Commit d3aa6c94 authored Apr 07, 2023 by Patrick Kelsey Committed by Greg Kroah-Hartman May 17, 2023

IB/hfi1: Fix SDMA mmu_rb_node not being evicted in LRU order



[ Upstream commit 9fe8fec5e43d5a80f43cbf61aaada1b047a1eb61 ]

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: 0636e9ab ("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>
Signed-off-by: Sasha Levin <sashal@kernel.org>

parent 281714e4

drivers/infiniband/hw/hfi1/mmu_rb.c

+6 −7

Original line number	Diff line number	Diff line
		@@ -175,7 +175,7 @@ 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) {
		@@ -222,8 +222,10 @@ 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;
		@@ -244,8 +246,7 @@ 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);
		@@ -257,9 +258,7 @@ 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);
		}
		}