netdev - [bpf-next V5 PATCH 5/8] xdp: introduce xdp_return_frame_rx

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <152717316714.4777.701114215508601596.stgit@firesoul>
Date:   Thu, 24 May 2018 16:46:07 +0200
From:   Jesper Dangaard Brouer <brouer@...hat.com>
To:     netdev@...r.kernel.org, Daniel Borkmann <borkmann@...earbox.net>,
        Alexei Starovoitov <alexei.starovoitov@...il.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>
Cc:     Christoph Hellwig <hch@...radead.org>,
        BjörnTöpel <bjorn.topel@...el.com>,
        John Fastabend <john.fastabend@...il.com>,
        Magnus Karlsson <magnus.karlsson@...el.com>,
        makita.toshiaki@....ntt.co.jp
Subject: [bpf-next V5 PATCH 5/8] xdp: introduce xdp_return_frame_rx_napi

When sending an xdp_frame through xdp_do_redirect call, then error
cases can happen where the xdp_frame needs to be dropped, and
returning an -errno code isn't sufficient/possible any-longer
(e.g. for cpumap case). This is already fully supported, by simply
calling xdp_return_frame.

This patch is an optimization, which provides xdp_return_frame_rx_napi,
which is a faster variant for these error cases.  It take advantage of
the protection provided by XDP RX running under NAPI protection.

This change is mostly relevant for drivers using the page_pool
allocator as it can take advantage of this. (Tested with mlx5).

Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
 include/net/page_pool.h |    5 +++--
 include/net/xdp.h       |    1 +
 kernel/bpf/cpumap.c     |    2 +-
 kernel/bpf/devmap.c     |    2 +-
 net/core/xdp.c          |   20 ++++++++++++++++----
 5 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index c79087153148..694d055e01ef 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -115,13 +115,14 @@ void page_pool_destroy(struct page_pool *pool);
 void __page_pool_put_page(struct page_pool *pool,
 			  struct page *page, bool allow_direct);
 
-static inline void page_pool_put_page(struct page_pool *pool, struct page *page)
+static inline void page_pool_put_page(struct page_pool *pool,
+				      struct page *page, bool allow_direct)
 {
 	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
 	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
 	 */
 #ifdef CONFIG_PAGE_POOL
-	__page_pool_put_page(pool, page, false);
+	__page_pool_put_page(pool, page, allow_direct);
 #endif
 }
 /* Very limited use-cases allow recycle direct */
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 0b689cf561c7..7ad779237ae8 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -104,6 +104,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 }
 
 void xdp_return_frame(struct xdp_frame *xdpf);
+void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
 void xdp_return_buff(struct xdp_buff *xdp);
 
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index c95b04ec103e..e0918d180f08 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -578,7 +578,7 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 		err = __ptr_ring_produce(q, xdpf);
 		if (err) {
 			drops++;
-			xdp_return_frame(xdpf);
+			xdp_return_frame_rx_napi(xdpf);
 		}
 		processed++;
 	}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index ff2f3bf59f2f..a9cd5c93dd2b 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -239,7 +239,7 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj,
 		err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
 		if (err) {
 			drops++;
-			xdp_return_frame(xdpf);
+			xdp_return_frame_rx_napi(xdpf);
 		} else {
 			sent++;
 		}
diff --git a/net/core/xdp.c b/net/core/xdp.c
index bf6758f74339..cb8c4e061a5a 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -308,7 +308,13 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 }
 EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
 
-static void xdp_return(void *data, struct xdp_mem_info *mem)
+/* XDP RX runs under NAPI protection, and in different delivery error
+ * scenarios (e.g. queue full), it is possible to return the xdp_frame
+ * while still leveraging this protection.  The @napi_direct boolian
+ * is used for those calls sites.  Thus, allowing for faster recycling
+ * of xdp_frames/pages in those cases.
+ */
+static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
 {
 	struct xdp_mem_allocator *xa;
 	struct page *page;
@@ -320,7 +326,7 @@ static void xdp_return(void *data, struct xdp_mem_info *mem)
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
 		if (xa)
-			page_pool_put_page(xa->page_pool, page);
+			page_pool_put_page(xa->page_pool, page, napi_direct);
 		else
 			put_page(page);
 		rcu_read_unlock();
@@ -340,12 +346,18 @@ static void xdp_return(void *data, struct xdp_mem_info *mem)
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {
-	xdp_return(xdpf->data, &xdpf->mem);
+	__xdp_return(xdpf->data, &xdpf->mem, false);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame);
 
+void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
+{
+	__xdp_return(xdpf->data, &xdpf->mem, true);
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
-	xdp_return(xdp->data, &xdp->rxq->mem);
+	__xdp_return(xdp->data, &xdp->rxq->mem, true);
 }
 EXPORT_SYMBOL_GPL(xdp_return_buff);