Google Git
Sign in
gfiber / kernel / skids / 0f523abce9eb51234627ddc2502590ec2714a9a8 / . / drivers / net / ixgbe / ixgbe_main.c
blob: 778243720649cded98803ae52cd40b026a820fa5 [file] [log] [blame]
/*******************************************************************************
Intel 10 Gigabit PCI Express Linux driver
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,
version 2, as published by the Free Software Foundation.
This program is distributed in the hope it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
more details.
You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
The full GNU General Public License is included in this distribution in
the file called "COPYING".
Contact Information:
e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
*******************************************************************************/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/pkt_sched.h>
#include <linux/ipv6.h>
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
#include <scsi/fc/fc_fcoe.h>
#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[] =
"Intel(R) 10 Gigabit PCI Express Network Driver";
#define DRV_VERSION "2.0.62-k2"
const char ixgbe_driver_version[] = DRV_VERSION;
static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation.";
static const struct ixgbe_info *ixgbe_info_tbl[] = {
[board_82598] = &ixgbe_82598_info,
[board_82599] = &ixgbe_82599_info,
};
/* ixgbe_pci_tbl - PCI Device ID Table
*
* Wildcard entries (PCI_ANY_ID) should come last
* Last entry must be all 0s
*
* { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
* Class, Class Mask, private data (not used) }
*/
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_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX),
board_82598 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4),
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),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM),
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE),
board_82599 },
/* required last entry */
{0, }
};
MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl);
#ifdef CONFIG_IXGBE_DCA
static int ixgbe_notify_dca(struct notifier_block *, unsigned long event,
void *p);
static struct notifier_block dca_notifier = {
.notifier_call = ixgbe_notify_dca,
.next = NULL,
.priority = 0
};
#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");
MODULE_VERSION(DRV_VERSION);
#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;
}
struct ixgbe_reg_info {
u32 ofs;
char *name;
};
static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = {
/* General Registers */
{IXGBE_CTRL, "CTRL"},
{IXGBE_STATUS, "STATUS"},
{IXGBE_CTRL_EXT, "CTRL_EXT"},
/* Interrupt Registers */
{IXGBE_EICR, "EICR"},
/* RX Registers */
{IXGBE_SRRCTL(0), "SRRCTL"},
{IXGBE_DCA_RXCTRL(0), "DRXCTL"},
{IXGBE_RDLEN(0), "RDLEN"},
{IXGBE_RDH(0), "RDH"},
{IXGBE_RDT(0), "RDT"},
{IXGBE_RXDCTL(0), "RXDCTL"},
{IXGBE_RDBAL(0), "RDBAL"},
{IXGBE_RDBAH(0), "RDBAH"},
/* TX Registers */
{IXGBE_TDBAL(0), "TDBAL"},
{IXGBE_TDBAH(0), "TDBAH"},
{IXGBE_TDLEN(0), "TDLEN"},
{IXGBE_TDH(0), "TDH"},
{IXGBE_TDT(0), "TDT"},
{IXGBE_TXDCTL(0), "TXDCTL"},
/* List Terminator */
{}
};
/*
* ixgbe_regdump - register printout routine
*/
static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo)
{
int i = 0, j = 0;
char rname[16];
u32 regs[64];
switch (reginfo->ofs) {
case IXGBE_SRRCTL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i));
break;
case IXGBE_DCA_RXCTRL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i));
break;
case IXGBE_RDLEN(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i));
break;
case IXGBE_RDH(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i));
break;
case IXGBE_RDT(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i));
break;
case IXGBE_RXDCTL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i));
break;
case IXGBE_RDBAL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i));
break;
case IXGBE_RDBAH(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i));
break;
case IXGBE_TDBAL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i));
break;
case IXGBE_TDBAH(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i));
break;
case IXGBE_TDLEN(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i));
break;
case IXGBE_TDH(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i));
break;
case IXGBE_TDT(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i));
break;
case IXGBE_TXDCTL(0):
for (i = 0; i < 64; i++)
regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i));
break;
default:
printk(KERN_INFO "%-15s %08x\n", reginfo->name,
IXGBE_READ_REG(hw, reginfo->ofs));
return;
}
for (i = 0; i < 8; i++) {
snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7);
printk(KERN_ERR "%-15s ", rname);
for (j = 0; j < 8; j++)
printk(KERN_CONT "%08x ", regs[i*8+j]);
printk(KERN_CONT "\n");
}
}
/*
* ixgbe_dump - Print registers, tx-rings and rx-rings
*/
static void ixgbe_dump(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
struct ixgbe_reg_info *reginfo;
int n = 0;
struct ixgbe_ring *tx_ring;
struct ixgbe_tx_buffer *tx_buffer_info;
union ixgbe_adv_tx_desc *tx_desc;
struct my_u0 { u64 a; u64 b; } *u0;
struct ixgbe_ring *rx_ring;
union ixgbe_adv_rx_desc *rx_desc;
struct ixgbe_rx_buffer *rx_buffer_info;
u32 staterr;
int i = 0;
if (!netif_msg_hw(adapter))
return;
/* Print netdevice Info */
if (netdev) {
dev_info(&adapter->pdev->dev, "Net device Info\n");
printk(KERN_INFO "Device Name state "
"trans_start last_rx\n");
printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
netdev->name,
netdev->state,
netdev->trans_start,
netdev->last_rx);
}
/* Print Registers */
dev_info(&adapter->pdev->dev, "Register Dump\n");
printk(KERN_INFO " Register Name Value\n");
for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl;
reginfo->name; reginfo++) {
ixgbe_regdump(hw, reginfo);
}
/* Print TX Ring Summary */
if (!netdev || !netif_running(netdev))
goto exit;
dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ] "
"leng ntw timestamp\n");
for (n = 0; n < adapter->num_tx_queues; n++) {
tx_ring = adapter->tx_ring[n];
tx_buffer_info =
&tx_ring->tx_buffer_info[tx_ring->next_to_clean];
printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n",
n, tx_ring->next_to_use, tx_ring->next_to_clean,
(u64)tx_buffer_info->dma,
tx_buffer_info->length,
tx_buffer_info->next_to_watch,
(u64)tx_buffer_info->time_stamp);
}
/* Print TX Rings */
if (!netif_msg_tx_done(adapter))
goto rx_ring_summary;
dev_info(&adapter->pdev->dev, "TX Rings Dump\n");
/* Transmit Descriptor Formats
*
* Advanced Transmit Descriptor
* +--------------------------------------------------------------+
* 0 | Buffer Address [63:0] |
* +--------------------------------------------------------------+
* 8 | PAYLEN | PORTS | IDX | STA | DCMD |DTYP | RSV | DTALEN |
* +--------------------------------------------------------------+
* 63 46 45 40 39 36 35 32 31 24 23 20 19 0
*/
for (n = 0; n < adapter->num_tx_queues; n++) {
tx_ring = adapter->tx_ring[n];
printk(KERN_INFO "------------------------------------\n");
printk(KERN_INFO "TX QUEUE INDEX = %d\n", tx_ring->queue_index);
printk(KERN_INFO "------------------------------------\n");
printk(KERN_INFO "T [desc] [address 63:0 ] "
"[PlPOIdStDDt Ln] [bi->dma ] "
"leng ntw timestamp bi->skb\n");
for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
tx_buffer_info = &tx_ring->tx_buffer_info[i];
u0 = (struct my_u0 *)tx_desc;
printk(KERN_INFO "T [0x%03X] %016llX %016llX %016llX"
" %04X %3X %016llX %p", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
(u64)tx_buffer_info->dma,
tx_buffer_info->length,
tx_buffer_info->next_to_watch,
(u64)tx_buffer_info->time_stamp,
tx_buffer_info->skb);
if (i == tx_ring->next_to_use &&
i == tx_ring->next_to_clean)
printk(KERN_CONT " NTC/U\n");
else if (i == tx_ring->next_to_use)
printk(KERN_CONT " NTU\n");
else if (i == tx_ring->next_to_clean)
printk(KERN_CONT " NTC\n");
else
printk(KERN_CONT "\n");
if (netif_msg_pktdata(adapter) &&
tx_buffer_info->dma != 0)
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
phys_to_virt(tx_buffer_info->dma),
tx_buffer_info->length, true);
}
}
/* Print RX Rings Summary */
rx_ring_summary:
dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
printk(KERN_INFO "Queue [NTU] [NTC]\n");
for (n = 0; n < adapter->num_rx_queues; n++) {
rx_ring = adapter->rx_ring[n];
printk(KERN_INFO "%5d %5X %5X\n", n,
rx_ring->next_to_use, rx_ring->next_to_clean);
}
/* Print RX Rings */
if (!netif_msg_rx_status(adapter))
goto exit;
dev_info(&adapter->pdev->dev, "RX Rings Dump\n");
/* Advanced Receive Descriptor (Read) Format
* 63 1 0
* +-----------------------------------------------------+
* 0 | Packet Buffer Address [63:1] |A0/NSE|
* +----------------------------------------------+------+
* 8 | Header Buffer Address [63:1] | DD |
* +-----------------------------------------------------+
*
*
* Advanced Receive Descriptor (Write-Back) Format
*
* 63 48 47 32 31 30 21 20 16 15 4 3 0
* +------------------------------------------------------+
* 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS |
* | Checksum Ident | | | | Type | Type |
* +------------------------------------------------------+
* 8 | VLAN Tag | Length | Extended Error | Extended Status |
* +------------------------------------------------------+
* 63 48 47 32 31 20 19 0
*/
for (n = 0; n < adapter->num_rx_queues; n++) {
rx_ring = adapter->rx_ring[n];
printk(KERN_INFO "------------------------------------\n");
printk(KERN_INFO "RX QUEUE INDEX = %d\n", rx_ring->queue_index);
printk(KERN_INFO "------------------------------------\n");
printk(KERN_INFO "R [desc] [ PktBuf A0] "
"[ HeadBuf DD] [bi->dma ] [bi->skb] "
"<-- Adv Rx Read format\n");
printk(KERN_INFO "RWB[desc] [PcsmIpSHl PtRs] "
"[vl er S cks ln] ---------------- [bi->skb] "
"<-- Adv Rx Write-Back format\n");
for (i = 0; i < rx_ring->count; i++) {
rx_buffer_info = &rx_ring->rx_buffer_info[i];
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
u0 = (struct my_u0 *)rx_desc;
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
if (staterr & IXGBE_RXD_STAT_DD) {
/* Descriptor Done */
printk(KERN_INFO "RWB[0x%03X] %016llX "
"%016llX ---------------- %p", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
rx_buffer_info->skb);
} else {
printk(KERN_INFO "R [0x%03X] %016llX "
"%016llX %016llX %p", i,
le64_to_cpu(u0->a),
le64_to_cpu(u0->b),
(u64)rx_buffer_info->dma,
rx_buffer_info->skb);
if (netif_msg_pktdata(adapter)) {
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
phys_to_virt(rx_buffer_info->dma),
rx_ring->rx_buf_len, true);
if (rx_ring->rx_buf_len
< IXGBE_RXBUFFER_2048)
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
phys_to_virt(
rx_buffer_info->page_dma +
rx_buffer_info->page_offset
),
PAGE_SIZE/2, true);
}
}
if (i == rx_ring->next_to_use)
printk(KERN_CONT " NTU\n");
else if (i == rx_ring->next_to_clean)
printk(KERN_CONT " NTC\n");
else
printk(KERN_CONT "\n");
}
}
exit:
return;
}
static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
{
u32 ctrl_ext;
/* Let firmware take over control of h/w */
ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD);
}
static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter)
{
u32 ctrl_ext;
/* Let firmware know the driver has taken over */
ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT,
ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD);
}
/*
* ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors
* @adapter: pointer to adapter struct
* @direction: 0 for Rx, 1 for Tx, -1 for other causes
* @queue: queue to map the corresponding interrupt to
* @msix_vector: the vector to map to the corresponding queue
*
*/
static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
u8 queue, u8 msix_vector)
{
u32 ivar, index;
struct ixgbe_hw *hw = &adapter->hw;
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
msix_vector |= IXGBE_IVAR_ALLOC_VAL;
if (direction == -1)
direction = 0;
index = (((direction * 64) + queue) >> 2) & 0x1F;
ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
ivar &= ~(0xFF << (8 * (queue & 0x3)));
ivar |= (msix_vector << (8 * (queue & 0x3)));
IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
break;
case ixgbe_mac_82599EB:
if (direction == -1) {
/* other causes */
msix_vector |= IXGBE_IVAR_ALLOC_VAL;
index = ((queue & 1) * 8);
ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC);
ivar &= ~(0xFF << index);
ivar |= (msix_vector << index);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar);
break;
} else {
/* tx or rx causes */
msix_vector |= IXGBE_IVAR_ALLOC_VAL;
index = ((16 * (queue & 1)) + (8 * direction));
ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1));
ivar &= ~(0xFF << index);
ivar |= (msix_vector << index);
IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar);
break;
}
default:
break;
}
}
static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
u64 qmask)
{
u32 mask;
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
} else {
mask = (qmask & 0xFFFFFFFF);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
mask = (qmask >> 32);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
}
}
static void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter,
struct ixgbe_tx_buffer
*tx_buffer_info)
{
if (tx_buffer_info->dma) {
if (tx_buffer_info->mapped_as_page)
dma_unmap_page(&adapter->pdev->dev,
tx_buffer_info->dma,
tx_buffer_info->length,
DMA_TO_DEVICE);
else
dma_unmap_single(&adapter->pdev->dev,
tx_buffer_info->dma,
tx_buffer_info->length,
DMA_TO_DEVICE);
tx_buffer_info->dma = 0;
}
if (tx_buffer_info->skb) {
dev_kfree_skb_any(tx_buffer_info->skb);
tx_buffer_info->skb = NULL;
}
tx_buffer_info->time_stamp = 0;
/* tx_buffer_info must be completely set up in the transmit path */
}
/**
* ixgbe_tx_xon_state - check the tx ring xon state
* @adapter: the ixgbe adapter
* @tx_ring: the corresponding tx_ring
*
* If not in DCB mode, checks TFCS.TXOFF, otherwise, find out the
* corresponding TC of this tx_ring when checking TFCS.
*
* Returns : true if in xon state (currently not paused)
*/
static inline bool ixgbe_tx_xon_state(struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
{
u32 txoff = IXGBE_TFCS_TXOFF;
#ifdef CONFIG_IXGBE_DCB
if (adapter->dcb_cfg.pfc_mode_enable) {
int tc;
int reg_idx = tx_ring->reg_idx;
int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
switch (adapter->hw.mac.type) {
case ixgbe_mac_82598EB:
tc = reg_idx >> 2;
txoff = IXGBE_TFCS_TXOFF0;
break;
case ixgbe_mac_82599EB:
tc = 0;
txoff = IXGBE_TFCS_TXOFF;
if (dcb_i == 8) {
/* TC0, TC1 */
tc = reg_idx >> 5;
if (tc == 2) /* TC2, TC3 */
tc += (reg_idx - 64) >> 4;
else if (tc == 3) /* TC4, TC5, TC6, TC7 */
tc += 1 + ((reg_idx - 96) >> 3);
} else if (dcb_i == 4) {
/* TC0, TC1 */
tc = reg_idx >> 6;
if (tc == 1) {
tc += (reg_idx - 64) >> 5;
if (tc == 2) /* TC2, TC3 */
tc += (reg_idx - 96) >> 4;
}
}
break;
default:
tc = 0;
}
txoff <<= tc;
}
#endif
return IXGBE_READ_REG(&adapter->hw, IXGBE_TFCS) & txoff;
}
static inline bool ixgbe_check_tx_hang(struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring,
unsigned int eop)
{
struct ixgbe_hw *hw = &adapter->hw;
/* Detect a transmit hang in hardware, this serializes the
* check with the clearing of time_stamp and movement of eop */
adapter->detect_tx_hung = false;
if (tx_ring->tx_buffer_info[eop].time_stamp &&
time_after(jiffies, tx_ring->tx_buffer_info[eop].time_stamp + HZ) &&
ixgbe_tx_xon_state(adapter, tx_ring)) {
/* detected Tx unit hang */
union ixgbe_adv_tx_desc *tx_desc;
tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
DPRINTK(DRV, ERR, "Detected Tx Unit Hang\n"
" Tx Queue <%d>\n"
" TDH, TDT <%x>, <%x>\n"
" next_to_use <%x>\n"
" next_to_clean <%x>\n"
"tx_buffer_info[next_to_clean]\n"
" time_stamp <%lx>\n"
" jiffies <%lx>\n",
tx_ring->queue_index,
IXGBE_READ_REG(hw, tx_ring->head),
IXGBE_READ_REG(hw, tx_ring->tail),
tx_ring->next_to_use, eop,
tx_ring->tx_buffer_info[eop].time_stamp, jiffies);
return true;
}
return false;
}
#define IXGBE_MAX_TXD_PWR 14
#define IXGBE_MAX_DATA_PER_TXD (1 << IXGBE_MAX_TXD_PWR)
/* Tx Descriptors needed, worst case */
#define TXD_USE_COUNT(S) (((S) >> IXGBE_MAX_TXD_PWR) + \
(((S) & (IXGBE_MAX_DATA_PER_TXD - 1)) ? 1 : 0))
#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \
MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1) /* for context */
static void ixgbe_tx_timeout(struct net_device *netdev);
/**
* ixgbe_clean_tx_irq - Reclaim resources after transmit completes
* @q_vector: structure containing interrupt and ring information
* @tx_ring: tx ring to clean
**/
static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *tx_ring)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct net_device *netdev = adapter->netdev;
union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
struct ixgbe_tx_buffer *tx_buffer_info;
unsigned int i, eop, count = 0;
unsigned int total_bytes = 0, total_packets = 0;
i = tx_ring->next_to_clean;
eop = tx_ring->tx_buffer_info[i].next_to_watch;
eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
(count < tx_ring->work_limit)) {
bool cleaned = false;
rmb(); /* read buffer_info after eop_desc */
for ( ; !cleaned; count++) {
struct sk_buff *skb;
tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
tx_buffer_info = &tx_ring->tx_buffer_info[i];
cleaned = (i == eop);
skb = tx_buffer_info->skb;
if (cleaned && skb) {
unsigned int segs, bytecount;
unsigned int hlen = skb_headlen(skb);
/* gso_segs is currently only valid for tcp */
segs = skb_shinfo(skb)->gso_segs ?: 1;
#ifdef IXGBE_FCOE
/* adjust for FCoE Sequence Offload */
if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
&& (skb->protocol == htons(ETH_P_FCOE)) &&
skb_is_gso(skb)) {
hlen = skb_transport_offset(skb) +
sizeof(struct fc_frame_header) +
sizeof(struct fcoe_crc_eof);
segs = DIV_ROUND_UP(skb->len - hlen,
skb_shinfo(skb)->gso_size);
}
#endif /* IXGBE_FCOE */
/* multiply data chunks by size of headers */
bytecount = ((segs - 1) * hlen) + skb->len;
total_packets += segs;
total_bytes += bytecount;
}
ixgbe_unmap_and_free_tx_resource(adapter,
tx_buffer_info);
tx_desc->wb.status = 0;
i++;
if (i == tx_ring->count)
i = 0;
}
eop = tx_ring->tx_buffer_info[i].next_to_watch;
eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
}
tx_ring->next_to_clean = i;
#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
if (unlikely(count && netif_carrier_ok(netdev) &&
(IXGBE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
*/
smp_mb();
if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
!test_bit(__IXGBE_DOWN, &adapter->state)) {
netif_wake_subqueue(netdev, tx_ring->queue_index);
++tx_ring->restart_queue;
}
}
if (adapter->detect_tx_hung) {
if (ixgbe_check_tx_hang(adapter, tx_ring, i)) {
/* schedule immediate reset if we believe we hung */
DPRINTK(PROBE, INFO,
"tx hang %d detected, resetting adapter\n",
adapter->tx_timeout_count + 1);
ixgbe_tx_timeout(adapter->netdev);
}
}
/* re-arm the interrupt */
if (count >= tx_ring->work_limit)
ixgbe_irq_rearm_queues(adapter, ((u64)1 << q_vector->v_idx));
tx_ring->total_bytes += total_bytes;
tx_ring->total_packets += total_packets;
tx_ring->stats.packets += total_packets;
tx_ring->stats.bytes += total_bytes;
return (count < tx_ring->work_limit);
}
#ifdef CONFIG_IXGBE_DCA
static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring)
{
u32 rxctrl;
int cpu = get_cpu();
int q = rx_ring->reg_idx;
if (rx_ring->cpu != cpu) {
rxctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_DCA_RXCTRL(q));
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK;
rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
} else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599;
rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599);
}
rxctrl |= IXGBE_DCA_RXCTRL_DESC_DCA_EN;
rxctrl |= IXGBE_DCA_RXCTRL_HEAD_DCA_EN;
rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_RRO_EN);
rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_WRO_EN |
IXGBE_DCA_RXCTRL_DESC_HSRO_EN);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_RXCTRL(q), rxctrl);
rx_ring->cpu = cpu;
}
put_cpu();
}
static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
{
u32 txctrl;
int cpu = get_cpu();
int q = tx_ring->reg_idx;
struct ixgbe_hw *hw = &adapter->hw;
if (tx_ring->cpu != cpu) {
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(q));
txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK;
txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(q), txctrl);
} else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(q));
txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK_82599;
txctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599);
txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(q), txctrl);
}
tx_ring->cpu = cpu;
}
put_cpu();
}
static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
{
int i;
if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED))
return;
/* always use CB2 mode, difference is masked in the CB driver */
IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2);
for (i = 0; i < adapter->num_tx_queues; i++) {
adapter->tx_ring[i]->cpu = -1;
ixgbe_update_tx_dca(adapter, adapter->tx_ring[i]);
}
for (i = 0; i < adapter->num_rx_queues; i++) {
adapter->rx_ring[i]->cpu = -1;
ixgbe_update_rx_dca(adapter, adapter->rx_ring[i]);
}
}
static int __ixgbe_notify_dca(struct device *dev, void *data)
{
struct net_device *netdev = dev_get_drvdata(dev);
struct ixgbe_adapter *adapter = netdev_priv(netdev);
unsigned long event = *(unsigned long *)data;
switch (event) {
case DCA_PROVIDER_ADD:
/* if we're already enabled, don't do it again */
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
break;
if (dca_add_requester(dev) == 0) {
adapter->flags |= IXGBE_FLAG_DCA_ENABLED;
ixgbe_setup_dca(adapter);
break;
}
/* Fall Through since DCA is disabled. */
case DCA_PROVIDER_REMOVE:
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
dca_remove_requester(dev);
adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED;
IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 1);
}
break;
}
return 0;
}
#endif /* CONFIG_IXGBE_DCA */
/**
* ixgbe_receive_skb - Send a completed packet up the stack
* @adapter: board private structure
* @skb: packet to send up
* @status: hardware indication of status of receive
* @rx_ring: rx descriptor ring (for a specific queue) to setup
* @rx_desc: rx descriptor
**/
static void ixgbe_receive_skb(struct ixgbe_q_vector *q_vector,
struct sk_buff *skb, u8 status,
struct ixgbe_ring *ring,
union ixgbe_adv_rx_desc *rx_desc)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct napi_struct *napi = &q_vector->napi;
bool is_vlan = (status & IXGBE_RXD_STAT_VP);
u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan);
skb_record_rx_queue(skb, ring->queue_index);
if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) {
if (adapter->vlgrp && is_vlan && (tag & VLAN_VID_MASK))
vlan_gro_receive(napi, adapter->vlgrp, tag, skb);
else
napi_gro_receive(napi, skb);
} else {
if (adapter->vlgrp && is_vlan && (tag & VLAN_VID_MASK))
vlan_hwaccel_rx(skb, adapter->vlgrp, tag);
else
netif_rx(skb);
}
}
/**
* ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum
* @adapter: address of board private structure
* @status_err: hardware indication of status of receive
* @skb: skb currently being received and modified
**/
static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter,
union ixgbe_adv_rx_desc *rx_desc,
struct sk_buff *skb)
{
u32 status_err = le32_to_cpu(rx_desc->wb.upper.status_error);
skb->ip_summed = CHECKSUM_NONE;
/* Rx csum disabled */
if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED))
return;
/* if IP and error */
if ((status_err & IXGBE_RXD_STAT_IPCS) &&
(status_err & IXGBE_RXDADV_ERR_IPE)) {
adapter->hw_csum_rx_error++;
return;
}
if (!(status_err & IXGBE_RXD_STAT_L4CS))
return;
if (status_err & IXGBE_RXDADV_ERR_TCPE) {
u16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
/*
* 82599 errata, UDP frames with a 0 checksum can be marked as
* checksum errors.
*/
if ((pkt_info & IXGBE_RXDADV_PKTTYPE_UDP) &&
(adapter->hw.mac.type == ixgbe_mac_82599EB))
return;
adapter->hw_csum_rx_error++;
return;
}
/* It must be a TCP or UDP packet with a valid checksum */
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
struct ixgbe_ring *rx_ring, u32 val)
{
/*
* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
* applicable for weak-ordered memory model archs,
* such as IA-64).
*/
wmb();
IXGBE_WRITE_REG(hw, IXGBE_RDT(rx_ring->reg_idx), val);
}
/**
* ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split
* @adapter: address of board private structure
**/
static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring,
int cleaned_count)
{
struct pci_dev *pdev = adapter->pdev;
union ixgbe_adv_rx_desc *rx_desc;
struct ixgbe_rx_buffer *bi;
unsigned int i;
i = rx_ring->next_to_use;
bi = &rx_ring->rx_buffer_info[i];
while (cleaned_count--) {
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
if (!bi->page_dma &&
(rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)) {
if (!bi->page) {
bi->page = alloc_page(GFP_ATOMIC);
if (!bi->page) {
adapter->alloc_rx_page_failed++;
goto no_buffers;
}
bi->page_offset = 0;
} else {
/* use a half page if we're re-using */
bi->page_offset ^= (PAGE_SIZE / 2);
}
bi->page_dma = dma_map_page(&pdev->dev, bi->page,
bi->page_offset,
(PAGE_SIZE / 2),
DMA_FROM_DEVICE);
}
if (!bi->skb) {
struct sk_buff *skb;
/* 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 = dma_map_single(&pdev->dev, skb->data,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
/* Refresh the desc even if buffer_addrs didn't change because
* each write-back erases this info. */
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
} else {
rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
}
i++;
if (i == rx_ring->count)
i = 0;
bi = &rx_ring->rx_buffer_info[i];
}
no_buffers:
if (rx_ring->next_to_use != i) {
rx_ring->next_to_use = i;
if (i-- == 0)
i = (rx_ring->count - 1);
ixgbe_release_rx_desc(&adapter->hw, rx_ring, i);
}
}
static inline u16 ixgbe_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc)
{
return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info;
}
static inline u16 ixgbe_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc)
{
return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
}
static inline u32 ixgbe_get_rsc_count(union ixgbe_adv_rx_desc *rx_desc)
{
return (le32_to_cpu(rx_desc->wb.lower.lo_dword.data) &
IXGBE_RXDADV_RSCCNT_MASK) >>
IXGBE_RXDADV_RSCCNT_SHIFT;
}
/**
* ixgbe_transform_rsc_queue - change rsc queue into a full packet
* @skb: pointer to the last skb in the rsc queue
* @count: pointer to number of packets coalesced in this context
*
* This function changes a queue full of hw rsc buffers into a completed
* packet. It uses the ->prev pointers to find the first packet and then
* turns it into the frag list owner.
**/
static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb,
u64 *count)
{
unsigned int frag_list_size = 0;
while (skb->prev) {
struct sk_buff *prev = skb->prev;
frag_list_size += skb->len;
skb->prev = NULL;
skb = prev;
*count += 1;
}
skb_shinfo(skb)->frag_list = skb->next;
skb->next = NULL;
skb->len += frag_list_size;
skb->data_len += frag_list_size;
skb->truesize += frag_list_size;
return skb;
}
struct ixgbe_rsc_cb {
dma_addr_t dma;
bool delay_unmap;
};
#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb)
static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *rx_ring,
int *work_done, int work_to_do)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct net_device *netdev = adapter->netdev;
struct pci_dev *pdev = adapter->pdev;
union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
struct ixgbe_rx_buffer *rx_buffer_info, *next_buffer;
struct sk_buff *skb;
unsigned int i, rsc_count = 0;
u32 len, staterr;
u16 hdr_info;
bool cleaned = false;
int cleaned_count = 0;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
#ifdef IXGBE_FCOE
int ddp_bytes = 0;
#endif /* IXGBE_FCOE */
i = rx_ring->next_to_clean;
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
rx_buffer_info = &rx_ring->rx_buffer_info[i];
while (staterr & IXGBE_RXD_STAT_DD) {
u32 upper_len = 0;
if (*work_done >= work_to_do)
break;
(*work_done)++;
rmb(); /* read descriptor and rx_buffer_info after status DD */
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
hdr_info = le16_to_cpu(ixgbe_get_hdr_info(rx_desc));
len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
IXGBE_RXDADV_HDRBUFLEN_SHIFT;
upper_len = le16_to_cpu(rx_desc->wb.upper.length);
if ((len > IXGBE_RX_HDR_SIZE) ||
(upper_len && !(hdr_info & IXGBE_RXDADV_SPH)))
len = IXGBE_RX_HDR_SIZE;
} else {
len = le16_to_cpu(rx_desc->wb.upper.length);
}
cleaned = true;
skb = rx_buffer_info->skb;
prefetch(skb->data);
rx_buffer_info->skb = NULL;
if (rx_buffer_info->dma) {
if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
(!(staterr & IXGBE_RXD_STAT_EOP)) &&
(!(skb->prev))) {
/*
* When HWRSC is enabled, delay unmapping
* of the first packet. It carries the
* header information, HW may still
* access the header after the writeback.
* Only unmap it when EOP is reached
*/
IXGBE_RSC_CB(skb)->delay_unmap = true;
IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
} else {
dma_unmap_single(&pdev->dev,
rx_buffer_info->dma,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
rx_buffer_info->dma = 0;
skb_put(skb, len);
}
if (upper_len) {
dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma,
PAGE_SIZE / 2, DMA_FROM_DEVICE);
rx_buffer_info->page_dma = 0;
skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
rx_buffer_info->page,
rx_buffer_info->page_offset,
upper_len);
if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) ||
(page_count(rx_buffer_info->page) != 1))
rx_buffer_info->page = NULL;
else
get_page(rx_buffer_info->page);
skb->len += upper_len;
skb->data_len += upper_len;
skb->truesize += upper_len;
}
i++;
if (i == rx_ring->count)
i = 0;
next_rxd = IXGBE_RX_DESC_ADV(*rx_ring, i);
prefetch(next_rxd);
cleaned_count++;
if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
rsc_count = ixgbe_get_rsc_count(rx_desc);
if (rsc_count) {
u32 nextp = (staterr & IXGBE_RXDADV_NEXTP_MASK) >>
IXGBE_RXDADV_NEXTP_SHIFT;
next_buffer = &rx_ring->rx_buffer_info[nextp];
} else {
next_buffer = &rx_ring->rx_buffer_info[i];
}
if (staterr & IXGBE_RXD_STAT_EOP) {
if (skb->prev)
skb = ixgbe_transform_rsc_queue(skb, &(rx_ring->rsc_count));
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
if (IXGBE_RSC_CB(skb)->delay_unmap) {
dma_unmap_single(&pdev->dev,
IXGBE_RSC_CB(skb)->dma,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
IXGBE_RSC_CB(skb)->dma = 0;
IXGBE_RSC_CB(skb)->delay_unmap = false;
}
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)
rx_ring->rsc_count += skb_shinfo(skb)->nr_frags;
else
rx_ring->rsc_count++;
rx_ring->rsc_flush++;
}
rx_ring->stats.packets++;
rx_ring->stats.bytes += skb->len;
} else {
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
rx_buffer_info->skb = next_buffer->skb;
rx_buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
next_buffer->dma = 0;
} else {
skb->next = next_buffer->skb;
skb->next->prev = skb;
}
rx_ring->non_eop_descs++;
goto next_desc;
}
if (staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK) {
dev_kfree_skb_irq(skb);
goto next_desc;
}
ixgbe_rx_checksum(adapter, rx_desc, skb);
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
total_rx_packets++;
skb->protocol = eth_type_trans(skb, adapter->netdev);
#ifdef IXGBE_FCOE
/* if ddp, not passing to ULD unless for FCP_RSP or error */
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb);
if (!ddp_bytes)
goto next_desc;
}
#endif /* IXGBE_FCOE */
ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
next_desc:
rx_desc->wb.upper.status_error = 0;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
ixgbe_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
cleaned_count = 0;
}
/* use prefetched values */
rx_desc = next_rxd;
rx_buffer_info = &rx_ring->rx_buffer_info[i];
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
}
rx_ring->next_to_clean = i;
cleaned_count = IXGBE_DESC_UNUSED(rx_ring);
if (cleaned_count)
ixgbe_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
#ifdef IXGBE_FCOE
/* include DDPed FCoE data */
if (ddp_bytes > 0) {
unsigned int mss;
mss = adapter->netdev->mtu - sizeof(struct fcoe_hdr) -
sizeof(struct fc_frame_header) -
sizeof(struct fcoe_crc_eof);
if (mss > 512)
mss &= ~511;
total_rx_bytes += ddp_bytes;
total_rx_packets += DIV_ROUND_UP(ddp_bytes, mss);
}
#endif /* IXGBE_FCOE */
rx_ring->total_packets += total_rx_packets;
rx_ring->total_bytes += total_rx_bytes;
netdev->stats.rx_bytes += total_rx_bytes;
netdev->stats.rx_packets += total_rx_packets;
return cleaned;
}
static int ixgbe_clean_rxonly(struct napi_struct *, int);
/**
* ixgbe_configure_msix - Configure MSI-X hardware
* @adapter: board private structure
*
* ixgbe_configure_msix sets up the hardware to properly generate MSI-X
* interrupts.
**/
static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
{
struct ixgbe_q_vector *q_vector;
int i, j, q_vectors, v_idx, r_idx;
u32 mask;
q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
/*
* Populate the IVAR table and set the ITR values to the
* corresponding register.
*/
for (v_idx = 0; v_idx < q_vectors; v_idx++) {
q_vector = adapter->q_vector[v_idx];
/* XXX for_each_set_bit(...) */
r_idx = find_first_bit(q_vector->rxr_idx,
adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
j = adapter->rx_ring[r_idx]->reg_idx;
ixgbe_set_ivar(adapter, 0, j, v_idx);
r_idx = find_next_bit(q_vector->rxr_idx,
adapter->num_rx_queues,
r_idx + 1);
}
r_idx = find_first_bit(q_vector->txr_idx,
adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
j = adapter->tx_ring[r_idx]->reg_idx;
ixgbe_set_ivar(adapter, 1, j, v_idx);
r_idx = find_next_bit(q_vector->txr_idx,
adapter->num_tx_queues,
r_idx + 1);
}
if (q_vector->txr_count && !q_vector->rxr_count)
/* tx only */
q_vector->eitr = adapter->tx_eitr_param;
else if (q_vector->rxr_count)
/* rx or mixed */
q_vector->eitr = adapter->rx_eitr_param;
ixgbe_write_eitr(q_vector);
}
if (adapter->hw.mac.type == ixgbe_mac_82598EB)
ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX,
v_idx);
else if (adapter->hw.mac.type == ixgbe_mac_82599EB)
ixgbe_set_ivar(adapter, -1, 1, v_idx);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950);
/* set up to autoclear timer, and the vectors */
mask = IXGBE_EIMS_ENABLE_MASK;
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);
}
enum latency_range {
lowest_latency = 0,
low_latency = 1,
bulk_latency = 2,
latency_invalid = 255
};
/**
* ixgbe_update_itr - update the dynamic ITR value based on statistics
* @adapter: pointer to adapter
* @eitr: eitr setting (ints per sec) to give last timeslice
* @itr_setting: current throttle rate in ints/second
* @packets: the number of packets during this measurement interval
* @bytes: the number of bytes during this measurement interval
*
* Stores a new ITR value based on packets and byte
* counts during the last interrupt. The advantage of per interrupt
* computation is faster updates and more accurate ITR for the current
* traffic pattern. Constants in this function were computed
* based on theoretical maximum wire speed and thresholds were set based
* on testing data as well as attempting to minimize response time
* while increasing bulk throughput.
* this functionality is controlled by the InterruptThrottleRate module
* parameter (see ixgbe_param.c)
**/
static u8 ixgbe_update_itr(struct ixgbe_adapter *adapter,
u32 eitr, u8 itr_setting,
int packets, int bytes)
{
unsigned int retval = itr_setting;
u32 timepassed_us;
u64 bytes_perint;
if (packets == 0)
goto update_itr_done;
/* simple throttlerate management
* 0-20MB/s lowest (100000 ints/s)
* 20-100MB/s low (20000 ints/s)
* 100-1249MB/s bulk (8000 ints/s)
*/
/* what was last interrupt timeslice? */
timepassed_us = 1000000/eitr;
bytes_perint = bytes / timepassed_us; /* bytes/usec */
switch (itr_setting) {
case lowest_latency:
if (bytes_perint > adapter->eitr_low)
retval = low_latency;
break;
case low_latency:
if (bytes_perint > adapter->eitr_high)
retval = bulk_latency;
else if (bytes_perint <= adapter->eitr_low)
retval = lowest_latency;
break;
case bulk_latency:
if (bytes_perint <= adapter->eitr_high)
retval = low_latency;
break;
}
update_itr_done:
return retval;
}
/**
* ixgbe_write_eitr - write EITR register in hardware specific way
* @q_vector: structure containing interrupt and ring information
*
* This function is made to be called by ethtool and by the driver
* when it needs to update EITR registers at runtime. Hardware
* specific quirks/differences are taken care of here.
*/
void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_hw *hw = &adapter->hw;
int v_idx = q_vector->v_idx;
u32 itr_reg = EITR_INTS_PER_SEC_TO_REG(q_vector->eitr);
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
/* must write high and low 16 bits to reset counter */
itr_reg |= (itr_reg << 16);
} else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
/*
* 82599 can support a value of zero, so allow it for
* max interrupt rate, but there is an errata where it can
* not be zero with RSC
*/
if (itr_reg == 8 &&
!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))
itr_reg = 0;
/*
* set the WDIS bit to not clear the timer bits and cause an
* immediate assertion of the interrupt
*/
itr_reg |= IXGBE_EITR_CNT_WDIS;
}
IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
}
static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
u32 new_itr;
u8 current_itr, ret_itr;
int i, r_idx;
struct ixgbe_ring *rx_ring, *tx_ring;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
tx_ring = adapter->tx_ring[r_idx];
ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
q_vector->tx_itr,
tx_ring->total_packets,
tx_ring->total_bytes);
/* if the result for this queue would decrease interrupt
* rate for this vector then use that result */
q_vector->tx_itr = ((q_vector->tx_itr > ret_itr) ?
q_vector->tx_itr - 1 : ret_itr);
r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
r_idx + 1);
}
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
rx_ring = adapter->rx_ring[r_idx];
ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
q_vector->rx_itr,
rx_ring->total_packets,
rx_ring->total_bytes);
/* if the result for this queue would decrease interrupt
* rate for this vector then use that result */
q_vector->rx_itr = ((q_vector->rx_itr > ret_itr) ?
q_vector->rx_itr - 1 : ret_itr);
r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
r_idx + 1);
}
current_itr = max(q_vector->rx_itr, q_vector->tx_itr);
switch (current_itr) {
/* counts and packets in update_itr are dependent on these numbers */
case lowest_latency:
new_itr = 100000;
break;
case low_latency:
new_itr = 20000; /* aka hwitr = ~200 */
break;
case bulk_latency:
default:
new_itr = 8000;
break;
}
if (new_itr != q_vector->eitr) {
/* do an exponential smoothing */
new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
/* save the algorithm value here, not the smoothed one */
q_vector->eitr = new_itr;
ixgbe_write_eitr(q_vector);
}
}
/**
* ixgbe_check_overtemp_task - worker thread to check over tempurature
* @work: pointer to work_struct containing our data
**/
static void ixgbe_check_overtemp_task(struct work_struct *work)
{
struct ixgbe_adapter *adapter = container_of(work,
struct ixgbe_adapter,
check_overtemp_task);
struct ixgbe_hw *hw = &adapter->hw;
u32 eicr = adapter->interrupt_event;
if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) {
switch (hw->device_id) {
case IXGBE_DEV_ID_82599_T3_LOM: {
u32 autoneg;
bool link_up = false;
if (hw->mac.ops.check_link)
hw->mac.ops.check_link(hw, &autoneg, &link_up, false);
if (((eicr & IXGBE_EICR_GPI_SDP0) && (!link_up)) ||
(eicr & IXGBE_EICR_LSC))
/* Check if this is due to overtemp */
if (hw->phy.ops.check_overtemp(hw) == IXGBE_ERR_OVERTEMP)
break;
}
return;
default:
if (!(eicr & IXGBE_EICR_GPI_SDP0))
return;
break;
}
DPRINTK(DRV, ERR, "Network adapter has been stopped because it "
"has over heated. Restart the computer. If the problem "
"persists, power off the system and replace the "
"adapter\n");
/* write to clear the interrupt */
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP0);
}
}
static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr)
{
struct ixgbe_hw *hw = &adapter->hw;
if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) &&
(eicr & IXGBE_EICR_GPI_SDP1)) {
DPRINTK(PROBE, CRIT, "Fan has stopped, replace the adapter\n");
/* write to clear the interrupt */
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
}
}
static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
struct ixgbe_hw *hw = &adapter->hw;
if (eicr & IXGBE_EICR_GPI_SDP1) {
/* Clear the interrupt */
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
schedule_work(&adapter->multispeed_fiber_task);
} else if (eicr & IXGBE_EICR_GPI_SDP2) {
/* Clear the interrupt */
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
schedule_work(&adapter->sfp_config_module_task);
} else {
/* Interrupt isn't for us... */
return;
}
}
static void ixgbe_check_lsc(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
adapter->lsc_int++;
adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
adapter->link_check_timeout = jiffies;
if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC);
IXGBE_WRITE_FLUSH(hw);
schedule_work(&adapter->watchdog_task);
}
}
static irqreturn_t ixgbe_msix_lsc(int irq, void *data)
{
struct net_device *netdev = data;
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
u32 eicr;
/*
* Workaround for Silicon errata. Use clear-by-write instead
* of clear-by-read. Reading with EICS will return the
* interrupt causes without clearing, which later be done
* with the write to EICR.
*/
eicr = IXGBE_READ_REG(hw, IXGBE_EICS);
IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr);
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);
if (hw->mac.type == ixgbe_mac_82599EB) {
ixgbe_check_sfp_event(adapter, eicr);
adapter->interrupt_event = eicr;
if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)))
schedule_work(&adapter->check_overtemp_task);
/* Handle Flow Director Full threshold interrupt */
if (eicr & IXGBE_EICR_FLOW_DIR) {
int i;
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_FLOW_DIR);
/* Disable transmits before FDIR Re-initialization */
netif_tx_stop_all_queues(netdev);
for (i = 0; i < adapter->num_tx_queues; i++) {
struct ixgbe_ring *tx_ring =
adapter->tx_ring[i];
if (test_and_clear_bit(__IXGBE_FDIR_INIT_DONE,
&tx_ring->reinit_state))
schedule_work(&adapter->fdir_reinit_task);
}
}
}
if (!test_bit(__IXGBE_DOWN, &adapter->state))
IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_OTHER);
return IRQ_HANDLED;
}
static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
u64 qmask)
{
u32 mask;
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
} else {
mask = (qmask & 0xFFFFFFFF);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS_EX(0), mask);
mask = (qmask >> 32);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS_EX(1), mask);
}
/* skip the flush */
}
static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
u64 qmask)
{
u32 mask;
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask);
} else {
mask = (qmask & 0xFFFFFFFF);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), mask);
mask = (qmask >> 32);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), mask);
}
/* skip the flush */
}
static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *tx_ring;
int i, r_idx;
if (!q_vector->txr_count)
return IRQ_HANDLED;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
tx_ring = adapter->tx_ring[r_idx];
tx_ring->total_bytes = 0;
tx_ring->total_packets = 0;
r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
r_idx + 1);
}
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
}
/**
* ixgbe_msix_clean_rx - single unshared vector rx clean (all queues)
* @irq: unused
* @data: pointer to our q_vector struct for this interrupt vector
**/
static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *rx_ring;
int r_idx;
int i;
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
rx_ring = adapter->rx_ring[r_idx];
rx_ring->total_bytes = 0;
rx_ring->total_packets = 0;
r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
r_idx + 1);
}
if (!q_vector->rxr_count)
return IRQ_HANDLED;
/* disable interrupts on this vector only */
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
}
static irqreturn_t ixgbe_msix_clean_many(int irq, void *data)
{
struct ixgbe_q_vector *q_vector = data;
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *ring;
int r_idx;
int i;
if (!q_vector->txr_count && !q_vector->rxr_count)
return IRQ_HANDLED;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
ring = adapter->tx_ring[r_idx];
ring->total_bytes = 0;
ring->total_packets = 0;
r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
r_idx + 1);
}
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
ring = adapter->rx_ring[r_idx];
ring->total_bytes = 0;
ring->total_packets = 0;
r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
r_idx + 1);
}
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
return IRQ_HANDLED;
}
/**
* ixgbe_clean_rxonly - msix (aka one shot) rx clean routine
* @napi: napi struct with our devices info in it
* @budget: amount of work driver is allowed to do this pass, in packets
*
* This function is optimized for cleaning one queue only on a single
* q_vector!!!
**/
static int ixgbe_clean_rxonly(struct napi_struct *napi, int budget)
{
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *rx_ring = NULL;
int work_done = 0;
long r_idx;
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
rx_ring = adapter->rx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_rx_dca(adapter, rx_ring);
#endif
ixgbe_clean_rx_irq(q_vector, rx_ring, &work_done, budget);
/* If all Rx work done, exit the polling mode */
if (work_done < budget) {
napi_complete(napi);
if (adapter->rx_itr_setting & 1)
ixgbe_set_itr_msix(q_vector);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_enable_queues(adapter,
((u64)1 << q_vector->v_idx));
}
return work_done;
}
/**
* ixgbe_clean_rxtx_many - msix (aka one shot) rx clean routine
* @napi: napi struct with our devices info in it
* @budget: amount of work driver is allowed to do this pass, in packets
*
* This function will clean more than one rx queue associated with a
* q_vector.
**/
static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
{
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *ring = NULL;
int work_done = 0, i;
long r_idx;
bool tx_clean_complete = true;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
ring = adapter->tx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_tx_dca(adapter, ring);
#endif
tx_clean_complete &= ixgbe_clean_tx_irq(q_vector, ring);
r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
r_idx + 1);
}
/* attempt to distribute budget to each queue fairly, but don't allow
* the budget to go below 1 because we'll exit polling */
budget /= (q_vector->rxr_count ?: 1);
budget = max(budget, 1);
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
ring = adapter->rx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_rx_dca(adapter, ring);
#endif
ixgbe_clean_rx_irq(q_vector, ring, &work_done, budget);
r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
r_idx + 1);
}
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
ring = adapter->rx_ring[r_idx];
/* If all Rx work done, exit the polling mode */
if (work_done < budget) {
napi_complete(napi);
if (adapter->rx_itr_setting & 1)
ixgbe_set_itr_msix(q_vector);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_enable_queues(adapter,
((u64)1 << q_vector->v_idx));
return 0;
}
return work_done;
}
/**
* ixgbe_clean_txonly - msix (aka one shot) tx clean routine
* @napi: napi struct with our devices info in it
* @budget: amount of work driver is allowed to do this pass, in packets
*
* This function is optimized for cleaning one queue only on a single
* q_vector!!!
**/
static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
{
struct ixgbe_q_vector *q_vector =
container_of(napi, struct ixgbe_q_vector, napi);
struct ixgbe_adapter *adapter = q_vector->adapter;
struct ixgbe_ring *tx_ring = NULL;
int work_done = 0;
long r_idx;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
tx_ring = adapter->tx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
ixgbe_update_tx_dca(adapter, tx_ring);
#endif
if (!ixgbe_clean_tx_irq(q_vector, tx_ring))
work_done = budget;
/* If all Tx work done, exit the polling mode */
if (work_done < budget) {
napi_complete(napi);
if (adapter->tx_itr_setting & 1)
ixgbe_set_itr_msix(q_vector);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_enable_queues(adapter, ((u64)1 << q_vector->v_idx));
}
return work_done;
}
static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx,
int r_idx)
{
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
set_bit(r_idx, q_vector->rxr_idx);
q_vector->rxr_count++;
}
static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
int t_idx)
{
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
set_bit(t_idx, q_vector->txr_idx);
q_vector->txr_count++;
}
/**
* ixgbe_map_rings_to_vectors - Maps descriptor rings to vectors
* @adapter: board private structure to initialize
* @vectors: allotted vector count for descriptor rings
*
* This function maps descriptor rings to the queue-specific vectors
* we were allotted through the MSI-X enabling code. Ideally, we'd have
* one vector per ring/queue, but on a constrained vector budget, we
* group the rings as "efficiently" as possible. You would add new
* mapping configurations in here.
**/
static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter,
int vectors)
{
int v_start = 0;
int rxr_idx = 0, txr_idx = 0;
int rxr_remaining = adapter->num_rx_queues;
int txr_remaining = adapter->num_tx_queues;
int i, j;
int rqpv, tqpv;
int err = 0;
/* No mapping required if MSI-X is disabled. */
if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
goto out;
/*
* The ideal configuration...
* We have enough vectors to map one per queue.
*/
if (vectors == adapter->num_rx_queues + adapter->num_tx_queues) {
for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
map_vector_to_rxq(adapter, v_start, rxr_idx);
for (; txr_idx < txr_remaining; v_start++, txr_idx++)
map_vector_to_txq(adapter, v_start, txr_idx);
goto out;
}
/*
* If we don't have enough vectors for a 1-to-1
* mapping, we'll have to group them so there are
* multiple queues per vector.
*/
/* Re-adjusting *qpv takes care of the remainder. */
for (i = v_start; i < vectors; i++) {
rqpv = DIV_ROUND_UP(rxr_remaining, vectors - i);
for (j = 0; j < rqpv; j++) {
map_vector_to_rxq(adapter, i, rxr_idx);
rxr_idx++;
rxr_remaining--;
}
}
for (i = v_start; i < vectors; i++) {
tqpv = DIV_ROUND_UP(txr_remaining, vectors - i);
for (j = 0; j < tqpv; j++) {
map_vector_to_txq(adapter, i, txr_idx);
txr_idx++;
txr_remaining--;
}
}
out:
return err;
}
/**
* ixgbe_request_msix_irqs - Initialize MSI-X interrupts
* @adapter: board private structure
*
* ixgbe_request_msix_irqs allocates MSI-X vectors and requests
* interrupts from the kernel.
**/
static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
irqreturn_t (*handler)(int, void *);
int i, vector, q_vectors, err;
int ri=0, ti=0;
/* Decrement for Other and TCP Timer vectors */
q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
/* Map the Tx/Rx rings to the vectors we were allotted. */
err = ixgbe_map_rings_to_vectors(adapter, q_vectors);
if (err)
goto out;
#define SET_HANDLER(_v) ((!(_v)->rxr_count) ? &ixgbe_msix_clean_tx : \
(!(_v)->txr_count) ? &ixgbe_msix_clean_rx : \
&ixgbe_msix_clean_many)
for (vector = 0; vector < q_vectors; vector++) {
handler = SET_HANDLER(adapter->q_vector[vector]);
if(handler == &ixgbe_msix_clean_rx) {
sprintf(adapter->name[vector], "%s-%s-%d",
netdev->name, "rx", ri++);
}
else if(handler == &ixgbe_msix_clean_tx) {
sprintf(adapter->name[vector], "%s-%s-%d",
netdev->name, "tx", ti++);
}
else
sprintf(adapter->name[vector], "%s-%s-%d",
netdev->name, "TxRx", vector);
err = request_irq(adapter->msix_entries[vector].vector,
handler, 0, adapter->name[vector],
adapter->q_vector[vector]);
if (err) {
DPRINTK(PROBE, ERR,
"request_irq failed for MSIX interrupt "
"Error: %d\n", err);
goto free_queue_irqs;
}
}
sprintf(adapter->name[vector], "%s:lsc", netdev->name);
err = request_irq(adapter->msix_entries[vector].vector,
ixgbe_msix_lsc, 0, adapter->name[vector], netdev);
if (err) {
DPRINTK(PROBE, ERR,
"request_irq for msix_lsc failed: %d\n", err);
goto free_queue_irqs;
}
return 0;
free_queue_irqs:
for (i = vector - 1; i >= 0; i--)
free_irq(adapter->msix_entries[--vector].vector,
adapter->q_vector[i]);
adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED;
pci_disable_msix(adapter->pdev);
kfree(adapter->msix_entries);
adapter->msix_entries = NULL;
out:
return err;
}
static void ixgbe_set_itr(struct ixgbe_adapter *adapter)
{
struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
u8 current_itr;
u32 new_itr = q_vector->eitr;
struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
q_vector->tx_itr = ixgbe_update_itr(adapter, new_itr,
q_vector->tx_itr,
tx_ring->total_packets,
tx_ring->total_bytes);
q_vector->rx_itr = ixgbe_update_itr(adapter, new_itr,
q_vector->rx_itr,
rx_ring->total_packets,
rx_ring->total_bytes);
current_itr = max(q_vector->rx_itr, q_vector->tx_itr);
switch (current_itr) {
/* counts and packets in update_itr are dependent on these numbers */
case lowest_latency:
new_itr = 100000;
break;
case low_latency:
new_itr = 20000; /* aka hwitr = ~200 */
break;
case bulk_latency:
new_itr = 8000;
break;
default:
break;
}
if (new_itr != q_vector->eitr) {
/* do an exponential smoothing */
new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
/* save the algorithm value here, not the smoothed one */
q_vector->eitr = new_itr;
ixgbe_write_eitr(q_vector);
}
}
/**
* ixgbe_irq_enable - Enable default interrupt generation settings
* @adapter: board private structure
**/
static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter)
{
u32 mask;
mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);
if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
mask |= IXGBE_EIMS_GPI_SDP0;
if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
mask |= IXGBE_EIMS_GPI_SDP1;
if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
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)
mask |= IXGBE_EIMS_FLOW_DIR;
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_intr - legacy mode Interrupt Handler
* @irq: interrupt number
* @data: pointer to a network interface device structure
**/
static irqreturn_t ixgbe_intr(int irq, void *data)
{
struct net_device *netdev = data;
struct ixgbe_adapter *adapter = netdev_priv(netdev);
struct ixgbe_hw *hw = &adapter->hw;
struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
u32 eicr;
/*
* Workaround for silicon errata. Mask the interrupts
* before the read of EICR.
*/
IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK);
/* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read
* therefore no explict interrupt disable is necessary */
eicr = IXGBE_READ_REG(hw, IXGBE_EICR);
if (!eicr) {
/* shared interrupt alert!
* make sure interrupts are enabled because the read will
* have disabled interrupts due to EIAM */
ixgbe_irq_enable(adapter);
return IRQ_NONE; /* Not our interrupt */
}
if (eicr & IXGBE_EICR_LSC)
ixgbe_check_lsc(adapter);
if (hw->mac.type == ixgbe_mac_82599EB)
ixgbe_check_sfp_event(adapter, eicr);
ixgbe_check_fan_failure(adapter, eicr);
if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)))
schedule_work(&adapter->check_overtemp_task);
if (napi_schedule_prep(&(q_vector->napi))) {
adapter->tx_ring[0]->total_packets = 0;
adapter->tx_ring[0]->total_bytes = 0;
adapter->rx_ring[0]->total_packets = 0;
adapter->rx_ring[0]->total_bytes = 0;
/* would disable interrupts here but EIAM disabled it */
__napi_schedule(&(q_vector->napi));
}
return IRQ_HANDLED;
}
static inline void ixgbe_reset_q_vectors(struct ixgbe_adapter *adapter)
{
int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
for (i = 0; i < q_vectors; i++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[i];
bitmap_zero(q_vector->rxr_idx, MAX_RX_QUEUES);
bitmap_zero(q_vector->txr_idx, MAX_TX_QUEUES);
q_vector->rxr_count = 0;
q_vector->txr_count = 0;
}
}
/**
* ixgbe_request_irq - initialize interrupts
* @adapter: board private structure
*
* Attempts to configure interrupts using the best available
* capabilities of the hardware and kernel.
**/
static int ixgbe_request_irq(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
int err;
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
err = ixgbe_request_msix_irqs(adapter);
} else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) {
err = request_irq(adapter->pdev->irq, ixgbe_intr, 0,
netdev->name, netdev);
} else {
err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED,
netdev->name, netdev);
}
if (err)
DPRINTK(PROBE, ERR, "request_irq failed, Error %d\n", err);
return err;
}
static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
int i, q_vectors;
q_vectors = adapter->num_msix_vectors;
i = q_vectors - 1;
free_irq(adapter->msix_entries[i].vector, netdev);
i--;
for (; i >= 0; i--) {
free_irq(adapter->msix_entries[i].vector,
adapter->q_vector[i]);
}
ixgbe_reset_q_vectors(adapter);
} else {
free_irq(adapter->pdev->irq, netdev);
}
}
/**
* ixgbe_irq_disable - Mask off interrupt generation on the NIC
* @adapter: board private structure
**/
static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
{
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0);
} else {
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) {
int i;
for (i = 0; i < adapter->num_msix_vectors; i++)
synchronize_irq(adapter->msix_entries[i].vector);
} else {
synchronize_irq(adapter->pdev->irq);
}
}
/**
* ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts
*
**/
static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
IXGBE_WRITE_REG(hw, IXGBE_EITR(0),
EITR_INTS_PER_SEC_TO_REG(adapter->rx_eitr_param));
ixgbe_set_ivar(adapter, 0, 0, 0);
ixgbe_set_ivar(adapter, 1, 0, 0);
map_vector_to_rxq(adapter, 0, 0);
map_vector_to_txq(adapter, 0, 0);
DPRINTK(HW, INFO, "Legacy interrupt IVAR setup done\n");
}
/**
* ixgbe_configure_tx - Configure 8259x Transmit Unit after Reset
* @adapter: board private structure
*
* Configure the Tx unit of the MAC after a reset.
**/
static void ixgbe_configure_tx(struct ixgbe_adapter *adapter)
{
u64 tdba;
struct ixgbe_hw *hw = &adapter->hw;
u32 i, j, tdlen, txctrl;
/* Setup the HW Tx Head and Tail descriptor pointers */
for (i = 0; i < adapter->num_tx_queues; i++) {
struct ixgbe_ring *ring = adapter->tx_ring[i];
j = ring->reg_idx;
tdba = ring->dma;
tdlen = ring->count * sizeof(union ixgbe_adv_tx_desc);
IXGBE_WRITE_REG(hw, IXGBE_TDBAL(j),
(tdba & DMA_BIT_MASK(32)));
IXGBE_WRITE_REG(hw, IXGBE_TDBAH(j), (tdba >> 32));
IXGBE_WRITE_REG(hw, IXGBE_TDLEN(j), tdlen);
IXGBE_WRITE_REG(hw, IXGBE_TDH(j), 0);
IXGBE_WRITE_REG(hw, IXGBE_TDT(j), 0);
adapter->tx_ring[i]->head = IXGBE_TDH(j);
adapter->tx_ring[i]->tail = IXGBE_TDT(j);
/*
* Disable Tx Head Writeback RO bit, since this hoses
* bookkeeping if things aren't delivered in order.
*/
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(j));
break;
case ixgbe_mac_82599EB:
default:
txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(j));
break;
}
txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(j), txctrl);
break;
case ixgbe_mac_82599EB:
default:
IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(j), txctrl);
break;
}
}
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);
/* 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;
IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
}
}
#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2
static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring)
{
u32 srrctl;
int index;
struct ixgbe_ring_feature *feature = adapter->ring_feature;
index = rx_ring->reg_idx;
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
unsigned long mask;
mask = (unsigned long) feature[RING_F_RSS].mask;
index = index & mask;
}
srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(index));
srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK;
srrctl &= ~IXGBE_SRRCTL_BSIZEPKT_MASK;
srrctl |= (IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) &
IXGBE_SRRCTL_BSIZEHDR_MASK;
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
#if (PAGE_SIZE / 2) > IXGBE_MAX_RXBUFFER
srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
#else
srrctl |= (PAGE_SIZE / 2) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
#endif
srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
} else {
srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >>
IXGBE_SRRCTL_BSIZEPKT_SHIFT;
srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
}
IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(index), srrctl);
}
static u32 ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
{
u32 mrqc = 0;
int mask;
if (!(adapter->hw.mac.type == ixgbe_mac_82599EB))
return mrqc;
mask = adapter->flags & (IXGBE_FLAG_RSS_ENABLED
#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;
break;
#endif /* CONFIG_IXGBE_DCB */
default:
break;
}
return mrqc;
}
/**
* ixgbe_configure_rscctl - enable RSC for the indicated ring
* @adapter: address of board private structure
* @index: index of ring to set
**/
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;
/*
* we must limit the number of descriptors so that the
* total size of max desc * buf_len is not greater
* than 65535
*/
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
#if (MAX_SKB_FRAGS > 16)
rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
#elif (MAX_SKB_FRAGS > 8)
rscctrl |= IXGBE_RSCCTL_MAXDESC_8;
#elif (MAX_SKB_FRAGS > 4)
rscctrl |= IXGBE_RSCCTL_MAXDESC_4;
#else
rscctrl |= IXGBE_RSCCTL_MAXDESC_1;
#endif
} else {
if (rx_buf_len < IXGBE_RXBUFFER_4096)
rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
else if (rx_buf_len < IXGBE_RXBUFFER_8192)
rscctrl |= IXGBE_RSCCTL_MAXDESC_8;
else
rscctrl |= IXGBE_RSCCTL_MAXDESC_4;
}
IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(j), rscctrl);
}
/**
* ixgbe_configure_rx - Configure 8259x Receive Unit after Reset
* @adapter: board private structure
*
* Configure the Rx unit of the MAC after a reset.
**/
static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
{
u64 rdba;
struct ixgbe_hw *hw = &adapter->hw;
struct ixgbe_ring *rx_ring;
struct net_device *netdev = adapter->netdev;
int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
int i, j;
u32 rdlen, rxctrl, rxcsum;
static const u32 seed[10] = { 0xE291D73D, 0x1805EC6C, 0x2A94B30D,
0xA54F2BEC, 0xEA49AF7C, 0xE214AD3D, 0xB855AABE,
0x6A3E67EA, 0x14364D17, 0x3BED200D};
u32 fctrl, hlreg0;
u32 reta = 0, mrqc = 0;
u32 rdrxctl;
int rx_buf_len;
/* Decide whether to use packet split mode or not */
/* Do not use packet split if we're in SR-IOV Mode */
if (!adapter->num_vfs)
adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
/* Disable packet split due to 82599 erratum #45 */
if (hw->mac.type == ixgbe_mac_82599EB)
adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
/* Set the RX buffer length according to the mode */
if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
rx_buf_len = IXGBE_RX_HDR_SIZE;
if (hw->mac.type == ixgbe_mac_82599EB) {
/* PSRTYPE must be initialized in 82599 */
u32 psrtype = IXGBE_PSRTYPE_TCPHDR |
IXGBE_PSRTYPE_UDPHDR |
IXGBE_PSRTYPE_IPV4HDR |
IXGBE_PSRTYPE_IPV6HDR |
IXGBE_PSRTYPE_L2HDR;
IXGBE_WRITE_REG(hw,
IXGBE_PSRTYPE(adapter->num_vfs),
psrtype);
}
} else {
if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
(netdev->mtu <= ETH_DATA_LEN))
rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
else
rx_buf_len = ALIGN(max_frame, 1024);
}
fctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_FCTRL);
fctrl |= IXGBE_FCTRL_BAM;
fctrl |= IXGBE_FCTRL_DPF; /* discard pause frames when FC enabled */
fctrl |= IXGBE_FCTRL_PMCF;
IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCTRL, fctrl);
hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
if (adapter->netdev->mtu <= ETH_DATA_LEN)
hlreg0 &= ~IXGBE_HLREG0_JUMBOEN;
else
hlreg0 |= IXGBE_HLREG0_JUMBOEN;
#ifdef IXGBE_FCOE
if (netdev->features & NETIF_F_FCOE_MTU)
hlreg0 |= IXGBE_HLREG0_JUMBOEN;
#endif
IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);
rdlen = adapter->rx_ring[0]->count * sizeof(union ixgbe_adv_rx_desc);
/* disable receives while setting up the descriptors */
rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL);
IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN);
/*
* Setup the HW Rx Head and Tail Descriptor Pointers and
* the Base and Length of the Rx Descriptor Ring
*/
for (i = 0; i < adapter->num_rx_queues; i++) {
rx_ring = adapter->rx_ring[i];
rdba = rx_ring->dma;
j = rx_ring->reg_idx;
IXGBE_WRITE_REG(hw, IXGBE_RDBAL(j), (rdba & DMA_BIT_MASK(32)));
IXGBE_WRITE_REG(hw, IXGBE_RDBAH(j), (rdba >> 32));
IXGBE_WRITE_REG(hw, IXGBE_RDLEN(j), rdlen);
IXGBE_WRITE_REG(hw, IXGBE_RDH(j), 0);
IXGBE_WRITE_REG(hw, IXGBE_RDT(j), 0);
rx_ring->head = IXGBE_RDH(j);
rx_ring->tail = IXGBE_RDT(j);
rx_ring->rx_buf_len = rx_buf_len;
if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)
rx_ring->flags |= IXGBE_RING_RX_PS_ENABLED;
else
rx_ring->flags &= ~IXGBE_RING_RX_PS_ENABLED;
#ifdef IXGBE_FCOE
if (netdev->features & NETIF_F_FCOE_MTU) {
struct ixgbe_ring_feature *f;
f = &adapter->ring_feature[RING_F_FCOE];
if ((i >= f->mask) && (i < f->mask + f->indices)) {
rx_ring->flags &= ~IXGBE_RING_RX_PS_ENABLED;
if (rx_buf_len < IXGBE_FCOE_JUMBO_FRAME_SIZE)
rx_ring->rx_buf_len =
IXGBE_FCOE_JUMBO_FRAME_SIZE;
}
}
#endif /* IXGBE_FCOE */
ixgbe_configure_srrctl(adapter, rx_ring);
}
if (hw->mac.type == ixgbe_mac_82598EB) {
/*
* For VMDq support of different descriptor types or
* buffer sizes through the use of multiple SRRCTL
* registers, RDRXCTL.MVMEN must be set to 1
*
* also, the manual doesn't mention it clearly but DCA hints
* will only use queue 0's tags unless this bit is set. Side
* effects of setting this bit are only that SRRCTL must be
* fully programmed [0..15]
*/
rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);
rdrxctl |= IXGBE_RDRXCTL_MVMEN;
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, true);
}
/* Program MRQC for the distribution of queues */
mrqc = ixgbe_setup_mrqc(adapter);
if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
/* Fill out redirection table */
for (i = 0, j = 0; i < 128; i++, j++) {
if (j == adapter->ring_feature[RING_F_RSS].indices)
j = 0;
/* reta = 4-byte sliding window of
* 0x00..(indices-1)(indices-1)00..etc. */
reta = (reta << 8) | (j * 0x11);
if ((i & 3) == 3)
IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta);
}
/* Fill out hash function seeds */
for (i = 0; i < 10; i++)
IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), seed[i]);
if (hw->mac.type == ixgbe_mac_82598EB)
mrqc |= IXGBE_MRQC_RSSEN;
/* Perform hash on these packet types */
mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4
| IXGBE_MRQC_RSS_FIELD_IPV4_TCP
| IXGBE_MRQC_RSS_FIELD_IPV4_UDP
| IXGBE_MRQC_RSS_FIELD_IPV6
| IXGBE_MRQC_RSS_FIELD_IPV6_TCP
| IXGBE_MRQC_RSS_FIELD_IPV6_UDP;
}
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 ||
adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED) {
/* Disable indicating checksum in descriptor, enables
* RSS hash */
rxcsum |= IXGBE_RXCSUM_PCSD;
}
if (!(rxcsum & IXGBE_RXCSUM_PCSD)) {
/* Enable IPv4 payload checksum for UDP fragments
* if PCSD is not set */
rxcsum |= IXGBE_RXCSUM_IPPCSE;
}
IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum);
if (hw->mac.type == ixgbe_mac_82599EB) {
rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);
rdrxctl |= IXGBE_RDRXCTL_CRCSTRIP;
rdrxctl &= ~IXGBE_RDRXCTL_RSCFRSTSIZE;
IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
}
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);
/* Disable RSC for ACK packets */
IXGBE_WRITE_REG(hw, IXGBE_RSCDBU,
(IXGBE_RSCDBU_RSCACKDIS | IXGBE_READ_REG(hw, IXGBE_RSCDBU)));
}
}
static void ixgbe_vlan_rx_add_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;
/* add VID to filter table */
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);
vlan_group_set_device(adapter->vlgrp, vid, NULL);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_enable(adapter);
/* remove VID from filter table */
hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false);
}
/**
* ixgbe_vlan_filter_disable - helper to disable hw vlan filtering
* @adapter: driver data
*/
static void ixgbe_vlan_filter_disable(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
int i, j;
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
vlnctrl &= ~IXGBE_VLNCTRL_VFE;
#ifdef CONFIG_IXGBE_DCB
if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED))
vlnctrl &= ~IXGBE_VLNCTRL_VME;
#endif
vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
break;
case ixgbe_mac_82599EB:
vlnctrl &= ~IXGBE_VLNCTRL_VFE;
vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
#ifdef CONFIG_IXGBE_DCB
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
break;
#endif
for (i = 0; i < adapter->num_rx_queues; i++) {
j = adapter->rx_ring[i]->reg_idx;
vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
vlnctrl &= ~IXGBE_RXDCTL_VME;
IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
}
break;
default:
break;
}
}
/**
* ixgbe_vlan_filter_enable - helper to enable hw vlan filtering
* @adapter: driver data
*/
static void ixgbe_vlan_filter_enable(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
int i, j;
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
vlnctrl |= IXGBE_VLNCTRL_VME | IXGBE_VLNCTRL_VFE;
vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
break;
case ixgbe_mac_82599EB:
vlnctrl |= IXGBE_VLNCTRL_VFE;
vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
for (i = 0; i < adapter->num_rx_queues; i++) {
j = adapter->rx_ring[i]->reg_idx;
vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
vlnctrl |= IXGBE_RXDCTL_VME;
IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl);
}
break;
default:
break;
}
}
static void ixgbe_vlan_rx_register(struct net_device *netdev,
struct vlan_group *grp)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_disable(adapter);
adapter->vlgrp = grp;
/*
* For a DCB driver, always enable VLAN tag stripping so we can
* still receive traffic from a DCB-enabled host even if we're
* not in DCB mode.
*/
ixgbe_vlan_filter_enable(adapter);
ixgbe_vlan_rx_add_vid(netdev, 0);
if (!test_bit(__IXGBE_DOWN, &adapter->state))
ixgbe_irq_enable(adapter);
}
static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
{