/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
#include "ixgbe.h"
#include "ixgbe_common.h"
#include "ixgbe_dcb_82599.h"
+#include "ixgbe_sriov.h"
char ixgbe_driver_name[] = "ixgbe";
static const char ixgbe_driver_string[] =
#define DRV_VERSION "2.0.44-k2"
const char ixgbe_driver_version[] = DRV_VERSION;
-static char ixgbe_copyright[] = "Copyright (c) 1999-2009 Intel Corporation.";
+static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation.";
static const struct ixgbe_info *ixgbe_info_tbl[] = {
[board_82598] = &ixgbe_82598_info,
* { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
* Class, Class Mask, private data (not used) }
*/
-static struct pci_device_id ixgbe_pci_tbl[] = {
+static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM),
board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR),
+ board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM),
};
#endif
+#ifdef CONFIG_PCI_IOV
+static unsigned int max_vfs;
+module_param(max_vfs, uint, 0);
+MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate "
+ "per physical function");
+#endif /* CONFIG_PCI_IOV */
+
MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver");
MODULE_LICENSE("GPL");
#define DEFAULT_DEBUG_LEVEL_SHIFT 3
+static inline void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 gcr;
+ u32 gpie;
+ u32 vmdctl;
+
+#ifdef CONFIG_PCI_IOV
+ /* disable iov and allow time for transactions to clear */
+ pci_disable_sriov(adapter->pdev);
+#endif
+
+ /* turn off device IOV mode */
+ gcr = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
+ gcr &= ~(IXGBE_GCR_EXT_SRIOV);
+ IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr);
+ gpie = IXGBE_READ_REG(hw, IXGBE_GPIE);
+ gpie &= ~IXGBE_GPIE_VTMODE_MASK;
+ IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
+
+ /* set default pool back to 0 */
+ vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
+ vmdctl &= ~IXGBE_VT_CTL_POOL_MASK;
+ IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
+
+ /* take a breather then clean up driver data */
+ msleep(100);
+ if (adapter->vfinfo)
+ kfree(adapter->vfinfo);
+ adapter->vfinfo = NULL;
+
+ adapter->num_vfs = 0;
+ adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+}
+
static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
{
u32 ctrl_ext;
struct ixgbe_tx_buffer
*tx_buffer_info)
{
- tx_buffer_info->dma = 0;
+ if (tx_buffer_info->dma) {
+ if (tx_buffer_info->mapped_as_page)
+ pci_unmap_page(adapter->pdev,
+ tx_buffer_info->dma,
+ tx_buffer_info->length,
+ PCI_DMA_TODEVICE);
+ else
+ pci_unmap_single(adapter->pdev,
+ tx_buffer_info->dma,
+ tx_buffer_info->length,
+ PCI_DMA_TODEVICE);
+ tx_buffer_info->dma = 0;
+ }
if (tx_buffer_info->skb) {
- skb_dma_unmap(&adapter->pdev->dev, tx_buffer_info->skb,
- DMA_TO_DEVICE);
dev_kfree_skb_any(tx_buffer_info->skb);
tx_buffer_info->skb = NULL;
}
static inline bool ixgbe_tx_is_paused(struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
{
- int tc;
u32 txoff = IXGBE_TFCS_TXOFF;
#ifdef CONFIG_IXGBE_DCB
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
+ int tc;
int reg_idx = tx_ring->reg_idx;
int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
tc = reg_idx >> 2;
txoff = IXGBE_TFCS_TXOFF0;
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ break;
+ case ixgbe_mac_82599EB:
tc = 0;
txoff = IXGBE_TFCS_TXOFF;
if (dcb_i == 8) {
tc += (reg_idx - 96) >> 4;
}
}
+ break;
+ default:
+ tc = 0;
}
txoff <<= tc;
}
if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
!test_bit(__IXGBE_DOWN, &adapter->state)) {
netif_wake_subqueue(netdev, tx_ring->queue_index);
- ++adapter->restart_queue;
+ ++tx_ring->restart_queue;
}
}
tx_ring->total_packets += total_packets;
tx_ring->stats.packets += total_packets;
tx_ring->stats.bytes += total_bytes;
- netdev->stats.tx_bytes += total_bytes;
- netdev->stats.tx_packets += total_packets;
return (count < tx_ring->work_limit);
}
/* It must be a TCP or UDP packet with a valid checksum */
skb->ip_summed = CHECKSUM_UNNECESSARY;
- adapter->hw_csum_rx_good++;
}
static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
if (!bi->skb) {
struct sk_buff *skb;
- skb = netdev_alloc_skb_ip_align(adapter->netdev,
- rx_ring->rx_buf_len);
+ /* netdev_alloc_skb reserves 32 bytes up front!! */
+ uint bufsz = rx_ring->rx_buf_len + SMP_CACHE_BYTES;
+ skb = netdev_alloc_skb(adapter->netdev, bufsz);
if (!skb) {
adapter->alloc_rx_buff_failed++;
goto no_buffers;
}
+ /* advance the data pointer to the next cache line */
+ skb_reserve(skb, (PTR_ALIGN(skb->data, SMP_CACHE_BYTES)
+ - skb->data));
+
bi->skb = skb;
bi->dma = pci_map_single(pdev, skb->data,
rx_ring->rx_buf_len,
hdr_info = le16_to_cpu(ixgbe_get_hdr_info(rx_desc));
len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
IXGBE_RXDADV_HDRBUFLEN_SHIFT;
- if (hdr_info & IXGBE_RXDADV_SPH)
- adapter->rx_hdr_split++;
if (len > IXGBE_RX_HDR_SIZE)
len = IXGBE_RX_HDR_SIZE;
upper_len = le16_to_cpu(rx_desc->wb.upper.length);
cleaned = true;
skb = rx_buffer_info->skb;
- prefetch(skb->data - NET_IP_ALIGN);
+ prefetch(skb->data);
rx_buffer_info->skb = NULL;
if (rx_buffer_info->dma) {
skb->next = next_buffer->skb;
skb->next->prev = skb;
}
- adapter->non_eop_descs++;
+ rx_ring->non_eop_descs++;
goto next_desc;
}
/* set up to autoclear timer, and the vectors */
mask = IXGBE_EIMS_ENABLE_MASK;
- mask &= ~(IXGBE_EIMS_OTHER | IXGBE_EIMS_LSC);
+ if (adapter->num_vfs)
+ mask &= ~(IXGBE_EIMS_OTHER |
+ IXGBE_EIMS_MAILBOX |
+ IXGBE_EIMS_LSC);
+ else
+ mask &= ~(IXGBE_EIMS_OTHER | IXGBE_EIMS_LSC);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
}
if (eicr & IXGBE_EICR_LSC)
ixgbe_check_lsc(adapter);
+ if (eicr & IXGBE_EICR_MAILBOX)
+ ixgbe_msg_task(adapter);
+
if (hw->mac.type == ixgbe_mac_82598EB)
ixgbe_check_fan_failure(adapter, eicr);
r_idx + 1);
}
- /* disable interrupts on this vector only */
- ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx));
+ /* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
return IRQ_HANDLED;
/* disable interrupts on this vector only */
- ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx));
+ /* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
r_idx + 1);
}
- /* disable interrupts on this vector only */
- ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx));
+ /* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
mask |= IXGBE_EIMS_ECC;
mask |= IXGBE_EIMS_GPI_SDP1;
mask |= IXGBE_EIMS_GPI_SDP2;
+ if (adapter->num_vfs)
+ mask |= IXGBE_EIMS_MAILBOX;
}
if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE ||
adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
ixgbe_irq_enable_queues(adapter, ~0);
IXGBE_WRITE_FLUSH(&adapter->hw);
+
+ if (adapter->num_vfs > 32) {
+ u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1;
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel);
+ }
}
/**
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
+ if (adapter->num_vfs > 32)
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0);
}
IXGBE_WRITE_FLUSH(&adapter->hw);
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
if (hw->mac.type == ixgbe_mac_82599EB) {
u32 rttdcs;
+ u32 mask;
/* disable the arbiter while setting MTQC */
rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS);
rttdcs |= IXGBE_RTTDCS_ARBDIS;
IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
- /* We enable 8 traffic classes, DCB only */
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
- IXGBE_WRITE_REG(hw, IXGBE_MTQC, (IXGBE_MTQC_RT_ENA |
- IXGBE_MTQC_8TC_8TQ));
- else
+ /* set transmit pool layout */
+ mask = (IXGBE_FLAG_SRIOV_ENABLED | IXGBE_FLAG_DCB_ENABLED);
+ switch (adapter->flags & mask) {
+
+ case (IXGBE_FLAG_SRIOV_ENABLED):
+ IXGBE_WRITE_REG(hw, IXGBE_MTQC,
+ (IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF));
+ break;
+
+ case (IXGBE_FLAG_DCB_ENABLED):
+ /* We enable 8 traffic classes, DCB only */
+ IXGBE_WRITE_REG(hw, IXGBE_MTQC,
+ (IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ));
+ break;
+
+ default:
IXGBE_WRITE_REG(hw, IXGBE_MTQC, IXGBE_MTQC_64Q_1PB);
+ break;
+ }
/* re-eable the arbiter */
rttdcs &= ~IXGBE_RTTDCS_ARBDIS;
#ifdef CONFIG_IXGBE_DCB
| IXGBE_FLAG_DCB_ENABLED
#endif
+ | IXGBE_FLAG_SRIOV_ENABLED
);
switch (mask) {
case (IXGBE_FLAG_RSS_ENABLED):
mrqc = IXGBE_MRQC_RSSEN;
break;
+ case (IXGBE_FLAG_SRIOV_ENABLED):
+ mrqc = IXGBE_MRQC_VMDQEN;
+ break;
#ifdef CONFIG_IXGBE_DCB
case (IXGBE_FLAG_DCB_ENABLED):
mrqc = IXGBE_MRQC_RT8TCEN;
* ixgbe_configure_rscctl - enable RSC for the indicated ring
* @adapter: address of board private structure
* @index: index of ring to set
- * @rx_buf_len: rx buffer length
**/
-static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, int index,
- int rx_buf_len)
+static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, int index)
{
struct ixgbe_ring *rx_ring;
struct ixgbe_hw *hw = &adapter->hw;
int j;
u32 rscctrl;
+ int rx_buf_len;
rx_ring = &adapter->rx_ring[index];
j = rx_ring->reg_idx;
+ rx_buf_len = rx_ring->rx_buf_len;
rscctrl = IXGBE_READ_REG(hw, IXGBE_RSCCTL(j));
rscctrl |= IXGBE_RSCCTL_RSCEN;
/*
int rx_buf_len;
/* Decide whether to use packet split mode or not */
- adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+ /* Do not use packet split if we're in SR-IOV Mode */
+ if (!adapter->num_vfs)
+ adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
/* Set the RX buffer length according to the mode */
if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
IXGBE_PSRTYPE_IPV4HDR |
IXGBE_PSRTYPE_IPV6HDR |
IXGBE_PSRTYPE_L2HDR;
- IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(0), psrtype);
+ IXGBE_WRITE_REG(hw,
+ IXGBE_PSRTYPE(adapter->num_vfs),
+ psrtype);
}
} else {
if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
}
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+ u32 vt_reg_bits;
+ u32 reg_offset, vf_shift;
+ u32 vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
+ vt_reg_bits = IXGBE_VMD_CTL_VMDQ_EN
+ | IXGBE_VT_CTL_REPLEN;
+ vt_reg_bits |= (adapter->num_vfs <<
+ IXGBE_VT_CTL_POOL_SHIFT);
+ IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl | vt_reg_bits);
+ IXGBE_WRITE_REG(hw, IXGBE_MRQC, 0);
+
+ vf_shift = adapter->num_vfs % 32;
+ reg_offset = adapter->num_vfs / 32;
+ IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0);
+ IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
+ IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0);
+ IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0);
+ /* Enable only the PF's pool for Tx/Rx */
+ IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (1 << vf_shift));
+ IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (1 << vf_shift));
+ IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
+ ixgbe_set_vmolr(hw, adapter->num_vfs);
+ }
+
/* Program MRQC for the distribution of queues */
mrqc = ixgbe_setup_mrqc(adapter);
}
IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc);
+ if (adapter->num_vfs) {
+ u32 reg;
+
+ /* Map PF MAC address in RAR Entry 0 to first pool
+ * following VFs */
+ hw->mac.ops.set_vmdq(hw, 0, adapter->num_vfs);
+
+ /* Set up VF register offsets for selected VT Mode, i.e.
+ * 64 VFs for SR-IOV */
+ reg = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
+ reg |= IXGBE_GCR_EXT_SRIOV;
+ IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, reg);
+ }
+
rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM);
if (adapter->flags & IXGBE_FLAG_RSS_ENABLED ||
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
/* Enable 82599 HW-RSC */
for (i = 0; i < adapter->num_rx_queues; i++)
- ixgbe_configure_rscctl(adapter, i, rx_buf_len);
+ ixgbe_configure_rscctl(adapter, i);
/* Disable RSC for ACK packets */
IXGBE_WRITE_REG(hw, IXGBE_RSCDBU,
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
+ int pool_ndx = adapter->num_vfs;
/* add VID to filter table */
- hw->mac.ops.set_vfta(&adapter->hw, vid, 0, true);
+ hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true);
}
static void ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
+ int pool_ndx = adapter->num_vfs;
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_disable(adapter);
ixgbe_irq_enable(adapter);
/* remove VID from filter table */
- hw->mac.ops.set_vfta(&adapter->hw, vid, 0, false);
+ hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false);
}
static void ixgbe_vlan_rx_register(struct net_device *netdev,
* not in DCB mode.
*/
ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_VLNCTRL);
+
+ /* Disable CFI check */
+ ctrl &= ~IXGBE_VLNCTRL_CFIEN;
+
+ /* enable VLAN tag stripping */
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- ctrl |= IXGBE_VLNCTRL_VME | IXGBE_VLNCTRL_VFE;
- ctrl &= ~IXGBE_VLNCTRL_CFIEN;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
+ ctrl |= IXGBE_VLNCTRL_VME;
} else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- ctrl |= IXGBE_VLNCTRL_VFE;
- /* enable VLAN tag insert/strip */
- ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_VLNCTRL);
- ctrl &= ~IXGBE_VLNCTRL_CFIEN;
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
for (i = 0; i < adapter->num_rx_queues; i++) {
+ u32 ctrl;
j = adapter->rx_ring[i].reg_idx;
ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_RXDCTL(j));
ctrl |= IXGBE_RXDCTL_VME;
IXGBE_WRITE_REG(&adapter->hw, IXGBE_RXDCTL(j), ctrl);
}
}
+
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
+
ixgbe_vlan_rx_add_vid(netdev, 0);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
* responsible for configuring the hardware for proper unicast, multicast and
* promiscuous mode.
**/
-static void ixgbe_set_rx_mode(struct net_device *netdev)
+void ixgbe_set_rx_mode(struct net_device *netdev)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
/* reprogram secondary unicast list */
- hw->mac.ops.update_uc_addr_list(hw, &netdev->uc.list);
+ hw->mac.ops.update_uc_addr_list(hw, netdev);
/* reprogram multicast list */
addr_count = netdev->mc_count;
addr_list = netdev->mc_list->dmi_addr;
hw->mac.ops.update_mc_addr_list(hw, addr_list, addr_count,
ixgbe_addr_list_itr);
+ if (adapter->num_vfs)
+ ixgbe_restore_vf_multicasts(adapter);
}
static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter)
u32 txdctl, rxdctl, mhadd;
u32 dmatxctl;
u32 gpie;
+ u32 ctrl_ext;
ixgbe_get_hw_control(adapter);
/* MSI only */
gpie = 0;
}
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+ gpie &= ~IXGBE_GPIE_VTMODE_MASK;
+ gpie |= IXGBE_GPIE_VTMODE_64;
+ }
/* XXX: to interrupt immediately for EICS writes, enable this */
/* gpie |= IXGBE_GPIE_EIMEN; */
IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
}
- if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
+ if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
+ /*
+ * use EIAM to auto-mask when MSI-X interrupt is asserted
+ * this saves a register write for every interrupt
+ */
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
+ break;
+ default:
+ case ixgbe_mac_82599EB:
+ IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
+ IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
+ break;
+ }
+ } else {
/* legacy interrupts, use EIAM to auto-mask when reading EICR,
* specifically only auto mask tx and rx interrupts */
IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
txdctl |= IXGBE_TXDCTL_ENABLE;
IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(j), txdctl);
+ if (hw->mac.type == ixgbe_mac_82599EB) {
+ int wait_loop = 10;
+ /* poll for Tx Enable ready */
+ do {
+ msleep(1);
+ txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
+ } while (--wait_loop &&
+ !(txdctl & IXGBE_TXDCTL_ENABLE));
+ if (!wait_loop)
+ DPRINTK(DRV, ERR, "Could not enable "
+ "Tx Queue %d\n", j);
+ }
}
for (i = 0; i < num_rx_rings; i++) {
adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
adapter->link_check_timeout = jiffies;
mod_timer(&adapter->watchdog_timer, jiffies);
+
+ /* Set PF Reset Done bit so PF/VF Mail Ops can work */
+ ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT);
+ ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD;
+ IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
+
return 0;
}
}
/* reprogram the RAR[0] in case user changed it. */
- hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV);
+ hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs,
+ IXGBE_RAH_AV);
}
/**
/* signal that we are down to the interrupt handler */
set_bit(__IXGBE_DOWN, &adapter->state);
+ /* disable receive for all VFs and wait one second */
+ if (adapter->num_vfs) {
+ for (i = 0 ; i < adapter->num_vfs; i++)
+ adapter->vfinfo[i].clear_to_send = 0;
+
+ /* ping all the active vfs to let them know we are going down */
+ ixgbe_ping_all_vfs(adapter);
+ /* Disable all VFTE/VFRE TX/RX */
+ ixgbe_disable_tx_rx(adapter);
+ }
+
/* disable receives */
rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN);
}
#endif /* IXGBE_FCOE */
+/**
+ * ixgbe_set_sriov_queues: Allocate queues for IOV use
+ * @adapter: board private structure to initialize
+ *
+ * IOV doesn't actually use anything, so just NAK the
+ * request for now and let the other queue routines
+ * figure out what to do.
+ */
+static inline bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
+{
+ return false;
+}
+
/*
* ixgbe_set_num_queues: Allocate queues for device, feature dependant
* @adapter: board private structure to initialize
**/
static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
{
+ /* Start with base case */
+ adapter->num_rx_queues = 1;
+ adapter->num_tx_queues = 1;
+ adapter->num_rx_pools = adapter->num_rx_queues;
+ adapter->num_rx_queues_per_pool = 1;
+
+ if (ixgbe_set_sriov_queues(adapter))
+ return;
+
#ifdef IXGBE_FCOE
if (ixgbe_set_fcoe_queues(adapter))
goto done;
#endif /* IXGBE_FCOE */
/**
+ * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov
+ * @adapter: board private structure to initialize
+ *
+ * SR-IOV doesn't use any descriptor rings but changes the default if
+ * no other mapping is used.
+ *
+ */
+static inline bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
+{
+ adapter->rx_ring[0].reg_idx = adapter->num_vfs * 2;
+ adapter->tx_ring[0].reg_idx = adapter->num_vfs * 2;
+ if (adapter->num_vfs)
+ return true;
+ else
+ return false;
+}
+
+/**
* ixgbe_cache_ring_register - Descriptor ring to register mapping
* @adapter: board private structure to initialize
*
adapter->rx_ring[0].reg_idx = 0;
adapter->tx_ring[0].reg_idx = 0;
+ if (ixgbe_cache_ring_sriov(adapter))
+ return;
+
#ifdef IXGBE_FCOE
if (ixgbe_cache_ring_fcoe(adapter))
return;
adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
adapter->atr_sample_rate = 0;
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+ ixgbe_disable_sriov(adapter);
+
ixgbe_set_num_queues(adapter);
err = pci_enable_msi(adapter->pdev);
adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
adapter->ring_feature[RING_F_FCOE].indices = 0;
+#ifdef CONFIG_IXGBE_DCB
/* Default traffic class to use for FCoE */
adapter->fcoe.tc = IXGBE_FCOE_DEFTC;
+#endif
#endif /* IXGBE_FCOE */
}
pci_set_power_state(pdev, PCI_D0);
pci_restore_state(pdev);
+ /*
+ * pci_restore_state clears dev->state_saved so call
+ * pci_save_state to restore it.
+ */
+ pci_save_state(pdev);
err = pci_enable_device_mem(pdev);
if (err) {
struct ixgbe_hw *hw = &adapter->hw;
u64 total_mpc = 0;
u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
+ u64 non_eop_descs = 0, restart_queue = 0;
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
u64 rsc_count = 0;
adapter->rsc_total_flush = rsc_flush;
}
+ /* gather some stats to the adapter struct that are per queue */
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ restart_queue += adapter->tx_ring[i].restart_queue;
+ adapter->restart_queue = restart_queue;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ non_eop_descs += adapter->rx_ring[i].non_eop_descs;
+ adapter->non_eop_descs = non_eop_descs;
+
adapter->stats.crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);
for (i = 0; i < 8; i++) {
/* for packet buffers not used, the register should read 0 */
iph->daddr, 0,
IPPROTO_TCP,
0);
- adapter->hw_tso_ctxt++;
- } else if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV6) {
+ } else if (skb_is_gso_v6(skb)) {
ipv6_hdr(skb)->payload_len = 0;
tcp_hdr(skb)->check =
~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr,
0, IPPROTO_TCP, 0);
- adapter->hw_tso6_ctxt++;
}
i = tx_ring->next_to_use;
IXGBE_ADVTXD_DTYP_CTXT);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
- switch (skb->protocol) {
+ __be16 protocol;
+
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ const struct vlan_ethhdr *vhdr =
+ (const struct vlan_ethhdr *)skb->data;
+
+ protocol = vhdr->h_vlan_encapsulated_proto;
+ } else {
+ protocol = skb->protocol;
+ }
+
+ switch (protocol) {
case cpu_to_be16(ETH_P_IP):
type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4;
if (ip_hdr(skb)->protocol == IPPROTO_TCP)
tx_buffer_info->time_stamp = jiffies;
tx_buffer_info->next_to_watch = i;
- adapter->hw_csum_tx_good++;
i++;
if (i == tx_ring->count)
i = 0;
struct sk_buff *skb, u32 tx_flags,
unsigned int first)
{
+ struct pci_dev *pdev = adapter->pdev;
struct ixgbe_tx_buffer *tx_buffer_info;
unsigned int len;
unsigned int total = skb->len;
unsigned int offset = 0, size, count = 0, i;
unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
unsigned int f;
- dma_addr_t *map;
i = tx_ring->next_to_use;
- if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) {
- dev_err(&adapter->pdev->dev, "TX DMA map failed\n");
- return 0;
- }
-
- map = skb_shinfo(skb)->dma_maps;
-
if (tx_flags & IXGBE_TX_FLAGS_FCOE)
/* excluding fcoe_crc_eof for FCoE */
total -= sizeof(struct fcoe_crc_eof);
size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD);
tx_buffer_info->length = size;
- tx_buffer_info->dma = skb_shinfo(skb)->dma_head + offset;
+ tx_buffer_info->mapped_as_page = false;
+ tx_buffer_info->dma = pci_map_single(pdev,
+ skb->data + offset,
+ size, PCI_DMA_TODEVICE);
+ if (pci_dma_mapping_error(pdev, tx_buffer_info->dma))
+ goto dma_error;
tx_buffer_info->time_stamp = jiffies;
tx_buffer_info->next_to_watch = i;
frag = &skb_shinfo(skb)->frags[f];
len = min((unsigned int)frag->size, total);
- offset = 0;
+ offset = frag->page_offset;
while (len) {
i++;
size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD);
tx_buffer_info->length = size;
- tx_buffer_info->dma = map[f] + offset;
+ tx_buffer_info->dma = pci_map_page(adapter->pdev,
+ frag->page,
+ offset, size,
+ PCI_DMA_TODEVICE);
+ tx_buffer_info->mapped_as_page = true;
+ if (pci_dma_mapping_error(pdev, tx_buffer_info->dma))
+ goto dma_error;
tx_buffer_info->time_stamp = jiffies;
tx_buffer_info->next_to_watch = i;
tx_ring->tx_buffer_info[first].next_to_watch = i;
return count;
+
+dma_error:
+ dev_err(&pdev->dev, "TX DMA map failed\n");
+
+ /* clear timestamp and dma mappings for failed tx_buffer_info map */
+ tx_buffer_info->dma = 0;
+ tx_buffer_info->time_stamp = 0;
+ tx_buffer_info->next_to_watch = 0;
+ if (count)
+ count--;
+
+ /* clear timestamp and dma mappings for remaining portion of packet */
+ while (count--) {
+ if (i==0)
+ i += tx_ring->count;
+ i--;
+ tx_buffer_info = &tx_ring->tx_buffer_info[i];
+ ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+ }
+
+ return 0;
}
static void ixgbe_tx_queue(struct ixgbe_adapter *adapter,
static int __ixgbe_maybe_stop_tx(struct net_device *netdev,
struct ixgbe_ring *tx_ring, int size)
{
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
-
netif_stop_subqueue(netdev, tx_ring->queue_index);
/* Herbert's original patch had:
* smp_mb__after_netif_stop_queue();
/* A reprieve! - use start_queue because it doesn't call schedule */
netif_start_subqueue(netdev, tx_ring->queue_index);
- ++adapter->restart_queue;
+ ++tx_ring->restart_queue;
return 0;
}
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
+ int txq = smp_processor_id();
- if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)
- return smp_processor_id();
+ if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
+ while (unlikely(txq >= dev->real_num_tx_queues))
+ txq -= dev->real_num_tx_queues;
+ return txq;
+ }
+#ifdef IXGBE_FCOE
+ if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
+ (skb->protocol == htons(ETH_P_FCOE))) {
+ txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1);
+ txq += adapter->ring_feature[RING_F_FCOE].mask;
+ return txq;
+ }
+#endif
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
return (skb->vlan_tci & IXGBE_TX_FLAGS_VLAN_PRIO_MASK) >> 13;
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_ring *tx_ring;
+ struct netdev_queue *txq;
unsigned int first;
unsigned int tx_flags = 0;
u8 hdr_len = 0;
- int r_idx = 0, tso;
+ int tso;
int count = 0;
unsigned int f;
tx_flags |= vlan_tx_tag_get(skb);
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
tx_flags &= ~IXGBE_TX_FLAGS_VLAN_PRIO_MASK;
- tx_flags |= (skb->queue_mapping << 13);
+ tx_flags |= ((skb->queue_mapping & 0x7) << 13);
}
tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
tx_flags |= IXGBE_TX_FLAGS_VLAN;
} else if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
if (skb->priority != TC_PRIO_CONTROL) {
- tx_flags |= (skb->queue_mapping << 13);
+ tx_flags |= ((skb->queue_mapping & 0x7) << 13);
tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
tx_flags |= IXGBE_TX_FLAGS_VLAN;
} else {
}
}
- r_idx = skb->queue_mapping;
- tx_ring = &adapter->tx_ring[r_idx];
+ tx_ring = &adapter->tx_ring[skb->queue_mapping];
if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
(skb->protocol == htons(ETH_P_FCOE))) {
tx_flags |= IXGBE_TX_FLAGS_FCOE;
#ifdef IXGBE_FCOE
- r_idx = smp_processor_id();
- r_idx &= (adapter->ring_feature[RING_F_FCOE].indices - 1);
- r_idx += adapter->ring_feature[RING_F_FCOE].mask;
- tx_ring = &adapter->tx_ring[r_idx];
+#ifdef CONFIG_IXGBE_DCB
+ tx_flags &= ~(IXGBE_TX_FLAGS_VLAN_PRIO_MASK
+ << IXGBE_TX_FLAGS_VLAN_SHIFT);
+ tx_flags |= ((adapter->fcoe.up << 13)
+ << IXGBE_TX_FLAGS_VLAN_SHIFT);
+#endif
#endif
}
/* four things can cause us to need a context descriptor */
tx_ring->atr_count = 0;
}
}
+ txq = netdev_get_tx_queue(netdev, tx_ring->queue_index);
+ txq->tx_bytes += skb->len;
+ txq->tx_packets++;
ixgbe_tx_queue(adapter, tx_ring, tx_flags, count, skb->len,
hdr_len);
ixgbe_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);
}
/**
- * ixgbe_get_stats - Get System Network Statistics
- * @netdev: network interface device structure
- *
- * Returns the address of the device statistics structure.
- * The statistics are actually updated from the timer callback.
- **/
-static struct net_device_stats *ixgbe_get_stats(struct net_device *netdev)
-{
- /* only return the current stats */
- return &netdev->stats;
-}
-
-/**
* ixgbe_set_mac - Change the Ethernet Address of the NIC
* @netdev: network interface device structure
* @p: pointer to an address structure
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
- hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV);
+ hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs,
+ IXGBE_RAH_AV);
return 0;
}
struct ixgbe_adapter *adapter = netdev_priv(netdev);
int i;
+ /* if interface is down do nothing */
+ if (test_bit(__IXGBE_DOWN, &adapter->state))
+ return;
+
adapter->flags |= IXGBE_FLAG_IN_NETPOLL;
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
.ndo_stop = ixgbe_close,
.ndo_start_xmit = ixgbe_xmit_frame,
.ndo_select_queue = ixgbe_select_queue,
- .ndo_get_stats = ixgbe_get_stats,
.ndo_set_rx_mode = ixgbe_set_rx_mode,
.ndo_set_multicast_list = ixgbe_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
#endif /* IXGBE_FCOE */
};
+static void __devinit ixgbe_probe_vf(struct ixgbe_adapter *adapter,
+ const struct ixgbe_info *ii)
+{
+#ifdef CONFIG_PCI_IOV
+ struct ixgbe_hw *hw = &adapter->hw;
+ int err;
+
+ if (hw->mac.type != ixgbe_mac_82599EB || !max_vfs)
+ return;
+
+ /* The 82599 supports up to 64 VFs per physical function
+ * but this implementation limits allocation to 63 so that
+ * basic networking resources are still available to the
+ * physical function
+ */
+ adapter->num_vfs = (max_vfs > 63) ? 63 : max_vfs;
+ adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
+ err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+ if (err) {
+ DPRINTK(PROBE, ERR,
+ "Failed to enable PCI sriov: %d\n", err);
+ goto err_novfs;
+ }
+ /* If call to enable VFs succeeded then allocate memory
+ * for per VF control structures.
+ */
+ adapter->vfinfo =
+ kcalloc(adapter->num_vfs,
+ sizeof(struct vf_data_storage), GFP_KERNEL);
+ if (adapter->vfinfo) {
+ /* Now that we're sure SR-IOV is enabled
+ * and memory allocated set up the mailbox parameters
+ */
+ ixgbe_init_mbx_params_pf(hw);
+ memcpy(&hw->mbx.ops, ii->mbx_ops,
+ sizeof(hw->mbx.ops));
+
+ /* Disable RSC when in SR-IOV mode */
+ adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
+ IXGBE_FLAG2_RSC_ENABLED);
+ return;
+ }
+
+ /* Oh oh */
+ DPRINTK(PROBE, ERR,
+ "Unable to allocate memory for VF "
+ "Data Storage - SRIOV disabled\n");
+ pci_disable_sriov(adapter->pdev);
+
+err_novfs:
+ adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+ adapter->num_vfs = 0;
+#endif /* CONFIG_PCI_IOV */
+}
+
/**
* ixgbe_probe - Device Initialization Routine
* @pdev: PCI device information struct
goto err_sw_init;
}
+ ixgbe_probe_vf(adapter, ii);
+
netdev->features = NETIF_F_SG |
NETIF_F_IP_CSUM |
NETIF_F_HW_VLAN_TX |
netdev->vlan_features |= NETIF_F_IPV6_CSUM;
netdev->vlan_features |= NETIF_F_SG;
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+ adapter->flags &= ~(IXGBE_FLAG_RSS_ENABLED |
+ IXGBE_FLAG_DCB_ENABLED);
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED;
ixgbe_setup_dca(adapter);
}
#endif
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+ DPRINTK(PROBE, INFO, "IOV is enabled with %d VFs\n",
+ adapter->num_vfs);
+ for (i = 0; i < adapter->num_vfs; i++)
+ ixgbe_vf_configuration(pdev, (i | 0x10000000));
+ }
+
/* add san mac addr to netdev */
ixgbe_add_sanmac_netdev(netdev);
ixgbe_clear_interrupt_scheme(adapter);
err_sw_init:
err_eeprom:
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+ ixgbe_disable_sriov(adapter);
clear_bit(__IXGBE_SFP_MODULE_NOT_FOUND, &adapter->state);
del_timer_sync(&adapter->sfp_timer);
cancel_work_sync(&adapter->sfp_task);
if (netdev->reg_state == NETREG_REGISTERED)
unregister_netdev(netdev);
+ if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+ ixgbe_disable_sriov(adapter);
+
ixgbe_clear_interrupt_scheme(adapter);
ixgbe_release_hw_control(adapter);