Every set_pages_array_wb call resulted in cross-core
interrupts and TLB flushes. Merge more of them for
less overhead.
This reduces the time needed to free a 1.6 GiB GTT WC
buffer as part of Vulkan CTS from ~2 sec to < 0.25 sec.
(Allocation still takes more than 2 sec though)
Signed-off-by: Bas Nieuwenhuizen <basni at chromium.org>
---
drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 31 ++++++++++++++++++------
1 file changed, 24 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 4c659405a008a..9440ba0a55116 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -299,6 +299,25 @@ static int set_pages_array_uc(struct page **pages, int addrinarray)
#endif
return 0;
}
+
+static int ttm_set_page_range_wb(struct page *p, unsigned long numpages)
+{
+#if IS_ENABLED(CONFIG_AGP)
+ unsigned long i;
+
+ for (i = 0; i < numpages; i++)
+ unmap_page_from_agp(p + i);
+#endif
+ return 0;
+}
+
+#else /* for !CONFIG_X86 */
+
+static int ttm_set_page_range_wb(struct page *p, unsigned long numpages)
+{
+ return set_memory_wb((unsigned long)page_address(p), numpages);
+}
+
#endif /* for !CONFIG_X86 */
static int ttm_set_pages_caching(struct dma_pool *pool,
@@ -387,18 +406,16 @@ static void ttm_pool_update_free_locked(struct dma_pool *pool,
static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
{
struct page *page = d_page->p;
- unsigned i, num_pages;
+ unsigned num_pages;
int ret;
/* Don't set WB on WB page pool. */
if (!(pool->type & IS_CACHED)) {
num_pages = pool->size / PAGE_SIZE;
- for (i = 0; i < num_pages; ++i, ++page) {
- ret = set_pages_array_wb(&page, 1);
- if (ret) {
- pr_err("%s: Failed to set %d pages to wb!\n",
- pool->dev_name, 1);
- }
+ ret = ttm_set_page_range_wb(page, num_pages);
+ if (ret) {
+ pr_err("%s: Failed to set %d pages to wb!\n",
+ pool->dev_name, num_pages);
}
}
--
2.18.0.233.g985f88cf7e-goog
