[PATCH net-26 0/6] cxgb4vf: a number of bug fixes

[PATCH net-26 0/6] cxgb4vf: a number of bug fixes

[Casey Leedom]

The following patch set includes a number of bug fixes for the cxgb4vf
network driver.  As always, please toss these in the bin if they're not
right.

 drivers/net/cxgb4vf/cxgb4vf_main.c |   42 ++++++++-----
 drivers/net/cxgb4vf/sge.c          |  122 ++++++++++++++++++++++--------------
 drivers/net/cxgb4vf/t4vf_common.h  |    1 +
 drivers/net/cxgb4vf/t4vf_hw.c      |   19 ++++++
 4 files changed, 122 insertions(+), 62 deletions(-)

[PATCH net-26 1/6] cxgb4vf: don't implement trivial (and incorrect) ndo_select_queue()

[Casey Leedom]

Don't implement (struct net_device_ops *)->ndo_select_queue() with simple
call to skb_tx_hash().  This leads to non-persistent TX queue selection in
the Linux dev_pick_tx() routine for TCP connections.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/cxgb4vf_main.c |   14 --------------
 1 files changed, 0 insertions(+), 14 deletions(-)

diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index 6de5e2e..24808ac 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -1103,18 +1103,6 @@ static int cxgb4vf_set_mac_addr(struct net_device *dev, void *_addr)
 	return 0;
 }
 
-/*
- * Return a TX Queue on which to send the specified skb.
- */
-static u16 cxgb4vf_select_queue(struct net_device *dev, struct sk_buff *skb)
-{
-	/*
-	 * XXX For now just use the default hash but we probably want to
-	 * XXX look at other possibilities ...
-	 */
-	return skb_tx_hash(dev, skb);
-}
-
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /*
  * Poll all of our receive queues.  This is called outside of normal interrupt
@@ -2417,7 +2405,6 @@ static const struct net_device_ops cxgb4vf_netdev_ops	= {
 	.ndo_get_stats		= cxgb4vf_get_stats,
 	.ndo_set_rx_mode	= cxgb4vf_set_rxmode,
 	.ndo_set_mac_address	= cxgb4vf_set_mac_addr,
-	.ndo_select_queue	= cxgb4vf_select_queue,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= cxgb4vf_do_ioctl,
 	.ndo_change_mtu		= cxgb4vf_change_mtu,
@@ -2624,7 +2611,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev->do_ioctl = cxgb4vf_do_ioctl;
 		netdev->change_mtu = cxgb4vf_change_mtu;
 		netdev->set_mac_address = cxgb4vf_set_mac_addr;
-		netdev->select_queue = cxgb4vf_select_queue;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 		netdev->poll_controller = cxgb4vf_poll_controller;
 #endif
-- 
1.7.0.4

[PATCH net-26 2/6] cxgb4vf: fix bug in Generic Receive Offload

[Casey Leedom]

Fix botch in Generic Receive Offload (the Packet Gather List Total length
field wasn't being initialized).

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/sge.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index f10864d..6a6e18b 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -1679,6 +1679,7 @@ int process_responses(struct sge_rspq *rspq, int budget)
 				}
 				len = RSPD_LEN(len);
 			}
+			gl.tot_len = len;
 
 			/*
 			 * Gather packet fragments.
-- 
1.7.0.4

[PATCH net-26 3/6] cxgb4vf: fix some errors in Gather List to skb conversion

[Casey Leedom]

There were some errors in the way that internal Gather Lists were being
translated into skb's.  This also makes the VF Driver look more like the PF
Driver to facilitate easier comarison.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/sge.c |  121 +++++++++++++++++++++++++++-----------------
 1 files changed, 74 insertions(+), 47 deletions(-)

diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index 6a6e18b..ecf0770 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -154,13 +154,14 @@ enum {
 	 */
 	RX_COPY_THRES = 256,
 	RX_PULL_LEN = 128,
-};
 
-/*
- * Can't define this in the above enum because PKTSHIFT isn't a constant in
- * the VF Driver ...
- */
-#define RX_PKT_PULL_LEN (RX_PULL_LEN + PKTSHIFT)
+	/*
+	 * Main body length for sk_buffs used for RX Ethernet packets with
+	 * fragments.  Should be >= RX_PULL_LEN but possibly bigger to give
+	 * pskb_may_pull() some room.
+	 */
+	RX_SKB_LEN = 512,
+};
 
 /*
  * Software state per TX descriptor.
@@ -1355,6 +1356,67 @@ out_free:
 }
 
 /**
+ *	t4vf_pktgl_to_skb - build an sk_buff from a packet gather list
+ *	@gl: the gather list
+ *	@skb_len: size of sk_buff main body if it carries fragments
+ *	@pull_len: amount of data to move to the sk_buff's main body
+ *
+ *	Builds an sk_buff from the given packet gather list.  Returns the
+ *	sk_buff or %NULL if sk_buff allocation failed.
+ */
+struct sk_buff *t4vf_pktgl_to_skb(const struct pkt_gl *gl,
+				  unsigned int skb_len, unsigned int pull_len)
+{
+	struct sk_buff *skb;
+	struct skb_shared_info *ssi;
+
+	/*
+	 * If the ingress packet is small enough, allocate an skb large enough
+	 * for all of the data and copy it inline.  Otherwise, allocate an skb
+	 * with enough room to pull in the header and reference the rest of
+	 * the data via the skb fragment list.
+	 *
+	 * Below we rely on RX_COPY_THRES being less than the smallest Rx
+	 * buff!  size, which is expected since buffers are at least
+	 * PAGE_SIZEd.  In this case packets up to RX_COPY_THRES have only one
+	 * fragment.
+	 */
+	if (gl->tot_len <= RX_COPY_THRES) {
+		/* small packets have only one fragment */
+		skb = alloc_skb(gl->tot_len, GFP_ATOMIC);
+		if (unlikely(!skb))
+			goto out;
+		__skb_put(skb, gl->tot_len);
+		skb_copy_to_linear_data(skb, gl->va, gl->tot_len);
+	} else {
+		skb = alloc_skb(skb_len, GFP_ATOMIC);
+		if (unlikely(!skb))
+			goto out;
+		__skb_put(skb, pull_len);
+		skb_copy_to_linear_data(skb, gl->va, pull_len);
+
+		ssi = skb_shinfo(skb);
+		ssi->frags[0].page = gl->frags[0].page;
+		ssi->frags[0].page_offset = gl->frags[0].page_offset + pull_len;
+		ssi->frags[0].size = gl->frags[0].size - pull_len;
+		if (gl->nfrags > 1)
+			memcpy(&ssi->frags[1], &gl->frags[1],
+			       (gl->nfrags-1) * sizeof(skb_frag_t));
+		ssi->nr_frags = gl->nfrags;
+
+		skb->len = gl->tot_len;
+		skb->data_len = skb->len - pull_len;
+		skb->truesize += skb->data_len;
+
+		/* Get a reference for the last page, we don't own it */
+		get_page(gl->frags[gl->nfrags - 1].page);
+	}
+
+out:
+	return skb;
+}
+
+/**
  *	t4vf_pktgl_free - free a packet gather list
  *	@gl: the gather list
  *
@@ -1463,10 +1525,8 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 {
 	struct sk_buff *skb;
 	struct port_info *pi;
-	struct skb_shared_info *ssi;
 	const struct cpl_rx_pkt *pkt = (void *)&rsp[1];
 	bool csum_ok = pkt->csum_calc && !pkt->err_vec;
-	unsigned int len = be16_to_cpu(pkt->len);
 	struct sge_eth_rxq *rxq = container_of(rspq, struct sge_eth_rxq, rspq);
 
 	/*
@@ -1481,42 +1541,14 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 	}
 
 	/*
-	 * If the ingress packet is small enough, allocate an skb large enough
-	 * for all of the data and copy it inline.  Otherwise, allocate an skb
-	 * with enough room to pull in the header and reference the rest of
-	 * the data via the skb fragment list.
+	 * Convert the Packet Gather List into an skb.
 	 */
-	if (len <= RX_COPY_THRES) {
-		/* small packets have only one fragment */
-		skb = alloc_skb(gl->frags[0].size, GFP_ATOMIC);
-		if (!skb)
-			goto nomem;
-		__skb_put(skb, gl->frags[0].size);
-		skb_copy_to_linear_data(skb, gl->va, gl->frags[0].size);
-	} else {
-		skb = alloc_skb(RX_PKT_PULL_LEN, GFP_ATOMIC);
-		if (!skb)
-			goto nomem;
-		__skb_put(skb, RX_PKT_PULL_LEN);
-		skb_copy_to_linear_data(skb, gl->va, RX_PKT_PULL_LEN);
-
-		ssi = skb_shinfo(skb);
-		ssi->frags[0].page = gl->frags[0].page;
-		ssi->frags[0].page_offset = (gl->frags[0].page_offset +
-					     RX_PKT_PULL_LEN);
-		ssi->frags[0].size = gl->frags[0].size - RX_PKT_PULL_LEN;
-		if (gl->nfrags > 1)
-			memcpy(&ssi->frags[1], &gl->frags[1],
-			       (gl->nfrags-1) * sizeof(skb_frag_t));
-		ssi->nr_frags = gl->nfrags;
-		skb->len = len + PKTSHIFT;
-		skb->data_len = skb->len - RX_PKT_PULL_LEN;
-		skb->truesize += skb->data_len;
-
-		/* Get a reference for the last page, we don't own it */
-		get_page(gl->frags[gl->nfrags - 1].page);
+	skb = t4vf_pktgl_to_skb(gl, RX_SKB_LEN, RX_PULL_LEN);
+	if (unlikely(!skb)) {
+		t4vf_pktgl_free(gl);
+		rxq->stats.rx_drops++;
+		return 0;
 	}
-
 	__skb_pull(skb, PKTSHIFT);
 	skb->protocol = eth_type_trans(skb, rspq->netdev);
 	skb_record_rx_queue(skb, rspq->idx);
@@ -1549,11 +1581,6 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 		netif_receive_skb(skb);
 
 	return 0;
-
-nomem:
-	t4vf_pktgl_free(gl);
-	rxq->stats.rx_drops++;
-	return 0;
 }
 
 /**
-- 
1.7.0.4

[PATCH net-26 4/6] cxgb4vf: flesh out PCI Device ID Table ...

[Casey Leedom]

Add a bunch of T4 Device IDs for the VF Driver.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/cxgb4vf_main.c |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index 24808ac..4487b1a 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -2829,6 +2829,14 @@ static struct pci_device_id cxgb4vf_pci_tbl[] = {
 	CH_DEVICE(0x4800, 0),	/* T440-dbg */
 	CH_DEVICE(0x4801, 0),	/* T420-cr */
 	CH_DEVICE(0x4802, 0),	/* T422-cr */
+	CH_DEVICE(0x4803, 0),	/* T440-cr */
+	CH_DEVICE(0x4804, 0),	/* T420-bch */
+	CH_DEVICE(0x4805, 0),   /* T440-bch */
+	CH_DEVICE(0x4806, 0),	/* T460-ch */
+	CH_DEVICE(0x4807, 0),	/* T420-so */
+	CH_DEVICE(0x4808, 0),	/* T420-cx */
+	CH_DEVICE(0x4809, 0),	/* T420-bt */
+	CH_DEVICE(0x480a, 0),   /* T404-bt */
 	{ 0, }
 };
 
-- 
1.7.0.4

[PATCH net-26 5/6] cxgb4vf: Fail open if link_start() fails.

[Casey Leedom]

Fail open if link_start() fails.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/cxgb4vf_main.c |    4 +++-
 1 files changed, 3 insertions(+), 1 deletions(-)

diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index 4487b1a..8da3bda 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -753,7 +753,9 @@ static int cxgb4vf_open(struct net_device *dev)
 	if (err)
 		return err;
 	set_bit(pi->port_id, &adapter->open_device_map);
-	link_start(dev);
+	err = link_start(dev);
+	if (err)
+		return err;
 	netif_tx_start_all_queues(dev);
 	return 0;
 }
-- 
1.7.0.4

[PATCH net-26 6/6] cxgb4vf: add call to Firmware to reset VF State.

[Casey Leedom]

Add call to Firmware to reset its VF State when we first attach to the VF.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
---
 drivers/net/cxgb4vf/cxgb4vf_main.c |   16 ++++++++++++++++
 drivers/net/cxgb4vf/t4vf_common.h  |    1 +
 drivers/net/cxgb4vf/t4vf_hw.c      |   19 +++++++++++++++++++
 3 files changed, 36 insertions(+), 0 deletions(-)

diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index 8da3bda..c3449bb 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -2065,6 +2065,22 @@ static int adap_init0(struct adapter *adapter)
 	}
 
 	/*
+	 * Some environments do not properly handle PCIE FLRs -- e.g. in Linux
+	 * 2.6.31 and later we can't call pci_reset_function() in order to
+	 * issue an FLR because of a self- deadlock on the device semaphore.
+	 * Meanwhile, the OS infrastructure doesn't issue FLRs in all the
+	 * cases where they're needed -- for instance, some versions of KVM
+	 * fail to reset "Assigned Devices" when the VM reboots.  Therefore we
+	 * use the firmware based reset in order to reset any per function
+	 * state.
+	 */
+	err = t4vf_fw_reset(adapter);
+	if (err < 0) {
+		dev_err(adapter->pdev_dev, "FW reset failed: err=%d\n", err);
+		return err;
+	}
+
+	/*
 	 * Grab basic operational parameters.  These will predominantly have
 	 * been set up by the Physical Function Driver or will be hard coded
 	 * into the adapter.  We just have to live with them ...  Note that
diff --git a/drivers/net/cxgb4vf/t4vf_common.h b/drivers/net/cxgb4vf/t4vf_common.h
index 873cb7d..a65c80a 100644
--- a/drivers/net/cxgb4vf/t4vf_common.h
+++ b/drivers/net/cxgb4vf/t4vf_common.h
@@ -235,6 +235,7 @@ static inline int t4vf_wr_mbox_ns(struct adapter *adapter, const void *cmd,
 int __devinit t4vf_wait_dev_ready(struct adapter *);
 int __devinit t4vf_port_init(struct adapter *, int);
 
+int t4vf_fw_reset(struct adapter *);
 int t4vf_query_params(struct adapter *, unsigned int, const u32 *, u32 *);
 int t4vf_set_params(struct adapter *, unsigned int, const u32 *, const u32 *);
 
diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c
index ea1c123..e306c20 100644
--- a/drivers/net/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/cxgb4vf/t4vf_hw.c
@@ -326,6 +326,25 @@ int __devinit t4vf_port_init(struct adapter *adapter, int pidx)
 }
 
 /**
+ *      t4vf_fw_reset - issue a reset to FW
+ *      @adapter: the adapter
+ *
+ *	Issues a reset command to FW.  For a Physical Function this would
+ *	result in the Firmware reseting all of its state.  For a Virtual
+ *	Function this just resets the state associated with the VF.
+ */
+int t4vf_fw_reset(struct adapter *adapter)
+{
+	struct fw_reset_cmd cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.op_to_write = cpu_to_be32(FW_CMD_OP(FW_RESET_CMD) |
+				      FW_CMD_WRITE);
+	cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
+	return t4vf_wr_mbox(adapter, &cmd, sizeof(cmd), NULL);
+}
+
+/**
  *	t4vf_query_params - query FW or device parameters
  *	@adapter: the adapter
  *	@nparams: the number of parameters
-- 
1.7.0.4

Re: [PATCH net-26 0/6] cxgb4vf: a number of bug fixes

[David Miller]

From: Casey Leedom <leedom@chelsio.com>
Date: Thu, 11 Nov 2010 11:06:47 -0800

> The following patch set includes a number of bug fixes for the cxgb4vf
> network driver.  As always, please toss these in the bin if they're not
> right.

All 6 patches applied to net-2.6, thanks.