From 9fe8fec5e43d5a80f43cbf61aaada1b047a1eb61 Mon Sep 17 00:00:00 2001

From: Patrick Kelsey <pat.kelsey@cornelisnetworks.com>

Date: Fri, 7 Apr 2023 12:52:39 -0400

Subject: [PATCH 1/1] IB/hfi1: Fix SDMA mmu_rb_node not being evicted in LRU

 order

Git-commit: 9fe8fec5e43d5a80f43cbf61aaada1b047a1eb61

Patch-mainline: v6.4-rc1

References: git-fixes

hfi1_mmu_rb_remove_unless_exact() did not move mmu_rb_node objects in

mmu_rb_handler->lru_list after getting a cache hit on an mmu_rb_node.

As a result, hfi1_mmu_rb_evict() was not guaranteed to evict truly

least-recently used nodes.

This could be a performance issue for an application when that

application:

- Uses some long-lived buffers frequently.

- Uses a large number of buffers once.

- Hits the mmu_rb_handler cache size or pinned-page limits, forcing

  mmu_rb_handler cache entries to be evicted.

In this case, the one-time use buffers cause the long-lived buffer

entries to eventually filter to the end of the LRU list where

hfi1_mmu_rb_evict() will consider evicting a frequently-used long-lived

entry instead of evicting one of the one-time use entries.

Fix this by inserting new mmu_rb_node at the tail of

mmu_rb_handler->lru_list and move mmu_rb_ndoe to the tail of

mmu_rb_handler->lru_list when the mmu_rb_node is a hit in

hfi1_mmu_rb_remove_unless_exact(). Change hfi1_mmu_rb_evict() to evict

from the head of mmu_rb_handler->lru_list instead of the tail.

Fixes: 0636e9ab8355 ("IB/hfi1: Add cache evict LRU list")

Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>

Signed-off-by: Patrick Kelsey <pat.kelsey@cornelisnetworks.com>

Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>

Link: https://lore.kernel.org/r/168088635931.3027109.10423156330761536044.stgit@252.162.96.66.static.eigbox.net

Signed-off-by: Leon Romanovsky <leon@kernel.org>

Acked-by: Nicolas Morey <nmorey@suse.com>

---

 drivers/infiniband/hw/hfi1/mmu_rb.c | 13 ++++++-------

 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c

index 7333646021bb..af46ff203342 100644

--- a/drivers/infiniband/hw/hfi1/mmu_rb.c

+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c

@@ -130,7 +130,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler,

 		goto unlock;

 	}

 	__mmu_int_rb_insert(mnode, &handler->root);

-	list_add(&mnode->list, &handler->lru_list);

+	list_add_tail(&mnode->list, &handler->lru_list);

 	ret = handler->ops->insert(handler->ops_arg, mnode);

 	if (ret) {

@@ -181,8 +181,10 @@ bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler,

 	spin_lock_irqsave(&handler->lock, flags);

 	node = __mmu_rb_search(handler, addr, len);

 	if (node) {

-		if (node->addr == addr && node->len == len)

+		if (node->addr == addr && node->len == len) {

+			list_move_tail(&node->list, &handler->lru_list);

 			goto unlock;

+		}

 		__mmu_int_rb_remove(node, &handler->root);

 		list_del(&node->list); /* remove from LRU list */

 		ret = true;

@@ -206,8 +208,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg)

 	INIT_LIST_HEAD(&del_list);

 	spin_lock_irqsave(&handler->lock, flags);

-	list_for_each_entry_safe_reverse(rbnode, ptr, &handler->lru_list,

-					 list) {

+	list_for_each_entry_safe(rbnode, ptr, &handler->lru_list, list) {

 		if (handler->ops->evict(handler->ops_arg, rbnode, evict_arg,

 					&stop)) {

 			__mmu_int_rb_remove(rbnode, &handler->root);

@@ -219,9 +220,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg)

 	}

 	spin_unlock_irqrestore(&handler->lock, flags);

-	while (!list_empty(&del_list)) {

-		rbnode = list_first_entry(&del_list, struct mmu_rb_node, list);

-		list_del(&rbnode->list);

+	list_for_each_entry_safe(rbnode, ptr, &del_list, list) {

 		handler->ops->remove(handler->ops_arg, rbnode);

 	}

 }

-- 

2.39.1.1.gbe015eda0162