aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_main.c')
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c7934
1 files changed, 7934 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
new file mode 100644
index 00000000000..e86297b3273
--- /dev/null
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -0,0 +1,7934 @@
+/*******************************************************************************
+
+ Intel 10 Gigabit PCI Express Linux driver
+ Copyright(c) 1999 - 2011 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/interrupt.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/sctp.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 <linux/prefetch.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 MAJ 3
+#define MIN 4
+#define BUILD 8
+#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
+ __stringify(BUILD) "-k"
+const char ixgbe_driver_version[] = DRV_VERSION;
+static const char ixgbe_copyright[] =
+ "Copyright (c) 1999-2011 Intel Corporation.";
+
+static const struct ixgbe_info *ixgbe_info_tbl[] = {
+ [board_82598] = &ixgbe_82598_info,
+ [board_82599] = &ixgbe_82599_info,
+ [board_X540] = &ixgbe_X540_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_BACKPLANE_FCOE),
+ board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE),
+ board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM),
+ board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE),
+ board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T),
+ board_X540 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2),
+ board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS),
+ 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);
+ IXGBE_WRITE_FLUSH(hw);
+
+ /* take a breather then clean up driver data */
+ msleep(100);
+
+ kfree(adapter->vfinfo);
+ adapter->vfinfo = NULL;
+
+ adapter->num_vfs = 0;
+ adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+}
+
+static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter)
+{
+ if (!test_bit(__IXGBE_DOWN, &adapter->state) &&
+ !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state))
+ schedule_work(&adapter->service_task);
+}
+
+static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
+{
+ BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));
+
+ /* flush memory to make sure state is correct before next watchog */
+ smp_mb__before_clear_bit();
+ clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
+}
+
+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:
+ pr_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);
+ pr_err("%-15s", rname);
+ for (j = 0; j < 8; j++)
+ pr_cont(" %08x", regs[i*8+j]);
+ pr_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");
+ pr_info("Device Name state "
+ "trans_start last_rx\n");
+ pr_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");
+ pr_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");
+ pr_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];
+ pr_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];
+ pr_info("------------------------------------\n");
+ pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
+ pr_info("------------------------------------\n");
+ pr_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;
+ pr_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)
+ pr_cont(" NTC/U\n");
+ else if (i == tx_ring->next_to_use)
+ pr_cont(" NTU\n");
+ else if (i == tx_ring->next_to_clean)
+ pr_cont(" NTC\n");
+ else
+ pr_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");
+ pr_info("Queue [NTU] [NTC]\n");
+ for (n = 0; n < adapter->num_rx_queues; n++) {
+ rx_ring = adapter->rx_ring[n];
+ pr_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];
+ pr_info("------------------------------------\n");
+ pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
+ pr_info("------------------------------------\n");
+ pr_info("R [desc] [ PktBuf A0] "
+ "[ HeadBuf DD] [bi->dma ] [bi->skb] "
+ "<-- Adv Rx Read format\n");
+ pr_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 */
+ pr_info("RWB[0x%03X] %016llX "
+ "%016llX ---------------- %p", i,
+ le64_to_cpu(u0->a),
+ le64_to_cpu(u0->b),
+ rx_buffer_info->skb);
+ } else {
+ pr_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)
+ pr_cont(" NTU\n");
+ else if (i == rx_ring->next_to_clean)
+ pr_cont(" NTC\n");
+ else
+ pr_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:
+ case ixgbe_mac_X540:
+ 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;
+
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
+ mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ 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);
+ break;
+ default:
+ break;
+ }
+}
+
+void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring,
+ struct ixgbe_tx_buffer *tx_buffer_info)
+{
+ if (tx_buffer_info->dma) {
+ if (tx_buffer_info->mapped_as_page)
+ dma_unmap_page(tx_ring->dev,
+ tx_buffer_info->dma,
+ tx_buffer_info->length,
+ DMA_TO_DEVICE);
+ else
+ dma_unmap_single(tx_ring->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 */
+}
+
+static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ struct ixgbe_hw_stats *hwstats = &adapter->stats;
+ u32 data = 0;
+ u32 xoff[8] = {0};
+ int i;
+
+ if ((hw->fc.current_mode == ixgbe_fc_full) ||
+ (hw->fc.current_mode == ixgbe_fc_rx_pause)) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
+ break;
+ default:
+ data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
+ }
+ hwstats->lxoffrxc += data;
+
+ /* refill credits (no tx hang) if we received xoff */
+ if (!data)
+ return;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ clear_bit(__IXGBE_HANG_CHECK_ARMED,
+ &adapter->tx_ring[i]->state);
+ return;
+ } else if (!(adapter->dcb_cfg.pfc_mode_enable))
+ return;
+
+ /* update stats for each tc, only valid with PFC enabled */
+ for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
+ break;
+ default:
+ xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
+ }
+ hwstats->pxoffrxc[i] += xoff[i];
+ }
+
+ /* disarm tx queues that have received xoff frames */
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+ u8 tc = tx_ring->dcb_tc;
+
+ if (xoff[tc])
+ clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
+ }
+}
+
+static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
+{
+ return ring->tx_stats.completed;
+}
+
+static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(ring->netdev);
+ struct ixgbe_hw *hw = &adapter->hw;
+
+ u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
+ u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));
+
+ if (head != tail)
+ return (head < tail) ?
+ tail - head : (tail + ring->count - head);
+
+ return 0;
+}
+
+static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
+{
+ u32 tx_done = ixgbe_get_tx_completed(tx_ring);
+ u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
+ u32 tx_pending = ixgbe_get_tx_pending(tx_ring);
+ bool ret = false;
+
+ clear_check_for_tx_hang(tx_ring);
+
+ /*
+ * Check for a hung queue, but be thorough. This verifies
+ * that a transmit has been completed since the previous
+ * check AND there is at least one packet pending. The
+ * ARMED bit is set to indicate a potential hang. The
+ * bit is cleared if a pause frame is received to remove
+ * false hang detection due to PFC or 802.3x frames. By
+ * requiring this to fail twice we avoid races with
+ * pfc clearing the ARMED bit and conditions where we
+ * run the check_tx_hang logic with a transmit completion
+ * pending but without time to complete it yet.
+ */
+ if ((tx_done_old == tx_done) && tx_pending) {
+ /* make sure it is true for two checks in a row */
+ ret = test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
+ &tx_ring->state);
+ } else {
+ /* update completed stats and continue */
+ tx_ring->tx_stats.tx_done_old = tx_done;
+ /* reset the countdown */
+ clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
+ }
+
+ return ret;
+}
+
+/**
+ * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout
+ * @adapter: driver private struct
+ **/
+static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter)
+{
+
+ /* Do the reset outside of interrupt context */
+ if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
+ adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
+ ixgbe_service_event_schedule(adapter);
+ }
+}
+
+/**
+ * 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;
+ union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
+ struct ixgbe_tx_buffer *tx_buffer_info;
+ unsigned int total_bytes = 0, total_packets = 0;
+ u16 i, eop, count = 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 < q_vector->tx.work_limit)) {
+ bool cleaned = false;
+ rmb(); /* read buffer_info after eop_desc */
+ for ( ; !cleaned; count++) {
+ tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i);
+ tx_buffer_info = &tx_ring->tx_buffer_info[i];
+
+ tx_desc->wb.status = 0;
+ cleaned = (i == eop);
+
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
+ if (cleaned && tx_buffer_info->skb) {
+ total_bytes += tx_buffer_info->bytecount;
+ total_packets += tx_buffer_info->gso_segs;
+ }
+
+ ixgbe_unmap_and_free_tx_resource(tx_ring,
+ tx_buffer_info);
+ }
+
+ tx_ring->tx_stats.completed++;
+ 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;
+ tx_ring->stats.bytes += total_bytes;
+ tx_ring->stats.packets += total_packets;
+ u64_stats_update_begin(&tx_ring->syncp);
+ q_vector->tx.total_bytes += total_bytes;
+ q_vector->tx.total_packets += total_packets;
+ u64_stats_update_end(&tx_ring->syncp);
+
+ if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
+ /* schedule immediate reset if we believe we hung */
+ struct ixgbe_hw *hw = &adapter->hw;
+ tx_desc = IXGBE_TX_DESC_ADV(tx_ring, eop);
+ e_err(drv, "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, IXGBE_TDH(tx_ring->reg_idx)),
+ IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
+ tx_ring->next_to_use, eop,
+ tx_ring->tx_buffer_info[eop].time_stamp, jiffies);
+
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+ e_info(probe,
+ "tx hang %d detected on queue %d, resetting adapter\n",
+ adapter->tx_timeout_count + 1, tx_ring->queue_index);
+
+ /* schedule immediate reset if we believe we hung */
+ ixgbe_tx_timeout_reset(adapter);
+
+ /* the adapter is about to reset, no point in enabling stuff */
+ return true;
+ }
+
+#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
+ if (unlikely(count && netif_carrier_ok(tx_ring->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(tx_ring->netdev, tx_ring->queue_index) &&
+ !test_bit(__IXGBE_DOWN, &adapter->state)) {
+ netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index);
+ ++tx_ring->tx_stats.restart_queue;
+ }
+ }
+
+ return count < q_vector->tx.work_limit;
+}
+
+#ifdef CONFIG_IXGBE_DCA
+static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *rx_ring,
+ int cpu)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 rxctrl;
+ u8 reg_idx = rx_ring->reg_idx;
+
+ rxctrl = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(reg_idx));
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK;
+ rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599;
+ rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
+ IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599);
+ break;
+ default:
+ break;
+ }
+ rxctrl |= IXGBE_DCA_RXCTRL_DESC_DCA_EN;
+ rxctrl |= IXGBE_DCA_RXCTRL_HEAD_DCA_EN;
+ rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_RRO_EN);
+ IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl);
+}
+
+static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *tx_ring,
+ int cpu)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 txctrl;
+ u8 reg_idx = tx_ring->reg_idx;
+
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(reg_idx));
+ 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(reg_idx), txctrl);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx));
+ 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(reg_idx), txctrl);
+ break;
+ default:
+ break;
+ }
+}
+
+static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
+{
+ struct ixgbe_adapter *adapter = q_vector->adapter;
+ int cpu = get_cpu();
+ long r_idx;
+ int i;
+
+ if (q_vector->cpu == cpu)
+ goto out_no_update;
+
+ r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
+ for (i = 0; i < q_vector->tx.count; i++) {
+ ixgbe_update_tx_dca(adapter, adapter->tx_ring[r_idx], cpu);
+ r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
+ r_idx + 1);
+ }
+
+ r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
+ for (i = 0; i < q_vector->rx.count; i++) {
+ ixgbe_update_rx_dca(adapter, adapter->rx_ring[r_idx], cpu);
+ r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
+ r_idx + 1);
+ }
+
+ q_vector->cpu = cpu;
+out_no_update:
+ put_cpu();
+}
+
+static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
+{
+ int num_q_vectors;
+ 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);
+
+ if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
+ num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ else
+ num_q_vectors = 1;
+
+ for (i = 0; i < num_q_vectors; i++) {
+ adapter->q_vector[i]->cpu = -1;
+ ixgbe_update_dca(adapter->q_vector[i]);
+ }
+}
+
+static int __ixgbe_notify_dca(struct device *dev, void *data)
+{
+ struct ixgbe_adapter *adapter = dev_get_drvdata(dev);
+ unsigned long event = *(unsigned long *)data;
+
+ if (!(adapter->flags & IXGBE_FLAG_DCA_CAPABLE))
+ return 0;
+
+ 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 */
+
+static inline void ixgbe_rx_hash(union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb)
+{
+ skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+}
+
+/**
+ * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type
+ * @adapter: address of board private structure
+ * @rx_desc: advanced rx descriptor
+ *
+ * Returns : true if it is FCoE pkt
+ */
+static inline bool ixgbe_rx_is_fcoe(struct ixgbe_adapter *adapter,
+ union ixgbe_adv_rx_desc *rx_desc)
+{
+ __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
+
+ return (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
+ ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) ==
+ (cpu_to_le16(IXGBE_ETQF_FILTER_FCOE <<
+ IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT)));
+}
+
+/**
+ * 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);
+
+ if (is_vlan && (tag & VLAN_VID_MASK))
+ __vlan_hwaccel_put_tag(skb, tag);
+
+ if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
+ napi_gro_receive(napi, skb);
+ 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
+ * @status_err: status error value of last descriptor in packet
+ **/
+static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter,
+ union ixgbe_adv_rx_desc *rx_desc,
+ struct sk_buff *skb,
+ u32 status_err)
+{
+ 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_TC