netdev - [PATCH v4 net-next 1/5] net: xdp: introduce bulking for xdp tx return path

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: <3764c855c42d719000aa56bb946b3ddfd00971f2.1604686496.git.lorenzo@kernel.org>
Date:   Fri,  6 Nov 2020 19:19:07 +0100
From:   Lorenzo Bianconi <lorenzo@...nel.org>
To:     netdev@...r.kernel.org
Cc:     bpf@...r.kernel.org, lorenzo.bianconi@...hat.com,
        davem@...emloft.net, kuba@...nel.org, brouer@...hat.com,
        ilias.apalodimas@...aro.org
Subject: [PATCH v4 net-next 1/5] net: xdp: introduce bulking for xdp tx return path

XDP bulk APIs introduce a defer/flush mechanism to return
pages belonging to the same xdp_mem_allocator object
(identified via the mem.id field) in bulk to optimize
I-cache and D-cache since xdp_return_frame is usually run
inside the driver NAPI tx completion loop.
The bulk queue size is set to 16 to be aligned to how
XDP_REDIRECT bulking works. The bulk is flushed when
it is full or when mem.id changes.
xdp_frame_bulk is usually stored/allocated on the function
call-stack to avoid locking penalties.
Current implementation considers only page_pool memory model.

Suggested-by: Jesper Dangaard Brouer <brouer@...hat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@...nel.org>
---
 include/net/xdp.h | 11 ++++++++-
 net/core/xdp.c    | 61 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 3814fb631d52..f89292ca305a 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -104,6 +104,12 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+#define XDP_BULK_QUEUE_SIZE	16
+struct xdp_frame_bulk {
+	int count;
+	void *xa;
+	void *q[XDP_BULK_QUEUE_SIZE];
+};
 
 static inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)
@@ -194,6 +200,9 @@ struct xdp_frame *xdp_convert_buff_to_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);
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq);
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq);
 
 /* When sending xdp_frame into the network stack, then there is no
  * return point callback, which is needed to release e.g. DMA-mapping
@@ -245,6 +254,6 @@ bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
 void xdp_attachment_setup(struct xdp_attachment_info *info,
 			  struct netdev_bpf *bpf);
 
-#define DEV_MAP_BULK_SIZE 16
+#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE
 
 #endif /* __LINUX_NET_XDP_H__ */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 48aba933a5a8..66ac275a0360 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -380,6 +380,67 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_allocator *xa = bq->xa;
+	int i;
+
+	if (unlikely(!xa))
+		return;
+
+	for (i = 0; i < bq->count; i++) {
+		struct page *page = virt_to_head_page(bq->q[i]);
+
+		page_pool_put_full_page(xa->page_pool, page, false);
+	}
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_info *mem = &xdpf->mem;
+	struct xdp_mem_allocator *xa;
+
+	if (mem->type != MEM_TYPE_PAGE_POOL) {
+		__xdp_return(xdpf->data, &xdpf->mem, false);
+		return;
+	}
+
+	rcu_read_lock();
+
+	xa = bq->xa;
+	if (unlikely(!xa)) {
+		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+		bq->count = 0;
+		bq->xa = xa;
+	}
+
+	if (bq->count == XDP_BULK_QUEUE_SIZE)
+		xdp_flush_frame_bulk(bq);
+
+	if (mem->id != xa->mem.id) {
+		xdp_flush_frame_bulk(bq);
+		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+	}
+
+	bq->q[bq->count++] = xdpf->data;
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
 	__xdp_return(xdp->data, &xdp->rxq->mem, true);
-- 
2.26.2