* [PATCH v2] net: page_pool: Add documentaion and examples on API usage
@ 2020-02-11 15:37 Ilias Apalodimas
2020-02-11 15:40 ` Ilias Apalodimas
0 siblings, 1 reply; 2+ messages in thread
From: Ilias Apalodimas @ 2020-02-11 15:37 UTC (permalink / raw)
To: brouer, lorenzo, davem, netdev; +Cc: Ilias Apalodimas
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
---
Documentation/networking/page_pool.rst | 148 +++++++++++++++++++++++++
1 file changed, 148 insertions(+)
create mode 100644 Documentation/networking/page_pool.rst
diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
new file mode 100644
index 000000000000..877fc5332983
--- /dev/null
+++ b/Documentation/networking/page_pool.rst
@@ -0,0 +1,148 @@
+=============
+Page Pool API
+=============
+
+The page_pool allocator is optimized for the XDP mode that uses one frame
+per-page, but it can fallback on the regular page allocator APIs.
+
+Basic use involve replacing alloc_pages() calls with the
+page_pool_alloc_pages() call. Drivers should use page_pool_dev_alloc_pages()
+replacing dev_alloc_pages().
+
+API keeps track of in-flight pages, in-order to let API user know
+when it is safe to free a page_pool object. Thus, API users
+must run page_pool_release_page() when a page is leaving the page_pool or
+call page_pool_put_page() where appropriate in order to maintain correct
+accounting.
+
+API user must call page_pool_put_page() once on a page, as it
+will either recycle the page, or in case of refcnt > 1, it will
+release the DMA mapping and in-flight state accounting.
+
+Architecture overview
+=====================
+
+.. code-block:: none
+
+ +------------------+
+ | Driver |
+ +------------------+
+ ^
+ |
+ |
+ |
+ v
+ +--------------------------------------------+
+ | request memory |
+ +--------------------------------------------+
+ ^ ^
+ | |
+ | Pool empty | Pool has entries
+ | |
+ v v
+ +-----------------------+ +------------------------+
+ | alloc (and map) pages | | get page from cache |
+ +-----------------------+ +------------------------+
+ ^ ^
+ | |
+ | in-softirq |
+ | |
+ v v
+ +-----------------+ +------------------+
+ | Fast cache | | ptr-ring cache |
+ +-----------------+ +------------------+
+
+API interface
+=============
+Ideally the number of pools created should match the number of hardware queuesm
+unless other hardware restriction make that impossible.
+
+* page_pool_create(): Create a pool.
+ * flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV
+ * pool_size: size of the ptr_ring
+ * nid: preferred NUMA node for allocation
+ * dev: struct device. Used on DMA operations
+ * dma_dir: DMA direction
+ * max_len: max DMA sync memory size
+ * offset: DMA address offset
+
+* page_pool_put_page(): The outcome of this depends on the page refcnt. If the
+ driver uses refcnt > 1 this will unmap the page. If the pool object is
+ responsible for DMA operations and account for the in-flight counting.
+ If the refcnt is 1, the allocator owns the page and will try to recycle and
+ sync it to be re-used by the device using dma_sync_single_range_for_device().
+
+* page_pool_release_page(): Unmap the page (if mapped) and account for it on
+ inflight counters.
+
+* page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool
+ caches.
+
+* page_pool_get_dma_addr(): Retrieve the stored DMA address.
+
+* page_pool_get_dma_dir(): Retrieve the stored DMA direction.
+
+* page_pool_recycle_direct(): Recycle the page immediately. Must be used under
+ NAPI context
+
+Coding examples
+===============
+
+Registration
+------------
+
+.. code-block:: c
+
+ /* Page pool registration */
+ struct page_pool_params pp_params = { 0 };
+ struct xdp_rxq_info xdp_rxq;
+ int err;
+
+ pp_params.order = 0;
+ /* internal DMA mapping in page_pool */
+ pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.pool_size = DESC_NUM;
+ pp_params.nid = NUMA_NO_NODE;
+ pp_params.dev = priv->dev;
+ pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+ page_pool = page_pool_create(&pp_params);
+
+ err = xdp_rxq_info_reg(&xdp_rxq, ndev, 0);
+ if (err)
+ goto err_out;
+
+ err = xdp_rxq_info_reg_mem_model(&xdp_rxq, MEM_TYPE_PAGE_POOL, page_pool);
+ if (err)
+ goto err_out;
+
+NAPI poller
+-----------
+
+
+.. code-block:: c
+
+ /* NAPI Rx poller */
+ enum dma_data_direction dma_dir;
+
+ dma_dir = page_pool_get_dma_dir(dring->page_pool);
+ while (done < budget) {
+ if (some error)
+ page_pool_recycle_direct(page_pool, page);
+ if (packet_is_xdp) {
+ if XDP_DROP:
+ page_pool_recycle_direct(page_pool, page);
+ } else (packet_is_skb) {
+ page_pool_release_page(page_pool, page);
+ new_page = page_pool_dev_alloc_pages(page_pool);
+ }
+ }
+
+Driver unload
+-------------
+
+.. code-block:: c
+
+ /* Driver unload */
+ page_pool_put_page(page_pool, page, false);
+ xdp_rxq_info_unreg(&xdp_rxq);
+ page_pool_destroy(page_pool);
--
2.25.0
^ permalink raw reply related [flat|nested] 2+ messages in thread* Re: [PATCH v2] net: page_pool: Add documentaion and examples on API usage
2020-02-11 15:37 [PATCH v2] net: page_pool: Add documentaion and examples on API usage Ilias Apalodimas
@ 2020-02-11 15:40 ` Ilias Apalodimas
0 siblings, 0 replies; 2+ messages in thread
From: Ilias Apalodimas @ 2020-02-11 15:40 UTC (permalink / raw)
To: brouer, lorenzo, davem, netdev
I accidentally send a wrong version.
Please igjnore this i'll send the proper one in a few minutes.
Sorry for the noise.
On Tue, Feb 11, 2020 at 05:37:46PM +0200, Ilias Apalodimas wrote:
> Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
> ---
> Documentation/networking/page_pool.rst | 148 +++++++++++++++++++++++++
> 1 file changed, 148 insertions(+)
> create mode 100644 Documentation/networking/page_pool.rst
>
> diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
> new file mode 100644
> index 000000000000..877fc5332983
> --- /dev/null
> +++ b/Documentation/networking/page_pool.rst
> @@ -0,0 +1,148 @@
> +=============
> +Page Pool API
> +=============
> +
> +The page_pool allocator is optimized for the XDP mode that uses one frame
> +per-page, but it can fallback on the regular page allocator APIs.
> +
> +Basic use involve replacing alloc_pages() calls with the
> +page_pool_alloc_pages() call. Drivers should use page_pool_dev_alloc_pages()
> +replacing dev_alloc_pages().
> +
> +API keeps track of in-flight pages, in-order to let API user know
> +when it is safe to free a page_pool object. Thus, API users
> +must run page_pool_release_page() when a page is leaving the page_pool or
> +call page_pool_put_page() where appropriate in order to maintain correct
> +accounting.
> +
> +API user must call page_pool_put_page() once on a page, as it
> +will either recycle the page, or in case of refcnt > 1, it will
> +release the DMA mapping and in-flight state accounting.
> +
> +Architecture overview
> +=====================
> +
> +.. code-block:: none
> +
> + +------------------+
> + | Driver |
> + +------------------+
> + ^
> + |
> + |
> + |
> + v
> + +--------------------------------------------+
> + | request memory |
> + +--------------------------------------------+
> + ^ ^
> + | |
> + | Pool empty | Pool has entries
> + | |
> + v v
> + +-----------------------+ +------------------------+
> + | alloc (and map) pages | | get page from cache |
> + +-----------------------+ +------------------------+
> + ^ ^
> + | |
> + | in-softirq |
> + | |
> + v v
> + +-----------------+ +------------------+
> + | Fast cache | | ptr-ring cache |
> + +-----------------+ +------------------+
> +
> +API interface
> +=============
> +Ideally the number of pools created should match the number of hardware queuesm
> +unless other hardware restriction make that impossible.
> +
> +* page_pool_create(): Create a pool.
> + * flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV
> + * pool_size: size of the ptr_ring
> + * nid: preferred NUMA node for allocation
> + * dev: struct device. Used on DMA operations
> + * dma_dir: DMA direction
> + * max_len: max DMA sync memory size
> + * offset: DMA address offset
> +
> +* page_pool_put_page(): The outcome of this depends on the page refcnt. If the
> + driver uses refcnt > 1 this will unmap the page. If the pool object is
> + responsible for DMA operations and account for the in-flight counting.
> + If the refcnt is 1, the allocator owns the page and will try to recycle and
> + sync it to be re-used by the device using dma_sync_single_range_for_device().
> +
> +* page_pool_release_page(): Unmap the page (if mapped) and account for it on
> + inflight counters.
> +
> +* page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool
> + caches.
> +
> +* page_pool_get_dma_addr(): Retrieve the stored DMA address.
> +
> +* page_pool_get_dma_dir(): Retrieve the stored DMA direction.
> +
> +* page_pool_recycle_direct(): Recycle the page immediately. Must be used under
> + NAPI context
> +
> +Coding examples
> +===============
> +
> +Registration
> +------------
> +
> +.. code-block:: c
> +
> + /* Page pool registration */
> + struct page_pool_params pp_params = { 0 };
> + struct xdp_rxq_info xdp_rxq;
> + int err;
> +
> + pp_params.order = 0;
> + /* internal DMA mapping in page_pool */
> + pp_params.flags = PP_FLAG_DMA_MAP;
> + pp_params.pool_size = DESC_NUM;
> + pp_params.nid = NUMA_NO_NODE;
> + pp_params.dev = priv->dev;
> + pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
> + page_pool = page_pool_create(&pp_params);
> +
> + err = xdp_rxq_info_reg(&xdp_rxq, ndev, 0);
> + if (err)
> + goto err_out;
> +
> + err = xdp_rxq_info_reg_mem_model(&xdp_rxq, MEM_TYPE_PAGE_POOL, page_pool);
> + if (err)
> + goto err_out;
> +
> +NAPI poller
> +-----------
> +
> +
> +.. code-block:: c
> +
> + /* NAPI Rx poller */
> + enum dma_data_direction dma_dir;
> +
> + dma_dir = page_pool_get_dma_dir(dring->page_pool);
> + while (done < budget) {
> + if (some error)
> + page_pool_recycle_direct(page_pool, page);
> + if (packet_is_xdp) {
> + if XDP_DROP:
> + page_pool_recycle_direct(page_pool, page);
> + } else (packet_is_skb) {
> + page_pool_release_page(page_pool, page);
> + new_page = page_pool_dev_alloc_pages(page_pool);
> + }
> + }
> +
> +Driver unload
> +-------------
> +
> +.. code-block:: c
> +
> + /* Driver unload */
> + page_pool_put_page(page_pool, page, false);
> + xdp_rxq_info_unreg(&xdp_rxq);
> + page_pool_destroy(page_pool);
> --
> 2.25.0
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-02-11 15:40 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2020-02-11 15:37 [PATCH v2] net: page_pool: Add documentaion and examples on API usage Ilias Apalodimas
2020-02-11 15:40 ` Ilias Apalodimas
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox