[PATCH 12/12] cxgb4: NUMA-aware Tx queue allocations

[PATCH 12/12] cxgb4: NUMA-aware Tx queue allocations

[Dimitris Michailidis]

Allocate Tx queue memory on the node indicated by the new
netdev_queue_numa_node_read.  If that fails we allocate on any node.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/sge.c |   20 +++++++++++++-------
 1 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
index cc0b997..ed98b8a 100644
--- a/drivers/net/cxgb4/sge.c
+++ b/drivers/net/cxgb4/sge.c
@@ -579,6 +579,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  *	@phys: the physical address of the allocated ring
  *	@metadata: address of the array holding the SW state for the ring
  *	@stat_size: extra space in HW ring for status information
+ *	@node: preferred node for memory allocations
  *
  *	Allocates resources for an SGE descriptor ring, such as Tx queues,
  *	free buffer lists, or response queues.  Each SGE ring requires
@@ -590,7 +591,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  */
 static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 			size_t sw_size, dma_addr_t *phys, void *metadata,
-			size_t stat_size)
+			size_t stat_size, int node)
 {
 	size_t len = nelem * elem_size + stat_size;
 	void *s = NULL;
@@ -599,7 +600,10 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 	if (!p)
 		return NULL;
 	if (sw_size) {
-		s = kcalloc(nelem, sw_size, GFP_KERNEL);
+		if (node >= 0)
+			s = kzalloc_node(nelem * sw_size, GFP_KERNEL, node);
+		if (!s)
+			s = kcalloc(nelem, sw_size, GFP_KERNEL);
 
 		if (!s) {
 			dma_free_coherent(dev, len, p, *phys);
@@ -1982,7 +1986,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->size = roundup(iq->size, 16);
 
 	iq->desc = alloc_ring(adap->pdev_dev, iq->size, iq->iqe_len, 0,
-			      &iq->phys_addr, NULL, 0);
+			      &iq->phys_addr, NULL, 0, NUMA_NO_NODE);
 	if (!iq->desc)
 		return -ENOMEM;
 
@@ -2008,7 +2012,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
-				      &fl->sdesc, STAT_LEN);
+				      &fl->sdesc, STAT_LEN, NUMA_NO_NODE);
 		if (!fl->desc)
 			goto fl_nomem;
 
@@ -2095,7 +2099,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			netdev_queue_numa_node_read(netdevq));
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2147,7 +2152,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, nentries,
 				 sizeof(struct tx_desc), 0, &txq->q.phys_addr,
-				 NULL, 0);
+				 NULL, 0, NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2198,7 +2203,8 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
-- 
1.5.4

Re: [PATCH 12/12] cxgb4: NUMA-aware Tx queue allocations

[Eric Dumazet]

Le mardi 14 décembre 2010 à 12:18 -0800, Dimitris Michailidis a écrit :
> Allocate Tx queue memory on the node indicated by the new
> netdev_queue_numa_node_read.  If that fails we allocate on any node.
> 
> Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
> ---
>  drivers/net/cxgb4/sge.c |   20 +++++++++++++-------
>  1 files changed, 13 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
> index cc0b997..ed98b8a 100644
> --- a/drivers/net/cxgb4/sge.c
> +++ b/drivers/net/cxgb4/sge.c
> @@ -579,6 +579,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
>   *	@phys: the physical address of the allocated ring
>   *	@metadata: address of the array holding the SW state for the ring
>   *	@stat_size: extra space in HW ring for status information
> + *	@node: preferred node for memory allocations
>   *
>   *	Allocates resources for an SGE descriptor ring, such as Tx queues,
>   *	free buffer lists, or response queues.  Each SGE ring requires
> @@ -590,7 +591,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
>   */
>  static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
>  			size_t sw_size, dma_addr_t *phys, void *metadata,
> -			size_t stat_size)
> +			size_t stat_size, int node)
>  {
>  	size_t len = nelem * elem_size + stat_size;
>  	void *s = NULL;
> @@ -599,7 +600,10 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
>  	if (!p)
>  		return NULL;
>  	if (sw_size) {
> -		s = kcalloc(nelem, sw_size, GFP_KERNEL);
> +		if (node >= 0)
> +			s = kzalloc_node(nelem * sw_size, GFP_KERNEL, node);

kzalloc_node() has a fallback, you dont need to retry with kcalloc()

> +		if (!s)
> +			s = kcalloc(nelem, sw_size, GFP_KERNEL);
>  
>  		if (!s) {
>  			dma_free_coherent(dev, len, p, *phys);

Also, I am not sure it is going to work, since we can setup XPS only
after device being setup ?

By the time your driver allocates rings, we probably read
-1/NUMA_NO_NODE

Re: [PATCH 12/12] cxgb4: NUMA-aware Tx queue allocations

[Dimitris Michailidis]

Eric Dumazet wrote:
> Le mardi 14 décembre 2010 à 12:18 -0800, Dimitris Michailidis a écrit :
>> Allocate Tx queue memory on the node indicated by the new
>> netdev_queue_numa_node_read.  If that fails we allocate on any node.
>>
>> Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
>> ---
>>  drivers/net/cxgb4/sge.c |   20 +++++++++++++-------
>>  1 files changed, 13 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
>> index cc0b997..ed98b8a 100644
>> --- a/drivers/net/cxgb4/sge.c
>> +++ b/drivers/net/cxgb4/sge.c
>> @@ -579,6 +579,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
>>   *	@phys: the physical address of the allocated ring
>>   *	@metadata: address of the array holding the SW state for the ring
>>   *	@stat_size: extra space in HW ring for status information
>> + *	@node: preferred node for memory allocations
>>   *
>>   *	Allocates resources for an SGE descriptor ring, such as Tx queues,
>>   *	free buffer lists, or response queues.  Each SGE ring requires
>> @@ -590,7 +591,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
>>   */
>>  static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
>>  			size_t sw_size, dma_addr_t *phys, void *metadata,
>> -			size_t stat_size)
>> +			size_t stat_size, int node)
>>  {
>>  	size_t len = nelem * elem_size + stat_size;
>>  	void *s = NULL;
>> @@ -599,7 +600,10 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
>>  	if (!p)
>>  		return NULL;
>>  	if (sw_size) {
>> -		s = kcalloc(nelem, sw_size, GFP_KERNEL);
>> +		if (node >= 0)
>> +			s = kzalloc_node(nelem * sw_size, GFP_KERNEL, node);
> 
> kzalloc_node() has a fallback, you dont need to retry with kcalloc()

I took this retry part from ixgbe but I can remove it if it's not needed. 
Luckily it's the last patch in the series.

> 
>> +		if (!s)
>> +			s = kcalloc(nelem, sw_size, GFP_KERNEL);
>>  
>>  		if (!s) {
>>  			dma_free_coherent(dev, len, p, *phys);
> 
> Also, I am not sure it is going to work, since we can setup XPS only
> after device being setup ?
> 
> By the time your driver allocates rings, we probably read
> -1/NUMA_NO_NODE

XPS is available after registration.  The queues are allocated at open time, 
if one configures XPS prior to that the allocations happen on the right 
nodes.  I've tried this and this is the behavior I see.  It is true that 
setting XPS after open doesn't affect the queue allocations.

[PATCH 00/12 net-next] cxgb4 update v2

[Dimitris Michailidis]

This is v2 of the cxgb4 series.  I've removed the fallback call to kcalloc in
patch 12 per Eric's comment and restored an accidentally removed increment in
patch 7.

 drivers/net/cxgb4/cxgb4.h      |    4 +-
 drivers/net/cxgb4/cxgb4_main.c |  134 +++++++++++++++++++---------------------
 drivers/net/cxgb4/sge.c        |   22 +++++--
 drivers/net/cxgb4/t4_hw.c      |   93 ++++++++++++++--------------
 drivers/net/cxgb4/t4fw_api.h   |    1 +
 5 files changed, 127 insertions(+), 127 deletions(-)

[PATCH 01/12] cxgb4: enable PCIe relaxed ordering

[Dimitris Michailidis]

Enable relaxed ordering for descriptor reads and packet I/O.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4_main.c |   14 ++++++++++++++
 drivers/net/cxgb4/sge.c        |    5 +++++
 2 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 848f89d..953d62a 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -3535,6 +3535,19 @@ static void __devinit print_port_info(struct adapter *adap)
 	}
 }
 
+static void __devinit enable_pcie_relaxed_ordering(struct pci_dev *dev)
+{
+	u16 v;
+	int pos;
+
+	pos = pci_pcie_cap(dev);
+	if (pos > 0) {
+		pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &v);
+		v |= PCI_EXP_DEVCTL_RELAX_EN;
+		pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, v);
+	}
+}
+
 /*
  * Free the following resources:
  * - memory used for tables
@@ -3609,6 +3622,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 	}
 
 	pci_enable_pcie_error_reporting(pdev);
+	enable_pcie_relaxed_ordering(pdev);
 	pci_set_master(pdev);
 	pci_save_state(pdev);
 
diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
index 1702225..cc0b997 100644
--- a/drivers/net/cxgb4/sge.c
+++ b/drivers/net/cxgb4/sge.c
@@ -2014,6 +2014,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 
 		flsz = fl->size / 8 + STAT_LEN / sizeof(struct tx_desc);
 		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_FL0PACKEN |
+					    FW_IQ_CMD_FL0FETCHRO(1) |
+					    FW_IQ_CMD_FL0DATARO(1) |
 					    FW_IQ_CMD_FL0PADEN);
 		c.fl0dcaen_to_fl0cidxfthresh = htons(FW_IQ_CMD_FL0FBMIN(2) |
 				FW_IQ_CMD_FL0FBMAX(3));
@@ -2106,6 +2108,7 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	c.viid_pkd = htonl(FW_EQ_ETH_CMD_VIID(pi->viid));
 	c.fetchszm_to_iqid = htonl(FW_EQ_ETH_CMD_HOSTFCMODE(2) |
 				   FW_EQ_ETH_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_ETH_CMD_FETCHRO(1) |
 				   FW_EQ_ETH_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_ETH_CMD_FBMIN(2) |
 				  FW_EQ_ETH_CMD_FBMAX(3) |
@@ -2158,6 +2161,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 	c.physeqid_pkd = htonl(0);
 	c.fetchszm_to_iqid = htonl(FW_EQ_CTRL_CMD_HOSTFCMODE(2) |
 				   FW_EQ_CTRL_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_CTRL_CMD_FETCHRO |
 				   FW_EQ_CTRL_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_CTRL_CMD_FBMIN(2) |
 				  FW_EQ_CTRL_CMD_FBMAX(3) |
@@ -2207,6 +2211,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 				 FW_EQ_OFLD_CMD_EQSTART | FW_LEN16(c));
 	c.fetchszm_to_iqid = htonl(FW_EQ_OFLD_CMD_HOSTFCMODE(2) |
 				   FW_EQ_OFLD_CMD_PCIECHN(pi->tx_chan) |
+				   FW_EQ_OFLD_CMD_FETCHRO(1) |
 				   FW_EQ_OFLD_CMD_IQID(iqid));
 	c.dcaen_to_eqsize = htonl(FW_EQ_OFLD_CMD_FBMIN(2) |
 				  FW_EQ_OFLD_CMD_FBMAX(3) |
-- 
1.5.4

[PATCH 02/12] cxgb4: do not read the clock frequency from VPD

[Dimitris Michailidis]

No need to read the clock frequency from VPD, we already get it a bit
later from FW, after any potential adjustments.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/t4_hw.c |    4 +---
 1 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/drivers/net/cxgb4/t4_hw.c b/drivers/net/cxgb4/t4_hw.c
index e97521c..6af0452 100644
--- a/drivers/net/cxgb4/t4_hw.c
+++ b/drivers/net/cxgb4/t4_hw.c
@@ -370,7 +370,7 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable)
 static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 {
 	int i, ret;
-	int ec, sn, v2;
+	int ec, sn;
 	u8 vpd[VPD_LEN], csum;
 	unsigned int vpdr_len;
 	const struct t4_vpd_hdr *v;
@@ -408,10 +408,8 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 
 	FIND_VPD_KW(ec, "EC");
 	FIND_VPD_KW(sn, "SN");
-	FIND_VPD_KW(v2, "V2");
 #undef FIND_VPD_KW
 
-	p->cclk = simple_strtoul(vpd + v2, NULL, 10);
 	memcpy(p->id, v->id_data, ID_LEN);
 	strim(p->id);
 	memcpy(p->ec, vpd + ec, EC_LEN);
-- 
1.5.4

[PATCH 03/12] cxgb4: set the number of queues before device registration

[Dimitris Michailidis]

The number of queues is known early, move the calls to
netif_set_real_num_[rt]x_queues before register_netdev.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4_main.c |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 953d62a..3012a8a 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -2717,10 +2717,6 @@ static int cxgb_open(struct net_device *dev)
 			return err;
 	}
 
-	netif_set_real_num_tx_queues(dev, pi->nqsets);
-	err = netif_set_real_num_rx_queues(dev, pi->nqsets);
-	if (err)
-		return err;
 	err = link_start(dev);
 	if (!err)
 		netif_tx_start_all_queues(dev);
@@ -3733,6 +3729,10 @@ static int __devinit init_one(struct pci_dev *pdev,
 	 * register at least one net device.
 	 */
 	for_each_port(adapter, i) {
+		pi = adap2pinfo(adapter, i);
+		netif_set_real_num_tx_queues(adapter->port[i], pi->nqsets);
+		netif_set_real_num_rx_queues(adapter->port[i], pi->nqsets);
+
 		err = register_netdev(adapter->port[i]);
 		if (err)
 			dev_warn(&pdev->dev,
@@ -3747,7 +3747,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 				adapter->name = adapter->port[i]->name;
 
 			__set_bit(i, &adapter->registered_device_map);
-			adapter->chan_map[adap2pinfo(adapter, i)->tx_chan] = i;
+			adapter->chan_map[pi->tx_chan] = i;
 		}
 	}
 	if (!adapter->registered_device_map) {
-- 
1.5.4

[PATCH 04/12] cxgb4: distinguish between 1-lane KR/KX and 4-lane KR/KX/KX4 ports

[Dimitris Michailidis]

And fix the supported flags ethtool reports for the two cases.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4_main.c |    9 +++++++--
 drivers/net/cxgb4/t4fw_api.h   |    1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 3012a8a..3f33d51 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -1375,7 +1375,12 @@ static unsigned int from_fw_linkcaps(unsigned int type, unsigned int caps)
 	} else if (type == FW_PORT_TYPE_KR)
 		v |= SUPPORTED_Backplane | SUPPORTED_10000baseKR_Full;
 	else if (type == FW_PORT_TYPE_BP_AP)
-		v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC;
+		v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC |
+		     SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full;
+	else if (type == FW_PORT_TYPE_BP4_AP)
+		v |= SUPPORTED_Backplane | SUPPORTED_10000baseR_FEC |
+		     SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full |
+		     SUPPORTED_10000baseKX4_Full;
 	else if (type == FW_PORT_TYPE_FIBER_XFI ||
 		 type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP)
 		v |= SUPPORTED_FIBRE;
@@ -3489,7 +3494,7 @@ static void __devinit print_port_info(struct adapter *adap)
 {
 	static const char *base[] = {
 		"R XFI", "R XAUI", "T SGMII", "T XFI", "T XAUI", "KX4", "CX4",
-		"KX", "KR", "KR SFP+", "KR FEC"
+		"KX", "KR", "R SFP+", "KR/KX", "KR/KX/KX4"
 	};
 
 	int i;
diff --git a/drivers/net/cxgb4/t4fw_api.h b/drivers/net/cxgb4/t4fw_api.h
index 940584a..edcfd7e 100644
--- a/drivers/net/cxgb4/t4fw_api.h
+++ b/drivers/net/cxgb4/t4fw_api.h
@@ -1239,6 +1239,7 @@ enum fw_port_type {
 	FW_PORT_TYPE_KR,
 	FW_PORT_TYPE_SFP,
 	FW_PORT_TYPE_BP_AP,
+	FW_PORT_TYPE_BP4_AP,
 
 	FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_MASK
 };
-- 
1.5.4

[PATCH 05/12] cxgb4: print port information after registering each netdev

[Dimitris Michailidis]

Print information about each port when its netdev is registered instead
of looping separately over the ports at the end.  The bulk of this patch
is due to indentation change.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4_main.c |   54 ++++++++++++++++-----------------------
 1 files changed, 22 insertions(+), 32 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 3f33d51..089b753 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -3490,50 +3490,41 @@ static int __devinit init_rss(struct adapter *adap)
 	return 0;
 }
 
-static void __devinit print_port_info(struct adapter *adap)
+static void __devinit print_port_info(const struct net_device *dev)
 {
 	static const char *base[] = {
 		"R XFI", "R XAUI", "T SGMII", "T XFI", "T XAUI", "KX4", "CX4",
 		"KX", "KR", "R SFP+", "KR/KX", "KR/KX/KX4"
 	};
 
-	int i;
 	char buf[80];
+	char *bufp = buf;
 	const char *spd = "";
+	const struct port_info *pi = netdev_priv(dev);
+	const struct adapter *adap = pi->adapter;
 
 	if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_2_5GB)
 		spd = " 2.5 GT/s";
 	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_5_0GB)
 		spd = " 5 GT/s";
 
-	for_each_port(adap, i) {
-		struct net_device *dev = adap->port[i];
-		const struct port_info *pi = netdev_priv(dev);
-		char *bufp = buf;
-
-		if (!test_bit(i, &adap->registered_device_map))
-			continue;
-
-		if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100M)
-			bufp += sprintf(bufp, "100/");
-		if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_1G)
-			bufp += sprintf(bufp, "1000/");
-		if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G)
-			bufp += sprintf(bufp, "10G/");
-		if (bufp != buf)
-			--bufp;
-		sprintf(bufp, "BASE-%s", base[pi->port_type]);
-
-		netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n",
-			    adap->params.vpd.id, adap->params.rev,
-			    buf, is_offload(adap) ? "R" : "",
-			    adap->params.pci.width, spd,
-			    (adap->flags & USING_MSIX) ? " MSI-X" :
-			    (adap->flags & USING_MSI) ? " MSI" : "");
-		if (adap->name == dev->name)
-			netdev_info(dev, "S/N: %s, E/C: %s\n",
-				    adap->params.vpd.sn, adap->params.vpd.ec);
-	}
+	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100M)
+		bufp += sprintf(bufp, "100/");
+	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_1G)
+		bufp += sprintf(bufp, "1000/");
+	if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G)
+		bufp += sprintf(bufp, "10G/");
+	if (bufp != buf)
+		--bufp;
+	sprintf(bufp, "BASE-%s", base[pi->port_type]);
+
+	netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n",
+		    adap->params.vpd.id, adap->params.rev, buf,
+		    is_offload(adap) ? "R" : "", adap->params.pci.width, spd,
+		    (adap->flags & USING_MSIX) ? " MSI-X" :
+		    (adap->flags & USING_MSI) ? " MSI" : "");
+	netdev_info(dev, "S/N: %s, E/C: %s\n",
+		    adap->params.vpd.sn, adap->params.vpd.ec);
 }
 
 static void __devinit enable_pcie_relaxed_ordering(struct pci_dev *dev)
@@ -3753,6 +3744,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 
 			__set_bit(i, &adapter->registered_device_map);
 			adapter->chan_map[pi->tx_chan] = i;
+			print_port_info(adapter->port[i]);
 		}
 	}
 	if (!adapter->registered_device_map) {
@@ -3769,8 +3761,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 	if (is_offload(adapter))
 		attach_ulds(adapter);
 
-	print_port_info(adapter);
-
 sriov:
 #ifdef CONFIG_PCI_IOV
 	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0)
-- 
1.5.4

[PATCH 06/12] cxgb4: allocate more space for MSI-X interrupt names

[Dimitris Michailidis]

Currently MSI-X names for netdevs with long names are truncated in
/proc/interrupts due to insufficient space.  Use IFNAMSIZ to size the
needed space.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4.h |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4.h b/drivers/net/cxgb4/cxgb4.h
index 3d4253d..f3d9f64 100644
--- a/drivers/net/cxgb4/cxgb4.h
+++ b/drivers/net/cxgb4/cxgb4.h
@@ -497,7 +497,7 @@ struct adapter {
 
 	struct {
 		unsigned short vec;
-		char desc[14];
+		char desc[IFNAMSIZ + 10];
 	} msix_info[MAX_INGQ + 1];
 
 	struct sge sge;
-- 
1.5.4

[PATCH 07/12] cxgb4: correct formatting of MSI-X interrupt names

[Dimitris Michailidis]

The last byte of the buffer for MSI-X names could not be used due to a
bogus -1.  Also do not explicitly clear the last byte, snprintf will do
the right thing.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4_main.c |   21 +++++++--------------
 1 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 089b753..7e26fe5 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -522,39 +522,32 @@ static irqreturn_t t4_nondata_intr(int irq, void *cookie)
  */
 static void name_msix_vecs(struct adapter *adap)
 {
-	int i, j, msi_idx = 2, n = sizeof(adap->msix_info[0].desc) - 1;
+	int i, j, msi_idx = 2, n = sizeof(adap->msix_info[0].desc);
 
 	/* non-data interrupts */
 	snprintf(adap->msix_info[0].desc, n, "%s", adap->name);
-	adap->msix_info[0].desc[n] = 0;
 
 	/* FW events */
 	snprintf(adap->msix_info[1].desc, n, "%s-FWeventq", adap->name);
-	adap->msix_info[1].desc[n] = 0;
 
 	/* Ethernet queues */
 	for_each_port(adap, j) {
 		struct net_device *d = adap->port[j];
 		const struct port_info *pi = netdev_priv(d);
 
-		for (i = 0; i < pi->nqsets; i++, msi_idx++) {
+		for (i = 0; i < pi->nqsets; i++, msi_idx++)
 			snprintf(adap->msix_info[msi_idx].desc, n, "%s-Rx%d",
 				 d->name, i);
-			adap->msix_info[msi_idx].desc[n] = 0;
-		}
 	}
 
 	/* offload queues */
-	for_each_ofldrxq(&adap->sge, i) {
-		snprintf(adap->msix_info[msi_idx].desc, n, "%s-ofld%d",
+	for_each_ofldrxq(&adap->sge, i)
+		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-ofld%d",
 			 adap->name, i);
-		adap->msix_info[msi_idx++].desc[n] = 0;
-	}
-	for_each_rdmarxq(&adap->sge, i) {
-		snprintf(adap->msix_info[msi_idx].desc, n, "%s-rdma%d",
+
+	for_each_rdmarxq(&adap->sge, i)
+		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma%d",
 			 adap->name, i);
-		adap->msix_info[msi_idx++].desc[n] = 0;
-	}
 }
 
 static int request_msix_queue_irqs(struct adapter *adap)
-- 
1.5.4

[PATCH 08/12] cxgb4: remove the name field from the adapter structure

[Dimitris Michailidis]

Remove a field the driver uses to keep track of the name of the first
netdev it manages to register.  Do this by changing the registration
loop to stop the first time it fails so the first registered device is
trivial to tell.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4.h      |    1 -
 drivers/net/cxgb4/cxgb4_main.c |   37 +++++++++++++++----------------------
 2 files changed, 15 insertions(+), 23 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4.h b/drivers/net/cxgb4/cxgb4.h
index f3d9f64..9caf95f 100644
--- a/drivers/net/cxgb4/cxgb4.h
+++ b/drivers/net/cxgb4/cxgb4.h
@@ -486,7 +486,6 @@ struct adapter {
 	unsigned int fn;
 	unsigned int flags;
 
-	const char *name;
 	int msg_enable;
 
 	struct adapter_params params;
diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 7e26fe5..4d7565c 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -525,10 +525,11 @@ static void name_msix_vecs(struct adapter *adap)
 	int i, j, msi_idx = 2, n = sizeof(adap->msix_info[0].desc);
 
 	/* non-data interrupts */
-	snprintf(adap->msix_info[0].desc, n, "%s", adap->name);
+	snprintf(adap->msix_info[0].desc, n, "%s", adap->port[0]->name);
 
 	/* FW events */
-	snprintf(adap->msix_info[1].desc, n, "%s-FWeventq", adap->name);
+	snprintf(adap->msix_info[1].desc, n, "%s-FWeventq",
+		 adap->port[0]->name);
 
 	/* Ethernet queues */
 	for_each_port(adap, j) {
@@ -543,11 +544,11 @@ static void name_msix_vecs(struct adapter *adap)
 	/* offload queues */
 	for_each_ofldrxq(&adap->sge, i)
 		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-ofld%d",
-			 adap->name, i);
+			 adap->port[0]->name, i);
 
 	for_each_rdmarxq(&adap->sge, i)
 		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma%d",
-			 adap->name, i);
+			 adap->port[0]->name, i);
 }
 
 static int request_msix_queue_irqs(struct adapter *adap)
@@ -2664,7 +2665,7 @@ static int cxgb_up(struct adapter *adap)
 	} else {
 		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
 				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
-				  adap->name, adap);
+				  adap->port[0]->name, adap);
 		if (err)
 			goto irq_err;
 	}
@@ -3627,7 +3628,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 	adapter->pdev = pdev;
 	adapter->pdev_dev = &pdev->dev;
 	adapter->fn = func;
-	adapter->name = pci_name(pdev);
 	adapter->msg_enable = dflt_msg_enable;
 	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
 
@@ -3724,26 +3724,19 @@ static int __devinit init_one(struct pci_dev *pdev,
 
 		err = register_netdev(adapter->port[i]);
 		if (err)
-			dev_warn(&pdev->dev,
-				 "cannot register net device %s, skipping\n",
-				 adapter->port[i]->name);
-		else {
-			/*
-			 * Change the name we use for messages to the name of
-			 * the first successfully registered interface.
-			 */
-			if (!adapter->registered_device_map)
-				adapter->name = adapter->port[i]->name;
-
-			__set_bit(i, &adapter->registered_device_map);
-			adapter->chan_map[pi->tx_chan] = i;
-			print_port_info(adapter->port[i]);
-		}
+			break;
+		__set_bit(i, &adapter->registered_device_map);
+		adapter->chan_map[pi->tx_chan] = i;
+		print_port_info(adapter->port[i]);
 	}
-	if (!adapter->registered_device_map) {
+	if (i == 0) {
 		dev_err(&pdev->dev, "could not register any net devices\n");
 		goto out_free_dev;
 	}
+	if (err) {
+		dev_warn(&pdev->dev, "only %d net devices registered\n", i);
+		err = 0;
+	};
 
 	if (cxgb4_debugfs_root) {
 		adapter->debugfs_root = debugfs_create_dir(pci_name(pdev),
-- 
1.5.4

[PATCH 09/12] cxgb4: remove a bitmap

[Dimitris Michailidis]

The driver keeps a bitmap of the netdevs it registered so it knows what to
unregister later.  Remove that and look at reg_state instead.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/cxgb4.h      |    1 -
 drivers/net/cxgb4/cxgb4_main.c |    3 +--
 2 files changed, 1 insertions(+), 3 deletions(-)

diff --git a/drivers/net/cxgb4/cxgb4.h b/drivers/net/cxgb4/cxgb4.h
index 9caf95f..01d49ea 100644
--- a/drivers/net/cxgb4/cxgb4.h
+++ b/drivers/net/cxgb4/cxgb4.h
@@ -482,7 +482,6 @@ struct adapter {
 	void __iomem *regs;
 	struct pci_dev *pdev;
 	struct device *pdev_dev;
-	unsigned long registered_device_map;
 	unsigned int fn;
 	unsigned int flags;
 
diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index 4d7565c..059c1ee 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -3725,7 +3725,6 @@ static int __devinit init_one(struct pci_dev *pdev,
 		err = register_netdev(adapter->port[i]);
 		if (err)
 			break;
-		__set_bit(i, &adapter->registered_device_map);
 		adapter->chan_map[pi->tx_chan] = i;
 		print_port_info(adapter->port[i]);
 	}
@@ -3785,7 +3784,7 @@ static void __devexit remove_one(struct pci_dev *pdev)
 			detach_ulds(adapter);
 
 		for_each_port(adapter, i)
-			if (test_bit(i, &adapter->registered_device_map))
+			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				unregister_netdev(adapter->port[i]);
 
 		if (adapter->debugfs_root)
-- 
1.5.4

[PATCH 10/12] cxgb4: add const to static arrays

[Dimitris Michailidis]

Patch originally from Joe Perches, unmodified.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/t4_hw.c |   48 ++++++++++++++++++++++----------------------
 1 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/net/cxgb4/t4_hw.c b/drivers/net/cxgb4/t4_hw.c
index 6af0452..c7fb549 100644
--- a/drivers/net/cxgb4/t4_hw.c
+++ b/drivers/net/cxgb4/t4_hw.c
@@ -183,7 +183,7 @@ static void dump_mbox(struct adapter *adap, int mbox, u32 data_reg)
 int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
 		    void *rpl, bool sleep_ok)
 {
-	static int delay[] = {
+	static const int delay[] = {
 		1, 1, 3, 5, 10, 10, 20, 50, 100, 200
 	};
 
@@ -917,7 +917,7 @@ static int t4_handle_intr_status(struct adapter *adapter, unsigned int reg,
  */
 static void pcie_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info sysbus_intr_info[] = {
+	static const struct intr_info sysbus_intr_info[] = {
 		{ RNPP, "RXNP array parity error", -1, 1 },
 		{ RPCP, "RXPC array parity error", -1, 1 },
 		{ RCIP, "RXCIF array parity error", -1, 1 },
@@ -925,7 +925,7 @@ static void pcie_intr_handler(struct adapter *adapter)
 		{ RFTP, "RXFT array parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info pcie_port_intr_info[] = {
+	static const struct intr_info pcie_port_intr_info[] = {
 		{ TPCP, "TXPC array parity error", -1, 1 },
 		{ TNPP, "TXNP array parity error", -1, 1 },
 		{ TFTP, "TXFT array parity error", -1, 1 },
@@ -937,7 +937,7 @@ static void pcie_intr_handler(struct adapter *adapter)
 		{ TDUE, "Tx uncorrectable data error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info pcie_intr_info[] = {
+	static const struct intr_info pcie_intr_info[] = {
 		{ MSIADDRLPERR, "MSI AddrL parity error", -1, 1 },
 		{ MSIADDRHPERR, "MSI AddrH parity error", -1, 1 },
 		{ MSIDATAPERR, "MSI data parity error", -1, 1 },
@@ -989,7 +989,7 @@ static void pcie_intr_handler(struct adapter *adapter)
  */
 static void tp_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info tp_intr_info[] = {
+	static const struct intr_info tp_intr_info[] = {
 		{ 0x3fffffff, "TP parity error", -1, 1 },
 		{ FLMTXFLSTEMPTY, "TP out of Tx pages", -1, 1 },
 		{ 0 }
@@ -1006,7 +1006,7 @@ static void sge_intr_handler(struct adapter *adapter)
 {
 	u64 v;
 
-	static struct intr_info sge_intr_info[] = {
+	static const struct intr_info sge_intr_info[] = {
 		{ ERR_CPL_EXCEED_IQE_SIZE,
 		  "SGE received CPL exceeding IQE size", -1, 1 },
 		{ ERR_INVALID_CIDX_INC,
@@ -1051,7 +1051,7 @@ static void sge_intr_handler(struct adapter *adapter)
  */
 static void cim_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info cim_intr_info[] = {
+	static const struct intr_info cim_intr_info[] = {
 		{ PREFDROPINT, "CIM control register prefetch drop", -1, 1 },
 		{ OBQPARERR, "CIM OBQ parity error", -1, 1 },
 		{ IBQPARERR, "CIM IBQ parity error", -1, 1 },
@@ -1061,7 +1061,7 @@ static void cim_intr_handler(struct adapter *adapter)
 		{ TIEQOUTPARERRINT, "CIM TIEQ incoming parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info cim_upintr_info[] = {
+	static const struct intr_info cim_upintr_info[] = {
 		{ RSVDSPACEINT, "CIM reserved space access", -1, 1 },
 		{ ILLTRANSINT, "CIM illegal transaction", -1, 1 },
 		{ ILLWRINT, "CIM illegal write", -1, 1 },
@@ -1108,7 +1108,7 @@ static void cim_intr_handler(struct adapter *adapter)
  */
 static void ulprx_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info ulprx_intr_info[] = {
+	static const struct intr_info ulprx_intr_info[] = {
 		{ 0x1800000, "ULPRX context error", -1, 1 },
 		{ 0x7fffff, "ULPRX parity error", -1, 1 },
 		{ 0 }
@@ -1123,7 +1123,7 @@ static void ulprx_intr_handler(struct adapter *adapter)
  */
 static void ulptx_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info ulptx_intr_info[] = {
+	static const struct intr_info ulptx_intr_info[] = {
 		{ PBL_BOUND_ERR_CH3, "ULPTX channel 3 PBL out of bounds", -1,
 		  0 },
 		{ PBL_BOUND_ERR_CH2, "ULPTX channel 2 PBL out of bounds", -1,
@@ -1145,7 +1145,7 @@ static void ulptx_intr_handler(struct adapter *adapter)
  */
 static void pmtx_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info pmtx_intr_info[] = {
+	static const struct intr_info pmtx_intr_info[] = {
 		{ PCMD_LEN_OVFL0, "PMTX channel 0 pcmd too large", -1, 1 },
 		{ PCMD_LEN_OVFL1, "PMTX channel 1 pcmd too large", -1, 1 },
 		{ PCMD_LEN_OVFL2, "PMTX channel 2 pcmd too large", -1, 1 },
@@ -1167,7 +1167,7 @@ static void pmtx_intr_handler(struct adapter *adapter)
  */
 static void pmrx_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info pmrx_intr_info[] = {
+	static const struct intr_info pmrx_intr_info[] = {
 		{ ZERO_E_CMD_ERROR, "PMRX 0-length pcmd", -1, 1 },
 		{ PMRX_FRAMING_ERROR, "PMRX framing error", -1, 1 },
 		{ OCSPI_PAR_ERROR, "PMRX ocspi parity error", -1, 1 },
@@ -1186,7 +1186,7 @@ static void pmrx_intr_handler(struct adapter *adapter)
  */
 static void cplsw_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info cplsw_intr_info[] = {
+	static const struct intr_info cplsw_intr_info[] = {
 		{ CIM_OP_MAP_PERR, "CPLSW CIM op_map parity error", -1, 1 },
 		{ CIM_OVFL_ERROR, "CPLSW CIM overflow", -1, 1 },
 		{ TP_FRAMING_ERROR, "CPLSW TP framing error", -1, 1 },
@@ -1205,7 +1205,7 @@ static void cplsw_intr_handler(struct adapter *adapter)
  */
 static void le_intr_handler(struct adapter *adap)
 {
-	static struct intr_info le_intr_info[] = {
+	static const struct intr_info le_intr_info[] = {
 		{ LIPMISS, "LE LIP miss", -1, 0 },
 		{ LIP0, "LE 0 LIP error", -1, 0 },
 		{ PARITYERR, "LE parity error", -1, 1 },
@@ -1223,11 +1223,11 @@ static void le_intr_handler(struct adapter *adap)
  */
 static void mps_intr_handler(struct adapter *adapter)
 {
-	static struct intr_info mps_rx_intr_info[] = {
+	static const struct intr_info mps_rx_intr_info[] = {
 		{ 0xffffff, "MPS Rx parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_tx_intr_info[] = {
+	static const struct intr_info mps_tx_intr_info[] = {
 		{ TPFIFO, "MPS Tx TP FIFO parity error", -1, 1 },
 		{ NCSIFIFO, "MPS Tx NC-SI FIFO parity error", -1, 1 },
 		{ TXDATAFIFO, "MPS Tx data FIFO parity error", -1, 1 },
@@ -1237,25 +1237,25 @@ static void mps_intr_handler(struct adapter *adapter)
 		{ FRMERR, "MPS Tx framing error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_trc_intr_info[] = {
+	static const struct intr_info mps_trc_intr_info[] = {
 		{ FILTMEM, "MPS TRC filter parity error", -1, 1 },
 		{ PKTFIFO, "MPS TRC packet FIFO parity error", -1, 1 },
 		{ MISCPERR, "MPS TRC misc parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_stat_sram_intr_info[] = {
+	static const struct intr_info mps_stat_sram_intr_info[] = {
 		{ 0x1fffff, "MPS statistics SRAM parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_stat_tx_intr_info[] = {
+	static const struct intr_info mps_stat_tx_intr_info[] = {
 		{ 0xfffff, "MPS statistics Tx FIFO parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_stat_rx_intr_info[] = {
+	static const struct intr_info mps_stat_rx_intr_info[] = {
 		{ 0xffffff, "MPS statistics Rx FIFO parity error", -1, 1 },
 		{ 0 }
 	};
-	static struct intr_info mps_cls_intr_info[] = {
+	static const struct intr_info mps_cls_intr_info[] = {
 		{ MATCHSRAM, "MPS match SRAM parity error", -1, 1 },
 		{ MATCHTCAM, "MPS match TCAM parity error", -1, 1 },
 		{ HASHSRAM, "MPS hash SRAM parity error", -1, 1 },
@@ -1354,7 +1354,7 @@ static void ma_intr_handler(struct adapter *adap)
  */
 static void smb_intr_handler(struct adapter *adap)
 {
-	static struct intr_info smb_intr_info[] = {
+	static const struct intr_info smb_intr_info[] = {
 		{ MSTTXFIFOPARINT, "SMB master Tx FIFO parity error", -1, 1 },
 		{ MSTRXFIFOPARINT, "SMB master Rx FIFO parity error", -1, 1 },
 		{ SLVFIFOPARINT, "SMB slave FIFO parity error", -1, 1 },
@@ -1370,7 +1370,7 @@ static void smb_intr_handler(struct adapter *adap)
  */
 static void ncsi_intr_handler(struct adapter *adap)
 {
-	static struct intr_info ncsi_intr_info[] = {
+	static const struct intr_info ncsi_intr_info[] = {
 		{ CIM_DM_PRTY_ERR, "NC-SI CIM parity error", -1, 1 },
 		{ MPS_DM_PRTY_ERR, "NC-SI MPS parity error", -1, 1 },
 		{ TXFIFO_PRTY_ERR, "NC-SI Tx FIFO parity error", -1, 1 },
@@ -1408,7 +1408,7 @@ static void xgmac_intr_handler(struct adapter *adap, int port)
  */
 static void pl_intr_handler(struct adapter *adap)
 {
-	static struct intr_info pl_intr_info[] = {
+	static const struct intr_info pl_intr_info[] = {
 		{ FATALPERR, "T4 fatal parity error", -1, 1 },
 		{ PERRVFID, "PL VFID_MAP parity error", -1, 1 },
 		{ 0 }
-- 
1.5.4

[PATCH 11/12] cxgb4: extend VPD parsing

[Dimitris Michailidis]

Current code parses the VPD RO section for keywords but makes static
assumptions about the location of the section.  Remove them and parse
the VPD to find it.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/t4_hw.c |   41 +++++++++++++++++++++--------------------
 1 files changed, 21 insertions(+), 20 deletions(-)

diff --git a/drivers/net/cxgb4/t4_hw.c b/drivers/net/cxgb4/t4_hw.c
index c7fb549..b9fd8a6 100644
--- a/drivers/net/cxgb4/t4_hw.c
+++ b/drivers/net/cxgb4/t4_hw.c
@@ -330,18 +330,6 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
 	return 0;
 }
 
-/*
- * Partial EEPROM Vital Product Data structure.  Includes only the ID and
- * VPD-R header.
- */
-struct t4_vpd_hdr {
-	u8  id_tag;
-	u8  id_len[2];
-	u8  id_data[ID_LEN];
-	u8  vpdr_tag;
-	u8  vpdr_len[2];
-};
-
 #define EEPROM_STAT_ADDR   0x7bfc
 #define VPD_BASE           0
 #define VPD_LEN            512
@@ -372,23 +360,36 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	int i, ret;
 	int ec, sn;
 	u8 vpd[VPD_LEN], csum;
-	unsigned int vpdr_len;
-	const struct t4_vpd_hdr *v;
+	unsigned int vpdr_len, kw_offset, id_len;
 
 	ret = pci_read_vpd(adapter->pdev, VPD_BASE, sizeof(vpd), vpd);
 	if (ret < 0)
 		return ret;
 
-	v = (const struct t4_vpd_hdr *)vpd;
-	vpdr_len = pci_vpd_lrdt_size(&v->vpdr_tag);
-	if (vpdr_len + sizeof(struct t4_vpd_hdr) > VPD_LEN) {
+	if (vpd[0] != PCI_VPD_LRDT_ID_STRING) {
+		dev_err(adapter->pdev_dev, "missing VPD ID string\n");
+		return -EINVAL;
+	}
+
+	id_len = pci_vpd_lrdt_size(vpd);
+	if (id_len > ID_LEN)
+		id_len = ID_LEN;
+
+	i = pci_vpd_find_tag(vpd, 0, VPD_LEN, PCI_VPD_LRDT_RO_DATA);
+	if (i < 0) {
+		dev_err(adapter->pdev_dev, "missing VPD-R section\n");
+		return -EINVAL;
+	}
+
+	vpdr_len = pci_vpd_lrdt_size(&vpd[i]);
+	kw_offset = i + PCI_VPD_LRDT_TAG_SIZE;
+	if (vpdr_len + kw_offset > VPD_LEN) {
 		dev_err(adapter->pdev_dev, "bad VPD-R length %u\n", vpdr_len);
 		return -EINVAL;
 	}
 
 #define FIND_VPD_KW(var, name) do { \
-	var = pci_vpd_find_info_keyword(&v->id_tag, sizeof(struct t4_vpd_hdr), \
-					vpdr_len, name); \
+	var = pci_vpd_find_info_keyword(vpd, kw_offset, vpdr_len, name); \
 	if (var < 0) { \
 		dev_err(adapter->pdev_dev, "missing VPD keyword " name "\n"); \
 		return -EINVAL; \
@@ -410,7 +411,7 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	FIND_VPD_KW(sn, "SN");
 #undef FIND_VPD_KW
 
-	memcpy(p->id, v->id_data, ID_LEN);
+	memcpy(p->id, vpd + PCI_VPD_LRDT_TAG_SIZE, id_len);
 	strim(p->id);
 	memcpy(p->ec, vpd + ec, EC_LEN);
 	strim(p->ec);
-- 
1.5.4

[PATCH 12/12] cxgb4: NUMA-aware Tx queue allocations

[Dimitris Michailidis]

Allocate Tx queue memory on the node indicated by the new
netdev_queue_numa_node_read.

Signed-off-by: Dimitris Michailidis <dm@chelsio.com>
---
 drivers/net/cxgb4/sge.c |   17 ++++++++++-------
 1 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
index cc0b997..311471b 100644
--- a/drivers/net/cxgb4/sge.c
+++ b/drivers/net/cxgb4/sge.c
@@ -579,6 +579,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  *	@phys: the physical address of the allocated ring
  *	@metadata: address of the array holding the SW state for the ring
  *	@stat_size: extra space in HW ring for status information
+ *	@node: preferred node for memory allocations
  *
  *	Allocates resources for an SGE descriptor ring, such as Tx queues,
  *	free buffer lists, or response queues.  Each SGE ring requires
@@ -590,7 +591,7 @@ static inline void __refill_fl(struct adapter *adap, struct sge_fl *fl)
  */
 static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 			size_t sw_size, dma_addr_t *phys, void *metadata,
-			size_t stat_size)
+			size_t stat_size, int node)
 {
 	size_t len = nelem * elem_size + stat_size;
 	void *s = NULL;
@@ -599,7 +600,7 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 	if (!p)
 		return NULL;
 	if (sw_size) {
-		s = kcalloc(nelem, sw_size, GFP_KERNEL);
+		s = kzalloc_node(nelem * sw_size, GFP_KERNEL, node);
 
 		if (!s) {
 			dma_free_coherent(dev, len, p, *phys);
@@ -1982,7 +1983,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->size = roundup(iq->size, 16);
 
 	iq->desc = alloc_ring(adap->pdev_dev, iq->size, iq->iqe_len, 0,
-			      &iq->phys_addr, NULL, 0);
+			      &iq->phys_addr, NULL, 0, NUMA_NO_NODE);
 	if (!iq->desc)
 		return -ENOMEM;
 
@@ -2008,7 +2009,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
-				      &fl->sdesc, STAT_LEN);
+				      &fl->sdesc, STAT_LEN, NUMA_NO_NODE);
 		if (!fl->desc)
 			goto fl_nomem;
 
@@ -2095,7 +2096,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			netdev_queue_numa_node_read(netdevq));
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2147,7 +2149,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, nentries,
 				 sizeof(struct tx_desc), 0, &txq->q.phys_addr,
-				 NULL, 0);
+				 NULL, 0, NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
@@ -2198,7 +2200,8 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, txq->q.size,
 			sizeof(struct tx_desc), sizeof(struct tx_sw_desc),
-			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN);
+			&txq->q.phys_addr, &txq->q.sdesc, STAT_LEN,
+			NUMA_NO_NODE);
 	if (!txq->q.desc)
 		return -ENOMEM;
 
-- 
1.5.4

Re: [PATCH 00/12 net-next] cxgb4 update v2

[David Miller]

From: Dimitris Michailidis <dm@chelsio.com>
Date: Tue, 14 Dec 2010 23:36:43 -0800

> 
> This is v2 of the cxgb4 series.  I've removed the fallback call to kcalloc in
> patch 12 per Eric's comment and restored an accidentally removed increment in
> patch 7.

All applied.

I made one change, I made sure that for Joe Perches's patch he will be
set as the author in the tree.

Next time you have a patch written by someone else, start the commit
message with:

From: NAME <EMAIL>

and GIT will take care of the rest.

Thanks.