[PATCH v3 04/12] mm, swap: add support for stable large allocation in swap cache directly

[Kairui Song via B4 Relay <devnull+kasong.tencent.com@kernel.org>]

From: Kairui Song <kasong@tencent.com>

To make it possible to allocate large folios directly in swap cache,
provide a new infrastructure helper to handle the swap cache status
check, allocation, and order fallback in the swap cache layer

The new helper replaces the existing swap_cache_alloc_folio. Based on
this, all the separate swap folio allocation that is being done by anon
/ shmem before is converted to use this helper directly, unifying folio
allocation for anon, shmem, and readahead.

This slightly consolidates how allocation is synchronized, making it
more stable and less prone to errors. The slot-count and cache-conflict
check is now always performed with the cluster lock held before
allocation, and repeated under the same lock right before cache
insertion. This double check produces a stable result compared to the
previous anon and shmem mTHP allocation implementation,  avoids the
false-negative conflict checks that the lockless path can return — large
allocations no longer have to be unwound because the range turned out to
be occupied — and aborts early for already-freed slots, which helps
ordinary swapin and especially readahead, with only a marginal increase
in cluster-lock contention (the lock is very lightly contended and stays
local in the first place). Hence, callers of swap_cache_alloc_folio() no
longer need to check the swap slot count or swap cache status
themselves.

And now whoever first successfully allocates a folio in the swap cache
will be the one who charges it and performs the swap-in. The race window
of swapping is also reduced since the loop is much more compact.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/swap.h       |   3 +-
 mm/swap_state.c | 222 +++++++++++++++++++++++++++++++++++++++++---------------
 mm/zswap.c      |   2 +-
 3 files changed, 165 insertions(+), 62 deletions(-)

diff --git a/mm/swap.h b/mm/swap.h
index ad8b17a93758..6774af10a943 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -280,7 +280,8 @@ bool swap_cache_has_folio(swp_entry_t entry);
 struct folio *swap_cache_get_folio(swp_entry_t entry);
 void *swap_cache_get_shadow(swp_entry_t entry);
 void swap_cache_del_folio(struct folio *folio);
-struct folio *swap_cache_alloc_folio(swp_entry_t entry, gfp_t gfp_flags,
+struct folio *swap_cache_alloc_folio(swp_entry_t target_entry, gfp_t gfp_mask,
+				     unsigned long orders, struct vm_fault *vmf,
 				     struct mempolicy *mpol, pgoff_t ilx);
 /* Below helpers require the caller to lock and pass in the swap cluster. */
 void __swap_cache_add_folio(struct swap_cluster_info *ci,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3da285a891b2..f5c77f348bbd 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -139,10 +139,10 @@ void *swap_cache_get_shadow(swp_entry_t entry)
 
 /**
  * __swap_cache_add_check - Check if a range is suitable for adding a folio.
- * @ci: The locked swap cluster.
- * @ci_off: Range start offset.
- * @nr: Number of slots to check.
- * @shadow: Returns the shadow value if one exists in the range.
+ * @ci: The locked swap cluster
+ * @targ_entry: The target swap entry to check, will be rounded down by @nr
+ * @nr: Number of slots to check, must be a power of 2
+ * @shadowp: Returns the shadow value if one exists in the range.
  *
  * Check if all slots covered by given range have a swap count >= 1.
  * Retrieves the shadow if there is one.
@@ -150,22 +150,38 @@ void *swap_cache_get_shadow(swp_entry_t entry)
  * Context: Caller must lock the cluster.
  */
 static int __swap_cache_add_check(struct swap_cluster_info *ci,
-				  unsigned int ci_off, unsigned int nr,
-				  void **shadow)
+				  swp_entry_t targ_entry,
+				  unsigned long nr, void **shadowp)
 {
-	unsigned int ci_end = ci_off + nr;
+	unsigned int ci_off, ci_end;
 	unsigned long old_tb;
 
+	/*
+	 * If the target slot is not swapped out, return
+	 * -EEXIST or -ENOENT. If the batch is not suitable, could be a
+	 * race with concurrent free or cache add, return -EBUSY.
+	 */
 	if (unlikely(!ci->table))
 		return -ENOENT;
+	ci_off = swp_cluster_offset(targ_entry);
+	old_tb = __swap_table_get(ci, ci_off);
+	if (swp_tb_is_folio(old_tb))
+		return -EEXIST;
+	if (!__swp_tb_get_count(old_tb))
+		return -ENOENT;
+	if (swp_tb_is_shadow(old_tb) && shadowp)
+		*shadowp = swp_tb_to_shadow(old_tb);
+
+	if (nr == 1)
+		return 0;
+
+	ci_off = round_down(ci_off, nr);
+	ci_end = ci_off + nr;
 	do {
 		old_tb = __swap_table_get(ci, ci_off);
-		if (unlikely(swp_tb_is_folio(old_tb)))
-			return -EEXIST;
-		if (unlikely(!__swp_tb_get_count(old_tb)))
-			return -ENOENT;
-		if (swp_tb_is_shadow(old_tb))
-			*shadow = swp_tb_to_shadow(old_tb);
+		if (unlikely(swp_tb_is_folio(old_tb) ||
+			     !__swp_tb_get_count(old_tb)))
+			return -EBUSY;
 	} while (++ci_off < ci_end);
 
 	return 0;
@@ -244,7 +260,7 @@ static int swap_cache_add_folio(struct folio *folio, swp_entry_t entry,
 	si = __swap_entry_to_info(entry);
 	ci = swap_cluster_lock(si, swp_offset(entry));
 	ci_off = swp_cluster_offset(entry);
-	err = __swap_cache_add_check(ci, ci_off, nr_pages, &shadow);
+	err = __swap_cache_add_check(ci, entry, nr_pages, &shadow);
 	if (err) {
 		swap_cluster_unlock(ci);
 		return err;
@@ -399,6 +415,137 @@ void __swap_cache_replace_folio(struct swap_cluster_info *ci,
 	}
 }
 
+/*
+ * Try to allocate a folio of given order in the swap cache.
+ *
+ * This helper resolves the potential races of swap allocation
+ * and prepares a folio to be used for swap IO. May return following
+ * value:
+ *
+ * -ENOMEM / -EBUSY: Order is too large or in conflict with sub slot,
+ *                   caller should shrink the order and retry
+ * -ENOENT / -EEXIST: Target swap entry is unavailable or cached, the caller
+ *                    should abort or try to use the cached folio instead
+ */
+static struct folio *__swap_cache_alloc(struct swap_cluster_info *ci,
+					swp_entry_t targ_entry, gfp_t gfp,
+					unsigned int order, struct vm_fault *vmf,
+					struct mempolicy *mpol, pgoff_t ilx)
+{
+	int err;
+	swp_entry_t entry;
+	struct folio *folio;
+	void *shadow = NULL;
+	unsigned long address, nr_pages = 1 << order;
+	struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
+
+	entry.val = round_down(targ_entry.val, nr_pages);
+
+	/* Check if the slot and range are available, skip allocation if not */
+	spin_lock(&ci->lock);
+	err = __swap_cache_add_check(ci, targ_entry, nr_pages, NULL);
+	spin_unlock(&ci->lock);
+	if (unlikely(err))
+		return ERR_PTR(err);
+
+	/*
+	 * Limit THP gfp. The limitation is a no-op for typical
+	 * GFP_HIGHUSER_MOVABLE but matters for shmem.
+	 */
+	if (order)
+		gfp = thp_limit_gfp_mask(vma_thp_gfp_mask(vma), gfp);
+
+	if (mpol || !vmf) {
+		folio = folio_alloc_mpol(gfp, order, mpol, ilx, numa_node_id());
+	} else {
+		address = round_down(vmf->address, PAGE_SIZE << order);
+		folio = vma_alloc_folio(gfp, order, vmf->vma, address);
+	}
+	if (unlikely(!folio))
+		return ERR_PTR(-ENOMEM);
+
+	/* Double check the range is still not in conflict */
+	spin_lock(&ci->lock);
+	err = __swap_cache_add_check(ci, targ_entry, nr_pages, &shadow);
+	if (unlikely(err)) {
+		spin_unlock(&ci->lock);
+		folio_put(folio);
+		return ERR_PTR(err);
+	}
+
+	__folio_set_locked(folio);
+	__folio_set_swapbacked(folio);
+	__swap_cache_do_add_folio(ci, folio, entry);
+	spin_unlock(&ci->lock);
+
+	if (mem_cgroup_swapin_charge_folio(folio, vmf ? vmf->vma->vm_mm : NULL,
+					   gfp, entry)) {
+		spin_lock(&ci->lock);
+		__swap_cache_do_del_folio(ci, folio, entry, shadow);
+		spin_unlock(&ci->lock);
+		folio_unlock(folio);
+		/* nr_pages refs from swap cache, 1 from allocation */
+		folio_put_refs(folio, nr_pages + 1);
+		count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* For memsw accounting, swap is uncharged when folio is added to swap cache */
+	memcg1_swapin(entry, 1 << order);
+	if (shadow)
+		workingset_refault(folio, shadow);
+
+	node_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages);
+	lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr_pages);
+
+	/* Caller will initiate read into locked new_folio */
+	folio_add_lru(folio);
+	return folio;
+}
+
+/**
+ * swap_cache_alloc_folio - Allocate folio for swapped out slot in swap cache.
+ * @targ_entry: swap entry indicating the target slot
+ * @gfp: memory allocation flags
+ * @orders: allocation orders
+ * @vmf: fault information
+ * @mpol: NUMA memory allocation policy to be applied
+ * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
+ *
+ * Allocate a folio in the swap cache for one swap slot, typically before
+ * doing IO (e.g. swap in or zswap writeback). The swap slot indicated by
+ * @targ_entry must have a non-zero swap count (swapped out).
+ *
+ * Context: Caller must protect the swap device with reference count or locks.
+ * Return: Returns the folio if allocation succeeded and folio is added to
+ * swap cache. Returns error code if allocation failed due to race.
+ */
+struct folio *swap_cache_alloc_folio(swp_entry_t targ_entry, gfp_t gfp,
+				     unsigned long orders, struct vm_fault *vmf,
+				     struct mempolicy *mpol, pgoff_t ilx)
+{
+	int order, err;
+	struct folio *ret;
+	struct swap_cluster_info *ci;
+
+	/* Always allow order 0 so swap won't fail under pressure. */
+	order = orders ? highest_order(orders |= BIT(0)) : 0;
+	ci = __swap_entry_to_cluster(targ_entry);
+	for (;;) {
+		ret = __swap_cache_alloc(ci, targ_entry, gfp, order,
+					 vmf, mpol, ilx);
+		if (!IS_ERR(ret))
+			break;
+		err = PTR_ERR(ret);
+		if (!order || (err && err != -EBUSY && err != -ENOMEM))
+			break;
+		count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK);
+		order = next_order(&orders, order);
+	}
+
+	return ret;
+}
+
 /*
  * If we are the only user, then try to free up the swap cache.
  *
@@ -542,51 +689,10 @@ static int __swap_cache_prepare_and_add(swp_entry_t entry,
 	return ret;
 }
 
-/**
- * swap_cache_alloc_folio - Allocate folio for swapped out slot in swap cache.
- * @entry: the swapped out swap entry to be binded to the folio.
- * @gfp_mask: memory allocation flags
- * @mpol: NUMA memory allocation policy to be applied
- * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE
- *
- * Allocate a folio in the swap cache for one swap slot, typically before
- * doing IO (e.g. swap in or zswap writeback). The swap slot indicated by
- * @entry must have a non-zero swap count (swapped out).
- * Currently only supports order 0.
- *
- * Context: Caller must protect the swap device with reference count or locks.
- * Return: Returns the folio if allocation succeeded and folio is added to
- * swap cache. Returns error code if allocation failed due to race.
- */
-struct folio *swap_cache_alloc_folio(swp_entry_t entry, gfp_t gfp_mask,
-				     struct mempolicy *mpol, pgoff_t ilx)
-{
-	int ret;
-	struct folio *folio;
-
-	/* Allocate a new folio to be added into the swap cache. */
-	folio = folio_alloc_mpol(gfp_mask, 0, mpol, ilx, numa_node_id());
-	if (!folio)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * Try to add the new folio to the swap cache. It returns
-	 * -EEXIST if the entry is already cached.
-	 */
-	ret = __swap_cache_prepare_and_add(entry, folio, gfp_mask, false);
-	if (ret) {
-		folio_put(folio);
-		return ERR_PTR(ret);
-	}
-
-	return folio;
-}
-
 static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
 					   struct mempolicy *mpol, pgoff_t ilx,
 					   struct swap_iocb **plug, bool readahead)
 {
-	struct swap_info_struct *si = __swap_entry_to_info(entry);
 	struct folio *folio;
 
 	/* Check the swap cache again for readahead path. */
@@ -594,16 +700,12 @@ static struct folio *swap_cache_read_folio(swp_entry_t entry, gfp_t gfp,
 	if (folio)
 		return folio;
 
-	/* Skip allocation for unused and bad swap slot for readahead. */
-	if (!swap_entry_swapped(si, entry))
-		return NULL;
-
 	do {
 		folio = swap_cache_get_folio(entry);
 		if (folio)
 			return folio;
 
-		folio = swap_cache_alloc_folio(entry, gfp, mpol, ilx);
+		folio = swap_cache_alloc_folio(entry, gfp, 0, NULL, mpol, ilx);
 	} while (IS_ERR(folio) && PTR_ERR(folio) == -EEXIST);
 
 	if (IS_ERR_OR_NULL(folio))
diff --git a/mm/zswap.c b/mm/zswap.c
index e27f6e96f003..4fcd95eb24cb 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1000,7 +1000,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 		return -EEXIST;
 
 	mpol = get_task_policy(current);
-	folio = swap_cache_alloc_folio(swpentry, GFP_KERNEL, mpol,
+	folio = swap_cache_alloc_folio(swpentry, GFP_KERNEL, 0, NULL, mpol,
 				       NO_INTERLEAVE_INDEX);
 	put_swap_device(si);
 

-- 
2.53.0