[Devel] [PATCH vz9 v2 65/65] dm-ploop: fix how current flags are managed inside threads

[Konstantin Khorenko]

From: Alexander Atanasov <alexander.atanasov at virtuozzo.com>

currently threads do

old_flags = current->flags;
current->flags |= ploop flags;
...
current->flags = old_flags;

this can break process flags

To fix this use  current_restore_flags(..) macro which only removes
our flags and it preserves any other flags.

https://virtuozzo.atlassian.net/browse/VSTOR-98626
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 | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/md/dm-ploop-map.c b/drivers/md/dm-ploop-map.c
index 0b934b83a176..4669efed3cc0 100644
--- a/drivers/md/dm-ploop-map.c
+++ b/drivers/md/dm-ploop-map.c
@@ -2149,6 +2149,7 @@ void ploop_resubmit_enospc_pios(struct ploop *ploop)
 		ploop_submit_embedded_pios(ploop, llist_reverse_order(enospc_pending));
 }
 
+#define PLOOP_PFLAGS (PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO)
 void do_ploop_run_work(struct ploop *ploop)
 {
 	LLIST_HEAD(deferred_pios);
@@ -2162,7 +2163,7 @@ void do_ploop_run_work(struct ploop *ploop)
 	int npios;
 	int force_md_update;
 
-	current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+	current->flags |= PLOOP_PFLAGS;
 
 	if (ploop->submit_enospc) {
 		ploop->submit_enospc = false;
@@ -2200,10 +2201,10 @@ void do_ploop_run_work(struct ploop *ploop)
 	 * put stick in the wheel - wait for all pios to be executed before doing metadata
 	 * we could gain a bit more iops if we can skip this wait but for now we can not
 	 */
-	current->flags = old_flags;
+	current_restore_flags(old_flags, PLOOP_PFLAGS);
 	wait_event_interruptible(ploop->dispatcher_wq_data,
 				 (!ploop_runners_have_pending(ploop)));
-	current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+	current->flags |= PLOOP_PFLAGS;
 
 	/* if we have a flush we must sync md data too */
 	force_md_update = !!llflush_pios | ploop->force_md_writeback;
@@ -2211,25 +2212,25 @@ void do_ploop_run_work(struct ploop *ploop)
 
 	if (npios) {
 		/* wait for metadata writeback to complete */
-		current->flags = old_flags;
+		current_restore_flags(old_flags, PLOOP_PFLAGS);
 		/* First wait all pios to be processed */
 		wait_event_interruptible(ploop->dispatcher_wq_data,
 					 (!ploop_runners_have_pending(ploop)));
-		current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+		current->flags |= PLOOP_PFLAGS;
 	}
 	if (llflush_pios || npios) {
 		/* Now process fsync pios after we have done all other */
 		npios = process_ploop_fsync_work(ploop, llflush_pios);
 		/* Since dispatcher is single thread no other work can be queued */
 		if (npios) {
-			current->flags = old_flags;
+			current_restore_flags(old_flags, PLOOP_PFLAGS);
 			wait_event_interruptible(ploop->dispatcher_wq_fsync,
 					!atomic_read(&ploop->kt_worker->fsync_pios));
-			current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+			current->flags |= PLOOP_PFLAGS;
 		}
 	}
 
-	current->flags = old_flags;
+	current_restore_flags(old_flags, PLOOP_PFLAGS);
 }
 
 void do_ploop_work(struct work_struct *ws)
@@ -2252,7 +2253,7 @@ int ploop_allocator(void *data)
 		if (ploop->prealloc_size) {
 			__set_current_state(TASK_RUNNING);
 			file = ploop_top_delta(ploop)->file;
-			current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+			current->flags |= PLOOP_PFLAGS;
 			ret = ploop_preallocate_cluster(ploop, file);
 			if (ret) {
 				/*
@@ -2265,7 +2266,7 @@ int ploop_allocator(void *data)
 					       ploop_device_name(ploop), ret);
 			}
 			wake_up_interruptible(&ploop->dispatcher_wq_prealloc);
-			current->flags = old_flags;
+			current_restore_flags(old_flags, PLOOP_PFLAGS);
 		}
 		if (kthread_should_stop()) {
 			__set_current_state(TASK_RUNNING);
@@ -2290,7 +2291,7 @@ int ploop_pio_runner(void *data)
 	int did_process_fsync = 0;
 
 	for (;;) {
-		current->flags = old_flags;
+		current_restore_flags(old_flags, PLOOP_PFLAGS);
 		set_current_state(TASK_INTERRUPTIBLE);
 
 check_for_more:
@@ -2313,8 +2314,7 @@ int ploop_pio_runner(void *data)
 			continue;
 		}
 		__set_current_state(TASK_RUNNING);
-		old_flags = current->flags;
-		current->flags |= PF_IO_THREAD|PF_LOCAL_THROTTLE|PF_MEMALLOC_NOIO;
+		current->flags |= PLOOP_PFLAGS;
 
 		llist_for_each_safe(pos, t, llwork) {
 			pio = llist_entry(pos, typeof(*pio), llist);
-- 
2.43.5