Skip to contentSkip to conversation

i40e: tweak page counting for XDP_REDIRECT

PATCH Superseded Björn Töpel 3 participants 5 messages Mar 22, 2018

Subsystems (3)

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/2 i40e: tweak page counting for XDP_REDIRECT

From: Bj?rn T?pel <[email protected]>

This commit tweaks the page counting for XDP_REDIRECT to function properly. XDP_REDIRECT support will be added in a future commit.

The current page counting scheme assumes that the reference count cannot decrease until the received frame is sent to the upper layers of the networking stack. This assumption does not hold for the XDP_REDIRECT action, since a page (pointed out by xdp_buff) can have its reference count decreased via the xdp_do_redirect call.

To work around that, we now start off by a large page count and then don't allow a refcount less than two.

---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_txrx.c +4 -5
index e8eef9a56b6b..2f817d1466eb 100644
@@ -1588,9 +1588,8 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = i40e_rx_offset(rx_ring);
-
-	/* initialize pagecnt_bias to 1 representing we fully own page */
-	bi->pagecnt_bias = 1;
+	page_ref_add(page, USHRT_MAX - 1);
+	bi->pagecnt_bias = USHRT_MAX;
 
 	return true;
 }
@@ -1956,8 +1955,8 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 	 * the pagecnt_bias and page count so that we fully restock the
 	 * number of references the driver holds.
 	 */
-	if (unlikely(!pagecnt_bias)) {
-		page_ref_add(page, USHRT_MAX);
+	if (unlikely(pagecnt_bias == 1)) {
+		page_ref_add(page, USHRT_MAX - 1);
 		rx_buffer->pagecnt_bias = USHRT_MAX;
 	}
 
Signature · 1 line
2.7.4
#1 lore raw

PATCH v2 2/2 i40e: add support for XDP_REDIRECT

From: Bj?rn T?pel <[email protected]>

The driver now acts upon the XDP_REDIRECT return action. Two new ndos are implemented, ndo_xdp_xmit and ndo_xdp_flush.

XDP_REDIRECT action enables XDP program to redirect frames to other netdevs.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |  2 +
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 74 +++++++++++++++++++++++++----
 drivers/net/ethernet/intel/i40e/i40e_txrx.h |  2 +
 3 files changed, 68 insertions(+), 10 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_main.c +2 -0
index 79ab52276d12..2fb4261b4fd9 100644
@@ -11815,6 +11815,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_bridge_getlink	= i40e_ndo_bridge_getlink,
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
 	.ndo_bpf		= i40e_xdp,
+	.ndo_xdp_xmit		= i40e_xdp_xmit,
+	.ndo_xdp_flush		= i40e_xdp_flush,
 };
 
 /**
drivers/net/ethernet/intel/i40e/i40e_txrx.c +64 -10

102 lines not on this page · raw message

drivers/net/ethernet/intel/i40e/i40e_txrx.h +2 -0
index 2444f338bb0c..a97e59721393 100644
@@ -510,6 +510,8 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw);
 void i40e_detect_recover_hung(struct i40e_vsi *vsi);
 int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size);
 bool __i40e_chk_linearize(struct sk_buff *skb);
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp);
+void i40e_xdp_flush(struct net_device *dev);
 
 /**
  * i40e_get_head - Retrieve head from head writeback
Signature · 1 line
2.7.4
#2 lore raw

Re: [PATCH v2 2/2] i40e: add support for XDP_REDIRECT

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3679

Quoted 9 lines · On Thu, 22 Mar 2018 10:03:07 +0100 Bj?rn T?pel <[email protected]> wrote:
drivers/net/ethernet/intel/i40e/i40e_txrx.c +9 -0
+/**
+ * i40e_xdp_xmit - Implements ndo_xdp_xmit
+ * @dev: netdev
+ * @xdp: XDP buffer
+ *
+ * Returns Zero if sent, else an error code
+ **/
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{

The return code is used by the XDP redirect tracepoint... this is the only way we have to debug/troubleshoot runtime issues with XDP. Thus, these need to be consistent across drives and distinguishable.

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3686

Quoted 7 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +7 -0
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	unsigned int queue_index = smp_processor_id();
+	struct i40e_vsi *vsi = np->vsi;
+	int err;
+
+	if (test_bit(__I40E_VSI_DOWN, vsi->state))
+		return -EINVAL;

Should be: -ENETDOWN

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3689

Quoted 3 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +3 -0
+
+	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+		return -EINVAL;

Should be: -ENXIO

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3693

Quoted 3 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +3 -0
+	err = i40e_xmit_xdp_ring(xdp, vsi->xdp_rings[queue_index]);
+	if (err != I40E_XDP_TX)
+		return -ENOMEM;

Should be: -ENOSPC

The ENOSPC return code is important, as this can be used as a feedback to a XDP_REDIRECT load-balancer facility.

Signature · 4 lines
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  LinkedIn: http://www.linkedin.com/in/brouer
#3 lore raw

Re: [PATCH v2 2/2] i40e: add support for XDP_REDIRECT

2018-03-22 12:58 GMT+01:00 Jesper Dangaard Brouer <[email protected]>:

Quoted 17 lines · On Thu, 22 Mar 2018 10:03:07 +0100 Bj?rn T?pel <[email protected]> wrote:

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3679

Quoted 10 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +9 -0
+/**
+ * i40e_xdp_xmit - Implements ndo_xdp_xmit
+ * @dev: netdev
+ * @xdp: XDP buffer
+ *
+ * Returns Zero if sent, else an error code
+ **/
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{

The return code is used by the XDP redirect tracepoint... this is the only way we have to debug/troubleshoot runtime issues with XDP. Thus, these need to be consistent across drives and distinguishable.

Thanks for pointing this out! I'll address all your comments and do a respin (but I'll wait for Alex' comments, if any).

Bj?rn

Quoted 30 lines

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3686

Quoted 7 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +7 -0
+     struct i40e_netdev_priv *np = netdev_priv(dev);
+     unsigned int queue_index = smp_processor_id();
+     struct i40e_vsi *vsi = np->vsi;
+     int err;
+
+     if (test_bit(__I40E_VSI_DOWN, vsi->state))
+             return -EINVAL;

Should be: -ENETDOWN

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3689

Quoted 3 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +3 -0
+
+     if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+             return -EINVAL;

Should be: -ENXIO

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3693

Quoted 3 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +3 -0
+     err = i40e_xmit_xdp_ring(xdp, vsi->xdp_rings[queue_index]);
+     if (err != I40E_XDP_TX)
+             return -ENOMEM;

Should be: -ENOSPC

The ENOSPC return code is important, as this can be used as a feedback to a XDP_REDIRECT load-balancer facility.

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

#4 lore raw

Re: [PATCH v2 2/2] i40e: add support for XDP_REDIRECT

Quoted 19 lines · Bj?rn T?pel

2018-03-22 12:58 GMT+01:00 Jesper Dangaard Brouer <[email protected]>:

Quoted 17 lines · On Thu, 22 Mar 2018 10:03:07 +0100 Bj?rn T?pel <[email protected]> wrote:

drivers/net/ethernet/intel/i40e/i40e_txrx.c netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) · line 3679

Quoted 10 lines
drivers/net/ethernet/intel/i40e/i40e_txrx.c +9 -0
+/**
+ * i40e_xdp_xmit - Implements ndo_xdp_xmit
+ * @dev: netdev
+ * @xdp: XDP buffer
+ *
+ * Returns Zero if sent, else an error code
+ **/
+int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{

The return code is used by the XDP redirect tracepoint... this is the only way we have to debug/troubleshoot runtime issues with XDP. Thus, these need to be consistent across drives and distinguishable.

Quoted 6 lines

Thanks for pointing this out! I'll address all your comments and do a respin (but I'll wait for Alex' comments, if any).

Bj?rn

The patch mostly looks okay to me. Maybe a bit of reverse xmas tree formatting needs to be addressed for the variable declarations in your two new functions but that is about it in terms of what I see.

- Alex