aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--block/bfq-cgroup.c1
-rw-r--r--block/bfq-iosched.c191
-rw-r--r--block/bfq-iosched.h6
-rw-r--r--block/bio.c112
-rw-r--r--block/blk-iocost.c2
-rw-r--r--block/blk-mq.c3
-rw-r--r--block/blk-throttle.c69
-rw-r--r--block/blk-throttle.h2
-rw-r--r--block/blk.h4
-rw-r--r--block/partitions/core.c8
-rw-r--r--drivers/block/drbd/drbd_state.c2
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c19
-rw-r--r--include/linux/mm.h1
-rw-r--r--mm/gup.c13
14 files changed, 261 insertions, 172 deletions
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 9fb9f3533150..e831aedb4643 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -736,7 +736,6 @@ static void bfq_sync_bfqq_move(struct bfq_data *bfqd,
*/
bfq_put_cooperator(sync_bfqq);
bic_set_bfqq(bic, NULL, true, act_idx);
- bfq_release_process_ref(bfqd, sync_bfqq);
}
}
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index d1bf2b8a3576..0747d9d0e48c 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -3129,10 +3129,12 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_put_queue(bfqq);
}
-static void
-bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
- struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+static struct bfq_queue *bfq_merge_bfqqs(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct bfq_queue *bfqq)
{
+ struct bfq_queue *new_bfqq = bfqq->new_bfqq;
+
bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
(unsigned long)new_bfqq->pid);
/* Save weight raising and idle window of the merged queues */
@@ -3226,6 +3228,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
bfq_reassign_last_bfqq(bfqq, new_bfqq);
bfq_release_process_ref(bfqd, bfqq);
+
+ return new_bfqq;
}
static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
@@ -3261,14 +3265,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
* fulfilled, i.e., bic can be redirected to new_bfqq
* and bfqq can be put.
*/
- bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
- new_bfqq);
- /*
- * If we get here, bio will be queued into new_queue,
- * so use new_bfqq to decide whether bio and rq can be
- * merged.
- */
- bfqq = new_bfqq;
+ while (bfqq != new_bfqq)
+ bfqq = bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq);
/*
* Change also bqfd->bio_bfqq, as
@@ -5436,6 +5434,8 @@ void bfq_put_cooperator(struct bfq_queue *bfqq)
bfq_put_queue(__bfqq);
__bfqq = next;
}
+
+ bfq_release_process_ref(bfqq->bfqd, bfqq);
}
static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
@@ -5448,8 +5448,6 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
bfq_put_cooperator(bfqq);
-
- bfq_release_process_ref(bfqd, bfqq);
}
static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync,
@@ -5705,9 +5703,7 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq,
* state before killing it.
*/
bfqq->bic = bic;
- bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
-
- return new_bfqq;
+ return bfq_merge_bfqqs(bfqd, bic, bfqq);
}
/*
@@ -6162,6 +6158,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
bool waiting, idle_timer_disabled = false;
if (new_bfqq) {
+ struct bfq_queue *old_bfqq = bfqq;
/*
* Release the request's reference to the old bfqq
* and make sure one is taken to the shared queue.
@@ -6178,18 +6175,18 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
* new_bfqq.
*/
if (bic_to_bfqq(RQ_BIC(rq), true,
- bfq_actuator_index(bfqd, rq->bio)) == bfqq)
- bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
- bfqq, new_bfqq);
+ bfq_actuator_index(bfqd, rq->bio)) == bfqq) {
+ while (bfqq != new_bfqq)
+ bfqq = bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq);
+ }
- bfq_clear_bfqq_just_created(bfqq);
+ bfq_clear_bfqq_just_created(old_bfqq);
/*
* rq is about to be enqueued into new_bfqq,
* release rq reference on bfqq
*/
- bfq_put_queue(bfqq);
+ bfq_put_queue(old_bfqq);
rq->elv.priv[1] = new_bfqq;
- bfqq = new_bfqq;
}
bfq_update_io_thinktime(bfqd, bfqq);
@@ -6737,16 +6734,13 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
bic_set_bfqq(bic, NULL, true, bfqq->actuator_idx);
bfq_put_cooperator(bfqq);
-
- bfq_release_process_ref(bfqq->bfqd, bfqq);
return NULL;
}
-static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
- struct bfq_io_cq *bic,
- struct bio *bio,
- bool split, bool is_sync,
- bool *new_queue)
+static struct bfq_queue *
+__bfq_get_bfqq_handle_split(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+ struct bio *bio, bool split, bool is_sync,
+ bool *new_queue)
{
unsigned int act_idx = bfq_actuator_index(bfqd, bio);
struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, act_idx);
@@ -6825,6 +6819,84 @@ static void bfq_prepare_request(struct request *rq)
rq->elv.priv[0] = rq->elv.priv[1] = NULL;
}
+static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq)
+{
+ struct bfq_queue *new_bfqq = bfqq->new_bfqq;
+ struct bfq_queue *waker_bfqq = bfqq->waker_bfqq;
+
+ if (!waker_bfqq)
+ return NULL;
+
+ while (new_bfqq) {
+ if (new_bfqq == waker_bfqq) {
+ /*
+ * If waker_bfqq is in the merge chain, and current
+ * is the only procress.
+ */
+ if (bfqq_process_refs(waker_bfqq) == 1)
+ return NULL;
+ break;
+ }
+
+ new_bfqq = new_bfqq->new_bfqq;
+ }
+
+ return waker_bfqq;
+}
+
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct bio *bio,
+ unsigned int idx,
+ bool is_sync)
+{
+ struct bfq_queue *waker_bfqq;
+ struct bfq_queue *bfqq;
+ bool new_queue = false;
+
+ bfqq = __bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+ &new_queue);
+ if (unlikely(new_queue))
+ return bfqq;
+
+ /* If the queue was seeky for too long, break it apart. */
+ if (!bfq_bfqq_coop(bfqq) || !bfq_bfqq_split_coop(bfqq) ||
+ bic->bfqq_data[idx].stably_merged)
+ return bfqq;
+
+ waker_bfqq = bfq_waker_bfqq(bfqq);
+
+ /* Update bic before losing reference to bfqq */
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bic->bfqq_data[idx].saved_in_large_burst = true;
+
+ bfqq = bfq_split_bfqq(bic, bfqq);
+ if (bfqq) {
+ bfq_bfqq_resume_state(bfqq, bfqd, bic, true);
+ return bfqq;
+ }
+
+ bfqq = __bfq_get_bfqq_handle_split(bfqd, bic, bio, true, is_sync, NULL);
+ if (unlikely(bfqq == &bfqd->oom_bfqq))
+ return bfqq;
+
+ bfq_bfqq_resume_state(bfqq, bfqd, bic, false);
+ bfqq->waker_bfqq = waker_bfqq;
+ bfqq->tentative_waker_bfqq = NULL;
+
+ /*
+ * If the waker queue disappears, then new_bfqq->waker_bfqq must be
+ * reset. So insert new_bfqq into the
+ * woken_list of the waker. See
+ * bfq_check_waker for details.
+ */
+ if (waker_bfqq)
+ hlist_add_head(&bfqq->woken_list_node,
+ &bfqq->waker_bfqq->woken_list);
+
+ return bfqq;
+}
+
/*
* If needed, init rq, allocate bfq data structures associated with
* rq, and increment reference counters in the destination bfq_queue
@@ -6856,8 +6928,6 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
struct bfq_io_cq *bic;
const int is_sync = rq_is_sync(rq);
struct bfq_queue *bfqq;
- bool new_queue = false;
- bool bfqq_already_existing = false, split = false;
unsigned int a_idx = bfq_actuator_index(bfqd, bio);
if (unlikely(!rq->elv.icq))
@@ -6874,54 +6944,9 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
return RQ_BFQQ(rq);
bic = icq_to_bic(rq->elv.icq);
-
bfq_check_ioprio_change(bic, bio);
-
bfq_bic_update_cgroup(bic, bio);
-
- bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
- &new_queue);
-
- if (likely(!new_queue)) {
- /* If the queue was seeky for too long, break it apart. */
- if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) &&
- !bic->bfqq_data[a_idx].stably_merged) {
- struct bfq_queue *old_bfqq = bfqq;
-
- /* Update bic before losing reference to bfqq */
- if (bfq_bfqq_in_large_burst(bfqq))
- bic->bfqq_data[a_idx].saved_in_large_burst =
- true;
-
- bfqq = bfq_split_bfqq(bic, bfqq);
- split = true;
-
- if (!bfqq) {
- bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
- true, is_sync,
- NULL);
- if (unlikely(bfqq == &bfqd->oom_bfqq))
- bfqq_already_existing = true;
- } else
- bfqq_already_existing = true;
-
- if (!bfqq_already_existing) {
- bfqq->waker_bfqq = old_bfqq->waker_bfqq;
- bfqq->tentative_waker_bfqq = NULL;
-
- /*
- * If the waker queue disappears, then
- * new_bfqq->waker_bfqq must be
- * reset. So insert new_bfqq into the
- * woken_list of the waker. See
- * bfq_check_waker for details.
- */
- if (bfqq->waker_bfqq)
- hlist_add_head(&bfqq->woken_list_node,
- &bfqq->waker_bfqq->woken_list);
- }
- }
- }
+ bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, a_idx, is_sync);
bfqq_request_allocated(bfqq);
bfqq->ref++;
@@ -6939,18 +6964,8 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
* resume its state.
*/
if (likely(bfqq != &bfqd->oom_bfqq) && !bfqq->new_bfqq &&
- bfqq_process_refs(bfqq) == 1) {
+ bfqq_process_refs(bfqq) == 1)
bfqq->bic = bic;
- if (split) {
- /*
- * The queue has just been split from a shared
- * queue: restore the idle window and the
- * possible weight raising period.
- */
- bfq_bfqq_resume_state(bfqq, bfqd, bic,
- bfqq_already_existing);
- }
- }
/*
* Consider bfqq as possibly belonging to a burst of newly
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index e16d96e2367b..687a3a7ba784 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -1185,11 +1185,6 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
"%s " fmt, pid_str, ##args); \
} while (0)
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
- blk_add_cgroup_trace_msg((bfqd)->queue, \
- &bfqg_to_blkg(bfqg)->blkcg->css, fmt, ##args); \
-} while (0)
-
#else /* CONFIG_BFQ_GROUP_IOSCHED */
#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
@@ -1199,7 +1194,6 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
bfq_bfqq_name((bfqq), pid_str, MAX_BFQQ_NAME_LENGTH); \
blk_add_trace_msg((bfqd)->queue, "%s " fmt, pid_str, ##args); \
} while (0)
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
#endif /* CONFIG_BFQ_GROUP_IOSCHED */
diff --git a/block/bio.c b/block/bio.c
index c4053d49679a..ac4d77c88932 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -931,7 +931,8 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
return false;
- *same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
+ *same_page = ((vec_end_addr & PAGE_MASK) == ((page_addr + off) &
+ PAGE_MASK));
if (!*same_page) {
if (IS_ENABLED(CONFIG_KMSAN))
return false;
@@ -1017,6 +1018,29 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
}
/**
+ * bio_add_hw_folio - attempt to add a folio to a bio with hw constraints
+ * @q: the target queue
+ * @bio: destination bio
+ * @folio: folio to add
+ * @len: vec entry length
+ * @offset: vec entry offset in the folio
+ * @max_sectors: maximum number of sectors that can be added
+ * @same_page: return if the segment has been merged inside the same folio
+ *
+ * Add a folio to a bio while respecting the hardware max_sectors, max_segment
+ * and gap limitations.
+ */
+int bio_add_hw_folio(struct request_queue *q, struct bio *bio,
+ struct folio *folio, size_t len, size_t offset,
+ unsigned int max_sectors, bool *same_page)
+{
+ if (len > UINT_MAX || offset > UINT_MAX)
+ return 0;
+ return bio_add_hw_page(q, bio, folio_page(folio, 0), len, offset,
+ max_sectors, same_page);
+}
+
+/**
* bio_add_pc_page - attempt to add page to passthrough bio
* @q: the target queue
* @bio: destination bio
@@ -1166,7 +1190,6 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
struct folio_iter fi;
bio_for_each_folio_all(fi, bio) {
- struct page *page;
size_t nr_pages;
if (mark_dirty) {
@@ -1174,12 +1197,9 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
folio_mark_dirty(fi.folio);
folio_unlock(fi.folio);
}
- page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
nr_pages = (fi.offset + fi.length - 1) / PAGE_SIZE -
fi.offset / PAGE_SIZE + 1;
- do {
- bio_release_page(bio, page++);
- } while (--nr_pages != 0);
+ unpin_user_folio(fi.folio, nr_pages);
}
}
EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1204,8 +1224,8 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
bio_set_flag(bio, BIO_CLONED);
}
-static int bio_iov_add_page(struct bio *bio, struct page *page,
- unsigned int len, unsigned int offset)
+static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len,
+ size_t offset)
{
bool same_page = false;
@@ -1214,30 +1234,61 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,
if (bio->bi_vcnt > 0 &&
bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
- page, len, offset, &same_page)) {
+ folio_page(folio, 0), len, offset,
+ &same_page)) {
bio->bi_iter.bi_size += len;
- if (same_page)
- bio_release_page(bio, page);
+ if (same_page && bio_flagged(bio, BIO_PAGE_PINNED))
+ unpin_user_folio(folio, 1);
return 0;
}
- __bio_add_page(bio, page, len, offset);
+ bio_add_folio_nofail(bio, folio, len, offset);
return 0;
}
-static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
- unsigned int len, unsigned int offset)
+static int bio_iov_add_zone_append_folio(struct bio *bio, struct folio *folio,
+ size_t len, size_t offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
bool same_page = false;
- if (bio_add_hw_page(q, bio, page, len, offset,
+ if (bio_add_hw_folio(q, bio, folio, len, offset,
queue_max_zone_append_sectors(q), &same_page) != len)
return -EINVAL;
- if (same_page)
- bio_release_page(bio, page);
+ if (same_page && bio_flagged(bio, BIO_PAGE_PINNED))
+ unpin_user_folio(folio, 1);
return 0;
}
+static unsigned int get_contig_folio_len(unsigned int *num_pages,
+ struct page **pages, unsigned int i,
+ struct folio *folio, size_t left,
+ size_t offset)
+{
+ size_t bytes = left;
+ size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, bytes);
+ unsigned int j;
+
+ /*
+ * We might COW a single page in the middle of
+ * a large folio, so we have to check that all
+ * pages belong to the same folio.
+ */
+ bytes -= contig_sz;
+ for (j = i + 1; j < i + *num_pages; j++) {
+ size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+ if (page_folio(pages[j]) != folio ||
+ pages[j] != pages[j - 1] + 1) {
+ break;
+ }
+ contig_sz += next;
+ bytes -= next;
+ }
+ *num_pages = j - i;
+
+ return contig_sz;
+}
+
#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
/**
@@ -1257,9 +1308,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
- ssize_t size, left;
- unsigned len, i = 0;
- size_t offset;
+ ssize_t size;
+ unsigned int num_pages, i = 0;
+ size_t offset, folio_offset, left, len;
int ret = 0;
/*
@@ -1299,17 +1350,28 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
goto out;
}
- for (left = size, i = 0; left > 0; left -= len, i++) {
+ for (left = size, i = 0; left > 0; left -= len, i += num_pages) {
struct page *page = pages[i];
+ struct folio *folio = page_folio(page);
+
+ folio_offset = ((size_t)folio_page_idx(folio, page) <<
+ PAGE_SHIFT) + offset;
+
+ len = min(folio_size(folio) - folio_offset, left);
+
+ num_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+
+ if (num_pages > 1)
+ len = get_contig_folio_len(&num_pages, pages, i,
+ folio, left, offset);
- len = min_t(size_t, PAGE_SIZE - offset, left);
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
- ret = bio_iov_add_zone_append_page(bio, page, len,
- offset);
+ ret = bio_iov_add_zone_append_folio(bio, folio, len,
+ folio_offset);
if (ret)
break;
} else
- bio_iov_add_page(bio, page, len, offset);
+ bio_iov_add_folio(bio, folio, len, folio_offset);
offset = 0;
}
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 5a6098a3db57..9dc9323f84ac 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -648,7 +648,7 @@ static const struct ioc_params autop[] = {
* vrate adjust percentages indexed by ioc->busy_level. We adjust up on
* vtime credit shortage and down on device saturation.
*/
-static u32 vrate_adj_pct[] =
+static const u32 vrate_adj_pct[] =
{ 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 36abbaefe387..3f1f7d0b3ff3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2753,6 +2753,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request *rq;
+ unsigned int depth;
/*
* We may have been called recursively midway through handling
@@ -2763,6 +2764,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
*/
if (plug->rq_count == 0)
return;
+ depth = plug->rq_count;
plug->rq_count = 0;
if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
@@ -2770,6 +2772,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
rq = rq_list_peek(&plug->mq_list);
q = rq->q;
+ trace_block_unplug(q, depth, true);
/*
* Peek first request and see if we have a ->queue_rqs() hook.
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index dc6140fa3de0..9c5bbd261724 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1595,6 +1595,22 @@ void blk_throtl_cancel_bios(struct gendisk *disk)
spin_unlock_irq(&q->queue_lock);
}
+static bool tg_within_limit(struct throtl_grp *tg, struct bio *bio, bool rw)
+{
+ /* throtl is FIFO - if bios are already queued, should queue */
+ if (tg->service_queue.nr_queued[rw])
+ return false;
+
+ return tg_may_dispatch(tg, bio, NULL);
+}
+
+static void tg_dispatch_in_debt(struct throtl_grp *tg, struct bio *bio, bool rw)
+{
+ if (!bio_flagged(bio, BIO_BPS_THROTTLED))
+ tg->carryover_bytes[rw] -= throtl_bio_data_size(bio);
+ tg->carryover_ios[rw]--;
+}
+
bool __blk_throtl_bio(struct bio *bio)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
@@ -1611,34 +1627,35 @@ bool __blk_throtl_bio(struct bio *bio)
sq = &tg->service_queue;
while (true) {
- if (tg->last_low_overflow_time[rw] == 0)
- tg->last_low_overflow_time[rw] = jiffies;
- /* throtl is FIFO - if bios are already queued, should queue */
- if (sq->nr_queued[rw])
- break;
-
- /* if above limits, break to queue */
- if (!tg_may_dispatch(tg, bio, NULL)) {
- tg->last_low_overflow_time[rw] = jiffies;
+ if (tg_within_limit(tg, bio, rw)) {
+ /* within limits, let's charge and dispatch directly */
+ throtl_charge_bio(tg, bio);
+
+ /*
+ * We need to trim slice even when bios are not being
+ * queued otherwise it might happen that a bio is not
+ * queued for a long time and slice keeps on extending
+ * and trim is not called for a long time. Now if limits
+ * are reduced suddenly we take into account all the IO
+ * dispatched so far at new low rate and * newly queued
+ * IO gets a really long dispatch time.
+ *
+ * So keep on trimming slice even if bio is not queued.
+ */
+ throtl_trim_slice(tg, rw);
+ } else if (bio_issue_as_root_blkg(bio)) {
+ /*
+ * IOs which may cause priority inversions are
+ * dispatched directly, even if they're over limit.
+ * Debts are handled by carryover_bytes/ios while
+ * calculating wait time.
+ */
+ tg_dispatch_in_debt(tg, bio, rw);
+ } else {
+ /* if above limits, break to queue */
break;
}
- /* within limits, let's charge and dispatch directly */
- throtl_charge_bio(tg, bio);
-
- /*
- * We need to trim slice even when bios are not being queued
- * otherwise it might happen that a bio is not queued for
- * a long time and slice keeps on extending and trim is not
- * called for a long time. Now if limits are reduced suddenly
- * we take into account all the IO dispatched so far at new
- * low rate and * newly queued IO gets a really long dispatch
- * time.
- *
- * So keep on trimming slice even if bio is not queued.
- */
- throtl_trim_slice(tg, rw);
-
/*
* @bio passed through this layer without being throttled.
* Climb up the ladder. If we're already at the top, it
@@ -1661,8 +1678,6 @@ bool __blk_throtl_bio(struct bio *bio)
tg->io_disp[rw], tg_iops_limit(tg, rw),
sq->nr_queued[READ], sq->nr_queued[WRITE]);
- tg->last_low_overflow_time[rw] = jiffies;
-
td->nr_queued[rw]++;
throtl_add_bio_tg(bio, qn, tg);
throttled = true;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 4d9ef5abdf21..1a36d1278eea 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -106,8 +106,6 @@ struct throtl_grp {
/* Number of bio's dispatched in current slice */
unsigned int io_disp[2];
- unsigned long last_low_overflow_time[2];
-
uint64_t last_bytes_disp[2];
unsigned int last_io_disp[2];
diff --git a/block/blk.h b/block/blk.h
index 32f4e9f630a3..86affb583eb6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -574,6 +574,10 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
unsigned int max_sectors, bool *same_page);
+int bio_add_hw_folio(struct request_queue *q, struct bio *bio,
+ struct folio *folio, size_t len, size_t offset,
+ unsigned int max_sectors, bool *same_page);
+
/*
* Clean up a page appropriately, where the page may be pinned, may have a
* ref taken on it or neither.
diff --git a/block/partitions/core.c b/block/partitions/core.c
index ab76e64f0f6c..5bd7a603092e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -555,9 +555,11 @@ static bool blk_add_partition(struct gendisk *disk,
part = add_partition(disk, p, from, size, state->parts[p].flags,
&state->parts[p].info);
- if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
- printk(KERN_ERR " %s: p%d could not be added: %pe\n",
- disk->disk_name, p, part);
+ if (IS_ERR(part)) {
+ if (PTR_ERR(part) != -ENXIO) {
+ printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+ disk->disk_name, p, part);
+ }
return true;
}
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index e858e7e0383f..c2b6c4d9729d 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -876,7 +876,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns)
ns.disk == D_OUTDATED)
rv = SS_CONNECTED_OUTDATES;
- else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
+ else if (nc && (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
(nc->verify_alg[0] == 0))
rv = SS_NO_VERIFY_ALG;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c6ef0546ffc9..11901f2812ad 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2269,25 +2269,12 @@ static const struct file_operations mtip_flags_fops = {
.llseek = no_llseek,
};
-static int mtip_hw_debugfs_init(struct driver_data *dd)
+static void mtip_hw_debugfs_init(struct driver_data *dd)
{
- if (!dfs_parent)
- return -1;
-
dd->dfs_node = debugfs_create_dir(dd->disk->disk_name, dfs_parent);
- if (IS_ERR_OR_NULL(dd->dfs_node)) {
- dev_warn(&dd->pdev->dev,
- "Error creating node %s under debugfs\n",
- dd->disk->disk_name);
- dd->dfs_node = NULL;
- return -1;
- }
-
debugfs_create_file("flags", 0444, dd->dfs_node, dd, &mtip_flags_fops);
debugfs_create_file("registers", 0444, dd->dfs_node, dd,
&mtip_regs_fops);
-
- return 0;
}
static void mtip_hw_debugfs_exit(struct driver_data *dd)
@@ -4043,10 +4030,6 @@ static int __init mtip_init(void)
mtip_major = error;
dfs_parent = debugfs_create_dir("rssd", NULL);
- if (IS_ERR_OR_NULL(dfs_parent)) {
- pr_warn("Error creating debugfs parent\n");
- dfs_parent = NULL;
- }
/* Register our PCI operations. */
error = pci_register_driver(&mtip_pci_driver);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c4b238a20b76..2fd88cd5997d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1597,6 +1597,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
bool make_dirty);
void unpin_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_folio(struct folio *folio, unsigned long npages);
void unpin_folios(struct folio **folios, unsigned long nfolios);
static inline bool is_cow_mapping(vm_flags_t flags)
diff --git a/mm/gup.c b/mm/gup.c
index 54d0dc3831fb..02c46ae33028 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -416,6 +416,19 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
EXPORT_SYMBOL(unpin_user_pages);
/**
+ * unpin_user_folio() - release pages of a folio
+ * @folio: pointer to folio to be released
+ * @npages: number of pages of same folio
+ *
+ * Release npages of the folio
+ */
+void unpin_user_folio(struct folio *folio, unsigned long npages)
+{
+ gup_put_folio(folio, npages, FOLL_PIN);
+}
+EXPORT_SYMBOL(unpin_user_folio);
+
+/**
* unpin_folios() - release an array of gup-pinned folios.
* @folios: array of folios to be marked dirty and released.
* @nfolios: number of folios in the @folios array.