[PATCH v2 net-next 0/7] net: ethernet: ti: cpsw: Add XDP support

[PATCH v2 net-next 0/7] net: ethernet: ti: cpsw: Add XDP support

[Ivan Khoronzhuk]

This patchset adds XDP support for TI cpsw driver and base it on
page_pool allocator. It was verified on af_xdp socket drop,
af_xdp l2f, ebpf XDP_DROP, XDP_REDIRECT, XDP_PASS, XDP_TX.

It was verified with following configs enabled:
CONFIG_JIT=y
CONFIG_BPFILTER=y
CONFIG_BPF_SYSCALL=y
CONFIG_XDP_SOCKETS=y
CONFIG_BPF_EVENTS=y
CONFIG_HAVE_EBPF_JIT=y
CONFIG_BPF_JIT=y
CONFIG_CGROUP_BPF=y

Link on previous v1:
https://lkml.org/lkml/2019/5/23/795

Also regular tests with iperf2 were done in order to verify impact on
regular netstack performance, compared with base commit:
https://pastebin.com/JSMT0iZ4

v1..v2:
- combined xdp_xmit functions
- used page allocation w/o refcnt juggle
- unmapped page for skb netstack
- moved rxq/page pool allocation to open/close pair
- added several preliminary patches:
  net: page_pool: add helper function to retrieve dma addresses
  net: page_pool: add helper function to unmap dma addresses
  net: ethernet: ti: cpsw: use cpsw as drv data
  net: ethernet: ti: cpsw_ethtool: simplify slave loops


Based on net-next/master

Ilias Apalodimas (2):
  net: page_pool: add helper function to retrieve dma addresses
  net: page_pool: add helper function to unmap dma addresses

Ivan Khoronzhuk (5):
  net: ethernet: ti: cpsw: use cpsw as drv data
  net: ethernet: ti: cpsw_ethtool: simplify slave loops
  net: ethernet: ti: davinci_cpdma: add dma mapped submit
  net: ethernet: ti: davinci_cpdma: return handler status
  net: ethernet: ti: cpsw: add XDP support

 drivers/net/ethernet/ti/Kconfig         |   1 +
 drivers/net/ethernet/ti/cpsw.c          | 537 ++++++++++++++++++++----
 drivers/net/ethernet/ti/cpsw_ethtool.c  | 136 +++++-
 drivers/net/ethernet/ti/cpsw_priv.h     |  12 +-
 drivers/net/ethernet/ti/davinci_cpdma.c | 122 ++++--
 drivers/net/ethernet/ti/davinci_cpdma.h |   6 +-
 drivers/net/ethernet/ti/davinci_emac.c  |  18 +-
 include/net/page_pool.h                 |   6 +
 net/core/page_pool.c                    |   7 +
 9 files changed, 710 insertions(+), 135 deletions(-)

-- 
2.17.1

[PATCH v2 net-next 1/7] net: page_pool: add helper function to retrieve dma addresses

[Ivan Khoronzhuk]

From: Ilias Apalodimas <ilias.apalodimas@linaro.org>

On a previous patch dma addr was stored in 'struct page'.
Use that to retrieve DMA addresses used by network drivers

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 include/net/page_pool.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 694d055e01ef..b885d86cb7a1 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -132,6 +132,11 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	__page_pool_put_page(pool, page, true);
 }
 
+static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
+{
+	return page->dma_addr;
+}
+
 static inline bool is_page_pool_compiled_in(void)
 {
 #ifdef CONFIG_PAGE_POOL
-- 
2.17.1

[PATCH v2 net-next 2/7] net: page_pool: add helper function to unmap dma addresses

[Ivan Khoronzhuk]

From: Ilias Apalodimas <ilias.apalodimas@linaro.org>

On a previous patch dma addr was stored in 'struct page'.
Use that to unmap DMA addresses used by network drivers

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 include/net/page_pool.h | 1 +
 net/core/page_pool.c    | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index b885d86cb7a1..ad218cef88c5 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -110,6 +110,7 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 
 void page_pool_destroy(struct page_pool *pool);
+void page_pool_unmap_page(struct page_pool *pool, struct page *page);
 
 /* Never call this directly, use helpers below */
 void __page_pool_put_page(struct page_pool *pool,
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 5b2252c6d49b..205af7bd6d09 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -190,6 +190,13 @@ static void __page_pool_clean_page(struct page_pool *pool,
 	page->dma_addr = 0;
 }
 
+/* unmap the page and clean our state */
+void page_pool_unmap_page(struct page_pool *pool, struct page *page)
+{
+	__page_pool_clean_page(pool, page);
+}
+EXPORT_SYMBOL(page_pool_unmap_page);
+
 /* Return a page to the page allocator, cleaning up our state */
 static void __page_pool_return_page(struct page_pool *pool, struct page *page)
 {
-- 
2.17.1

[PATCH v2 net-next 3/7] net: ethernet: ti: cpsw: use cpsw as drv data

[Ivan Khoronzhuk]

No need to set ndev for drvdata when mainly cpsw reference is needed,
so correct this legacy decision.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 drivers/net/ethernet/ti/cpsw.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 6d3f1f3f90cb..3430503e1053 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2265,8 +2265,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 
 static void cpsw_remove_dt(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	struct cpsw_platform_data *data = &cpsw->data;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *slave_node;
@@ -2477,7 +2476,7 @@ static int cpsw_probe(struct platform_device *pdev)
 		goto clean_cpts;
 	}
 
-	platform_set_drvdata(pdev, ndev);
+	platform_set_drvdata(pdev, cpsw);
 	priv = netdev_priv(ndev);
 	priv->cpsw = cpsw;
 	priv->ndev = ndev;
@@ -2570,9 +2569,8 @@ static int cpsw_probe(struct platform_device *pdev)
 
 static int cpsw_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	int ret;
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
+	int i, ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
@@ -2580,9 +2578,9 @@ static int cpsw_remove(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (cpsw->data.dual_emac)
-		unregister_netdev(cpsw->slaves[1].ndev);
-	unregister_netdev(ndev);
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
+			unregister_netdev(cpsw->slaves[i].ndev);
 
 	cpts_release(cpsw->cpts);
 	cpdma_ctlr_destroy(cpsw->dma);
-- 
2.17.1

[PATCH v2 net-next 4/7] net: ethernet: ti: cpsw_ethtool: simplify slave loops

[Ivan Khoronzhuk]

Only for consistency reasons, do it like in main cpsw.c module
and use ndev reference but not by means of slave.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 drivers/net/ethernet/ti/cpsw_ethtool.c | 40 ++++++++++++++------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index a4a7ec0d2531..c260bb32aacf 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -458,7 +458,6 @@ int cpsw_nway_reset(struct net_device *ndev)
 static void cpsw_suspend_data_pass(struct net_device *ndev)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	struct cpsw_slave *slave;
 	int i;
 
 	/* Disable NAPI scheduling */
@@ -467,12 +466,13 @@ static void cpsw_suspend_data_pass(struct net_device *ndev)
 	/* Stop all transmit queues for every network device.
 	 * Disable re-using rx descriptors with dormant_on.
 	 */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
-		if (!(slave->ndev && netif_running(slave->ndev)))
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
 			continue;
 
-		netif_tx_stop_all_queues(slave->ndev);
-		netif_dormant_on(slave->ndev);
+		netif_tx_stop_all_queues(ndev);
+		netif_dormant_on(ndev);
 	}
 
 	/* Handle rest of tx packets and stop cpdma channels */
@@ -483,13 +483,14 @@ static int cpsw_resume_data_pass(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpsw_slave *slave;
 	int i, ret;
 
 	/* Allow rx packets handling */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
-		if (slave->ndev && netif_running(slave->ndev))
-			netif_dormant_off(slave->ndev);
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev && netif_running(ndev))
+			netif_dormant_off(ndev);
+	}
 
 	/* After this receive is started */
 	if (cpsw->usage_count) {
@@ -502,9 +503,11 @@ static int cpsw_resume_data_pass(struct net_device *ndev)
 	}
 
 	/* Resume transmit for every affected interface */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
-		if (slave->ndev && netif_running(slave->ndev))
-			netif_tx_start_all_queues(slave->ndev);
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev && netif_running(ndev))
+			netif_tx_start_all_queues(ndev);
+	}
 
 	return 0;
 }
@@ -587,7 +590,6 @@ int cpsw_set_channels_common(struct net_device *ndev,
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpsw_slave *slave;
 	int i, ret;
 
 	ret = cpsw_check_ch_settings(cpsw, chs);
@@ -604,20 +606,20 @@ int cpsw_set_channels_common(struct net_device *ndev,
 	if (ret)
 		goto err;
 
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
-		if (!(slave->ndev && netif_running(slave->ndev)))
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
 			continue;
 
 		/* Inform stack about new count of queues */
-		ret = netif_set_real_num_tx_queues(slave->ndev,
-						   cpsw->tx_ch_num);
+		ret = netif_set_real_num_tx_queues(ndev, cpsw->tx_ch_num);
 		if (ret) {
 			dev_err(priv->dev, "cannot set real number of tx queues\n");
 			goto err;
 		}
 
-		ret = netif_set_real_num_rx_queues(slave->ndev,
-						   cpsw->rx_ch_num);
+		ret = netif_set_real_num_rx_queues(ndev, cpsw->rx_ch_num);
 		if (ret) {
 			dev_err(priv->dev, "cannot set real number of rx queues\n");
 			goto err;
-- 
2.17.1

[PATCH v2 net-next 5/7] net: ethernet: ti: davinci_cpdma: add dma mapped submit

[Ivan Khoronzhuk]

In case if dma mapped packet needs to be sent, like with XDP
page pool, the "mapped" submit can be used. This patch adds dma
mapped submit based on regular one.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 drivers/net/ethernet/ti/davinci_cpdma.c | 88 ++++++++++++++++++++-----
 drivers/net/ethernet/ti/davinci_cpdma.h |  2 +
 2 files changed, 75 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 35bf14d8e7af..7f89b2299f05 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -125,6 +125,15 @@ struct cpdma_chan {
 	u32				rate;
 };
 
+struct submit_info {
+	struct cpdma_chan *chan;
+	int directed;
+	void *token;
+	void *data;
+	int flags;
+	int len;
+};
+
 struct cpdma_control_info {
 	u32		reg;
 	u32		shift, mask;
@@ -176,6 +185,8 @@ static struct cpdma_control_info controls[] = {
 				 (directed << CPDMA_TO_PORT_SHIFT));	\
 	} while (0)
 
+#define CPDMA_DMA_EXT_MAP		BIT(16)
+
 static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
 {
 	struct cpdma_desc_pool *pool = ctlr->pool;
@@ -1002,10 +1013,12 @@ static void __cpdma_chan_submit(struct cpdma_chan *chan,
 	}
 }
 
-int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
-		      int len, int directed)
+static int cpdma_chan_submit_si(struct submit_info *si)
 {
+	struct cpdma_chan		*chan = si->chan;
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
+	int				len = si->len;
+	int				swlen = len;
 	struct cpdma_desc __iomem	*desc;
 	dma_addr_t			buffer;
 	unsigned long			flags;
@@ -1037,16 +1050,22 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		chan->stats.runt_transmit_buff++;
 	}
 
-	buffer = dma_map_single(ctlr->dev, data, len, chan->dir);
-	ret = dma_mapping_error(ctlr->dev, buffer);
-	if (ret) {
-		cpdma_desc_free(ctlr->pool, desc, 1);
-		ret = -EINVAL;
-		goto unlock_ret;
-	}
-
 	mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
-	cpdma_desc_to_port(chan, mode, directed);
+	cpdma_desc_to_port(chan, mode, si->directed);
+
+	if (si->flags & CPDMA_DMA_EXT_MAP) {
+		buffer = (dma_addr_t)si->data;
+		dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
+		swlen |= CPDMA_DMA_EXT_MAP;
+	} else {
+		buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
+		ret = dma_mapping_error(ctlr->dev, buffer);
+		if (ret) {
+			cpdma_desc_free(ctlr->pool, desc, 1);
+			ret = -EINVAL;
+			goto unlock_ret;
+		}
+	}
 
 	/* Relaxed IO accessors can be used here as there is read barrier
 	 * at the end of write sequence.
@@ -1055,9 +1074,9 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 	writel_relaxed(buffer, &desc->hw_buffer);
 	writel_relaxed(len, &desc->hw_len);
 	writel_relaxed(mode | len, &desc->hw_mode);
-	writel_relaxed((uintptr_t)token, &desc->sw_token);
+	writel_relaxed((uintptr_t)si->token, &desc->sw_token);
 	writel_relaxed(buffer, &desc->sw_buffer);
-	writel_relaxed(len, &desc->sw_len);
+	writel_relaxed(swlen, &desc->sw_len);
 	desc_read(desc, sw_len);
 
 	__cpdma_chan_submit(chan, desc);
@@ -1072,6 +1091,38 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 	return ret;
 }
 
+int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data, int len,
+		      int directed)
+{
+	struct submit_info si;
+
+	si.chan = chan;
+	si.token = token;
+	si.data = data;
+	si.len = len;
+	si.directed = directed;
+	si.flags = 0;
+
+	return cpdma_chan_submit_si(&si);
+}
+EXPORT_SYMBOL_GPL(cpdma_chan_submit);
+
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed)
+{
+	struct submit_info si;
+
+	si.chan = chan;
+	si.token = token;
+	si.data = (void *)data;
+	si.len = len;
+	si.directed = directed;
+	si.flags = CPDMA_DMA_EXT_MAP;
+
+	return cpdma_chan_submit_si(&si);
+}
+EXPORT_SYMBOL_GPL(cpdma_chan_submit_mapped);
+
 bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
 {
 	struct cpdma_ctlr	*ctlr = chan->ctlr;
@@ -1097,10 +1148,17 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
 	uintptr_t			token;
 
 	token      = desc_read(desc, sw_token);
-	buff_dma   = desc_read(desc, sw_buffer);
 	origlen    = desc_read(desc, sw_len);
 
-	dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+	buff_dma   = desc_read(desc, sw_buffer);
+	if (origlen & CPDMA_DMA_EXT_MAP) {
+		origlen &= ~CPDMA_DMA_EXT_MAP;
+		dma_sync_single_for_cpu(ctlr->dev, buff_dma, origlen,
+					chan->dir);
+	} else {
+		dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+	}
+
 	cpdma_desc_free(pool, desc, 1);
 	(*chan->handler)((void *)token, outlen, status);
 }
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 10376062dafa..8f6f27185c63 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -77,6 +77,8 @@ int cpdma_chan_stop(struct cpdma_chan *chan);
 
 int cpdma_chan_get_stats(struct cpdma_chan *chan,
 			 struct cpdma_chan_stats *stats);
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed);
 int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		      int len, int directed);
 int cpdma_chan_process(struct cpdma_chan *chan, int quota);
-- 
2.17.1

[PATCH v2 net-next 6/7] net: ethernet: ti: davinci_cpdma: return handler status

[Ivan Khoronzhuk]

This change is needed to return flush status of rx handler for
flushing redirected xdp frames after processing channel packets.
Do it as separate patch for simplicity.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 drivers/net/ethernet/ti/cpsw.c          | 23 +++++++++++------
 drivers/net/ethernet/ti/cpsw_ethtool.c  |  2 +-
 drivers/net/ethernet/ti/cpsw_priv.h     |  2 +-
 drivers/net/ethernet/ti/davinci_cpdma.c | 34 +++++++++++++++----------
 drivers/net/ethernet/ti/davinci_cpdma.h |  4 +--
 drivers/net/ethernet/ti/davinci_emac.c  | 18 ++++++++-----
 6 files changed, 50 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 3430503e1053..d89ad428315c 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -337,7 +337,7 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
 	return;
 }
 
-void cpsw_tx_handler(void *token, int len, int status)
+int cpsw_tx_handler(void *token, int len, int status)
 {
 	struct netdev_queue	*txq;
 	struct sk_buff		*skb = token;
@@ -355,6 +355,7 @@ void cpsw_tx_handler(void *token, int len, int status)
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += len;
 	dev_kfree_skb_any(skb);
+	return 0;
 }
 
 static void cpsw_rx_vlan_encap(struct sk_buff *skb)
@@ -400,7 +401,7 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
 	}
 }
 
-static void cpsw_rx_handler(void *token, int len, int status)
+static int cpsw_rx_handler(void *token, int len, int status)
 {
 	struct cpdma_chan	*ch;
 	struct sk_buff		*skb = token;
@@ -434,7 +435,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 
 		/* the interface is going down, skbs are purged */
 		dev_kfree_skb_any(skb);
-		return;
+		return 0;
 	}
 
 	new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
@@ -459,7 +460,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 requeue:
 	if (netif_dormant(ndev)) {
 		dev_kfree_skb_any(new_skb);
-		return;
+		return 0;
 	}
 
 	ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
@@ -467,6 +468,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 				skb_tailroom(new_skb), 0);
 	if (WARN_ON(ret < 0))
 		dev_kfree_skb_any(new_skb);
+
+	return 0;
 }
 
 void cpsw_split_res(struct cpsw_common *cpsw)
@@ -605,7 +608,8 @@ static int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
 		else
 			cur_budget = txv->budget;
 
-		num_tx += cpdma_chan_process(txv->ch, cur_budget);
+		cpdma_chan_process(txv->ch, &cur_budget);
+		num_tx += cur_budget;
 		if (num_tx >= budget)
 			break;
 	}
@@ -623,7 +627,8 @@ static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
 	struct cpsw_common *cpsw = napi_to_cpsw(napi_tx);
 	int num_tx;
 
-	num_tx = cpdma_chan_process(cpsw->txv[0].ch, budget);
+	num_tx = budget;
+	cpdma_chan_process(cpsw->txv[0].ch, &num_tx);
 	if (num_tx < budget) {
 		napi_complete(napi_tx);
 		writel(0xff, &cpsw->wr_regs->tx_en);
@@ -655,7 +660,8 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
 		else
 			cur_budget = rxv->budget;
 
-		num_rx += cpdma_chan_process(rxv->ch, cur_budget);
+		cpdma_chan_process(rxv->ch, &cur_budget);
+		num_rx += cur_budget;
 		if (num_rx >= budget)
 			break;
 	}
@@ -673,7 +679,8 @@ static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
 	struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
 	int num_rx;
 
-	num_rx = cpdma_chan_process(cpsw->rxv[0].ch, budget);
+	num_rx = budget;
+	cpdma_chan_process(cpsw->rxv[0].ch, &num_rx);
 	if (num_rx < budget) {
 		napi_complete_done(napi_rx, num_rx);
 		writel(0xff, &cpsw->wr_regs->rx_en);
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index c260bb32aacf..1a7c4818c890 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -538,8 +538,8 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
 				    cpdma_handler_fn rx_handler)
 {
 	struct cpsw_common *cpsw = priv->cpsw;
-	void (*handler)(void *, int, int);
 	struct netdev_queue *queue;
+	cpdma_handler_fn handler;
 	struct cpsw_vector *vec;
 	int ret, *ch, vch;
 
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 04795b97ee71..2ecb3af59fe9 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -390,7 +390,7 @@ void cpsw_split_res(struct cpsw_common *cpsw);
 int cpsw_fill_rx_channels(struct cpsw_priv *priv);
 void cpsw_intr_enable(struct cpsw_common *cpsw);
 void cpsw_intr_disable(struct cpsw_common *cpsw);
-void cpsw_tx_handler(void *token, int len, int status);
+int cpsw_tx_handler(void *token, int len, int status);
 
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 7f89b2299f05..a59011d315d5 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -1137,15 +1137,16 @@ bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
 	return free_tx_desc;
 }
 
-static void __cpdma_chan_free(struct cpdma_chan *chan,
-			      struct cpdma_desc __iomem *desc,
-			      int outlen, int status)
+static int __cpdma_chan_free(struct cpdma_chan *chan,
+			     struct cpdma_desc __iomem *desc, int outlen,
+			     int status)
 {
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
 	struct cpdma_desc_pool		*pool = ctlr->pool;
 	dma_addr_t			buff_dma;
 	int				origlen;
 	uintptr_t			token;
+	int				ret;
 
 	token      = desc_read(desc, sw_token);
 	origlen    = desc_read(desc, sw_len);
@@ -1160,14 +1161,16 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
 	}
 
 	cpdma_desc_free(pool, desc, 1);
-	(*chan->handler)((void *)token, outlen, status);
+	ret = (*chan->handler)((void *)token, outlen, status);
+
+	return ret;
 }
 
 static int __cpdma_chan_process(struct cpdma_chan *chan)
 {
+	int				status, outlen, ret;
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
 	struct cpdma_desc __iomem	*desc;
-	int				status, outlen;
 	int				cb_status = 0;
 	struct cpdma_desc_pool		*pool = ctlr->pool;
 	dma_addr_t			desc_dma;
@@ -1178,7 +1181,7 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
 	desc = chan->head;
 	if (!desc) {
 		chan->stats.empty_dequeue++;
-		status = -ENOENT;
+		ret = -ENOENT;
 		goto unlock_ret;
 	}
 	desc_dma = desc_phys(pool, desc);
@@ -1187,7 +1190,7 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
 	outlen	= status & 0x7ff;
 	if (status & CPDMA_DESC_OWNER) {
 		chan->stats.busy_dequeue++;
-		status = -EBUSY;
+		ret = -EBUSY;
 		goto unlock_ret;
 	}
 
@@ -1213,28 +1216,31 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
 	else
 		cb_status = status;
 
-	__cpdma_chan_free(chan, desc, outlen, cb_status);
-	return status;
+	ret = __cpdma_chan_free(chan, desc, outlen, cb_status);
+	return ret;
 
 unlock_ret:
 	spin_unlock_irqrestore(&chan->lock, flags);
-	return status;
+	return ret;
 }
 
-int cpdma_chan_process(struct cpdma_chan *chan, int quota)
+int cpdma_chan_process(struct cpdma_chan *chan, int *quota)
 {
-	int used = 0, ret = 0;
+	int used = 0, ret = 0, res = 0;
 
 	if (chan->state != CPDMA_STATE_ACTIVE)
 		return -EINVAL;
 
-	while (used < quota) {
+	while (used < *quota) {
 		ret = __cpdma_chan_process(chan);
 		if (ret < 0)
 			break;
+		res |= ret;
 		used++;
 	}
-	return used;
+
+	*quota = used;
+	return res;
 }
 
 int cpdma_chan_start(struct cpdma_chan *chan)
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 8f6f27185c63..56543d375923 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -61,7 +61,7 @@ struct cpdma_chan_stats {
 struct cpdma_ctlr;
 struct cpdma_chan;
 
-typedef void (*cpdma_handler_fn)(void *token, int len, int status);
+typedef int (*cpdma_handler_fn)(void *token, int len, int status);
 
 struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params);
 int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr);
@@ -81,7 +81,7 @@ int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
 			     dma_addr_t data, int len, int directed);
 int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		      int len, int directed);
-int cpdma_chan_process(struct cpdma_chan *chan, int quota);
+int cpdma_chan_process(struct cpdma_chan *chan, int *quota);
 
 int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable);
 void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value);
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 4bf65cab79e6..3592690b8dd8 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -860,7 +860,7 @@ static struct sk_buff *emac_rx_alloc(struct emac_priv *priv)
 	return skb;
 }
 
-static void emac_rx_handler(void *token, int len, int status)
+static int emac_rx_handler(void *token, int len, int status)
 {
 	struct sk_buff		*skb = token;
 	struct net_device	*ndev = skb->dev;
@@ -871,7 +871,7 @@ static void emac_rx_handler(void *token, int len, int status)
 	/* free and bail if we are shutting down */
 	if (unlikely(!netif_running(ndev))) {
 		dev_kfree_skb_any(skb);
-		return;
+		return 0;
 	}
 
 	/* recycle on receive error */
@@ -892,7 +892,7 @@ static void emac_rx_handler(void *token, int len, int status)
 	if (!skb) {
 		if (netif_msg_rx_err(priv) && net_ratelimit())
 			dev_err(emac_dev, "failed rx buffer alloc\n");
-		return;
+		return 0;
 	}
 
 recycle:
@@ -902,9 +902,11 @@ static void emac_rx_handler(void *token, int len, int status)
 	WARN_ON(ret == -ENOMEM);
 	if (unlikely(ret < 0))
 		dev_kfree_skb_any(skb);
+
+	return 0;
 }
 
-static void emac_tx_handler(void *token, int len, int status)
+static int emac_tx_handler(void *token, int len, int status)
 {
 	struct sk_buff		*skb = token;
 	struct net_device	*ndev = skb->dev;
@@ -917,6 +919,7 @@ static void emac_tx_handler(void *token, int len, int status)
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += len;
 	dev_kfree_skb_any(skb);
+	return 0;
 }
 
 /**
@@ -1237,8 +1240,8 @@ static int emac_poll(struct napi_struct *napi, int budget)
 		mask = EMAC_DM646X_MAC_IN_VECTOR_TX_INT_VEC;
 
 	if (status & mask) {
-		num_tx_pkts = cpdma_chan_process(priv->txchan,
-					      EMAC_DEF_TX_MAX_SERVICE);
+		num_tx_pkts = EMAC_DEF_TX_MAX_SERVICE;
+		cpdma_chan_process(priv->txchan, &num_tx_pkts);
 	} /* TX processing */
 
 	mask = EMAC_DM644X_MAC_IN_VECTOR_RX_INT_VEC;
@@ -1247,7 +1250,8 @@ static int emac_poll(struct napi_struct *napi, int budget)
 		mask = EMAC_DM646X_MAC_IN_VECTOR_RX_INT_VEC;
 
 	if (status & mask) {
-		num_rx_pkts = cpdma_chan_process(priv->rxchan, budget);
+		num_rx_pkts = budget;
+		cpdma_chan_process(priv->rxchan, &num_rx_pkts);
 	} /* RX processing */
 
 	mask = EMAC_DM644X_MAC_IN_VECTOR_HOST_INT;
-- 
2.17.1

[PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Ivan Khoronzhuk]

Add XDP support based on rx page_pool allocator, one frame per page.
Page pool allocator is used with assumption that only one rx_handler
is running simultaneously. DMA map/unmap is reused from page pool
despite there is no need to map whole page.

Due to specific of cpsw, the same TX/RX handler can be used by 2
network devices, so special fields in buffer are added to identify
an interface the frame is destined to. Thus XDP works for both
interfaces, that allows to test xdp redirect between two interfaces
easily.

XDP prog is common for all channels till appropriate changes are added
in XDP infrastructure. Also, once page_pool recycling becomes part of
skb netstack some simplifications can be added marked with comments.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
 drivers/net/ethernet/ti/Kconfig        |   1 +
 drivers/net/ethernet/ti/cpsw.c         | 506 ++++++++++++++++++++++---
 drivers/net/ethernet/ti/cpsw_ethtool.c |  94 ++++-
 drivers/net/ethernet/ti/cpsw_priv.h    |  10 +
 4 files changed, 548 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index bd05a977ee7e..3cb8c5214835 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -50,6 +50,7 @@ config TI_CPSW
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
 	select TI_DAVINCI_MDIO
 	select MFD_SYSCON
+	select PAGE_POOL
 	select REGMAP
 	---help---
 	  This driver supports TI's CPSW Ethernet Switch.
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index d89ad428315c..6eb7bde9409b 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,6 +31,10 @@
 #include <linux/if_vlan.h>
 #include <linux/kmemleak.h>
 #include <linux/sys_soc.h>
+#include <net/page_pool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include <linux/pinctrl/consumer.h>
 #include <net/pkt_cls.h>
@@ -60,6 +64,10 @@ static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
 module_param(descs_pool_size, int, 0444);
 MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
 
+/* The buf includes headroom compatible with both skb and xdpf */
+#define CPSW_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define CPSW_HEADROOM  ALIGN(CPSW_HEADROOM_NA, sizeof(long))
+
 #define for_each_slave(priv, func, arg...)				\
 	do {								\
 		struct cpsw_slave *slave;				\
@@ -74,6 +82,13 @@ MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
 				(func)(slave++, ##arg);			\
 	} while (0)
 
+#define CPSW_XMETA_OFFSET	ALIGN(sizeof(struct xdp_frame), sizeof(long))
+
+#define CPSW_XDP_CONSUMED		1
+#define CPSW_XDP_CONSUMED_FLUSH		2
+#define CPSW_XDP_PASS			0
+#define CPSW_FLUSH_XDP_MAP		1
+
 static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 				    __be16 proto, u16 vid);
 
@@ -337,24 +352,58 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
 	return;
 }
 
+static int cpsw_is_xdpf_handle(void *handle)
+{
+	return (unsigned long)handle & BIT(0);
+}
+
+static void *cpsw_xdpf_to_handle(struct xdp_frame *xdpf)
+{
+	return (void *)((unsigned long)xdpf | BIT(0));
+}
+
+static struct xdp_frame *cpsw_handle_to_xdpf(void *handle)
+{
+	return (struct xdp_frame *)((unsigned long)handle & ~BIT(0));
+}
+
+struct __aligned(sizeof(long)) cpsw_meta_xdp {
+	struct net_device *ndev;
+	int ch;
+};
+
 int cpsw_tx_handler(void *token, int len, int status)
 {
+	struct cpsw_meta_xdp	*xmeta;
+	struct xdp_frame	*xdpf;
+	struct net_device	*ndev;
 	struct netdev_queue	*txq;
-	struct sk_buff		*skb = token;
-	struct net_device	*ndev = skb->dev;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct sk_buff		*skb;
+	int			ch;
+
+	if (cpsw_is_xdpf_handle(token)) {
+		xdpf = cpsw_handle_to_xdpf(token);
+		xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+		ndev = xmeta->ndev;
+		ch = xmeta->ch;
+		xdp_return_frame_rx_napi(xdpf);
+	} else {
+		skb = token;
+		ndev = skb->dev;
+		ch = skb_get_queue_mapping(skb);
+		cpts_tx_timestamp(ndev_to_cpsw(ndev)->cpts, skb);
+		dev_kfree_skb_any(skb);
+	}
 
 	/* Check whether the queue is stopped due to stalled tx dma, if the
 	 * queue is stopped then start the queue as we have free desc for tx
 	 */
-	txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
+	txq = netdev_get_tx_queue(ndev, ch);
 	if (unlikely(netif_tx_queue_stopped(txq)))
 		netif_tx_wake_queue(txq);
 
-	cpts_tx_timestamp(cpsw->cpts, skb);
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += len;
-	dev_kfree_skb_any(skb);
 	return 0;
 }
 
@@ -401,22 +450,220 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
 	}
 }
 
+static int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf,
+			     struct page *page)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_meta_xdp *xmeta;
+	struct netdev_queue *txq;
+	struct cpdma_chan *txch;
+	dma_addr_t dma;
+	int ret, port;
+
+	xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+	xmeta->ch = 0;
+	txch = cpsw->txv[0].ch;
+
+	port = priv->emac_port + cpsw->data.dual_emac;
+	if (page) {
+		dma = page_pool_get_dma_addr(page);
+		dma += xdpf->data - (void *)xdpf;
+		ret = cpdma_chan_submit_mapped(txch, cpsw_xdpf_to_handle(xdpf),
+					       dma, xdpf->len, port);
+	} else {
+		if (sizeof(*xmeta) > xdpf->headroom) {
+			xdp_return_frame_rx_napi(xdpf);
+			return -EINVAL;
+		}
+
+		xmeta->ndev = priv->ndev;
+		ret = cpdma_chan_submit(txch, cpsw_xdpf_to_handle(xdpf),
+					xdpf->data, xdpf->len, port);
+	}
+
+	if (ret) {
+		xdp_return_frame_rx_napi(xdpf);
+		goto stop;
+	}
+
+	/* no tx desc - stop sending us tx frames */
+	if (unlikely(!cpdma_check_free_tx_desc(txch)))
+		goto stop;
+
+	return ret;
+stop:
+	txq = netdev_get_tx_queue(priv->ndev, 0);
+	netif_tx_stop_queue(txq);
+
+	/* Barrier, so that stop_queue visible to other cpus */
+	smp_mb__after_atomic();
+
+	if (cpdma_check_free_tx_desc(txch))
+		netif_tx_wake_queue(txq);
+
+	return ret;
+}
+
+static int cpsw_run_xdp(struct cpsw_priv *priv, struct cpsw_vector *rxv,
+			struct xdp_buff *xdp, struct page *page)
+{
+	struct net_device *ndev = priv->ndev;
+	int ret = CPSW_XDP_CONSUMED;
+	struct xdp_frame *xdpf;
+	struct bpf_prog *prog;
+	u32 act;
+
+	rcu_read_lock();
+
+	prog = READ_ONCE(priv->xdp_prog);
+	if (!prog) {
+		ret = CPSW_XDP_PASS;
+		goto out;
+	}
+
+	act = bpf_prog_run_xdp(prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		ret = CPSW_XDP_PASS;
+		break;
+	case XDP_TX:
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf))
+			goto drop;
+
+		cpsw_xdp_tx_frame(priv, xdpf, page);
+		break;
+	case XDP_REDIRECT:
+		if (xdp_do_redirect(ndev, xdp, prog))
+			goto drop;
+
+		ret = CPSW_XDP_CONSUMED_FLUSH;
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(ndev, prog, act);
+		/* fall through -- handle aborts by dropping packet */
+	case XDP_DROP:
+		goto drop;
+	}
+out:
+	rcu_read_unlock();
+	return ret;
+drop:
+	rcu_read_unlock();
+	page_pool_recycle_direct(priv->cpsw->page_pool, page);
+	return ret;
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+	len += CPSW_HEADROOM;
+	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	return SKB_DATA_ALIGN(len);
+}
+
+void cpsw_xdp_unreg_rxqs(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	int i;
+
+	for (i = 0; i < cpsw->rx_ch_num; i++)
+		xdp_rxq_info_unreg(&priv->xdp_rxq[i]);
+}
+
+int cpsw_xdp_reg_rxq(struct cpsw_priv *priv, int ch)
+{
+	struct xdp_rxq_info *xdp_rxq = &priv->xdp_rxq[ch];
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+
+	ret = xdp_rxq_info_reg(xdp_rxq, priv->ndev, ch);
+	if (ret)
+		goto err_cleanup;
+
+	ret = xdp_rxq_info_reg_mem_model(xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 cpsw->page_pool);
+	if (ret)
+		goto err_cleanup;
+
+	return 0;
+
+err_cleanup:
+	if (xdp_rxq_info_is_reg(xdp_rxq))
+		xdp_rxq_info_unreg(xdp_rxq);
+
+	return ret;
+}
+
+int cpsw_xdp_reg_rxqs(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct xdp_rxq_info *xdp_rxq;
+	int i, ret;
+
+	for (i = 0; i < cpsw->rx_ch_num; i++) {
+		ret = cpsw_xdp_reg_rxq(priv, i);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	return 0;
+
+err_cleanup:
+	while (i--) {
+		xdp_rxq = &priv->xdp_rxq[i];
+		if (xdp_rxq_info_is_reg(xdp_rxq))
+			xdp_rxq_info_unreg(xdp_rxq);
+	}
+
+	return ret;
+}
+
+struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, int size)
+{
+	struct page_pool_params pp_params = { 0 };
+	struct page_pool *pool;
+
+	pp_params.order = 0;
+	pp_params.flags = PP_FLAG_DMA_MAP;
+
+	/* set it to number of RX descriptors, but can be more */
+	pp_params.pool_size = size;
+	pp_params.nid = NUMA_NO_NODE;
+	pp_params.dma_dir = DMA_BIDIRECTIONAL;
+	pp_params.dev = cpsw->dev;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		dev_err(cpsw->dev, "cannot create rx page pool\n");
+
+	return pool;
+}
+
 static int cpsw_rx_handler(void *token, int len, int status)
 {
-	struct cpdma_chan	*ch;
-	struct sk_buff		*skb = token;
-	struct sk_buff		*new_skb;
-	struct net_device	*ndev = skb->dev;
-	int			ret = 0, port;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct page		*new_page, *page = token;
+	void			*pa = page_address(page);
+	struct cpsw_meta_xdp	*xmeta = pa + CPSW_XMETA_OFFSET;
+	struct cpsw_common	*cpsw = ndev_to_cpsw(xmeta->ndev);
+	int			pkt_size = cpsw->rx_packet_max;
+	int			ret = 0, port, ch = xmeta->ch;
+	struct page_pool	*pool = cpsw->page_pool;
+	int			headroom = CPSW_HEADROOM;
+	struct net_device	*ndev = xmeta->ndev;
+	int			res = 0;
 	struct cpsw_priv	*priv;
+	struct sk_buff		*skb;
+	struct xdp_buff		xdp;
+	dma_addr_t		dma;
 
 	if (cpsw->data.dual_emac) {
 		port = CPDMA_RX_SOURCE_PORT(status);
-		if (port) {
+		if (port)
 			ndev = cpsw->slaves[--port].ndev;
-			skb->dev = ndev;
-		}
 	}
 
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
@@ -427,49 +674,97 @@ static int cpsw_rx_handler(void *token, int len, int status)
 			 * is already down and the other interface is up
 			 * and running, instead of freeing which results
 			 * in reducing of the number of rx descriptor in
-			 * DMA engine, requeue skb back to cpdma.
+			 * DMA engine, requeue page back to cpdma.
 			 */
-			new_skb = skb;
+			new_page = page;
 			goto requeue;
 		}
 
-		/* the interface is going down, skbs are purged */
-		dev_kfree_skb_any(skb);
+		/* the interface is going down, pages are purged */
+		page_pool_recycle_direct(pool, page);
 		return 0;
 	}
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
-	if (new_skb) {
-		skb_copy_queue_mapping(new_skb, skb);
-		skb_put(skb, len);
-		if (status & CPDMA_RX_VLAN_ENCAP)
-			cpsw_rx_vlan_encap(skb);
-		priv = netdev_priv(ndev);
-		if (priv->rx_ts_enabled)
-			cpts_rx_timestamp(cpsw->cpts, skb);
-		skb->protocol = eth_type_trans(skb, ndev);
-		netif_receive_skb(skb);
-		ndev->stats.rx_bytes += len;
-		ndev->stats.rx_packets++;
-		kmemleak_not_leak(new_skb);
-	} else {
+	new_page = page_pool_dev_alloc_pages(cpsw->page_pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
 		ndev->stats.rx_dropped++;
-		new_skb = skb;
+		goto requeue;
 	}
 
+	priv = netdev_priv(ndev);
+	if (priv->xdp_prog) {
+		if (status & CPDMA_RX_VLAN_ENCAP) {
+			xdp.data = (void *)pa + CPSW_HEADROOM +
+				   CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+			xdp.data_end = xdp.data + len -
+				       CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+		} else {
+			xdp.data = (void *)pa + CPSW_HEADROOM;
+			xdp.data_end = xdp.data + len;
+		}
+
+		xdp_set_data_meta_invalid(&xdp);
+
+		xdp.data_hard_start = pa;
+		xdp.rxq = &priv->xdp_rxq[ch];
+
+		ret = cpsw_run_xdp(priv, &cpsw->rxv[ch], &xdp, page);
+		if (ret != CPSW_XDP_PASS) {
+			if (ret == CPSW_XDP_CONSUMED_FLUSH)
+				res = CPSW_FLUSH_XDP_MAP;
+
+			goto requeue;
+		}
+
+		/* XDP prog might have changed packet data and boundaries */
+		len = xdp.data_end - xdp.data;
+		headroom = xdp.data - xdp.data_hard_start;
+	}
+
+	/* Build skb and pass it to netstack if XDP off or XDP prog
+	 * returned XDP_PASS
+	 */
+	skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
+	}
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+	skb->dev = ndev;
+	if (status & CPDMA_RX_VLAN_ENCAP)
+		cpsw_rx_vlan_encap(skb);
+	if (priv->rx_ts_enabled)
+		cpts_rx_timestamp(cpsw->cpts, skb);
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	/* unmap page as no skb page recycling */
+	page_pool_unmap_page(pool, page);
+	netif_receive_skb(skb);
+
+	ndev->stats.rx_bytes += len;
+	ndev->stats.rx_packets++;
+
 requeue:
 	if (netif_dormant(ndev)) {
-		dev_kfree_skb_any(new_skb);
-		return 0;
+		page_pool_recycle_direct(pool, new_page);
+		return res;
 	}
 
-	ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
-	ret = cpdma_chan_submit(ch, new_skb, new_skb->data,
-				skb_tailroom(new_skb), 0);
+	xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+	xmeta->ndev = ndev;
+	xmeta->ch = ch;
+
+	dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+	ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+				       pkt_size, 0);
 	if (WARN_ON(ret < 0))
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(pool, new_page);
 
-	return 0;
+	return res;
 }
 
 void cpsw_split_res(struct cpsw_common *cpsw)
@@ -644,8 +939,8 @@ static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
 static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
 {
 	u32			ch_map;
-	int			num_rx, cur_budget, ch;
 	struct cpsw_common	*cpsw = napi_to_cpsw(napi_rx);
+	int			num_rx, cur_budget, ch, res;
 	struct cpsw_vector	*rxv;
 
 	/* process every unprocessed channel */
@@ -660,8 +955,12 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
 		else
 			cur_budget = rxv->budget;
 
-		cpdma_chan_process(rxv->ch, &cur_budget);
+		res = cpdma_chan_process(rxv->ch, &cur_budget);
 		num_rx += cur_budget;
+
+		if (res & CPSW_FLUSH_XDP_MAP)
+			xdp_do_flush_map();
+
 		if (num_rx >= budget)
 			break;
 	}
@@ -677,10 +976,15 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
 static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
 {
 	struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
-	int num_rx;
+	struct cpsw_vector *rxv;
+	int num_rx, res;
 
 	num_rx = budget;
-	cpdma_chan_process(cpsw->rxv[0].ch, &num_rx);
+	rxv = &cpsw->rxv[0];
+	res = cpdma_chan_process(rxv->ch, &num_rx);
+	if (res & CPSW_FLUSH_XDP_MAP)
+		xdp_do_flush_map();
+
 	if (num_rx < budget) {
 		napi_complete_done(napi_rx, num_rx);
 		writel(0xff, &cpsw->wr_regs->rx_en);
@@ -1042,33 +1346,36 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
 int cpsw_fill_rx_channels(struct cpsw_priv *priv)
 {
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct sk_buff *skb;
+	struct cpsw_meta_xdp *xmeta;
+	struct page *page;
 	int ch_buf_num;
 	int ch, i, ret;
+	dma_addr_t dma;
 
 	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
 		ch_buf_num = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
 		for (i = 0; i < ch_buf_num; i++) {
-			skb = __netdev_alloc_skb_ip_align(priv->ndev,
-							  cpsw->rx_packet_max,
-							  GFP_KERNEL);
-			if (!skb) {
-				cpsw_err(priv, ifup, "cannot allocate skb\n");
+			page = page_pool_dev_alloc_pages(cpsw->page_pool);
+			if (!page) {
+				cpsw_err(priv, ifup, "allocate rx page err\n");
 				return -ENOMEM;
 			}
 
-			skb_set_queue_mapping(skb, ch);
-			ret = cpdma_chan_submit(cpsw->rxv[ch].ch, skb,
-						skb->data, skb_tailroom(skb),
-						0);
+			xmeta = page_address(page) + CPSW_XMETA_OFFSET;
+			xmeta->ndev = priv->ndev;
+			xmeta->ch = ch;
+
+			dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+			ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, page,
+						       dma, cpsw->rx_packet_max,
+						       0);
 			if (ret < 0) {
 				cpsw_err(priv, ifup,
-					 "cannot submit skb to channel %d rx, error %d\n",
+					 "cannot submit page to channel %d rx, error %d\n",
 					 ch, ret);
-				kfree_skb(skb);
+				page_pool_recycle_direct(cpsw->page_pool, page);
 				return ret;
 			}
-			kmemleak_not_leak(skb);
 		}
 
 		cpsw_info(priv, ifup, "ch %d rx, submitted %d descriptors\n",
@@ -1338,7 +1645,7 @@ static int cpsw_ndo_open(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	int ret;
+	int ret, pool_size;
 	u32 reg;
 
 	ret = pm_runtime_get_sync(cpsw->dev);
@@ -1404,6 +1711,14 @@ static int cpsw_ndo_open(struct net_device *ndev)
 			enable_irq(cpsw->irqs_table[0]);
 		}
 
+		pool_size = cpdma_get_num_rx_descs(cpsw->dma);
+		cpsw->page_pool = cpsw_create_page_pool(cpsw, pool_size);
+		if (IS_ERR(cpsw->page_pool)) {
+			ret = PTR_ERR(cpsw->page_pool);
+			cpsw->page_pool = NULL;
+			goto err_cleanup;
+		}
+
 		ret = cpsw_fill_rx_channels(priv);
 		if (ret < 0)
 			goto err_cleanup;
@@ -1423,6 +1738,10 @@ static int cpsw_ndo_open(struct net_device *ndev)
 		cpsw_set_coalesce(ndev, &coal);
 	}
 
+	ret = cpsw_xdp_reg_rxqs(priv);
+	if (ret)
+		goto err_cleanup;
+
 	cpdma_ctlr_start(cpsw->dma);
 	cpsw_intr_enable(cpsw);
 	cpsw->usage_count++;
@@ -1432,9 +1751,11 @@ static int cpsw_ndo_open(struct net_device *ndev)
 err_cleanup:
 	if (!cpsw->usage_count) {
 		cpdma_ctlr_stop(cpsw->dma);
-		for_each_slave(priv, cpsw_slave_stop, cpsw);
+		if (cpsw->page_pool)
+			page_pool_destroy(cpsw->page_pool);
 	}
 
+	for_each_slave(priv, cpsw_slave_stop, cpsw);
 	pm_runtime_put_sync(cpsw->dev);
 	netif_carrier_off(priv->ndev);
 	return ret;
@@ -1457,12 +1778,15 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 		cpsw_intr_disable(cpsw);
 		cpdma_ctlr_stop(cpsw->dma);
 		cpsw_ale_stop(cpsw->ale);
+		page_pool_destroy(cpsw->page_pool);
 	}
 	for_each_slave(priv, cpsw_slave_stop, cpsw);
 
 	if (cpsw_need_resplit(cpsw))
 		cpsw_split_res(cpsw);
 
+	cpsw_xdp_unreg_rxqs(priv);
+
 	cpsw->usage_count--;
 	pm_runtime_put_sync(cpsw->dev);
 	return 0;
@@ -2014,6 +2338,64 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf)
+{
+	struct bpf_prog *prog = bpf->prog;
+
+	if (!priv->xdpi.prog && !prog)
+		return 0;
+
+	if (!xdp_attachment_flags_ok(&priv->xdpi, bpf))
+		return -EBUSY;
+
+	WRITE_ONCE(priv->xdp_prog, prog);
+
+	xdp_attachment_setup(&priv->xdpi, bpf);
+
+	return 0;
+}
+
+static int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return cpsw_xdp_prog_setup(priv, bpf);
+
+	case XDP_QUERY_PROG:
+		return xdp_attachment_query(&priv->xdpi, bpf);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+			     struct xdp_frame **frames, u32 flags)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct xdp_frame *xdpf;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
+
+		if (cpsw_xdp_tx_frame(priv, xdpf, NULL))
+			drops++;
+	}
+
+	return n - drops;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void cpsw_ndo_poll_controller(struct net_device *ndev)
 {
@@ -2042,6 +2424,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
 	.ndo_setup_tc           = cpsw_ndo_setup_tc,
+	.ndo_bpf		= cpsw_ndo_bpf,
+	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
 };
 
 static void cpsw_get_drvinfo(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 1a7c4818c890..45028088b070 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -14,6 +14,7 @@
 #include <linux/phy.h>
 #include <linux/pm_runtime.h>
 #include <linux/skbuff.h>
+#include <net/page_pool.h>
 
 #include "cpsw.h"
 #include "cpts.h"
@@ -534,6 +535,59 @@ static int cpsw_check_ch_settings(struct cpsw_common *cpsw,
 	return 0;
 }
 
+void cpsw_xdp_rxq_unreg(struct cpsw_common *cpsw, int ch)
+{
+	struct net_device *ndev;
+	struct cpsw_priv *priv;
+	int i;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		priv = netdev_priv(ndev);
+		xdp_rxq_info_unreg(&priv->xdp_rxq[ch]);
+	}
+}
+
+static int cpsw_xdp_sl_reg_rxq(struct cpsw_common *cpsw, int ch)
+{
+	struct net_device *ndev;
+	struct cpsw_priv *priv;
+	int i, ret;
+
+	/* As channels are common for both ports sharing same queues, xdp_rxq
+	 * information also becomes shared and used by every packet on this
+	 * channel. But each xdp_rxq holds link on netdev, which by the theory
+	 * can have different memory model and so, network device must hold it's
+	 * own set of rxq and thus both netdevs should be prepared
+	 */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		ret = cpsw_xdp_reg_rxq(netdev_priv(ndev), ch);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	return 0;
+
+err_cleanup:
+	while (i--) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		priv = netdev_priv(ndev);
+		xdp_rxq_info_unreg(&priv->xdp_rxq[ch]);
+	}
+
+	return ret;
+}
+
 static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
 				    cpdma_handler_fn rx_handler)
 {
@@ -565,6 +619,11 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
 		if (!vec[*ch].ch)
 			return -EINVAL;
 
+		if (rx && cpsw_xdp_sl_reg_rxq(cpsw, *ch)) {
+			cpdma_chan_destroy(vec[*ch].ch);
+			return -EINVAL;
+		}
+
 		cpsw_info(priv, ifup, "created new %d %s channel\n", *ch,
 			  (rx ? "rx" : "tx"));
 		(*ch)++;
@@ -573,6 +632,9 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
 	while (*ch > ch_num) {
 		(*ch)--;
 
+		if (rx)
+			cpsw_xdp_rxq_unreg(cpsw, *ch);
+
 		ret = cpdma_chan_destroy(vec[*ch].ch);
 		if (ret)
 			return ret;
@@ -656,7 +718,8 @@ int cpsw_set_ringparam(struct net_device *ndev,
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
 	struct cpsw_common *cpsw = priv->cpsw;
-	int ret;
+	struct page_pool *pool;
+	int ret, i;
 
 	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
 
@@ -668,6 +731,10 @@ int cpsw_set_ringparam(struct net_device *ndev,
 	if (ering->rx_pending == cpdma_get_num_rx_descs(cpsw->dma))
 		return 0;
 
+	pool = cpsw_create_page_pool(cpsw, ering->rx_pending);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
 	cpsw_suspend_data_pass(ndev);
 
 	cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
@@ -675,10 +742,33 @@ int cpsw_set_ringparam(struct net_device *ndev,
 	if (cpsw->usage_count)
 		cpdma_chan_split_pool(cpsw->dma);
 
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		cpsw_xdp_unreg_rxqs(netdev_priv(ndev));
+	}
+
+	page_pool_destroy(cpsw->page_pool);
+	cpsw->page_pool = pool;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct net_device *ndev = cpsw->slaves[i].ndev;
+
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		ret = cpsw_xdp_reg_rxqs(netdev_priv(ndev));
+		if (ret)
+			goto err;
+	}
+
 	ret = cpsw_resume_data_pass(ndev);
 	if (!ret)
 		return 0;
-
+err:
 	dev_err(cpsw->dev, "cannot set ring params, closing device\n");
 	dev_close(ndev);
 	return ret;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 2ecb3af59fe9..e59a54ee7540 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -346,6 +346,7 @@ struct cpsw_common {
 	int				rx_ch_num, tx_ch_num;
 	int				speed;
 	int				usage_count;
+	struct page_pool		*page_pool;
 };
 
 struct cpsw_priv {
@@ -360,6 +361,10 @@ struct cpsw_priv {
 	int				shp_cfg_speed;
 	int				tx_ts_enabled;
 	int				rx_ts_enabled;
+	struct bpf_prog			*xdp_prog;
+	struct xdp_rxq_info		xdp_rxq[CPSW_MAX_QUEUES];
+	struct xdp_attachment_info	xdpi;
+
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -391,6 +396,11 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv);
 void cpsw_intr_enable(struct cpsw_common *cpsw);
 void cpsw_intr_disable(struct cpsw_common *cpsw);
 int cpsw_tx_handler(void *token, int len, int status);
+void cpsw_xdp_rxq_unreg(struct cpsw_common *cpsw, int ch);
+struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, int size);
+int cpsw_xdp_reg_rxq(struct cpsw_priv *priv, int ch);
+int cpsw_xdp_reg_rxqs(struct cpsw_priv *priv);
+void cpsw_xdp_unreg_rxqs(struct cpsw_priv *priv);
 
 /* ethtool */
 u32 cpsw_get_msglevel(struct net_device *ndev);
-- 
2.17.1

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Jesper Dangaard Brouer]

Hi Ivan,

From below code snippets, it looks like you only allocated 1 page_pool
and sharing it with several RX-queues, as I don't have the full context
and don't know this driver, I might be wrong?

To be clear, a page_pool object is needed per RX-queue, as it is
accessing a small RX page cache (which protected by NAPI/softirq).

On Thu, 30 May 2019 21:20:39 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> @@ -1404,6 +1711,14 @@ static int cpsw_ndo_open(struct net_device *ndev)
>  			enable_irq(cpsw->irqs_table[0]);
>  		}
>  
> +		pool_size = cpdma_get_num_rx_descs(cpsw->dma);
> +		cpsw->page_pool = cpsw_create_page_pool(cpsw, pool_size);
> +		if (IS_ERR(cpsw->page_pool)) {
> +			ret = PTR_ERR(cpsw->page_pool);
> +			cpsw->page_pool = NULL;
> +			goto err_cleanup;
> +		}

On Thu, 30 May 2019 21:20:39 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> @@ -675,10 +742,33 @@ int cpsw_set_ringparam(struct net_device *ndev,
>  	if (cpsw->usage_count)
>  		cpdma_chan_split_pool(cpsw->dma);
>  
> +	for (i = 0; i < cpsw->data.slaves; i++) {
> +		struct net_device *ndev = cpsw->slaves[i].ndev;
> +
> +		if (!(ndev && netif_running(ndev)))
> +			continue;
> +
> +		cpsw_xdp_unreg_rxqs(netdev_priv(ndev));
> +	}
> +
> +	page_pool_destroy(cpsw->page_pool);
> +	cpsw->page_pool = pool;
> +

On Thu, 30 May 2019 21:20:39 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> +void cpsw_xdp_unreg_rxqs(struct cpsw_priv *priv)
> +{
> +	struct cpsw_common *cpsw = priv->cpsw;
> +	int i;
> +
> +	for (i = 0; i < cpsw->rx_ch_num; i++)
> +		xdp_rxq_info_unreg(&priv->xdp_rxq[i]);
> +}


On Thu, 30 May 2019 21:20:39 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> +int cpsw_xdp_reg_rxq(struct cpsw_priv *priv, int ch)
> +{
> +	struct xdp_rxq_info *xdp_rxq = &priv->xdp_rxq[ch];
> +	struct cpsw_common *cpsw = priv->cpsw;
> +	int ret;
> +
> +	ret = xdp_rxq_info_reg(xdp_rxq, priv->ndev, ch);
> +	if (ret)
> +		goto err_cleanup;
> +
> +	ret = xdp_rxq_info_reg_mem_model(xdp_rxq, MEM_TYPE_PAGE_POOL,
> +					 cpsw->page_pool);
> +	if (ret)
> +		goto err_cleanup;
> +
> +	return 0;



-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Ivan Khoronzhuk]

On Fri, May 31, 2019 at 05:46:43PM +0200, Jesper Dangaard Brouer wrote:

Hi Jesper,

>
>Hi Ivan,
>
>From below code snippets, it looks like you only allocated 1 page_pool
>and sharing it with several RX-queues, as I don't have the full context
>and don't know this driver, I might be wrong?
>
>To be clear, a page_pool object is needed per RX-queue, as it is
>accessing a small RX page cache (which protected by NAPI/softirq).

There is one RX interrupt and one RX NAPI for all rx channels.

>
>On Thu, 30 May 2019 21:20:39 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> @@ -1404,6 +1711,14 @@ static int cpsw_ndo_open(struct net_device *ndev)
>>  			enable_irq(cpsw->irqs_table[0]);
>>  		}
>>
>> +		pool_size = cpdma_get_num_rx_descs(cpsw->dma);
>> +		cpsw->page_pool = cpsw_create_page_pool(cpsw, pool_size);
>> +		if (IS_ERR(cpsw->page_pool)) {
>> +			ret = PTR_ERR(cpsw->page_pool);
>> +			cpsw->page_pool = NULL;
>> +			goto err_cleanup;
>> +		}
>
>On Thu, 30 May 2019 21:20:39 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> @@ -675,10 +742,33 @@ int cpsw_set_ringparam(struct net_device *ndev,
>>  	if (cpsw->usage_count)
>>  		cpdma_chan_split_pool(cpsw->dma);
>>
>> +	for (i = 0; i < cpsw->data.slaves; i++) {
>> +		struct net_device *ndev = cpsw->slaves[i].ndev;
>> +
>> +		if (!(ndev && netif_running(ndev)))
>> +			continue;
>> +
>> +		cpsw_xdp_unreg_rxqs(netdev_priv(ndev));
>> +	}
>> +
>> +	page_pool_destroy(cpsw->page_pool);
>> +	cpsw->page_pool = pool;
>> +
>
>On Thu, 30 May 2019 21:20:39 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> +void cpsw_xdp_unreg_rxqs(struct cpsw_priv *priv)
>> +{
>> +	struct cpsw_common *cpsw = priv->cpsw;
>> +	int i;
>> +
>> +	for (i = 0; i < cpsw->rx_ch_num; i++)
>> +		xdp_rxq_info_unreg(&priv->xdp_rxq[i]);
>> +}
>
>
>On Thu, 30 May 2019 21:20:39 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> +int cpsw_xdp_reg_rxq(struct cpsw_priv *priv, int ch)
>> +{
>> +	struct xdp_rxq_info *xdp_rxq = &priv->xdp_rxq[ch];
>> +	struct cpsw_common *cpsw = priv->cpsw;
>> +	int ret;
>> +
>> +	ret = xdp_rxq_info_reg(xdp_rxq, priv->ndev, ch);
>> +	if (ret)
>> +		goto err_cleanup;
>> +
>> +	ret = xdp_rxq_info_reg_mem_model(xdp_rxq, MEM_TYPE_PAGE_POOL,
>> +					 cpsw->page_pool);
>> +	if (ret)
>> +		goto err_cleanup;
>> +
>> +	return 0;
>
>
>
>-- 
>Best regards,
>  Jesper Dangaard Brouer
>  MSc.CS, Principal Kernel Engineer at Red Hat
>  LinkedIn: http://www.linkedin.com/in/brouer

-- 
Regards,
Ivan Khoronzhuk

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Jesper Dangaard Brouer]

On Fri, 31 May 2019 19:25:24 +0300 Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> On Fri, May 31, 2019 at 05:46:43PM +0200, Jesper Dangaard Brouer wrote:
> >
> >From below code snippets, it looks like you only allocated 1 page_pool
> >and sharing it with several RX-queues, as I don't have the full context
> >and don't know this driver, I might be wrong?
> >
> >To be clear, a page_pool object is needed per RX-queue, as it is
> >accessing a small RX page cache (which protected by NAPI/softirq).  
> 
> There is one RX interrupt and one RX NAPI for all rx channels.

So, what are you saying?

You _are_ sharing the page_pool between several RX-channels, but it is
safe because this hardware only have one RX interrupt + NAPI instance??

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Ivan Khoronzhuk]

On Fri, May 31, 2019 at 06:32:41PM +0200, Jesper Dangaard Brouer wrote:
>
>On Fri, 31 May 2019 19:25:24 +0300 Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> On Fri, May 31, 2019 at 05:46:43PM +0200, Jesper Dangaard Brouer wrote:
>> >
>> >From below code snippets, it looks like you only allocated 1 page_pool
>> >and sharing it with several RX-queues, as I don't have the full context
>> >and don't know this driver, I might be wrong?
>> >
>> >To be clear, a page_pool object is needed per RX-queue, as it is
>> >accessing a small RX page cache (which protected by NAPI/softirq).
>>
>> There is one RX interrupt and one RX NAPI for all rx channels.
>
>So, what are you saying?
>
>You _are_ sharing the page_pool between several RX-channels, but it is
>safe because this hardware only have one RX interrupt + NAPI instance??

I can miss smth but in case of cpsw technically it means:
1) RX interrupts are disabled while NAPI is scheduled,
   not for particular CPU or channel, but at all, for whole cpsw module.
2) RX channels are handled one by one by priority.
3) After all of them handled and no more in budget - interrupts are enabled.
4) If page is returned to the pool, and it's within NAPI, no races as it's
   returned protected by softirq. If it's returned not in softirq it's protected 
   by producer lock of the ring.

Probably it's not good example for others how it should be used, not a big
problem to move it to separate pools.., even don't remember why I decided to
use shared pool, there was some more reasons... need search in history.

>
>-- 
>Best regards,
>  Jesper Dangaard Brouer
>  MSc.CS, Principal Kernel Engineer at Red Hat
>  LinkedIn: http://www.linkedin.com/in/brouer

-- 
Regards,
Ivan Khoronzhuk

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Saeed Mahameed]

On Fri, 2019-05-31 at 20:03 +0300, Ivan Khoronzhuk wrote:
> On Fri, May 31, 2019 at 06:32:41PM +0200, Jesper Dangaard Brouer
> wrote:
> > On Fri, 31 May 2019 19:25:24 +0300 Ivan Khoronzhuk <
> > ivan.khoronzhuk@linaro.org> wrote:
> > 
> > > On Fri, May 31, 2019 at 05:46:43PM +0200, Jesper Dangaard Brouer
> > > wrote:
> > > > From below code snippets, it looks like you only allocated 1
> > > > page_pool
> > > > and sharing it with several RX-queues, as I don't have the full
> > > > context
> > > > and don't know this driver, I might be wrong?
> > > > 
> > > > To be clear, a page_pool object is needed per RX-queue, as it
> > > > is
> > > > accessing a small RX page cache (which protected by
> > > > NAPI/softirq).
> > > 
> > > There is one RX interrupt and one RX NAPI for all rx channels.
> > 
> > So, what are you saying?
> > 
> > You _are_ sharing the page_pool between several RX-channels, but it
> > is
> > safe because this hardware only have one RX interrupt + NAPI
> > instance??
> 
> I can miss smth but in case of cpsw technically it means:
> 1) RX interrupts are disabled while NAPI is scheduled,
>    not for particular CPU or channel, but at all, for whole cpsw
> module.
> 2) RX channels are handled one by one by priority.

Hi Ivan, I got a silly question.. 

What is the reason behind having multiple RX rings and one CPU/NAPI
handling all of them ? priority ? how do you priorities ?

> 3) After all of them handled and no more in budget - interrupts are
> enabled.
> 4) If page is returned to the pool, and it's within NAPI, no races as
> it's
>    returned protected by softirq. If it's returned not in softirq
> it's protected 
>    by producer lock of the ring.
> 
> Probably it's not good example for others how it should be used, not
> a big
> problem to move it to separate pools.., even don't remember why I
> decided to
> use shared pool, there was some more reasons... need search in
> history.
> 
> > -- 
> > Best regards,
> >  Jesper Dangaard Brouer
> >  MSc.CS, Principal Kernel Engineer at Red Hat
> >  LinkedIn: http://www.linkedin.com/in/brouer

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Jesper Dangaard Brouer]

On Fri, 31 May 2019 20:03:33 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:

> Probably it's not good example for others how it should be used, not
> a big problem to move it to separate pools.., even don't remember why
> I decided to use shared pool, there was some more reasons... need
> search in history.

Using a shared pool is makes it a lot harder to solve the issue I'm
currently working on.  That is handling/waiting for in-flight frames to
complete, before removing the mem ID from the (r)hashtable lookup.  I
have working code, that basically remove page_pool_destroy() from
public API, and instead lets xdp_rxq_info_unreg() call it when
in-flight count reach zero (and delay fully removing the mem ID).

-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Ivan Khoronzhuk]

On Fri, May 31, 2019 at 10:08:03PM +0000, Saeed Mahameed wrote:
>On Fri, 2019-05-31 at 20:03 +0300, Ivan Khoronzhuk wrote:
>> On Fri, May 31, 2019 at 06:32:41PM +0200, Jesper Dangaard Brouer
>> wrote:
>> > On Fri, 31 May 2019 19:25:24 +0300 Ivan Khoronzhuk <
>> > ivan.khoronzhuk@linaro.org> wrote:
>> >
>> > > On Fri, May 31, 2019 at 05:46:43PM +0200, Jesper Dangaard Brouer
>> > > wrote:
>> > > > From below code snippets, it looks like you only allocated 1
>> > > > page_pool
>> > > > and sharing it with several RX-queues, as I don't have the full
>> > > > context
>> > > > and don't know this driver, I might be wrong?
>> > > >
>> > > > To be clear, a page_pool object is needed per RX-queue, as it
>> > > > is
>> > > > accessing a small RX page cache (which protected by
>> > > > NAPI/softirq).
>> > >
>> > > There is one RX interrupt and one RX NAPI for all rx channels.
>> >
>> > So, what are you saying?
>> >
>> > You _are_ sharing the page_pool between several RX-channels, but it
>> > is
>> > safe because this hardware only have one RX interrupt + NAPI
>> > instance??
>>
>> I can miss smth but in case of cpsw technically it means:
>> 1) RX interrupts are disabled while NAPI is scheduled,
>>    not for particular CPU or channel, but at all, for whole cpsw
>> module.
>> 2) RX channels are handled one by one by priority.
>
>Hi Ivan, I got a silly question..
>
>What is the reason behind having multiple RX rings and one CPU/NAPI
>handling all of them ? priority ? how do you priorities ?
Several.
One of the reason, from what I know, it can handle for several cpus/napi but
because of errata on some SoCs or for all of them it was discarded, but idea was
it can. Second it uses same davinci_cpdma API as tx channels that can be rate
limited, and it's used not only by cpsw but also by other driver, so can't be
modified easily and no reason. And third one, h/w has ability to steer some
filtered traffic to rx queues and can be potentially configured with ethtool
ntuples or so, but it's not implemented....yet.

>
>> 3) After all of them handled and no more in budget - interrupts are
>> enabled.
>> 4) If page is returned to the pool, and it's within NAPI, no races as
>> it's
>>    returned protected by softirq. If it's returned not in softirq
>> it's protected
>>    by producer lock of the ring.
>>
>> Probably it's not good example for others how it should be used, not
>> a big
>> problem to move it to separate pools.., even don't remember why I
>> decided to
>> use shared pool, there was some more reasons... need search in
>> history.
>>
>> > --
>> > Best regards,
>> >  Jesper Dangaard Brouer
>> >  MSc.CS, Principal Kernel Engineer at Red Hat
>> >  LinkedIn: http://www.linkedin.com/in/brouer

-- 
Regards,
Ivan Khoronzhuk

Re: [PATCH v2 net-next 7/7] net: ethernet: ti: cpsw: add XDP support

[Ivan Khoronzhuk]

On Sat, Jun 01, 2019 at 12:37:36AM +0200, Jesper Dangaard Brouer wrote:
>On Fri, 31 May 2019 20:03:33 +0300
>Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> wrote:
>
>> Probably it's not good example for others how it should be used, not
>> a big problem to move it to separate pools.., even don't remember why
>> I decided to use shared pool, there was some more reasons... need
>> search in history.
>
>Using a shared pool is makes it a lot harder to solve the issue I'm
>currently working on.  That is handling/waiting for in-flight frames to
>complete, before removing the mem ID from the (r)hashtable lookup.  I
>have working code, that basically remove page_pool_destroy() from
>public API, and instead lets xdp_rxq_info_unreg() call it when
>in-flight count reach zero (and delay fully removing the mem ID).

Frankly, not see reason why it can block smth, it can be considered
like not shared pool. But Ok, anyway it can look more logical and can be
reused by another SoC. I will add it per channel not a problem,
at least for now no blockers. Adding pool per channel will create more
page_pool_destroy() calls, per each pool, that I can be dropped once
you decided to remove it form the API.

This API is called along with xdp_rxq_info_unreg(), and seems like not
a problem to just remove page_pool_destroy(), except one case that
worries me... cpsw has one interesting feature, share same h/w with 2
network devices like dual mac, basically it's 3 port switch, but used
as 2 separate interfaces. So that, both of them share same queues/channels/rings.
XDP rxq requires network device to be set in rxq info, wich is used in the
code as a pointer and is shared between xdp buffers, so can't be changed in
flight. That's why each network interface has it's own instances of rxq, but
page pools per each network device is common, so when I call
xdp_rxq_info_unreg() per net device it doesn't mean I want to delete
page pool....But seems I can avoid it calling xdp_rxq_info_unreg()
for both when delete page pools...

>
>-- 
>Best regards,
>  Jesper Dangaard Brouer
>  MSc.CS, Principal Kernel Engineer at Red Hat
>  LinkedIn: http://www.linkedin.com/in/brouer

-- 
Regards,
Ivan Khoronzhuk

Re: [PATCH v2 net-next 3/7] net: ethernet: ti: cpsw: use cpsw as drv data

[grygorii]

On 30/05/2019 21:20, Ivan Khoronzhuk wrote:
> No need to set ndev for drvdata when mainly cpsw reference is needed,
> so correct this legacy decision.
> 
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
> ---
>   drivers/net/ethernet/ti/cpsw.c | 16 +++++++---------
>   1 file changed, 7 insertions(+), 9 deletions(-)


Thank you.
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>

-- 
Best regards,
grygorii

Re: [PATCH v2 net-next 4/7] net: ethernet: ti: cpsw_ethtool: simplify slave loops

[grygorii]

On 30/05/2019 21:20, Ivan Khoronzhuk wrote:
> Only for consistency reasons, do it like in main cpsw.c module
> and use ndev reference but not by means of slave.
> 
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
> ---
>   drivers/net/ethernet/ti/cpsw_ethtool.c | 40 ++++++++++++++------------
>   1 file changed, 21 insertions(+), 19 deletions(-)
> 
> diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
> index a4a7ec0d2531..c260bb32aacf 100644
> --- a/drivers/net/ethernet/ti/cpsw_ethtool.c
> +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
> @@ -458,7 +458,6 @@ int cpsw_nway_reset(struct net_device *ndev)
>   static void cpsw_suspend_data_pass(struct net_device *ndev)
>   {

[...]

>   
>   	return 0;
>   }
> @@ -587,7 +590,6 @@ int cpsw_set_channels_common(struct net_device *ndev,
>   {
>   	struct cpsw_priv *priv = netdev_priv(ndev);
>   	struct cpsw_common *cpsw = priv->cpsw;
> -	struct cpsw_slave *slave;
>   	int i, ret;
>   
>   	ret = cpsw_check_ch_settings(cpsw, chs);
> @@ -604,20 +606,20 @@ int cpsw_set_channels_common(struct net_device *ndev,
>   	if (ret)
>   		goto err;
>   
> -	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
> -		if (!(slave->ndev && netif_running(slave->ndev)))
> +	for (i = 0; i < cpsw->data.slaves; i++) {
> +		struct net_device *ndev = cpsw->slaves[i].ndev;

Sry, but could you rename this local var "ndev" and make it differ from func argument name.

> +
> +		if (!(ndev && netif_running(ndev)))
>   			continue;
>   
>   		/* Inform stack about new count of queues */
> -		ret = netif_set_real_num_tx_queues(slave->ndev,
> -						   cpsw->tx_ch_num);
> +		ret = netif_set_real_num_tx_queues(ndev, cpsw->tx_ch_num);
>   		if (ret) {
>   			dev_err(priv->dev, "cannot set real number of tx queues\n");
>   			goto err;
>   		}
>   
> -		ret = netif_set_real_num_rx_queues(slave->ndev,
> -						   cpsw->rx_ch_num);
> +		ret = netif_set_real_num_rx_queues(ndev, cpsw->rx_ch_num);
>   		if (ret) {
>   			dev_err(priv->dev, "cannot set real number of rx queues\n");
>   			goto err;
> 

-- 
Best regards,
grygorii