[RFC PATCH v2 01/12] ixgbevf: Macros, data structures, useful defines and registers

[RFC PATCH v2 01/12] ixgbevf: Macros, data structures, useful defines and registers

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

These two headers define the commonly used macros, data structures,
register bits and register offsets used by the ixgbevf driver on the
82599 virtual function device

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbevf/defines.h |  301 +++++++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbevf/regs.h    |   85 ++++++++++++
 2 files changed, 386 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbevf/defines.h
 create mode 100644 drivers/net/ixgbevf/regs.h

diff --git a/drivers/net/ixgbevf/defines.h b/drivers/net/ixgbevf/defines.h
new file mode 100644
index 0000000..b111771
--- /dev/null
+++ b/drivers/net/ixgbevf/defines.h
@@ -0,0 +1,301 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBEVF_DEFINES_H_
+#define _IXGBEVF_DEFINES_H_
+
+/* Device IDs */
+#define IXGBE_DEV_ID_82599_VF           0x10ED
+
+#define IXGBE_VF_IRQ_CLEAR_MASK         7
+#define IXGBE_VF_MAX_TX_QUEUES          1
+#define IXGBE_VF_MAX_RX_QUEUES          1
+#define IXGBE_ETH_LENGTH_OF_ADDRESS     6
+
+/* Link speed */
+typedef u32 ixgbe_link_speed;
+#define IXGBE_LINK_SPEED_1GB_FULL       0x0020
+#define IXGBE_LINK_SPEED_10GB_FULL      0x0080
+
+#define IXGBE_CTRL_RST          0x04000000 /* Reset (SW) */
+#define IXGBE_RXDCTL_ENABLE     0x02000000 /* Enable specific Rx Queue */
+#define IXGBE_TXDCTL_ENABLE     0x02000000 /* Enable specific Tx Queue */
+#define IXGBE_LINKS_UP          0x40000000
+#define IXGBE_LINKS_SPEED       0x20000000
+
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE  8
+#define IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE  8
+#define IXGBE_REQ_TX_BUFFER_GRANULARITY   1024
+
+/* Interrupt Vector Allocation Registers */
+#define IXGBE_IVAR_ALLOC_VAL    0x80 /* Interrupt Allocation valid */
+
+#define IXGBE_VF_INIT_TIMEOUT   200 /* Number of retries to clear RSTI */
+
+/* Receive Config masks */
+#define IXGBE_RXCTRL_RXEN       0x00000001  /* Enable Receiver */
+#define IXGBE_RXCTRL_DMBYPS     0x00000002  /* Descriptor Monitor Bypass */
+#define IXGBE_RXDCTL_ENABLE     0x02000000  /* Enable specific Rx Queue */
+#define IXGBE_RXDCTL_VME        0x40000000  /* VLAN mode enable */
+
+/* DCA Control */
+#define IXGBE_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */
+
+/* Check whether address is multicast.  This is little-endian specific check.*/
+#define IXGBE_IS_MULTICAST(Address) \
+	(bool)(((u8 *)(Address))[0] & ((u8)0x01))
+
+/* Check whether an address is broadcast. */
+#define IXGBE_IS_BROADCAST(Address)              \
+	((((u8 *)(Address))[0] == ((u8)0xFF)) && \
+	 (((u8 *)(Address))[1] == ((u8)0xFF)))
+
+/* PSRTYPE bit definitions */
+#define IXGBE_PSRTYPE_TCPHDR    0x00000010
+#define IXGBE_PSRTYPE_UDPHDR    0x00000020
+#define IXGBE_PSRTYPE_IPV4HDR   0x00000100
+#define IXGBE_PSRTYPE_IPV6HDR   0x00000200
+#define IXGBE_PSRTYPE_L2HDR     0x00001000
+
+/* SRRCTL bit definitions */
+#define IXGBE_SRRCTL_BSIZEPKT_SHIFT     10     /* so many KBs */
+#define IXGBE_SRRCTL_RDMTS_SHIFT        22
+#define IXGBE_SRRCTL_RDMTS_MASK         0x01C00000
+#define IXGBE_SRRCTL_DROP_EN            0x10000000
+#define IXGBE_SRRCTL_BSIZEPKT_MASK      0x0000007F
+#define IXGBE_SRRCTL_BSIZEHDR_MASK      0x00003F00
+#define IXGBE_SRRCTL_DESCTYPE_LEGACY    0x00000000
+#define IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000
+#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT  0x04000000
+#define IXGBE_SRRCTL_DESCTYPE_HDR_REPLICATION_LARGE_PKT 0x08000000
+#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS 0x0A000000
+#define IXGBE_SRRCTL_DESCTYPE_MASK      0x0E000000
+
+/* Receive Descriptor bit definitions */
+#define IXGBE_RXD_STAT_DD         0x01    /* Descriptor Done */
+#define IXGBE_RXD_STAT_EOP        0x02    /* End of Packet */
+#define IXGBE_RXD_STAT_FLM        0x04    /* FDir Match */
+#define IXGBE_RXD_STAT_VP         0x08    /* IEEE VLAN Packet */
+#define IXGBE_RXDADV_NEXTP_MASK   0x000FFFF0 /* Next Descriptor Index */
+#define IXGBE_RXDADV_NEXTP_SHIFT  0x00000004
+#define IXGBE_RXD_STAT_UDPCS      0x10    /* UDP xsum calculated */
+#define IXGBE_RXD_STAT_L4CS       0x20    /* L4 xsum calculated */
+#define IXGBE_RXD_STAT_IPCS       0x40    /* IP xsum calculated */
+#define IXGBE_RXD_STAT_PIF        0x80    /* passed in-exact filter */
+#define IXGBE_RXD_STAT_CRCV       0x100   /* Speculative CRC Valid */
+#define IXGBE_RXD_STAT_VEXT       0x200   /* 1st VLAN found */
+#define IXGBE_RXD_STAT_UDPV       0x400   /* Valid UDP checksum */
+#define IXGBE_RXD_STAT_DYNINT     0x800   /* Pkt caused INT via DYNINT */
+#define IXGBE_RXD_STAT_TS         0x10000 /* Time Stamp */
+#define IXGBE_RXD_STAT_SECP       0x20000 /* Security Processing */
+#define IXGBE_RXD_STAT_LB         0x40000 /* Loopback Status */
+#define IXGBE_RXD_STAT_ACK        0x8000  /* ACK Packet indication */
+#define IXGBE_RXD_ERR_CE          0x01    /* CRC Error */
+#define IXGBE_RXD_ERR_LE          0x02    /* Length Error */
+#define IXGBE_RXD_ERR_PE          0x08    /* Packet Error */
+#define IXGBE_RXD_ERR_OSE         0x10    /* Oversize Error */
+#define IXGBE_RXD_ERR_USE         0x20    /* Undersize Error */
+#define IXGBE_RXD_ERR_TCPE        0x40    /* TCP/UDP Checksum Error */
+#define IXGBE_RXD_ERR_IPE         0x80    /* IP Checksum Error */
+#define IXGBE_RXDADV_ERR_MASK     0xFFF00000 /* RDESC.ERRORS mask */
+#define IXGBE_RXDADV_ERR_SHIFT    20         /* RDESC.ERRORS shift */
+#define IXGBE_RXDADV_ERR_HBO      0x00800000 /*Header Buffer Overflow */
+#define IXGBE_RXDADV_ERR_CE       0x01000000 /* CRC Error */
+#define IXGBE_RXDADV_ERR_LE       0x02000000 /* Length Error */
+#define IXGBE_RXDADV_ERR_PE       0x08000000 /* Packet Error */
+#define IXGBE_RXDADV_ERR_OSE      0x10000000 /* Oversize Error */
+#define IXGBE_RXDADV_ERR_USE      0x20000000 /* Undersize Error */
+#define IXGBE_RXDADV_ERR_TCPE     0x40000000 /* TCP/UDP Checksum Error */
+#define IXGBE_RXDADV_ERR_IPE      0x80000000 /* IP Checksum Error */
+#define IXGBE_RXD_VLAN_ID_MASK    0x0FFF  /* VLAN ID is in lower 12 bits */
+#define IXGBE_RXD_PRI_MASK        0xE000  /* Priority is in upper 3 bits */
+#define IXGBE_RXD_PRI_SHIFT       13
+#define IXGBE_RXD_CFI_MASK        0x1000  /* CFI is bit 12 */
+#define IXGBE_RXD_CFI_SHIFT       12
+
+#define IXGBE_RXDADV_STAT_DD            IXGBE_RXD_STAT_DD  /* Done */
+#define IXGBE_RXDADV_STAT_EOP           IXGBE_RXD_STAT_EOP /* End of Packet */
+#define IXGBE_RXDADV_STAT_FLM           IXGBE_RXD_STAT_FLM /* FDir Match */
+#define IXGBE_RXDADV_STAT_VP            IXGBE_RXD_STAT_VP  /* IEEE VLAN Pkt */
+#define IXGBE_RXDADV_STAT_MASK          0x000FFFFF /* Stat/NEXTP: bit 0-19 */
+#define IXGBE_RXDADV_STAT_FCEOFS        0x00000040 /* FCoE EOF/SOF Stat */
+#define IXGBE_RXDADV_STAT_FCSTAT        0x00000030 /* FCoE Pkt Stat */
+#define IXGBE_RXDADV_STAT_FCSTAT_NOMTCH 0x00000000 /* 00: No Ctxt Match */
+#define IXGBE_RXDADV_STAT_FCSTAT_NODDP  0x00000010 /* 01: Ctxt w/o DDP */
+#define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */
+#define IXGBE_RXDADV_STAT_FCSTAT_DDP    0x00000030 /* 11: Ctxt w/ DDP */
+
+#define IXGBE_RXDADV_RSSTYPE_MASK       0x0000000F
+#define IXGBE_RXDADV_PKTTYPE_MASK       0x0000FFF0
+#define IXGBE_RXDADV_PKTTYPE_MASK_EX    0x0001FFF0
+#define IXGBE_RXDADV_HDRBUFLEN_MASK     0x00007FE0
+#define IXGBE_RXDADV_RSCCNT_MASK        0x001E0000
+#define IXGBE_RXDADV_RSCCNT_SHIFT       17
+#define IXGBE_RXDADV_HDRBUFLEN_SHIFT    5
+#define IXGBE_RXDADV_SPLITHEADER_EN     0x00001000
+#define IXGBE_RXDADV_SPH                0x8000
+
+#define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \
+				      IXGBE_RXD_ERR_CE |  \
+				      IXGBE_RXD_ERR_LE |  \
+				      IXGBE_RXD_ERR_PE |  \
+				      IXGBE_RXD_ERR_OSE | \
+				      IXGBE_RXD_ERR_USE)
+
+#define IXGBE_RXDADV_ERR_FRAME_ERR_MASK ( \
+					 IXGBE_RXDADV_ERR_CE |  \
+					 IXGBE_RXDADV_ERR_LE |  \
+					 IXGBE_RXDADV_ERR_PE |  \
+					 IXGBE_RXDADV_ERR_OSE | \
+					 IXGBE_RXDADV_ERR_USE)
+
+#define IXGBE_TXD_POPTS_IXSM 0x01       /* Insert IP checksum */
+#define IXGBE_TXD_POPTS_TXSM 0x02       /* Insert TCP/UDP checksum */
+#define IXGBE_TXD_CMD_EOP    0x01000000 /* End of Packet */
+#define IXGBE_TXD_CMD_IFCS   0x02000000 /* Insert FCS (Ethernet CRC) */
+#define IXGBE_TXD_CMD_IC     0x04000000 /* Insert Checksum */
+#define IXGBE_TXD_CMD_RS     0x08000000 /* Report Status */
+#define IXGBE_TXD_CMD_DEXT   0x20000000 /* Descriptor extension (0 = legacy) */
+#define IXGBE_TXD_CMD_VLE    0x40000000 /* Add VLAN tag */
+#define IXGBE_TXD_STAT_DD    0x00000001 /* Descriptor Done */
+
+/* Transmit Descriptor - Advanced */
+union ixgbe_adv_tx_desc {
+	struct {
+		__le64 buffer_addr;      /* Address of descriptor's data buf */
+		__le32 cmd_type_len;
+		__le32 olinfo_status;
+	} read;
+	struct {
+		__le64 rsvd;       /* Reserved */
+		__le32 nxtseq_seed;
+		__le32 status;
+	} wb;
+};
+
+/* Receive Descriptor - Advanced */
+union ixgbe_adv_rx_desc {
+	struct {
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
+	} read;
+	struct {
+		struct {
+			union {
+				__le32 data;
+				struct {
+					__le16 pkt_info; /* RSS, Pkt type */
+					__le16 hdr_info; /* Splithdr, hdrlen */
+				} hs_rss;
+			} lo_dword;
+			union {
+				__le32 rss; /* RSS Hash */
+				struct {
+					__le16 ip_id; /* IP id */
+					__le16 csum; /* Packet Checksum */
+				} csum_ip;
+			} hi_dword;
+		} lower;
+		struct {
+			__le32 status_error; /* ext status/error */
+			__le16 length; /* Packet length */
+			__le16 vlan; /* VLAN tag */
+		} upper;
+	} wb;  /* writeback */
+};
+
+/* Context descriptors */
+struct ixgbe_adv_tx_context_desc {
+	__le32 vlan_macip_lens;
+	__le32 seqnum_seed;
+	__le32 type_tucmd_mlhl;
+	__le32 mss_l4len_idx;
+};
+
+/* Adv Transmit Descriptor Config Masks */
+#define IXGBE_ADVTXD_DTYP_MASK  0x00F00000 /* DTYP mask */
+#define IXGBE_ADVTXD_DTYP_CTXT  0x00200000 /* Advanced Context Desc */
+#define IXGBE_ADVTXD_DTYP_DATA  0x00300000 /* Advanced Data Descriptor */
+#define IXGBE_ADVTXD_DCMD_EOP   IXGBE_TXD_CMD_EOP  /* End of Packet */
+#define IXGBE_ADVTXD_DCMD_IFCS  IXGBE_TXD_CMD_IFCS /* Insert FCS */
+#define IXGBE_ADVTXD_DCMD_RS    IXGBE_TXD_CMD_RS   /* Report Status */
+#define IXGBE_ADVTXD_DCMD_DEXT  IXGBE_TXD_CMD_DEXT /* Desc ext (1=Adv) */
+#define IXGBE_ADVTXD_DCMD_VLE   IXGBE_TXD_CMD_VLE  /* VLAN pkt enable */
+#define IXGBE_ADVTXD_DCMD_TSE   0x80000000 /* TCP Seg enable */
+#define IXGBE_ADVTXD_STAT_DD    IXGBE_TXD_STAT_DD  /* Descriptor Done */
+#define IXGBE_ADVTXD_TUCMD_IPV4      0x00000400  /* IP Packet Type: 1=IPv4 */
+#define IXGBE_ADVTXD_TUCMD_IPV6      0x00000000  /* IP Packet Type: 0=IPv6 */
+#define IXGBE_ADVTXD_TUCMD_L4T_UDP   0x00000000  /* L4 Packet TYPE of UDP */
+#define IXGBE_ADVTXD_TUCMD_L4T_TCP   0x00000800  /* L4 Packet TYPE of TCP */
+#define IXGBE_ADVTXD_TUCMD_L4T_SCTP  0x00001000  /* L4 Packet TYPE of SCTP */
+#define IXGBE_ADVTXD_IDX_SHIFT  4 /* Adv desc Index shift */
+#define IXGBE_ADVTXD_POPTS_SHIFT      8  /* Adv desc POPTS shift */
+#define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \
+				 IXGBE_ADVTXD_POPTS_SHIFT)
+#define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \
+				 IXGBE_ADVTXD_POPTS_SHIFT)
+#define IXGBE_ADVTXD_PAYLEN_SHIFT    14 /* Adv desc PAYLEN shift */
+#define IXGBE_ADVTXD_MACLEN_SHIFT    9  /* Adv ctxt desc mac len shift */
+#define IXGBE_ADVTXD_VLAN_SHIFT      16  /* Adv ctxt vlan tag shift */
+#define IXGBE_ADVTXD_L4LEN_SHIFT     8  /* Adv ctxt L4LEN shift */
+#define IXGBE_ADVTXD_MSS_SHIFT       16  /* Adv ctxt MSS shift */
+
+/* Interrupt register bitmasks */
+
+/* Extended Interrupt Cause Read */
+#define IXGBE_EICR_RTX_QUEUE    0x0000FFFF /* RTx Queue Interrupt */
+#define IXGBE_EICR_MAILBOX      0x00080000 /* VF to PF Mailbox Interrupt */
+#define IXGBE_EICR_OTHER        0x80000000 /* Interrupt Cause Active */
+
+/* Extended Interrupt Cause Set */
+#define IXGBE_EICS_RTX_QUEUE    IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */
+#define IXGBE_EICS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
+#define IXGBE_EICS_OTHER        IXGBE_EICR_OTHER     /* INT Cause Active */
+
+/* Extended Interrupt Mask Set */
+#define IXGBE_EIMS_RTX_QUEUE    IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */
+#define IXGBE_EIMS_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
+#define IXGBE_EIMS_OTHER        IXGBE_EICR_OTHER     /* INT Cause Active */
+
+/* Extended Interrupt Mask Clear */
+#define IXGBE_EIMC_RTX_QUEUE    IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */
+#define IXGBE_EIMC_MAILBOX      IXGBE_EICR_MAILBOX   /* VF to PF Mailbox Int */
+#define IXGBE_EIMC_OTHER        IXGBE_EICR_OTHER     /* INT Cause Active */
+
+#define IXGBE_EIMS_ENABLE_MASK ( \
+				IXGBE_EIMS_RTX_QUEUE       | \
+				IXGBE_EIMS_MAILBOX         | \
+				IXGBE_EIMS_OTHER)
+
+#define IXGBE_EITR_CNT_WDIS     0x80000000
+
+/* Error Codes */
+#define IXGBE_ERR_INVALID_MAC_ADDR              -1
+#define IXGBE_ERR_RESET_FAILED                  -2
+
+#endif /* _IXGBEVF_DEFINES_H_ */
diff --git a/drivers/net/ixgbevf/regs.h b/drivers/net/ixgbevf/regs.h
new file mode 100644
index 0000000..12f7596
--- /dev/null
+++ b/drivers/net/ixgbevf/regs.h
@@ -0,0 +1,85 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBEVF_REGS_H_
+#define _IXGBEVF_REGS_H_
+
+#define IXGBE_VFCTRL           0x00000
+#define IXGBE_VFSTATUS         0x00008
+#define IXGBE_VFLINKS          0x00010
+#define IXGBE_VFRTIMER         0x00048
+#define IXGBE_VFRXMEMWRAP      0x03190
+#define IXGBE_VTEICR           0x00100
+#define IXGBE_VTEICS           0x00104
+#define IXGBE_VTEIMS           0x00108
+#define IXGBE_VTEIMC           0x0010C
+#define IXGBE_VTEIAC           0x00110
+#define IXGBE_VTEIAM           0x00114
+#define IXGBE_VTEITR(x)        (0x00820 + (4 * x))
+#define IXGBE_VTIVAR(x)        (0x00120 + (4 * x))
+#define IXGBE_VTIVAR_MISC      0x00140
+#define IXGBE_VTRSCINT(x)      (0x00180 + (4 * x))
+#define IXGBE_VFRDBAL(x)       (0x01000 + (0x40 * x))
+#define IXGBE_VFRDBAH(x)       (0x01004 + (0x40 * x))
+#define IXGBE_VFRDLEN(x)       (0x01008 + (0x40 * x))
+#define IXGBE_VFRDH(x)         (0x01010 + (0x40 * x))
+#define IXGBE_VFRDT(x)         (0x01018 + (0x40 * x))
+#define IXGBE_VFRXDCTL(x)      (0x01028 + (0x40 * x))
+#define IXGBE_VFSRRCTL(x)      (0x01014 + (0x40 * x))
+#define IXGBE_VFRSCCTL(x)      (0x0102C + (0x40 * x))
+#define IXGBE_VFPSRTYPE        0x00300
+#define IXGBE_VFTDBAL(x)       (0x02000 + (0x40 * x))
+#define IXGBE_VFTDBAH(x)       (0x02004 + (0x40 * x))
+#define IXGBE_VFTDLEN(x)       (0x02008 + (0x40 * x))
+#define IXGBE_VFTDH(x)         (0x02010 + (0x40 * x))
+#define IXGBE_VFTDT(x)         (0x02018 + (0x40 * x))
+#define IXGBE_VFTXDCTL(x)      (0x02028 + (0x40 * x))
+#define IXGBE_VFTDWBAL(x)      (0x02038 + (0x40 * x))
+#define IXGBE_VFTDWBAH(x)      (0x0203C + (0x40 * x))
+#define IXGBE_VFDCA_RXCTRL(x)  (0x0100C + (0x40 * x))
+#define IXGBE_VFDCA_TXCTRL(x)  (0x0200c + (0x40 * x))
+#define IXGBE_VFGPRC           0x0101C
+#define IXGBE_VFGPTC           0x0201C
+#define IXGBE_VFGORC_LSB       0x01020
+#define IXGBE_VFGORC_MSB       0x01024
+#define IXGBE_VFGOTC_LSB       0x02020
+#define IXGBE_VFGOTC_MSB       0x02024
+#define IXGBE_VFMPRC           0x01034
+
+#define IXGBE_WRITE_REG(a, reg, value) writel((value), ((a)->hw_addr + (reg)))
+
+#define IXGBE_READ_REG(a, reg) readl((a)->hw_addr + (reg))
+
+#define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) ( \
+    writel((value), ((a)->hw_addr + (reg) + ((offset) << 2))))
+
+#define IXGBE_READ_REG_ARRAY(a, reg, offset) ( \
+    readl((a)->hw_addr + (reg) + ((offset) << 2)))
+
+#define IXGBE_WRITE_FLUSH(a) (IXGBE_READ_REG(a, IXGBE_VFSTATUS))
+
+#endif /* _IXGBEVF_REGS_H_ */

[RFC PATCH v2 02/12] ixgbevf: 82599 Virtual Function core functions and header

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

This module and header file contain the core functions for the 82599
virtual function device.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbevf/vf.c |  410 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbevf/vf.h |  168 +++++++++++++++++++
 2 files changed, 578 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbevf/vf.c
 create mode 100644 drivers/net/ixgbevf/vf.h

diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c
new file mode 100644
index 0000000..38784eb
--- /dev/null
+++ b/drivers/net/ixgbevf/vf.c
@@ -0,0 +1,410 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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 "vf.h"
+
+static s32 ixgbevf_init_hw_vf(struct ixgbe_hw *hw);
+static s32 ixgbevf_start_hw_vf(struct ixgbe_hw *hw);
+static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw);
+static s32 ixgbevf_stop_hw_vf(struct ixgbe_hw *hw);
+static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr);
+static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw,
+				   ixgbe_link_speed speed, bool autoneg,
+				   bool autoneg_wait_to_complete);
+static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
+				   ixgbe_link_speed *speed,
+				   bool *link_up,
+				   bool autoneg_wait_to_complete);
+static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr,
+			      u32 vmdq);
+static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, u8 *mc_addr_list,
+					u32 mc_addr_count, ixgbe_mc_addr_itr);
+static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind,
+			     bool vlan_on);
+
+/**
+ *  ixgbevf_start_hw_vf - Prepare hardware for Tx/Rx
+ *  @hw: pointer to hardware structure
+ *
+ *  Starts the hardware by filling the bus info structure and media type, clears
+ *  all on chip counters, initializes receive address registers, multicast
+ *  table, VLAN filter table, calls routine to set up link and flow control
+ *  settings, and leaves transmit and receive units disabled and uninitialized
+ **/
+static s32 ixgbevf_start_hw_vf(struct ixgbe_hw *hw)
+{
+	/* Clear adapter stopped flag */
+	hw->adapter_stopped = false;
+
+	return 0;
+}
+
+/**
+ *  ixgbevf_init_hw_vf - virtual function hardware initialization
+ *  @hw: pointer to hardware structure
+ *
+ *  Initialize the hardware by resetting the hardware and then starting
+ *  the hardware
+ **/
+static s32 ixgbevf_init_hw_vf(struct ixgbe_hw *hw)
+{
+	s32 status = hw->mac.ops.start_hw(hw);
+
+	hw->mac.ops.get_mac_addr(hw, hw->mac.addr);
+
+	return status;
+}
+
+/**
+ *  ixgbevf_reset_hw_vf - Performs hardware reset
+ *  @hw: pointer to hardware structure
+ *
+ *  Resets the hardware by reseting the transmit and receive units, masks and
+ *  clears all interrupts.
+ **/
+static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	u32 timeout = IXGBE_VF_INIT_TIMEOUT;
+	s32 ret_val = IXGBE_ERR_INVALID_MAC_ADDR;
+	u32 msgbuf[IXGBE_VF_PERMADDR_MSG_LEN];
+	u8 *addr = (u8 *)(&msgbuf[1]);
+
+	/* Call adapter stop to disable tx/rx and clear interrupts */
+	hw->mac.ops.stop_adapter(hw);
+
+	IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST);
+	IXGBE_WRITE_FLUSH(hw);
+
+	/* we cannot reset while the RSTI / RSTD bits are asserted */
+	while (!mbx->ops.check_for_rst(hw) && timeout) {
+		timeout--;
+		udelay(5);
+	}
+
+	if (timeout) {
+		/* mailbox timeout can now become active */
+		mbx->timeout = IXGBE_VF_MBX_INIT_TIMEOUT;
+
+		msgbuf[0] = IXGBE_VF_RESET;
+		mbx->ops.write_posted(hw, msgbuf, 1);
+
+		msleep(10);
+
+		/* set our "perm_addr" based on info provided by PF */
+		/* also set up the mc_filter_type which is piggy backed
+		 * on the mac address in word 3 */
+		ret_val = mbx->ops.read_posted(hw, msgbuf,
+					       IXGBE_VF_PERMADDR_MSG_LEN);
+		if (!ret_val) {
+			if (msgbuf[0] == (IXGBE_VF_RESET |
+					  IXGBE_VT_MSGTYPE_ACK)) {
+				memcpy(hw->mac.perm_addr, addr,
+				       IXGBE_ETH_LENGTH_OF_ADDRESS);
+				hw->mac.mc_filter_type =
+					msgbuf[IXGBE_VF_MC_TYPE_WORD];
+			} else {
+				ret_val = IXGBE_ERR_INVALID_MAC_ADDR;
+			}
+		}
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_stop_hw_vf - Generic stop Tx/Rx units
+ *  @hw: pointer to hardware structure
+ *
+ *  Sets the adapter_stopped flag within ixgbe_hw struct. Clears interrupts,
+ *  disables transmit and receive units. The adapter_stopped flag is used by
+ *  the shared code and drivers to determine if the adapter is in a stopped
+ *  state and should not touch the hardware.
+ **/
+static s32 ixgbevf_stop_hw_vf(struct ixgbe_hw *hw)
+{
+	u32 number_of_queues;
+	u32 reg_val;
+	u16 i;
+
+	/*
+	 * Set the adapter_stopped flag so other driver functions stop touching
+	 * the hardware
+	 */
+	hw->adapter_stopped = true;
+
+	/* Disable the receive unit by stopped each queue */
+	number_of_queues = hw->mac.max_rx_queues;
+	for (i = 0; i < number_of_queues; i++) {
+		reg_val = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i));
+		if (reg_val & IXGBE_RXDCTL_ENABLE) {
+			reg_val &= ~IXGBE_RXDCTL_ENABLE;
+			IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(i), reg_val);
+		}
+	}
+
+	IXGBE_WRITE_FLUSH(hw);
+
+	/* Clear interrupt mask to stop from interrupts being generated */
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, IXGBE_VF_IRQ_CLEAR_MASK);
+
+	/* Clear any pending interrupts */
+	IXGBE_READ_REG(hw, IXGBE_VTEICR);
+
+	/* Disable the transmit unit.  Each queue must be disabled. */
+	number_of_queues = hw->mac.max_tx_queues;
+	for (i = 0; i < number_of_queues; i++) {
+		reg_val = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i));
+		if (reg_val & IXGBE_TXDCTL_ENABLE) {
+			reg_val &= ~IXGBE_TXDCTL_ENABLE;
+			IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(i), reg_val);
+		}
+	}
+
+	return 0;
+}
+
+/**
+ *  ixgbevf_mta_vector - Determines bit-vector in multicast table to set
+ *  @hw: pointer to hardware structure
+ *  @mc_addr: the multicast address
+ *
+ *  Extracts the 12 bits, from a multicast address, to determine which
+ *  bit-vector to set in the multicast table. The hardware uses 12 bits, from
+ *  incoming rx multicast addresses, to determine the bit-vector to check in
+ *  the MTA. Which of the 4 combination, of 12-bits, the hardware uses is set
+ *  by the MO field of the MCSTCTRL. The MO field is set during initialization
+ *  to mc_filter_type.
+ **/
+static s32 ixgbevf_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr)
+{
+	u32 vector = 0;
+
+	switch (hw->mac.mc_filter_type) {
+	case 0:   /* use bits [47:36] of the address */
+		vector = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4));
+		break;
+	case 1:   /* use bits [46:35] of the address */
+		vector = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5));
+		break;
+	case 2:   /* use bits [45:34] of the address */
+		vector = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6));
+		break;
+	case 3:   /* use bits [43:32] of the address */
+		vector = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8));
+		break;
+	default:  /* Invalid mc_filter_type */
+		break;
+	}
+
+	/* vector can only be 12-bits or boundary will be exceeded */
+	vector &= 0xFFF;
+	return vector;
+}
+
+/**
+ *  ixgbevf_set_rar_vf - set device MAC address
+ *  @hw: pointer to hardware structure
+ *  @index: Receive address register to write
+ *  @addr: Address to put into receive address register
+ *  @vmdq: VMDq "set" or "pool" index
+ **/
+static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr,
+			      u32 vmdq)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	u32 msgbuf[3];
+	u8 *msg_addr = (u8 *)(&msgbuf[1]);
+	s32 ret_val;
+
+	memset(msgbuf, 0, 12);
+	msgbuf[0] = IXGBE_VF_SET_MAC_ADDR;
+	memcpy(msg_addr, addr, 6);
+	ret_val = mbx->ops.write_posted(hw, msgbuf, 3);
+
+	if (!ret_val)
+		ret_val = mbx->ops.read_posted(hw, msgbuf, 3);
+
+	msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS;
+
+	/* if nacked the address was rejected, use "perm_addr" */
+	if (!ret_val &&
+	    (msgbuf[0] == (IXGBE_VF_SET_MAC_ADDR | IXGBE_VT_MSGTYPE_NACK)))
+		ixgbevf_get_mac_addr_vf(hw, hw->mac.addr);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_update_mc_addr_list_vf - Update Multicast addresses
+ *  @hw: pointer to the HW structure
+ *  @mc_addr_list: array of multicast addresses to program
+ *  @mc_addr_count: number of multicast addresses to program
+ *  @next: caller supplied function to return next address in list
+ *
+ *  Updates the Multicast Table Array.
+ **/
+static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, u8 *mc_addr_list,
+					u32 mc_addr_count,
+					ixgbe_mc_addr_itr next)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	u32 msgbuf[IXGBE_VFMAILBOX_SIZE];
+	u16 *vector_list = (u16 *)&msgbuf[1];
+	u32 vector;
+	u32 cnt, i;
+	u32 vmdq;
+
+	/* Each entry in the list uses 1 16 bit word.  We have 30
+	 * 16 bit words available in our HW msg buffer (minus 1 for the
+	 * msg type).  That's 30 hash values if we pack 'em right.  If
+	 * there are more than 30 MC addresses to add then punt the
+	 * extras for now and then add code to handle more than 30 later.
+	 * It would be unusual for a server to request that many multi-cast
+	 * addresses except for in large enterprise network environments.
+	 */
+
+	cnt = (mc_addr_count > 30) ? 30 : mc_addr_count;
+	msgbuf[0] = IXGBE_VF_SET_MULTICAST;
+	msgbuf[0] |= cnt << IXGBE_VT_MSGINFO_SHIFT;
+
+	for (i = 0; i < cnt; i++) {
+		vector = ixgbevf_mta_vector(hw, next(hw, &mc_addr_list, &vmdq));
+		vector_list[i] = vector;
+	}
+
+	mbx->ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE);
+
+	return 0;
+}
+
+/**
+ *  ixgbevf_set_vfta_vf - Set/Unset vlan filter table address
+ *  @hw: pointer to the HW structure
+ *  @vlan: 12 bit VLAN ID
+ *  @vind: unused by VF drivers
+ *  @vlan_on: if true then set bit, else clear bit
+ **/
+static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind,
+			       bool vlan_on)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	u32 msgbuf[2];
+
+	msgbuf[0] = IXGBE_VF_SET_VLAN;
+	msgbuf[1] = vlan;
+	/* Setting the 8 bit field MSG INFO to TRUE indicates "add" */
+	msgbuf[0] |= vlan_on << IXGBE_VT_MSGINFO_SHIFT;
+
+	return mbx->ops.write_posted(hw, msgbuf, 2);
+}
+
+/**
+ *  ixgbevf_get_mac_addr_vf - Read device MAC address
+ *  @hw: pointer to the HW structure
+ **/
+static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr)
+{
+	int i;
+
+	for (i = 0; i < IXGBE_ETH_LENGTH_OF_ADDRESS; i++)
+		mac_addr[i] = hw->mac.perm_addr[i];
+
+	return 0;
+}
+
+/**
+ *  ixgbevf_setup_mac_link_vf - Setup MAC link settings
+ *  @hw: pointer to hardware structure
+ *  @speed: new link speed
+ *  @autoneg: true if autonegotiation enabled
+ *  @autoneg_wait_to_complete: true when waiting for completion is needed
+ *
+ *  Set the link speed in the AUTOC register and restarts link.
+ **/
+static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw,
+				     ixgbe_link_speed speed, bool autoneg,
+				     bool autoneg_wait_to_complete)
+{
+	return 0;
+}
+
+/**
+ *  ixgbevf_check_mac_link_vf - Get link/speed status
+ *  @hw: pointer to hardware structure
+ *  @speed: pointer to link speed
+ *  @link_up: true is link is up, false otherwise
+ *  @autoneg_wait_to_complete: true when waiting for completion is needed
+ *
+ *  Reads the links register to determine if link is up and the current speed
+ **/
+static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *link_up,
+				     bool autoneg_wait_to_complete)
+{
+	u32 links_reg;
+
+	if (!(hw->mbx.ops.check_for_rst(hw))) {
+		*link_up = false;
+		*speed = 0;
+		return -1;
+	}
+
+	links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+
+	if (links_reg & IXGBE_LINKS_UP)
+		*link_up = true;
+	else
+		*link_up = false;
+
+	if (links_reg & IXGBE_LINKS_SPEED)
+		*speed = IXGBE_LINK_SPEED_10GB_FULL;
+	else
+		*speed = IXGBE_LINK_SPEED_1GB_FULL;
+
+	return 0;
+}
+
+struct ixgbe_mac_operations ixgbevf_mac_ops = {
+	.init_hw             = ixgbevf_init_hw_vf,
+	.reset_hw            = ixgbevf_reset_hw_vf,
+	.start_hw            = ixgbevf_start_hw_vf,
+	.get_mac_addr        = ixgbevf_get_mac_addr_vf,
+	.stop_adapter        = ixgbevf_stop_hw_vf,
+	.setup_link          = ixgbevf_setup_mac_link_vf,
+	.check_link          = ixgbevf_check_mac_link_vf,
+	.set_rar             = ixgbevf_set_rar_vf,
+	.update_mc_addr_list = ixgbevf_update_mc_addr_list_vf,
+	.set_vfta            = ixgbevf_set_vfta_vf,
+};
+
+struct ixgbevf_info ixgbevf_vf_info = {
+	.mac = ixgbe_mac_82599_vf,
+	.mac_ops = &ixgbevf_mac_ops,
+};
+
diff --git a/drivers/net/ixgbevf/vf.h b/drivers/net/ixgbevf/vf.h
new file mode 100644
index 0000000..799600e
--- /dev/null
+++ b/drivers/net/ixgbevf/vf.h
@@ -0,0 +1,168 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef __IXGBE_VF_H__
+#define __IXGBE_VF_H__
+
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+
+#include "defines.h"
+#include "regs.h"
+#include "mbx.h"
+
+struct ixgbe_hw;
+
+/* iterator type for walking multicast address lists */
+typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr,
+				  u32 *vmdq);
+struct ixgbe_mac_operations {
+	s32 (*init_hw)(struct ixgbe_hw *);
+	s32 (*reset_hw)(struct ixgbe_hw *);
+	s32 (*start_hw)(struct ixgbe_hw *);
+	s32 (*clear_hw_cntrs)(struct ixgbe_hw *);
+	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
+	u32 (*get_supported_physical_layer)(struct ixgbe_hw *);
+	s32 (*get_mac_addr)(struct ixgbe_hw *, u8 *);
+	s32 (*stop_adapter)(struct ixgbe_hw *);
+	s32 (*get_bus_info)(struct ixgbe_hw *);
+
+	/* Link */
+	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool);
+	s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool);
+	s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *,
+				     bool *);
+
+	/* RAR, Multicast, VLAN */
+	s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32);
+	s32 (*init_rx_addrs)(struct ixgbe_hw *);
+	s32 (*update_mc_addr_list)(struct ixgbe_hw *, u8 *, u32,
+				   ixgbe_mc_addr_itr);
+	s32 (*enable_mc)(struct ixgbe_hw *);
+	s32 (*disable_mc)(struct ixgbe_hw *);
+	s32 (*clear_vfta)(struct ixgbe_hw *);
+	s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool);
+};
+
+enum ixgbe_mac_type {
+	ixgbe_mac_unknown = 0,
+	ixgbe_mac_82599_vf,
+	ixgbe_num_macs
+};
+
+struct ixgbe_mac_info {
+	struct ixgbe_mac_operations ops;
+	u8 addr[6];
+	u8 perm_addr[6];
+
+	enum ixgbe_mac_type type;
+
+	s32  mc_filter_type;
+
+	bool get_link_status;
+	u32  max_tx_queues;
+	u32  max_rx_queues;
+	u32  max_msix_vectors;
+};
+
+struct ixgbe_mbx_operations {
+	s32 (*init_params)(struct ixgbe_hw *hw);
+	s32 (*read)(struct ixgbe_hw *, u32 *, u16);
+	s32 (*write)(struct ixgbe_hw *, u32 *, u16);
+	s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16);
+	s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16);
+	s32 (*check_for_msg)(struct ixgbe_hw *);
+	s32 (*check_for_ack)(struct ixgbe_hw *);
+	s32 (*check_for_rst)(struct ixgbe_hw *);
+};
+
+struct ixgbe_mbx_stats {
+	u32 msgs_tx;
+	u32 msgs_rx;
+
+	u32 acks;
+	u32 reqs;
+	u32 rsts;
+};
+
+struct ixgbe_mbx_info {
+	struct ixgbe_mbx_operations ops;
+	struct ixgbe_mbx_stats stats;
+	u32 timeout;
+	u32 udelay;
+	u32 v2p_mailbox;
+	u16 size;
+};
+
+struct ixgbe_hw {
+	void *back;
+
+	u8 __iomem *hw_addr;
+	u8 *flash_address;
+	unsigned long io_base;
+
+	struct ixgbe_mac_info mac;
+	struct ixgbe_mbx_info mbx;
+
+	u16 device_id;
+	u16 subsystem_vendor_id;
+	u16 subsystem_device_id;
+	u16 vendor_id;
+
+	u8  revision_id;
+	bool adapter_stopped;
+};
+
+struct ixgbevf_hw_stats {
+	u64 base_vfgprc;
+	u64 base_vfgptc;
+	u64 base_vfgorc;
+	u64 base_vfgotc;
+	u64 base_vfmprc;
+
+	u64 last_vfgprc;
+	u64 last_vfgptc;
+	u64 last_vfgorc;
+	u64 last_vfgotc;
+	u64 last_vfmprc;
+
+	u64 vfgprc;
+	u64 vfgptc;
+	u64 vfgorc;
+	u64 vfgotc;
+	u64 vfmprc;
+};
+
+struct ixgbevf_info {
+	enum ixgbe_mac_type		mac;
+	struct ixgbe_mac_operations	*mac_ops;
+};
+
+#endif /* __IXGBE_VF_H__ */
+

Re: [RFC PATCH v2 02/12] ixgbevf: 82599 Virtual Function core functions and header

[Simon Horman]

On Fri, Dec 18, 2009 at 02:51:23PM -0800, Jeff Kirsher wrote:
> From: Greg Rose <gregory.v.rose@intel.com>
> 
> This module and header file contain the core functions for the 82599
> virtual function device.
> 
> Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> ---
> 
>  drivers/net/ixgbevf/vf.c |  410 ++++++++++++++++++++++++++++++++++++++++++++++
>  drivers/net/ixgbevf/vf.h |  168 +++++++++++++++++++
>  2 files changed, 578 insertions(+), 0 deletions(-)
>  create mode 100644 drivers/net/ixgbevf/vf.c
>  create mode 100644 drivers/net/ixgbevf/vf.h
> 
> diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c
> new file mode 100644
> index 0000000..38784eb
> --- /dev/null
> +++ b/drivers/net/ixgbevf/vf.c
> @@ -0,0 +1,410 @@

[snip]

> +
> +#include "vf.h"
> +
> +static s32 ixgbevf_init_hw_vf(struct ixgbe_hw *hw);
> +static s32 ixgbevf_start_hw_vf(struct ixgbe_hw *hw);
> +static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw);
> +static s32 ixgbevf_stop_hw_vf(struct ixgbe_hw *hw);
> +static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr);
> +static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw,
> +				   ixgbe_link_speed speed, bool autoneg,
> +				   bool autoneg_wait_to_complete);
> +static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
> +				   ixgbe_link_speed *speed,
> +				   bool *link_up,
> +				   bool autoneg_wait_to_complete);
> +static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr,
> +			      u32 vmdq);
> +static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, u8 *mc_addr_list,
> +					u32 mc_addr_count, ixgbe_mc_addr_itr);
> +static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind,
> +			     bool vlan_on);

It seems that if the definition of ixgbevf_get_mac_addr_vf() was moved to
before ixgbevf_set_rar_vf() then all of the above static declarations could
be removed.

[snip]

> +/**
> + *  ixgbevf_reset_hw_vf - Performs hardware reset
> + *  @hw: pointer to hardware structure
> + *
> + *  Resets the hardware by reseting the transmit and receive units, masks and
> + *  clears all interrupts.
> + **/
> +static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
> +{
> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
> +	u32 timeout = IXGBE_VF_INIT_TIMEOUT;
> +	s32 ret_val = IXGBE_ERR_INVALID_MAC_ADDR;
> +	u32 msgbuf[IXGBE_VF_PERMADDR_MSG_LEN];
> +	u8 *addr = (u8 *)(&msgbuf[1]);
> +
> +	/* Call adapter stop to disable tx/rx and clear interrupts */
> +	hw->mac.ops.stop_adapter(hw);
> +
> +	IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST);
> +	IXGBE_WRITE_FLUSH(hw);
> +
> +	/* we cannot reset while the RSTI / RSTD bits are asserted */
> +	while (!mbx->ops.check_for_rst(hw) && timeout) {
> +		timeout--;
> +		udelay(5);
> +	}
> +
> +	if (timeout) {
> +		/* mailbox timeout can now become active */
> +		mbx->timeout = IXGBE_VF_MBX_INIT_TIMEOUT;
> +
> +		msgbuf[0] = IXGBE_VF_RESET;
> +		mbx->ops.write_posted(hw, msgbuf, 1);
> +
> +		msleep(10);
> +
> +		/* set our "perm_addr" based on info provided by PF */
> +		/* also set up the mc_filter_type which is piggy backed
> +		 * on the mac address in word 3 */
> +		ret_val = mbx->ops.read_posted(hw, msgbuf,
> +					       IXGBE_VF_PERMADDR_MSG_LEN);
> +		if (!ret_val) {
> +			if (msgbuf[0] == (IXGBE_VF_RESET |
> +					  IXGBE_VT_MSGTYPE_ACK)) {
> +				memcpy(hw->mac.perm_addr, addr,
> +				       IXGBE_ETH_LENGTH_OF_ADDRESS);
> +				hw->mac.mc_filter_type =
> +					msgbuf[IXGBE_VF_MC_TYPE_WORD];
> +			} else {
> +				ret_val = IXGBE_ERR_INVALID_MAC_ADDR;
> +			}
> +		}
> +	}
> +
> +	return ret_val;
> +}

I wonder if it would be easier to follow the flow of ixgbevf_reset_hw_vf()
if it was written as:

static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
{
	struct ixgbe_mbx_info *mbx = &hw->mbx;
	u32 timeout = IXGBE_VF_INIT_TIMEOUT;
	s32 ret_val;
	u32 msgbuf[IXGBE_VF_PERMADDR_MSG_LEN];
	u8 *addr = (u8 *)(&msgbuf[1]);

	/* Call adapter stop to disable tx/rx and clear interrupts */
	hw->mac.ops.stop_adapter(hw);

	IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST);
	IXGBE_WRITE_FLUSH(hw);

	/* we cannot reset while the RSTI / RSTD bits are asserted */
	while (!mbx->ops.check_for_rst(hw) && timeout) {
		timeout--;
		udelay(5);
	}

	if (!timeout)
		return IXGBE_ERR_INVALID_MAC_ADDR;

	/* mailbox timeout can now become active */
	mbx->timeout = IXGBE_VF_MBX_INIT_TIMEOUT;

	msgbuf[0] = IXGBE_VF_RESET;
	mbx->ops.write_posted(hw, msgbuf, 1);

	msleep(10);

	/* Set our "perm_addr" based on info provided by PF.
	 * Also set up the mc_filter_type which is piggy backed
	 * on the mac address in word 3
	 */
	ret_val = mbx->ops.read_posted(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN);
	if (ret_val)
		return ret_val;

	if (msgbuf[0] != (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK))
		return IXGBE_ERR_INVALID_MAC_ADDR;

	memcpy(hw->mac.perm_addr, addr, IXGBE_ETH_LENGTH_OF_ADDRESS);
	hw->mac.mc_filter_type = msgbuf[IXGBE_VF_MC_TYPE_WORD];

	return 0;
}

Re: [RFC PATCH v2 02/12] ixgbevf: 82599 Virtual Function core functions and header

[Ben Hutchings]

On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
> From: Greg Rose <gregory.v.rose@intel.com>
> 
> This module and header file contain the core functions for the 82599
> virtual function device.
[...]
> diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c
> new file mode 100644
> index 0000000..38784eb
> --- /dev/null
> +++ b/drivers/net/ixgbevf/vf.c
[...]
> +/**
> + *  ixgbevf_set_rar_vf - set device MAC address
> + *  @hw: pointer to hardware structure
> + *  @index: Receive address register to write
> + *  @addr: Address to put into receive address register
> + *  @vmdq: VMDq "set" or "pool" index
> + **/
> +static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr,
> +			      u32 vmdq)
> +{
> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
> +	u32 msgbuf[3];
> +	u8 *msg_addr = (u8 *)(&msgbuf[1]);
> +	s32 ret_val;
> +
> +	memset(msgbuf, 0, 12);

Seems like it would be clearer to write sizeof(msgbuf) rather than 12.
But does it even matter that you clear the padding bytes?

[...]
> +/**
> + *  ixgbevf_update_mc_addr_list_vf - Update Multicast addresses
> + *  @hw: pointer to the HW structure
> + *  @mc_addr_list: array of multicast addresses to program
> + *  @mc_addr_count: number of multicast addresses to program
> + *  @next: caller supplied function to return next address in list
> + *
> + *  Updates the Multicast Table Array.
> + **/
> +static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, u8 *mc_addr_list,
> +					u32 mc_addr_count,
> +					ixgbe_mc_addr_itr next)
> +{
> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
> +	u32 msgbuf[IXGBE_VFMAILBOX_SIZE];
> +	u16 *vector_list = (u16 *)&msgbuf[1];
> +	u32 vector;
> +	u32 cnt, i;
> +	u32 vmdq;
> +
> +	/* Each entry in the list uses 1 16 bit word.  We have 30
> +	 * 16 bit words available in our HW msg buffer (minus 1 for the
> +	 * msg type).  That's 30 hash values if we pack 'em right.  If
> +	 * there are more than 30 MC addresses to add then punt the
> +	 * extras for now and then add code to handle more than 30 later.
> +	 * It would be unusual for a server to request that many multi-cast
> +	 * addresses except for in large enterprise network environments.
> +	 */
> +	cnt = (mc_addr_count > 30) ? 30 : mc_addr_count;

What, you don't want to support large enterprise networks now? ;-)
You should switch to all-multicast behaviour rather than dropping
multicast addresses.

[...]
> +/**
> + *  ixgbevf_get_mac_addr_vf - Read device MAC address
> + *  @hw: pointer to the HW structure

The mac_addr parameter is missing.

> + **/
> +static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr)
> +{
> +	int i;
> +
> +	for (i = 0; i < IXGBE_ETH_LENGTH_OF_ADDRESS; i++)
> +		mac_addr[i] = hw->mac.perm_addr[i];

memcpy()?

[...]
> +/**
> + *  ixgbevf_setup_mac_link_vf - Setup MAC link settings
> + *  @hw: pointer to hardware structure
> + *  @speed: new link speed
> + *  @autoneg: true if autonegotiation enabled
> + *  @autoneg_wait_to_complete: true when waiting for completion is needed
> + *
> + *  Set the link speed in the AUTOC register and restarts link.
> + **/

This description is obviously not correct.

> +static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw,
> +				     ixgbe_link_speed speed, bool autoneg,
> +				     bool autoneg_wait_to_complete)
> +{
> +	return 0;
> +}
[...]
> diff --git a/drivers/net/ixgbevf/vf.h b/drivers/net/ixgbevf/vf.h
> new file mode 100644
> index 0000000..799600e
> --- /dev/null
> +++ b/drivers/net/ixgbevf/vf.h
[...]
> +struct ixgbe_mac_operations {
> +	s32 (*init_hw)(struct ixgbe_hw *);
> +	s32 (*reset_hw)(struct ixgbe_hw *);
> +	s32 (*start_hw)(struct ixgbe_hw *);
> +	s32 (*clear_hw_cntrs)(struct ixgbe_hw *);
> +	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
> +	u32 (*get_supported_physical_layer)(struct ixgbe_hw *);
> +	s32 (*get_mac_addr)(struct ixgbe_hw *, u8 *);
> +	s32 (*stop_adapter)(struct ixgbe_hw *);
> +	s32 (*get_bus_info)(struct ixgbe_hw *);
> +
> +	/* Link */
> +	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool);
> +	s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool);
> +	s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *,
> +				     bool *);
> +
> +	/* RAR, Multicast, VLAN */
> +	s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32);
> +	s32 (*init_rx_addrs)(struct ixgbe_hw *);
> +	s32 (*update_mc_addr_list)(struct ixgbe_hw *, u8 *, u32,
> +				   ixgbe_mc_addr_itr);
> +	s32 (*enable_mc)(struct ixgbe_hw *);
> +	s32 (*disable_mc)(struct ixgbe_hw *);
> +	s32 (*clear_vfta)(struct ixgbe_hw *);
> +	s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool);
> +};
> +
> +enum ixgbe_mac_type {
> +	ixgbe_mac_unknown = 0,
> +	ixgbe_mac_82599_vf,
> +	ixgbe_num_macs
> +};

Is this abstraction really justified, given you have only one
implementation?

[...]
> +struct ixgbe_mbx_operations {
> +	s32 (*init_params)(struct ixgbe_hw *hw);
> +	s32 (*read)(struct ixgbe_hw *, u32 *, u16);
> +	s32 (*write)(struct ixgbe_hw *, u32 *, u16);
> +	s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16);
> +	s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16);
> +	s32 (*check_for_msg)(struct ixgbe_hw *);
> +	s32 (*check_for_ack)(struct ixgbe_hw *);
> +	s32 (*check_for_rst)(struct ixgbe_hw *);
> +};
[...]

Ditto for this.

Ben.

-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

RE: [RFC PATCH v2 02/12] ixgbevf: 82599 Virtual Function core functions and header

[Rose, Gregory V]

>-----Original Message-----
>From: Ben Hutchings [mailto:bhutchings@solarflare.com]
>Sent: Wednesday, December 23, 2009 12:22 PM
>To: Kirsher, Jeffrey T
>Cc: netdev@vger.kernel.org; gospo@redhat.com; Rose, Gregory V
>Subject: Re: [RFC PATCH v2 02/12] ixgbevf: 82599 Virtual Function core
>functions and header
>
>On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
>> From: Greg Rose <gregory.v.rose@intel.com>
>>
>> This module and header file contain the core functions for the 82599
>> virtual function device.
>[...]
>> diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c
>> new file mode 100644
>> index 0000000..38784eb
>> --- /dev/null
>> +++ b/drivers/net/ixgbevf/vf.c
>[...]
>> +/**
>> + *  ixgbevf_set_rar_vf - set device MAC address
>> + *  @hw: pointer to hardware structure
>> + *  @index: Receive address register to write
>> + *  @addr: Address to put into receive address register
>> + *  @vmdq: VMDq "set" or "pool" index
>> + **/
>> +static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8
>*addr,
>> +			      u32 vmdq)
>> +{
>> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
>> +	u32 msgbuf[3];
>> +	u8 *msg_addr = (u8 *)(&msgbuf[1]);
>> +	s32 ret_val;
>> +
>> +	memset(msgbuf, 0, 12);
>
>Seems like it would be clearer to write sizeof(msgbuf) rather than 12.

Sure, we can do that.

>But does it even matter that you clear the padding bytes?

I don't know, bits getting or'ed in and masked out all over the place and
MAC addresses that span 6 bytes over 2 32 bit words... It doesn't hurt right?

>
>[...]
>> +/**
>> + *  ixgbevf_update_mc_addr_list_vf - Update Multicast addresses
>> + *  @hw: pointer to the HW structure
>> + *  @mc_addr_list: array of multicast addresses to program
>> + *  @mc_addr_count: number of multicast addresses to program
>> + *  @next: caller supplied function to return next address in list
>> + *
>> + *  Updates the Multicast Table Array.
>> + **/
>> +static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, u8
>*mc_addr_list,
>> +					u32 mc_addr_count,
>> +					ixgbe_mc_addr_itr next)
>> +{
>> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
>> +	u32 msgbuf[IXGBE_VFMAILBOX_SIZE];
>> +	u16 *vector_list = (u16 *)&msgbuf[1];
>> +	u32 vector;
>> +	u32 cnt, i;
>> +	u32 vmdq;
>> +
>> +	/* Each entry in the list uses 1 16 bit word.  We have 30
>> +	 * 16 bit words available in our HW msg buffer (minus 1 for the
>> +	 * msg type).  That's 30 hash values if we pack 'em right.  If
>> +	 * there are more than 30 MC addresses to add then punt the
>> +	 * extras for now and then add code to handle more than 30 later.
>> +	 * It would be unusual for a server to request that many multi-
>cast
>> +	 * addresses except for in large enterprise network environments.
>> +	 */
>> +	cnt = (mc_addr_count > 30) ? 30 : mc_addr_count;
>
>What, you don't want to support large enterprise networks now? ;-)
>You should switch to all-multicast behaviour rather than dropping
>multicast addresses.

In a future release yes, for now no.

>
>[...]
>> +/**
>> + *  ixgbevf_get_mac_addr_vf - Read device MAC address
>> + *  @hw: pointer to the HW structure
>
>The mac_addr parameter is missing.
>
>> + **/
>> +static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr)
>> +{
>> +	int i;
>> +
>> +	for (i = 0; i < IXGBE_ETH_LENGTH_OF_ADDRESS; i++)
>> +		mac_addr[i] = hw->mac.perm_addr[i];
>
>memcpy()?

Sure, why not.

>
>[...]
>> +/**
>> + *  ixgbevf_setup_mac_link_vf - Setup MAC link settings
>> + *  @hw: pointer to hardware structure
>> + *  @speed: new link speed
>> + *  @autoneg: true if autonegotiation enabled
>> + *  @autoneg_wait_to_complete: true when waiting for completion is
>needed
>> + *
>> + *  Set the link speed in the AUTOC register and restarts link.
>> + **/
>
>This description is obviously not correct.

Hah...  you're obviously correct.

;-)

>
>> +static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw,
>> +				     ixgbe_link_speed speed, bool autoneg,
>> +				     bool autoneg_wait_to_complete)
>> +{
>> +	return 0;
>> +}
>[...]
>> diff --git a/drivers/net/ixgbevf/vf.h b/drivers/net/ixgbevf/vf.h
>> new file mode 100644
>> index 0000000..799600e
>> --- /dev/null
>> +++ b/drivers/net/ixgbevf/vf.h
>[...]
>> +struct ixgbe_mac_operations {
>> +	s32 (*init_hw)(struct ixgbe_hw *);
>> +	s32 (*reset_hw)(struct ixgbe_hw *);
>> +	s32 (*start_hw)(struct ixgbe_hw *);
>> +	s32 (*clear_hw_cntrs)(struct ixgbe_hw *);
>> +	enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *);
>> +	u32 (*get_supported_physical_layer)(struct ixgbe_hw *);
>> +	s32 (*get_mac_addr)(struct ixgbe_hw *, u8 *);
>> +	s32 (*stop_adapter)(struct ixgbe_hw *);
>> +	s32 (*get_bus_info)(struct ixgbe_hw *);
>> +
>> +	/* Link */
>> +	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool,
>bool);
>> +	s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *,
>bool);
>> +	s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed
>*,
>> +				     bool *);
>> +
>> +	/* RAR, Multicast, VLAN */
>> +	s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32);
>> +	s32 (*init_rx_addrs)(struct ixgbe_hw *);
>> +	s32 (*update_mc_addr_list)(struct ixgbe_hw *, u8 *, u32,
>> +				   ixgbe_mc_addr_itr);
>> +	s32 (*enable_mc)(struct ixgbe_hw *);
>> +	s32 (*disable_mc)(struct ixgbe_hw *);
>> +	s32 (*clear_vfta)(struct ixgbe_hw *);
>> +	s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool);
>> +};
>> +
>> +enum ixgbe_mac_type {
>> +	ixgbe_mac_unknown = 0,
>> +	ixgbe_mac_82599_vf,
>> +	ixgbe_num_macs
>> +};
>
>Is this abstraction really justified, given you have only one
>implementation?

Leaving room for future development.

>
>[...]
>> +struct ixgbe_mbx_operations {
>> +	s32 (*init_params)(struct ixgbe_hw *hw);
>> +	s32 (*read)(struct ixgbe_hw *, u32 *, u16);
>> +	s32 (*write)(struct ixgbe_hw *, u32 *, u16);
>> +	s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16);
>> +	s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16);
>> +	s32 (*check_for_msg)(struct ixgbe_hw *);
>> +	s32 (*check_for_ack)(struct ixgbe_hw *);
>> +	s32 (*check_for_rst)(struct ixgbe_hw *);
>> +};
>[...]
>
>Ditto for this.

We wanted some level of indirection for the mailbox stuff because this
Linux VF driver may run on top of hypervisors/VMMs in which they don't wish to
use our HW based mailbox for messaging between the PF and VF.  This facilitates
that.

Thanks for the comments.

Regards,

- Greg

[RFC PATCH v2 03/12] ixgbevf: Mailbox communication

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

The 82599 virtual function device and the master 82599 physical function
device implement a mailbox utility for communication between the devices
using some SRAM scratch memory and a doorbell/answering mechanism enabled
via interrupt and/or polling.  This C module and accompanying header
file implement the base functions for use of this feature.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbevf/mbx.c |  354 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbevf/mbx.h |  100 +++++++++++++
 2 files changed, 454 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbevf/mbx.c
 create mode 100644 drivers/net/ixgbevf/mbx.h

diff --git a/drivers/net/ixgbevf/mbx.c b/drivers/net/ixgbevf/mbx.c
new file mode 100644
index 0000000..a6e81fe
--- /dev/null
+++ b/drivers/net/ixgbevf/mbx.c
@@ -0,0 +1,354 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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 "mbx.h"
+
+/**
+ *  ixgbevf_poll_for_msg - Wait for message notification
+ *  @hw: pointer to the HW structure
+ *
+ *  returns 0 if it successfully received a message notification
+ **/
+static s32 ixgbevf_poll_for_msg(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	int countdown = mbx->timeout;
+
+	if (!mbx->ops.check_for_msg)
+		goto out;
+
+	while (countdown && mbx->ops.check_for_msg(hw)) {
+		countdown--;
+		udelay(mbx->udelay);
+	}
+
+	/* if we failed, all future posted messages fail until reset */
+	if (!countdown)
+		mbx->timeout = 0;
+out:
+	return countdown ? 0 : IXGBE_ERR_MBX;
+}
+
+/**
+ *  ixgbevf_poll_for_ack - Wait for message acknowledgement
+ *  @hw: pointer to the HW structure
+ *
+ *  returns 0 if it successfully received a message acknowledgement
+ **/
+static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	int countdown = mbx->timeout;
+
+	if (!mbx->ops.check_for_ack)
+		goto out;
+
+	while (countdown && mbx->ops.check_for_ack(hw)) {
+		countdown--;
+		udelay(mbx->udelay);
+	}
+
+	/* if we failed, all future posted messages fail until reset */
+	if (!countdown)
+		mbx->timeout = 0;
+out:
+	return countdown ? 0 : IXGBE_ERR_MBX;
+}
+
+/**
+ *  ixgbevf_read_posted_mbx - Wait for message notification and receive message
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *
+ *  returns 0 if it successfully received a message notification and
+ *  copied it into the receive buffer.
+ **/
+static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (!mbx->ops.read)
+		goto out;
+
+	ret_val = ixgbevf_poll_for_msg(hw);
+
+	/* if ack received read message, otherwise we timed out */
+	if (!ret_val)
+		ret_val = mbx->ops.read(hw, msg, size);
+out:
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_write_posted_mbx - Write a message to the mailbox, wait for ack
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *
+ *  returns 0 if it successfully copied message into the buffer and
+ *  received an ack to that message within delay * timeout period
+ **/
+static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	/* exit if either we can't write or there isn't a defined timeout */
+	if (!mbx->ops.write || !mbx->timeout)
+		goto out;
+
+	/* send msg */
+	ret_val = mbx->ops.write(hw, msg, size);
+
+	/* if msg sent wait until we receive an ack */
+	if (!ret_val)
+		ret_val = ixgbevf_poll_for_ack(hw);
+out:
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_read_v2p_mailbox - read v2p mailbox
+ *  @hw: pointer to the HW structure
+ *
+ *  This function is used to read the v2p mailbox without losing the read to
+ *  clear status bits.
+ **/
+static u32 ixgbevf_read_v2p_mailbox(struct ixgbe_hw *hw)
+{
+	u32 v2p_mailbox = IXGBE_READ_REG(hw, IXGBE_VFMAILBOX);
+
+	v2p_mailbox |= hw->mbx.v2p_mailbox;
+	hw->mbx.v2p_mailbox |= v2p_mailbox & IXGBE_VFMAILBOX_R2C_BITS;
+
+	return v2p_mailbox;
+}
+
+/**
+ *  ixgbevf_check_for_bit_vf - Determine if a status bit was set
+ *  @hw: pointer to the HW structure
+ *  @mask: bitmask for bits to be tested and cleared
+ *
+ *  This function is used to check for the read to clear bits within
+ *  the V2P mailbox.
+ **/
+static s32 ixgbevf_check_for_bit_vf(struct ixgbe_hw *hw, u32 mask)
+{
+	u32 v2p_mailbox = ixgbevf_read_v2p_mailbox(hw);
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (v2p_mailbox & mask)
+		ret_val = 0;
+
+	hw->mbx.v2p_mailbox &= ~mask;
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_check_for_msg_vf - checks to see if the PF has sent mail
+ *  @hw: pointer to the HW structure
+ *
+ *  returns 0 if the PF has set the Status bit or else ERR_MBX
+ **/
+static s32 ixgbevf_check_for_msg_vf(struct ixgbe_hw *hw)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (!ixgbevf_check_for_bit_vf(hw, IXGBE_VFMAILBOX_PFSTS)) {
+		ret_val = 0;
+		hw->mbx.stats.reqs++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_check_for_ack_vf - checks to see if the PF has ACK'd
+ *  @hw: pointer to the HW structure
+ *
+ *  returns 0 if the PF has set the ACK bit or else ERR_MBX
+ **/
+static s32 ixgbevf_check_for_ack_vf(struct ixgbe_hw *hw)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (!ixgbevf_check_for_bit_vf(hw, IXGBE_VFMAILBOX_PFACK)) {
+		ret_val = 0;
+		hw->mbx.stats.acks++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_check_for_rst_vf - checks to see if the PF has reset
+ *  @hw: pointer to the HW structure
+ *
+ *  returns true if the PF has set the reset done bit or else false
+ **/
+static s32 ixgbevf_check_for_rst_vf(struct ixgbe_hw *hw)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (!ixgbevf_check_for_bit_vf(hw, (IXGBE_VFMAILBOX_RSTD |
+					 IXGBE_VFMAILBOX_RSTI))) {
+		ret_val = 0;
+		hw->mbx.stats.rsts++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_obtain_mbx_lock_vf - obtain mailbox lock
+ *  @hw: pointer to the HW structure
+ *
+ *  return 0 if we obtained the mailbox lock
+ **/
+static s32 ixgbevf_obtain_mbx_lock_vf(struct ixgbe_hw *hw)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	/* Take ownership of the buffer */
+	IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_VFU);
+
+	/* reserve mailbox for vf use */
+	if (ixgbevf_read_v2p_mailbox(hw) & IXGBE_VFMAILBOX_VFU)
+		ret_val = 0;
+
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_write_mbx_vf - Write a message to the mailbox
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *
+ *  returns 0 if it successfully copied message into the buffer
+ **/
+static s32 ixgbevf_write_mbx_vf(struct ixgbe_hw *hw, u32 *msg, u16 size)
+{
+	s32 ret_val;
+	u16 i;
+
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret_val = ixgbevf_obtain_mbx_lock_vf(hw);
+	if (ret_val)
+		goto out_no_write;
+
+	/* flush msg and acks as we are overwriting the message buffer */
+	ixgbevf_check_for_msg_vf(hw);
+	ixgbevf_check_for_ack_vf(hw);
+
+	/* copy the caller specified message to the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		IXGBE_WRITE_REG_ARRAY(hw, IXGBE_VFMBMEM, i, msg[i]);
+
+	/* update stats */
+	hw->mbx.stats.msgs_tx++;
+
+	/* Drop VFU and interrupt the PF to tell it a message has been sent */
+	IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_REQ);
+
+out_no_write:
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_read_mbx_vf - Reads a message from the inbox intended for vf
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *
+ *  returns 0 if it successfuly read message from buffer
+ **/
+static s32 ixgbevf_read_mbx_vf(struct ixgbe_hw *hw, u32 *msg, u16 size)
+{
+	s32 ret_val = 0;
+	u16 i;
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret_val = ixgbevf_obtain_mbx_lock_vf(hw);
+	if (ret_val)
+		goto out_no_read;
+
+	/* copy the message from the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		msg[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_VFMBMEM, i);
+
+	/* Acknowledge receipt and release mailbox, then we're done */
+	IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_ACK);
+
+	/* update stats */
+	hw->mbx.stats.msgs_rx++;
+
+out_no_read:
+	return ret_val;
+}
+
+/**
+ *  ixgbevf_init_mbx_params_vf - set initial values for vf mailbox
+ *  @hw: pointer to the HW structure
+ *
+ *  Initializes the hw->mbx struct to correct values for vf mailbox
+ */
+s32 ixgbevf_init_mbx_params_vf(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+
+	/* start mailbox as timed out and let the reset_hw call set the timeout
+	 * value to begin communications */
+	mbx->timeout = 0;
+	mbx->udelay = IXGBE_VF_MBX_INIT_DELAY;
+
+	mbx->size = IXGBE_VFMAILBOX_SIZE;
+
+	mbx->stats.msgs_tx = 0;
+	mbx->stats.msgs_rx = 0;
+	mbx->stats.reqs = 0;
+	mbx->stats.acks = 0;
+	mbx->stats.rsts = 0;
+
+	return 0;
+}
+
+struct ixgbe_mbx_operations ixgbevf_mbx_ops = {
+	.init_params   = ixgbevf_init_mbx_params_vf,
+	.read          = ixgbevf_read_mbx_vf,
+	.write         = ixgbevf_write_mbx_vf,
+	.read_posted   = ixgbevf_read_posted_mbx,
+	.write_posted  = ixgbevf_write_posted_mbx,
+	.check_for_msg = ixgbevf_check_for_msg_vf,
+	.check_for_ack = ixgbevf_check_for_ack_vf,
+	.check_for_rst = ixgbevf_check_for_rst_vf,
+};
+
diff --git a/drivers/net/ixgbevf/mbx.h b/drivers/net/ixgbevf/mbx.h
new file mode 100644
index 0000000..1b0e0bf
--- /dev/null
+++ b/drivers/net/ixgbevf/mbx.h
@@ -0,0 +1,100 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBE_MBX_H_
+#define _IXGBE_MBX_H_
+
+#include "vf.h"
+
+#define IXGBE_VFMAILBOX_SIZE        16 /* 16 32 bit words - 64 bytes */
+#define IXGBE_ERR_MBX               -100
+
+#define IXGBE_VFMAILBOX             0x002FC
+#define IXGBE_VFMBMEM               0x00200
+
+/* Define mailbox register bits */
+#define IXGBE_VFMAILBOX_REQ      0x00000001 /* Request for PF Ready bit */
+#define IXGBE_VFMAILBOX_ACK      0x00000002 /* Ack PF message received */
+#define IXGBE_VFMAILBOX_VFU      0x00000004 /* VF owns the mailbox buffer */
+#define IXGBE_VFMAILBOX_PFU      0x00000008 /* PF owns the mailbox buffer */
+#define IXGBE_VFMAILBOX_PFSTS    0x00000010 /* PF wrote a message in the MB */
+#define IXGBE_VFMAILBOX_PFACK    0x00000020 /* PF ack the previous VF msg */
+#define IXGBE_VFMAILBOX_RSTI     0x00000040 /* PF has reset indication */
+#define IXGBE_VFMAILBOX_RSTD     0x00000080 /* PF has indicated reset done */
+#define IXGBE_VFMAILBOX_R2C_BITS 0x000000B0 /* All read to clear bits */
+
+#define IXGBE_PFMAILBOX(x)          (0x04B00 + (4 * x))
+#define IXGBE_PFMBMEM(vfn)          (0x13000 + (64 * vfn))
+
+#define IXGBE_PFMAILBOX_STS   0x00000001 /* Initiate message send to VF */
+#define IXGBE_PFMAILBOX_ACK   0x00000002 /* Ack message recv'd from VF */
+#define IXGBE_PFMAILBOX_VFU   0x00000004 /* VF owns the mailbox buffer */
+#define IXGBE_PFMAILBOX_PFU   0x00000008 /* PF owns the mailbox buffer */
+#define IXGBE_PFMAILBOX_RVFU  0x00000010 /* Reset VFU - used when VF stuck */
+
+#define IXGBE_MBVFICR_VFREQ_MASK 0x0000FFFF /* bits for VF messages */
+#define IXGBE_MBVFICR_VFREQ_VF1  0x00000001 /* bit for VF 1 message */
+#define IXGBE_MBVFICR_VFACK_MASK 0xFFFF0000 /* bits for VF acks */
+#define IXGBE_MBVFICR_VFACK_VF1  0x00010000 /* bit for VF 1 ack */
+
+
+/* If it's a IXGBE_VF_* msg then it originates in the VF and is sent to the
+ * PF.  The reverse is true if it is IXGBE_PF_*.
+ * Message ACK's are the value or'd with 0xF0000000
+ */
+#define IXGBE_VT_MSGTYPE_ACK      0x80000000  /* Messages below or'd with
+					       * this are the ACK */
+#define IXGBE_VT_MSGTYPE_NACK     0x40000000  /* Messages below or'd with
+					       * this are the NACK */
+#define IXGBE_VT_MSGTYPE_CTS      0x20000000  /* Indicates that VF is still
+					       *  clear to send requests */
+#define IXGBE_VT_MSGINFO_SHIFT    16
+/* bits 23:16 are used for exra info for certain messages */
+#define IXGBE_VT_MSGINFO_MASK     (0xFF << IXGBE_VT_MSGINFO_SHIFT)
+
+#define IXGBE_VF_RESET            0x01 /* VF requests reset */
+#define IXGBE_VF_SET_MAC_ADDR     0x02 /* VF requests PF to set MAC addr */
+#define IXGBE_VF_SET_MULTICAST    0x03 /* VF requests PF to set MC addr */
+#define IXGBE_VF_SET_VLAN         0x04 /* VF requests PF to set VLAN */
+#define IXGBE_VF_SET_LPE          0x05 /* VF requests PF to set VMOLR.LPE */
+
+/* length of permanent address message returned from PF */
+#define IXGBE_VF_PERMADDR_MSG_LEN 4
+/* word in permanent address message with the current multicast type */
+#define IXGBE_VF_MC_TYPE_WORD     3
+
+#define IXGBE_PF_CONTROL_MSG      0x0100 /* PF control message */
+
+#define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */
+#define IXGBE_VF_MBX_INIT_DELAY   500  /* microseconds between retries */
+
+/* forward declaration of the HW struct */
+struct ixgbe_hw;
+
+s32 ixgbevf_init_mbx_params_vf(struct ixgbe_hw *);
+
+#endif /* _IXGBE_MBX_H_ */

Re: [RFC PATCH v2 03/12] ixgbevf: Mailbox communication

[Ben Hutchings]

On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
> From: Greg Rose <gregory.v.rose@intel.com>
> 
> The 82599 virtual function device and the master 82599 physical function
> device implement a mailbox utility for communication between the devices
> using some SRAM scratch memory and a doorbell/answering mechanism enabled
> via interrupt and/or polling.  This C module and accompanying header
> file implement the base functions for use of this feature.
[...]
> diff --git a/drivers/net/ixgbevf/mbx.c b/drivers/net/ixgbevf/mbx.c
> new file mode 100644
> index 0000000..a6e81fe
> --- /dev/null
> +++ b/drivers/net/ixgbevf/mbx.c
[...]
> +/**
> + *  ixgbevf_poll_for_msg - Wait for message notification
> + *  @hw: pointer to the HW structure
> + *
> + *  returns 0 if it successfully received a message notification
> + **/
> +static s32 ixgbevf_poll_for_msg(struct ixgbe_hw *hw)
> +{
> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
> +	int countdown = mbx->timeout;
> +
> +	if (!mbx->ops.check_for_msg)
> +		goto out;
[...]

Can this ever be true?  Wouldn't that be a bug?

There are several similar, apparently unnecessary, tests in the
following functions.

Ben.

-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

RE: [RFC PATCH v2 03/12] ixgbevf: Mailbox communication

[Rose, Gregory V]

>-----Original Message-----
>From: Ben Hutchings [mailto:bhutchings@solarflare.com]
>Sent: Wednesday, December 23, 2009 12:28 PM
>To: Kirsher, Jeffrey T
>Cc: netdev@vger.kernel.org; gospo@redhat.com; Rose, Gregory V
>Subject: Re: [RFC PATCH v2 03/12] ixgbevf: Mailbox communication
>
>On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
>> From: Greg Rose <gregory.v.rose@intel.com>
>>
>> The 82599 virtual function device and the master 82599 physical
>function
>> device implement a mailbox utility for communication between the
>devices
>> using some SRAM scratch memory and a doorbell/answering mechanism
>enabled
>> via interrupt and/or polling.  This C module and accompanying header
>> file implement the base functions for use of this feature.
>[...]
>> diff --git a/drivers/net/ixgbevf/mbx.c b/drivers/net/ixgbevf/mbx.c
>> new file mode 100644
>> index 0000000..a6e81fe
>> --- /dev/null
>> +++ b/drivers/net/ixgbevf/mbx.c
>[...]
>> +/**
>> + *  ixgbevf_poll_for_msg - Wait for message notification
>> + *  @hw: pointer to the HW structure
>> + *
>> + *  returns 0 if it successfully received a message notification
>> + **/
>> +static s32 ixgbevf_poll_for_msg(struct ixgbe_hw *hw)
>> +{
>> +	struct ixgbe_mbx_info *mbx = &hw->mbx;
>> +	int countdown = mbx->timeout;
>> +
>> +	if (!mbx->ops.check_for_msg)
>> +		goto out;
>[...]
>
>Can this ever be true?

In this case no.

>Wouldn't that be a bug?

Most definitely.

>
>There are several similar, apparently unnecessary, tests in the
>following functions.

Yeah, the code was derived from a more general purpose code base.  I'll remove these unnecessary tests from the kernel driver.

Regards,

- Greg

[RFC PATCH v2 04/12] ixgbevf: Driver main and ethool interface module and main header

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

These modules and header contain the Linux OS network interface code and core
interrupt and network send/receive handlers.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbevf/ethtool.c      |  718 +++++++
 drivers/net/ixgbevf/ixgbevf.h      |  318 +++
 drivers/net/ixgbevf/ixgbevf_main.c | 3594 ++++++++++++++++++++++++++++++++++++
 3 files changed, 4630 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbevf/ethtool.c
 create mode 100644 drivers/net/ixgbevf/ixgbevf.h
 create mode 100644 drivers/net/ixgbevf/ixgbevf_main.c

diff --git a/drivers/net/ixgbevf/ethtool.c b/drivers/net/ixgbevf/ethtool.c
new file mode 100644
index 0000000..6cf0110
--- /dev/null
+++ b/drivers/net/ixgbevf/ethtool.c
@@ -0,0 +1,718 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+/* ethtool support for ixgbevf */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/vmalloc.h>
+#include <linux/if_vlan.h>
+#include <linux/uaccess.h>
+
+#include "ixgbevf.h"
+
+#define IXGBE_ALL_RAR_ENTRIES 16
+
+#ifdef ETHTOOL_GSTATS
+struct ixgbe_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+	int base_stat_offset;
+};
+
+#define IXGBEVF_STAT(m, b)  sizeof(((struct ixgbevf_adapter *)0)->m), \
+			    offsetof(struct ixgbevf_adapter, m),      \
+			    offsetof(struct ixgbevf_adapter, b)
+static struct ixgbe_stats ixgbe_gstrings_stats[] = {
+	{"rx_packets", IXGBEVF_STAT(stats.vfgprc, stats.base_vfgprc)},
+	{"tx_packets", IXGBEVF_STAT(stats.vfgptc, stats.base_vfgptc)},
+	{"rx_bytes", IXGBEVF_STAT(stats.vfgorc, stats.base_vfgorc)},
+	{"tx_bytes", IXGBEVF_STAT(stats.vfgotc, stats.base_vfgotc)},
+	{"tx_busy", IXGBEVF_STAT(tx_busy, zero_base)},
+	{"multicast", IXGBEVF_STAT(stats.vfmprc, stats.base_vfmprc)},
+	{"rx_csum_offload_good", IXGBEVF_STAT(hw_csum_rx_good, zero_base)},
+	{"rx_csum_offload_errors", IXGBEVF_STAT(hw_csum_rx_error, zero_base)},
+	{"tx_csum_offload_ctxt", IXGBEVF_STAT(hw_csum_tx_good, zero_base)},
+	{"rx_header_split", IXGBEVF_STAT(rx_hdr_split, zero_base)},
+};
+
+#define IXGBE_QUEUE_STATS_LEN 0
+#define IXGBE_GLOBAL_STATS_LEN	ARRAY_SIZE(ixgbe_gstrings_stats)
+
+#define IXGBEVF_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + IXGBE_QUEUE_STATS_LEN)
+#endif /* ETHTOOL_GSTATS */
+#ifdef ETHTOOL_TEST
+static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
+	"Register test  (offline)",
+	"Link test   (on/offline)"
+};
+#define IXGBE_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN)
+#endif /* ETHTOOL_TEST */
+
+static int ixgbevf_get_settings(struct net_device *netdev,
+				struct ethtool_cmd *ecmd)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 link_speed = 0;
+	bool link_up;
+
+	ecmd->supported = SUPPORTED_10000baseT_Full;
+	ecmd->autoneg = AUTONEG_DISABLE;
+	ecmd->transceiver = XCVR_DUMMY1;
+	ecmd->port = -1;
+
+	hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
+
+	if (link_up) {
+		ecmd->speed = (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
+			       SPEED_10000 : SPEED_1000;
+		ecmd->duplex = DUPLEX_FULL;
+	} else {
+		ecmd->speed = -1;
+		ecmd->duplex = -1;
+	}
+
+	return 0;
+}
+
+static u32 ixgbevf_get_rx_csum(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	return adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED;
+}
+
+static int ixgbevf_set_rx_csum(struct net_device *netdev, u32 data)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	if (data)
+		adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED;
+	else
+		adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED;
+
+	if (netif_running(netdev)) {
+		if (!adapter->dev_closed)
+			ixgbevf_reinit_locked(adapter);
+	} else {
+		ixgbevf_reset(adapter);
+	}
+
+	return 0;
+}
+
+static int ixgbevf_set_tso(struct net_device *netdev, u32 data)
+{
+	if (data) {
+		netdev->features |= NETIF_F_TSO;
+		netdev->features |= NETIF_F_TSO6;
+	} else {
+		netif_tx_stop_all_queues(netdev);
+		netdev->features &= ~NETIF_F_TSO;
+		netdev->features &= ~NETIF_F_TSO6;
+		netif_tx_start_all_queues(netdev);
+	}
+	return 0;
+}
+
+static u32 ixgbevf_get_msglevel(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	return adapter->msg_enable;
+}
+
+static void ixgbevf_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	adapter->msg_enable = data;
+}
+
+#define IXGBE_GET_STAT(_A_, _R_) (_A_->stats._R_)
+
+static char *ixgbevf_reg_names[] = {
+	"IXGBE_VFCTRL",
+	"IXGBE_VFSTATUS",
+	"IXGBE_VFLINKS",
+	"IXGBE_VFRXMEMWRAP",
+	"IXGBE_VFRTIMER",
+	"IXGBE_VTEICR",
+	"IXGBE_VTEICS",
+	"IXGBE_VTEIMS",
+	"IXGBE_VTEIMC",
+	"IXGBE_VTEIAC",
+	"IXGBE_VTEIAM",
+	"IXGBE_VTEITR",
+	"IXGBE_VTIVAR",
+	"IXGBE_VTIVAR_MISC",
+	"IXGBE_VFRDBAL0",
+	"IXGBE_VFRDBAL1",
+	"IXGBE_VFRDBAH0",
+	"IXGBE_VFRDBAH1",
+	"IXGBE_VFRDLEN0",
+	"IXGBE_VFRDLEN1",
+	"IXGBE_VFRDH0",
+	"IXGBE_VFRDH1",
+	"IXGBE_VFRDT0",
+	"IXGBE_VFRDT1",
+	"IXGBE_VFRXDCTL0",
+	"IXGBE_VFRXDCTL1",
+	"IXGBE_VFSRRCTL0",
+	"IXGBE_VFSRRCTL1",
+	"IXGBE_VFPSRTYPE",
+	"IXGBE_VFTDBAL0",
+	"IXGBE_VFTDBAL1",
+	"IXGBE_VFTDBAH0",
+	"IXGBE_VFTDBAH1",
+	"IXGBE_VFTDLEN0",
+	"IXGBE_VFTDLEN1",
+	"IXGBE_VFTDH0",
+	"IXGBE_VFTDH1",
+	"IXGBE_VFTDT0",
+	"IXGBE_VFTDT1",
+	"IXGBE_VFTXDCTL0",
+	"IXGBE_VFTXDCTL1",
+	"IXGBE_VFTDWBAL0",
+	"IXGBE_VFTDWBAL1",
+	"IXGBE_VFTDWBAH0",
+	"IXGBE_VFTDWBAH1"
+};
+
+
+static int ixgbevf_get_regs_len(struct net_device *netdev)
+{
+	return (ARRAY_SIZE(ixgbevf_reg_names)) * sizeof(u32);
+}
+
+static void ixgbevf_get_regs(struct net_device *netdev,
+			     struct ethtool_regs *regs,
+			     void *p)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u32 regs_len = ixgbevf_get_regs_len(netdev);
+	u8 i;
+
+	memset(p, 0, regs_len);
+
+	regs->version = (1 << 24) | hw->revision_id << 16 | hw->device_id;
+
+	/* General Registers */
+	regs_buff[0] = IXGBE_READ_REG(hw, IXGBE_VFCTRL);
+	regs_buff[1] = IXGBE_READ_REG(hw, IXGBE_VFSTATUS);
+	regs_buff[2] = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
+	regs_buff[3] = IXGBE_READ_REG(hw, IXGBE_VFRXMEMWRAP);
+	regs_buff[4] = IXGBE_READ_REG(hw, IXGBE_VFRTIMER);
+
+	/* Interrupt */
+	/* don't read EICR because it can clear interrupt causes, instead
+	 * read EICS which is a shadow but doesn't clear EICR */
+	regs_buff[5] = IXGBE_READ_REG(hw, IXGBE_VTEICS);
+	regs_buff[6] = IXGBE_READ_REG(hw, IXGBE_VTEICS);
+	regs_buff[7] = IXGBE_READ_REG(hw, IXGBE_VTEIMS);
+	regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_VTEIMC);
+	regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_VTEIAC);
+	regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_VTEIAM);
+	regs_buff[11] = IXGBE_READ_REG(hw, IXGBE_VTEITR(0));
+	regs_buff[12] = IXGBE_READ_REG(hw, IXGBE_VTIVAR(0));
+	regs_buff[13] = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC);
+
+	/* Receive DMA */
+	for (i = 0; i < 2; i++)
+		regs_buff[14 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAL(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[16 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAH(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[18 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDLEN(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[20 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDH(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[22 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDT(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[24 + i] = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[26 + i] = IXGBE_READ_REG(hw, IXGBE_VFSRRCTL(i));
+
+	/* Receive */
+	regs_buff[28] = IXGBE_READ_REG(hw, IXGBE_VFPSRTYPE);
+
+	/* Transmit */
+	for (i = 0; i < 2; i++)
+		regs_buff[29 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAL(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[31 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAH(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[33 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDLEN(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDH(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[37 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDT(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[39 + i] = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[41 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAL(i));
+	for (i = 0; i < 2; i++)
+		regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAH(i));
+
+	for (i = 0; i < regs_len; i++)
+		printk(KERN_INFO "%s\t%8.8x\n",
+		       ixgbevf_reg_names[i], regs_buff[i]);
+}
+
+static void ixgbevf_get_drvinfo(struct net_device *netdev,
+				struct ethtool_drvinfo *drvinfo)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver, ixgbevf_driver_name, 32);
+	strlcpy(drvinfo->version, ixgbevf_driver_version, 32);
+
+	strlcpy(drvinfo->fw_version, "N/A", 4);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+}
+
+static void ixgbevf_get_ringparam(struct net_device *netdev,
+				  struct ethtool_ringparam *ring)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbevf_ring *tx_ring = adapter->tx_ring;
+	struct ixgbevf_ring *rx_ring = adapter->rx_ring;
+
+	ring->rx_max_pending = IXGBEVF_MAX_RXD;
+	ring->tx_max_pending = IXGBEVF_MAX_TXD;
+	ring->rx_mini_max_pending = 0;
+	ring->rx_jumbo_max_pending = 0;
+	ring->rx_pending = rx_ring->count;
+	ring->tx_pending = tx_ring->count;
+	ring->rx_mini_pending = 0;
+	ring->rx_jumbo_pending = 0;
+}
+
+static int ixgbevf_set_ringparam(struct net_device *netdev,
+				 struct ethtool_ringparam *ring)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbevf_ring *tx_ring, *rx_ring;
+	int i, err;
+	u32 new_rx_count, new_tx_count;
+	bool need_update = false;
+
+	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
+		return -EINVAL;
+
+	new_rx_count = max(ring->rx_pending, (u32)IXGBEVF_MIN_RXD);
+	new_rx_count = min(new_rx_count, (u32)IXGBEVF_MAX_RXD);
+	new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	new_tx_count = max(ring->tx_pending, (u32)IXGBEVF_MIN_TXD);
+	new_tx_count = min(new_tx_count, (u32)IXGBEVF_MAX_TXD);
+	new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	if ((new_tx_count == adapter->tx_ring->count) &&
+	    (new_rx_count == adapter->rx_ring->count)) {
+		/* nothing to do */
+		return 0;
+	}
+
+	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
+		msleep(1);
+
+	tx_ring = kcalloc(adapter->num_tx_queues,
+			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
+	if (!tx_ring) {
+		err = -ENOMEM;
+		goto err_setup;
+	}
+
+	if (new_tx_count != adapter->tx_ring_count) {
+		memcpy(tx_ring, adapter->tx_ring,
+		       adapter->num_tx_queues * sizeof(struct ixgbevf_ring));
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			tx_ring[i].count = new_tx_count;
+			err = ixgbevf_setup_tx_resources(adapter,
+							 &tx_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					ixgbevf_free_tx_resources(adapter,
+								  &tx_ring[i]);
+				}
+				goto err_setup;
+			}
+			tx_ring[i].v_idx = adapter->tx_ring[i].v_idx;
+		}
+		need_update = true;
+	}
+
+	rx_ring = kcalloc(adapter->num_rx_queues,
+			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
+	if ((!rx_ring) && (need_update)) {
+		for (i = 0; i < adapter->num_tx_queues; i++)
+			ixgbevf_free_tx_resources(adapter, &tx_ring[i]);
+		kfree(tx_ring);
+		err = -ENOMEM;
+		goto err_setup;
+	}
+
+	if (new_rx_count != adapter->rx_ring_count) {
+		memcpy(rx_ring, adapter->rx_ring,
+		       adapter->num_rx_queues * sizeof(struct ixgbevf_ring));
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			rx_ring[i].count = new_rx_count;
+			err = ixgbevf_setup_rx_resources(adapter,
+							 &rx_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					ixgbevf_free_rx_resources(adapter,
+								  &rx_ring[i]);
+				}
+				goto err_setup;
+			}
+			rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
+		}
+		need_update = true;
+	}
+
+	/* if rings need to be updated, here's the place to do it in one shot */
+	if (need_update) {
+		if (netif_running(netdev))
+			ixgbevf_down(adapter);
+
+		/* tx */
+		if (new_tx_count != adapter->tx_ring_count) {
+			kfree(adapter->tx_ring);
+			adapter->tx_ring = tx_ring;
+			tx_ring = NULL;
+			adapter->tx_ring_count = new_tx_count;
+		}
+
+		/* rx */
+		if (new_rx_count != adapter->rx_ring_count) {
+			kfree(adapter->rx_ring);
+			adapter->rx_ring = rx_ring;
+			rx_ring = NULL;
+			adapter->rx_ring_count = new_rx_count;
+		}
+	}
+
+	/* success! */
+	err = 0;
+	if (netif_running(netdev))
+		ixgbevf_up(adapter);
+
+err_setup:
+	clear_bit(__IXGBEVF_RESETTING, &adapter->state);
+	return err;
+}
+
+static int ixgbevf_get_sset_count(struct net_device *dev, int stringset)
+{
+       switch (stringset) {
+       case ETH_SS_TEST:
+	       return IXGBE_TEST_LEN;
+       case ETH_SS_STATS:
+	       return IXGBE_GLOBAL_STATS_LEN;
+       default:
+	       return -EINVAL;
+       }
+}
+
+static void ixgbevf_get_ethtool_stats(struct net_device *netdev,
+				      struct ethtool_stats *stats, u64 *data)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	ixgbevf_update_stats(adapter);
+	for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) {
+		char *p = (char *)adapter +
+			ixgbe_gstrings_stats[i].stat_offset;
+		char *b = (char *)adapter +
+			ixgbe_gstrings_stats[i].base_stat_offset;
+		data[i] = ((ixgbe_gstrings_stats[i].sizeof_stat ==
+			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p) -
+			  ((ixgbe_gstrings_stats[i].sizeof_stat ==
+			    sizeof(u64)) ? *(u64 *)b : *(u32 *)b);
+	}
+}
+
+static void ixgbevf_get_strings(struct net_device *netdev, u32 stringset,
+				u8 *data)
+{
+	char *p = (char *)data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_TEST:
+		memcpy(data, *ixgbe_gstrings_test,
+		       IXGBE_TEST_LEN * ETH_GSTRING_LEN);
+		break;
+	case ETH_SS_STATS:
+		for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) {
+			memcpy(p, ixgbe_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	}
+}
+
+static int ixgbevf_link_test(struct ixgbevf_adapter *adapter, u64 *data)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	bool link_up;
+	u32 link_speed = 0;
+	*data = 0;
+
+	hw->mac.ops.check_link(hw, &link_speed, &link_up, true);
+	if (!link_up)
+		*data = 1;
+
+	return *data;
+}
+
+/* ethtool register test data */
+struct ixgbevf_reg_test {
+	u16 reg;
+	u8  array_len;
+	u8  test_type;
+	u32 mask;
+	u32 write;
+};
+
+/* In the hardware, registers are laid out either singly, in arrays
+ * spaced 0x40 bytes apart, or in contiguous tables.  We assume
+ * most tests take place on arrays or single registers (handled
+ * as a single-element array) and special-case the tables.
+ * Table tests are always pattern tests.
+ *
+ * We also make provision for some required setup steps by specifying
+ * registers to be written without any read-back testing.
+ */
+
+#define PATTERN_TEST	1
+#define SET_READ_TEST	2
+#define WRITE_NO_TEST	3
+#define TABLE32_TEST	4
+#define TABLE64_TEST_LO	5
+#define TABLE64_TEST_HI	6
+
+/* default VF register test */
+static struct ixgbevf_reg_test reg_test_vf[] = {
+	{ IXGBE_VFRDBAL(0), 2, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFF80 },
+	{ IXGBE_VFRDBAH(0), 2, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
+	{ IXGBE_VFRDLEN(0), 2, PATTERN_TEST, 0x000FFF80, 0x000FFFFF },
+	{ IXGBE_VFRXDCTL(0), 2, WRITE_NO_TEST, 0, IXGBE_RXDCTL_ENABLE },
+	{ IXGBE_VFRDT(0), 2, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
+	{ IXGBE_VFRXDCTL(0), 2, WRITE_NO_TEST, 0, 0 },
+	{ IXGBE_VFTDBAL(0), 2, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF },
+	{ IXGBE_VFTDBAH(0), 2, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
+	{ IXGBE_VFTDLEN(0), 2, PATTERN_TEST, 0x000FFF80, 0x000FFF80 },
+	{ 0, 0, 0, 0 }
+};
+
+#define REG_PATTERN_TEST(R, M, W)                                             \
+{                                                                             \
+	u32 pat, val, before;                                                 \
+	const u32 _test[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; \
+	for (pat = 0; pat < ARRAY_SIZE(_test); pat++) {                       \
+		before = readl(adapter->hw.hw_addr + R);                      \
+		writel((_test[pat] & W), (adapter->hw.hw_addr + R));          \
+		val = readl(adapter->hw.hw_addr + R);                         \
+		if (val != (_test[pat] & W & M)) {                            \
+			hw_dbg(&adapter->hw,                                  \
+			"pattern test reg %04X failed: got "                  \
+			"0x%08X expected 0x%08X\n",                           \
+			R, val, (_test[pat] & W & M));                        \
+			*data = R;                                            \
+			writel(before, adapter->hw.hw_addr + R);              \
+			return 1;                                             \
+		}                                                             \
+		writel(before, adapter->hw.hw_addr + R);                      \
+	}                                                                     \
+}
+
+#define REG_SET_AND_CHECK(R, M, W)                                            \
+{                                                                             \
+	u32 val, before;                                                      \
+	before = readl(adapter->hw.hw_addr + R);                              \
+	writel((W & M), (adapter->hw.hw_addr + R));                           \
+	val = readl(adapter->hw.hw_addr + R);                                 \
+	if ((W & M) != (val & M)) {                                           \
+		printk(KERN_ERR "set/check reg %04X test failed: got 0x%08X " \
+				 "expected 0x%08X\n", R, (val & M), (W & M)); \
+		*data = R;                                                    \
+		writel(before, (adapter->hw.hw_addr + R));                    \
+		return 1;                                                     \
+	}                                                                     \
+	writel(before, (adapter->hw.hw_addr + R));                            \
+}
+
+static int ixgbevf_reg_test(struct ixgbevf_adapter *adapter, u64 *data)
+{
+	struct ixgbevf_reg_test *test;
+	u32 i;
+
+	test = reg_test_vf;
+
+	/*
+	 * Perform the register test, looping through the test table
+	 * until we either fail or reach the null entry.
+	 */
+	while (test->reg) {
+		for (i = 0; i < test->array_len; i++) {
+			switch (test->test_type) {
+			case PATTERN_TEST:
+				REG_PATTERN_TEST(test->reg + (i * 0x40),
+						test->mask,
+						test->write);
+				break;
+			case SET_READ_TEST:
+				REG_SET_AND_CHECK(test->reg + (i * 0x40),
+						test->mask,
+						test->write);
+				break;
+			case WRITE_NO_TEST:
+				writel(test->write,
+				       (adapter->hw.hw_addr + test->reg)
+				       + (i * 0x40));
+				break;
+			case TABLE32_TEST:
+				REG_PATTERN_TEST(test->reg + (i * 4),
+						test->mask,
+						test->write);
+				break;
+			case TABLE64_TEST_LO:
+				REG_PATTERN_TEST(test->reg + (i * 8),
+						test->mask,
+						test->write);
+				break;
+			case TABLE64_TEST_HI:
+				REG_PATTERN_TEST((test->reg + 4) + (i * 8),
+						test->mask,
+						test->write);
+				break;
+			}
+		}
+		test++;
+	}
+
+	*data = 0;
+	return *data;
+}
+
+static void ixgbevf_diag_test(struct net_device *netdev,
+			      struct ethtool_test *eth_test, u64 *data)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	bool if_running = netif_running(netdev);
+
+	set_bit(__IXGBEVF_TESTING, &adapter->state);
+	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+		/* Offline tests */
+
+		hw_dbg(&adapter->hw, "offline testing starting\n");
+
+		/* Link test performed before hardware reset so autoneg doesn't
+		 * interfere with test result */
+		if (ixgbevf_link_test(adapter, &data[1]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		if (if_running)
+			/* indicate we're in test mode */
+			dev_close(netdev);
+		else
+			ixgbevf_reset(adapter);
+
+		hw_dbg(&adapter->hw, "register testing starting\n");
+		if (ixgbevf_reg_test(adapter, &data[0]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		ixgbevf_reset(adapter);
+
+		clear_bit(__IXGBEVF_TESTING, &adapter->state);
+		if (if_running)
+			dev_open(netdev);
+	} else {
+		hw_dbg(&adapter->hw, "online testing starting\n");
+		/* Online tests */
+		if (ixgbevf_link_test(adapter, &data[1]))
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		/* Online tests aren't run; pass by default */
+		data[0] = 0;
+
+		clear_bit(__IXGBEVF_TESTING, &adapter->state);
+	}
+	msleep_interruptible(4 * 1000);
+}
+
+static int ixgbevf_nway_reset(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	if (netif_running(netdev)) {
+		if (!adapter->dev_closed)
+			ixgbevf_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
+static struct ethtool_ops ixgbevf_ethtool_ops = {
+	.get_settings           = ixgbevf_get_settings,
+	.get_drvinfo            = ixgbevf_get_drvinfo,
+	.get_regs_len           = ixgbevf_get_regs_len,
+	.get_regs               = ixgbevf_get_regs,
+	.nway_reset             = ixgbevf_nway_reset,
+	.get_link               = ethtool_op_get_link,
+	.get_ringparam          = ixgbevf_get_ringparam,
+	.set_ringparam          = ixgbevf_set_ringparam,
+	.get_rx_csum            = ixgbevf_get_rx_csum,
+	.set_rx_csum            = ixgbevf_set_rx_csum,
+	.get_tx_csum            = ethtool_op_get_tx_csum,
+	.set_tx_csum            = ethtool_op_set_tx_ipv6_csum,
+	.get_sg                 = ethtool_op_get_sg,
+	.set_sg                 = ethtool_op_set_sg,
+	.get_msglevel           = ixgbevf_get_msglevel,
+	.set_msglevel           = ixgbevf_set_msglevel,
+	.get_tso                = ethtool_op_get_tso,
+	.set_tso                = ixgbevf_set_tso,
+	.self_test              = ixgbevf_diag_test,
+	.get_sset_count         = ixgbevf_get_sset_count,
+	.get_strings            = ixgbevf_get_strings,
+	.get_ethtool_stats      = ixgbevf_get_ethtool_stats,
+};
+
+void ixgbevf_set_ethtool_ops(struct net_device *netdev)
+{
+	SET_ETHTOOL_OPS(netdev, &ixgbevf_ethtool_ops);
+}
diff --git a/drivers/net/ixgbevf/ixgbevf.h b/drivers/net/ixgbevf/ixgbevf.h
new file mode 100644
index 0000000..f7015ef
--- /dev/null
+++ b/drivers/net/ixgbevf/ixgbevf.h
@@ -0,0 +1,318 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBEVF_H_
+#define _IXGBEVF_H_
+
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+
+#include "vf.h"
+
+/* wrapper around a pointer to a socket buffer,
+ * so a DMA handle can be stored along with the buffer */
+struct ixgbevf_tx_buffer {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+	unsigned long time_stamp;
+	u16 length;
+	u16 next_to_watch;
+	u16 mapped_as_page;
+};
+
+struct ixgbevf_rx_buffer {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+	struct page *page;
+	dma_addr_t page_dma;
+	unsigned int page_offset;
+};
+
+struct ixgbevf_ring {
+	struct ixgbevf_adapter *adapter;  /* backlink */
+	void *desc;			/* descriptor ring memory */
+	dma_addr_t dma;			/* phys. address of descriptor ring */
+	unsigned int size;		/* length in bytes */
+	unsigned int count;		/* amount of descriptors */
+	unsigned int next_to_use;
+	unsigned int next_to_clean;
+
+	int queue_index; /* needed for multiqueue queue management */
+	union {
+		struct ixgbevf_tx_buffer *tx_buffer_info;
+		struct ixgbevf_rx_buffer *rx_buffer_info;
+	};
+
+	u16 head;
+	u16 tail;
+
+	unsigned int total_bytes;
+	unsigned int total_packets;
+
+	u16 reg_idx; /* holds the special value that gets the hardware register
+		      * offset associated with this ring, which is different
+		      * for DCB and RSS modes */
+
+#if defined(CONFIG_DCA) || defined(CONFIG_DCA_MODULE)
+	/* cpu for tx queue */
+	int cpu;
+#endif
+
+	u64 v_idx; /* maps directly to the index for this ring in the hardware
+		    * vector array, can also be used for finding the bit in EICR
+		    * and friends that represents the vector for this ring */
+
+	u16 work_limit;                /* max work per interrupt */
+	u16 rx_buf_len;
+};
+
+enum ixgbevf_ring_f_enum {
+	RING_F_NONE = 0,
+	RING_F_ARRAY_SIZE      /* must be last in enum set */
+};
+
+struct ixgbevf_ring_feature {
+	int indices;
+	int mask;
+};
+
+/* How many Rx Buffers do we bundle into one write to the hardware ? */
+#define IXGBEVF_RX_BUFFER_WRITE	16	/* Must be power of 2 */
+
+#define MAX_RX_QUEUES 1
+#define MAX_TX_QUEUES 1
+
+#define IXGBEVF_DEFAULT_TXD   1024
+#define IXGBEVF_DEFAULT_RXD   512
+#define IXGBEVF_MAX_TXD       4096
+#define IXGBEVF_MIN_TXD       64
+#define IXGBEVF_MAX_RXD       4096
+#define IXGBEVF_MIN_RXD       64
+
+/* Supported Rx Buffer Sizes */
+#define IXGBEVF_RXBUFFER_64    64     /* Used for packet split */
+#define IXGBEVF_RXBUFFER_128   128    /* Used for packet split */
+#define IXGBEVF_RXBUFFER_256   256    /* Used for packet split */
+#define IXGBEVF_RXBUFFER_2048  2048
+#define IXGBEVF_MAX_RXBUFFER   16384  /* largest size for single descriptor */
+
+#define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256
+
+#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+
+#define IXGBE_TX_FLAGS_CSUM		(u32)(1)
+#define IXGBE_TX_FLAGS_VLAN		(u32)(1 << 1)
+#define IXGBE_TX_FLAGS_TSO		(u32)(1 << 2)
+#define IXGBE_TX_FLAGS_IPV4		(u32)(1 << 3)
+#define IXGBE_TX_FLAGS_FCOE		(u32)(1 << 4)
+#define IXGBE_TX_FLAGS_FSO		(u32)(1 << 5)
+#define IXGBE_TX_FLAGS_VLAN_MASK	0xffff0000
+#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK	0x0000e000
+#define IXGBE_TX_FLAGS_VLAN_SHIFT	16
+
+/* MAX_MSIX_Q_VECTORS of these are allocated,
+ * but we only use one per queue-specific vector.
+ */
+struct ixgbevf_q_vector {
+	struct ixgbevf_adapter *adapter;
+	struct napi_struct napi;
+	DECLARE_BITMAP(rxr_idx, MAX_RX_QUEUES); /* Rx ring indices */
+	DECLARE_BITMAP(txr_idx, MAX_TX_QUEUES); /* Tx ring indices */
+	u8 rxr_count;     /* Rx ring count assigned to this vector */
+	u8 txr_count;     /* Tx ring count assigned to this vector */
+	u8 tx_itr;
+	u8 rx_itr;
+	u32 eitr;
+	int v_idx;	  /* vector index in list */
+};
+
+/* Helper macros to switch between ints/sec and what the register uses.
+ * And yes, it's the same math going both ways.  The lowest value
+ * supported by all of the ixgbe hardware is 8.
+ */
+#define EITR_INTS_PER_SEC_TO_REG(_eitr) \
+	((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8)
+#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG
+
+#define IXGBE_DESC_UNUSED(R) \
+	((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
+	(R)->next_to_clean - (R)->next_to_use - 1)
+
+#define IXGBE_RX_DESC_ADV(R, i)	    \
+	(&(((union ixgbe_adv_rx_desc *)((R).desc))[i]))
+#define IXGBE_TX_DESC_ADV(R, i)	    \
+	(&(((union ixgbe_adv_tx_desc *)((R).desc))[i]))
+#define IXGBE_TX_CTXTDESC_ADV(R, i)	    \
+	(&(((struct ixgbe_adv_tx_context_desc *)((R).desc))[i]))
+
+#define IXGBE_MAX_JUMBO_FRAME_SIZE        16128
+
+#define OTHER_VECTOR 1
+#define NON_Q_VECTORS (OTHER_VECTOR)
+
+#define MAX_MSIX_Q_VECTORS 2
+#define MAX_MSIX_COUNT 2
+
+#define MIN_MSIX_Q_VECTORS 2
+#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS)
+
+/* board specific private data structure */
+struct ixgbevf_adapter {
+	struct timer_list watchdog_timer;
+#ifdef NETIF_F_HW_VLAN_TX
+	struct vlan_group *vlgrp;
+#endif
+	u16 bd_number;
+	struct work_struct reset_task;
+	struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
+	char name[MAX_MSIX_COUNT][IFNAMSIZ + 9];
+
+	/* Interrupt Throttle Rate */
+	u32 itr_setting;
+	u16 eitr_low;
+	u16 eitr_high;
+
+	/* TX */
+	struct ixgbevf_ring *tx_ring;	/* One per active queue */
+	int num_tx_queues;
+	u64 restart_queue;
+	u64 hw_csum_tx_good;
+	u64 lsc_int;
+	u64 hw_tso_ctxt;
+	u64 hw_tso6_ctxt;
+	u32 tx_timeout_count;
+	bool detect_tx_hung;
+
+	/* RX */
+	struct ixgbevf_ring *rx_ring;	/* One per active queue */
+	int num_rx_queues;
+	int num_rx_pools;               /* == num_rx_queues in 82598 */
+	int num_rx_queues_per_pool;	/* 1 if 82598, can be many if 82599 */
+	u64 hw_csum_rx_error;
+	u64 hw_rx_no_dma_resources;
+	u64 hw_csum_rx_good;
+	u64 non_eop_descs;
+	int num_msix_vectors;
+	int max_msix_q_vectors;         /* true count of q_vectors for device */
+	struct ixgbevf_ring_feature ring_feature[RING_F_ARRAY_SIZE];
+	struct msix_entry *msix_entries;
+
+	u64 rx_hdr_split;
+	u32 alloc_rx_page_failed;
+	u32 alloc_rx_buff_failed;
+
+	/* Some features need tri-state capability,
+	 * thus the additional *_CAPABLE flags.
+	 */
+	u32 flags;
+#define IXGBE_FLAG_RX_CSUM_ENABLED              (u32)(1)
+#define IXGBE_FLAG_RX_1BUF_CAPABLE              (u32)(1 << 1)
+#define IXGBE_FLAG_RX_PS_CAPABLE                (u32)(1 << 2)
+#define IXGBE_FLAG_RX_PS_ENABLED                (u32)(1 << 3)
+#define IXGBE_FLAG_IN_NETPOLL                   (u32)(1 << 4)
+#define IXGBE_FLAG_IMIR_ENABLED                 (u32)(1 << 5)
+#define IXGBE_FLAG_MQ_CAPABLE                   (u32)(1 << 6)
+#define IXGBE_FLAG_NEED_LINK_UPDATE             (u32)(1 << 7)
+#define IXGBE_FLAG_IN_WATCHDOG_TASK             (u32)(1 << 8)
+	/* OS defined structs */
+	struct net_device *netdev;
+	struct pci_dev *pdev;
+	struct net_device_stats net_stats;
+
+	/* structs defined in ixgbe_vf.h */
+	struct ixgbe_hw hw;
+	u16 msg_enable;
+	struct ixgbevf_hw_stats stats;
+	u64 zero_base;
+	/* Interrupt Throttle Rate */
+	u32 eitr_param;
+
+	unsigned long state;
+	u32 *config_space;
+	u64 tx_busy;
+	unsigned int tx_ring_count;
+	unsigned int rx_ring_count;
+
+	u32 link_speed;
+	bool link_up;
+	unsigned long link_check_timeout;
+
+	struct work_struct watchdog_task;
+	bool netdev_registered;
+	bool dev_closed;
+};
+
+enum ixbgevf_state_t {
+	__IXGBEVF_TESTING,
+	__IXGBEVF_RESETTING,
+	__IXGBEVF_DOWN
+};
+
+enum ixgbevf_boards {
+	board_82599_vf,
+};
+
+extern struct ixgbevf_info ixgbevf_vf_info;
+extern struct ixgbe_mac_operations ixgbevf_mbx_ops;
+
+/* needed by ethtool.c */
+extern char ixgbevf_driver_name[];
+extern const char ixgbevf_driver_version[];
+
+extern int ixgbevf_up(struct ixgbevf_adapter *adapter);
+extern void ixgbevf_down(struct ixgbevf_adapter *adapter);
+extern void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter);
+extern void ixgbevf_reset(struct ixgbevf_adapter *adapter);
+extern void ixgbevf_set_ethtool_ops(struct net_device *netdev);
+extern int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *,
+				      struct ixgbevf_ring *);
+extern int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *,
+				      struct ixgbevf_ring *);
+extern void ixgbevf_free_rx_resources(struct ixgbevf_adapter *,
+				      struct ixgbevf_ring *);
+extern void ixgbevf_free_tx_resources(struct ixgbevf_adapter *,
+				      struct ixgbevf_ring *);
+extern void ixgbevf_update_stats(struct ixgbevf_adapter *adapter);
+
+#ifdef ETHTOOL_OPS_COMPAT
+extern int ethtool_ioctl(struct ifreq *ifr);
+
+#endif
+extern void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter);
+extern void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter);
+
+#ifdef DEBUG
+extern char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw);
+#define hw_dbg(hw, format, arg...) \
+	printk(KERN_DEBUG "%s: " format, ixgbevf_get_hw_dev_name(hw), ##arg)
+#else
+#define hw_dbg(hw, format, arg...) do {} while (0)
+#endif
+
+#endif /* _IXGBEVF_H_ */
diff --git a/drivers/net/ixgbevf/ixgbevf_main.c b/drivers/net/ixgbevf/ixgbevf_main.c
new file mode 100644
index 0000000..20e8ea7
--- /dev/null
+++ b/drivers/net/ixgbevf/ixgbevf_main.c
@@ -0,0 +1,3594 @@
+/*******************************************************************************
+
+  Intel 82599 Virtual Function driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+
+/******************************************************************************
+ Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
+******************************************************************************/
+#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/ipv6.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+
+#include "ixgbevf.h"
+
+char ixgbevf_driver_name[] = "ixgbevf";
+static const char ixgbevf_driver_string[] =
+	"Intel(R) 82599 Virtual Function";
+
+#define DRV_VERSION "1.0.0-k0"
+const char ixgbevf_driver_version[] = DRV_VERSION;
+static char ixgbevf_copyright[] = "Copyright (c) 2009 Intel Corporation.";
+
+static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
+	[board_82599_vf] = &ixgbevf_vf_info,
+};
+
+/* ixgbevf_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 struct pci_device_id ixgbevf_pci_tbl[] = {
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_VF),
+	board_82599_vf},
+
+	/* required last entry */
+	{0, }
+};
+MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl);
+
+MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
+MODULE_DESCRIPTION("Intel(R) 82599 Virtual Function Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+#define DEFAULT_DEBUG_LEVEL_SHIFT 3
+
+/* forward decls */
+static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector);
+static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx,
+			       u32 itr_reg);
+
+/**
+ *  ixgbe_validate_mac_addr - Validate MAC address
+ *  @mac_addr: pointer to MAC address.
+ *
+ *  Tests a MAC address to ensure it is a valid Individual Address
+ **/
+static s32 ixgbevf_validate_mac_addr(u8 *mac_addr)
+{
+	s32 status = 0;
+
+	/* Make sure it is not a multicast address */
+	if (IXGBE_IS_MULTICAST(mac_addr))
+		status = IXGBE_ERR_INVALID_MAC_ADDR;
+	/* Not a broadcast address */
+	else if (IXGBE_IS_BROADCAST(mac_addr))
+		status = IXGBE_ERR_INVALID_MAC_ADDR;
+	/* Reject the zero address */
+	else if (mac_addr[0] == 0 && mac_addr[1] == 0 && mac_addr[2] == 0 &&
+		 mac_addr[3] == 0 && mac_addr[4] == 0 && mac_addr[5] == 0)
+		status = IXGBE_ERR_INVALID_MAC_ADDR;
+	return status;
+}
+
+static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw,
+					   struct ixgbevf_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_VFRDT(rx_ring->reg_idx), val);
+}
+
+/*
+ * 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 ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction,
+			     u8 queue, u8 msix_vector)
+{
+	u32 ivar, index;
+	struct ixgbe_hw *hw = &adapter->hw;
+	if (direction == -1) {
+		/* other causes */
+		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
+		ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC);
+		ivar &= ~0xFF;
+		ivar |= msix_vector;
+		IXGBE_WRITE_REG(hw, IXGBE_VTIVAR_MISC, ivar);
+	} else {
+		/* tx or rx causes */
+		msix_vector |= IXGBE_IVAR_ALLOC_VAL;
+		index = ((16 * (queue & 1)) + (8 * direction));
+		ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR(queue >> 1));
+		ivar &= ~(0xFF << index);
+		ivar |= (msix_vector << index);
+		IXGBE_WRITE_REG(hw, IXGBE_VTIVAR(queue >> 1), ivar);
+	}
+}
+
+static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_adapter *adapter,
+					       struct ixgbevf_tx_buffer
+					       *tx_buffer_info)
+{
+	if (tx_buffer_info->dma) {
+		if (tx_buffer_info->mapped_as_page)
+			pci_unmap_page(adapter->pdev,
+				       tx_buffer_info->dma,
+				       tx_buffer_info->length,
+				       PCI_DMA_TODEVICE);
+		else
+			pci_unmap_single(adapter->pdev,
+					 tx_buffer_info->dma,
+					 tx_buffer_info->length,
+					 PCI_DMA_TODEVICE);
+		tx_buffer_info->dma = 0;
+	}
+	if (tx_buffer_info->skb) {
+		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 inline bool ixgbevf_check_tx_hang(struct ixgbevf_adapter *adapter,
+					 struct ixgbevf_ring *tx_ring,
+					 unsigned int eop)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 head, tail;
+
+	/* Detect a transmit hang in hardware, this serializes the
+	 * check with the clearing of time_stamp and movement of eop */
+	head = readl(hw->hw_addr + tx_ring->head);
+	tail = readl(hw->hw_addr + tx_ring->tail);
+	adapter->detect_tx_hung = false;
+	if ((head != tail) &&
+	    tx_ring->tx_buffer_info[eop].time_stamp &&
+	    time_after(jiffies, tx_ring->tx_buffer_info[eop].time_stamp + HZ)) {
+		/* detected Tx unit hang */
+		union ixgbe_adv_tx_desc *tx_desc;
+		tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop);
+		printk(KERN_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,
+		       head, 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))
+#ifdef MAX_SKB_FRAGS
+#define DESC_NEEDED (TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD) /* skb->data */ + \
+	MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1)      /* for context */
+#else
+#define DESC_NEEDED TXD_USE_COUNT(IXGBE_MAX_DATA_PER_TXD)
+#endif
+
+static void ixgbevf_tx_timeout(struct net_device *netdev);
+
+/**
+ * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes
+ * @adapter: board private structure
+ * @tx_ring: tx ring to clean
+ **/
+static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter,
+				 struct ixgbevf_ring *tx_ring)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
+	struct ixgbevf_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;
+		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;
+
+				/* gso_segs is currently only valid for tcp */
+				segs = skb_shinfo(skb)->gso_segs ?: 1;
+				/* multiply data chunks by size of headers */
+				bytecount = ((segs - 1) * skb_headlen(skb)) +
+					    skb->len;
+				total_packets += segs;
+				total_bytes += bytecount;
+			}
+
+			ixgbevf_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();
+#ifdef HAVE_TX_MQ
+		if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
+		    !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
+			netif_wake_subqueue(netdev, tx_ring->queue_index);
+			++adapter->restart_queue;
+		}
+#else
+		if (netif_queue_stopped(netdev) &&
+		    !test_bit(__IXGBEVF_DOWN, &adapter->state)) {
+			netif_wake_queue(netdev);
+			++adapter->restart_queue;
+		}
+#endif
+	}
+
+	if (adapter->detect_tx_hung) {
+		if (ixgbevf_check_tx_hang(adapter, tx_ring, i)) {
+			/* schedule immediate reset if we believe we hung */
+			printk(KERN_INFO
+			       "tx hang %d detected, resetting adapter\n",
+			       adapter->tx_timeout_count + 1);
+			ixgbevf_tx_timeout(adapter->netdev);
+		}
+	}
+
+	/* re-arm the interrupt */
+	if ((count >= tx_ring->work_limit) &&
+	    (!test_bit(__IXGBEVF_DOWN, &adapter->state))) {
+		IXGBE_WRITE_REG(hw, IXGBE_VTEICS, tx_ring->v_idx);
+	}
+
+	tx_ring->total_bytes += total_bytes;
+	tx_ring->total_packets += total_packets;
+
+	adapter->net_stats.tx_bytes += total_bytes;
+	adapter->net_stats.tx_packets += total_packets;
+
+	return (count < tx_ring->work_limit);
+}
+
+/**
+ * ixgbevf_receive_skb - Send a completed packet up the stack
+ * @q_vector: structure containing interrupt and ring information
+ * @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 ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
+				struct sk_buff *skb, u8 status,
+				struct ixgbevf_ring *ring,
+				union ixgbe_adv_rx_desc *rx_desc)
+{
+	struct ixgbevf_adapter *adapter = q_vector->adapter;
+	bool is_vlan = (status & IXGBE_RXD_STAT_VP);
+	u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan);
+	int ret;
+
+	if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) {
+		if (adapter->vlgrp && is_vlan)
+			vlan_gro_receive(&q_vector->napi,
+					 adapter->vlgrp,
+					 tag, skb);
+		else
+			napi_gro_receive(&q_vector->napi, skb);
+	} else {
+		if (adapter->vlgrp && is_vlan)
+			ret = vlan_hwaccel_rx(skb, adapter->vlgrp, tag);
+		else
+			ret = netif_rx(skb);
+	}
+}
+
+/**
+ * ixgbevf_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 ixgbevf_rx_checksum(struct ixgbevf_adapter *adapter,
+				       u32 status_err, struct sk_buff *skb)
+{
+	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) {
+		adapter->hw_csum_rx_error++;
+		return;
+	}
+
+	/* It must be a TCP or UDP packet with a valid checksum */
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	adapter->hw_csum_rx_good++;
+}
+
+/**
+ * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split
+ * @adapter: address of board private structure
+ **/
+static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
+				     struct ixgbevf_ring *rx_ring,
+				     int cleaned_count)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	union ixgbe_adv_rx_desc *rx_desc;
+	struct ixgbevf_rx_buffer *bi;
+	struct sk_buff *skb;
+	unsigned int i;
+	unsigned int bufsz = rx_ring->rx_buf_len + NET_IP_ALIGN;
+
+	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 &&
+		    (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
+			if (!bi->page) {
+				bi->page = netdev_alloc_page(adapter->netdev);
+				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 = pci_map_page(pdev, bi->page,
+						    bi->page_offset,
+						    (PAGE_SIZE / 2),
+						    PCI_DMA_FROMDEVICE);
+		}
+
+		skb = bi->skb;
+		if (!skb) {
+			skb = netdev_alloc_skb(adapter->netdev,
+							       bufsz);
+
+			if (!skb) {
+				adapter->alloc_rx_buff_failed++;
+				goto no_buffers;
+			}
+
+			/*
+			 * Make buffer alignment 2 beyond a 16 byte boundary
+			 * this will result in a 16 byte aligned IP header after
+			 * the 14 byte MAC header is removed
+			 */
+			skb_reserve(skb, NET_IP_ALIGN);
+
+			bi->skb = skb;
+		}
+		if (!bi->dma) {
+			bi->dma = pci_map_single(pdev, skb->data,
+						 rx_ring->rx_buf_len,
+						 PCI_DMA_FROMDEVICE);
+		}
+		/* Refresh the desc even if buffer_addrs didn't change because
+		 * each write-back erases this info. */
+		if (adapter->flags & IXGBE_FLAG_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);
+
+		ixgbevf_release_rx_desc(&adapter->hw, rx_ring, i);
+	}
+}
+
+static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
+					     u64 qmask)
+{
+	u32 mask;
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	mask = (qmask & 0xFFFFFFFF);
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask);
+}
+
+static inline u16 ixgbevf_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc)
+{
+	return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info;
+}
+
+static inline u16 ixgbevf_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc)
+{
+	return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
+}
+
+static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
+				 struct ixgbevf_ring *rx_ring,
+				 int *work_done, int work_to_do)
+{
+	struct ixgbevf_adapter *adapter = q_vector->adapter;
+	struct pci_dev *pdev = adapter->pdev;
+	union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
+	struct ixgbevf_rx_buffer *rx_buffer_info, *next_buffer;
+	struct sk_buff *skb;
+	unsigned int i;
+	u32 len, staterr;
+	u16 hdr_info;
+	bool cleaned = false;
+	int cleaned_count = 0;
+	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+
+	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)++;
+
+		if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
+			hdr_info = le16_to_cpu(ixgbevf_get_hdr_info(rx_desc));
+			len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
+			       IXGBE_RXDADV_HDRBUFLEN_SHIFT;
+			if (hdr_info & IXGBE_RXDADV_SPH)
+				adapter->rx_hdr_split++;
+			if (len > IXGBEVF_RX_HDR_SIZE)
+				len = IXGBEVF_RX_HDR_SIZE;
+			upper_len = le16_to_cpu(rx_desc->wb.upper.length);
+		} else {
+			len = le16_to_cpu(rx_desc->wb.upper.length);
+		}
+		cleaned = true;
+		skb = rx_buffer_info->skb;
+		prefetch(skb->data - NET_IP_ALIGN);
+		rx_buffer_info->skb = NULL;
+
+		if (rx_buffer_info->dma) {
+			pci_unmap_single(pdev, rx_buffer_info->dma,
+					 rx_ring->rx_buf_len,
+					 PCI_DMA_FROMDEVICE);
+			rx_buffer_info->dma = 0;
+			skb_put(skb, len);
+		}
+
+		if (upper_len) {
+			pci_unmap_page(pdev, rx_buffer_info->page_dma,
+				       PAGE_SIZE / 2, PCI_DMA_FROMDEVICE);
+			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++;
+
+		next_buffer = &rx_ring->rx_buffer_info[i];
+
+		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
+			if (adapter->flags & IXGBE_FLAG_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;
+			}
+			adapter->non_eop_descs++;
+			goto next_desc;
+		}
+
+		/* ERR_MASK will only have valid bits if EOP set */
+		if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) {
+			dev_kfree_skb_irq(skb);
+			goto next_desc;
+		}
+
+		ixgbevf_rx_checksum(adapter, staterr, skb);
+
+		/* probably a little skewed due to removing CRC */
+		total_rx_bytes += skb->len;
+		total_rx_packets++;
+
+		/*
+		 * Work around issue of some types of VM to VM loop back
+		 * packets not getting split correctly
+		 */
+		if (staterr & IXGBE_RXD_STAT_LB) {
+			u32 header_fixup_len = skb->len - skb->data_len;
+			if (header_fixup_len < 14)
+				skb_push(skb, header_fixup_len);
+		}
+		skb->protocol = eth_type_trans(skb, adapter->netdev);
+
+		ixgbevf_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
+		adapter->netdev->last_rx = jiffies;
+
+next_desc:
+		rx_desc->wb.upper.status_error = 0;
+
+		/* return some buffers to hardware, one at a time is too slow */
+		if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) {
+			ixgbevf_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)
+		ixgbevf_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
+
+	rx_ring->total_packets += total_rx_packets;
+	rx_ring->total_bytes += total_rx_bytes;
+	adapter->net_stats.rx_bytes += total_rx_bytes;
+	adapter->net_stats.rx_packets += total_rx_packets;
+
+	return cleaned;
+}
+
+/**
+ * ixgbevf_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 ixgbevf_clean_rxonly(struct napi_struct *napi, int budget)
+{
+	struct ixgbevf_q_vector *q_vector =
+		container_of(napi, struct ixgbevf_q_vector, napi);
+	struct ixgbevf_adapter *adapter = q_vector->adapter;
+	struct ixgbevf_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]);
+
+	ixgbevf_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->itr_setting & 1)
+			ixgbevf_set_itr_msix(q_vector);
+		if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+			ixgbevf_irq_enable_queues(adapter, rx_ring->v_idx);
+	}
+
+	return work_done;
+}
+
+/**
+ * ixgbevf_clean_rxonly_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 ixgbevf_clean_rxonly_many(struct napi_struct *napi, int budget)
+{
+	struct ixgbevf_q_vector *q_vector =
+		container_of(napi, struct ixgbevf_q_vector, napi);
+	struct ixgbevf_adapter *adapter = q_vector->adapter;
+	struct ixgbevf_ring *rx_ring = NULL;
+	int work_done = 0, i;
+	long r_idx;
+	u64 enable_mask = 0;
+
+	/* 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++) {
+		rx_ring = &(adapter->rx_ring[r_idx]);
+		ixgbevf_clean_rx_irq(q_vector, rx_ring, &work_done, budget);
+		enable_mask |= rx_ring->v_idx;
+		r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
+				      r_idx + 1);
+	}
+
+#ifndef HAVE_NETDEV_NAPI_LIST
+	if (!netif_running(adapter->netdev))
+		work_done = 0;
+
+#endif
+	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
+	rx_ring = &(adapter->rx_ring[r_idx]);
+
+	/* If all Rx work done, exit the polling mode */
+	if (work_done < budget) {
+		napi_complete(napi);
+		if (adapter->itr_setting & 1)
+			ixgbevf_set_itr_msix(q_vector);
+		if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+			ixgbevf_irq_enable_queues(adapter, enable_mask);
+	}
+
+	return work_done;
+}
+
+
+/**
+ * ixgbevf_configure_msix - Configure MSI-X hardware
+ * @adapter: board private structure
+ *
+ * ixgbevf_configure_msix sets up the hardware to properly generate MSI-X
+ * interrupts.
+ **/
+static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbevf_q_vector *q_vector;
+	struct ixgbe_hw *hw = &adapter->hw;
+	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_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;
+			ixgbevf_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;
+			ixgbevf_set_ivar(adapter, 1, j, v_idx);
+			r_idx = find_next_bit(q_vector->txr_idx,
+					      adapter->num_tx_queues,
+					      r_idx + 1);
+		}
+
+		/* if this is a tx only vector halve the interrupt rate */
+		if (q_vector->txr_count && !q_vector->rxr_count)
+			q_vector->eitr = (adapter->eitr_param >> 1);
+		else if (q_vector->rxr_count)
+			/* rx only */
+			q_vector->eitr = adapter->eitr_param;
+
+		ixgbevf_write_eitr(adapter, v_idx, q_vector->eitr);
+	}
+
+	ixgbevf_set_ivar(adapter, -1, 1, v_idx);
+
+	/* set up to autoclear timer, and the vectors */
+	mask = IXGBE_EIMS_ENABLE_MASK;
+	mask &= ~IXGBE_EIMS_OTHER;
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, mask);
+}
+
+enum latency_range {
+	lowest_latency = 0,
+	low_latency = 1,
+	bulk_latency = 2,
+	latency_invalid = 255
+};
+
+/**
+ * ixgbevf_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.
+ **/
+static u8 ixgbevf_update_itr(struct ixgbevf_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;
+}
+
+/**
+ * ixgbevf_write_eitr - write VTEITR register in hardware specific way
+ * @adapter: pointer to adapter struct
+ * @v_idx: vector index into q_vector array
+ * @itr_reg: new value to be written in *register* format, not ints/s
+ *
+ * This function is made to be called by ethtool and by the driver
+ * when it needs to update VTEITR registers at runtime.  Hardware
+ * specific quirks/differences are taken care of here.
+ */
+static void ixgbevf_write_eitr(struct ixgbevf_adapter *adapter, int v_idx,
+			       u32 itr_reg)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	itr_reg = EITR_INTS_PER_SEC_TO_REG(itr_reg);
+
+	/*
+	 * 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_VTEITR(v_idx), itr_reg);
+}
+
+static void ixgbevf_set_itr_msix(struct ixgbevf_q_vector *q_vector)
+{
+	struct ixgbevf_adapter *adapter = q_vector->adapter;
+	u32 new_itr;
+	u8 current_itr, ret_itr;
+	int i, r_idx, v_idx = q_vector->v_idx;
+	struct ixgbevf_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 = ixgbevf_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 = ixgbevf_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) {
+		u32 itr_reg;
+
+		/* save the algorithm value here, not the smoothed one */
+		q_vector->eitr = new_itr;
+		/* do an exponential smoothing */
+		new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
+		itr_reg = EITR_INTS_PER_SEC_TO_REG(new_itr);
+		ixgbevf_write_eitr(adapter, v_idx, itr_reg);
+	}
+
+	return;
+}
+
+static irqreturn_t ixgbevf_msix_mbx(int irq, void *data)
+{
+	struct net_device *netdev = data;
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 eicr;
+
+	eicr = IXGBE_READ_REG(hw, IXGBE_VTEICS);
+	IXGBE_WRITE_REG(hw, IXGBE_VTEICR, eicr);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data)
+{
+	struct ixgbevf_q_vector *q_vector = data;
+	struct ixgbevf_adapter  *adapter = q_vector->adapter;
+	struct ixgbevf_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;
+		ixgbevf_clean_tx_irq(adapter, tx_ring);
+		r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
+				      r_idx + 1);
+	}
+
+	if (adapter->itr_setting & 1)
+		ixgbevf_set_itr_msix(q_vector);
+
+	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 ixgbevf_msix_clean_rx(int irq, void *data)
+{
+	struct ixgbevf_q_vector *q_vector = data;
+	struct ixgbevf_adapter  *adapter = q_vector->adapter;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct ixgbevf_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;
+
+	r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
+	rx_ring = &(adapter->rx_ring[r_idx]);
+	/* disable interrupts on this vector only */
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, rx_ring->v_idx);
+	napi_schedule(&q_vector->napi);
+
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ixgbevf_msix_clean_many(int irq, void *data)
+{
+	ixgbevf_msix_clean_rx(irq, data);
+	ixgbevf_msix_clean_tx(irq, data);
+
+	return IRQ_HANDLED;
+}
+
+static inline void map_vector_to_rxq(struct ixgbevf_adapter *a, int v_idx,
+				     int r_idx)
+{
+	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];
+
+	set_bit(r_idx, q_vector->rxr_idx);
+	q_vector->rxr_count++;
+	a->rx_ring[r_idx].v_idx = 1 << v_idx;
+}
+
+static inline void map_vector_to_txq(struct ixgbevf_adapter *a, int v_idx,
+				     int t_idx)
+{
+	struct ixgbevf_q_vector *q_vector = a->q_vector[v_idx];
+
+	set_bit(t_idx, q_vector->txr_idx);
+	q_vector->txr_count++;
+	a->tx_ring[t_idx].v_idx = 1 << v_idx;
+}
+
+/**
+ * ixgbevf_map_rings_to_vectors - Maps descriptor rings to vectors
+ * @adapter: board private structure to initialize
+ *
+ * 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 ixgbevf_map_rings_to_vectors(struct ixgbevf_adapter *adapter)
+{
+	int q_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;
+
+	q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+
+	/*
+	 * The ideal configuration...
+	 * We have enough vectors to map one per queue.
+	 */
+	if (q_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 < q_vectors; i++) {
+		rqpv = DIV_ROUND_UP(rxr_remaining, q_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 < q_vectors; i++) {
+		tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
+		for (j = 0; j < tqpv; j++) {
+			map_vector_to_txq(adapter, i, txr_idx);
+			txr_idx++;
+			txr_remaining--;
+		}
+	}
+
+out:
+	return err;
+}
+
+/**
+ * ixgbevf_request_msix_irqs - Initialize MSI-X interrupts
+ * @adapter: board private structure
+ *
+ * ixgbevf_request_msix_irqs allocates MSI-X vectors and requests
+ * interrupts from the kernel.
+ **/
+static int ixgbevf_request_msix_irqs(struct ixgbevf_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;
+
+#define SET_HANDLER(_v) (((_v)->rxr_count && (_v)->txr_count)          \
+					  ? &ixgbevf_msix_clean_many : \
+			  (_v)->rxr_count ? &ixgbevf_msix_clean_rx   : \
+			  (_v)->txr_count ? &ixgbevf_msix_clean_tx   : \
+			  NULL)
+	for (vector = 0; vector < q_vectors; vector++) {
+		handler = SET_HANDLER(adapter->q_vector[vector]);
+
+		if (handler == &ixgbevf_msix_clean_rx) {
+			sprintf(adapter->name[vector], "%s-%s-%d",
+				netdev->name, "rx", ri++);
+		} else if (handler == &ixgbevf_msix_clean_tx) {
+			sprintf(adapter->name[vector], "%s-%s-%d",
+				netdev->name, "tx", ti++);
+		} else if (handler == &ixgbevf_msix_clean_many) {
+			sprintf(adapter->name[vector], "%s-%s-%d",
+				netdev->name, "TxRx", vector);
+		} else {
+			/* skip this unused q_vector */
+			continue;
+		}
+		err = request_irq(adapter->msix_entries[vector].vector,
+				  handler, 0, adapter->name[vector],
+				  adapter->q_vector[vector]);
+		if (err) {
+			hw_dbg(&adapter->hw,
+			       "request_irq failed for MSIX interrupt "
+			       "Error: %d\n", err);
+			goto free_queue_irqs;
+		}
+	}
+
+	sprintf(adapter->name[vector], "%s:mbx", netdev->name);
+	err = request_irq(adapter->msix_entries[vector].vector,
+			  &ixgbevf_msix_mbx, 0, adapter->name[vector], netdev);
+	if (err) {
+		hw_dbg(&adapter->hw,
+		       "request_irq for msix_mbx 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]));
+	pci_disable_msix(adapter->pdev);
+	kfree(adapter->msix_entries);
+	adapter->msix_entries = NULL;
+	return err;
+}
+
+static inline void ixgbevf_reset_q_vectors(struct ixgbevf_adapter *adapter)
+{
+	int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+
+	for (i = 0; i < q_vectors; i++) {
+		struct ixgbevf_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;
+		q_vector->eitr = adapter->eitr_param;
+	}
+}
+
+/**
+ * ixgbevf_request_irq - initialize interrupts
+ * @adapter: board private structure
+ *
+ * Attempts to configure interrupts using the best available
+ * capabilities of the hardware and kernel.
+ **/
+static int ixgbevf_request_irq(struct ixgbevf_adapter *adapter)
+{
+	int err = 0;
+
+	err = ixgbevf_request_msix_irqs(adapter);
+
+	if (err)
+		hw_dbg(&adapter->hw,
+		       "request_irq failed, Error %d\n", err);
+
+	return err;
+}
+
+static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	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]);
+	}
+
+	ixgbevf_reset_q_vectors(adapter);
+}
+
+/**
+ * ixgbevf_irq_disable - Mask off interrupt generation on the NIC
+ * @adapter: board private structure
+ **/
+static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter)
+{
+	int i;
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0);
+
+	IXGBE_WRITE_FLUSH(hw);
+
+	for (i = 0; i < adapter->num_msix_vectors; i++)
+		synchronize_irq(adapter->msix_entries[i].vector);
+}
+
+/**
+ * ixgbevf_irq_enable - Enable default interrupt generation settings
+ * @adapter: board private structure
+ **/
+static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter,
+				      bool queues, bool flush)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 mask;
+	u64 qmask;
+
+	mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);
+	qmask = ~0;
+
+	IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, mask);
+
+	if (queues)
+		ixgbevf_irq_enable_queues(adapter, qmask);
+
+	if (flush)
+		IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
+ * ixgbevf_configure_tx - Configure 82599 VF Transmit Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Tx unit of the MAC after a reset.
+ **/
+static void ixgbevf_configure_tx(struct ixgbevf_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 ixgbevf_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_VFTDBAL(j),
+				(tdba & DMA_BIT_MASK(32)));
+		IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(j), (tdba >> 32));
+		IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(j), tdlen);
+		IXGBE_WRITE_REG(hw, IXGBE_VFTDH(j), 0);
+		IXGBE_WRITE_REG(hw, IXGBE_VFTDT(j), 0);
+		adapter->tx_ring[i].head = IXGBE_VFTDH(j);
+		adapter->tx_ring[i].tail = IXGBE_VFTDT(j);
+		/* Disable Tx Head Writeback RO bit, since this hoses
+		 * bookkeeping if things aren't delivered in order.
+		 */
+		txctrl = IXGBE_READ_REG(hw, IXGBE_VFDCA_TXCTRL(j));
+		txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
+		IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(j), txctrl);
+	}
+}
+
+#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT	2
+
+static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
+{
+	struct ixgbevf_ring *rx_ring;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 srrctl;
+
+	rx_ring = &adapter->rx_ring[index];
+
+	srrctl = IXGBE_SRRCTL_DROP_EN;
+
+	if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
+		u16 bufsz = IXGBEVF_RXBUFFER_2048;
+		/* grow the amount we can receive on large page machines */
+		if (bufsz < (PAGE_SIZE / 2))
+			bufsz = (PAGE_SIZE / 2);
+		/* cap the bufsz at our largest descriptor size */
+		bufsz = min((u16)IXGBEVF_MAX_RXBUFFER, bufsz);
+
+		srrctl |= bufsz >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+		srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS;
+		srrctl |= ((IXGBEVF_RX_HDR_SIZE <<
+			   IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) &
+			   IXGBE_SRRCTL_BSIZEHDR_MASK);
+	} else {
+		srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
+
+		if (rx_ring->rx_buf_len == MAXIMUM_ETHERNET_VLAN_SIZE)
+			srrctl |= IXGBEVF_RXBUFFER_2048 >>
+				IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+		else
+			srrctl |= rx_ring->rx_buf_len >>
+				IXGBE_SRRCTL_BSIZEPKT_SHIFT;
+	}
+	IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
+}
+
+/**
+ * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset
+ * @adapter: board private structure
+ *
+ * Configure the Rx unit of the MAC after a reset.
+ **/
+static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
+{
+	u64 rdba;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
+	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+	int i, j;
+	u32 rdlen;
+	int rx_buf_len;
+
+	/* Decide whether to use packet split mode or not */
+	if (netdev->mtu > ETH_DATA_LEN) {
+		if (adapter->flags & IXGBE_FLAG_RX_PS_CAPABLE)
+			adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+		else
+			adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
+	} else {
+		if (adapter->flags & IXGBE_FLAG_RX_1BUF_CAPABLE)
+			adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
+		else
+			adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+	}
+
+	/* Set the RX buffer length according to the mode */
+	if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
+		/* 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_VFPSRTYPE, psrtype);
+		rx_buf_len = IXGBEVF_RX_HDR_SIZE;
+	} else {
+		IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, 0);
+		if (netdev->mtu <= ETH_DATA_LEN)
+			rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
+		else
+			rx_buf_len = ALIGN(max_frame, 1024);
+	}
+
+	rdlen = adapter->rx_ring[0].count * sizeof(union ixgbe_adv_rx_desc);
+	/* 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++) {
+		rdba = adapter->rx_ring[i].dma;
+		j = adapter->rx_ring[i].reg_idx;
+		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(j),
+				(rdba & DMA_BIT_MASK(32)));
+		IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(j), (rdba >> 32));
+		IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(j), rdlen);
+		IXGBE_WRITE_REG(hw, IXGBE_VFRDH(j), 0);
+		IXGBE_WRITE_REG(hw, IXGBE_VFRDT(j), 0);
+		adapter->rx_ring[i].head = IXGBE_VFRDH(j);
+		adapter->rx_ring[i].tail = IXGBE_VFRDT(j);
+		adapter->rx_ring[i].rx_buf_len = rx_buf_len;
+
+		ixgbevf_configure_srrctl(adapter, j);
+	}
+}
+
+static void ixgbevf_vlan_rx_register(struct net_device *netdev,
+				     struct vlan_group *grp)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, j;
+	u32 ctrl;
+
+	adapter->vlgrp = grp;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		j = adapter->rx_ring[i].reg_idx;
+		ctrl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
+		ctrl |= IXGBE_RXDCTL_VME;
+		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), ctrl);
+	}
+}
+
+static void ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *v_netdev;
+
+	/* add VID to filter table */
+	if (hw->mac.ops.set_vfta)
+		hw->mac.ops.set_vfta(hw, vid, 0, true);
+	/*
+	 * Copy feature flags from netdev to the vlan netdev for this vid.
+	 * This allows things like TSO to bubble down to our vlan device.
+	 */
+	v_netdev = vlan_group_get_device(adapter->vlgrp, vid);
+	v_netdev->features |= adapter->netdev->features;
+	vlan_group_set_device(adapter->vlgrp, vid, v_netdev);
+}
+
+static void ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+		ixgbevf_irq_disable(adapter);
+
+	vlan_group_set_device(adapter->vlgrp, vid, NULL);
+
+	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+		ixgbevf_irq_enable(adapter, true, true);
+
+	/* remove VID from filter table */
+	if (hw->mac.ops.set_vfta)
+		hw->mac.ops.set_vfta(hw, vid, 0, false);
+}
+
+static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
+{
+	ixgbevf_vlan_rx_register(adapter->netdev, adapter->vlgrp);
+
+	if (adapter->vlgrp) {
+		u16 vid;
+		for (vid = 0; vid < VLAN_GROUP_ARRAY_LEN; vid++) {
+			if (!vlan_group_get_device(adapter->vlgrp, vid))
+				continue;
+			ixgbevf_vlan_rx_add_vid(adapter->netdev, vid);
+		}
+	}
+}
+
+static u8 *ixgbevf_addr_list_itr(struct ixgbe_hw *hw, u8 **mc_addr_ptr,
+				 u32 *vmdq)
+{
+	struct dev_mc_list *mc_ptr;
+	u8 *addr = *mc_addr_ptr;
+	*vmdq = 0;
+
+	mc_ptr = container_of(addr, struct dev_mc_list, dmi_addr[0]);
+	if (mc_ptr->next)
+		*mc_addr_ptr = mc_ptr->next->dmi_addr;
+	else
+		*mc_addr_ptr = NULL;
+
+	return addr;
+}
+
+/**
+ * ixgbevf_set_rx_mode - Multicast set
+ * @netdev: network interface device structure
+ *
+ * The set_rx_method entry point is called whenever the multicast address
+ * list or the network interface flags are updated.  This routine is
+ * responsible for configuring the hardware for proper multicast mode.
+ **/
+static void ixgbevf_set_rx_mode(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	u8 *addr_list = NULL;
+	int addr_count = 0;
+
+	/* reprogram multicast list */
+	addr_count = netdev->mc_count;
+	if (addr_count)
+		addr_list = netdev->mc_list->dmi_addr;
+	if (hw->mac.ops.update_mc_addr_list)
+		hw->mac.ops.update_mc_addr_list(hw, addr_list, addr_count,
+						ixgbevf_addr_list_itr);
+}
+
+static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter)
+{
+	int q_idx;
+	struct ixgbevf_q_vector *q_vector;
+	int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+
+	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
+		struct napi_struct *napi;
+		q_vector = adapter->q_vector[q_idx];
+		if (!q_vector->rxr_count)
+			continue;
+		napi = &q_vector->napi;
+		if (q_vector->rxr_count > 1)
+			napi->poll = &ixgbevf_clean_rxonly_many;
+
+		napi_enable(napi);
+	}
+}
+
+static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter)
+{
+	int q_idx;
+	struct ixgbevf_q_vector *q_vector;
+	int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+
+	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
+		q_vector = adapter->q_vector[q_idx];
+		if (!q_vector->rxr_count)
+			continue;
+		napi_disable(&q_vector->napi);
+	}
+}
+
+static void ixgbevf_configure(struct ixgbevf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int i;
+
+	ixgbevf_set_rx_mode(netdev);
+
+	ixgbevf_restore_vlan(adapter);
+
+	ixgbevf_configure_tx(adapter);
+	ixgbevf_configure_rx(adapter);
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct ixgbevf_ring *ring = &adapter->rx_ring[i];
+		ixgbevf_alloc_rx_buffers(adapter, ring, ring->count);
+		ring->next_to_use = ring->count - 1;
+		writel(ring->next_to_use, adapter->hw.hw_addr + ring->tail);
+	}
+}
+
+#define IXGBE_MAX_RX_DESC_POLL 10
+static inline void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter,
+						int rxr)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int j = adapter->rx_ring[rxr].reg_idx;
+	int k;
+
+	for (k = 0; k < IXGBE_MAX_RX_DESC_POLL; k++) {
+		if (IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j)) & IXGBE_RXDCTL_ENABLE)
+			break;
+		else
+			msleep(1);
+	}
+	if (k >= IXGBE_MAX_RX_DESC_POLL) {
+		hw_dbg(hw, "RXDCTL.ENABLE on Rx queue %d "
+		       "not set within the polling period\n", rxr);
+	}
+
+	ixgbevf_release_rx_desc(&adapter->hw, &adapter->rx_ring[rxr],
+				(adapter->rx_ring[rxr].count - 1));
+}
+
+static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, j = 0;
+	int num_rx_rings = adapter->num_rx_queues;
+	u32 txdctl, rxdctl;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		j = adapter->tx_ring[i].reg_idx;
+		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
+		/* enable WTHRESH=8 descriptors, to encourage burst writeback */
+		txdctl |= (8 << 16);
+		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
+	}
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		j = adapter->tx_ring[i].reg_idx;
+		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
+		txdctl |= IXGBE_TXDCTL_ENABLE;
+		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j), txdctl);
+	}
+
+	for (i = 0; i < num_rx_rings; i++) {
+		j = adapter->rx_ring[i].reg_idx;
+		rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j));
+		rxdctl |= IXGBE_RXDCTL_ENABLE;
+		IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl);
+		ixgbevf_rx_desc_queue_enable(adapter, i);
+	}
+
+	ixgbevf_configure_msix(adapter);
+
+	if (hw->mac.ops.set_rar) {
+		if (is_valid_ether_addr(hw->mac.addr))
+			hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0);
+		else
+			hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0);
+	}
+
+	clear_bit(__IXGBEVF_DOWN, &adapter->state);
+	ixgbevf_napi_enable_all(adapter);
+
+	/* enable transmits */
+	netif_tx_start_all_queues(netdev);
+
+	/* bring the link up in the watchdog, this could race with our first
+	 * link up interrupt but shouldn't be a problem */
+	adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
+	adapter->link_check_timeout = jiffies;
+	mod_timer(&adapter->watchdog_timer, jiffies);
+	return 0;
+}
+
+int ixgbevf_up(struct ixgbevf_adapter *adapter)
+{
+	int err;
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	ixgbevf_configure(adapter);
+
+	err = ixgbevf_up_complete(adapter);
+
+	/* clear any pending interrupts, may auto mask */
+	IXGBE_READ_REG(hw, IXGBE_VTEICR);
+
+	ixgbevf_irq_enable(adapter, true, true);
+
+	return err;
+}
+
+/**
+ * ixgbevf_clean_rx_ring - Free Rx Buffers per Queue
+ * @adapter: board private structure
+ * @rx_ring: ring to free buffers from
+ **/
+static void ixgbevf_clean_rx_ring(struct ixgbevf_adapter *adapter,
+				  struct ixgbevf_ring *rx_ring)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	unsigned long size;
+	unsigned int i;
+
+	/* Free all the Rx ring sk_buffs */
+
+	for (i = 0; i < rx_ring->count; i++) {
+		struct ixgbevf_rx_buffer *rx_buffer_info;
+
+		rx_buffer_info = &rx_ring->rx_buffer_info[i];
+		if (rx_buffer_info->dma) {
+			pci_unmap_single(pdev, rx_buffer_info->dma,
+					 rx_ring->rx_buf_len,
+					 PCI_DMA_FROMDEVICE);
+			rx_buffer_info->dma = 0;
+		}
+		if (rx_buffer_info->skb) {
+			struct sk_buff *skb = rx_buffer_info->skb;
+			rx_buffer_info->skb = NULL;
+			do {
+				struct sk_buff *this = skb;
+				skb = skb->prev;
+				dev_kfree_skb(this);
+			} while (skb);
+		}
+		if (!rx_buffer_info->page)
+			continue;
+		pci_unmap_page(pdev, rx_buffer_info->page_dma, PAGE_SIZE / 2,
+			       PCI_DMA_FROMDEVICE);
+		rx_buffer_info->page_dma = 0;
+		put_page(rx_buffer_info->page);
+		rx_buffer_info->page = NULL;
+		rx_buffer_info->page_offset = 0;
+	}
+
+	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
+	memset(rx_ring->rx_buffer_info, 0, size);
+
+	/* Zero out the descriptor ring */
+	memset(rx_ring->desc, 0, rx_ring->size);
+
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+
+	if (rx_ring->head)
+		writel(0, adapter->hw.hw_addr + rx_ring->head);
+	if (rx_ring->tail)
+		writel(0, adapter->hw.hw_addr + rx_ring->tail);
+}
+
+/**
+ * ixgbevf_clean_tx_ring - Free Tx Buffers
+ * @adapter: board private structure
+ * @tx_ring: ring to be cleaned
+ **/
+static void ixgbevf_clean_tx_ring(struct ixgbevf_adapter *adapter,
+				  struct ixgbevf_ring *tx_ring)
+{
+	struct ixgbevf_tx_buffer *tx_buffer_info;
+	unsigned long size;
+	unsigned int i;
+
+	/* Free all the Tx ring sk_buffs */
+
+	for (i = 0; i < tx_ring->count; i++) {
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+	}
+
+	size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count;
+	memset(tx_ring->tx_buffer_info, 0, size);
+
+	memset(tx_ring->desc, 0, tx_ring->size);
+
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+
+	if (tx_ring->head)
+		writel(0, adapter->hw.hw_addr + tx_ring->head);
+	if (tx_ring->tail)
+		writel(0, adapter->hw.hw_addr + tx_ring->tail);
+}
+
+/**
+ * ixgbevf_clean_all_rx_rings - Free Rx Buffers for all queues
+ * @adapter: board private structure
+ **/
+static void ixgbevf_clean_all_rx_rings(struct ixgbevf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		ixgbevf_clean_rx_ring(adapter, &adapter->rx_ring[i]);
+}
+
+/**
+ * ixgbevf_clean_all_tx_rings - Free Tx Buffers for all queues
+ * @adapter: board private structure
+ **/
+static void ixgbevf_clean_all_tx_rings(struct ixgbevf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		ixgbevf_clean_tx_ring(adapter, &adapter->tx_ring[i]);
+}
+
+void ixgbevf_down(struct ixgbevf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 txdctl;
+	int i, j;
+
+	/* signal that we are down to the interrupt handler */
+	set_bit(__IXGBEVF_DOWN, &adapter->state);
+	/* disable receives */
+
+	netif_tx_disable(netdev);
+
+	msleep(10);
+
+	netif_tx_stop_all_queues(netdev);
+
+	ixgbevf_irq_disable(adapter);
+
+	ixgbevf_napi_disable_all(adapter);
+
+	del_timer_sync(&adapter->watchdog_timer);
+	/* can't call flush scheduled work here because it can deadlock
+	 * if linkwatch_event tries to acquire the rtnl_lock which we are
+	 * holding */
+	while (adapter->flags & IXGBE_FLAG_IN_WATCHDOG_TASK)
+		msleep(1);
+
+	/* disable transmits in the hardware now that interrupts are off */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		j = adapter->tx_ring[i].reg_idx;
+		txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(j));
+		IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(j),
+				(txdctl & ~IXGBE_TXDCTL_ENABLE));
+	}
+
+	netif_carrier_off(netdev);
+
+	if (!pci_channel_offline(adapter->pdev))
+		ixgbevf_reset(adapter);
+
+	ixgbevf_clean_all_tx_rings(adapter);
+	ixgbevf_clean_all_rx_rings(adapter);
+}
+
+void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter)
+{
+	WARN_ON(in_interrupt());
+	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
+		msleep(1);
+
+	ixgbevf_down(adapter);
+	ixgbevf_up(adapter);
+
+	clear_bit(__IXGBEVF_RESETTING, &adapter->state);
+}
+
+void ixgbevf_reset(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
+
+	if (hw->mac.ops.reset_hw(hw))
+		hw_dbg(hw, "PF still resetting\n");
+	else
+		hw->mac.ops.init_hw(hw);
+
+	if (is_valid_ether_addr(adapter->hw.mac.addr)) {
+		memcpy(netdev->dev_addr, adapter->hw.mac.addr,
+		       netdev->addr_len);
+		memcpy(netdev->perm_addr, adapter->hw.mac.addr,
+		       netdev->addr_len);
+	}
+}
+
+static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter,
+					 int vectors)
+{
+	int err, vector_threshold;
+
+	/* We'll want at least 3 (vector_threshold):
+	 * 1) TxQ[0] Cleanup
+	 * 2) RxQ[0] Cleanup
+	 * 3) Other (Link Status Change, etc.)
+	 */
+	vector_threshold = MIN_MSIX_COUNT;
+
+	/* The more we get, the more we will assign to Tx/Rx Cleanup
+	 * for the separate queues...where Rx Cleanup >= Tx Cleanup.
+	 * Right now, we simply care about how many we'll get; we'll
+	 * set them up later while requesting irq's.
+	 */
+	while (vectors >= vector_threshold) {
+		err = pci_enable_msix(adapter->pdev, adapter->msix_entries,
+				      vectors);
+		if (!err) /* Success in acquiring all requested vectors. */
+			break;
+		else if (err < 0)
+			vectors = 0; /* Nasty failure, quit now */
+		else /* err == number of vectors we should try again with */
+			vectors = err;
+	}
+
+	if (vectors < vector_threshold) {
+		/* Can't allocate enough MSI-X interrupts?  Oh well.
+		 * This just means we'll go with either a single MSI
+		 * vector or fall back to legacy interrupts.
+		 */
+		hw_dbg(&adapter->hw,
+		       "Unable to allocate MSI-X interrupts\n");
+		kfree(adapter->msix_entries);
+		adapter->msix_entries = NULL;
+	} else {
+		/*
+		 * Adjust for only the vectors we'll use, which is minimum
+		 * of max_msix_q_vectors + NON_Q_VECTORS, or the number of
+		 * vectors we were allocated.
+		 */
+		adapter->num_msix_vectors = vectors;
+	}
+}
+
+/*
+ * ixgbe_set_num_queues: Allocate queues for device, feature dependant
+ * @adapter: board private structure to initialize
+ *
+ * This is the top level queue allocation routine.  The order here is very
+ * important, starting with the "most" number of features turned on at once,
+ * and ending with the smallest set of features.  This way large combinations
+ * can be allocated if they're turned on, and smaller combinations are the
+ * fallthrough conditions.
+ *
+ **/
+static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter)
+{
+	/* Start with base case */
+	adapter->num_rx_queues = 1;
+	adapter->num_tx_queues = 1;
+	adapter->num_rx_pools = adapter->num_rx_queues;
+	adapter->num_rx_queues_per_pool = 1;
+}
+
+/**
+ * ixgbevf_alloc_queues - Allocate memory for all rings
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one ring per queue at run-time since we don't know the
+ * number of queues at compile-time.  The polling_netdev array is
+ * intended for Multiqueue, but should work fine with a single queue.
+ **/
+static int ixgbevf_alloc_queues(struct ixgbevf_adapter *adapter)
+{
+	int i;
+
+	adapter->tx_ring = kcalloc(adapter->num_tx_queues,
+				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
+	if (!adapter->tx_ring)
+		goto err_tx_ring_allocation;
+
+	adapter->rx_ring = kcalloc(adapter->num_rx_queues,
+				   sizeof(struct ixgbevf_ring), GFP_KERNEL);
+	if (!adapter->rx_ring)
+		goto err_rx_ring_allocation;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		adapter->tx_ring[i].count = adapter->tx_ring_count;
+		adapter->tx_ring[i].queue_index = i;
+		adapter->tx_ring[i].reg_idx = i;
+	}
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		adapter->rx_ring[i].count = adapter->rx_ring_count;
+		adapter->rx_ring[i].queue_index = i;
+		adapter->rx_ring[i].reg_idx = i;
+	}
+
+	return 0;
+
+err_rx_ring_allocation:
+	kfree(adapter->tx_ring);
+err_tx_ring_allocation:
+	return -ENOMEM;
+}
+
+/**
+ * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported
+ * @adapter: board private structure to initialize
+ *
+ * Attempt to configure the interrupts using the best available
+ * capabilities of the hardware and the kernel.
+ **/
+static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter)
+{
+	int err = 0;
+	int vector, v_budget;
+
+	/*
+	 * It's easy to be greedy for MSI-X vectors, but it really
+	 * doesn't do us much good if we have a lot more vectors
+	 * than CPU's.  So let's be conservative and only ask for
+	 * (roughly) twice the number of vectors as there are CPU's.
+	 */
+	v_budget = min(adapter->num_rx_queues + adapter->num_tx_queues,
+		       (int)(num_online_cpus() * 2)) + NON_Q_VECTORS;
+
+	/* A failure in MSI-X entry allocation isn't fatal, but it does
+	 * mean we disable MSI-X capabilities of the adapter. */
+	adapter->msix_entries = kcalloc(v_budget,
+					sizeof(struct msix_entry), GFP_KERNEL);
+	if (!adapter->msix_entries) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (vector = 0; vector < v_budget; vector++)
+		adapter->msix_entries[vector].entry = vector;
+
+	ixgbevf_acquire_msix_vectors(adapter, v_budget);
+
+out:
+	return err;
+}
+
+/**
+ * ixgbevf_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * We allocate one q_vector per queue interrupt.  If allocation fails we
+ * return -ENOMEM.
+ **/
+static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter)
+{
+	int q_idx, num_q_vectors;
+	struct ixgbevf_q_vector *q_vector;
+	int napi_vectors;
+	int (*poll)(struct napi_struct *, int);
+
+	num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+	napi_vectors = adapter->num_rx_queues;
+	poll = &ixgbevf_clean_rxonly;
+
+	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+		q_vector = kzalloc(sizeof(struct ixgbevf_q_vector), GFP_KERNEL);
+		if (!q_vector)
+			goto err_out;
+		q_vector->adapter = adapter;
+		q_vector->v_idx = q_idx;
+		q_vector->eitr = adapter->eitr_param;
+		if (q_idx < napi_vectors)
+			netif_napi_add(adapter->netdev, &q_vector->napi,
+				       (*poll), 64);
+		adapter->q_vector[q_idx] = q_vector;
+	}
+
+	return 0;
+
+err_out:
+	while (q_idx) {
+		q_idx--;
+		q_vector = adapter->q_vector[q_idx];
+		netif_napi_del(&q_vector->napi);
+		kfree(q_vector);
+		adapter->q_vector[q_idx] = NULL;
+	}
+	return -ENOMEM;
+}
+
+/**
+ * ixgbevf_free_q_vectors - Free memory allocated for interrupt vectors
+ * @adapter: board private structure to initialize
+ *
+ * This function frees the memory allocated to the q_vectors.  In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ **/
+static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter)
+{
+	int q_idx, num_q_vectors;
+	int napi_vectors;
+
+	num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+	napi_vectors = adapter->num_rx_queues;
+
+	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
+		struct ixgbevf_q_vector *q_vector = adapter->q_vector[q_idx];
+
+		adapter->q_vector[q_idx] = NULL;
+		if (q_idx < napi_vectors)
+			netif_napi_del(&q_vector->napi);
+		kfree(q_vector);
+	}
+}
+
+/**
+ * ixgbevf_reset_interrupt_capability - Reset MSIX setup
+ * @adapter: board private structure
+ *
+ **/
+static void ixgbevf_reset_interrupt_capability(struct ixgbevf_adapter *adapter)
+{
+	pci_disable_msix(adapter->pdev);
+	kfree(adapter->msix_entries);
+	adapter->msix_entries = NULL;
+
+	return;
+}
+
+/**
+ * ixgbevf_init_interrupt_scheme - Determine if MSIX is supported and init
+ * @adapter: board private structure to initialize
+ *
+ **/
+static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter)
+{
+	int err;
+
+	/* Number of supported queues */
+	ixgbevf_set_num_queues(adapter);
+
+	err = ixgbevf_set_interrupt_capability(adapter);
+	if (err) {
+		hw_dbg(&adapter->hw,
+		       "Unable to setup interrupt capabilities\n");
+		goto err_set_interrupt;
+	}
+
+	err = ixgbevf_alloc_q_vectors(adapter);
+	if (err) {
+		hw_dbg(&adapter->hw, "Unable to allocate memory for queue "
+		       "vectors\n");
+		goto err_alloc_q_vectors;
+	}
+
+	err = ixgbevf_alloc_queues(adapter);
+	if (err) {
+		printk(KERN_ERR "Unable to allocate memory for queues\n");
+		goto err_alloc_queues;
+	}
+
+	hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, "
+	       "Tx Queue count = %u\n",
+	       (adapter->num_rx_queues > 1) ? "Enabled" :
+	       "Disabled", adapter->num_rx_queues, adapter->num_tx_queues);
+
+	set_bit(__IXGBEVF_DOWN, &adapter->state);
+
+	return 0;
+err_alloc_queues:
+	ixgbevf_free_q_vectors(adapter);
+err_alloc_q_vectors:
+	ixgbevf_reset_interrupt_capability(adapter);
+err_set_interrupt:
+	return err;
+}
+
+/**
+ * ixgbevf_sw_init - Initialize general software structures
+ * (struct ixgbevf_adapter)
+ * @adapter: board private structure to initialize
+ *
+ * ixgbevf_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ **/
+static int __devinit ixgbevf_sw_init(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct pci_dev *pdev = adapter->pdev;
+	int err;
+
+	/* PCI config space info */
+
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id);
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+
+	hw->mbx.ops.init_params(hw);
+	hw->mac.max_tx_queues = MAX_TX_QUEUES;
+	hw->mac.max_rx_queues = MAX_RX_QUEUES;
+	err = hw->mac.ops.reset_hw(hw);
+	if (err) {
+		dev_info(&pdev->dev,
+		         "PF still in reset state, assigning new address\n");
+		random_ether_addr(hw->mac.addr);
+	} else {
+		err = hw->mac.ops.init_hw(hw);
+		if (err) {
+			printk(KERN_ERR "init_shared_code failed: %d\n", err);
+			goto out;
+		}
+	}
+
+	/* Enable dynamic interrupt throttling rates */
+	adapter->eitr_param = 20000;
+	adapter->itr_setting = 1;
+
+	/* set defaults for eitr in MegaBytes */
+	adapter->eitr_low = 10;
+	adapter->eitr_high = 20;
+
+	/* set default ring sizes */
+	adapter->tx_ring_count = IXGBEVF_DEFAULT_TXD;
+	adapter->rx_ring_count = IXGBEVF_DEFAULT_RXD;
+
+	/* enable rx csum by default */
+	adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED;
+
+	set_bit(__IXGBEVF_DOWN, &adapter->state);
+
+out:
+	return err;
+}
+
+static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	adapter->stats.last_vfgprc = IXGBE_READ_REG(hw, IXGBE_VFGPRC);
+	adapter->stats.last_vfgorc = IXGBE_READ_REG(hw, IXGBE_VFGORC_LSB);
+	adapter->stats.last_vfgorc |=
+		(((u64)(IXGBE_READ_REG(hw, IXGBE_VFGORC_MSB))) << 32);
+	adapter->stats.last_vfgptc = IXGBE_READ_REG(hw, IXGBE_VFGPTC);
+	adapter->stats.last_vfgotc = IXGBE_READ_REG(hw, IXGBE_VFGOTC_LSB);
+	adapter->stats.last_vfgotc |=
+		(((u64)(IXGBE_READ_REG(hw, IXGBE_VFGOTC_MSB))) << 32);
+	adapter->stats.last_vfmprc = IXGBE_READ_REG(hw, IXGBE_VFMPRC);
+
+	adapter->stats.base_vfgprc = adapter->stats.last_vfgprc;
+	adapter->stats.base_vfgorc = adapter->stats.last_vfgorc;
+	adapter->stats.base_vfgptc = adapter->stats.last_vfgptc;
+	adapter->stats.base_vfgotc = adapter->stats.last_vfgotc;
+	adapter->stats.base_vfmprc = adapter->stats.last_vfmprc;
+}
+
+#define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter)	\
+	{							\
+		u32 current_counter = IXGBE_READ_REG(hw, reg);	\
+		if (current_counter < last_counter)		\
+			counter += 0x100000000LL;		\
+		last_counter = current_counter;			\
+		counter &= 0xFFFFFFFF00000000LL;		\
+		counter |= current_counter;			\
+	}
+
+#define UPDATE_VF_COUNTER_36bit(reg_lsb, reg_msb, last_counter, counter) \
+	{								 \
+		u64 current_counter_lsb = IXGBE_READ_REG(hw, reg_lsb);	 \
+		u64 current_counter_msb = IXGBE_READ_REG(hw, reg_msb);	 \
+		u64 current_counter = (current_counter_msb << 32) |      \
+			current_counter_lsb;                             \
+		if (current_counter < last_counter)			 \
+			counter += 0x1000000000LL;			 \
+		last_counter = current_counter;				 \
+		counter &= 0xFFFFFFF000000000LL;			 \
+		counter |= current_counter;				 \
+	}
+/**
+ * ixgbevf_update_stats - Update the board statistics counters.
+ * @adapter: board private structure
+ **/
+void ixgbevf_update_stats(struct ixgbevf_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc,
+				adapter->stats.vfgprc);
+	UPDATE_VF_COUNTER_32bit(IXGBE_VFGPTC, adapter->stats.last_vfgptc,
+				adapter->stats.vfgptc);
+	UPDATE_VF_COUNTER_36bit(IXGBE_VFGORC_LSB, IXGBE_VFGORC_MSB,
+				adapter->stats.last_vfgorc,
+				adapter->stats.vfgorc);
+	UPDATE_VF_COUNTER_36bit(IXGBE_VFGOTC_LSB, IXGBE_VFGOTC_MSB,
+				adapter->stats.last_vfgotc,
+				adapter->stats.vfgotc);
+	UPDATE_VF_COUNTER_32bit(IXGBE_VFMPRC, adapter->stats.last_vfmprc,
+				adapter->stats.vfmprc);
+
+	/* Fill out the OS statistics structure */
+	adapter->net_stats.multicast = adapter->stats.vfmprc -
+		adapter->stats.base_vfmprc;
+}
+
+/**
+ * ixgbevf_watchdog - Timer Call-back
+ * @data: pointer to adapter cast into an unsigned long
+ **/
+static void ixgbevf_watchdog(unsigned long data)
+{
+	struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 eics = 0;
+	int i;
+
+	/*
+	 * Do the watchdog outside of interrupt context due to the lovely
+	 * delays that some of the newer hardware requires
+	 */
+
+	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
+		goto watchdog_short_circuit;
+
+	/* get one bit for every active tx/rx interrupt vector */
+	for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) {
+		struct ixgbevf_q_vector *qv = adapter->q_vector[i];
+		if (qv->rxr_count || qv->txr_count)
+			eics |= (1 << i);
+	}
+
+	IXGBE_WRITE_REG(hw, IXGBE_VTEICS, (u32)eics);
+
+watchdog_short_circuit:
+	schedule_work(&adapter->watchdog_task);
+}
+
+/**
+ * ixgbevf_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ **/
+static void ixgbevf_tx_timeout(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	/* Do the reset outside of interrupt context */
+	schedule_work(&adapter->reset_task);
+}
+
+static void ixgbevf_reset_task(struct work_struct *work)
+{
+	struct ixgbevf_adapter *adapter;
+	adapter = container_of(work, struct ixgbevf_adapter, reset_task);
+
+	/* If we're already down or resetting, just bail */
+	if (test_bit(__IXGBEVF_DOWN, &adapter->state) ||
+	    test_bit(__IXGBEVF_RESETTING, &adapter->state))
+		return;
+
+	adapter->tx_timeout_count++;
+
+	ixgbevf_reinit_locked(adapter);
+}
+
+/**
+ * ixgbevf_watchdog_task - worker thread to bring link up
+ * @work: pointer to work_struct containing our data
+ **/
+static void ixgbevf_watchdog_task(struct work_struct *work)
+{
+	struct ixgbevf_adapter *adapter = container_of(work,
+						       struct ixgbevf_adapter,
+						       watchdog_task);
+	struct net_device *netdev = adapter->netdev;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 link_speed = adapter->link_speed;
+	bool link_up = adapter->link_up;
+
+	adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK;
+
+	/*
+	 * Always check the link on the watchdog because we have
+	 * no LSC interrupt
+	 */
+	if (hw->mac.ops.check_link) {
+		if ((hw->mac.ops.check_link(hw, &link_speed,
+					    &link_up, false)) != 0) {
+			adapter->link_up = link_up;
+			adapter->link_speed = link_speed;
+			schedule_work(&adapter->reset_task);
+			goto pf_has_reset;
+		}
+	} else {
+		/* always assume link is up, if no check link
+		 * function */
+		link_speed = IXGBE_LINK_SPEED_10GB_FULL;
+		link_up = true;
+	}
+	adapter->link_up = link_up;
+	adapter->link_speed = link_speed;
+
+	if (link_up) {
+		if (!netif_carrier_ok(netdev)) {
+			hw_dbg(&adapter->hw, "NIC Link is Up %s, ",
+			       ((link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
+				"10 Gbps" : "1 Gbps"));
+			netif_carrier_on(netdev);
+			netif_tx_wake_all_queues(netdev);
+		} else {
+			/* Force detection of hung controller */
+			adapter->detect_tx_hung = true;
+		}
+	} else {
+		adapter->link_up = false;
+		adapter->link_speed = 0;
+		if (netif_carrier_ok(netdev)) {
+			hw_dbg(&adapter->hw, "NIC Link is Down\n");
+			netif_carrier_off(netdev);
+			netif_tx_stop_all_queues(netdev);
+		}
+	}
+
+pf_has_reset:
+	ixgbevf_update_stats(adapter);
+
+	/* Force detection of hung controller every watchdog period */
+	adapter->detect_tx_hung = true;
+
+	/* Reset the timer */
+	if (!test_bit(__IXGBEVF_DOWN, &adapter->state))
+		mod_timer(&adapter->watchdog_timer,
+			  round_jiffies(jiffies + (2 * HZ)));
+
+	adapter->flags &= ~IXGBE_FLAG_IN_WATCHDOG_TASK;
+}
+
+/**
+ * ixgbevf_free_tx_resources - Free Tx Resources per Queue
+ * @adapter: board private structure
+ * @tx_ring: Tx descriptor ring for a specific queue
+ *
+ * Free all transmit software resources
+ **/
+void ixgbevf_free_tx_resources(struct ixgbevf_adapter *adapter,
+			       struct ixgbevf_ring *tx_ring)
+{
+	struct pci_dev *pdev = adapter->pdev;
+
+
+	ixgbevf_clean_tx_ring(adapter, tx_ring);
+
+	vfree(tx_ring->tx_buffer_info);
+	tx_ring->tx_buffer_info = NULL;
+
+	pci_free_consistent(pdev, tx_ring->size, tx_ring->desc, tx_ring->dma);
+
+	tx_ring->desc = NULL;
+}
+
+/**
+ * ixgbevf_free_all_tx_resources - Free Tx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all transmit software resources
+ **/
+static void ixgbevf_free_all_tx_resources(struct ixgbevf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++)
+		if (adapter->tx_ring[i].desc)
+			ixgbevf_free_tx_resources(adapter,
+						  &adapter->tx_ring[i]);
+
+}
+
+/**
+ * ixgbevf_setup_tx_resources - allocate Tx resources (Descriptors)
+ * @adapter: board private structure
+ * @tx_ring:    tx descriptor ring (for a specific queue) to setup
+ *
+ * Return 0 on success, negative on failure
+ **/
+int ixgbevf_setup_tx_resources(struct ixgbevf_adapter *adapter,
+			       struct ixgbevf_ring *tx_ring)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	int size;
+
+	size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count;
+	tx_ring->tx_buffer_info = vmalloc(size);
+	if (!tx_ring->tx_buffer_info)
+		goto err;
+	memset(tx_ring->tx_buffer_info, 0, size);
+
+	/* round up to nearest 4K */
+	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
+	tx_ring->size = ALIGN(tx_ring->size, 4096);
+
+	tx_ring->desc = pci_alloc_consistent(pdev, tx_ring->size,
+					     &tx_ring->dma);
+	if (!tx_ring->desc)
+		goto err;
+
+	tx_ring->next_to_use = 0;
+	tx_ring->next_to_clean = 0;
+	tx_ring->work_limit = tx_ring->count;
+	return 0;
+
+err:
+	vfree(tx_ring->tx_buffer_info);
+	tx_ring->tx_buffer_info = NULL;
+	hw_dbg(&adapter->hw, "Unable to allocate memory for the transmit "
+	       "descriptor ring\n");
+	return -ENOMEM;
+}
+
+/**
+ * ixgbevf_setup_all_tx_resources - allocate all queues Tx resources
+ * @adapter: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not).  It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter)
+{
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		err = ixgbevf_setup_tx_resources(adapter, &adapter->tx_ring[i]);
+		if (!err)
+			continue;
+		hw_dbg(&adapter->hw,
+		       "Allocation for Tx Queue %u failed\n", i);
+		break;
+	}
+
+	return err;
+}
+
+/**
+ * ixgbevf_setup_rx_resources - allocate Rx resources (Descriptors)
+ * @adapter: board private structure
+ * @rx_ring:    rx descriptor ring (for a specific queue) to setup
+ *
+ * Returns 0 on success, negative on failure
+ **/
+int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter,
+			       struct ixgbevf_ring *rx_ring)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	int size;
+
+	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
+	rx_ring->rx_buffer_info = vmalloc(size);
+	if (!rx_ring->rx_buffer_info) {
+		hw_dbg(&adapter->hw,
+		       "Unable to vmalloc buffer memory for "
+		       "the receive descriptor ring\n");
+		goto alloc_failed;
+	}
+	memset(rx_ring->rx_buffer_info, 0, size);
+
+	/* Round up to nearest 4K */
+	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
+	rx_ring->size = ALIGN(rx_ring->size, 4096);
+
+	rx_ring->desc = pci_alloc_consistent(pdev, rx_ring->size,
+					     &rx_ring->dma);
+
+	if (!rx_ring->desc) {
+		hw_dbg(&adapter->hw,
+		       "Unable to allocate memory for "
+		       "the receive descriptor ring\n");
+		vfree(rx_ring->rx_buffer_info);
+		rx_ring->rx_buffer_info = NULL;
+		goto alloc_failed;
+	}
+
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+
+	return 0;
+alloc_failed:
+	return -ENOMEM;
+}
+
+/**
+ * ixgbevf_setup_all_rx_resources - allocate all queues Rx resources
+ * @adapter: board private structure
+ *
+ * If this function returns with an error, then it's possible one or
+ * more of the rings is populated (while the rest are not).  It is the
+ * callers duty to clean those orphaned rings.
+ *
+ * Return 0 on success, negative on failure
+ **/
+static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter)
+{
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		err = ixgbevf_setup_rx_resources(adapter, &adapter->rx_ring[i]);
+		if (!err)
+			continue;
+		hw_dbg(&adapter->hw,
+		       "Allocation for Rx Queue %u failed\n", i);
+		break;
+	}
+	return err;
+}
+
+/**
+ * ixgbevf_free_rx_resources - Free Rx Resources
+ * @adapter: board private structure
+ * @rx_ring: ring to clean the resources from
+ *
+ * Free all receive software resources
+ **/
+void ixgbevf_free_rx_resources(struct ixgbevf_adapter *adapter,
+			       struct ixgbevf_ring *rx_ring)
+{
+	struct pci_dev *pdev = adapter->pdev;
+
+	ixgbevf_clean_rx_ring(adapter, rx_ring);
+
+	vfree(rx_ring->rx_buffer_info);
+	rx_ring->rx_buffer_info = NULL;
+
+	pci_free_consistent(pdev, rx_ring->size, rx_ring->desc, rx_ring->dma);
+
+	rx_ring->desc = NULL;
+}
+
+/**
+ * ixgbevf_free_all_rx_resources - Free Rx Resources for All Queues
+ * @adapter: board private structure
+ *
+ * Free all receive software resources
+ **/
+static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		if (adapter->rx_ring[i].desc)
+			ixgbevf_free_rx_resources(adapter,
+						  &adapter->rx_ring[i]);
+}
+
+/**
+ * ixgbevf_open - Called when a network interface is made active
+ * @netdev: network interface device structure
+ *
+ * Returns 0 on success, negative value on failure
+ *
+ * The open entry point is called when a network interface is made
+ * active by the system (IFF_UP).  At this point all resources needed
+ * for transmit and receive operations are allocated, the interrupt
+ * handler is registered with the OS, the watchdog timer is started,
+ * and the stack is notified that the interface is ready.
+ **/
+static int ixgbevf_open(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	/* disallow open during test */
+	if (test_bit(__IXGBEVF_TESTING, &adapter->state))
+		return -EBUSY;
+
+	if (hw->adapter_stopped) {
+		ixgbevf_reset(adapter);
+		/* if adapter is still stopped then PF isn't up and
+		 * the vf can't start. */
+		if (hw->adapter_stopped) {
+			err = IXGBE_ERR_MBX;
+			printk(KERN_ERR "Unable to start - perhaps the PF"
+			       "Driver isn't up yet\n");
+			goto err_setup_reset;
+		}
+	}
+
+	/* allocate transmit descriptors */
+	err = ixgbevf_setup_all_tx_resources(adapter);
+	if (err)
+		goto err_setup_tx;
+
+	/* allocate receive descriptors */
+	err = ixgbevf_setup_all_rx_resources(adapter);
+	if (err)
+		goto err_setup_rx;
+
+	ixgbevf_configure(adapter);
+
+	/*
+	 * Map the Tx/Rx rings to the vectors we were allotted.
+	 * if request_irq will be called in this function map_rings
+	 * must be called *before* up_complete
+	 */
+	ixgbevf_map_rings_to_vectors(adapter);
+
+	err = ixgbevf_up_complete(adapter);
+	if (err)
+		goto err_up;
+
+	/* clear any pending interrupts, may auto mask */
+	IXGBE_READ_REG(hw, IXGBE_VTEICR);
+	err = ixgbevf_request_irq(adapter);
+	if (err)
+		goto err_req_irq;
+
+	ixgbevf_irq_enable(adapter, true, true);
+
+	return 0;
+
+err_req_irq:
+	ixgbevf_down(adapter);
+err_up:
+	ixgbevf_free_irq(adapter);
+err_setup_rx:
+	ixgbevf_free_all_rx_resources(adapter);
+err_setup_tx:
+	ixgbevf_free_all_tx_resources(adapter);
+	ixgbevf_reset(adapter);
+
+err_setup_reset:
+
+	return err;
+}
+
+/**
+ * ixgbevf_close - Disables a network interface
+ * @netdev: network interface device structure
+ *
+ * Returns 0, this is not allowed to fail
+ *
+ * The close entry point is called when an interface is de-activated
+ * by the OS.  The hardware is still under the drivers control, but
+ * needs to be disabled.  A global MAC reset is issued to stop the
+ * hardware, and all transmit and receive resources are freed.
+ **/
+static int ixgbevf_close(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	ixgbevf_down(adapter);
+	ixgbevf_free_irq(adapter);
+
+	ixgbevf_free_all_tx_resources(adapter);
+	ixgbevf_free_all_rx_resources(adapter);
+
+	return 0;
+}
+
+static int ixgbevf_tso(struct ixgbevf_adapter *adapter,
+		       struct ixgbevf_ring *tx_ring,
+		       struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+{
+	struct ixgbe_adv_tx_context_desc *context_desc;
+	unsigned int i;
+	int err;
+	struct ixgbevf_tx_buffer *tx_buffer_info;
+	u32 vlan_macip_lens = 0, type_tucmd_mlhl;
+	u32 mss_l4len_idx, l4len;
+
+	if (skb_is_gso(skb)) {
+		if (skb_header_cloned(skb)) {
+			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+			if (err)
+				return err;
+		}
+		l4len = tcp_hdrlen(skb);
+		*hdr_len += l4len;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			struct iphdr *iph = ip_hdr(skb);
+			iph->tot_len = 0;
+			iph->check = 0;
+			tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
+								 iph->daddr, 0,
+								 IPPROTO_TCP,
+								 0);
+			adapter->hw_tso_ctxt++;
+		} else if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV6) {
+			ipv6_hdr(skb)->payload_len = 0;
+			tcp_hdr(skb)->check =
+			    ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					     &ipv6_hdr(skb)->daddr,
+					     0, IPPROTO_TCP, 0);
+			adapter->hw_tso6_ctxt++;
+		}
+
+		i = tx_ring->next_to_use;
+
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i);
+
+		/* VLAN MACLEN IPLEN */
+		if (tx_flags & IXGBE_TX_FLAGS_VLAN)
+			vlan_macip_lens |=
+				(tx_flags & IXGBE_TX_FLAGS_VLAN_MASK);
+		vlan_macip_lens |= ((skb_network_offset(skb)) <<
+				    IXGBE_ADVTXD_MACLEN_SHIFT);
+		*hdr_len += skb_network_offset(skb);
+		vlan_macip_lens |=
+			(skb_transport_header(skb) - skb_network_header(skb));
+		*hdr_len +=
+			(skb_transport_header(skb) - skb_network_header(skb));
+		context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
+		context_desc->seqnum_seed = 0;
+
+		/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
+		type_tucmd_mlhl = (IXGBE_TXD_CMD_DEXT |
+				    IXGBE_ADVTXD_DTYP_CTXT);
+
+		if (skb->protocol == htons(ETH_P_IP))
+			type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4;
+		type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_L4T_TCP;
+		context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl);
+
+		/* MSS L4LEN IDX */
+		mss_l4len_idx =
+			(skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT);
+		mss_l4len_idx |= (l4len << IXGBE_ADVTXD_L4LEN_SHIFT);
+		/* use index 1 for TSO */
+		mss_l4len_idx |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
+		context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx);
+
+		tx_buffer_info->time_stamp = jiffies;
+		tx_buffer_info->next_to_watch = i;
+
+		i++;
+		if (i == tx_ring->count)
+			i = 0;
+		tx_ring->next_to_use = i;
+
+		return true;
+	}
+
+	return false;
+}
+
+static bool ixgbevf_tx_csum(struct ixgbevf_adapter *adapter,
+			    struct ixgbevf_ring *tx_ring,
+			    struct sk_buff *skb, u32 tx_flags)
+{
+	struct ixgbe_adv_tx_context_desc *context_desc;
+	unsigned int i;
+	struct ixgbevf_tx_buffer *tx_buffer_info;
+	u32 vlan_macip_lens = 0, type_tucmd_mlhl = 0;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL ||
+	    (tx_flags & IXGBE_TX_FLAGS_VLAN)) {
+		i = tx_ring->next_to_use;
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		context_desc = IXGBE_TX_CTXTDESC_ADV(*tx_ring, i);
+
+		if (tx_flags & IXGBE_TX_FLAGS_VLAN)
+			vlan_macip_lens |= (tx_flags &
+					    IXGBE_TX_FLAGS_VLAN_MASK);
+		vlan_macip_lens |= (skb_network_offset(skb) <<
+				    IXGBE_ADVTXD_MACLEN_SHIFT);
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			vlan_macip_lens |= (skb_transport_header(skb) -
+					    skb_network_header(skb));
+
+		context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens);
+		context_desc->seqnum_seed = 0;
+
+		type_tucmd_mlhl |= (IXGBE_TXD_CMD_DEXT |
+				    IXGBE_ADVTXD_DTYP_CTXT);
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			switch (skb->protocol) {
+			case __constant_htons(ETH_P_IP):
+				type_tucmd_mlhl |= IXGBE_ADVTXD_TUCMD_IPV4;
+				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+					type_tucmd_mlhl |=
+					    IXGBE_ADVTXD_TUCMD_L4T_TCP;
+				break;
+			case __constant_htons(ETH_P_IPV6):
+				/* XXX what about other V6 headers?? */
+				if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
+					type_tucmd_mlhl |=
+						IXGBE_ADVTXD_TUCMD_L4T_TCP;
+				break;
+			default:
+				if (unlikely(net_ratelimit())) {
+					printk(KERN_WARNING
+					       "partial checksum but "
+					       "proto=%x!\n",
+					       skb->protocol);
+				}
+				break;
+			}
+		}
+
+		context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd_mlhl);
+		/* use index zero for tx checksum offload */
+		context_desc->mss_l4len_idx = 0;
+
+		tx_buffer_info->time_stamp = jiffies;
+		tx_buffer_info->next_to_watch = i;
+
+		adapter->hw_csum_tx_good++;
+		i++;
+		if (i == tx_ring->count)
+			i = 0;
+		tx_ring->next_to_use = i;
+
+		return true;
+	}
+
+	return false;
+}
+
+static int ixgbevf_tx_map(struct ixgbevf_adapter *adapter,
+			  struct ixgbevf_ring *tx_ring,
+			  struct sk_buff *skb, u32 tx_flags,
+			  unsigned int first)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ixgbevf_tx_buffer *tx_buffer_info;
+	unsigned int len;
+	unsigned int total = skb->len;
+	unsigned int offset = 0, size, count = 0, i;
+	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+	unsigned int f;
+
+	i = tx_ring->next_to_use;
+
+	len = min(skb_headlen(skb), total);
+	while (len) {
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);
+
+		tx_buffer_info->length = size;
+		tx_buffer_info->mapped_as_page = false;
+		tx_buffer_info->dma = pci_map_single(adapter->pdev,
+						     skb->data + offset,
+						     size, PCI_DMA_TODEVICE);
+		if (pci_dma_mapping_error(pdev, tx_buffer_info->dma))
+			goto dma_error;
+		tx_buffer_info->time_stamp = jiffies;
+		tx_buffer_info->next_to_watch = i;
+
+		len -= size;
+		total -= size;
+		offset += size;
+		count++;
+		i++;
+		if (i == tx_ring->count)
+			i = 0;
+	}
+
+	for (f = 0; f < nr_frags; f++) {
+		struct skb_frag_struct *frag;
+
+		frag = &skb_shinfo(skb)->frags[f];
+		len = min((unsigned int)frag->size, total);
+		offset = frag->page_offset;
+
+		while (len) {
+			tx_buffer_info = &tx_ring->tx_buffer_info[i];
+			size = min(len, (unsigned int)IXGBE_MAX_DATA_PER_TXD);
+
+			tx_buffer_info->length = size;
+			tx_buffer_info->dma = pci_map_page(adapter->pdev,
+							   frag->page,
+							   offset,
+							   size,
+							   PCI_DMA_TODEVICE);
+			tx_buffer_info->mapped_as_page = true;
+			if (pci_dma_mapping_error(pdev, tx_buffer_info->dma))
+				goto dma_error;
+			tx_buffer_info->time_stamp = jiffies;
+			tx_buffer_info->next_to_watch = i;
+
+			len -= size;
+			total -= size;
+			offset += size;
+			count++;
+			i++;
+			if (i == tx_ring->count)
+				i = 0;
+		}
+		if (total == 0)
+			break;
+	}
+
+	if (i == 0)
+		i = tx_ring->count - 1;
+	else
+		i = i - 1;
+	tx_ring->tx_buffer_info[i].skb = skb;
+	tx_ring->tx_buffer_info[first].next_to_watch = i;
+
+	return count;
+
+dma_error:
+	dev_err(&pdev->dev, "TX DMA map failed\n");
+
+	/* clear timestamp and dma mappings for failed tx_buffer_info map */
+	tx_buffer_info->dma = 0;
+	tx_buffer_info->time_stamp = 0;
+	tx_buffer_info->next_to_watch = 0;
+	count--;
+
+	/* clear timestamp and dma mappings for remaining portion of packet */
+	while (count >= 0) {
+		count--;
+		i--;
+		if (i < 0)
+			i += tx_ring->count;
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		ixgbevf_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+	}
+
+	return count;
+}
+
+static void ixgbevf_tx_queue(struct ixgbevf_adapter *adapter,
+			     struct ixgbevf_ring *tx_ring, int tx_flags,
+			     int count, u32 paylen, u8 hdr_len)
+{
+	union ixgbe_adv_tx_desc *tx_desc = NULL;
+	struct ixgbevf_tx_buffer *tx_buffer_info;
+	u32 olinfo_status = 0, cmd_type_len = 0;
+	unsigned int i;
+
+	u32 txd_cmd = IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS | IXGBE_TXD_CMD_IFCS;
+
+	cmd_type_len |= IXGBE_ADVTXD_DTYP_DATA;
+
+	cmd_type_len |= IXGBE_ADVTXD_DCMD_IFCS | IXGBE_ADVTXD_DCMD_DEXT;
+
+	if (tx_flags & IXGBE_TX_FLAGS_VLAN)
+		cmd_type_len |= IXGBE_ADVTXD_DCMD_VLE;
+
+	if (tx_flags & IXGBE_TX_FLAGS_TSO) {
+		cmd_type_len |= IXGBE_ADVTXD_DCMD_TSE;
+
+		olinfo_status |= IXGBE_TXD_POPTS_TXSM <<
+			IXGBE_ADVTXD_POPTS_SHIFT;
+
+		/* use index 1 context for tso */
+		olinfo_status |= (1 << IXGBE_ADVTXD_IDX_SHIFT);
+		if (tx_flags & IXGBE_TX_FLAGS_IPV4)
+			olinfo_status |= IXGBE_TXD_POPTS_IXSM <<
+				IXGBE_ADVTXD_POPTS_SHIFT;
+
+	} else if (tx_flags & IXGBE_TX_FLAGS_CSUM)
+		olinfo_status |= IXGBE_TXD_POPTS_TXSM <<
+			IXGBE_ADVTXD_POPTS_SHIFT;
+
+	olinfo_status |= ((paylen - hdr_len) << IXGBE_ADVTXD_PAYLEN_SHIFT);
+
+	i = tx_ring->next_to_use;
+	while (count--) {
+		tx_buffer_info = &tx_ring->tx_buffer_info[i];
+		tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
+		tx_desc->read.buffer_addr = cpu_to_le64(tx_buffer_info->dma);
+		tx_desc->read.cmd_type_len =
+			cpu_to_le32(cmd_type_len | tx_buffer_info->length);
+		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
+		i++;
+		if (i == tx_ring->count)
+			i = 0;
+	}
+
+	tx_desc->read.cmd_type_len |= cpu_to_le32(txd_cmd);
+
+	/*
+	 * 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();
+
+	tx_ring->next_to_use = i;
+	writel(i, adapter->hw.hw_addr + tx_ring->tail);
+}
+
+static int __ixgbevf_maybe_stop_tx(struct net_device *netdev,
+				   struct ixgbevf_ring *tx_ring, int size)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	netif_stop_subqueue(netdev, tx_ring->queue_index);
+	/* Herbert's original patch had:
+	 *  smp_mb__after_netif_stop_queue();
+	 * but since that doesn't exist yet, just open code it. */
+	smp_mb();
+
+	/* We need to check again in a case another CPU has just
+	 * made room available. */
+	if (likely(IXGBE_DESC_UNUSED(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(netdev, tx_ring->queue_index);
+	++adapter->restart_queue;
+	return 0;
+}
+
+static int ixgbevf_maybe_stop_tx(struct net_device *netdev,
+				 struct ixgbevf_ring *tx_ring, int size)
+{
+	if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size))
+		return 0;
+	return __ixgbevf_maybe_stop_tx(netdev, tx_ring, size);
+}
+
+static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbevf_ring *tx_ring;
+	unsigned int first;
+	unsigned int tx_flags = 0;
+	u8 hdr_len = 0;
+	int r_idx = 0, tso;
+	int count = 0;
+
+	unsigned int f;
+
+	tx_ring = &adapter->tx_ring[r_idx];
+
+	if (adapter->vlgrp && vlan_tx_tag_present(skb)) {
+		tx_flags |= vlan_tx_tag_get(skb);
+		tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
+		tx_flags |= IXGBE_TX_FLAGS_VLAN;
+	}
+
+	/* four things can cause us to need a context descriptor */
+	if (skb_is_gso(skb) ||
+	    (skb->ip_summed == CHECKSUM_PARTIAL) ||
+	    (tx_flags & IXGBE_TX_FLAGS_VLAN))
+		count++;
+
+	count += TXD_USE_COUNT(skb_headlen(skb));
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+
+	if (ixgbevf_maybe_stop_tx(netdev, tx_ring, count)) {
+		adapter->tx_busy++;
+		return NETDEV_TX_BUSY;
+	}
+
+	first = tx_ring->next_to_use;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		tx_flags |= IXGBE_TX_FLAGS_IPV4;
+	tso = ixgbevf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len);
+	if (tso < 0) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	if (tso)
+		tx_flags |= IXGBE_TX_FLAGS_TSO;
+	else if (ixgbevf_tx_csum(adapter, tx_ring, skb, tx_flags) &&
+		 (skb->ip_summed == CHECKSUM_PARTIAL))
+		tx_flags |= IXGBE_TX_FLAGS_CSUM;
+
+	ixgbevf_tx_queue(adapter, tx_ring, tx_flags,
+			 ixgbevf_tx_map(adapter, tx_ring, skb, tx_flags, first),
+			 skb->len, hdr_len);
+
+	netdev->trans_start = jiffies;
+
+	ixgbevf_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);
+
+	return NETDEV_TX_OK;
+}
+
+/**
+ * ixgbevf_get_stats - Get System Network Statistics
+ * @netdev: network interface device structure
+ *
+ * Returns the address of the device statistics structure.
+ * The statistics are actually updated from the timer callback.
+ **/
+static struct net_device_stats *ixgbevf_get_stats(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	/* only return the current stats */
+	return &adapter->net_stats;
+}
+
+/**
+ * ixgbevf_set_mac - Change the Ethernet Address of the NIC
+ * @netdev: network interface device structure
+ * @p: pointer to an address structure
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int ixgbevf_set_mac(struct net_device *netdev, void *p)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
+
+	if (hw->mac.ops.set_rar)
+		hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0);
+
+	return 0;
+}
+
+/**
+ * ixgbevf_change_mtu - Change the Maximum Transfer Unit
+ * @netdev: network interface device structure
+ * @new_mtu: new value for maximum frame size
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+
+	/* MTU < 68 is an error and causes problems on some kernels */
+	if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE))
+		return -EINVAL;
+
+	hw_dbg(&adapter->hw, "changing MTU from %d to %d\n",
+	       netdev->mtu, new_mtu);
+	/* must set new MTU before calling down or up */
+	netdev->mtu = new_mtu;
+
+	if (netif_running(netdev))
+		ixgbevf_reinit_locked(adapter);
+
+	return 0;
+}
+
+static void ixgbevf_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	netif_device_detach(netdev);
+
+	if (netif_running(netdev)) {
+		ixgbevf_down(adapter);
+		ixgbevf_free_irq(adapter);
+		ixgbevf_free_all_tx_resources(adapter);
+		ixgbevf_free_all_rx_resources(adapter);
+	}
+
+#ifdef CONFIG_PM
+	pci_save_state(pdev);
+#endif
+
+	pci_disable_device(pdev);
+}
+
+#ifdef HAVE_NET_DEVICE_OPS
+static const struct net_device_ops ixgbe_netdev_ops = {
+	.ndo_open		= &ixgbevf_open,
+	.ndo_stop		= &ixgbevf_close,
+	.ndo_start_xmit		= &ixgbevf_xmit_frame,
+	.ndo_get_stats		= &ixgbevf_get_stats,
+	.ndo_set_rx_mode	= &ixgbevf_set_rx_mode,
+	.ndo_set_multicast_list	= &ixgbevf_set_rx_mode,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= &ixgbevf_set_mac,
+	.ndo_change_mtu		= &ixgbevf_change_mtu,
+	.ndo_tx_timeout		= &ixgbevf_tx_timeout,
+	.ndo_vlan_rx_register	= &ixgbevf_vlan_rx_register,
+	.ndo_vlan_rx_add_vid	= &ixgbevf_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= &ixgbevf_vlan_rx_kill_vid,
+};
+#endif /* HAVE_NET_DEVICE_OPS */
+
+static void ixgbevf_assign_netdev_ops(struct net_device *dev)
+{
+	struct ixgbevf_adapter *adapter;
+	adapter = netdev_priv(dev);
+#ifdef HAVE_NET_DEVICE_OPS
+	dev->netdev_ops = &ixgbe_netdev_ops;
+#else /* HAVE_NET_DEVICE_OPS */
+	dev->open = &ixgbevf_open;
+	dev->stop = &ixgbevf_close;
+
+	dev->hard_start_xmit = &ixgbevf_xmit_frame;
+
+	dev->get_stats = &ixgbevf_get_stats;
+	dev->set_multicast_list = &ixgbevf_set_rx_mode;
+	dev->set_mac_address = &ixgbevf_set_mac;
+	dev->change_mtu = &ixgbevf_change_mtu;
+	dev->tx_timeout = &ixgbevf_tx_timeout;
+	dev->vlan_rx_register = &ixgbevf_vlan_rx_register;
+	dev->vlan_rx_add_vid = &ixgbevf_vlan_rx_add_vid;
+	dev->vlan_rx_kill_vid = &ixgbevf_vlan_rx_kill_vid;
+#endif /* HAVE_NET_DEVICE_OPS */
+	ixgbevf_set_ethtool_ops(dev);
+	dev->watchdog_timeo = 5 * HZ;
+}
+
+/**
+ * ixgbevf_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in ixgbevf_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * ixgbevf_probe initializes an adapter identified by a pci_dev structure.
+ * The OS initialization, configuring of the adapter private structure,
+ * and a hardware reset occur.
+ **/
+static int __devinit ixgbevf_probe(struct pci_dev *pdev,
+				   const struct pci_device_id *ent)
+{
+	struct net_device *netdev;
+	struct ixgbevf_adapter *adapter = NULL;
+	struct ixgbe_hw *hw = NULL;
+	const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data];
+	static int cards_found;
+	int err, pci_using_dac;
+
+	err = pci_enable_device(pdev);
+	if (err)
+		return err;
+
+	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) &&
+	    !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		pci_using_dac = 1;
+	} else {
+		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (err) {
+			err = pci_set_consistent_dma_mask(pdev,
+							  DMA_BIT_MASK(32));
+			if (err) {
+				dev_err(&pdev->dev, "No usable DMA "
+					"configuration, aborting\n");
+				goto err_dma;
+			}
+		}
+		pci_using_dac = 0;
+	}
+
+	err = pci_request_regions(pdev, ixgbevf_driver_name);
+	if (err) {
+		dev_err(&pdev->dev, "pci_request_regions failed 0x%x\n", err);
+		goto err_pci_reg;
+	}
+
+	pci_set_master(pdev);
+
+#ifdef HAVE_TX_MQ
+	netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter),
+				   MAX_TX_QUEUES);
+#else
+	netdev = alloc_etherdev(sizeof(struct ixgbevf_adapter));
+#endif
+	if (!netdev) {
+		err = -ENOMEM;
+		goto err_alloc_etherdev;
+	}
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+
+	pci_set_drvdata(pdev, netdev);
+	adapter = netdev_priv(netdev);
+
+	adapter->netdev = netdev;
+	adapter->pdev = pdev;
+	hw = &adapter->hw;
+	hw->back = adapter;
+	adapter->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
+
+	/*
+	 * call save state here in standalone driver because it relies on
+	 * adapter struct to exist, and needs to call netdev_priv
+	 */
+	pci_save_state(pdev);
+
+	hw->hw_addr = ioremap(pci_resource_start(pdev, 0),
+			      pci_resource_len(pdev, 0));
+	if (!hw->hw_addr) {
+		err = -EIO;
+		goto err_ioremap;
+	}
+
+	ixgbevf_assign_netdev_ops(netdev);
+
+	adapter->bd_number = cards_found;
+
+	/* Setup hw api */
+	memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops));
+	hw->mac.type  = ii->mac;
+
+	memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops,
+	       sizeof(struct ixgbe_mac_operations));
+
+	adapter->flags &= ~IXGBE_FLAG_RX_PS_CAPABLE;
+	adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
+	adapter->flags |= IXGBE_FLAG_RX_1BUF_CAPABLE;
+
+	/* setup the private structure */
+	err = ixgbevf_sw_init(adapter);
+
+	ixgbevf_init_last_counter_stats(adapter);
+
+#ifdef MAX_SKB_FRAGS
+	netdev->features = NETIF_F_SG |
+			   NETIF_F_IP_CSUM |
+			   NETIF_F_HW_VLAN_TX |
+			   NETIF_F_HW_VLAN_RX |
+			   NETIF_F_HW_VLAN_FILTER;
+
+	netdev->features |= NETIF_F_IPV6_CSUM;
+	netdev->features |= NETIF_F_TSO;
+	netdev->features |= NETIF_F_TSO6;
+	netdev->vlan_features |= NETIF_F_TSO;
+	netdev->vlan_features |= NETIF_F_TSO6;
+	netdev->vlan_features |= NETIF_F_IP_CSUM;
+	netdev->vlan_features |= NETIF_F_SG;
+
+	if (pci_using_dac)
+		netdev->features |= NETIF_F_HIGHDMA;
+
+#endif /* MAX_SKB_FRAGS */
+
+	/* The HW MAC address was set and/or determined in sw_init */
+	memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
+	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
+
+	if (ixgbevf_validate_mac_addr(netdev->dev_addr)) {
+		printk(KERN_ERR "invalid MAC address\n");
+		err = -EIO;
+		goto err_sw_init;
+	}
+
+	init_timer(&adapter->watchdog_timer);
+	adapter->watchdog_timer.function = &ixgbevf_watchdog;
+	adapter->watchdog_timer.data = (unsigned long)adapter;
+
+	INIT_WORK(&adapter->reset_task, ixgbevf_reset_task);
+	INIT_WORK(&adapter->watchdog_task, ixgbevf_watchdog_task);
+
+	err = ixgbevf_init_interrupt_scheme(adapter);
+	if (err)
+		goto err_sw_init;
+
+	/* pick up the PCI bus settings for reporting later */
+	if (hw->mac.ops.get_bus_info)
+		hw->mac.ops.get_bus_info(hw);
+
+
+	netif_carrier_off(netdev);
+	netif_tx_stop_all_queues(netdev);
+
+	strcpy(netdev->name, "eth%d");
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_register;
+
+	adapter->netdev_registered = true;
+
+	/* print the MAC address */
+	hw_dbg(hw, "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x\n",
+	       netdev->dev_addr[0],
+	       netdev->dev_addr[1],
+	       netdev->dev_addr[2],
+	       netdev->dev_addr[3],
+	       netdev->dev_addr[4],
+	       netdev->dev_addr[5]);
+
+	hw_dbg(hw, "MAC: %d\n", hw->mac.type);
+
+	hw_dbg(hw, "LRO is disabled \n");
+
+	hw_dbg(hw, "Intel(R) 82599 Virtual Function\n");
+	cards_found++;
+	return 0;
+
+err_register:
+err_sw_init:
+	ixgbevf_reset_interrupt_capability(adapter);
+	iounmap(hw->hw_addr);
+err_ioremap:
+	free_netdev(netdev);
+err_alloc_etherdev:
+	pci_release_regions(pdev);
+err_pci_reg:
+err_dma:
+	pci_disable_device(pdev);
+	return err;
+}
+
+/**
+ * ixgbevf_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * ixgbevf_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device.  The could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ **/
+static void __devexit ixgbevf_remove(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+
+	set_bit(__IXGBEVF_DOWN, &adapter->state);
+
+	del_timer_sync(&adapter->watchdog_timer);
+
+	cancel_work_sync(&adapter->watchdog_task);
+
+	flush_scheduled_work();
+
+	if (adapter->netdev_registered) {
+		unregister_netdev(netdev);
+		adapter->netdev_registered = false;
+	}
+
+	ixgbevf_reset_interrupt_capability(adapter);
+
+	iounmap(adapter->hw.hw_addr);
+	pci_release_regions(pdev);
+
+	hw_dbg(&adapter->hw, "Remove complete\n");
+
+	kfree(adapter->tx_ring);
+	kfree(adapter->rx_ring);
+
+	free_netdev(netdev);
+
+	pci_disable_device(pdev);
+}
+
+static struct pci_driver ixgbevf_driver = {
+	.name     = ixgbevf_driver_name,
+	.id_table = ixgbevf_pci_tbl,
+	.probe    = ixgbevf_probe,
+	.remove   = __devexit_p(ixgbevf_remove),
+	.shutdown = ixgbevf_shutdown,
+};
+
+/**
+ * ixgbe_init_module - Driver Registration Routine
+ *
+ * ixgbe_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ **/
+static int __init ixgbevf_init_module(void)
+{
+	int ret;
+	printk(KERN_INFO "ixgbevf: %s - version %s\n", ixgbevf_driver_string,
+	       ixgbevf_driver_version);
+
+	printk(KERN_INFO "%s\n", ixgbevf_copyright);
+
+	ret = pci_register_driver(&ixgbevf_driver);
+	return ret;
+}
+
+module_init(ixgbevf_init_module);
+
+/**
+ * ixgbe_exit_module - Driver Exit Cleanup Routine
+ *
+ * ixgbe_exit_module is called just before the driver is removed
+ * from memory.
+ **/
+static void __exit ixgbevf_exit_module(void)
+{
+	pci_unregister_driver(&ixgbevf_driver);
+}
+
+#ifdef DEBUG
+/**
+ * ixgbe_get_hw_dev_name - return device name string
+ * used by hardware layer to print debugging information
+ **/
+char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw)
+{
+	struct ixgbevf_adapter *adapter = hw->back;
+	return adapter->netdev->name;
+}
+
+#endif
+module_exit(ixgbevf_exit_module);
+
+/* ixgbevf_main.c */

Re: [RFC PATCH v2 04/12] ixgbevf: Driver main and ethool interface module and main header

[Simon Horman]

On Fri, Dec 18, 2009 at 02:51:58PM -0800, Jeff Kirsher wrote:
> From: Greg Rose <gregory.v.rose@intel.com>
> 
> These modules and header contain the Linux OS network interface code and core
> interrupt and network send/receive handlers.
> 
> Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> ---
> 
>  drivers/net/ixgbevf/ethtool.c      |  718 +++++++
>  drivers/net/ixgbevf/ixgbevf.h      |  318 +++
>  drivers/net/ixgbevf/ixgbevf_main.c | 3594 ++++++++++++++++++++++++++++++++++++
>  3 files changed, 4630 insertions(+), 0 deletions(-)
>  create mode 100644 drivers/net/ixgbevf/ethtool.c
>  create mode 100644 drivers/net/ixgbevf/ixgbevf.h
>  create mode 100644 drivers/net/ixgbevf/ixgbevf_main.c
> 
> diff --git a/drivers/net/ixgbevf/ethtool.c b/drivers/net/ixgbevf/ethtool.c
> new file mode 100644
> index 0000000..6cf0110
> --- /dev/null
> +++ b/drivers/net/ixgbevf/ethtool.c
> @@ -0,0 +1,718 @@
> +/*******************************************************************************
> +
> +  Intel 82599 Virtual Function driver
> +  Copyright(c) 1999 - 2009 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
> +
> +*******************************************************************************/
> +
> +/* ethtool support for ixgbevf */
> +
> +#include <linux/types.h>
> +#include <linux/module.h>
> +#include <linux/pci.h>
> +#include <linux/netdevice.h>
> +#include <linux/ethtool.h>
> +#include <linux/vmalloc.h>
> +#include <linux/if_vlan.h>
> +#include <linux/uaccess.h>
> +
> +#include "ixgbevf.h"
> +
> +#define IXGBE_ALL_RAR_ENTRIES 16
> +
> +#ifdef ETHTOOL_GSTATS
> +struct ixgbe_stats {
> +	char stat_string[ETH_GSTRING_LEN];
> +	int sizeof_stat;
> +	int stat_offset;
> +	int base_stat_offset;
> +};
> +
> +#define IXGBEVF_STAT(m, b)  sizeof(((struct ixgbevf_adapter *)0)->m), \
> +			    offsetof(struct ixgbevf_adapter, m),      \
> +			    offsetof(struct ixgbevf_adapter, b)
> +static struct ixgbe_stats ixgbe_gstrings_stats[] = {
> +	{"rx_packets", IXGBEVF_STAT(stats.vfgprc, stats.base_vfgprc)},
> +	{"tx_packets", IXGBEVF_STAT(stats.vfgptc, stats.base_vfgptc)},
> +	{"rx_bytes", IXGBEVF_STAT(stats.vfgorc, stats.base_vfgorc)},
> +	{"tx_bytes", IXGBEVF_STAT(stats.vfgotc, stats.base_vfgotc)},
> +	{"tx_busy", IXGBEVF_STAT(tx_busy, zero_base)},
> +	{"multicast", IXGBEVF_STAT(stats.vfmprc, stats.base_vfmprc)},
> +	{"rx_csum_offload_good", IXGBEVF_STAT(hw_csum_rx_good, zero_base)},
> +	{"rx_csum_offload_errors", IXGBEVF_STAT(hw_csum_rx_error, zero_base)},
> +	{"tx_csum_offload_ctxt", IXGBEVF_STAT(hw_csum_tx_good, zero_base)},
> +	{"rx_header_split", IXGBEVF_STAT(rx_hdr_split, zero_base)},
> +};
> +
> +#define IXGBE_QUEUE_STATS_LEN 0
> +#define IXGBE_GLOBAL_STATS_LEN	ARRAY_SIZE(ixgbe_gstrings_stats)
> +
> +#define IXGBEVF_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + IXGBE_QUEUE_STATS_LEN)
> +#endif /* ETHTOOL_GSTATS */
> +#ifdef ETHTOOL_TEST
> +static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
> +	"Register test  (offline)",
> +	"Link test   (on/offline)"
> +};
> +#define IXGBE_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN)
> +#endif /* ETHTOOL_TEST */
> +
> +static int ixgbevf_get_settings(struct net_device *netdev,
> +				struct ethtool_cmd *ecmd)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	struct ixgbe_hw *hw = &adapter->hw;
> +	u32 link_speed = 0;
> +	bool link_up;
> +
> +	ecmd->supported = SUPPORTED_10000baseT_Full;
> +	ecmd->autoneg = AUTONEG_DISABLE;
> +	ecmd->transceiver = XCVR_DUMMY1;
> +	ecmd->port = -1;
> +
> +	hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
> +
> +	if (link_up) {
> +		ecmd->speed = (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
> +			       SPEED_10000 : SPEED_1000;
> +		ecmd->duplex = DUPLEX_FULL;
> +	} else {
> +		ecmd->speed = -1;
> +		ecmd->duplex = -1;
> +	}
> +
> +	return 0;
> +}
> +
> +static u32 ixgbevf_get_rx_csum(struct net_device *netdev)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	return adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED;
> +}
> +
> +static int ixgbevf_set_rx_csum(struct net_device *netdev, u32 data)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	if (data)
> +		adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED;
> +	else
> +		adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED;
> +
> +	if (netif_running(netdev)) {
> +		if (!adapter->dev_closed)
> +			ixgbevf_reinit_locked(adapter);
> +	} else {
> +		ixgbevf_reset(adapter);
> +	}
> +
> +	return 0;
> +}
> +
> +static int ixgbevf_set_tso(struct net_device *netdev, u32 data)
> +{
> +	if (data) {
> +		netdev->features |= NETIF_F_TSO;
> +		netdev->features |= NETIF_F_TSO6;
> +	} else {
> +		netif_tx_stop_all_queues(netdev);
> +		netdev->features &= ~NETIF_F_TSO;
> +		netdev->features &= ~NETIF_F_TSO6;
> +		netif_tx_start_all_queues(netdev);
> +	}
> +	return 0;
> +}
> +
> +static u32 ixgbevf_get_msglevel(struct net_device *netdev)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	return adapter->msg_enable;
> +}
> +
> +static void ixgbevf_set_msglevel(struct net_device *netdev, u32 data)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	adapter->msg_enable = data;
> +}
> +
> +#define IXGBE_GET_STAT(_A_, _R_) (_A_->stats._R_)
> +
> +static char *ixgbevf_reg_names[] = {
> +	"IXGBE_VFCTRL",
> +	"IXGBE_VFSTATUS",
> +	"IXGBE_VFLINKS",
> +	"IXGBE_VFRXMEMWRAP",
> +	"IXGBE_VFRTIMER",
> +	"IXGBE_VTEICR",
> +	"IXGBE_VTEICS",
> +	"IXGBE_VTEIMS",
> +	"IXGBE_VTEIMC",
> +	"IXGBE_VTEIAC",
> +	"IXGBE_VTEIAM",
> +	"IXGBE_VTEITR",
> +	"IXGBE_VTIVAR",
> +	"IXGBE_VTIVAR_MISC",
> +	"IXGBE_VFRDBAL0",
> +	"IXGBE_VFRDBAL1",
> +	"IXGBE_VFRDBAH0",
> +	"IXGBE_VFRDBAH1",
> +	"IXGBE_VFRDLEN0",
> +	"IXGBE_VFRDLEN1",
> +	"IXGBE_VFRDH0",
> +	"IXGBE_VFRDH1",
> +	"IXGBE_VFRDT0",
> +	"IXGBE_VFRDT1",
> +	"IXGBE_VFRXDCTL0",
> +	"IXGBE_VFRXDCTL1",
> +	"IXGBE_VFSRRCTL0",
> +	"IXGBE_VFSRRCTL1",
> +	"IXGBE_VFPSRTYPE",
> +	"IXGBE_VFTDBAL0",
> +	"IXGBE_VFTDBAL1",
> +	"IXGBE_VFTDBAH0",
> +	"IXGBE_VFTDBAH1",
> +	"IXGBE_VFTDLEN0",
> +	"IXGBE_VFTDLEN1",
> +	"IXGBE_VFTDH0",
> +	"IXGBE_VFTDH1",
> +	"IXGBE_VFTDT0",
> +	"IXGBE_VFTDT1",
> +	"IXGBE_VFTXDCTL0",
> +	"IXGBE_VFTXDCTL1",
> +	"IXGBE_VFTDWBAL0",
> +	"IXGBE_VFTDWBAL1",
> +	"IXGBE_VFTDWBAH0",
> +	"IXGBE_VFTDWBAH1"
> +};
> +
> +
> +static int ixgbevf_get_regs_len(struct net_device *netdev)
> +{
> +	return (ARRAY_SIZE(ixgbevf_reg_names)) * sizeof(u32);
> +}
> +
> +static void ixgbevf_get_regs(struct net_device *netdev,
> +			     struct ethtool_regs *regs,
> +			     void *p)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	struct ixgbe_hw *hw = &adapter->hw;
> +	u32 *regs_buff = p;
> +	u32 regs_len = ixgbevf_get_regs_len(netdev);
> +	u8 i;
> +
> +	memset(p, 0, regs_len);
> +
> +	regs->version = (1 << 24) | hw->revision_id << 16 | hw->device_id;
> +
> +	/* General Registers */
> +	regs_buff[0] = IXGBE_READ_REG(hw, IXGBE_VFCTRL);
> +	regs_buff[1] = IXGBE_READ_REG(hw, IXGBE_VFSTATUS);
> +	regs_buff[2] = IXGBE_READ_REG(hw, IXGBE_VFLINKS);
> +	regs_buff[3] = IXGBE_READ_REG(hw, IXGBE_VFRXMEMWRAP);
> +	regs_buff[4] = IXGBE_READ_REG(hw, IXGBE_VFRTIMER);
> +
> +	/* Interrupt */
> +	/* don't read EICR because it can clear interrupt causes, instead
> +	 * read EICS which is a shadow but doesn't clear EICR */
> +	regs_buff[5] = IXGBE_READ_REG(hw, IXGBE_VTEICS);
> +	regs_buff[6] = IXGBE_READ_REG(hw, IXGBE_VTEICS);
> +	regs_buff[7] = IXGBE_READ_REG(hw, IXGBE_VTEIMS);
> +	regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_VTEIMC);
> +	regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_VTEIAC);
> +	regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_VTEIAM);
> +	regs_buff[11] = IXGBE_READ_REG(hw, IXGBE_VTEITR(0));
> +	regs_buff[12] = IXGBE_READ_REG(hw, IXGBE_VTIVAR(0));
> +	regs_buff[13] = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC);
> +
> +	/* Receive DMA */
> +	for (i = 0; i < 2; i++)
> +		regs_buff[14 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAL(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[16 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAH(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[18 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDLEN(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[20 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDH(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[22 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDT(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[24 + i] = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[26 + i] = IXGBE_READ_REG(hw, IXGBE_VFSRRCTL(i));
> +
> +	/* Receive */
> +	regs_buff[28] = IXGBE_READ_REG(hw, IXGBE_VFPSRTYPE);
> +
> +	/* Transmit */
> +	for (i = 0; i < 2; i++)
> +		regs_buff[29 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAL(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[31 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAH(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[33 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDLEN(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDH(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[37 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDT(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[39 + i] = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[41 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAL(i));
> +	for (i = 0; i < 2; i++)
> +		regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAH(i));
> +
> +	for (i = 0; i < regs_len; i++)
> +		printk(KERN_INFO "%s\t%8.8x\n",
> +		       ixgbevf_reg_names[i], regs_buff[i]);
> +}
> +
> +static void ixgbevf_get_drvinfo(struct net_device *netdev,
> +				struct ethtool_drvinfo *drvinfo)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +
> +	strlcpy(drvinfo->driver, ixgbevf_driver_name, 32);
> +	strlcpy(drvinfo->version, ixgbevf_driver_version, 32);
> +
> +	strlcpy(drvinfo->fw_version, "N/A", 4);
> +	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
> +}
> +
> +static void ixgbevf_get_ringparam(struct net_device *netdev,
> +				  struct ethtool_ringparam *ring)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	struct ixgbevf_ring *tx_ring = adapter->tx_ring;
> +	struct ixgbevf_ring *rx_ring = adapter->rx_ring;
> +
> +	ring->rx_max_pending = IXGBEVF_MAX_RXD;
> +	ring->tx_max_pending = IXGBEVF_MAX_TXD;
> +	ring->rx_mini_max_pending = 0;
> +	ring->rx_jumbo_max_pending = 0;
> +	ring->rx_pending = rx_ring->count;
> +	ring->tx_pending = tx_ring->count;
> +	ring->rx_mini_pending = 0;
> +	ring->rx_jumbo_pending = 0;
> +}
> +
> +static int ixgbevf_set_ringparam(struct net_device *netdev,
> +				 struct ethtool_ringparam *ring)
> +{
> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
> +	struct ixgbevf_ring *tx_ring, *rx_ring;
> +	int i, err;
> +	u32 new_rx_count, new_tx_count;
> +	bool need_update = false;
> +
> +	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
> +		return -EINVAL;
> +
> +	new_rx_count = max(ring->rx_pending, (u32)IXGBEVF_MIN_RXD);
> +	new_rx_count = min(new_rx_count, (u32)IXGBEVF_MAX_RXD);
> +	new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE);
> +
> +	new_tx_count = max(ring->tx_pending, (u32)IXGBEVF_MIN_TXD);
> +	new_tx_count = min(new_tx_count, (u32)IXGBEVF_MAX_TXD);
> +	new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE);
> +
> +	if ((new_tx_count == adapter->tx_ring->count) &&
> +	    (new_rx_count == adapter->rx_ring->count)) {
> +		/* nothing to do */
> +		return 0;
> +	}
> +
> +	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
> +		msleep(1);
> +
> +	tx_ring = kcalloc(adapter->num_tx_queues,
> +			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
> +	if (!tx_ring) {
> +		err = -ENOMEM;
> +		goto err_setup;
> +	}
> +
> +	if (new_tx_count != adapter->tx_ring_count) {
> +		memcpy(tx_ring, adapter->tx_ring,
> +		       adapter->num_tx_queues * sizeof(struct ixgbevf_ring));
> +		for (i = 0; i < adapter->num_tx_queues; i++) {
> +			tx_ring[i].count = new_tx_count;
> +			err = ixgbevf_setup_tx_resources(adapter,
> +							 &tx_ring[i]);
> +			if (err) {
> +				while (i) {
> +					i--;
> +					ixgbevf_free_tx_resources(adapter,
> +								  &tx_ring[i]);
> +				}
> +				goto err_setup;
> +			}
> +			tx_ring[i].v_idx = adapter->tx_ring[i].v_idx;
> +		}
> +		need_update = true;
> +	}

> +
> +	rx_ring = kcalloc(adapter->num_rx_queues,
> +			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
> +	if ((!rx_ring) && (need_update)) {
> +		for (i = 0; i < adapter->num_tx_queues; i++)
> +			ixgbevf_free_tx_resources(adapter, &tx_ring[i]);
> +		kfree(tx_ring);
> +		err = -ENOMEM;
> +		goto err_setup;
> +	}
> +
> +	if (new_rx_count != adapter->rx_ring_count) {
> +		memcpy(rx_ring, adapter->rx_ring,
> +		       adapter->num_rx_queues * sizeof(struct ixgbevf_ring));
> +		for (i = 0; i < adapter->num_rx_queues; i++) {
> +			rx_ring[i].count = new_rx_count;
> +			err = ixgbevf_setup_rx_resources(adapter,
> +							 &rx_ring[i]);
> +			if (err) {
> +				while (i) {
> +					i--;
> +					ixgbevf_free_rx_resources(adapter,
> +								  &rx_ring[i]);
> +				}
> +				goto err_setup;

				Are some calls to ixgbevf_free_tx_resources()
				needed here? Perhaps the ones for
				on rx_ring failure could be moved down
				to an err_tx_clear or similar?
				(sorry for the shoddy name)


> +			}
> +			rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
> +		}
> +		need_update = true;
> +	}
> +
> +	/* if rings need to be updated, here's the place to do it in one shot */
> +	if (need_update) {
> +		if (netif_running(netdev))
> +			ixgbevf_down(adapter);
> +
> +		/* tx */
> +		if (new_tx_count != adapter->tx_ring_count) {
> +			kfree(adapter->tx_ring);
> +			adapter->tx_ring = tx_ring;
> +			tx_ring = NULL;
> +			adapter->tx_ring_count = new_tx_count;
> +		}
> +
> +		/* rx */
> +		if (new_rx_count != adapter->rx_ring_count) {
> +			kfree(adapter->rx_ring);
> +			adapter->rx_ring = rx_ring;
> +			rx_ring = NULL;
> +			adapter->rx_ring_count = new_rx_count;
> +		}
> +	}

	Can tx_ring and rx_ring leak here?
> +
> +	/* success! */
> +	err = 0;
> +	if (netif_running(netdev))
> +		ixgbevf_up(adapter);
> +
> +err_setup:
> +	clear_bit(__IXGBEVF_RESETTING, &adapter->state);
> +	return err;
> +}

Dinner calls...

RE: [RFC PATCH v2 04/12] ixgbevf: Driver main and ethool interface module and main header

[Rose, Gregory V]

-----Original Message-----
From: Simon Horman [mailto:horms@verge.net.au] 
Sent: Monday, December 21, 2009 12:00 AM
To: Kirsher, Jeffrey T
Cc: netdev@vger.kernel.org; gospo@redhat.com; Rose, Gregory V
Subject: Re: [RFC PATCH v2 04/12] ixgbevf: Driver main and ethool interface module and main header

> +
> +	if (new_rx_count != adapter->rx_ring_count) {
> +		memcpy(rx_ring, adapter->rx_ring,
> +		       adapter->num_rx_queues * sizeof(struct ixgbevf_ring));
> +		for (i = 0; i < adapter->num_rx_queues; i++) {
> +			rx_ring[i].count = new_rx_count;
> +			err = ixgbevf_setup_rx_resources(adapter,
> +							 &rx_ring[i]);
> +			if (err) {
> +				while (i) {
> +					i--;
> +					ixgbevf_free_rx_resources(adapter,
> +								  &rx_ring[i]);
> +				}
> +				goto err_setup;

				Are some calls to ixgbevf_free_tx_resources()
				needed here? Perhaps the ones for
				on rx_ring failure could be moved down
				to an err_tx_clear or similar?
				(sorry for the shoddy name)

Let me have a look at it and see what I can (or should) do with it.

> +			}
> +			rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
> +		}
> +		need_update = true;
> +	}
> +
> +	/* if rings need to be updated, here's the place to do it in one shot */
> +	if (need_update) {
> +		if (netif_running(netdev))
> +			ixgbevf_down(adapter);
> +
> +		/* tx */
> +		if (new_tx_count != adapter->tx_ring_count) {
> +			kfree(adapter->tx_ring);
> +			adapter->tx_ring = tx_ring;
> +			tx_ring = NULL;
> +			adapter->tx_ring_count = new_tx_count;
> +		}
> +
> +		/* rx */
> +		if (new_rx_count != adapter->rx_ring_count) {
> +			kfree(adapter->rx_ring);
> +			adapter->rx_ring = rx_ring;
> +			rx_ring = NULL;
> +			adapter->rx_ring_count = new_rx_count;
> +		}
> +	}

	Can tx_ring and rx_ring leak here?

Maybe?  Let me look at it a bit closer and see.

I've also looked at your comments to 2/12 and will see what I can do to incorporate your suggestions there.  I appreciate the close review of the code.

- Greg

RE: [RFC PATCH v2 04/12] ixgbevf: Driver main and ethool interface module and main header

[Rose, Gregory V]

>-----Original Message-----
>From: Simon Horman [mailto:horms@verge.net.au]
>Sent: Monday, December 21, 2009 12:00 AM
>To: Kirsher, Jeffrey T
>Cc: netdev@vger.kernel.org; gospo@redhat.com; Rose, Gregory V
>Subject: Re: [RFC PATCH v2 04/12] ixgbevf: Driver main and ethool
>interface module and main header

[snip]

>
>> +
>> +static int ixgbevf_set_ringparam(struct net_device *netdev,
>> +				 struct ethtool_ringparam *ring)
>> +{
>> +	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
>> +	struct ixgbevf_ring *tx_ring, *rx_ring;
>> +	int i, err;
>> +	u32 new_rx_count, new_tx_count;
>> +	bool need_update = false;
>> +
>> +	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
>> +		return -EINVAL;
>> +
>> +	new_rx_count = max(ring->rx_pending, (u32)IXGBEVF_MIN_RXD);
>> +	new_rx_count = min(new_rx_count, (u32)IXGBEVF_MAX_RXD);
>> +	new_rx_count = ALIGN(new_rx_count,
>IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE);
>> +
>> +	new_tx_count = max(ring->tx_pending, (u32)IXGBEVF_MIN_TXD);
>> +	new_tx_count = min(new_tx_count, (u32)IXGBEVF_MAX_TXD);
>> +	new_tx_count = ALIGN(new_tx_count,
>IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE);
>> +
>> +	if ((new_tx_count == adapter->tx_ring->count) &&
>> +	    (new_rx_count == adapter->rx_ring->count)) {
>> +		/* nothing to do */
>> +		return 0;
>> +	}
>> +
>> +	while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state))
>> +		msleep(1);
>> +
>> +	tx_ring = kcalloc(adapter->num_tx_queues,
>> +			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
>> +	if (!tx_ring) {
>> +		err = -ENOMEM;
>> +		goto err_setup;
>> +	}
>> +
>> +	if (new_tx_count != adapter->tx_ring_count) {
>> +		memcpy(tx_ring, adapter->tx_ring,
>> +		       adapter->num_tx_queues * sizeof(struct
>ixgbevf_ring));
>> +		for (i = 0; i < adapter->num_tx_queues; i++) {
>> +			tx_ring[i].count = new_tx_count;
>> +			err = ixgbevf_setup_tx_resources(adapter,
>> +							 &tx_ring[i]);
>> +			if (err) {
>> +				while (i) {
>> +					i--;
>> +					ixgbevf_free_tx_resources(adapter,
>> +								  &tx_ring[i]);
>> +				}
>> +				goto err_setup;
>> +			}
>> +			tx_ring[i].v_idx = adapter->tx_ring[i].v_idx;
>> +		}
>> +		need_update = true;
>> +	}
>
>> +
>> +	rx_ring = kcalloc(adapter->num_rx_queues,
>> +			       sizeof(struct ixgbevf_ring), GFP_KERNEL);
>> +	if ((!rx_ring) && (need_update)) {
>> +		for (i = 0; i < adapter->num_tx_queues; i++)
>> +			ixgbevf_free_tx_resources(adapter, &tx_ring[i]);
>> +		kfree(tx_ring);
>> +		err = -ENOMEM;
>> +		goto err_setup;
>> +	}
>> +
>> +	if (new_rx_count != adapter->rx_ring_count) {
>> +		memcpy(rx_ring, adapter->rx_ring,
>> +		       adapter->num_rx_queues * sizeof(struct
>ixgbevf_ring));
>> +		for (i = 0; i < adapter->num_rx_queues; i++) {
>> +			rx_ring[i].count = new_rx_count;
>> +			err = ixgbevf_setup_rx_resources(adapter,
>> +							 &rx_ring[i]);
>> +			if (err) {
>> +				while (i) {
>> +					i--;
>> +					ixgbevf_free_rx_resources(adapter,
>> +								  &rx_ring[i]);
>> +				}
>> +				goto err_setup;
>
>				Are some calls to ixgbevf_free_tx_resources()
>				needed here? Perhaps the ones for
>				on rx_ring failure could be moved down
>				to an err_tx_clear or similar?
>				(sorry for the shoddy name)
>
>
>> +			}
>> +			rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
>> +		}
>> +		need_update = true;
>> +	}
>> +
>> +	/* if rings need to be updated, here's the place to do it in one
>shot */
>> +	if (need_update) {
>> +		if (netif_running(netdev))
>> +			ixgbevf_down(adapter);
>> +
>> +		/* tx */
>> +		if (new_tx_count != adapter->tx_ring_count) {
>> +			kfree(adapter->tx_ring);
>> +			adapter->tx_ring = tx_ring;
>> +			tx_ring = NULL;
>> +			adapter->tx_ring_count = new_tx_count;
>> +		}
>> +
>> +		/* rx */
>> +		if (new_rx_count != adapter->rx_ring_count) {
>> +			kfree(adapter->rx_ring);
>> +			adapter->rx_ring = rx_ring;
>> +			rx_ring = NULL;
>> +			adapter->rx_ring_count = new_rx_count;
>> +		}
>> +	}
>
>	Can tx_ring and rx_ring leak here?

Most definitely.  I'm fixing this up and will have it straightened out for the next revision of the driver patches.  Good catch again.

Regards,

- Greg

[RFC PATCH v2 05/12] ixgbevf: Driver Makefile

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

82599 Virtual Function Device Driver Makefile

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbevf/Makefile |   38 ++++++++++++++++++++++++++++++++++++++
 1 files changed, 38 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbevf/Makefile

diff --git a/drivers/net/ixgbevf/Makefile b/drivers/net/ixgbevf/Makefile
new file mode 100644
index 0000000..dd4e0d2
--- /dev/null
+++ b/drivers/net/ixgbevf/Makefile
@@ -0,0 +1,38 @@
+################################################################################
+#
+# Intel 82599 Virtual Function driver
+# Copyright(c) 1999 - 2009 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
+#
+################################################################################
+
+#
+# Makefile for the Intel(R) 82599 VF ethernet driver
+#
+
+obj-$(CONFIG_IXGBEVF) += ixgbevf.o
+
+ixgbevf-objs := vf.o \
+                mbx.o \
+                ethtool.o \
+                ixgbevf_main.o
+

[RFC PATCH v2 06/12] ixgbevf: Kconfig, Makefile and Documentation

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

Modifications for the Kconfig and network device Makefile to add the ixgbevf
driver module to the kernel plus basic driver documentation.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 Documentation/networking/ixgbevf.txt |   90 ++++++++++++++++++++++++++++++++++
 drivers/net/Kconfig                  |   22 ++++++++
 drivers/net/Makefile                 |    1 
 3 files changed, 113 insertions(+), 0 deletions(-)
 create mode 100755 Documentation/networking/ixgbevf.txt

diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
new file mode 100755
index 0000000..19015de
--- /dev/null
+++ b/Documentation/networking/ixgbevf.txt
@@ -0,0 +1,90 @@
+Linux* Base Driver for Intel(R) Network Connection
+==================================================
+
+November 24, 2009
+
+Contents
+========
+
+- In This Release
+- Identifying Your Adapter
+- Known Issues/Troubleshooting
+- Support
+
+In This Release
+===============
+
+This file describes the ixgbevf Linux* Base Driver for Intel Network
+Connection.
+
+The ixgbevf driver supports 82599-based virtual function devices that can only
+be activated on kernels with CONFIG_PCI_IOV enabled.
+
+The ixgbevf driver supports virtual functions generated by the ixgbe driver
+with a max_vfs value of 1 or greater.
+
+The guest OS loading the ixgbevf driver must support MSI-X interrupts.
+
+VLANs: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
+
+Identifying Your Adapter
+========================
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/network/sb/CS-008441.htm
+
+Known Issues/Troubleshooting
+============================
+
+  Unloading Physical Function (PF) Driver Causes System Reboots When VM is
+  Running and VF is Loaded on the VM
+  ------------------------------------------------------------------------
+  Do not unload the PF driver (ixgbe) while VFs are assigned to guests.
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
+
+License
+=======
+
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2009 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".
+
+Trademarks
+==========
+
+Intel, Itanium, and Pentium are trademarks or registered trademarks of
+Intel Corporation or its subsidiaries in the United States and other
+countries.
+
+* Other names and brands may be claimed as the property of others.
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index a5be9ac..967bf4b 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2614,6 +2614,28 @@ config IXGBE_DCB
 
 	  If unsure, say N.
 
+config IXGBEVF
+       tristate "Intel(R) 82599 Virtual Function Ethernet support"
+       depends on PCI_MSI
+       ---help---
+         This driver supports Intel(R) 82599 virtual functions.  For more
+         information on how to identify your adapter, go to the Adapter &
+         Driver ID Guide at:
+
+         <http://support.intel.com/support/network/sb/CS-008441.htm>
+
+         For general information and support, go to the Intel support
+         website at:
+
+         <http://support.intel.com>
+
+         More specific information on configuring the driver is in
+         <file:Documentation/networking/ixgbevf.txt>.
+
+         To compile this driver as a module, choose M here. The module
+         will be called ixgbevf.  MSI-X interrupt support is required
+         for this driver to work correctly.
+
 config IXGB
 	tristate "Intel(R) PRO/10GbE support"
 	depends on PCI
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 246323d..da7658b 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IBM_NEW_EMAC) += ibm_newemac/
 obj-$(CONFIG_IGB) += igb/
 obj-$(CONFIG_IGBVF) += igbvf/
 obj-$(CONFIG_IXGBE) += ixgbe/
+obj-$(CONFIG_IXGBEVF) += ixgbevf/
 obj-$(CONFIG_IXGB) += ixgb/
 obj-$(CONFIG_IP1000) += ipg.o
 obj-$(CONFIG_CHELSIO_T1) += chelsio/

[RFC PATCH v2 07/12] ixgbe: Mailbox header and code module

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

The 82599 virtual function device and the master 82599 physical function
device implement a mailbox utility for communication between the devices
using some SRAM scratch memory and a doorbell/answering mechanism enabled
via interrupt and/or polling.  This C module and accompanying header
file implement the base functions for use of this feature.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe_mbx.c |  479 +++++++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_mbx.h |   96 ++++++++
 2 files changed, 575 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbe/ixgbe_mbx.c
 create mode 100644 drivers/net/ixgbe/ixgbe_mbx.h

diff --git a/drivers/net/ixgbe/ixgbe_mbx.c b/drivers/net/ixgbe/ixgbe_mbx.c
new file mode 100644
index 0000000..d75f914
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_mbx.c
@@ -0,0 +1,479 @@
+/*******************************************************************************
+
+  Intel 10 Gigabit PCI Express Linux driver
+  Copyright(c) 1999 - 2009 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/pci.h>
+#include <linux/delay.h>
+#include "ixgbe_type.h"
+#include "ixgbe_common.h"
+#include "ixgbe_mbx.h"
+
+/**
+ *  ixgbe_read_mbx - Reads a message from the mailbox
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @mbx_id: id of mailbox to read
+ *
+ *  returns SUCCESS if it successfuly read message from buffer
+ **/
+s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	/* limit read to size of mailbox */
+	if (size > mbx->size)
+		size = mbx->size;
+
+	if (mbx->ops.read)
+		ret_val = mbx->ops.read(hw, msg, size, mbx_id);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_write_mbx - Write a message to the mailbox
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @mbx_id: id of mailbox to write
+ *
+ *  returns SUCCESS if it successfully copied message into the buffer
+ **/
+s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = 0;
+
+	if (size > mbx->size)
+		ret_val = IXGBE_ERR_MBX;
+
+	else if (mbx->ops.write)
+		ret_val = mbx->ops.write(hw, msg, size, mbx_id);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_msg - checks to see if someone sent us mail
+ *  @hw: pointer to the HW structure
+ *  @mbx_id: id of mailbox to check
+ *
+ *  returns SUCCESS if the Status bit was found or else ERR_MBX
+ **/
+s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (mbx->ops.check_for_msg)
+		ret_val = mbx->ops.check_for_msg(hw, mbx_id);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_ack - checks to see if someone sent us ACK
+ *  @hw: pointer to the HW structure
+ *  @mbx_id: id of mailbox to check
+ *
+ *  returns SUCCESS if the Status bit was found or else ERR_MBX
+ **/
+s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (mbx->ops.check_for_ack)
+		ret_val = mbx->ops.check_for_ack(hw, mbx_id);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_rst - checks to see if other side has reset
+ *  @hw: pointer to the HW structure
+ *  @mbx_id: id of mailbox to check
+ *
+ *  returns SUCCESS if the Status bit was found or else ERR_MBX
+ **/
+s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (mbx->ops.check_for_rst)
+		ret_val = mbx->ops.check_for_rst(hw, mbx_id);
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_poll_for_msg - Wait for message notification
+ *  @hw: pointer to the HW structure
+ *  @mbx_id: id of mailbox to write
+ *
+ *  returns SUCCESS if it successfully received a message notification
+ **/
+static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	int countdown = mbx->timeout;
+
+	if (!countdown || !mbx->ops.check_for_msg)
+		goto out;
+
+	while (countdown && mbx->ops.check_for_msg(hw, mbx_id)) {
+		countdown--;
+		if (!countdown)
+			break;
+		udelay(mbx->usec_delay);
+	}
+
+	/* if we failed, all future posted messages fail until reset */
+	if (!countdown)
+		mbx->timeout = 0;
+out:
+	return countdown ? 0 : IXGBE_ERR_MBX;
+}
+
+/**
+ *  ixgbe_poll_for_ack - Wait for message acknowledgement
+ *  @hw: pointer to the HW structure
+ *  @mbx_id: id of mailbox to write
+ *
+ *  returns SUCCESS if it successfully received a message acknowledgement
+ **/
+static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	int countdown = mbx->timeout;
+
+	if (!countdown || !mbx->ops.check_for_ack)
+		goto out;
+
+	while (countdown && mbx->ops.check_for_ack(hw, mbx_id)) {
+		countdown--;
+		if (!countdown)
+			break;
+		udelay(mbx->usec_delay);
+	}
+
+	/* if we failed, all future posted messages fail until reset */
+	if (!countdown)
+		mbx->timeout = 0;
+out:
+	return countdown ? 0 : IXGBE_ERR_MBX;
+}
+
+/**
+ *  ixgbe_read_posted_mbx - Wait for message notification and receive message
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @mbx_id: id of mailbox to write
+ *
+ *  returns SUCCESS if it successfully received a message notification and
+ *  copied it into the receive buffer.
+ **/
+s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (!mbx->ops.read)
+		goto out;
+
+	ret_val = ixgbe_poll_for_msg(hw, mbx_id);
+
+	/* if ack received read message, otherwise we timed out */
+	if (!ret_val)
+		ret_val = mbx->ops.read(hw, msg, size, mbx_id);
+out:
+	return ret_val;
+}
+
+/**
+ *  ixgbe_write_posted_mbx - Write a message to the mailbox, wait for ack
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @mbx_id: id of mailbox to write
+ *
+ *  returns SUCCESS if it successfully copied message into the buffer and
+ *  received an ack to that message within delay * timeout period
+ **/
+s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size,
+                           u16 mbx_id)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	/* exit if either we can't write or there isn't a defined timeout */
+	if (!mbx->ops.write || !mbx->timeout)
+		goto out;
+
+	/* send msg */
+	ret_val = mbx->ops.write(hw, msg, size, mbx_id);
+
+	/* if msg sent wait until we receive an ack */
+	if (!ret_val)
+		ret_val = ixgbe_poll_for_ack(hw, mbx_id);
+out:
+	return ret_val;
+}
+
+/**
+ *  ixgbe_init_mbx_ops_generic - Initialize MB function pointers
+ *  @hw: pointer to the HW structure
+ *
+ *  Setup the mailbox read and write message function pointers
+ **/
+void ixgbe_init_mbx_ops_generic(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+
+	mbx->ops.read_posted = ixgbe_read_posted_mbx;
+	mbx->ops.write_posted = ixgbe_write_posted_mbx;
+}
+
+static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index)
+{
+	u32 mbvficr = IXGBE_READ_REG(hw, IXGBE_MBVFICR(index));
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (mbvficr & mask) {
+		ret_val = 0;
+		IXGBE_WRITE_REG(hw, IXGBE_MBVFICR(index), mask);
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_msg_pf - checks to see if the VF has sent mail
+ *  @hw: pointer to the HW structure
+ *  @vf_number: the VF index
+ *
+ *  returns SUCCESS if the VF has set the Status bit or else ERR_MBX
+ **/
+static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+	s32 index = IXGBE_MBVFICR_INDEX(vf_number);
+	u32 vf_bit = vf_number % 16;
+
+	if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFREQ_VF1 << vf_bit,
+	                            index)) {
+		ret_val = 0;
+		hw->mbx.stats.reqs++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_ack_pf - checks to see if the VF has ACKed
+ *  @hw: pointer to the HW structure
+ *  @vf_number: the VF index
+ *
+ *  returns SUCCESS if the VF has set the Status bit or else ERR_MBX
+ **/
+static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+	s32 index = IXGBE_MBVFICR_INDEX(vf_number);
+	u32 vf_bit = vf_number % 16;
+
+	if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFACK_VF1 << vf_bit,
+	                            index)) {
+		ret_val = 0;
+		hw->mbx.stats.acks++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_check_for_rst_pf - checks to see if the VF has reset
+ *  @hw: pointer to the HW structure
+ *  @vf_number: the VF index
+ *
+ *  returns SUCCESS if the VF has set the Status bit or else ERR_MBX
+ **/
+static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number)
+{
+	u32 reg_offset = (vf_number < 32) ? 0 : 1;
+	u32 vf_shift = vf_number % 32;
+	u32 vflre = 0;
+	s32 ret_val = IXGBE_ERR_MBX;
+
+	if (hw->mac.type == ixgbe_mac_82599EB)
+		vflre = IXGBE_READ_REG(hw, IXGBE_VFLRE(reg_offset));
+
+	if (vflre & (1 << vf_shift)) {
+		ret_val = 0;
+		IXGBE_WRITE_REG(hw, IXGBE_VFLREC(reg_offset), (1 << vf_shift));
+		hw->mbx.stats.rsts++;
+	}
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_obtain_mbx_lock_pf - obtain mailbox lock
+ *  @hw: pointer to the HW structure
+ *  @vf_number: the VF index
+ *
+ *  return SUCCESS if we obtained the mailbox lock
+ **/
+static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number)
+{
+	s32 ret_val = IXGBE_ERR_MBX;
+	u32 p2v_mailbox;
+
+	/* Take ownership of the buffer */
+	IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_PFU);
+
+	/* reserve mailbox for vf use */
+	p2v_mailbox = IXGBE_READ_REG(hw, IXGBE_PFMAILBOX(vf_number));
+	if (p2v_mailbox & IXGBE_PFMAILBOX_PFU)
+		ret_val = 0;
+
+	return ret_val;
+}
+
+/**
+ *  ixgbe_write_mbx_pf - Places a message in the mailbox
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf_number: the VF index
+ *
+ *  returns SUCCESS if it successfully copied message into the buffer
+ **/
+static s32 ixgbe_write_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size,
+                              u16 vf_number)
+{
+	s32 ret_val;
+	u16 i;
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret_val = ixgbe_obtain_mbx_lock_pf(hw, vf_number);
+	if (ret_val)
+		goto out_no_write;
+
+	/* flush msg and acks as we are overwriting the message buffer */
+	ixgbe_check_for_msg_pf(hw, vf_number);
+	ixgbe_check_for_ack_pf(hw, vf_number);
+
+	/* copy the caller specified message to the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf_number), i, msg[i]);
+
+	/* Interrupt VF to tell it a message has been sent and release buffer*/
+	IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_STS);
+
+	/* update stats */
+	hw->mbx.stats.msgs_tx++;
+
+out_no_write:
+	return ret_val;
+
+}
+
+/**
+ *  ixgbe_read_mbx_pf - Read a message from the mailbox
+ *  @hw: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf_number: the VF index
+ *
+ *  This function copies a message from the mailbox buffer to the caller's
+ *  memory buffer.  The presumption is that the caller knows that there was
+ *  a message due to a VF request so no polling for message is needed.
+ **/
+static s32 ixgbe_read_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size,
+                             u16 vf_number)
+{
+	s32 ret_val;
+	u16 i;
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret_val = ixgbe_obtain_mbx_lock_pf(hw, vf_number);
+	if (ret_val)
+		goto out_no_read;
+
+	/* copy the message to the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		msg[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_PFMBMEM(vf_number), i);
+
+	/* Acknowledge the message and release buffer */
+	IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_ACK);
+
+	/* update stats */
+	hw->mbx.stats.msgs_rx++;
+
+out_no_read:
+	return ret_val;
+}
+
+/**
+ *  ixgbe_init_mbx_params_pf - set initial values for pf mailbox
+ *  @hw: pointer to the HW structure
+ *
+ *  Initializes the hw->mbx struct to correct values for pf mailbox
+ */
+void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw)
+{
+	struct ixgbe_mbx_info *mbx = &hw->mbx;
+
+	if (hw->mac.type != ixgbe_mac_82599EB)
+		return;
+
+	mbx->timeout = 0;
+	mbx->usec_delay = 0;
+
+	mbx->size = IXGBE_VFMAILBOX_SIZE;
+
+	mbx->stats.msgs_tx = 0;
+	mbx->stats.msgs_rx = 0;
+	mbx->stats.reqs = 0;
+	mbx->stats.acks = 0;
+	mbx->stats.rsts = 0;
+}
+
+struct ixgbe_mbx_operations mbx_ops_82599 = {
+	.read                   = ixgbe_read_mbx_pf,
+	.write                  = ixgbe_write_mbx_pf,
+	.read_posted            = ixgbe_read_posted_mbx,
+	.write_posted           = ixgbe_write_posted_mbx,
+	.check_for_msg          = ixgbe_check_for_msg_pf,
+	.check_for_ack          = ixgbe_check_for_ack_pf,
+	.check_for_rst          = ixgbe_check_for_rst_pf,
+};
+
diff --git a/drivers/net/ixgbe/ixgbe_mbx.h b/drivers/net/ixgbe/ixgbe_mbx.h
new file mode 100644
index 0000000..be7ab33
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_mbx.h
@@ -0,0 +1,96 @@
+/*******************************************************************************
+
+  Intel 10 Gigabit PCI Express Linux driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBE_MBX_H_
+#define _IXGBE_MBX_H_
+
+#include "ixgbe_type.h"
+
+#define IXGBE_VFMAILBOX_SIZE        16 /* 16 32 bit words - 64 bytes */
+#define IXGBE_ERR_MBX               -100
+
+#define IXGBE_VFMAILBOX             0x002FC
+#define IXGBE_VFMBMEM               0x00200
+
+#define IXGBE_PFMAILBOX(x)          (0x04B00 + (4 * x))
+#define IXGBE_PFMBMEM(vfn)          (0x13000 + (64 * vfn))
+
+#define IXGBE_PFMAILBOX_STS   0x00000001 /* Initiate message send to VF */
+#define IXGBE_PFMAILBOX_ACK   0x00000002 /* Ack message recv'd from VF */
+#define IXGBE_PFMAILBOX_VFU   0x00000004 /* VF owns the mailbox buffer */
+#define IXGBE_PFMAILBOX_PFU   0x00000008 /* PF owns the mailbox buffer */
+#define IXGBE_PFMAILBOX_RVFU  0x00000010 /* Reset VFU - used when VF stuck */
+
+#define IXGBE_MBVFICR_VFREQ_MASK 0x0000FFFF /* bits for VF messages */
+#define IXGBE_MBVFICR_VFREQ_VF1  0x00000001 /* bit for VF 1 message */
+#define IXGBE_MBVFICR_VFACK_MASK 0xFFFF0000 /* bits for VF acks */
+#define IXGBE_MBVFICR_VFACK_VF1  0x00010000 /* bit for VF 1 ack */
+
+
+/* If it's a IXGBE_VF_* msg then it originates in the VF and is sent to the
+ * PF.  The reverse is true if it is IXGBE_PF_*.
+ * Message ACK's are the value or'd with 0xF0000000
+ */
+#define IXGBE_VT_MSGTYPE_ACK      0x80000000  /* Messages below or'd with
+                                               * this are the ACK */
+#define IXGBE_VT_MSGTYPE_NACK     0x40000000  /* Messages below or'd with
+                                               * this are the NACK */
+#define IXGBE_VT_MSGTYPE_CTS      0x20000000  /* Indicates that VF is still
+                                                 clear to send requests */
+#define IXGBE_VT_MSGINFO_SHIFT    16
+/* bits 23:16 are used for exra info for certain messages */
+#define IXGBE_VT_MSGINFO_MASK     (0xFF << IXGBE_VT_MSGINFO_SHIFT)
+
+#define IXGBE_VF_RESET            0x01 /* VF requests reset */
+#define IXGBE_VF_SET_MAC_ADDR     0x02 /* VF requests PF to set MAC addr */
+#define IXGBE_VF_SET_MULTICAST    0x03 /* VF requests PF to set MC addr */
+#define IXGBE_VF_SET_VLAN         0x04 /* VF requests PF to set VLAN */
+#define IXGBE_VF_SET_LPE          0x05 /* VF requests PF to set VMOLR.LPE */
+
+/* length of permanent address message returned from PF */
+#define IXGBE_VF_PERMADDR_MSG_LEN 4
+/* word in permanent address message with the current multicast type */
+#define IXGBE_VF_MC_TYPE_WORD     3
+
+#define IXGBE_PF_CONTROL_MSG      0x0100 /* PF control message */
+
+#define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */
+#define IXGBE_VF_MBX_INIT_DELAY   500  /* microseconds between retries */
+
+s32 ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16);
+s32 ixgbe_write_mbx(struct ixgbe_hw *, u32 *, u16, u16);
+s32 ixgbe_read_posted_mbx(struct ixgbe_hw *, u32 *, u16, u16);
+s32 ixgbe_write_posted_mbx(struct ixgbe_hw *, u32 *, u16, u16);
+s32 ixgbe_check_for_msg(struct ixgbe_hw *, u16);
+s32 ixgbe_check_for_ack(struct ixgbe_hw *, u16);
+s32 ixgbe_check_for_rst(struct ixgbe_hw *, u16);
+void ixgbe_init_mbx_ops_generic(struct ixgbe_hw *hw);
+void ixgbe_init_mbx_params_pf(struct ixgbe_hw *);
+
+extern struct ixgbe_mbx_operations mbx_ops_82599;
+
+#endif /* _IXGBE_MBX_H_ */

[RFC PATCH v2 08/12] ixgbe: Add SR-IOV register, structure and bit defines

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

This patch adds register definitions, bit definitions and structures used by
the driver to support SR-IOV features of the 82599 controller.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe.h      |   31 ++++++++++++++++++++++-
 drivers/net/ixgbe/ixgbe_main.c |    2 +-
 drivers/net/ixgbe/ixgbe_type.h |   53 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 8da8eb5..ed73585 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -98,6 +98,23 @@
 
 #define IXGBE_MAX_RSC_INT_RATE          162760
 
+#define IXGBE_MAX_VF_MC_ENTRIES         30
+#define IXGBE_MAX_VF_FUNCTIONS          64
+#define IXGBE_MAX_VFTA_ENTRIES          128
+#define MAX_EMULATION_MAC_ADDRS         16
+#define VMDQ_P(p)   ((p) + adapter->num_vfs)
+
+struct vf_data_storage {
+	unsigned char vf_mac_addresses[ETH_ALEN];
+	u16 vf_mc_hashes[IXGBE_MAX_VF_MC_ENTRIES];
+	u16 num_vf_mc_hashes;
+	u16 default_vf_vlan_id;
+	u16 vlans_enabled;
+	unsigned char em_mac_addresses[MAX_EMULATION_MAC_ADDRS * ETH_ALEN];
+	bool clear_to_send;
+	int rar;
+};
+
 /* wrapper around a pointer to a socket buffer,
  * so a DMA handle can be stored along with the buffer */
 struct ixgbe_tx_buffer {
@@ -171,7 +188,7 @@ struct ixgbe_ring {
 enum ixgbe_ring_f_enum {
 	RING_F_NONE = 0,
 	RING_F_DCB,
-	RING_F_VMDQ,
+	RING_F_VMDQ,  /* SR-IOV uses the same ring feature */
 	RING_F_RSS,
 	RING_F_FDIR,
 #ifdef IXGBE_FCOE
@@ -183,7 +200,7 @@ enum ixgbe_ring_f_enum {
 
 #define IXGBE_MAX_DCB_INDICES   8
 #define IXGBE_MAX_RSS_INDICES  16
-#define IXGBE_MAX_VMDQ_INDICES 16
+#define IXGBE_MAX_VMDQ_INDICES 64
 #define IXGBE_MAX_FDIR_INDICES 64
 #ifdef IXGBE_FCOE
 #define IXGBE_MAX_FCOE_INDICES  8
@@ -288,6 +305,8 @@ struct ixgbe_adapter {
 	/* RX */
 	struct ixgbe_ring *rx_ring ____cacheline_aligned_in_smp; /* One per active queue */
 	int num_rx_queues;
+	int num_rx_pools;		/* == num_rx_queues in 82598 */
+	int num_rx_queues_per_pool;	/* 1 if 82598, can be many if 82599 */
 	u64 hw_csum_rx_error;
 	u64 hw_rx_no_dma_resources;
 	u64 non_eop_descs;
@@ -330,6 +349,8 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG_FDIR_PERFECT_CAPABLE         (u32)(1 << 27)
 #define IXGBE_FLAG_FCOE_CAPABLE                 (u32)(1 << 28)
 #define IXGBE_FLAG_FCOE_ENABLED                 (u32)(1 << 29)
+#define IXGBE_FLAG_SRIOV_CAPABLE                (u32)(1 << 30)
+#define IXGBE_FLAG_SRIOV_ENABLED                (u32)(1 << 31)
 
 	u32 flags2;
 #define IXGBE_FLAG2_RSC_CAPABLE                 (u32)(1)
@@ -379,6 +400,11 @@ struct ixgbe_adapter {
 	u64 rsc_total_flush;
 	u32 wol;
 	u16 eeprom_version;
+
+	/* SR-IOV */
+	DECLARE_BITMAP(active_vfs, IXGBE_MAX_VF_FUNCTIONS);
+	unsigned int num_vfs;
+	struct vf_data_storage *vfinfo;
 };
 
 enum ixbge_state_t {
@@ -440,6 +466,7 @@ extern s32 ixgbe_atr_set_flex_byte_82599(struct ixgbe_atr_input *input,
                                          u16 flex_byte);
 extern s32 ixgbe_atr_set_l4type_82599(struct ixgbe_atr_input *input,
                                       u8 l4type);
+extern void ixgbe_set_rx_mode(struct net_device *netdev);
 #ifdef IXGBE_FCOE
 extern void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter);
 extern int ixgbe_fso(struct ixgbe_adapter *adapter,
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index bd64387..22152c6 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -2409,7 +2409,7 @@ static u8 *ixgbe_addr_list_itr(struct ixgbe_hw *hw, u8 **mc_addr_ptr, u32 *vmdq)
  * responsible for configuring the hardware for proper unicast, multicast and
  * promiscuous mode.
  **/
-static void ixgbe_set_rx_mode(struct net_device *netdev)
+void ixgbe_set_rx_mode(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h
index 84650c6..ec8ad18 100644
--- a/drivers/net/ixgbe/ixgbe_type.h
+++ b/drivers/net/ixgbe/ixgbe_type.h
@@ -277,6 +277,7 @@
 #define IXGBE_DTXCTL    0x07E00
 
 #define IXGBE_DMATXCTL  0x04A80
+#define IXGBE_PFDTXGSWC     0x08220
 #define IXGBE_DTXMXSZRQ     0x08100
 #define IXGBE_DTXTCPFLGL    0x04A88
 #define IXGBE_DTXTCPFLGH    0x04A8C
@@ -287,6 +288,8 @@
 #define IXGBE_DMATXCTL_NS       0x2 /* No Snoop LSO hdr buffer */
 #define IXGBE_DMATXCTL_GDV      0x8 /* Global Double VLAN */
 #define IXGBE_DMATXCTL_VT_SHIFT 16  /* VLAN EtherType */
+
+#define IXGBE_PFDTXGSWC_VT_LBEN 0x1 /* Local L2 VT switch enable */
 #define IXGBE_DCA_TXCTRL(_i)    (0x07200 + ((_i) * 4)) /* 16 of these (0-15) */
 /* Tx DCA Control register : 128 of these (0-127) */
 #define IXGBE_DCA_TXCTRL_82599(_i)  (0x0600C + ((_i) * 0x40))
@@ -497,6 +500,7 @@
 /* DCB registers */
 #define IXGBE_RTRPCS      0x02430
 #define IXGBE_RTTDCS      0x04900
+#define IXGBE_RTTDCS_ARBDIS     0x00000040 /* DCB arbiter disable */
 #define IXGBE_RTTPCS      0x0CD00
 #define IXGBE_RTRUP2TC    0x03020
 #define IXGBE_RTTUP2TC    0x0C800
@@ -730,6 +734,13 @@
 #define IXGBE_GCR_CMPL_TMOUT_RESEND     0x00010000
 #define IXGBE_GCR_CAP_VER2              0x00040000
 
+#define IXGBE_GCR_EXT_MSIX_EN           0x80000000
+#define IXGBE_GCR_EXT_VT_MODE_16        0x00000001
+#define IXGBE_GCR_EXT_VT_MODE_32        0x00000002
+#define IXGBE_GCR_EXT_VT_MODE_64        0x00000003
+#define IXGBE_GCR_EXT_SRIOV             (IXGBE_GCR_EXT_MSIX_EN | \
+                                         IXGBE_GCR_EXT_VT_MODE_64)
+
 /* Time Sync Registers */
 #define IXGBE_TSYNCRXCTL 0x05188 /* Rx Time Sync Control register - RW */
 #define IXGBE_TSYNCTXCTL 0x08C00 /* Tx Time Sync Control register - RW */
@@ -1065,6 +1076,8 @@
 /* VFRE bitmask */
 #define IXGBE_VFRE_ENABLE_ALL   0xFFFFFFFF
 
+#define IXGBE_VF_INIT_TIMEOUT   200 /* Number of retries to clear RSTI */
+
 /* RDHMPN and TDHMPN bitmasks */
 #define IXGBE_RDHMPN_RDICADDR       0x007FF800
 #define IXGBE_RDHMPN_RDICRDREQ      0x00800000
@@ -1295,6 +1308,7 @@
 /* VLAN pool filtering masks */
 #define IXGBE_VLVF_VIEN         0x80000000  /* filter is valid */
 #define IXGBE_VLVF_ENTRIES      64
+#define IXGBE_VLVF_VLANID_MASK  0x00000FFF
 
 #define IXGBE_ETHERNET_IEEE_VLAN_TYPE 0x8100  /* 802.1q protocol */
 
@@ -1843,6 +1857,12 @@
 #define IXGBE_RX_DESC_SPECIAL_PRI_SHIFT  0x000D /* Priority in upper 3 of 16 */
 #define IXGBE_TX_DESC_SPECIAL_PRI_SHIFT  IXGBE_RX_DESC_SPECIAL_PRI_SHIFT
 
+/* SR-IOV specific macros */
+#define IXGBE_MBVFICR_INDEX(vf_number)   (vf_number >> 4)
+#define IXGBE_MBVFICR(_i)                (0x00710 + (_i * 4))
+#define IXGBE_VFLRE(_i)                  (((_i & 1) ? 0x001C0 : 0x00600))
+#define IXGBE_VFLREC(_i)                 (0x00700 + (_i * 4))
+
 /* Little Endian defines */
 #ifndef __le32
 #define __le32  u32
@@ -2463,6 +2483,37 @@ struct ixgbe_phy_info {
 	bool                            multispeed_fiber;
 };
 
+#include "ixgbe_mbx.h"
+
+struct ixgbe_mbx_operations {
+	s32 (*init_params)(struct ixgbe_hw *hw);
+	s32 (*read)(struct ixgbe_hw *, u32 *, u16,  u16);
+	s32 (*write)(struct ixgbe_hw *, u32 *, u16, u16);
+	s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16,  u16);
+	s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16, u16);
+	s32 (*check_for_msg)(struct ixgbe_hw *, u16);
+	s32 (*check_for_ack)(struct ixgbe_hw *, u16);
+	s32 (*check_for_rst)(struct ixgbe_hw *, u16);
+};
+
+struct ixgbe_mbx_stats {
+	u32 msgs_tx;
+	u32 msgs_rx;
+
+	u32 acks;
+	u32 reqs;
+	u32 rsts;
+};
+
+struct ixgbe_mbx_info {
+	struct ixgbe_mbx_operations ops;
+	struct ixgbe_mbx_stats stats;
+	u32 timeout;
+	u32 usec_delay;
+	u32 v2p_mailbox;
+	u16 size;
+};
+
 struct ixgbe_hw {
 	u8 __iomem			*hw_addr;
 	void				*back;
@@ -2472,6 +2523,7 @@ struct ixgbe_hw {
 	struct ixgbe_phy_info		phy;
 	struct ixgbe_eeprom_info	eeprom;
 	struct ixgbe_bus_info		bus;
+	struct ixgbe_mbx_info		mbx;
 	u16				device_id;
 	u16				vendor_id;
 	u16				subsystem_device_id;
@@ -2486,6 +2538,7 @@ struct ixgbe_info {
 	struct ixgbe_mac_operations	*mac_ops;
 	struct ixgbe_eeprom_operations	*eeprom_ops;
 	struct ixgbe_phy_operations	*phy_ops;
+	struct ixgbe_mbx_operations	*mbx_ops;
 };
 
 

[RFC PATCH v2 09/12] ixgbe: Add SR-IOV specific features

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

This module and header file add functions to support SR-IOV features of the
82599 10Gbe controller.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe_sriov.c |  336 +++++++++++++++++++++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_sriov.h |   45 +++++
 2 files changed, 381 insertions(+), 0 deletions(-)
 create mode 100644 drivers/net/ixgbe/ixgbe_sriov.c
 create mode 100644 drivers/net/ixgbe/ixgbe_sriov.h

diff --git a/drivers/net/ixgbe/ixgbe_sriov.c b/drivers/net/ixgbe/ixgbe_sriov.c
new file mode 100644
index 0000000..74bca74
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_sriov.c
@@ -0,0 +1,336 @@
+/*******************************************************************************
+
+  Intel 10 Gigabit PCI Express Linux driver
+  Copyright(c) 1999 - 2009 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/ipv6.h>
+#ifdef NETIF_F_HW_VLAN_TX
+#include <linux/if_vlan.h>
+#endif
+
+#include "ixgbe.h"
+
+#include "ixgbe_sriov.h"
+
+int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
+			    int entries, u16 *hash_list, u32 vf)
+{
+	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
+	int i;
+
+	/* only so many hash values supported */
+	entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES);
+
+	/*
+	 * salt away the number of multi cast addresses assigned
+	 * to this VF for later use to restore when the PF multi cast
+	 * list changes
+	 */
+	vfinfo->num_vf_mc_hashes = entries;
+
+	/*
+	 * VFs are limited to using the MTA hash table for their multicast
+	 * addresses
+	 */
+	for (i = 0; i < entries; i++) {
+		vfinfo->vf_mc_hashes[i] = hash_list[i];;
+	}
+
+	/* Flush and reset the mta with the new values */
+	ixgbe_set_rx_mode(adapter->netdev);
+
+	return 0;
+}
+
+void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct vf_data_storage *vfinfo;
+	int i, j;
+	u32 vector_bit;
+	u32 vector_reg;
+	u32 mta_reg;
+
+	for (i = 0; i < adapter->num_vfs; i++) {
+		vfinfo = &adapter->vfinfo[i];
+		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
+			hw->addr_ctrl.mta_in_use++;
+			vector_reg = (vfinfo->vf_mc_hashes[j] >> 5) & 0x7F;
+			vector_bit = vfinfo->vf_mc_hashes[j] & 0x1F;
+			mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
+			mta_reg |= (1 << vector_bit);
+			IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
+		}
+	}
+}
+
+int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf)
+{
+	u32 ctrl;
+
+	/* Check if global VLAN already set, if not set it */
+	ctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_VLNCTRL);
+	if (!(ctrl & IXGBE_VLNCTRL_VFE)) {
+		/* enable VLAN tag insert/strip */
+		ctrl |= IXGBE_VLNCTRL_VFE;
+		ctrl &= ~IXGBE_VLNCTRL_CFIEN;
+		IXGBE_WRITE_REG(&adapter->hw, IXGBE_VLNCTRL, ctrl);
+	}
+
+	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
+}
+
+
+void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf)
+{
+	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
+	vmolr |= (IXGBE_VMOLR_AUPE |
+		  IXGBE_VMOLR_ROMPE |
+		  IXGBE_VMOLR_ROPE |
+		  IXGBE_VMOLR_BAM);
+	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
+}
+
+inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	/* reset offloads to defaults */
+	ixgbe_set_vmolr(hw, vf);
+
+
+	/* reset multicast table array for vf */
+	adapter->vfinfo[vf].num_vf_mc_hashes = 0;
+
+	/* Flush and reset the mta with the new values */
+	ixgbe_set_rx_mode(adapter->netdev);
+
+	if (adapter->vfinfo[vf].rar > 0) {
+		adapter->hw.mac.ops.clear_rar(&adapter->hw,
+		                              adapter->vfinfo[vf].rar);
+		adapter->vfinfo[vf].rar = -1;
+	}
+}
+
+int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
+                          int vf, unsigned char *mac_addr)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	adapter->vfinfo[vf].rar = hw->mac.ops.set_rar(hw, vf + 1, mac_addr,
+	                                              vf, IXGBE_RAH_AV);
+	if (adapter->vfinfo[vf].rar < 0) {
+		DPRINTK(DRV, ERR, "Could not set MAC Filter for VF %d\n", vf);
+		return -1;
+	}
+
+	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6);
+
+	return 0;
+}
+
+int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
+{
+	unsigned char vf_mac_addr[6];
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	unsigned int vfn = (event_mask & 0x3f);
+
+	bool enable = ((event_mask & 0x10000000U) != 0);
+
+	if (enable) {
+		random_ether_addr(vf_mac_addr);
+		DPRINTK(PROBE, INFO, "IOV: VF %d is enabled "
+		       "mac %02X:%02X:%02X:%02X:%02X:%02X\n",
+		       vfn,
+		       vf_mac_addr[0], vf_mac_addr[1], vf_mac_addr[2],
+		       vf_mac_addr[3], vf_mac_addr[4], vf_mac_addr[5]);
+		/*
+		 * Store away the VF "permananet" MAC address, it will ask
+		 * for it later.
+		 */
+		memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6);
+	}
+
+	return 0;
+}
+
+inline void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 reg;
+	u32 reg_offset, vf_shift;
+
+	vf_shift = vf % 32;
+	reg_offset = vf / 32;
+
+	/* enable transmit and receive for vf */
+	reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset));
+	reg |= (reg | (1 << vf_shift));
+	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg);
+
+	reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset));
+	reg |= (reg | (1 << vf_shift));
+	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg);
+
+	ixgbe_vf_reset_event(adapter, vf);
+}
+
+static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
+{
+	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
+	u32 msgbuf[mbx_size];
+	struct ixgbe_hw *hw = &adapter->hw;
+	s32 retval;
+	int entries;
+	u16 *hash_list;
+	int add, vid;
+
+	retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf);
+
+	if (retval)
+		printk(KERN_ERR "Error receiving message from VF\n");
+
+	/* this is a message we already processed, do nothing */
+	if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK))
+		return retval;
+
+	/*
+	 * until the vf completes a virtual function reset it should not be
+	 * allowed to start any configuration.
+	 */
+
+	if (msgbuf[0] == IXGBE_VF_RESET) {
+		unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses;
+		u8 *addr = (u8 *)(&msgbuf[1]);
+		DPRINTK(PROBE, INFO, "VF Reset msg received from vf %d\n", vf);
+		adapter->vfinfo[vf].clear_to_send = false;
+		ixgbe_vf_reset_msg(adapter, vf);
+		adapter->vfinfo[vf].clear_to_send = true;
+
+		/* reply to reset with ack and vf mac address */
+		msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
+		memcpy(addr, vf_mac, IXGBE_ETH_LENGTH_OF_ADDRESS);
+		/*
+		 * Piggyback the multicast filter type so VF can compute the
+		 * correct vectors
+		 */
+		msgbuf[3] = hw->mac.mc_filter_type;
+		ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf);
+
+		return retval;
+	}
+
+	if (!adapter->vfinfo[vf].clear_to_send) {
+		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
+		ixgbe_write_mbx(hw, msgbuf, 1, vf);
+		return retval;
+	}
+
+	switch ((msgbuf[0] & 0xFFFF)) {
+	case IXGBE_VF_SET_MAC_ADDR:
+		{
+			u8 *new_mac = ((u8 *)(&msgbuf[1]));
+			if (is_valid_ether_addr(new_mac))
+				ixgbe_set_vf_mac(adapter, vf, new_mac);
+			else
+				retval = -1;
+		}
+		break;
+	case IXGBE_VF_SET_MULTICAST:
+		entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
+		          >> IXGBE_VT_MSGINFO_SHIFT;
+		hash_list = (u16 *)&msgbuf[1];
+		retval = ixgbe_set_vf_multicasts(adapter, entries,
+		                                 hash_list, vf);
+		break;
+	case IXGBE_VF_SET_LPE:
+		WARN_ON((msgbuf[0] & 0xFFFF) == IXGBE_VF_SET_LPE);
+		break;
+	case IXGBE_VF_SET_VLAN:
+		add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
+		      >> IXGBE_VT_MSGINFO_SHIFT;
+		vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);
+		retval = ixgbe_set_vf_vlan(adapter, add, vid, vf);
+		break;
+	default:
+		DPRINTK(DRV, ERR, "Unhandled Msg %8.8x\n", msgbuf[0]);
+		retval = IXGBE_ERR_MBX;
+		break;
+	}
+
+	/* notify the VF of the results of what it sent us */
+	if (retval)
+		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
+	else
+		msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK;
+
+	msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS;
+
+	ixgbe_write_mbx(hw, msgbuf, 1, vf);
+
+	return retval;
+}
+
+static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 msg = IXGBE_VT_MSGTYPE_NACK;
+
+	/* if device isn't clear to send it shouldn't be reading either */
+	if (!adapter->vfinfo[vf].clear_to_send)
+		ixgbe_write_mbx(hw, &msg, 1, vf);
+}
+
+void ixgbe_msg_task(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 vf;
+
+	for (vf = 0; vf < adapter->num_vfs; vf++) {
+		/* process any reset requests */
+		if (!ixgbe_check_for_rst(hw, vf))
+			ixgbe_vf_reset_event(adapter, vf);
+
+		/* process any messages pending */
+		if (!ixgbe_check_for_msg(hw, vf))
+			ixgbe_rcv_msg_from_vf(adapter, vf);
+
+		/* process any acks */
+		if (!ixgbe_check_for_ack(hw, vf))
+			ixgbe_rcv_ack_from_vf(adapter, vf);
+	}
+}
+
diff --git a/drivers/net/ixgbe/ixgbe_sriov.h b/drivers/net/ixgbe/ixgbe_sriov.h
new file mode 100644
index 0000000..664b237
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_sriov.h
@@ -0,0 +1,45 @@
+/*******************************************************************************
+
+  Intel 10 Gigabit PCI Express Linux driver
+  Copyright(c) 1999 - 2009 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
+
+*******************************************************************************/
+
+#ifndef _IXGBE_SRIOV_H_
+#define _IXGBE_SRIOV_H_
+
+int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
+                            int entries, u16 *hash_list, u32 vf);
+void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter);
+int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf);
+void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf);
+void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf);
+void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf);
+void ixgbe_msg_task(struct ixgbe_adapter *adapter);
+int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
+                     int vf, unsigned char *mac_addr);
+int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask);
+void ixgbe_dump_registers(struct ixgbe_adapter *adapter);
+
+#endif /* _IXGBE_SRIOV_H_ */
+

[RFC PATCH v2 10/12] ixgbe: Add SR-IOV specific modules to driver Makefile

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

Add the mailbox and SR-IOV feature modules to the ixgbe driver Makefile.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/Makefile |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ixgbe/Makefile b/drivers/net/ixgbe/Makefile
index 21b41f4..1dd867d 100644
--- a/drivers/net/ixgbe/Makefile
+++ b/drivers/net/ixgbe/Makefile
@@ -33,7 +33,8 @@
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
 ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
-              ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o
+              ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
+              ixgbe_mbx.o
 
 ixgbe-$(CONFIG_IXGBE_DCB) +=  ixgbe_dcb.o ixgbe_dcb_82598.o \
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o

[RFC PATCH v2 11/12] ixgbe: Add SR-IOV feature enablement code

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

Adds code to the core 82599 module to support SR-IOV features of the 82599
network controller

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe_82599.c |   10 ++++++----
 1 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_82599.c b/drivers/net/ixgbe/ixgbe_82599.c
index 5383405..8d555a9 100644
--- a/drivers/net/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ixgbe/ixgbe_82599.c
@@ -31,6 +31,7 @@
 
 #include "ixgbe.h"
 #include "ixgbe_phy.h"
+#include "ixgbe_mbx.h"
 
 #define IXGBE_82599_MAX_TX_QUEUES 128
 #define IXGBE_82599_MAX_RX_QUEUES 128
@@ -951,8 +952,6 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw)
 
 	msleep(50);
 
-
-
 	/*
 	 * Store the original AUTOC/AUTOC2 values if they have not been
 	 * stored off yet.  Otherwise restore the stored original
@@ -1098,6 +1097,7 @@ static s32 ixgbe_set_vfta_82599(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 	u32 bitindex;
 	u32 bits;
 	u32 first_empty_slot;
+	u32 vt_ctl;
 
 	if (vlan > 4095)
 		return IXGBE_ERR_PARAM;
@@ -1124,14 +1124,15 @@ static s32 ixgbe_set_vfta_82599(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 
 
 	/* Part 2
-	 * If the vind is set
+	 * If VT mode is set
 	 *   Either vlan_on
 	 *     make sure the vlan is in VLVF
 	 *     set the vind bit in the matching VLVFB
 	 *   Or !vlan_on
 	 *     clear the pool bit and possibly the vind
 	 */
-	if (vind) {
+	vt_ctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
+	if (vt_ctl & IXGBE_VT_CTL_VT_ENABLE) {
 		/* find the vlanid or the first empty slot */
 		first_empty_slot = 0;
 
@@ -2655,4 +2656,5 @@ struct ixgbe_info ixgbe_82599_info = {
 	.mac_ops                = &mac_ops_82599,
 	.eeprom_ops             = &eeprom_ops_82599,
 	.phy_ops                = &phy_ops_82599,
+	.mbx_ops                = &mbx_ops_82599,
 };

[RFC PATCH v2 12/12] ixgbe: Add SR-IOV features to main module

[Jeff Kirsher]

From: Greg Rose <gregory.v.rose@intel.com>

Adds SR-IOV features supported by the 82599 controller to the main driver
module.  If the CONFIG_PCI_IOV kernel option is selected then the SR-IOV
features are enabled.  Use the max_vfs module option to allocate up to 63
virtual functions per physical port.

Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe_main.c |  278 +++++++++++++++++++++++++++++++++++++++-
 1 files changed, 268 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 22152c6..876064c 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -45,6 +45,7 @@
 #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[] =
@@ -124,6 +125,13 @@ static struct notifier_block dca_notifier = {
 };
 #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");
@@ -131,6 +139,41 @@ 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;
+}
+
 static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter)
 {
 	u32 ctrl_ext;
@@ -1020,7 +1063,12 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
 
 	/* set up to autoclear timer, and the vectors */
 	mask = IXGBE_EIMS_ENABLE_MASK;
-	mask &= ~(IXGBE_EIMS_OTHER | IXGBE_EIMS_LSC);
+	if (adapter->num_vfs)
+		mask &= ~(IXGBE_EIMS_OTHER |
+			  IXGBE_EIMS_MAILBOX |
+			  IXGBE_EIMS_LSC);
+	else
+		mask &= ~(IXGBE_EIMS_OTHER | IXGBE_EIMS_LSC);
 	IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask);
 }
 
@@ -1249,6 +1297,9 @@ static irqreturn_t ixgbe_msix_lsc(int irq, void *data)
 	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);
 
@@ -1763,6 +1814,8 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter)
 		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)
@@ -1771,6 +1824,11 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter)
 	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);
+	}
 }
 
 /**
@@ -1900,6 +1958,8 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
 		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) {
@@ -1984,18 +2044,32 @@ static void ixgbe_configure_tx(struct ixgbe_adapter *adapter)
 
 	if (hw->mac.type == ixgbe_mac_82599EB) {
 		u32 rttdcs;
+		u32 mask;
 
 		/* disable the arbiter while setting MTQC */
 		rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS);
 		rttdcs |= IXGBE_RTTDCS_ARBDIS;
 		IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs);
 
-		/* We enable 8 traffic classes, DCB only */
-		if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
-			IXGBE_WRITE_REG(hw, IXGBE_MTQC, (IXGBE_MTQC_RT_ENA |
-			                IXGBE_MTQC_8TC_8TQ));
-		else
+		/* set transmit pool layout */
+		mask = (IXGBE_FLAG_SRIOV_ENABLED | IXGBE_FLAG_DCB_ENABLED);
+		switch (adapter->flags & mask) {
+
+		case (IXGBE_FLAG_SRIOV_ENABLED):
+			IXGBE_WRITE_REG(hw, IXGBE_MTQC,
+					(IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF));
+			break;
+
+		case (IXGBE_FLAG_DCB_ENABLED):
+			/* We enable 8 traffic classes, DCB only */
+			IXGBE_WRITE_REG(hw, IXGBE_MTQC,
+				      (IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ));
+			break;
+
+		default:
 			IXGBE_WRITE_REG(hw, IXGBE_MTQC, IXGBE_MTQC_64Q_1PB);
+			break;
+		}
 
 		/* re-eable the arbiter */
 		rttdcs &= ~IXGBE_RTTDCS_ARBDIS;
@@ -2054,12 +2128,16 @@ static u32 ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
 #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;
@@ -2140,7 +2218,9 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 	int rx_buf_len;
 
 	/* Decide whether to use packet split mode or not */
-	adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
+	/* Do not use packet split if we're in SR-IOV Mode */
+	if (!adapter->num_vfs)
+		adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED;
 
 	/* Set the RX buffer length according to the mode */
 	if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
@@ -2152,7 +2232,9 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 			              IXGBE_PSRTYPE_IPV4HDR |
 			              IXGBE_PSRTYPE_IPV6HDR |
 			              IXGBE_PSRTYPE_L2HDR;
-			IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(0), psrtype);
+			IXGBE_WRITE_REG(hw,
+					IXGBE_PSRTYPE(adapter->num_vfs),
+					psrtype);
 		}
 	} else {
 		if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
@@ -2238,6 +2320,30 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 		IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
 	}
 
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+		u32 vt_reg_bits;
+		u32 reg_offset, vf_shift;
+		u32 vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
+		vt_reg_bits = IXGBE_VMD_CTL_VMDQ_EN
+			| IXGBE_VT_CTL_REPLEN;
+		vt_reg_bits |= (adapter->num_vfs <<
+				IXGBE_VT_CTL_POOL_SHIFT);
+		IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl | vt_reg_bits);
+		IXGBE_WRITE_REG(hw, IXGBE_MRQC, 0);
+
+		vf_shift = adapter->num_vfs % 32;
+		reg_offset = adapter->num_vfs / 32;
+		IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0);
+		IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
+		IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0);
+		IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0);
+		/* Enable only the PF's pool for Tx/Rx */
+		IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (1 << vf_shift));
+		IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (1 << vf_shift));
+		IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN);
+		ixgbe_set_vmolr(hw, adapter->num_vfs);
+	}
+
 	/* Program MRQC for the distribution of queues */
 	mrqc = ixgbe_setup_mrqc(adapter);
 
@@ -2269,6 +2375,20 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 	}
 	IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc);
 
+	if (adapter->num_vfs) {
+		u32 reg;
+
+		/* Map PF MAC address in RAR Entry 0 to first pool
+		 * following VFs */
+		hw->mac.ops.set_vmdq(hw, 0, adapter->num_vfs);
+
+		/* Set up VF register offsets for selected VT Mode, i.e.
+		 * 64 VFs for SR-IOV */
+		reg = IXGBE_READ_REG(hw, IXGBE_GCR_EXT);
+		reg |= IXGBE_GCR_EXT_SRIOV;
+		IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, reg);
+	}
+
 	rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM);
 
 	if (adapter->flags & IXGBE_FLAG_RSS_ENABLED ||
@@ -2449,6 +2569,8 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 		addr_list = netdev->mc_list->dmi_addr;
 	hw->mac.ops.update_mc_addr_list(hw, addr_list, addr_count,
 	                                ixgbe_addr_list_itr);
+	if (adapter->num_vfs)
+		ixgbe_restore_vf_multicasts(adapter);
 }
 
 static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter)
@@ -2709,6 +2831,10 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
 			/* MSI only */
 			gpie = 0;
 		}
+		if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+			gpie &= ~IXGBE_GPIE_VTMODE_MASK;
+			gpie |= IXGBE_GPIE_VTMODE_64;
+		}
 		/* XXX: to interrupt immediately for EICS writes, enable this */
 		/* gpie |= IXGBE_GPIE_EIMEN; */
 		IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
@@ -2783,6 +2909,18 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
 		txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
 		txdctl |= IXGBE_TXDCTL_ENABLE;
 		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(j), txdctl);
+		if (hw->mac.type == ixgbe_mac_82599EB) {
+			int wait_loop = 10;
+			/* poll for Tx Enable ready */
+			do {
+				msleep(1);
+				txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
+			} while (--wait_loop &&
+			         !(txdctl & IXGBE_TXDCTL_ENABLE));
+			if (!wait_loop)
+				DPRINTK(DRV, ERR, "Could not enable "
+				        "Tx Queue %d\n", j);
+		}
 	}
 
 	for (i = 0; i < num_rx_rings; i++) {
@@ -2918,7 +3056,8 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 	}
 
 	/* reprogram the RAR[0] in case user changed it. */
-	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV);
+	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs,
+			    IXGBE_RAH_AV);
 }
 
 /**
@@ -3286,6 +3425,19 @@ static inline bool ixgbe_set_fcoe_queues(struct ixgbe_adapter *adapter)
 }
 
 #endif /* IXGBE_FCOE */
+/**
+ * ixgbe_set_sriov_queues: Allocate queues for IOV use
+ * @adapter: board private structure to initialize
+ *
+ * IOV doesn't actually use anything, so just NAK the
+ * request for now and let the other queue routines
+ * figure out what to do.
+ */
+static inline bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter)
+{
+	return false;
+}
+
 /*
  * ixgbe_set_num_queues: Allocate queues for device, feature dependant
  * @adapter: board private structure to initialize
@@ -3299,6 +3451,15 @@ static inline bool ixgbe_set_fcoe_queues(struct ixgbe_adapter *adapter)
  **/
 static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
 {
+	/* Start with base case */
+	adapter->num_rx_queues = 1;
+	adapter->num_tx_queues = 1;
+	adapter->num_rx_pools = adapter->num_rx_queues;
+	adapter->num_rx_queues_per_pool = 1;
+
+	if (ixgbe_set_sriov_queues(adapter))
+		return;
+
 #ifdef IXGBE_FCOE
 	if (ixgbe_set_fcoe_queues(adapter))
 		goto done;
@@ -3570,6 +3731,24 @@ static inline bool ixgbe_cache_ring_fcoe(struct ixgbe_adapter *adapter)
 
 #endif /* IXGBE_FCOE */
 /**
+ * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov
+ * @adapter: board private structure to initialize
+ *
+ * SR-IOV doesn't use any descriptor rings but changes the default if
+ * no other mapping is used.
+ *
+ */
+static inline bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter)
+{
+	adapter->rx_ring[0].reg_idx = adapter->num_vfs * 2;
+	adapter->tx_ring[0].reg_idx = adapter->num_vfs * 2;
+	if (adapter->num_vfs)
+		return true;
+	else
+		return false;
+}
+
+/**
  * ixgbe_cache_ring_register - Descriptor ring to register mapping
  * @adapter: board private structure to initialize
  *
@@ -3586,6 +3765,9 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
 	adapter->rx_ring[0].reg_idx = 0;
 	adapter->tx_ring[0].reg_idx = 0;
 
+	if (ixgbe_cache_ring_sriov(adapter))
+		return;
+
 #ifdef IXGBE_FCOE
 	if (ixgbe_cache_ring_fcoe(adapter))
 		return;
@@ -3695,6 +3877,9 @@ static int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 	adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
 	adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
 	adapter->atr_sample_rate = 0;
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+		ixgbe_disable_sriov(adapter);
+
 	ixgbe_set_num_queues(adapter);
 
 	err = pci_enable_msi(adapter->pdev);
@@ -5474,7 +5659,8 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p)
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
 
-	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV);
+	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs,
+			    IXGBE_RAH_AV);
 
 	return 0;
 }
@@ -5607,6 +5793,61 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 #endif /* IXGBE_FCOE */
 };
 
+static void __devinit ixgbe_probe_vf(struct ixgbe_adapter *adapter,
+			   const struct ixgbe_info *ii)
+{
+#ifdef CONFIG_PCI_IOV
+	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	if (hw->mac.type != ixgbe_mac_82599EB || !max_vfs)
+		return;
+
+	/* The 82599 supports up to 64 VFs per physical function
+	 * but this implementation limits allocation to 63 so that
+	 * basic networking resources are still available to the
+	 * physical function
+	 */
+	adapter->num_vfs = (max_vfs > 63) ? 63 : max_vfs;
+	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
+	err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+	if (err) {
+		DPRINTK(PROBE, ERR,
+			"Failed to enable PCI sriov: %d\n", err);
+		goto err_novfs;
+	}
+	/* If call to enable VFs succeeded then allocate memory
+	 * for per VF control structures.
+	 */
+	adapter->vfinfo =
+		kcalloc(adapter->num_vfs,
+			sizeof(struct vf_data_storage), GFP_KERNEL);
+	if (adapter->vfinfo) {
+		/* Now that we're sure SR-IOV is enabled
+		 * and memory allocated set up the mailbox parameters
+		 */
+		ixgbe_init_mbx_params_pf(hw);
+		memcpy(&hw->mbx.ops, ii->mbx_ops,
+		       sizeof(hw->mbx.ops));
+
+		/* Disable RSC when in SR-IOV mode */
+		adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
+				     IXGBE_FLAG2_RSC_ENABLED);
+		return;
+	}
+
+	/* Oh oh */
+	DPRINTK(PROBE, ERR,
+		"Unable to allocate memory for VF "
+		"Data Storage - SRIOV disabled\n");
+	pci_disable_sriov(adapter->pdev);
+
+err_novfs:
+	adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
+	adapter->num_vfs = 0;
+#endif /* CONFIG_PCI_IOV */
+}
+
 /**
  * ixgbe_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -5781,6 +6022,8 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
 		goto err_sw_init;
 	}
 
+	ixgbe_probe_vf(adapter, ii);
+
 	netdev->features = NETIF_F_SG |
 	                   NETIF_F_IP_CSUM |
 	                   NETIF_F_HW_VLAN_TX |
@@ -5801,6 +6044,9 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
 	netdev->vlan_features |= NETIF_F_IPV6_CSUM;
 	netdev->vlan_features |= NETIF_F_SG;
 
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+		adapter->flags &= ~(IXGBE_FLAG_RSS_ENABLED |
+				    IXGBE_FLAG_DCB_ENABLED);
 	if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
 		adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED;
 
@@ -5927,6 +6173,13 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
 		ixgbe_setup_dca(adapter);
 	}
 #endif
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) {
+		DPRINTK(PROBE, INFO, "IOV is enabled with %d VFs\n",
+			adapter->num_vfs);
+		for (i = 0; i < adapter->num_vfs; i++)
+			ixgbe_vf_configuration(pdev, (i | 0x10000000));
+	}
+
 	/* add san mac addr to netdev */
 	ixgbe_add_sanmac_netdev(netdev);
 
@@ -5939,6 +6192,8 @@ err_register:
 	ixgbe_clear_interrupt_scheme(adapter);
 err_sw_init:
 err_eeprom:
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+		ixgbe_disable_sriov(adapter);
 	clear_bit(__IXGBE_SFP_MODULE_NOT_FOUND, &adapter->state);
 	del_timer_sync(&adapter->sfp_timer);
 	cancel_work_sync(&adapter->sfp_task);
@@ -6007,6 +6262,9 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev)
 	if (netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdev(netdev);
 
+	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
+		ixgbe_disable_sriov(adapter);
+
 	ixgbe_clear_interrupt_scheme(adapter);
 
 	ixgbe_release_hw_control(adapter);

Re: [RFC PATCH v2 01/12] ixgbevf: Macros, data structures, useful defines and registers

[Ben Hutchings]

On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
> From: Greg Rose <gregory.v.rose@intel.com>
> 
> These two headers define the commonly used macros, data structures,
> register bits and register offsets used by the ixgbevf driver on the
> 82599 virtual function device
> 
[...]
> diff --git a/drivers/net/ixgbevf/defines.h b/drivers/net/ixgbevf/defines.h
> new file mode 100644
> index 0000000..b111771
> --- /dev/null
> +++ b/drivers/net/ixgbevf/defines.h
[...]
> +/* Check whether address is multicast.  This is little-endian specific check.*/
> +#define IXGBE_IS_MULTICAST(Address) \
> +	(bool)(((u8 *)(Address))[0] & ((u8)0x01))
> +
> +/* Check whether an address is broadcast. */
> +#define IXGBE_IS_BROADCAST(Address)              \
> +	((((u8 *)(Address))[0] == ((u8)0xFF)) && \
> +	 (((u8 *)(Address))[1] == ((u8)0xFF)))
[...]

Why not use is_multicast_ether_addr() and  is_broadcast_ether_addr()?

Ben.

-- 
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

RE: [RFC PATCH v2 01/12] ixgbevf: Macros, data structures, useful defines and registers

[Rose, Gregory V]

>-----Original Message-----
>From: Ben Hutchings [mailto:bhutchings@solarflare.com]
>Sent: Monday, December 21, 2009 10:38 AM
>To: Kirsher, Jeffrey T
>Cc: netdev@vger.kernel.org; gospo@redhat.com; Rose, Gregory V
>Subject: Re: [RFC PATCH v2 01/12] ixgbevf: Macros, data structures,
>useful defines and registers
>
>On Fri, 2009-12-18 at 14:51 -0800, Jeff Kirsher wrote:
>> From: Greg Rose <gregory.v.rose@intel.com>
>>
>> These two headers define the commonly used macros, data structures,
>> register bits and register offsets used by the ixgbevf driver on the
>> 82599 virtual function device
>>
>[...]
>> diff --git a/drivers/net/ixgbevf/defines.h
>b/drivers/net/ixgbevf/defines.h
>> new file mode 100644
>> index 0000000..b111771
>> --- /dev/null
>> +++ b/drivers/net/ixgbevf/defines.h
>[...]
>> +/* Check whether address is multicast.  This is little-endian
>specific check.*/
>> +#define IXGBE_IS_MULTICAST(Address) \
>> +	(bool)(((u8 *)(Address))[0] & ((u8)0x01))
>> +
>> +/* Check whether an address is broadcast. */
>> +#define IXGBE_IS_BROADCAST(Address)              \
>> +	((((u8 *)(Address))[0] == ((u8)0xFF)) && \
>> +	 (((u8 *)(Address))[1] == ((u8)0xFF)))
>[...]
>
>Why not use is_multicast_ether_addr() and  is_broadcast_ether_addr()?

This driver was derived from the ixgbe driver and I just copied and pasted those macros from drivers/net/ixgbe/ixgbe_type.h.  We (Intel/LAD) should probably post a patch to fix up both of these at some point.  We'll discuss this amongst ourselves and a patch should be forthcoming, though it may be outside the context of this series of patches.

- Greg