[Devel] [PATCH RHEL9 COMMIT] dm-ploop: convert enospc handling to use lockless lists

[Konstantin Khorenko]

The commit is pushed to "branch-rh9-5.14.0-427.44.1.vz9.80.x-ovz" and will appear at git at bitbucket.org:openvz/vzkernel.git
after rh9-5.14.0-427.44.1.vz9.80.6
------>
commit 818f30259604dc696d0a0dc79ba79471499c980c
Author: Alexander Atanasov <alexander.atanasov at virtuozzo.com>
Date:   Fri Jan 24 17:35:40 2025 +0200

    dm-ploop: convert enospc handling to use lockless lists
    
    https://virtuozzo.atlassian.net/browse/VSTOR-91820
    Signed-off-by: Alexander Atanasov <alexander.atanasov at virtuozzo.com>
    
    ======
    Patchset description:
    ploop: optimistations and scalling
    
    Ploop processes requsts in a different threads in parallel
    where possible which results in significant improvement in
    performance and makes further optimistations possible.
    
    Known bugs:
      - delayed metadata writeback is not working and is missing error handling
         - patch to disable it until fixed
      - fast path is not working - causes rcu lockups - patch to disable it
    
    Further improvements:
      - optimize md pages lookups
    
    Alexander Atanasov (50):
      dm-ploop: md_pages map all pages at creation time
      dm-ploop: Use READ_ONCE/WRITE_ONCE to access md page data
      dm-ploop: fsync after all pios are sent
      dm-ploop: move md status to use proper bitops
      dm-ploop: convert wait_list and wb_batch_llist to use lockless lists
      dm-ploop: convert enospc handling to use lockless lists
      dm-ploop: convert suspended_pios list to use lockless list
      dm-ploop: convert the rest of the lists to use llist variant
      dm-ploop: combine processing of pios thru prepare list and remove
        fsync worker
      dm-ploop: move from wq to kthread
      dm-ploop: move preparations of pios into the caller from worker
      dm-ploop: fast path execution for reads
      dm-ploop: do not use a wrapper for set_bit to make a page writeback
      dm-ploop: BAT use only one list for writeback
      dm-ploop: make md writeback timeout to be per page
      dm-ploop: add interface to disable bat writeback delay
      dm-ploop: convert wb_batch_list to lockless variant
      dm-ploop: convert high_prio to status
      dm-ploop: split cow processing into two functions
      dm-ploop: convert md page rw lock to spin lock
      dm-ploop: convert bat_rwlock to bat_lock spinlock
      dm-ploop: prepare bat updates under bat_lock
      dm-ploop: make ploop_bat_write_complete ready for parallel pio
        completion
      dm-ploop: make ploop_submit_metadata_writeback return number of
        requests sent
      dm-ploop: introduce pio runner threads
      dm-ploop: add pio list ids to be used when passing pios to runners
      dm-ploop: process pios via runners
      dm-ploop: disable metadata writeback delay
      dm-ploop: disable fast path
      dm-ploop: use lockless lists for chained cow updates list
      dm-ploop: use lockless lists for data ready pios
      dm-ploop: give runner threads better name
      dm-ploop: resize operation - add holes bitmap locking
      dm-ploop: remove unnecessary operations
      dm-ploop: use filp per thread
      dm-ploop: catch if we try to advance pio past bio end
      dm-ploop: support REQ_FUA for data pios
      dm-ploop: proplerly access nr_bat_entries
      dm-ploop: fix locking and improve error handling when submitting pios
      dm-ploop: fix how ENOTBLK is handled
      dm-ploop: sync when suspended or stopping
      dm-ploop: rework bat completion logic
      dm-ploop: rework logic in pio processing
      dm-ploop: end fsync pios in parallel
      dm-ploop: make filespace preallocations async
      dm-ploop: resubmit enospc pios from dispatcher thread
      dm-ploop: dm-ploop: simplify discard completion
      dm-ploop: use GFP_ATOMIC instead of GFP_NOIO
      dm-ploop: fix locks used in mixed context
      dm-ploop: fix how current flags are managed inside threads
    
    Andrey Zhadchenko (13):
      dm-ploop: do not flush after metadata writes
      dm-ploop: set IOCB_DSYNC on all FUA requests
      dm-ploop: remove extra ploop_cluster_is_in_top_delta()
      dm-ploop: introduce per-md page locking
      dm-ploop: reduce BAT accesses on discard completion
      dm-ploop: simplify llseek
      dm-ploop: speed up ploop_prepare_bat_update()
      dm-ploop: make new allocations immediately visible in BAT
      dm-ploop: drop ploop_cluster_is_in_top_delta()
      dm-ploop: do not wait for BAT update for non-FUA requests
      dm-ploop: add delay for metadata writeback
      dm-ploop: submit all postponed metadata on REQ_OP_FLUSH
      dm-ploop: handle REQ_PREFLUSH
    
    Feature: dm-ploop: ploop target driver
---
 drivers/md/dm-ploop-map.c    | 21 +++++++++++++--------
 drivers/md/dm-ploop-target.c |  3 ++-
 drivers/md/dm-ploop.h        |  2 +-
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index 5fb98740f32e..08d5391aa9d3 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -143,14 +143,19 @@ static void ploop_init_prq_and_embedded_pio(struct ploop *ploop,
 void ploop_enospc_timer(struct timer_list *timer)
 {
 	struct ploop *ploop = from_timer(ploop, timer, enospc_timer);
-	unsigned long flags;
 	LIST_HEAD(list);
+	struct llist_node *pos, *t;
+	struct llist_node *enospc_pending = llist_del_all(&ploop->enospc_pios);
 
-	spin_lock_irqsave(&ploop->deferred_lock, flags);
-	list_splice_init(&ploop->enospc_pios, &list);
-	spin_unlock_irqrestore(&ploop->deferred_lock, flags);
+	if (enospc_pending) {
+		enospc_pending = llist_reverse_order(enospc_pending);
+		llist_for_each_safe(pos, t, enospc_pending) {
+			struct pio *pio = list_entry((struct list_head *)pos, typeof(*pio), list);
 
-	ploop_submit_embedded_pios(ploop, &list);
+			list_add(&pio->list, &list);
+		}
+		ploop_submit_embedded_pios(ploop, &list);
+	}
 }
 
 void do_ploop_event_work(struct work_struct *ws)
@@ -166,7 +171,6 @@ static bool ploop_try_delay_enospc(struct ploop_rq *prq, struct pio *pio)
 	bool delayed = true;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ploop->deferred_lock, flags);
 	if (unlikely(ploop->wants_suspend)) {
 		delayed = false;
 		goto unlock;
@@ -176,10 +180,11 @@ static bool ploop_try_delay_enospc(struct ploop_rq *prq, struct pio *pio)
 
 	pr_err_once(PL_FMT("underlying disk is almost full"),
 		ploop_device_name(ploop));
+	spin_lock_irqsave(&ploop->deferred_lock, flags);
 	ploop->event_enospc = true;
-	list_add_tail(&pio->list, &ploop->enospc_pios);
-unlock:
 	spin_unlock_irqrestore(&ploop->deferred_lock, flags);
+	llist_add((struct llist_node *)(&pio->list), &ploop->enospc_pios);
+unlock:
 
 	if (delayed)
 		mod_timer(&ploop->enospc_timer, jiffies + PLOOP_ENOSPC_TIMEOUT);
diff --git a/drivers/md/dm-ploop-target.c b/drivers/md/dm-ploop-target.c
index b66ae3a9a4b0..3ac9e1f832f5 100644
--- a/drivers/md/dm-ploop-target.c
+++ b/drivers/md/dm-ploop-target.c
@@ -376,7 +376,8 @@ static int ploop_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		INIT_LIST_HEAD(&ploop->pios[i]);
 
 	INIT_LIST_HEAD(&ploop->resubmit_pios);
-	INIT_LIST_HEAD(&ploop->enospc_pios);
+	init_llist_head(&ploop->enospc_pios);
+
 	INIT_LIST_HEAD(&ploop->cluster_lk_list);
 	init_llist_head(&ploop->wb_batch_llist);
 	ploop->bat_entries = RB_ROOT;
diff --git a/drivers/md/dm-ploop.h b/drivers/md/dm-ploop.h
index b640bf275473..da5d8cfcf8ca 100644
--- a/drivers/md/dm-ploop.h
+++ b/drivers/md/dm-ploop.h
@@ -198,7 +198,7 @@ struct ploop {
 	struct list_head pios[PLOOP_LIST_COUNT];
 
 	struct list_head resubmit_pios; /* After partial IO */
-	struct list_head enospc_pios; /* Delayed after ENOSPC */
+	struct llist_head enospc_pios; /* Delayed after ENOSPC */
 
 	atomic_t service_pios;
 	struct wait_queue_head service_wq;