[Devel] [PATCH hci-8.1 v6 7/7] block/blk-cbt: account a write request also when dm starts it

[Pavel Tikhomirov <ptikhomirov@virtuozzo.com>]

CBT accounts a write at bio submission. dm suspend of request based dm
waits only for started requests, so a request submitted before the
suspend but dispatched after resume is accounted before a backup point
taken under the suspend (BLKCBTSTART, CBT_SNAP_CREATE) while its data
lands after it. push_backup then saves the old data, and no incremental
backup copies the new one.

Account a write again when dm starts it. This runs under the dispatch
rcu_read_lock(), so it can't allocate: it sets the bits directly in the
bitmap pages, and the allocation of missing pages is now queued to the
kblockd workqueue already at submission. If a page is still missing when
dm starts the request (the work did not run yet, or the write was
submitted before BLKCBTSTART), dm returns BLK_STS_RESOURCE, so that
blk-mq dispatches the request again later.

https://virtuozzo.atlassian.net/browse/VSTOR-149268
Feature: cbt: changed block tracking (for backup)
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
---
 block/blk-cbt.c        | 175 +++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/md/dm-rq.c     |   3 +
 include/linux/blkdev.h |   5 ++
 3 files changed, 183 insertions(+)

diff --git a/block/blk-cbt.c b/block/blk-cbt.c
index 5535480847405..c114fb63cc134 100644
--- a/block/blk-cbt.c
+++ b/block/blk-cbt.c
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/list.h>
@@ -58,6 +59,10 @@ struct cbt_info {
 	struct page **snp_map;
 	blkcnt_t snp_block_max;
 
+	/* Map pages to allocate, see cbt_alloc_work_fn() */
+	unsigned long *missing;
+	struct work_struct alloc_work;
+
 	spinlock_t lock;
 	struct list_head list;
 };
@@ -231,6 +236,85 @@ static int __blk_cbt_set(struct cbt_info  *cbt, blkcnt_t block,
 	return (pages_missed && *pages_missed) ? -EAGAIN : 0;
 }
 
+/* Drop a cbt->count reference, release the cbt if it is dead */
+static void cbt_put(struct cbt_info *cbt)
+{
+	unsigned long flags;
+	bool release;
+
+	spin_lock_irqsave(&cbt->lock, flags);
+	release = !--cbt->count && test_bit(CBT_DEAD, &cbt->flags);
+	spin_unlock_irqrestore(&cbt->lock, flags);
+	if (release)
+		call_srcu(&cbt_srcu, &cbt->rcu, &cbt_release_callback);
+}
+
+/* Allocate the map pages queued in cbt->missing */
+static void cbt_alloc_work_fn(struct work_struct *work)
+{
+	struct cbt_info *cbt = container_of(work, struct cbt_info, alloc_work);
+	unsigned long idx;
+
+	for_each_set_bit(idx, cbt->missing, NR_PAGES(cbt->block_max)) {
+		struct page *page;
+
+		clear_bit(idx, cbt->missing);
+		if (CBT_PAGE(cbt, idx))
+			continue;
+
+		page = alloc_page(GFP_NOIO | __GFP_ZERO);
+		spin_lock_irq(&cbt->lock);
+		if (!CBT_PAGE(cbt, idx) && !test_bit(CBT_DEAD, &cbt->flags)) {
+			if (page) {
+				/* Release: lockless readers use the page */
+				smp_store_release(&cbt->map[idx], page);
+				page = NULL;
+			} else {
+				set_bit(CBT_ERROR, &cbt->flags);
+			}
+		}
+		spin_unlock_irq(&cbt->lock);
+		if (page)
+			__free_page(page);
+	}
+	cbt_put(cbt);
+}
+
+static void cbt_queue_alloc(struct cbt_info *cbt, unsigned long idx)
+{
+	unsigned long flags;
+
+	/* Already queued: the work allocates it */
+	if (test_and_set_bit(idx, cbt->missing))
+		return;
+	spin_lock_irqsave(&cbt->lock, flags);
+	if (test_bit(CBT_DEAD, &cbt->flags)) {
+		spin_unlock_irqrestore(&cbt->lock, flags);
+		return;
+	}
+	cbt->count++;
+	spin_unlock_irqrestore(&cbt->lock, flags);
+
+	/* The queued work drops the reference, or drop it if already queued */
+	if (!kblockd_schedule_work(&cbt->alloc_work))
+		cbt_put(cbt);
+}
+
+/* Queue the allocation of the missing map pages for [block, block + count) */
+static void cbt_queue_alloc_pages(struct cbt_info *cbt, blkcnt_t block,
+				  blkcnt_t count)
+{
+	unsigned long idx, last;
+
+	if (unlikely(!count || block + count > cbt->block_max))
+		return;
+
+	last = (block + count - 1) / BITS_PER_PAGE;
+	for (idx = block / BITS_PER_PAGE; idx <= last; idx++)
+		if (!CBT_PAGE(cbt, idx))
+			cbt_queue_alloc(cbt, idx);
+}
+
 /* Return true if all the map pages for [block, block + count) are there */
 static bool cbt_pages_present(struct cbt_info *cbt, blkcnt_t block,
 			      blkcnt_t count)
@@ -272,6 +356,8 @@ static bool blk_cbt_add(struct cbt_info *cbt, blkcnt_t start, blkcnt_t len,
 		__blk_cbt_set(cbt, start, len, 1, NULL, NULL);
 		return false;
 	}
+	/* Queue the allocation early, so blk_cbt_rq_start() finds the pages */
+	cbt_queue_alloc_pages(cbt, start, len);
 	ex = get_cpu_ptr(cbt->cache);
 	if (ex->start + ex->len == start) {
 		ex->len += len;
@@ -316,6 +402,86 @@ bool blk_cbt_bio_queue(struct request_queue *q, struct bio *bio, bool nowait)
 	return wouldblock;
 }
 
+/*
+ * Set the bits of [start, start + len) in the present pages, without
+ * allocating. Return true if a page is missing, its allocation is queued.
+ */
+static bool cbt_set_present(struct cbt_info *cbt, blkcnt_t start, blkcnt_t len)
+{
+	blkcnt_t block, end;
+	unsigned long flags;
+	bool missing = false;
+
+	end = DIV_ROUND_UP(start + len, 1UL << cbt->block_bits);
+	block = start >> cbt->block_bits;
+	if (unlikely(end > cbt->block_max)) {
+		set_bit(CBT_ERROR, &cbt->flags);
+		return false;
+	}
+
+	while (block < end) {
+		unsigned long idx = block / BITS_PER_PAGE;
+		unsigned long off = block & (BITS_PER_PAGE - 1);
+		unsigned long n = min_t(unsigned long, BITS_PER_PAGE - off,
+					end - block);
+		struct page *page = CBT_PAGE(cbt, idx);
+
+		if (page) {
+			local_irq_save(flags);
+			spin_lock_page(page);
+			set_bits(page_address(page), off, n, 1);
+			unlock_page(page);
+			local_irq_restore(flags);
+		} else {
+			cbt_queue_alloc(cbt, idx);
+			missing = true;
+		}
+		block += n;
+	}
+
+	return missing;
+}
+
+/*
+ * Account a write again when request based dm starts it: dm suspend waits
+ * only for started requests, so one accounted at submission before a
+ * backup point taken under suspend may still reach the disk after it.
+ *
+ * Runs under the dispatch rcu_read_lock() (blk_mq_run_dispatch_ops()), so
+ * it must not sleep: if a bitmap page is missing, its allocation is queued
+ * and true is returned, for dm to retry the request later.
+ */
+bool blk_cbt_rq_start(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct cbt_info *cbt;
+	struct bio *bio;
+	bool retry = false;
+	int idx;
+
+	if (likely(list_empty(&q->cbt_list)))
+		return false;
+	if (rq_data_dir(rq) == READ || blk_rq_is_passthrough(rq))
+		return false;
+
+	idx = srcu_read_lock(&cbt_srcu);
+	list_for_each_entry_srcu(cbt, &q->cbt_list, list,
+				 srcu_read_lock_held(&cbt_srcu)) {
+		if (unlikely(test_bit(CBT_ERROR, &cbt->flags)))
+			continue;
+		__rq_for_each_bio(bio, rq) {
+			if (bio->bi_iter.bi_size &&
+			    cbt_set_present(cbt, bio->bi_iter.bi_sector << 9,
+					    bio->bi_iter.bi_size))
+				retry = true;
+		}
+	}
+	srcu_read_unlock(&cbt_srcu, idx);
+
+	return retry;
+}
+EXPORT_SYMBOL_GPL(blk_cbt_rq_start);
+
 static struct cbt_info *do_cbt_alloc(struct request_queue *q, __u8 *name,
 				     loff_t size, loff_t blocksize)
 {
@@ -338,8 +504,16 @@ static struct cbt_info *do_cbt_alloc(struct request_queue *q, __u8 *name,
 		goto err_pcpu;
 
 	memset(cbt->map, 0, NR_PAGES(cbt->block_max) * sizeof(void*));
+
+	cbt->missing = bitmap_zalloc(NR_PAGES(cbt->block_max), GFP_KERNEL);
+	if (!cbt->missing)
+		goto err_map;
+	INIT_WORK(&cbt->alloc_work, cbt_alloc_work_fn);
+
 	cbt->queue = q;
 	return cbt;
+err_map:
+	vfree(cbt->map);
 err_pcpu:
 	free_percpu(cbt->cache);
 err_cbt:
@@ -721,6 +895,7 @@ static void cbt_release_callback(struct rcu_head *head)
 		free_map(cbt->snp_map, nr_pages);
 	}
 
+	bitmap_free(cbt->missing);
 	free_percpu(cbt->cache);
 	kfree(cbt);
 }
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 20f495bf5399d..5a8cd59ec257f 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -522,6 +522,9 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (ti->type->busy && ti->type->busy(ti))
 		return BLK_STS_RESOURCE;
 
+	if (blk_cbt_rq_start(rq))
+		return BLK_STS_RESOURCE;
+
 	dm_start_request(md, rq);
 
 	/* Init tio using md established in .init_request */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 885555f480462..9698a582356a9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1628,6 +1628,7 @@ extern void blk_cbt_update_size(struct block_device *bdev);
 extern void blk_cbt_release(struct request_queue *q);
 extern bool blk_cbt_bio_queue(struct request_queue *q, struct bio *bio,
 			      bool nowait);
+extern bool blk_cbt_rq_start(struct request *rq);
 extern int blk_cbt_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg);
 #else /* CONFIG_BLK_DEV_CBT */
 static inline void blk_cbt_update_size(struct block_device *bdev)
@@ -1641,6 +1642,10 @@ static inline bool blk_cbt_bio_queue(struct request_queue *q, struct bio *bio,
 {
 	return false;
 }
+static inline bool blk_cbt_rq_start(struct request *rq)
+{
+	return false;
+}
 static inline int blk_cbt_ioctl(struct block_device *bdev, unsigned cmd,
 				char __user *arg)
 {

-- 
2.55.0

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel