diff options
| -rw-r--r-- | MAINTAINERS | 7 | ||||
| -rw-r--r-- | drivers/net/Kconfig | 8 | ||||
| -rw-r--r-- | drivers/net/Makefile | 1 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/Makefile | 35 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/upt1_defs.h | 96 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_defs.h | 535 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_drv.c | 2556 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_ethtool.c | 566 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_int.h | 389 |
9 files changed, 4193 insertions, 0 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index c34b728bbf0..70bc7ded944 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5612,6 +5612,13 @@ S: Maintained F: drivers/vlynq/vlynq.c F: include/linux/vlynq.h +VMWARE VMXNET3 ETHERNET DRIVER +M: Shreyas Bhatewara <sbhatewara@vmware.com> +M: VMware, Inc. <pv-drivers@vmware.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/vmxnet3/ + VOLTAGE AND CURRENT REGULATOR FRAMEWORK M: Liam Girdwood <lrg@slimlogic.co.uk> M: Mark Brown <broonie@opensource.wolfsonmicro.com> diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 712776089b4..9789de23413 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -3230,4 +3230,12 @@ config VIRTIO_NET This is the virtual network driver for virtio. It can be used with lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. +config VMXNET3 + tristate "VMware VMXNET3 ethernet driver" + depends on PCI && X86 + help + This driver supports VMware's vmxnet3 virtual ethernet NIC. + To compile this driver as a module, choose M here: the + module will be called vmxnet3. + endif # NETDEVICES diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 48d82e901aa..fc6c8bb92c5 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_TEHUTI) += tehuti.o obj-$(CONFIG_ENIC) += enic/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_BE2NET) += benet/ +obj-$(CONFIG_VMXNET3) += vmxnet3/ gianfar_driver-objs := gianfar.o \ gianfar_ethtool.o \ diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile new file mode 100644 index 00000000000..880f5098eac --- /dev/null +++ b/drivers/net/vmxnet3/Makefile @@ -0,0 +1,35 @@ +################################################################################ +# +# Linux driver for VMware's vmxnet3 ethernet NIC. +# +# Copyright (C) 2007-2009, VMware, Inc. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the +# Free Software Foundation; version 2 of the License and no later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or +# NON INFRINGEMENT. See the GNU General Public License for more +# details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. +# +# The full GNU General Public License is included in this distribution in +# the file called "COPYING". +# +# Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com> +# +# +################################################################################ + +# +# Makefile for the VMware vmxnet3 ethernet NIC driver +# + +obj-$(CONFIG_VMXNET3) += vmxnet3.o + +vmxnet3-objs := vmxnet3_drv.o vmxnet3_ethtool.o diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h new file mode 100644 index 00000000000..37108fb226d --- /dev/null +++ b/drivers/net/vmxnet3/upt1_defs.h @@ -0,0 +1,96 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License and no later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. 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". + * + * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com> + * + */ + +#ifndef _UPT1_DEFS_H +#define _UPT1_DEFS_H + +struct UPT1_TxStats { + u64 TSOPktsTxOK; /* TSO pkts post-segmentation */ + u64 TSOBytesTxOK; + u64 ucastPktsTxOK; + u64 ucastBytesTxOK; + u64 mcastPktsTxOK; + u64 mcastBytesTxOK; + u64 bcastPktsTxOK; + u64 bcastBytesTxOK; + u64 pktsTxError; + u64 pktsTxDiscard; +}; + +struct UPT1_RxStats { + u64 LROPktsRxOK; /* LRO pkts */ + u64 LROBytesRxOK; /* bytes from LRO pkts */ + /* the following counters are for pkts from the wire, i.e., pre-LRO */ + u64 ucastPktsRxOK; + u64 ucastBytesRxOK; + u64 mcastPktsRxOK; + u64 mcastBytesRxOK; + u64 bcastPktsRxOK; + u64 bcastBytesRxOK; + u64 pktsRxOutOfBuf; + u64 pktsRxError; +}; + +/* interrupt moderation level */ +enum { + UPT1_IML_NONE = 0, /* no interrupt moderation */ + UPT1_IML_HIGHEST = 7, /* least intr generated */ + UPT1_IML_ADAPTIVE = 8, /* adpative intr moderation */ +}; +/* values for UPT1_RSSConf.hashFunc */ +enum { + UPT1_RSS_HASH_TYPE_NONE = 0x0, + UPT1_RSS_HASH_TYPE_IPV4 = 0x01, + UPT1_RSS_HASH_TYPE_TCP_IPV4 = 0x02, + UPT1_RSS_HASH_TYPE_IPV6 = 0x04, + UPT1_RSS_HASH_TYPE_TCP_IPV6 = 0x08, +}; + +enum { + UPT1_RSS_HASH_FUNC_NONE = 0x0, + UPT1_RSS_HASH_FUNC_TOEPLITZ = 0x01, +}; + +#define UPT1_RSS_MAX_KEY_SIZE 40 +#define UPT1_RSS_MAX_IND_TABLE_SIZE 128 + +struct UPT1_RSSConf { + u16 hashType; + u16 hashFunc; + u16 hashKeySize; + u16 indTableSize; + u8 hashKey[UPT1_RSS_MAX_KEY_SIZE]; + u8 indTable[UPT1_RSS_MAX_IND_TABLE_SIZE]; +}; + +/* features */ +enum { + UPT1_F_RXCSUM = 0x0001, /* rx csum verification */ + UPT1_F_RSS = 0x0002, + UPT1_F_RXVLAN = 0x0004, /* VLAN tag stripping */ + UPT1_F_LRO = 0x0008, +}; +#endif diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h new file mode 100644 index 00000000000..dc8ee4438a4 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_defs.h @@ -0,0 +1,535 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License and no later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. 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". + * + * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com> + * + */ + +#ifndef _VMXNET3_DEFS_H_ +#define _VMXNET3_DEFS_H_ + +#include "upt1_defs.h" + +/* all registers are 32 bit wide */ +/* BAR 1 */ +enum { + VMXNET3_REG_VRRS = 0x0, /* Vmxnet3 Revision Report Selection */ + VMXNET3_REG_UVRS = 0x8, /* UPT Version Report Selection */ + VMXNET3_REG_DSAL = 0x10, /* Driver Shared Address Low */ + VMXNET3_REG_DSAH = 0x18, /* Driver Shared Address High */ + VMXNET3_REG_CMD = 0x20, /* Command */ + VMXNET3_REG_MACL = 0x28, /* MAC Address Low */ + VMXNET3_REG_MACH = 0x30, /* MAC Address High */ + VMXNET3_REG_ICR = 0x38, /* Interrupt Cause Register */ + VMXNET3_REG_ECR = 0x40 /* Event Cause Register */ +}; + +/* BAR 0 */ +enum { + VMXNET3_REG_IMR = 0x0, /* Interrupt Mask Register */ + VMXNET3_REG_TXPROD = 0x600, /* Tx Producer Index */ + VMXNET3_REG_RXPROD = 0x800, /* Rx Producer Index for ring 1 */ + VMXNET3_REG_RXPROD2 = 0xA00 /* Rx Producer Index for ring 2 */ +}; + +#define VMXNET3_PT_REG_SIZE 4096 /* BAR 0 */ +#define VMXNET3_VD_REG_SIZE 4096 /* BAR 1 */ + +#define VMXNET3_REG_ALIGN 8 /* All registers are 8-byte aligned. */ +#define VMXNET3_REG_ALIGN_MASK 0x7 + +/* I/O Mapped access to registers */ +#define VMXNET3_IO_TYPE_PT 0 +#define VMXNET3_IO_TYPE_VD 1 +#define VMXNET3_IO_ADDR(type, reg) (((type) << 24) | ((reg) & 0xFFFFFF)) +#define VMXNET3_IO_TYPE(addr) ((addr) >> 24) +#define VMXNET3_IO_REG(addr) ((addr) & 0xFFFFFF) + +enum { + VMXNET3_CMD_FIRST_SET = 0xCAFE0000, + VMXNET3_CMD_ACTIVATE_DEV = VMXNET3_CMD_FIRST_SET, + VMXNET3_CMD_QUIESCE_DEV, + VMXNET3_CMD_RESET_DEV, + VMXNET3_CMD_UPDATE_RX_MODE, + VMXNET3_CMD_UPDATE_MAC_FILTERS, + VMXNET3_CMD_UPDATE_VLAN_FILTERS, + VMXNET3_CMD_UPDATE_RSSIDT, + VMXNET3_CMD_UPDATE_IML, + VMXNET3_CMD_UPDATE_PMCFG, + VMXNET3_CMD_UPDATE_FEATURE, + VMXNET3_CMD_LOAD_PLUGIN, + + VMXNET3_CMD_FIRST_GET = 0xF00D0000, + VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET, + VMXNET3_CMD_GET_STATS, + VMXNET3_CMD_GET_LINK, + VMXNET3_CMD_GET_PERM_MAC_LO, + VMXNET3_CMD_GET_PERM_MAC_HI, + VMXNET3_CMD_GET_DID_LO, + VMXNET3_CMD_GET_DID_HI, + VMXNET3_CMD_GET_DEV_EXTRA_INFO, + VMXNET3_CMD_GET_CONF_INTR +}; + +struct Vmxnet3_TxDesc { + u64 addr; + + u32 len:14; + u32 gen:1; /* generation bit */ + u32 rsvd:1; + u32 dtype:1; /* descriptor type */ + u32 ext1:1; + u32 msscof:14; /* MSS, checksum offset, flags */ + + u32 hlen:10; /* header len */ + u32 om:2; /* offload mode */ + u32 eop:1; /* End Of Packet */ + u32 cq:1; /* completion request */ + u32 ext2:1; + u32 ti:1; /* VLAN Tag Insertion */ + u32 tci:16; /* Tag to Insert */ +}; + +/* TxDesc.OM values */ +#define VMXNET3_OM_NONE 0 +#define VMXNET3_OM_CSUM 2 +#define VMXNET3_OM_TSO 3 + +/* fields in TxDesc we access w/o using bit fields */ +#define VMXNET3_TXD_EOP_SHIFT 12 +#define VMXNET3_TXD_CQ_SHIFT 13 +#define VMXNET3_TXD_GEN_SHIFT 14 + +#define VMXNET3_TXD_CQ (1 << VMXNET3_TXD_CQ_SHIFT) +#define VMXNET3_TXD_EOP (1 << VMXNET3_TXD_EOP_SHIFT) +#define VMXNET3_TXD_GEN (1 << VMXNET3_TXD_GEN_SHIFT) + +#define VMXNET3_HDR_COPY_SIZE 128 + + +struct Vmxnet3_TxDataDesc { + u8 data[VMXNET3_HDR_COPY_SIZE]; +}; + + +struct Vmxnet3_TxCompDesc { + u32 txdIdx:12; /* Index of the EOP TxDesc */ + u32 ext1:20; + + u32 ext2; + u32 ext3; + + u32 rsvd:24; + u32 type:7; /* completion type */ + u32 gen:1; /* generation bit */ +}; + + +struct Vmxnet3_RxDesc { + u64 addr; + + u32 len:14; + u32 btype:1; /* Buffer Type */ + u32 dtype:1; /* Descriptor type */ + u32 rsvd:15; + u32 gen:1; /* Generation bit */ + + u32 ext1; +}; + +/* values of RXD.BTYPE */ +#define VMXNET3_RXD_BTYPE_HEAD 0 /* head only */ +#define VMXNET3_RXD_BTYPE_BODY 1 /* body only */ + +/* fields in RxDesc we access w/o using bit fields */ +#define VMXNET3_RXD_BTYPE_SHIFT 14 +#define VMXNET3_RXD_GEN_SHIFT 31 + + +struct Vmxnet3_RxCompDesc { + u32 rxdIdx:12; /* Index of the RxDesc */ + u32 ext1:2; + u32 eop:1; /* End of Packet */ + u32 sop:1; /* Start of Packet */ + u32 rqID:10; /* rx queue/ring ID */ + u32 rssType:4; /* RSS hash type used */ + u32 cnc:1; /* Checksum Not Calculated */ + u32 ext2:1; + + u32 rssHash; /* RSS hash value */ + + u32 len:14; /* data length */ + u32 err:1; /* Error */ + u32 ts:1; /* Tag is stripped */ + u32 tci:16; /* Tag stripped */ + + u32 csum:16; + u32 tuc:1; /* TCP/UDP Checksum Correct */ + u32 udp:1; /* UDP packet */ + u32 tcp:1; /* TCP packet */ + u32 ipc:1; /* IP Checksum Correct */ + u32 v6:1; /* IPv6 */ + u32 v4:1; /* IPv4 */ + u32 frg:1; /* IP Fragment */ + u32 fcs:1; /* Frame CRC correct */ + u32 type:7; /* completion type */ + u32 gen:1; /* generation bit */ +}; + +/* fields in RxCompDesc we access via Vmxnet3_GenericDesc.dword[3] */ +#define VMXNET3_RCD_TUC_SHIFT 16 +#define VMXNET3_RCD_IPC_SHIFT 19 + +/* fields in RxCompDesc we access via Vmxnet3_GenericDesc.qword[1] */ +#define VMXNET3_RCD_TYPE_SHIFT 56 +#define VMXNET3_RCD_GEN_SHIFT 63 + +/* csum OK for TCP/UDP pkts over IP */ +#define VMXNET3_RCD_CSUM_OK (1 << VMXNET3_RCD_TUC_SHIFT | \ + 1 << VMXNET3_RCD_IPC_SHIFT) + +/* value of RxCompDesc.rssType */ +enum { + VMXNET3_RCD_RSS_TYPE_NONE = 0, + VMXNET3_RCD_RSS_TYPE_IPV4 = 1, + VMXNET3_RCD_RSS_TYPE_TCPIPV4 = 2, + VMXNET3_RCD_RSS_TYPE_IPV6 = 3, + VMXNET3_RCD_RSS_TYPE_TCPIPV6 = 4, +}; + + +/* a union for accessing all cmd/completion descriptors */ +union Vmxnet3_GenericDesc { + u64 qword[2]; + u32 dword[4]; + u16 word[8]; + struct Vmxnet3_TxDesc txd; + struct Vmxnet3_RxDesc rxd; + struct Vmxnet3_TxCompDesc tcd; + struct Vmxnet3_RxCompDesc rcd; +}; + +#define VMXNET3_INIT_GEN 1 + +/* Max size of a single tx buffer */ +#define VMXNET3_MAX_TX_BUF_SIZE (1 << 14) + +/* # of tx desc needed for a tx buffer size */ +#define VMXNET3_TXD_NEEDED(size) (((size) + VMXNET3_MAX_TX_BUF_SIZE - 1) / \ + VMXNET3_MAX_TX_BUF_SIZE) + +/* max # of tx descs for a non-tso pkt */ +#define VMXNET3_MAX_TXD_PER_PKT 16 + +/* Max size of a single rx buffer */ +#define VMXNET3_MAX_RX_BUF_SIZE ((1 << 14) - 1) +/* Minimum size of a type 0 buffer */ +#define VMXNET3_MIN_T0_BUF_SIZE 128 +#define VMXNET3_MAX_CSUM_OFFSET 1024 + +/* Ring base address alignment */ +#define VMXNET3_RING_BA_ALIGN 512 +#define VMXNET3_RING_BA_MASK (VMXNET3_RING_BA_ALIGN - 1) + +/* Ring size must be a multiple of 32 */ +#define VMXNET3_RING_SIZE_ALIGN 32 +#define VMXNET3_RING_SIZE_MASK (VMXNET3_RING_SIZE_ALIGN - 1) + +/* Max ring size */ +#define VMXNET3_TX_RING_MAX_SIZE 4096 +#define VMXNET3_TC_RING_MAX_SIZE 4096 +#define VMXNET3_RX_RING_MAX_SIZE 4096 +#define VMXNET3_RC_RING_MAX_SIZE 8192 + +/* a list of reasons for queue stop */ + +enum { + VMXNET3_ERR_NOEOP = 0x80000000, /* cannot find the EOP desc of a pkt */ + VMXNET3_ERR_TXD_REUSE = 0x80000001, /* reuse TxDesc before tx completion */ + VMXNET3_ERR_BIG_PKT = 0x80000002, /* too many TxDesc for a pkt */ + VMXNET3_ERR_DESC_NOT_SPT = 0x80000003, /* descriptor type not supported */ + VMXNET3_ERR_SMALL_BUF = 0x80000004, /* type 0 buffer too small */ + VMXNET3_ERR_STRESS = 0x80000005, /* stress option firing in vmkernel */ + VMXNET3_ERR_SWITCH = 0x80000006, /* mode switch failure */ + VMXNET3_ERR_TXD_INVALID = 0x80000007, /* invalid TxDesc */ +}; + +/* completion descriptor types */ +#define VMXNET3_CDTYPE_TXCOMP 0 /* Tx Completion Descriptor */ +#define VMXNET3_CDTYPE_RXCOMP 3 /* Rx Completion Descriptor */ + +enum { + VMXNET3_GOS_BITS_UNK = 0, /* unknown */ + VMXNET3_GOS_BITS_32 = 1, + VMXNET3_GOS_BITS_64 = 2, +}; + +#define VMXNET3_GOS_TYPE_LINUX 1 + + +struct Vmxnet3_GOSInfo { + u32 gosBits:2; /* 32-bit or 64-bit? */ + u32 gosType:4; /* which guest */ + u32 gosVer:16; /* gos version */ + u32 gosMisc:10; /* other info about gos */ +}; + + +struct Vmxnet3_DriverInfo { + u32 version; + struct Vmxnet3_GOSInfo gos; + u32 vmxnet3RevSpt; + u32 uptVerSpt; +}; + + +#define VMXNET3_REV1_MAGIC 0xbabefee1 + +/* + * QueueDescPA must be 128 bytes aligned. It points to an array of + * Vmxnet3_TxQueueDesc followed by an array of Vmxnet3_RxQueueDesc. + * The number of Vmxnet3_TxQueueDesc/Vmxnet3_RxQueueDesc are specified by + * Vmxnet3_MiscConf.numTxQueues/numRxQueues, respectively. + */ +#define VMXNET3_QUEUE_DESC_ALIGN 128 + + +struct Vmxnet3_MiscConf { + struct Vmxnet3_DriverInfo driverInfo; + u64 uptFeatures; + u64 ddPA; /* driver data PA */ + u64 queueDescPA; /* queue descriptor table PA */ + u32 ddLen; /* driver data len */ + u32 queueDescLen; /* queue desc. table len in bytes */ + u32 mtu; + u16 maxNumRxSG; + u8 numTxQueues; + u8 numRxQueues; + u32 reserved[4]; +}; + + +struct Vmxnet3_TxQueueConf { + u64 txRingBasePA; + u64 dataRingBasePA; + u64 compRingBasePA; + u64 ddPA; /* driver data */ + u64 reserved; + u32 txRingSize; /* # of tx desc */ + u32 dataRingSize; /* # of data desc */ + u32 compRingSize; /* # of comp desc */ + u32 ddLen; /* size of driver data */ + u8 intrIdx; + u8 _pad[7]; +}; + + +struct Vmxnet3_RxQueueConf { + u64 rxRingBasePA[2]; + u64 compRingBasePA; + u64 ddPA; /* driver data */ + u64 reserved; + u32 rxRingSize[2]; /* # of rx desc */ + u32 compRingSize; /* # of rx comp desc */ + u32 ddLen; /* size of driver data */ + u8 intrIdx; + u8 _pad[7]; +}; + + +enum vmxnet3_intr_mask_mode { + VMXNET3_IMM_AUTO = 0, + VMXNET3_IMM_ACTIVE = 1, + VMXNET3_IMM_LAZY = 2 +}; + +enum vmxnet3_intr_type { + VMXNET3_IT_AUTO = 0, + VMXNET3_IT_INTX = 1, + VMXNET3_IT_MSI = 2, + VMXNET3_IT_MSIX = 3 +}; + +#define VMXNET3_MAX_TX_QUEUES 8 +#define VMXNET3_MAX_RX_QUEUES 16 +/* addition 1 for events */ +#define VMXNET3_MAX_INTRS 25 + + +struct Vmxnet3_IntrConf { + bool autoMask; + u8 numIntrs; /* # of interrupts */ + u8 eventIntrIdx; + u8 modLevels[VMXNET3_MAX_INTRS]; /* moderation level for + * each intr */ + u32 reserved[3]; +}; + +/* one bit per VLAN ID, the size is in the units of u32 */ +#define VMXNET3_VFT_SIZE (4096 / (sizeof(u32) * 8)) + + +struct Vmxnet3_QueueStatus { + bool stopped; + u8 _pad[3]; + u32 error; +}; + + +struct Vmxnet3_TxQueueCtrl { + u32 txNumDeferred; + u32 txThreshold; + u64 reserved; +}; + + +struct Vmxnet3_RxQueueCtrl { + bool updateRxProd; + u8 _pad[7]; + u64 reserved; +}; + +enum { + VMXNET3_RXM_UCAST = 0x01, /* unicast only */ + VMXNET3_RXM_MCAST = 0x02, /* multicast passing the filters */ + VMXNET3_RXM_BCAST = 0x04, /* broadcast only */ + VMXNET3_RXM_ALL_MULTI = 0x08, /* all multicast */ + VMXNET3_RXM_PROMISC = 0x10 /* promiscuous */ +}; + +struct Vmxnet3_RxFilterConf { + u32 rxMode; /* VMXNET3_RXM_xxx */ + u16 mfTableLen; /* size of the multicast filter table */ + u16 _pad1; + u64 mfTablePA; /* PA of the multicast filters table */ + u32 vfTable[VMXNET3_VFT_SIZE]; /* vlan filter */ +}; + + +#define VMXNET3_PM_MAX_FILTERS 6 +#define VMXNET3_PM_MAX_PATTERN_SIZE 128 +#define VMXNET3_PM_MAX_MASK_SIZE (VMXNET3_PM_MAX_PATTERN_SIZE / 8) + +#define VMXNET3_PM_WAKEUP_MAGIC 0x01 /* wake up on magic pkts */ +#define VMXNET3_PM_WAKEUP_FILTER 0x02 /* wake up on pkts matching + * filters */ + + +struct Vmxnet3_PM_PktFilter { + u8 maskSize; + u8 patternSize; + u8 mask[VMXNET3_PM_MAX_MASK_SIZE]; + u8 pattern[VMXNET3_PM_MAX_PATTERN_SIZE]; + u8 pad[6]; +}; + + +struct Vmxnet3_PMConf { + u16 wakeUpEvents; /* VMXNET3_PM_WAKEUP_xxx */ + u8 numFilters; + u8 pad[5]; + struct Vmxnet3_PM_PktFilter filters[VMXNET3_PM_MAX_FILTERS]; +}; + + +struct Vmxnet3_VariableLenConfDesc { + u32 confVer; + u32 confLen; + u64 confPA; +}; + + +struct Vmxnet3_TxQueueDesc { + struct Vmxnet3_TxQueueCtrl ctrl; + struct Vmxnet3_TxQueueConf conf; + + /* Driver read after a GET command */ + struct Vmxnet3_QueueStatus status; + struct UPT1_TxStats stats; + u8 _pad[88]; /* 128 aligned */ +}; + + +struct Vmxnet3_RxQueueDesc { + struct Vmxnet3_RxQueueCtrl ctrl; + struct Vmxnet3_RxQueueConf conf; + /* Driver read after a GET commad */ + struct Vmxnet3_QueueStatus status; + struct UPT1_RxStats stats; + u8 __pad[88]; /* 128 aligned */ +}; + + +struct Vmxnet3_DSDevRead { + /* read-only region for device, read by dev in response to a SET cmd */ + struct Vmxnet3_MiscConf misc; + struct Vmxnet3_IntrConf intrConf; + struct Vmxnet3_RxFilterConf rxFilterConf; + struct Vmxnet3_VariableLenConfDesc rssConfDesc; + struct Vmxnet3_VariableLenConfDesc pmConfDesc; + struct Vmxnet3_VariableLenConfDesc pluginConfDesc; +}; + +/* All structures in DriverShared are padded to multiples of 8 bytes */ +struct Vmxnet3_DriverShared { + u32 magic; + /* make devRead start at 64bit boundaries */ + u32 pad; + struct Vmxnet3_DSDevRead devRead; + u32 ecr; + u32 reserved[5]; +}; + + +#define VMXNET3_ECR_RQERR (1 << 0) +#define VMXNET3_ECR_TQERR (1 << 1) +#define VMXNET3_ECR_LINK (1 << 2) +#define VMXNET3_ECR_DIC (1 << 3) +#define VMXNET3_ECR_DEBUG (1 << 4) + +/* flip the gen bit of a ring */ +#define VMXNET3_FLIP_RING_GEN(gen) ((gen) = (gen) ^ 0x1) + +/* only use this if moving the idx won't affect the gen bit */ +#define VMXNET3_INC_RING_IDX_ONLY(idx, ring_size) \ + do {\ + (idx)++;\ + if (unlikely((idx) == (ring_size))) {\ + (idx) = 0;\ + } \ + } while (0) + +#define VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid) \ + (vfTable[vid >> 5] |= (1 << (vid & 31))) +#define VMXNET3_CLEAR_VFTABLE_ENTRY(vfTable, vid) \ + (vfTable[vid >> 5] &= ~(1 << (vid & 31))) + +#define VMXNET3_VFTABLE_ENTRY_IS_SET(vfTable, vid) \ + ((vfTable[vid >> 5] & (1 << (vid & 31))) != 0) + +#define VMXNET3_MAX_MTU 9000 +#define VMXNET3_MIN_MTU 60 + +#define VMXNET3_LINK_UP (10000 << 16 | 1) /* 10 Gbps, up */ +#define VMXNET3_LINK_DOWN 0 + +#endif /* _VMXNET3_DEFS_H_ */ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c new file mode 100644 index 00000000000..44fb0c5a280 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -0,0 +1,2556 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License and no later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. 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". + * + * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com> + * + */ + +#include "vmxnet3_int.h" + +char vmxnet3_driver_name[] = "vmxnet3"; +#define VMXNET3_DRIVER_DESC "VMware vmxnet3 virtual NIC driver" + + +/* + * PCI Device ID Table + * Last entry must be all 0s + */ +static const struct pci_device_id vmxnet3_pciid_table[] = { + {PCI_VDEVICE(VMWARE, PCI_DEVICE_ID_VMWARE_VMXNET3)}, + {0} +}; + +MODULE_DEVICE_TABLE(pci, vmxnet3_pciid_table); + +static atomic_t devices_found; + + +/* + * Enable/Disable the given intr + */ +static void +vmxnet3_enable_intr(struct vmxnet3_adapter *adapter, unsigned intr_idx) +{ + VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_IMR + intr_idx * 8, 0); +} + + +static void +vmxnet3_disable_intr(struct vmxnet3_adapter *adapter, unsigned intr_idx) +{ + VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_IMR + intr_idx * 8, 1); +} + + +/* + * Enable/Disable all intrs used by the device + */ +static void +vmxnet3_enable_all_intrs(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->intr.num_intrs; i++) + vmxnet3_enable_intr(adapter, i); +} + + +static void +vmxnet3_disable_all_intrs(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->intr.num_intrs; i++) + vmxnet3_disable_intr(adapter, i); +} + + +static void +vmxnet3_ack_events(struct vmxnet3_adapter *adapter, u32 events) +{ + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_ECR, events); +} + + +static bool +vmxnet3_tq_stopped(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + return netif_queue_stopped(adapter->netdev); +} + + +static void +vmxnet3_tq_start(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = false; + netif_start_queue(adapter->netdev); +} + + +static void +vmxnet3_tq_wake(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = false; + netif_wake_queue(adapter->netdev); +} + + +static void +vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = true; + tq->num_stop++; + netif_stop_queue(adapter->netdev); +} + + +/* + * Check the link state. This may start or stop the tx queue. + */ +static void +vmxnet3_check_link(struct vmxnet3_adapter *adapter) +{ + u32 ret; + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_LINK); + ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + adapter->link_speed = ret >> 16; + if (ret & 1) { /* Link is up. */ + printk(KERN_INFO "%s: NIC Link is Up %d Mbps\n", + adapter->netdev->name, adapter->link_speed); + if (!netif_carrier_ok(adapter->netdev)) + netif_carrier_on(adapter->netdev); + + vmxnet3_tq_start(&adapter->tx_queue, adapter); + } else { + printk(KERN_INFO "%s: NIC Link is Down\n", + adapter->netdev->name); + if (netif_carrier_ok(adapter->netdev)) + netif_carrier_off(adapter->netdev); + + vmxnet3_tq_stop(&adapter->tx_queue, adapter); + } +} + + +static void +vmxnet3_process_events(struct vmxnet3_adapter *adapter) +{ + u32 events = adapter->shared->ecr; + if (!events) + return; + + vmxnet3_ack_events(adapter, events); + + /* Check if link state has changed */ + if (events & VMXNET3_ECR_LINK) + vmxnet3_check_link(adapter); + + /* Check if there is an error on xmit/recv queues */ + if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_QUEUE_STATUS); + + if (adapter->tqd_start->status.stopped) { + printk(KERN_ERR "%s: tq error 0x%x\n", + adapter->netdev->name, + adapter->tqd_start->status.error); + } + if (adapter->rqd_start->status.stopped) { + printk(KERN_ERR "%s: rq error 0x%x\n", + adapter->netdev->name, + adapter->rqd_start->status.error); + } + + schedule_work(&adapter->work); + } +} + + +static void +vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, + struct pci_dev *pdev) +{ + if (tbi->map_type == VMXNET3_MAP_SINGLE) + pci_unmap_single(pdev, tbi->dma_addr, tbi->len, + PCI_DMA_TODEVICE); + else if (tbi->map_type == VMXNET3_MAP_PAGE) + pci_unmap_page(pdev, tbi->dma_addr, tbi->len, + PCI_DMA_TODEVICE); + else + BUG_ON(tbi->map_type != VMXNET3_MAP_NONE); + + tbi->map_type = VMXNET3_MAP_NONE; /* to help debugging */ +} + + +static int +vmxnet3_unmap_pkt(u32 eop_idx, struct vmxnet3_tx_queue *tq, + struct pci_dev *pdev, struct vmxnet3_adapter *adapter) +{ + struct sk_buff *skb; + int entries = 0; + + /* no out of order completion */ + BUG_ON(tq->buf_info[eop_idx].sop_idx != tq->tx_ring.next2comp); + BUG_ON(tq->tx_ring.base[eop_idx].txd.eop != 1); + + skb = tq->buf_info[eop_idx].skb; + BUG_ON(skb == NULL); + tq->buf_info[eop_idx].skb = NULL; + + VMXNET3_INC_RING_IDX_ONLY(eop_idx, tq->tx_ring.size); + + while (tq->tx_ring.next2comp != eop_idx) { + vmxnet3_unmap_tx_buf(tq->buf_info + tq->tx_ring.next2comp, + pdev); + + /* update next2comp w/o tx_lock. Since we are marking more, + * instead of less, tx ring entries avail, the worst case is + * that the tx routine incorrectly re-queues a pkt due to + * insufficient tx ring entries. + */ + vmxnet3_cmd_ring_adv_next2comp(&tq->tx_ring); + entries++; + } + + dev_kfree_skb_any(skb); + return entries; +} + + +static int +vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + int completed = 0; + union Vmxnet3_GenericDesc *gdesc; + + gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; + while (gdesc->tcd.gen == tq->comp_ring.gen) { + completed += vmxnet3_unmap_pkt(gdesc->tcd.txdIdx, tq, + adapter->pdev, adapter); + + vmxnet3_comp_ring_adv_next2proc(&tq->comp_ring); + gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; + } + + if (completed) { + spin_lock(&tq->tx_lock); + if (unlikely(vmxnet3_tq_stopped(tq, adapter) && + vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) > + VMXNET3_WAKE_QUEUE_THRESHOLD(tq) && + netif_carrier_ok(adapter->netdev))) { + vmxnet3_tq_wake(tq, adapter); + } + spin_unlock(&tq->tx_lock); + } + return completed; +} + + +static void +vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + int i; + + while (tq->tx_ring.next2comp != tq->tx_ring.next2fill) { + struct vmxnet3_tx_buf_info *tbi; + union Vmxnet3_GenericDesc *gdesc; + + tbi = tq->buf_info + tq->tx_ring.next2comp; + gdesc = tq->tx_ring.base + tq->tx_ring.next2comp; + + vmxnet3_unmap_tx_buf(tbi, adapter->pdev); + if (tbi->skb) { + dev_kfree_skb_any(tbi->skb); + tbi->skb = NULL; + } + vmxnet3_cmd_ring_adv_next2comp(&tq->tx_ring); + } + + /* sanity check, verify all buffers are indeed unmapped and freed */ + for (i = 0; i < tq->tx_ring.size; i++) { + BUG_ON(tq->buf_info[i].skb != NULL || + tq->buf_info[i].map_type != VMXNET3_MAP_NONE); + } + + tq->tx_ring.gen = VMXNET3_INIT_GEN; + tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0; + + tq->comp_ring.gen = VMXNET3_INIT_GEN; + tq->comp_ring.next2proc = 0; +} + + +void +vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + if (tq->tx_ring.base) { + pci_free_consistent(adapter->pdev, tq->tx_ring.size * + sizeof(struct Vmxnet3_TxDesc), + tq->tx_ring.base, tq->tx_ring.basePA); + tq->tx_ring.base = NULL; + } + if (tq->data_ring.base) { + pci_free_consistent(adapter->pdev, tq->data_ring.size * + sizeof(struct Vmxnet3_TxDataDesc), + tq->data_ring.base, tq->data_ring.basePA); + tq->data_ring.base = NULL; + } + if (tq->comp_ring.base) { + pci_free_consistent(adapter->pdev, tq->comp_ring.size * + sizeof(struct Vmxnet3_TxCompDesc), + tq->comp_ring.base, tq->comp_ring.basePA); + tq->comp_ring.base = NULL; + } + kfree(tq->buf_info); + tq->buf_info = NULL; +} + + +static void +vmxnet3_tq_init(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + int i; + + /* reset the tx ring contents to 0 and reset the tx ring states */ + memset(tq->tx_ring.base, 0, tq->tx_ring.size * + sizeof(struct Vmxnet3_TxDesc)); + tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0; + tq->tx_ring.gen = VMXNET3_INIT_GEN; + + memset(tq->data_ring.base, 0, tq->data_ring.size * + sizeof(struct Vmxnet3_TxDataDesc)); + + /* reset the tx comp ring contents to 0 and reset comp ring states */ + memset(tq->comp_ring.base, 0, tq->comp_ring.size * + sizeof(struct Vmxnet3_TxCompDesc)); + tq->comp_ring.next2proc = 0; + tq->comp_ring.gen = VMXNET3_INIT_GEN; + + /* reset the bookkeeping data */ + memset(tq->buf_info, 0, sizeof(tq->buf_info[0]) * tq->tx_ring.size); + for (i = 0; i < tq->tx_ring.size; i++) + tq->buf_info[i].map_type = VMXNET3_MAP_NONE; + + /* stats are not reset */ +} + + +static int +vmxnet3_tq_create(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + BUG_ON(tq->tx_ring.base || tq->data_ring.base || + tq->comp_ring.base || tq->buf_info); + + tq->tx_ring.base = pci_alloc_consistent(adapter->pdev, tq->tx_ring.size + * sizeof(struct Vmxnet3_TxDesc), + &tq->tx_ring.basePA); + if (!tq->tx_ring.base) { + printk(KERN_ERR "%s: failed to allocate tx ring\n", < |