iter_set); -static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args) +static inline bool btree_iter_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_iter1 = iter1; - struct btree_iter_set *_iter2 = iter2; - - swap(*_iter1, *_iter2); + return bkey_cmp(l.k, r.k) > 0; } static inline bool btree_iter_end(struct btree_iter *iter) { - return !iter->heap.nr; + return !iter->used; } 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(!min_heap_push(&iter->heap, - &((struct btree_iter_set) { k, end }), - &callbacks, - NULL)); + BUG_ON(!heap_add(iter, + ((struct btree_iter_set) { k, end }), + btree_iter_cmp)); } -static struct bkey *__bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search, - struct bset_tree *start) +static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search, + struct bset_tree *start) { struct bkey *ret = NULL; - iter->heap.size = ARRAY_SIZE(iter->heap.preallocated); - iter->heap.nr = 0; + iter->iter.size = ARRAY_SIZE(iter->stack_data); + iter->iter.used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter->b = b; + iter->iter.b = b; #endif for (; start <= bset_tree_last(b); start++) { ret = bch_bset_search(b, start, search); - bch_btree_iter_push(iter, ret, bset_bkey_last(start->data)); + bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data)); } return ret; } -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, struct bkey *search) { - return __bch_btree_iter_init(b, iter, search, b->set); + return __bch_btree_iter_stack_init(b, iter, search, b->set); } static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter, - new_btree_iter_cmp_fn *cmp) + 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->heap.data->k; - iter->heap.data->k = bkey_next(iter->heap.data->k); + ret = iter->data->k; + iter->data->k = bkey_next(iter->data->k); - if (iter->heap.data->k > iter->heap.data->end) { + if (iter->data->k > iter->data->end) { WARN_ONCE(1, "bset was corrupt!\n"); - iter->heap.data->k = iter->heap.data->end; + iter->data->k = iter->data->end; } - if (iter->heap.data->k == iter->heap.data->end) { - if (iter->heap.nr) { - b = min_heap_peek(&iter->heap)[0]; - min_heap_pop(&iter->heap, &callbacks, NULL); - } - } + if (iter->data->k == iter->data->end) + heap_pop(iter, b, cmp); else - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, cmp); } return ret; @@ -1186,7 +1157,7 @@ static inline struct bkey *__bch_btree_i struct bkey *bch_btree_iter_next(struct btree_iter *iter) { - return __bch_btree_iter_next(iter, new_btree_iter_cmp); + return __bch_btree_iter_next(iter, btree_iter_cmp); } @@ -1224,18 +1195,16 @@ static void btree_mergesort(struct btree 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 */ - min_heapify_all(&iter->heap, &callbacks, NULL); + for (i = iter->used / 2 - 1; i >= 0; --i) + heap_sift(iter, i, b->ops->sort_cmp); while (!btree_iter_end(iter)) { if (b->ops->sort_fixup && fixup) @@ -1324,11 +1293,10 @@ void bch_btree_sort_partial(struct btree struct bset_sort_state *state) { size_t order = b->page_order, keys = 0; - struct btree_iter iter; + struct btree_iter_stack iter; int oldsize = bch_count_data(b); - min_heap_init(&iter.heap, NULL, MAX_BSETS); - __bch_btree_iter_init(b, &iter, NULL, &b->set[start]); + __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]); if (start) { unsigned int i; @@ -1339,7 +1307,7 @@ void bch_btree_sort_partial(struct btree order = get_order(__set_bytes(b->set->data, keys)); } - __btree_sort(b, &iter, start, order, false, state); + __btree_sort(b, &iter.iter, start, order, false, state); EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize); } @@ -1355,13 +1323,11 @@ void bch_btree_sort_into(struct btree_ke struct bset_sort_state *state) { uint64_t start_time = local_clock(); - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; - bch_btree_iter_init(b, &iter, NULL); + bch_btree_iter_stack_init(b, &iter, NULL); - btree_mergesort(b, new->set->data, &iter, false, true); + btree_mergesort(b, new->set->data, &iter.iter, false, true); bch_time_stats_update(&state->time, start_time); --- a/drivers/md/bcache/bset.h~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/bset.h @@ -187,9 +187,8 @@ struct bset_tree { }; struct btree_keys_ops { - bool (*sort_cmp)(const void *l, - const void *r, - void *args); + bool (*sort_cmp)(struct btree_iter_set l, + struct btree_iter_set r); struct bkey *(*sort_fixup)(struct btree_iter *iter, struct bkey *tmp); bool (*insert_fixup)(struct btree_keys *b, @@ -313,17 +312,23 @@ 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 - MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap; + struct btree_iter_set { + 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); @@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter( void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k, struct bkey *end); -struct bkey *bch_btree_iter_init(struct btree_keys *b, - struct btree_iter *iter, - struct bkey *search); +struct bkey *bch_btree_iter_stack_init(struct btree_keys *b, + struct btree_iter_stack *iter, + struct bkey *search); struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t, const struct bkey *search); @@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_sear return search ? __bch_bset_search(b, t, search) : t->data->start; } -#define for_each_key_filter(b, k, iter, filter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next_filter((iter), (b), filter));) - -#define for_each_key(b, k, iter) \ - for (bch_btree_iter_init((b), (iter), NULL); \ - ((k) = bch_btree_iter_next(iter));) +#define for_each_key_filter(b, k, stack_iter, filter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \ + filter));) + +#define for_each_key(b, k, stack_iter) \ + for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \ + ((k) = bch_btree_iter_next(&((stack_iter)->iter)));) /* Sorting */ --- a/drivers/md/bcache/btree.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/btree.c @@ -148,19 +148,19 @@ void bch_btree_node_read_done(struct btr { 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.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO); - iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; - iter.heap.nr = 0; + iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO); + iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size; + iter->used = 0; #ifdef CONFIG_BCACHE_DEBUG - iter.b = &b->keys; + iter->b = &b->keys; #endif if (!i->seq) @@ -198,7 +198,7 @@ void bch_btree_node_read_done(struct btr 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)); } @@ -210,7 +210,7 @@ void bch_btree_node_read_done(struct btr 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"; @@ -222,7 +222,7 @@ void bch_btree_node_read_done(struct btr bch_bset_init_next(&b->keys, write_block(b), bset_magic(&b->c->cache->sb)); out: - mempool_free(iter.heap.data, &b->c->fill_iter); + mempool_free(iter, &b->c->fill_iter); return; err: set_btree_node_io_error(b); @@ -1306,11 +1306,9 @@ static bool btree_gc_mark_node(struct bt uint8_t stale = 0; unsigned int keys = 0, good_keys = 0; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack 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) { @@ -1569,11 +1567,9 @@ static int btree_gc_rewrite_node(struct static unsigned int btree_gc_count_keys(struct btree *b) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack 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); @@ -1612,18 +1608,18 @@ static int btree_gc_recurse(struct btree int ret = 0; bool should_rewrite; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; struct gc_merge_info r[GC_MERGE_NODES]; struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done); + bch_btree_iter_stack_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, &b->keys, bch_ptr_bad); + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad); if (k) { r->b = bch_btree_node_get(b->c, op, k, b->level - 1, true, b); @@ -1918,9 +1914,7 @@ static int bch_btree_check_recurse(struc { int ret = 0; struct bkey *k, *p = NULL; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) bch_initial_mark_key(b->c, b->level, k); @@ -1928,10 +1922,10 @@ static int bch_btree_check_recurse(struc bch_initial_mark_key(b->c, b->level + 1, &b->key); if (b->level) { - bch_btree_iter_init(&b->keys, &iter, NULL); + bch_btree_iter_stack_init(&b->keys, &iter, NULL); do { - k = bch_btree_iter_next_filter(&iter, &b->keys, + k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad); if (k) { btree_node_prefetch(b, k); @@ -1959,7 +1953,7 @@ static int bch_btree_check_thread(void * struct btree_check_info *info = arg; struct btree_check_state *check_state = info->state; struct cache_set *c = check_state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; @@ -1967,11 +1961,9 @@ static int bch_btree_check_thread(void * 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_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -1989,7 +1981,7 @@ static int bch_btree_check_thread(void * skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -2062,11 +2054,9 @@ int bch_btree_check(struct cache_set *c) int ret = 0; int i; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack 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); @@ -2560,12 +2550,11 @@ static int bch_btree_map_nodes_recurse(s if (b->level) { struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, bch_ptr_bad))) { ret = bcache_btree(map_nodes_recurse, k, b, op, from, fn, flags); @@ -2594,12 +2583,12 @@ int bch_btree_map_keys_recurse(struct bt { int ret = MAP_CONTINUE; struct bkey *k; - struct btree_iter iter; + struct btree_iter_stack iter; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&b->keys, &iter, from); + bch_btree_iter_stack_init(&b->keys, &iter, from); - while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) { + while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys, + bch_ptr_bad))) { ret = !b->level ? fn(op, b, k) : bcache_btree(map_keys_recurse, k, --- a/drivers/md/bcache/extents.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/extents.c @@ -33,16 +33,15 @@ static void sort_key_next(struct btree_i i->k = bkey_next(i->k); if (i->k == i->end) - *i = iter->heap.data[--iter->heap.nr]; + *i = iter->data[--iter->used]; } -static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args) +static bool bch_key_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - 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); + 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) @@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(s } const struct btree_keys_ops bch_btree_keys_ops = { - .sort_cmp = new_bch_key_sort_cmp, + .sort_cmp = bch_key_sort_cmp, .insert_fixup = bch_btree_ptr_insert_fixup, .key_invalid = bch_btree_ptr_invalid, .key_bad = bch_btree_ptr_bad, @@ -256,36 +255,22 @@ const struct btree_keys_ops bch_btree_ke * 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 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) +static bool bch_extent_sort_cmp(struct btree_iter_set l, + struct btree_iter_set r) { - struct btree_iter_set *_iter1 = iter1; - struct btree_iter_set *_iter2 = iter2; + int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k)); - swap(*_iter1, *_iter2); + return c ? c > 0 : l.k < r.k; } static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter, struct bkey *tmp) { - const struct min_heap_callbacks callbacks = { - .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; + while (iter->used > 1) { + struct btree_iter_set *top = iter->data, *i = top + 1; - if (iter->heap.nr > 2 && - !new_bch_extent_sort_cmp(&i[0], &i[1], NULL)) + if (iter->used > 2 && + bch_extent_sort_cmp(i[0], i[1])) i++; if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) @@ -293,7 +278,7 @@ static struct bkey *bch_extent_sort_fixu if (!KEY_SIZE(i->k)) { sort_key_next(iter, i); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); continue; } @@ -303,7 +288,7 @@ static struct bkey *bch_extent_sort_fixu else bch_cut_front(top->k, i->k); - min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL); + heap_sift(iter, i - top, bch_extent_sort_cmp); } else { /* can't happen because of comparison func */ BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); @@ -313,7 +298,7 @@ static struct bkey *bch_extent_sort_fixu bch_cut_back(&START_KEY(i->k), tmp); bch_cut_front(i->k, top->k); - min_heap_sift_down(&iter->heap, 0, &callbacks, NULL); + heap_sift(iter, 0, bch_extent_sort_cmp); return tmp; } else { @@ -633,7 +618,7 @@ static bool bch_extent_merge(struct btre } const struct btree_keys_ops bch_extent_keys_ops = { - .sort_cmp = new_bch_extent_sort_cmp, + .sort_cmp = bch_extent_sort_cmp, .sort_fixup = bch_extent_sort_fixup, .insert_fixup = bch_extent_insert_fixup, .key_invalid = bch_extent_invalid, --- a/drivers/md/bcache/movinggc.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/movinggc.c @@ -182,27 +182,16 @@ err: if (!IS_ERR_OR_NULL(w->private)) closure_sync(&cl); } -static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args) +static bool bucket_cmp(struct bucket *l, struct bucket *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); + return GC_SECTORS_USED(l) < GC_SECTORS_USED(r); } static unsigned int bucket_heap_top(struct cache *ca) { struct bucket *b; - return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0; + return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0; } void bch_moving_gc(struct cache_set *c) @@ -210,10 +199,6 @@ 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; @@ -224,7 +209,7 @@ void bch_moving_gc(struct cache_set *c) reserve_sectors = ca->sb.bucket_size * fifo_used(&ca->free[RESERVE_MOVINGGC]); - ca->heap.nr = 0; + ca->heap.used = 0; for_each_bucket(b, ca) { if (GC_MARK(b) == GC_MARK_METADATA || @@ -233,31 +218,25 @@ void bch_moving_gc(struct cache_set *c) atomic_read(&b->pin)) continue; - if (!min_heap_full(&ca->heap)) { + if (!heap_full(&ca->heap)) { sectors_to_move += GC_SECTORS_USED(b); - min_heap_push(&ca->heap, &b, &callbacks, NULL); - } else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) { + heap_add(&ca->heap, b, bucket_cmp); + } else if (bucket_cmp(b, heap_peek(&ca->heap))) { sectors_to_move -= bucket_heap_top(ca); sectors_to_move += GC_SECTORS_USED(b); ca->heap.data[0] = b; - min_heap_sift_down(&ca->heap, 0, &callbacks, NULL); + heap_sift(&ca->heap, 0, bucket_cmp); } } while (sectors_to_move > reserve_sectors) { - if (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); - } + heap_pop(&ca->heap, b, bucket_cmp); sectors_to_move -= GC_SECTORS_USED(b); } - while (ca->heap.nr) { - b = min_heap_peek(&ca->heap)[0]; - min_heap_pop(&ca->heap, &callbacks, NULL); + while (heap_pop(&ca->heap, b, bucket_cmp)) SET_GC_MOVE(b, 1); - } mutex_unlock(&c->bucket_lock); --- a/drivers/md/bcache/super.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/super.c @@ -1912,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(st INIT_LIST_HEAD(&c->btree_cache_freed); INIT_LIST_HEAD(&c->data_buckets); - iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * + iter_size = sizeof(struct btree_iter) + + ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) * sizeof(struct btree_iter_set); c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL); --- a/drivers/md/bcache/sysfs.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/sysfs.c @@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struc unsigned int bytes = 0; struct bkey *k; struct btree *b; - struct btree_iter iter; - - min_heap_init(&iter.heap, NULL, MAX_BSETS); + struct btree_iter_stack iter; goto lock_root; --- a/drivers/md/bcache/util.h~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/util.h @@ -9,7 +9,6 @@ #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> @@ -31,10 +30,16 @@ 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)->nr = 0; \ + (heap)->used = 0; \ (heap)->size = (_size); \ _bytes = (heap)->size * sizeof(*(heap)->data); \ (heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \ @@ -47,6 +52,64 @@ 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; \ --- a/drivers/md/bcache/writeback.c~revert-bcache-remove-heap-related-macros-and-switch-to-generic-min_heap +++ a/drivers/md/bcache/writeback.c @@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *a struct dirty_init_thrd_info *info = arg; struct bch_dirty_init_state *state = info->state; struct cache_set *c = state->c; - struct btree_iter iter; + struct btree_iter_stack iter; struct bkey *k, *p; int cur_idx, prev_idx, skip_nr; k = p = NULL; prev_idx = 0; - min_heap_init(&iter.heap, NULL, MAX_BSETS); - bch_btree_iter_init(&c->root->keys, &iter, NULL); - k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); + bch_btree_iter_stack_init(&c->root->keys, &iter, NULL); + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); BUG_ON(!k); p = k; @@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *a skip_nr = cur_idx - prev_idx; while (skip_nr) { - k = bch_btree_iter_next_filter(&iter, + k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad); if (k) @@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcach int i; struct btree *b = NULL; struct bkey *k = NULL; - struct btree_iter iter; + struct btree_iter_stack 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); _ Patches currently in -mm which might be from visitorckw(a)gmail.com are lib-math-gcd-use-static-key-to-select-implementation-at-runtime.patch riscv-optimize-gcd-code-size-when-config_riscv_isa_zbb-is-disabled.patch riscv-optimize-gcd-performance-on-risc-v-without-zbb-extension.patch

2 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: Revert "bcache: update min_heap_callbacks to use default builtin swap" has been removed from the -mm tree. Its filename was revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kuan-Wei Chiu <visitorckw(a)gmail.com> Subject: Revert "bcache: update min_heap_callbacks to use default builtin swap" Date: Sun, 15 Jun 2025 04:23:51 +0800 Patch series "bcache: Revert min_heap migration due to performance regression". This patch series reverts the migration of bcache from its original heap implementation to the generic min_heap library. While the original change aimed to simplify the code and improve maintainability, it introduced a severe performance regression in real-world scenarios. As reported by Robert, systems using bcache now suffer from periodic latency spikes, with P100 (max) latency increasing from 600 ms to 2.4 seconds every 5 minutes. This degrades bcache's value as a low-latency caching layer, and leads to frequent timeouts and application stalls in production environments. The primary cause of this regression is the behavior of the generic min_heap implementation's bottom-up sift_down, which performs up to 2 * log2(n) comparisons when many elements are equal. The original top-down variant used by bcache only required O(1) comparisons in such cases. The issue was further exacerbated by commit 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions"), which introduced non-inlined versions of the min_heap API, adding function call overhead to a performance-critical hot path. This patch (of 3): This reverts commit 3d8a9a1c35227c3f1b0bd132c9f0a80dbda07b65. Although removing the custom swap function simplified the code, this change is part of a broader migration to the generic min_heap API that introduced significant performance regressions in bcache. As reported by Robert, bcache now suffers from latency spikes, with P100 (max) latency increasing from 600 ms to 2.4 seconds every 5 minutes. These regressions degrade bcache's effectiveness as a low-latency cache layer and lead to frequent timeouts and application stalls in production environments. This revert is part of a series of changes to restore previous performance by undoing the min_heap transition. Link: https://lkml.kernel.org/r/20250614202353.1632957-1-visitorckw@gmail.com Link: https://lore.kernel.org/lkml/CAJhEC05+0S69z+3+FB2Cd0hD+pCRyWTKLEOsc8BOmH73p… Link: https://lkml.kernel.org/r/20250614202353.1632957-2-visitorckw@gmail.com Fixes: 866898efbb25 ("bcache: remove heap-related macros and switch to generic min_heap") Fixes: 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions") Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Reported-by: Robert Pang <robertpang(a)google.com> Closes: https://lore.kernel.org/linux-bcache/CAJhEC06F_AtrPgw2-7CvCqZgeStgCtitbD-ry… Acked-by: Coly Li <colyli(a)kernel.org> Cc: Ching-Chun (Jim) Huang <jserv(a)ccns.ncku.edu.tw> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- drivers/md/bcache/alloc.c | 11 +++++++++-- drivers/md/bcache/bset.c | 14 +++++++++++--- drivers/md/bcache/extents.c | 10 +++++++++- drivers/md/bcache/movinggc.c | 10 +++++++++- 4 files changed, 38 insertions(+), 7 deletions(-) --- a/drivers/md/bcache/alloc.c~revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap +++ a/drivers/md/bcache/alloc.c @@ -189,16 +189,23 @@ static inline bool new_bucket_min_cmp(co 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; const struct min_heap_callbacks bucket_max_cmp_callback = { .less = new_bucket_max_cmp, - .swp = NULL, + .swp = new_bucket_swap, }; const struct min_heap_callbacks bucket_min_cmp_callback = { .less = new_bucket_min_cmp, - .swp = NULL, + .swp = new_bucket_swap, }; ca->heap.nr = 0; --- a/drivers/md/bcache/bset.c~revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap +++ a/drivers/md/bcache/bset.c @@ -1093,6 +1093,14 @@ static inline bool new_btree_iter_cmp(co 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->heap.nr; @@ -1103,7 +1111,7 @@ void bch_btree_iter_push(struct btree_it { const struct min_heap_callbacks callbacks = { .less = new_btree_iter_cmp, - .swp = NULL, + .swp = new_btree_iter_swap, }; if (k != end) @@ -1149,7 +1157,7 @@ static inline struct bkey *__bch_btree_i struct bkey *ret = NULL; const struct min_heap_callbacks callbacks = { .less = cmp, - .swp = NULL, + .swp = new_btree_iter_swap, }; if (!btree_iter_end(iter)) { @@ -1223,7 +1231,7 @@ static void btree_mergesort(struct btree : bch_ptr_invalid; const struct min_heap_callbacks callbacks = { .less = b->ops->sort_cmp, - .swp = NULL, + .swp = new_btree_iter_swap, }; /* Heapify the iterator, using our comparison function */ --- a/drivers/md/bcache/extents.c~revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap +++ a/drivers/md/bcache/extents.c @@ -266,12 +266,20 @@ static bool new_bch_extent_sort_cmp(cons 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) { const struct min_heap_callbacks callbacks = { .less = new_bch_extent_sort_cmp, - .swp = NULL, + .swp = new_btree_iter_swap, }; while (iter->heap.nr > 1) { struct btree_iter_set *top = iter->heap.data, *i = top + 1; --- a/drivers/md/bcache/movinggc.c~revert-bcache-update-min_heap_callbacks-to-use-default-builtin-swap +++ a/drivers/md/bcache/movinggc.c @@ -190,6 +190,14 @@ static bool new_bucket_cmp(const void *l 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; @@ -204,7 +212,7 @@ void bch_moving_gc(struct cache_set *c) unsigned long sectors_to_move, reserve_sectors; const struct min_heap_callbacks callbacks = { .less = new_bucket_cmp, - .swp = NULL, + .swp = new_bucket_swap, }; if (!c->copy_gc_enabled) _ Patches currently in -mm which might be from visitorckw(a)gmail.com are lib-math-gcd-use-static-key-to-select-implementation-at-runtime.patch riscv-optimize-gcd-code-size-when-config_riscv_isa_zbb-is-disabled.patch riscv-optimize-gcd-performance-on-risc-v-without-zbb-extension.patch

2 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-userfaultfd-fix-race-of-userfaultfd_move-and-swap-cache.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: userfaultfd: fix race of userfaultfd_move and swap cache has been removed from the -mm tree. Its filename was mm-userfaultfd-fix-race-of-userfaultfd_move-and-swap-cache.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kairui Song <kasong(a)tencent.com> Subject: mm: userfaultfd: fix race of userfaultfd_move and swap cache Date: Wed, 4 Jun 2025 23:10:38 +0800 This commit fixes two kinds of races, they may have different results: Barry reported a BUG_ON in commit c50f8e6053b0, we may see the same BUG_ON if the filemap lookup returned NULL and folio is added to swap cache after that. If another kind of race is triggered (folio changed after lookup) we may see RSS counter is corrupted: [ 406.893936] BUG: Bad rss-counter state mm:ffff0000c5a9ddc0 type:MM_ANONPAGES val:-1 [ 406.894071] BUG: Bad rss-counter state mm:ffff0000c5a9ddc0 type:MM_SHMEMPAGES val:1 Because the folio is being accounted to the wrong VMA. I'm not sure if there will be any data corruption though, seems no. The issues above are critical already. On seeing a swap entry PTE, userfaultfd_move does a lockless swap cache lookup, and tries to move the found folio to the faulting vma. Currently, it relies on checking the PTE value to ensure that the moved folio still belongs to the src swap entry and that no new folio has been added to the swap cache, which turns out to be unreliable. While working and reviewing the swap table series with Barry, following existing races are observed and reproduced [1]: In the example below, move_pages_pte is moving src_pte to dst_pte, where src_pte is a swap entry PTE holding swap entry S1, and S1 is not in the swap cache: CPU1 CPU2 userfaultfd_move move_pages_pte() entry = pte_to_swp_entry(orig_src_pte); // Here it got entry = S1 ... < interrupted> ... <swapin src_pte, alloc and use folio A> // folio A is a new allocated folio // and get installed into src_pte <frees swap entry S1> // src_pte now points to folio A, S1 // has swap count == 0, it can be freed // by folio_swap_swap or swap // allocator's reclaim. <try to swap out another folio B> // folio B is a folio in another VMA. <put folio B to swap cache using S1 > // S1 is freed, folio B can use it // for swap out with no problem. ... folio = filemap_get_folio(S1) // Got folio B here !!! ... < interrupted again> ... <swapin folio B and free S1> // Now S1 is free to be used again. <swapout src_pte & folio A using S1> // Now src_pte is a swap entry PTE // holding S1 again. folio_trylock(folio) move_swap_pte double_pt_lock is_pte_pages_stable // Check passed because src_pte == S1 folio_move_anon_rmap(...) // Moved invalid folio B here !!! The race window is very short and requires multiple collisions of multiple rare events, so it's very unlikely to happen, but with a deliberately constructed reproducer and increased time window, it can be reproduced easily. This can be fixed by checking if the folio returned by filemap is the valid swap cache folio after acquiring the folio lock. Another similar race is possible: filemap_get_folio may return NULL, but folio (A) could be swapped in and then swapped out again using the same swap entry after the lookup. In such a case, folio (A) may remain in the swap cache, so it must be moved too: CPU1 CPU2 userfaultfd_move move_pages_pte() entry = pte_to_swp_entry(orig_src_pte); // Here it got entry = S1, and S1 is not in swap cache folio = filemap_get_folio(S1) // Got NULL ... < interrupted again> ... <swapin folio A and free S1> <swapout folio A re-using S1> move_swap_pte double_pt_lock is_pte_pages_stable // Check passed because src_pte == S1 folio_move_anon_rmap(...) // folio A is ignored !!! Fix this by checking the swap cache again after acquiring the src_pte lock. And to avoid the filemap overhead, we check swap_map directly [2]. The SWP_SYNCHRONOUS_IO path does make the problem more complex, but so far we don't need to worry about that, since folios can only be exposed to the swap cache in the swap out path, and this is covered in this patch by checking the swap cache again after acquiring the src_pte lock. Testing with a simple C program that allocates and moves several GB of memory did not show any observable performance change. Link: https://lkml.kernel.org/r/20250604151038.21968-1-ryncsn@gmail.com Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Kairui Song <kasong(a)tencent.com> Closes: https://lore.kernel.org/linux-mm/CAMgjq7B1K=6OOrK2OUZ0-tqCzi+EJt+2_K97TPGoS… [1] Link: https://lore.kernel.org/all/CAGsJ_4yJhJBo16XhiC-nUzSheyX-V3-nFE+tAi=8Y560K8… [2] Reviewed-by: Lokesh Gidra <lokeshgidra(a)google.com> Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Suren Baghdasaryan <surenb(a)google.com> Reviewed-by: Barry Song <baohua(a)kernel.org> Reviewed-by: Chris Li <chrisl(a)kernel.org> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kairui Song <kasong(a)tencent.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/userfaultfd.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) --- a/mm/userfaultfd.c~mm-userfaultfd-fix-race-of-userfaultfd_move-and-swap-cache +++ a/mm/userfaultfd.c @@ -1084,8 +1084,18 @@ static int move_swap_pte(struct mm_struc pte_t orig_dst_pte, pte_t orig_src_pte, pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl, - struct folio *src_folio) + struct folio *src_folio, + struct swap_info_struct *si, swp_entry_t entry) { + /* + * Check if the folio still belongs to the target swap entry after + * acquiring the lock. Folio can be freed in the swap cache while + * not locked. + */ + if (src_folio && unlikely(!folio_test_swapcache(src_folio) || + entry.val != src_folio->swap.val)) + return -EAGAIN; + double_pt_lock(dst_ptl, src_ptl); if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, @@ -1102,6 +1112,25 @@ static int move_swap_pte(struct mm_struc if (src_folio) { folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); + } else { + /* + * Check if the swap entry is cached after acquiring the src_pte + * lock. Otherwise, we might miss a newly loaded swap cache folio. + * + * Check swap_map directly to minimize overhead, READ_ONCE is sufficient. + * We are trying to catch newly added swap cache, the only possible case is + * when a folio is swapped in and out again staying in swap cache, using the + * same entry before the PTE check above. The PTL is acquired and released + * twice, each time after updating the swap_map's flag. So holding + * the PTL here ensures we see the updated value. False positive is possible, + * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the + * cache, or during the tiny synchronization window between swap cache and + * swap_map, but it will be gone very quickly, worst result is retry jitters. + */ + if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) { + double_pt_unlock(dst_ptl, src_ptl); + return -EAGAIN; + } } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); @@ -1412,7 +1441,7 @@ retry: } err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval, - dst_ptl, src_ptl, src_folio); + dst_ptl, src_ptl, src_folio, si, entry); } out: _ Patches currently in -mm which might be from kasong(a)tencent.com are mm-list_lru-refactor-the-locking-code.patch mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung.patch mm-shmem-swap-avoid-redundant-xarray-lookup-during-swapin.patch mm-shmem-swap-improve-mthp-swapin-process.patch mm-shmem-swap-avoid-false-positive-swap-cache-lookup.patch

2 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-gup-revert-mm-gup-fix-infinite-loop-within-__get_longterm_locked.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/gup: revert "mm: gup: fix infinite loop within __get_longterm_locked" has been removed from the -mm tree. Its filename was mm-gup-revert-mm-gup-fix-infinite-loop-within-__get_longterm_locked.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: David Hildenbrand <david(a)redhat.com> Subject: mm/gup: revert "mm: gup: fix infinite loop within __get_longterm_locked" Date: Wed, 11 Jun 2025 15:13:14 +0200 After commit 1aaf8c122918 ("mm: gup: fix infinite loop within __get_longterm_locked") we are able to longterm pin folios that are not supposed to get longterm pinned, simply because they temporarily have the LRU flag cleared (esp. temporarily isolated). For example, two __get_longterm_locked() callers can race, or __get_longterm_locked() can race with anything else that temporarily isolates folios. The introducing commit mentions the use case of a driver that uses vm_ops->fault to insert pages allocated through cma_alloc() into the page tables, assuming they can later get longterm pinned. These pages/ folios would never have the LRU flag set and consequently cannot get isolated. There is no known in-tree user making use of that so far, fortunately. To handle that in the future -- and avoid retrying forever to isolate/migrate them -- we will need a different mechanism for the CMA area *owner* to indicate that it actually already allocated the page and is fine with longterm pinning it. The LRU flag is not suitable for that. Probably we can lookup the relevant CMA area and query the bitmap; we only have have to care about some races, probably. If already allocated, we could just allow longterm pinning) Anyhow, let's fix the "must not be longterm pinned" problem first by reverting the original commit. Link: https://lkml.kernel.org/r/20250611131314.594529-1-david@redhat.com Fixes: 1aaf8c122918 ("mm: gup: fix infinite loop within __get_longterm_locked") Signed-off-by: David Hildenbrand <david(a)redhat.com> Closes: https://lore.kernel.org/all/20250522092755.GA3277597@tiffany/ Reported-by: Hyesoo Yu <hyesoo.yu(a)samsung.com> Reviewed-by: John Hubbard <jhubbard(a)nvidia.com> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Peter Xu <peterx(a)redhat.com> Cc: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com> Cc: Aijun Sun <aijun.sun(a)unisoc.com> Cc: Alistair Popple <apopple(a)nvidia.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/gup.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) --- a/mm/gup.c~mm-gup-revert-mm-gup-fix-infinite-loop-within-__get_longterm_locked +++ a/mm/gup.c @@ -2303,13 +2303,13 @@ static void pofs_unpin(struct pages_or_f /* * Returns the number of collected folios. Return value is always >= 0. */ -static void collect_longterm_unpinnable_folios( +static unsigned long collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { + unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; - unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); @@ -2321,6 +2321,8 @@ static void collect_longterm_unpinnable_ if (folio_is_longterm_pinnable(folio)) continue; + collected++; + if (folio_is_device_coherent(folio)) continue; @@ -2342,6 +2344,8 @@ static void collect_longterm_unpinnable_ NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } + + return collected; } /* @@ -2418,9 +2422,11 @@ static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); + unsigned long collected; - collect_longterm_unpinnable_folios(&movable_folio_list, pofs); - if (list_empty(&movable_folio_list)) + collected = collect_longterm_unpinnable_folios(&movable_folio_list, + pofs); + if (!collected) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); _ Patches currently in -mm which might be from david(a)redhat.com are fs-proc-task_mmu-fix-page_is_pfnzero-detection-for-the-huge-zero-folio.patch mm-gup-remove-vm_bug_ons.patch mm-gup-remove-vm_bug_ons-fix.patch mm-huge_memory-dont-ignore-queried-cachemode-in-vmf_insert_pfn_pud.patch mm-huge_memory-dont-mark-refcounted-folios-special-in-vmf_insert_folio_pmd.patch mm-huge_memory-dont-mark-refcounted-folios-special-in-vmf_insert_folio_pud.patch

2 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-shmem-swap-fix-softlockup-with-mthp-swapin.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/shmem, swap: fix softlockup with mTHP swapin has been removed from the -mm tree. Its filename was mm-shmem-swap-fix-softlockup-with-mthp-swapin.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kairui Song <kasong(a)tencent.com> Subject: mm/shmem, swap: fix softlockup with mTHP swapin Date: Tue, 10 Jun 2025 01:17:51 +0800 Following softlockup can be easily reproduced on my test machine with: echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled swapon /dev/zram0 # zram0 is a 48G swap device mkdir -p /sys/fs/cgroup/memory/test echo 1G > /sys/fs/cgroup/test/memory.max echo $BASHPID > /sys/fs/cgroup/test/cgroup.procs while true; do dd if=/dev/zero of=/tmp/test.img bs=1M count=5120 cat /tmp/test.img > /dev/null rm /tmp/test.img done Then after a while: watchdog: BUG: soft lockup - CPU#0 stuck for 763s! [cat:5787] Modules linked in: zram virtiofs CPU: 0 UID: 0 PID: 5787 Comm: cat Kdump: loaded Tainted: G L 6.15.0.orig-gf3021d9246bc-dirty #118 PREEMPT(voluntary)�� Tainted: [L]=SOFTLOCKUP Hardware name: Red Hat KVM/RHEL-AV, BIOS 0.0.0 02/06/2015 RIP: 0010:mpol_shared_policy_lookup+0xd/0x70 Code: e9 b8 b4 ff ff 31 c0 c3 cc cc cc cc 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 41 54 55 53 <48> 8b 1f 48 85 db 74 41 4c 8d 67 08 48 89 fb 48 89 f5 4c 89 e7 e8 RSP: 0018:ffffc90002b1fc28 EFLAGS: 00000202 RAX: 00000000001c20ca RBX: 0000000000724e1e RCX: 0000000000000001 RDX: ffff888118e214c8 RSI: 0000000000057d42 RDI: ffff888118e21518 RBP: 000000000002bec8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000bf4 R11: 0000000000000000 R12: 0000000000000001 R13: 00000000001c20ca R14: 00000000001c20ca R15: 0000000000000000 FS: 00007f03f995c740(0000) GS:ffff88a07ad9a000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f03f98f1000 CR3: 0000000144626004 CR4: 0000000000770eb0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> shmem_alloc_folio+0x31/0xc0 shmem_swapin_folio+0x309/0xcf0 ? filemap_get_entry+0x117/0x1e0 ? xas_load+0xd/0xb0 ? filemap_get_entry+0x101/0x1e0 shmem_get_folio_gfp+0x2ed/0x5b0 shmem_file_read_iter+0x7f/0x2e0 vfs_read+0x252/0x330 ksys_read+0x68/0xf0 do_syscall_64+0x4c/0x1c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f03f9a46991 Code: 00 48 8b 15 81 14 10 00 f7 d8 64 89 02 b8 ff ff ff ff eb bd e8 20 ad 01 00 f3 0f 1e fa 80 3d 35 97 10 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 4f c3 66 0f 1f 44 00 00 55 48 89 e5 48 83 ec RSP: 002b:00007fff3c52bd28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000040000 RCX: 00007f03f9a46991 RDX: 0000000000040000 RSI: 00007f03f98ba000 RDI: 0000000000000003 RBP: 00007fff3c52bd50 R08: 0000000000000000 R09: 00007f03f9b9a380 R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000040000 R13: 00007f03f98ba000 R14: 0000000000000003 R15: 0000000000000000 </TASK> The reason is simple, readahead brought some order 0 folio in swap cache, and the swapin mTHP folio being allocated is in conflict with it, so swapcache_prepare fails and causes shmem_swap_alloc_folio to return -EEXIST, and shmem simply retries again and again causing this loop. Fix it by applying a similar fix for anon mTHP swapin. The performance change is very slight, time of swapin 10g zero folios with shmem (test for 12 times): Before: 2.47s After: 2.48s [kasong(a)tencent.com: add comment] Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250609171751.36305-1-ryncsn@gmail.com Fixes: 1dd44c0af4fa ("mm: shmem: skip swapcache for swapin of synchronous swap device") Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: Barry Song <baohua(a)kernel.org> Acked-by: Nhat Pham <nphamcs(a)gmail.com> Reviewed-by: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Baoquan He <bhe(a)redhat.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: Usama Arif <usamaarif642(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory.c | 20 -------------------- mm/shmem.c | 6 +++++- mm/swap.h | 23 +++++++++++++++++++++++ 3 files changed, 28 insertions(+), 21 deletions(-) --- a/mm/memory.c~mm-shmem-swap-fix-softlockup-with-mthp-swapin +++ a/mm/memory.c @@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio( } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) -{ - struct swap_info_struct *si = swp_swap_info(entry); - pgoff_t offset = swp_offset(entry); - int i; - - /* - * While allocating a large folio and doing swap_read_folio, which is - * the case the being faulted pte doesn't have swapcache. We need to - * ensure all PTEs have no cache as well, otherwise, we might go to - * swap devices while the content is in swapcache. - */ - for (i = 0; i < max_nr; i++) { - if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) - return i; - } - - return i; -} - /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. --- a/mm/shmem.c~mm-shmem-swap-fix-softlockup-with-mthp-swapin +++ a/mm/shmem.c @@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct ino folio = swap_cache_get_folio(swap, NULL, 0); order = xa_get_order(&mapping->i_pages, index); if (!folio) { + int nr_pages = 1 << order; bool fallback_order0 = false; /* Or update major stats only when swapin succeeds?? */ @@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct ino * If uffd is active for the vma, we need per-page fault * fidelity to maintain the uffd semantics, then fallback * to swapin order-0 folio, as well as for zswap case. + * Any existing sub folio in the swap cache also blocks + * mTHP swapin. */ if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) || - !zswap_never_enabled())) + !zswap_never_enabled() || + non_swapcache_batch(swap, nr_pages) != nr_pages)) fallback_order0 = true; /* Skip swapcache for synchronous device. */ --- a/mm/swap.h~mm-shmem-swap-fix-softlockup-with-mthp-swapin +++ a/mm/swap.h @@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp return find_next_bit(sis->zeromap, end, start) - start; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + struct swap_info_struct *si = swp_swap_info(entry); + pgoff_t offset = swp_offset(entry); + int i; + + /* + * While allocating a large folio and doing mTHP swapin, we need to + * ensure all entries are not cached, otherwise, the mTHP folio will + * be in conflict with the folio in swap cache. + */ + for (i = 0; i < max_nr; i++) { + if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) + return i; + } + + return i; +} + #else /* CONFIG_SWAP */ struct swap_iocb; static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug) @@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp return 0; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + return 0; +} #endif /* CONFIG_SWAP */ /** _ Patches currently in -mm which might be from kasong(a)tencent.com are mm-list_lru-refactor-the-locking-code.patch mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung.patch mm-shmem-swap-avoid-redundant-xarray-lookup-during-swapin.patch mm-shmem-swap-improve-mthp-swapin-process.patch mm-shmem-swap-avoid-false-positive-swap-cache-lookup.patch

2 months, 1 week

1
0
0 0

[PATCH v6 1/4] scsi: fnic: Fix crash in fnic_wq_cmpl_handler when FDMI times out

by Karan Tilak Kumar

When both the RHBA and RPA FDMI requests time out, fnic reuses a frame to send ABTS for each of them. On send completion, this causes an attempt to free the same frame twice that leads to a crash. Fix crash by allocating separate frames for RHBA and RPA, and modify ABTS logic accordingly. Tested by checking MDS for FDMI information. Tested by using instrumented driver to: Drop PLOGI response Drop RHBA response Drop RPA response Drop RHBA and RPA response Drop PLOGI response + ABTS response Drop RHBA response + ABTS response Drop RPA response + ABTS response Drop RHBA and RPA response + ABTS response for both of them Fixes: 09c1e6ab4ab2 ("scsi: fnic: Add and integrate support for FDMI") Reviewed-by: Sesidhar Baddela <sebaddel(a)cisco.com> Reviewed-by: Arulprabhu Ponnusamy <arulponn(a)cisco.com> Reviewed-by: Gian Carlo Boffa <gcboffa(a)cisco.com> Tested-by: Arun Easi <aeasi(a)cisco.com> Co-developed-by: Arun Easi <aeasi(a)cisco.com> Signed-off-by: Arun Easi <aeasi(a)cisco.com> Tested-by: Karan Tilak Kumar <kartilak(a)cisco.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Karan Tilak Kumar <kartilak(a)cisco.com> --- Changes between v5 and v6: - Incorporate review comments from John: - Rebase patches on 6.17/scsi-queue Changes between v4 and v5: - Incorporate review comments from John: - Refactor patches Changes between v3 and v4: - Incorporate review comments from Dan: - Remove comments from Cc tag Changes between v2 and v3: - Incorporate review comments from Dan: - Add Cc to stable Changes between v1 and v2: - Incorporate review comments from Dan: - Add Fixes tag --- drivers/scsi/fnic/fdls_disc.c | 113 +++++++++++++++++++++++++--------- drivers/scsi/fnic/fnic.h | 2 +- drivers/scsi/fnic/fnic_fdls.h | 1 + 3 files changed, 87 insertions(+), 29 deletions(-) diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c index f8ab69c51dab..36b498ad55b4 100644 --- a/drivers/scsi/fnic/fdls_disc.c +++ b/drivers/scsi/fnic/fdls_disc.c @@ -763,47 +763,69 @@ static void fdls_send_fabric_abts(struct fnic_iport_s *iport) iport->fabric.timer_pending = 1; } -static void fdls_send_fdmi_abts(struct fnic_iport_s *iport) +static uint8_t *fdls_alloc_init_fdmi_abts_frame(struct fnic_iport_s *iport, + uint16_t oxid) { - uint8_t *frame; + struct fc_frame_header *pfdmi_abts; uint8_t d_id[3]; + uint8_t *frame; struct fnic *fnic = iport->fnic; - struct fc_frame_header *pfabric_abts; - unsigned long fdmi_tov; - uint16_t oxid; - uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + - sizeof(struct fc_frame_header); frame = fdls_alloc_frame(iport); if (frame == NULL) { FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num, "Failed to allocate frame to send FDMI ABTS"); - return; + return NULL; } - pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); + pfdmi_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET); fdls_init_fabric_abts_frame(frame, iport); hton24(d_id, FC_FID_MGMT_SERV); - FNIC_STD_SET_D_ID(*pfabric_abts, d_id); + FNIC_STD_SET_D_ID(*pfdmi_abts, d_id); + FNIC_STD_SET_OX_ID(*pfdmi_abts, oxid); + + return frame; +} + +static void fdls_send_fdmi_abts(struct fnic_iport_s *iport) +{ + uint8_t *frame; + unsigned long fdmi_tov; + uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET + + sizeof(struct fc_frame_header); if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) { - oxid = iport->active_oxid_fdmi_plogi; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_plogi); + if (frame == NULL) + return; + fnic_send_fcoe_frame(iport, frame, frame_size); } else { if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) { - oxid = iport->active_oxid_fdmi_rhba; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_rhba); + if (frame == NULL) + return; + fnic_send_fcoe_frame(iport, frame, frame_size); } if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) { - oxid = iport->active_oxid_fdmi_rpa; - FNIC_STD_SET_OX_ID(*pfabric_abts, oxid); + frame = fdls_alloc_init_fdmi_abts_frame(iport, + iport->active_oxid_fdmi_rpa); + if (frame == NULL) { + if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) + goto arm_timer; + else + return; + } + fnic_send_fcoe_frame(iport, frame, frame_size); } } +arm_timer: fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov); mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov)); iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING; @@ -2245,6 +2267,21 @@ void fdls_fabric_timer_callback(struct timer_list *t) spin_unlock_irqrestore(&fnic->fnic_lock, flags); } +void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport) +{ + struct fnic *fnic = iport->fnic; + + iport->fabric.fdmi_pending = 0; + /* If max retries not exhausted, start over from fdmi plogi */ + if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) { + iport->fabric.fdmi_retry++; + FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, + "Retry FDMI PLOGI. FDMI retry: %d", + iport->fabric.fdmi_retry); + fdls_send_fdmi_plogi(iport); + } +} + void fdls_fdmi_timer_callback(struct timer_list *t) { struct fnic_fdls_fabric_s *fabric = timer_container_of(fabric, t, @@ -2291,14 +2328,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t) FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); - iport->fabric.fdmi_pending = 0; - /* If max retries not exhaused, start over from fdmi plogi */ - if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) { - iport->fabric.fdmi_retry++; - FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, - "retry fdmi timer %d", iport->fabric.fdmi_retry); - fdls_send_fdmi_plogi(iport); - } + fdls_fdmi_retry_plogi(iport); FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num, "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending); spin_unlock_irqrestore(&fnic->fnic_lock, flags); @@ -3716,11 +3746,32 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport, switch (FNIC_FRAME_TYPE(oxid)) { case FNIC_FRAME_TYPE_FDMI_PLOGI: fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi); + + iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING; + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; break; case FNIC_FRAME_TYPE_FDMI_RHBA: + iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING; + + /* If RPA is still pending, don't turn off ABORT PENDING. + * We count on the timer to detect the ABTS timeout and take + * corrective action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING)) + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba); break; case FNIC_FRAME_TYPE_FDMI_RPA: + iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING; + + /* If RHBA is still pending, don't turn off ABORT PENDING. + * We count on the timer to detect the ABTS timeout and take + * corrective action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)) + iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; + fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa); break; default: @@ -3730,10 +3781,16 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport, break; } - timer_delete_sync(&iport->fabric.fdmi_timer); - iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING; - - fdls_send_fdmi_plogi(iport); + /* + * Only if ABORT PENDING is off, delete the timer, and if no other + * operations are pending, retry FDMI. + * Otherwise, let the timer pop and take the appropriate action. + */ + if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) { + timer_delete_sync(&iport->fabric.fdmi_timer); + if (!iport->fabric.fdmi_pending) + fdls_fdmi_retry_plogi(iport); + } } static void diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h index 6c5f6046b1f5..86e293ce530d 100644 --- a/drivers/scsi/fnic/fnic.h +++ b/drivers/scsi/fnic/fnic.h @@ -30,7 +30,7 @@ #define DRV_NAME "fnic" #define DRV_DESCRIPTION "Cisco FCoE HBA Driver" -#define DRV_VERSION "1.8.0.0" +#define DRV_VERSION "1.8.0.1" #define PFX DRV_NAME ": " #define DFX DRV_NAME "%d: " diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h index 8e610b65ad57..531d0b37e450 100644 --- a/drivers/scsi/fnic/fnic_fdls.h +++ b/drivers/scsi/fnic/fnic_fdls.h @@ -394,6 +394,7 @@ void fdls_send_tport_abts(struct fnic_iport_s *iport, bool fdls_delete_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport); void fdls_fdmi_timer_callback(struct timer_list *t); +void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport); /* fnic_fcs.c */ void fnic_fdls_init(struct fnic *fnic, int usefip); -- 2.47.1

2 months, 1 week

4
5
0 0

[PATCH] scsi: mpt3sas: drop unused variable in mpt3sas_send_mctp_passthru_req()

by André Draszik

With W=1, gcc complains correctly: mpt3sas_ctl.c: In function ‘mpt3sas_send_mctp_passthru_req’: mpt3sas_ctl.c:2917:29: error: variable ‘mpi_reply’ set but not used [-Werror=unused-but-set-variable] 2917 | MPI2DefaultReply_t *mpi_reply; | ^~~~~~~~~ Drop the unused assignment and variable. Fixes: c72be4b5bb7c ("scsi: mpt3sas: Add support for MCTP Passthrough commands") Cc: stable(a)vger.kernel.org Signed-off-by: André Draszik <andre.draszik(a)linaro.org> --- drivers/scsi/mpt3sas/mpt3sas_ctl.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 02fc204b9bf7b276115bf6db52746155381799fd..3b951589feeb6c13094ea44b494ca3050a309b15 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -2914,7 +2914,6 @@ int mpt3sas_send_mctp_passthru_req(struct mpt3_passthru_command *command) { struct MPT3SAS_ADAPTER *ioc; MPI2RequestHeader_t *mpi_request = NULL, *request; - MPI2DefaultReply_t *mpi_reply; Mpi26MctpPassthroughRequest_t *mctp_passthru_req; u16 smid; unsigned long timeout; @@ -3022,8 +3021,6 @@ int mpt3sas_send_mctp_passthru_req(struct mpt3_passthru_command *command) goto issue_host_reset; } - mpi_reply = ioc->ctl_cmds.reply; - /* copy out xdata to user */ if (data_in_sz) memcpy(command->data_in_buf_ptr, data_in, data_in_sz); --- base-commit: a0bea9e39035edc56a994630e6048c8a191a99d8 change-id: 20250606-mpt3sas-15563809f705 Best regards, -- André Draszik <andre.draszik(a)linaro.org>

2 months, 1 week

2
2
0 0

[PATCH] ARM: Use an absolute path to unified.h in KBUILD_AFLAGS

by Nathan Chancellor

After commit d5c8d6e0fa61 ("kbuild: Update assembler calls to use proper flags and language target"), which updated as-instr to use the 'assembler-with-cpp' language option, the Kbuild version of as-instr always fails internally for arch/arm with <command-line>: fatal error: asm/unified.h: No such file or directory compilation terminated. because '-include' flags are now taken into account by the compiler driver and as-instr does not have '$(LINUXINCLUDE)', so unified.h is not found. This went unnoticed at the time of the Kbuild change because the last use of as-instr in Kbuild that arch/arm could reach was removed in 5.7 by commit 541ad0150ca4 ("arm: Remove 32bit KVM host support") but a stable backport of the Kbuild change to before that point exposed this potential issue if one were to be reintroduced. Follow the general pattern of '-include' paths throughout the tree and make unified.h absolute using '$(srctree)' to ensure KBUILD_AFLAGS can be used independently. Cc: stable(a)vger.kernel.org Fixes: d5c8d6e0fa61 ("kbuild: Update assembler calls to use proper flags and language target") Reported-by: KernelCI bot <bot(a)kernelci.org> Closes: https://lore.kernel.org/CACo-S-1qbCX4WAVFA63dWfHtrRHZBTyyr2js8Lx=Az03XHTTHg… Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> --- arch/arm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4808d3ed98e4..e31e95ffd33f 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -149,7 +149,7 @@ endif # Need -Uarm for gcc < 3.x KBUILD_CPPFLAGS +=$(cpp-y) KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm -KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float +KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include $(srctree)/arch/arm/include/asm/unified.h -msoft-float KBUILD_RUSTFLAGS += --target=arm-unknown-linux-gnueabi CHECKFLAGS += -D__arm__ --- base-commit: e04c78d86a9699d136910cfc0bdcf01087e3267e change-id: 20250618-arm-expand-include-unified-h-path-60e65adcda1e Best regards, -- Nathan Chancellor <nathan(a)kernel.org>

2 months, 1 week

2
1
0 0

[PATCH 6.1/6.6] platform/x86: ideapad-laptop: add missing Ideapad Pro 5 fn keys

by WangYuli

From: Renato Caldas <renato(a)calgera.com> [ Upstream commit 36e66be874a7ea9d28fb9757629899a8449b8748 ] The scancodes for the Mic Mute and Airplane keys on the Ideapad Pro 5 (14AHP9 at least, probably the other variants too) are different and were not being picked up by the driver. This adds them to the keymap. Apart from what is already supported, the remaining fn keys are unfortunately producing windows-specific key-combos. Signed-off-by: Renato Caldas <renato(a)calgera.com> Link: https://lore.kernel.org/r/20241102183116.30142-1-renato@calgera.com Reviewed-by: Hans de Goede <hdegoede(a)redhat.com> Signed-off-by: Hans de Goede <hdegoede(a)redhat.com> Signed-off-by: WangYuli <wangyuli(a)uniontech.com> --- drivers/platform/x86/ideapad-laptop.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 88eefccb6ed2..50013af0537c 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1101,6 +1101,9 @@ static const struct key_entry ideapad_keymap[] = { { KE_KEY, 0x27 | IDEAPAD_WMI_KEY, { KEY_HELP } }, /* Refresh Rate Toggle */ { KE_KEY, 0x0a | IDEAPAD_WMI_KEY, { KEY_DISPLAYTOGGLE } }, + /* Specific to some newer models */ + { KE_KEY, 0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } }, + { KE_KEY, 0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } }, { KE_END }, }; -- 2.50.0

2 months, 1 week

2
1
0 0

FAILED: patch "[PATCH] HID: usbhid: Eliminate recurrent out-of-bounds bug in" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x fe7f7ac8e0c708446ff017453add769ffc15deed # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025061738-circus-skipping-ed0c@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From fe7f7ac8e0c708446ff017453add769ffc15deed Mon Sep 17 00:00:00 2001 From: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Date: Wed, 12 Mar 2025 15:23:31 -0700 Subject: [PATCH] HID: usbhid: Eliminate recurrent out-of-bounds bug in usbhid_parse() Update struct hid_descriptor to better reflect the mandatory and optional parts of the HID Descriptor as per USB HID 1.11 specification. Note: the kernel currently does not parse any optional HID class descriptors, only the mandatory report descriptor. Update all references to member element desc[0] to rpt_desc. Add test to verify bLength and bNumDescriptors values are valid. Replace the for loop with direct access to the mandatory HID class descriptor member for the report descriptor. This eliminates the possibility of getting an out-of-bounds fault. Add a warning message if the HID descriptor contains any unsupported optional HID class descriptors. Reported-by: syzbot+c52569baf0c843f35495(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c52569baf0c843f35495 Fixes: f043bfc98c19 ("HID: usbhid: fix out-of-bounds bug") Cc: stable(a)vger.kernel.org Signed-off-by: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 0fb210e40a41..9eafff0b6ea4 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -192,7 +192,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, goto cleanup; input_device->report_desc_size = le16_to_cpu( - desc->desc[0].wDescriptorLength); + desc->rpt_desc.wDescriptorLength); if (input_device->report_desc_size == 0) { input_device->dev_info_status = -EINVAL; goto cleanup; @@ -210,7 +210,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, memcpy(input_device->report_desc, ((unsigned char *)desc) + desc->bLength, - le16_to_cpu(desc->desc[0].wDescriptorLength)); + le16_to_cpu(desc->rpt_desc.wDescriptorLength)); /* Send the ack */ memset(&ack, 0, sizeof(struct mousevsc_prt_msg)); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 44c2351b870f..fc2b92dfc242 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -984,12 +984,11 @@ static int usbhid_parse(struct hid_device *hid) struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; + struct hid_class_descriptor *hcdesc; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; - int ret, n; - int num_descriptors; - size_t offset = offsetof(struct hid_descriptor, desc); + int ret; quirks = hid_lookup_quirk(hid); @@ -1011,20 +1010,19 @@ static int usbhid_parse(struct hid_device *hid) return -ENODEV; } - if (hdesc->bLength < sizeof(struct hid_descriptor)) { - dbg_hid("hid descriptor is too short\n"); + if (!hdesc->bNumDescriptors || + hdesc->bLength != sizeof(*hdesc) + + (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) { + dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n", + hdesc->bLength, hdesc->bNumDescriptors); return -EINVAL; } hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; - num_descriptors = min_t(int, hdesc->bNumDescriptors, - (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); - - for (n = 0; n < num_descriptors; n++) - if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) - rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); + if (hdesc->rpt_desc.bDescriptorType == HID_DT_REPORT) + rsize = le16_to_cpu(hdesc->rpt_desc.wDescriptorLength); if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) { dbg_hid("weird size of report descriptor (%u)\n", rsize); @@ -1052,6 +1050,11 @@ static int usbhid_parse(struct hid_device *hid) goto err; } + if (hdesc->bNumDescriptors > 1) + hid_warn(intf, + "%u unsupported optional hid class descriptors\n", + (int)(hdesc->bNumDescriptors - 1)); + hid->quirks |= quirks; return 0; diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 740311c4fa24..c7a05f842745 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -144,8 +144,8 @@ static struct hid_descriptor hidg_desc = { .bcdHID = cpu_to_le16(0x0101), .bCountryCode = 0x00, .bNumDescriptors = 0x1, - /*.desc[0].bDescriptorType = DYNAMIC */ - /*.desc[0].wDescriptorLenght = DYNAMIC */ + /*.rpt_desc.bDescriptorType = DYNAMIC */ + /*.rpt_desc.wDescriptorLength = DYNAMIC */ }; /* Super-Speed Support */ @@ -939,8 +939,8 @@ static int hidg_setup(struct usb_function *f, struct hid_descriptor hidg_desc_copy = hidg_desc; VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n"); - hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc_copy.desc[0].wDescriptorLength = + hidg_desc_copy.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc_copy.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); length = min_t(unsigned short, length, @@ -1210,8 +1210,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) * We can use hidg_desc struct here but we should not relay * that its content won't change after returning from this function. */ - hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc.desc[0].wDescriptorLength = + hidg_desc.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); hidg_hs_in_ep_desc.bEndpointAddress = diff --git a/include/linux/hid.h b/include/linux/hid.h index ef9a90ca0fbd..daae1d6d11a7 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -740,8 +740,9 @@ struct hid_descriptor { __le16 bcdHID; __u8 bCountryCode; __u8 bNumDescriptors; + struct hid_class_descriptor rpt_desc; - struct hid_class_descriptor desc[1]; + struct hid_class_descriptor opt_descs[]; } __attribute__ ((packed)); #define HID_DEVICE(b, g, ven, prod) \

2 months, 1 week

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025