summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
authorLorenzo Bianconi <lorenzo@kernel.org>2019-11-20 16:54:18 +0200
committerDavid S. Miller <davem@davemloft.net>2019-11-20 12:34:28 -0800
commite68bc75691cc3de608c2c7505057c948d13ae587 (patch)
treedb2eb770f81d99a4b87dfe9e54e757be8dd9f74f /net/core
parentf383b2950070ce4f34e74db94f70bb565b746e97 (diff)
downloadlinux-e68bc75691cc3de608c2c7505057c948d13ae587.tar.bz2
net: page_pool: add the possibility to sync DMA memory for device
Introduce the following parameters in order to add the possibility to sync DMA memory for device before putting allocated pages in the page_pool caches: - PP_FLAG_DMA_SYNC_DEV: if set in page_pool_params flags, all pages that the driver gets from page_pool will be DMA-synced-for-device according to the length provided by the device driver. Please note DMA-sync-for-CPU is still device driver responsibility - offset: DMA address offset where the DMA engine starts copying rx data - max_len: maximum DMA memory size page_pool is allowed to flush. This is currently used in __page_pool_alloc_pages_slow routine when pages are allocated from page allocator These parameters are supposed to be set by device drivers. This optimization reduces the length of the DMA-sync-for-device. The optimization is valid because pages are initially DMA-synced-for-device as defined via max_len. At RX time, the driver will perform a DMA-sync-for-CPU on the memory for the packet length. What is important is the memory occupied by packet payload, because this is the area CPU is allowed to read and modify. As we don't track cache-lines written into by the CPU, simply use the packet payload length as dma_sync_size at page_pool recycle time. This also take into account any tail-extend. Tested-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
-rw-r--r--net/core/page_pool.c36
1 files changed, 34 insertions, 2 deletions
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 6c7f78bd6421..a6aefe989043 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -47,6 +47,21 @@ static int page_pool_init(struct page_pool *pool,
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
return -EINVAL;
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
+ /* In order to request DMA-sync-for-device the page
+ * needs to be mapped
+ */
+ if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+ return -EINVAL;
+
+ if (!pool->p.max_len)
+ return -EINVAL;
+
+ /* pool->p.offset has to be set according to the address
+ * offset used by the DMA engine to start copying rx data
+ */
+ }
+
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
return -ENOMEM;
@@ -115,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)
return page;
}
+static void page_pool_dma_sync_for_device(struct page_pool *pool,
+ struct page *page,
+ unsigned int dma_sync_size)
+{
+ dma_sync_size = min(dma_sync_size, pool->p.max_len);
+ dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
+ pool->p.offset, dma_sync_size,
+ pool->p.dma_dir);
+}
+
/* slow path */
noinline
static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
@@ -159,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
}
page->dma_addr = dma;
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
+
skip_dma_map:
/* Track how many pages are held 'in-flight' */
pool->pages_state_hold_cnt++;
@@ -292,8 +320,8 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid;
}
-void __page_pool_put_page(struct page_pool *pool,
- struct page *page, bool allow_direct)
+void __page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
@@ -305,6 +333,10 @@ void __page_pool_put_page(struct page_pool *pool,
pool_page_reusable(pool, page))) {
/* Read barrier done in page_ref_count / READ_ONCE */
+ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+ page_pool_dma_sync_for_device(pool, page,
+ dma_sync_size);
+
if (allow_direct && in_serving_softirq())
if (__page_pool_recycle_direct(page, pool))
return;