[RFC PATCH v2 19/25] iommu/dma: Stop recycling old PISA pages when allocator waste is high

[Luigi Rizzo]

When a PISA allocator holds many partially used 2MB pages with low
overall utilization, callers that recycle blocks in place (page_pool,
per-task TX page_frags, and per-CPU block caches) can keep old 2MB pages
pinned indefinitely with only a few blocks in use.

Record @alloc_jiffies in struct pisa_meta when a 2MB page is bound to an
allocator or taken from the allocator's idle list, and add two module
parameters:
- pisa.wasted_pct (1..99%, 0 disables): wasted block percentage
  threshold above which compaction kicks in.
- pisa.old_ms (1..100000 ms, 0 disables): age threshold after which a
  partially used 2MB page is eligible to stop recycling.

When both parameters are set and an allocator's wasted block fraction
exceeds wasted_pct, pisa_page_can_recycle() returns false for partial
2MB pages older than old_ms (except the head page actively being
filled).

Signed-off-by: Luigi Rizzo <lrizzo@xxxxxxxxxx>
---
 drivers/iommu/pisa-alloc.c | 48 ++++++++++++++++++++++++++++++++------
 drivers/iommu/pisa-priv.h  |  2 ++
 2 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/pisa-alloc.c b/drivers/iommu/pisa-alloc.c
index 1930135880d2b..5054a96f0f4e9 100644
--- a/drivers/iommu/pisa-alloc.c
+++ b/drivers/iommu/pisa-alloc.c
@@ -74,6 +74,14 @@ module_param_named(idle_ms, pisa_idle_ms, uint, 0644);
 static unsigned int pisa_compact __read_mostly;
 module_param_named(compact, pisa_compact, uint, 0644);
 
+/* Stop recycling partial pages older than @pisa_old_ms when wasted blocks > @pisa_wasted_pct%. */
+#define PISA_OLD_MS_MAX		100000U
+static unsigned int pisa_wasted_pct __read_mostly;
+module_param_named(wasted_pct, pisa_wasted_pct, uint, 0644);
+
+static unsigned int pisa_old_ms __read_mostly;
+module_param_named(old_ms, pisa_old_ms, uint, 0644);
+
 /* Max pages zeroed in each scrubber run (0 = disabled, capped at PISA_SCRUB_MAX_LIMIT). */
 unsigned int pisa_scrub_max __read_mostly;
 #define PISA_SCRUB_MAX_LIMIT	65536U
@@ -399,6 +407,7 @@ static struct pisa_meta *pisa_pick_dirty_meta(struct pisa_alloc *pa)
 		meta = list_last_entry(&pa->idle, struct pisa_meta, list);
 		if (meta->nr_dirty) {
 			pa->num_idle_pages--;
+			WRITE_ONCE(meta->alloc_jiffies, jiffies);
 			return meta;
 		}
 	}
@@ -603,7 +612,7 @@ static void pisa_return_block_locked(struct pisa_alloc *pa, struct page *block,
  * pisa_page_can_recycle - Check if a block can stay cached in a caller pool
  * @page: Block head page
  *
- * Called on the recycle fast path (per-CPU cache, TX page_frag, page_pool).
+ * Called on the recycle fast path (per-CPU cache, TX page_frag).
  * Fast-path cost is a static-key branch plus a READ_ONCE() of module parameters
  * (~1-2 ns when compaction is off); when enabled, it does a lockless RCU +
  * metadata array lookup (~5-10 ns).
@@ -613,10 +622,11 @@ static void pisa_return_block_locked(struct pisa_alloc *pa, struct page *block,
  */
 bool pisa_page_can_recycle(const struct page *page)
 {
-	unsigned long bpp, in_use, free_blocks, pfn;
+	unsigned int compact, wasted_pct, old_ms;
+	unsigned long bpp, in_use, free_blocks;
 	const struct pisa_meta *meta;
 	const struct pisa_alloc *pa;
-	unsigned int compact;
+	unsigned long pfn;
 	bool ret = true;
 	u8 on_list;
 	long held;
@@ -625,7 +635,9 @@ bool pisa_page_can_recycle(const struct page *page)
 		return true;
 
 	compact = READ_ONCE(pisa_compact);
-	if (!compact)
+	wasted_pct = READ_ONCE(pisa_wasted_pct);
+	old_ms = READ_ONCE(pisa_old_ms);
+	if (!compact && (!wasted_pct || !old_ms))
 		return true;
 
 	pfn = page_to_pfn(page);
@@ -638,6 +650,13 @@ bool pisa_page_can_recycle(const struct page *page)
 	if (on_list == PISA_LIST_FULL || on_list == PISA_LIST_NONE)
 		goto out;
 
+	if (!compact) {
+		unsigned long max_age = msecs_to_jiffies(min(old_ms, PISA_OLD_MS_MAX));
+
+		if (!time_after(jiffies, READ_ONCE(meta->alloc_jiffies) + max_age))
+			goto out;
+	}
+
 	pa = meta->pa;
 	if (!pa)
 		goto out;
@@ -657,12 +676,21 @@ bool pisa_page_can_recycle(const struct page *page)
 	free_blocks = held > 0 && (unsigned long)held * bpp > in_use ?
 		      (unsigned long)held * bpp - in_use : 0;
 
-	ret = free_blocks <= (unsigned long)compact * bpp;
+	if (compact && free_blocks > (unsigned long)compact * bpp) {
+		ret = false;
+		goto out;
+	}
+	if (wasted_pct && old_ms && held > 0 &&
+	    free_blocks * 100 > (unsigned long)held * bpp * wasted_pct) {
+		unsigned long max_age = msecs_to_jiffies(min(old_ms, PISA_OLD_MS_MAX));
+
+		ret = !time_after(jiffies, READ_ONCE(meta->alloc_jiffies) + max_age);
+	}
 out:
 	rcu_read_unlock();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(pisa_page_can_recycle);
+EXPORT_SYMBOL(pisa_page_can_recycle);
 
 /* Return @n freed blocks to @pa under a single acquisition of @pa->lock. */
 static void pisa_free_bulk(struct pisa_alloc *pa, struct page **blocks, unsigned int n)
@@ -1195,6 +1223,7 @@ static struct pisa_meta *pisa_pick_meta(struct pisa_alloc *pa, bool zero)
 		meta = list_first_entry_or_null(&pa->idle, struct pisa_meta, list);
 		if (meta && meta->nr_clean) {
 			pa->num_idle_pages--;
+			WRITE_ONCE(meta->alloc_jiffies, jiffies);
 			WRITE_ONCE(pa->idle_jiffies, jiffies);
 			return meta;
 		}
@@ -1218,6 +1247,7 @@ static struct pisa_meta *pisa_pick_meta(struct pisa_alloc *pa, bool zero)
 	if (!list_empty(&pa->idle)) {
 		meta = list_last_entry(&pa->idle, struct pisa_meta, list);
 		pa->num_idle_pages--;
+		WRITE_ONCE(meta->alloc_jiffies, jiffies);
 		WRITE_ONCE(pa->idle_jiffies, jiffies);
 		return meta;
 	}
@@ -1287,6 +1317,7 @@ static unsigned long __pisa_alloc_bulk(struct pisa_alloc *pa, gfp_t gfp, unsigne
 		spin_lock_irqsave(&pa->lock, flags);
 		meta->pa = pa;
 		meta->prot = pa->prot;
+		WRITE_ONCE(meta->alloc_jiffies, jiffies);
 		/* Set PISA_ACTIVE after @meta is fully set up. */
 		WRITE_ONCE(meta->flags, meta->flags | PISA_ACTIVE);
 		pa->stats.page_alloc_cnt++;
@@ -1454,8 +1485,10 @@ static struct page *pisa_take_contig(struct pisa_meta *meta, unsigned int nblock
 	}
 
 	if (meta->on_list == PISA_LIST_IDLE_CLEAN ||
-	    meta->on_list == PISA_LIST_IDLE_DIRTY)
+	    meta->on_list == PISA_LIST_IDLE_DIRTY) {
 		pa->num_idle_pages--;
+		WRITE_ONCE(meta->alloc_jiffies, jiffies);
+	}
 
 	for (i = 0; i < nblocks; i++) {
 		if (__test_and_clear_bit(off + i, meta->clean_bitmap)) {
@@ -1544,6 +1577,7 @@ void *pisa_alloc_coherent(struct page **pagep, struct device *dev,
 		spin_lock_irqsave(&pa->lock, flags);
 		meta->pa = pa;
 		meta->prot = pa->prot;
+		WRITE_ONCE(meta->alloc_jiffies, jiffies);
 		WRITE_ONCE(meta->flags, meta->flags | PISA_ACTIVE);
 		pa->stats.page_alloc_cnt++;
 		page = pisa_take_contig(meta, nblocks, align_mask);
diff --git a/drivers/iommu/pisa-priv.h b/drivers/iommu/pisa-priv.h
index fe1bff0bba322..4d04bb191ecea 100644
--- a/drivers/iommu/pisa-priv.h
+++ b/drivers/iommu/pisa-priv.h
@@ -74,6 +74,7 @@ enum {
  * @list:	Node in @pa lists or per-node reservoir (pisa_node.pages)
  * @llnode:	Node in lockless pisa_free_list for async release to the buddy allocator
  * @rcu:	RCU head used to defer release to the buddy allocator
+ * @alloc_jiffies: Timestamp (jiffies) when the page entered or re-entered use
  * @clean_bitmap: Bitmap of zeroed available block indices
  * @dirty_bitmap: Bitmap of dirty available block indices
  */
@@ -94,6 +95,7 @@ struct pisa_meta {
 		struct llist_node llnode;
 		struct rcu_head rcu;
 	};
+	unsigned long alloc_jiffies;
 
 	DECLARE_BITMAP(clean_bitmap, PISA_MAX_BLOCKS) ____cacheline_aligned;
 	DECLARE_BITMAP(dirty_bitmap, PISA_MAX_BLOCKS) ____cacheline_aligned;
-- 
2.56.0.542.g3ef89b7020-goog