From 35c7fd2d25b3214d150a746019405dd245d9fafc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 1 Apr 2021 15:45:33 +0200
Subject: drm/ttm: optimize the pool shrinker a bit v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 450b2622bc11037c8108f7d2f2d8a43e980e847d
Patch-mainline: v5.16-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
Switch back to using a spinlock again by moving the IOMMU unmap outside
of the locked region.
This avoids contention especially while freeing pages.
v2: Add a comment explaining why we need sync_shrinkers().
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210820120528.81114-3-christian.koenig@amd.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/ttm/ttm_pool.c | 40 +++++++++++++++++++---------------
1 file changed, 22 insertions(+), 18 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 82cbb29a05aa..c961a788b519 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -70,7 +70,7 @@ static struct ttm_pool_type global_uncached[MAX_ORDER];
static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
-static struct mutex shrinker_lock;
+static spinlock_t shrinker_lock;
static struct list_head shrinker_list;
static struct shrinker mm_shrinker;
@@ -263,9 +263,9 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
spin_lock_init(&pt->lock);
INIT_LIST_HEAD(&pt->pages);
- mutex_lock(&shrinker_lock);
+ spin_lock(&shrinker_lock);
list_add_tail(&pt->shrinker_list, &shrinker_list);
- mutex_unlock(&shrinker_lock);
+ spin_unlock(&shrinker_lock);
}
/* Remove a pool_type from the global shrinker list and free all pages */
@@ -273,9 +273,9 @@ static void ttm_pool_type_fini(struct ttm_pool_type *pt)
{
struct page *p;
- mutex_lock(&shrinker_lock);
+ spin_lock(&shrinker_lock);
list_del(&pt->shrinker_list);
- mutex_unlock(&shrinker_lock);
+ spin_unlock(&shrinker_lock);
while ((p = ttm_pool_type_take(pt)))
ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
@@ -313,24 +313,23 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
static unsigned int ttm_pool_shrink(void)
{
struct ttm_pool_type *pt;
- unsigned int num_freed;
+ unsigned int num_pages;
struct page *p;
- mutex_lock(&shrinker_lock);
+ spin_lock(&shrinker_lock);
pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
+ list_move_tail(&pt->shrinker_list, &shrinker_list);
+ spin_unlock(&shrinker_lock);
p = ttm_pool_type_take(pt);
if (p) {
ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
- num_freed = 1 << pt->order;
+ num_pages = 1 << pt->order;
} else {
- num_freed = 0;
+ num_pages = 0;
}
- list_move_tail(&pt->shrinker_list, &shrinker_list);
- mutex_unlock(&shrinker_lock);
-
- return num_freed;
+ return num_pages;
}
/* Return the allocation order based for a page */
@@ -531,6 +530,11 @@ void ttm_pool_fini(struct ttm_pool *pool)
for (j = 0; j < MAX_ORDER; ++j)
ttm_pool_type_fini(&pool->caching[i].orders[j]);
}
+
+ /* We removed the pool types from the LRU, but we need to also make sure
+ * that no shrinker is concurrently freeing pages from the pool.
+ */
+ synchronize_shrinkers();
}
/* As long as pages are available make sure to release at least one */
@@ -605,7 +609,7 @@ static int ttm_pool_debugfs_globals_show(struct seq_file *m, void *data)
{
ttm_pool_debugfs_header(m);
- mutex_lock(&shrinker_lock);
+ spin_lock(&shrinker_lock);
seq_puts(m, "wc\t:");
ttm_pool_debugfs_orders(global_write_combined, m);
seq_puts(m, "uc\t:");
@@ -614,7 +618,7 @@ static int ttm_pool_debugfs_globals_show(struct seq_file *m, void *data)
ttm_pool_debugfs_orders(global_dma32_write_combined, m);
seq_puts(m, "uc 32\t:");
ttm_pool_debugfs_orders(global_dma32_uncached, m);
- mutex_unlock(&shrinker_lock);
+ spin_unlock(&shrinker_lock);
ttm_pool_debugfs_footer(m);
@@ -641,7 +645,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
ttm_pool_debugfs_header(m);
- mutex_lock(&shrinker_lock);
+ spin_lock(&shrinker_lock);
for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
seq_puts(m, "DMA ");
switch (i) {
@@ -657,7 +661,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
}
ttm_pool_debugfs_orders(pool->caching[i].orders, m);
}
- mutex_unlock(&shrinker_lock);
+ spin_unlock(&shrinker_lock);
ttm_pool_debugfs_footer(m);
return 0;
@@ -694,7 +698,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
if (!page_pool_size)
page_pool_size = num_pages;
- mutex_init(&shrinker_lock);
+ spin_lock_init(&shrinker_lock);
INIT_LIST_HEAD(&shrinker_list);
for (i = 0; i < MAX_ORDER; ++i) {
--
2.38.1