diff options
Diffstat (limited to 'drivers/net/vmxnet3')
| -rw-r--r-- | drivers/net/vmxnet3/Makefile | 35 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/upt1_defs.h | 99 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_defs.h | 864 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_drv.c | 4442 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_ethtool.c | 1377 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_int.h | 538 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_xdp.c | 419 | ||||
| -rw-r--r-- | drivers/net/vmxnet3/vmxnet3_xdp.h | 47 |
8 files changed, 7821 insertions, 0 deletions
diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile new file mode 100644 index 0000000000..f82870c102 --- /dev/null +++ b/drivers/net/vmxnet3/Makefile @@ -0,0 +1,35 @@ +################################################################################ +# +# Linux driver for VMware's vmxnet3 ethernet NIC. +# +# Copyright (C) 2007-2022, 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: 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 vmxnet3_xdp.o diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h new file mode 100644 index 0000000000..41c0660a0c --- /dev/null +++ b/drivers/net/vmxnet3/upt1_defs.h @@ -0,0 +1,99 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, 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: 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 = cpu_to_le64(0x0001), /* rx csum verification */ + UPT1_F_RSS = cpu_to_le64(0x0002), + UPT1_F_RXVLAN = cpu_to_le64(0x0004), /* VLAN tag stripping */ + UPT1_F_LRO = cpu_to_le64(0x0008), + UPT1_F_RXINNEROFLD = cpu_to_le64(0x00010), /* Geneve/Vxlan rx csum + * offloading + */ +}; +#endif diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h new file mode 100644 index 0000000000..41d6767283 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_defs.h @@ -0,0 +1,864 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, 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: 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 */ + VMXNET3_REG_DCR = 0x48, /* Device capability register, + * from 0x48 to 0x80 + */ + VMXNET3_REG_PTCR = 0x88, /* Passthru capbility register + * from 0x88 to 0xb0 + */ +}; + +/* 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 */ +}; + +/* For Large PT BAR, the following offset to DB register */ +enum { + VMXNET3_REG_LB_TXPROD = 0x1000, /* Tx Producer Index */ + VMXNET3_REG_LB_RXPROD = 0x1400, /* Rx Producer Index for ring 1 */ + VMXNET3_REG_LB_RXPROD2 = 0x1800, /* Rx Producer Index for ring 2 */ +}; + +#define VMXNET3_PT_REG_SIZE 4096 /* BAR 0 */ +#define VMXNET3_LARGE_PT_REG_SIZE 8192 /* large PT pages */ +#define VMXNET3_VD_REG_SIZE 4096 /* BAR 1 */ +#define VMXNET3_LARGE_BAR0_REG_SIZE (4096 * 4096) /* LARGE BAR 0 */ +#define VMXNET3_OOB_REG_SIZE (4094 * 4096) /* OOB pages */ + +#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_RESERVED1, + VMXNET3_CMD_LOAD_PLUGIN, + VMXNET3_CMD_RESERVED2, + VMXNET3_CMD_RESERVED3, + VMXNET3_CMD_SET_COALESCE, + VMXNET3_CMD_REGISTER_MEMREGS, + VMXNET3_CMD_SET_RSS_FIELDS, + VMXNET3_CMD_RESERVED4, + VMXNET3_CMD_RESERVED5, + VMXNET3_CMD_SET_RING_BUFFER_SIZE, + + 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, + VMXNET3_CMD_GET_RESERVED1, + VMXNET3_CMD_GET_TXDATA_DESC_SIZE, + VMXNET3_CMD_GET_COALESCE, + VMXNET3_CMD_GET_RSS_FIELDS, + VMXNET3_CMD_GET_RESERVED2, + VMXNET3_CMD_GET_RESERVED3, + VMXNET3_CMD_GET_MAX_QUEUES_CONF, + VMXNET3_CMD_GET_RESERVED4, + VMXNET3_CMD_GET_MAX_CAPABILITIES, + VMXNET3_CMD_GET_DCR0_REG, +}; + +/* + * Little Endian layout of bitfields - + * Byte 0 : 7.....len.....0 + * Byte 1 : oco gen 13.len.8 + * Byte 2 : 5.msscof.0 ext1 dtype + * Byte 3 : 13...msscof...6 + * + * Big Endian layout of bitfields - + * Byte 0: 13...msscof...6 + * Byte 1 : 5.msscof.0 ext1 dtype + * Byte 2 : oco gen 13.len.8 + * Byte 3 : 7.....len.....0 + * + * Thus, le32_to_cpu on the dword will allow the big endian driver to read + * the bit fields correctly. And cpu_to_le32 will convert bitfields + * bit fields written by big endian driver to format required by device. + */ + +struct Vmxnet3_TxDesc { + __le64 addr; + +#ifdef __BIG_ENDIAN_BITFIELD + u32 msscof:14; /* MSS, checksum offset, flags */ + u32 ext1:1; /* set to 1 to indicate inner csum/tso, vmxnet3 v7 */ + u32 dtype:1; /* descriptor type */ + u32 oco:1; /* Outer csum offload */ + u32 gen:1; /* generation bit */ + u32 len:14; +#else + u32 len:14; + u32 gen:1; /* generation bit */ + u32 oco:1; /* Outer csum offload */ + u32 dtype:1; /* descriptor type */ + u32 ext1:1; /* set to 1 to indicate inner csum/tso, vmxnet3 v7 */ + u32 msscof:14; /* MSS, checksum offset, flags */ +#endif /* __BIG_ENDIAN_BITFIELD */ + +#ifdef __BIG_ENDIAN_BITFIELD + u32 tci:16; /* Tag to Insert */ + u32 ti:1; /* VLAN Tag Insertion */ + u32 ext2:1; + u32 cq:1; /* completion request */ + u32 eop:1; /* End Of Packet */ + u32 om:2; /* offload mode */ + u32 hlen:10; /* header len */ +#else + 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 */ +#endif /* __BIG_ENDIAN_BITFIELD */ +}; + +/* TxDesc.OM values */ +#define VMXNET3_OM_NONE 0 +#define VMXNET3_OM_ENCAP 1 +#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_EOP_DWORD_SHIFT 3 +#define VMXNET3_TXD_GEN_DWORD_SHIFT 2 + +#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]; +}; + +typedef u8 Vmxnet3_RxDataDesc; + +#define VMXNET3_TCD_GEN_SHIFT 31 +#define VMXNET3_TCD_GEN_SIZE 1 +#define VMXNET3_TCD_TXIDX_SHIFT 0 +#define VMXNET3_TCD_TXIDX_SIZE 12 +#define VMXNET3_TCD_GEN_DWORD_SHIFT 3 + +struct Vmxnet3_TxCompDesc { + u32 txdIdx:12; /* Index of the EOP TxDesc */ + u32 ext1:20; + + __le32 ext2; + __le32 ext3; + + u32 rsvd:24; + u32 type:7; /* completion type */ + u32 gen:1; /* generation bit */ +}; + +struct Vmxnet3_RxDesc { + __le64 addr; + +#ifdef __BIG_ENDIAN_BITFIELD + u32 gen:1; /* Generation bit */ + u32 rsvd:15; + u32 dtype:1; /* Descriptor type */ + u32 btype:1; /* Buffer Type */ + u32 len:14; +#else + u32 len:14; + u32 btype:1; /* Buffer Type */ + u32 dtype:1; /* Descriptor type */ + u32 rsvd:15; + u32 gen:1; /* Generation bit */ +#endif + 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 + +#define VMXNET3_RCD_HDR_INNER_SHIFT 13 + +struct Vmxnet3_RxCompDesc { +#ifdef __BIG_ENDIAN_BITFIELD + u32 ext2:1; + u32 cnc:1; /* Checksum Not Calculated */ + u32 rssType:4; /* RSS hash type used */ + u32 rqID:10; /* rx queue/ring ID */ + u32 sop:1; /* Start of Packet */ + u32 eop:1; /* End of Packet */ + u32 ext1:2; /* bit 0: indicating v4/v6/.. is for inner header */ + /* bit 1: indicating rssType is based on inner header */ + u32 rxdIdx:12; /* Index of the RxDesc */ +#else + u32 rxdIdx:12; /* Index of the RxDesc */ + u32 ext1:2; /* bit 0: indicating v4/v6/.. is for inner header */ + /* bit 1: indicating rssType is based on inner header */ + 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; +#endif /* __BIG_ENDIAN_BITFIELD */ + + __le32 rssHash; /* RSS hash value */ + +#ifdef __BIG_ENDIAN_BITFIELD + u32 tci:16; /* Tag stripped */ + u32 ts:1; /* Tag is stripped */ + u32 err:1; /* Error */ + u32 len:14; /* data length */ +#else + u32 len:14; /* data length */ + u32 err:1; /* Error */ + u32 ts:1; /* Tag is stripped */ + u32 tci:16; /* Tag stripped */ +#endif /* __BIG_ENDIAN_BITFIELD */ + + +#ifdef __BIG_ENDIAN_BITFIELD + u32 gen:1; /* generation bit */ + u32 type:7; /* completion type */ + u32 fcs:1; /* Frame CRC correct */ + u32 frg:1; /* IP Fragment */ + u32 v4:1; /* IPv4 */ + u32 v6:1; /* IPv6 */ + u32 ipc:1; /* IP Checksum Correct */ + u32 tcp:1; /* TCP packet */ + u32 udp:1; /* UDP packet */ + u32 tuc:1; /* TCP/UDP Checksum Correct */ + u32 csum:16; +#else + 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 */ +#endif /* __BIG_ENDIAN_BITFIELD */ +}; + +struct Vmxnet3_RxCompDescExt { + __le32 dword1; + u8 segCnt; /* Number of aggregated packets */ + u8 dupAckCnt; /* Number of duplicate Acks */ + __le16 tsDelta; /* TCP timestamp difference */ + __le32 dword2; +#ifdef __BIG_ENDIAN_BITFIELD + u32 gen:1; /* generation bit */ + u32 type:7; /* completion type */ + u32 fcs:1; /* Frame CRC correct */ + u32 frg:1; /* IP Fragment */ + u32 v4:1; /* IPv4 */ + u32 v6:1; /* IPv6 */ + u32 ipc:1; /* IP Checksum Correct */ + u32 tcp:1; /* TCP packet */ + u32 udp:1; /* UDP packet */ + u32 tuc:1; /* TCP/UDP Checksum Correct */ + u32 mss:16; +#else + u32 mss: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 */ +#endif /* __BIG_ENDIAN_BITFIELD */ +}; + + +/* 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) +#define VMXNET3_TXD_GEN_SIZE 1 +#define VMXNET3_TXD_EOP_SIZE 1 + +/* value of RxCompDesc.rssType */ +#define VMXNET3_RCD_RSS_TYPE_NONE 0 +#define VMXNET3_RCD_RSS_TYPE_IPV4 1 +#define VMXNET3_RCD_RSS_TYPE_TCPIPV4 2 +#define VMXNET3_RCD_RSS_TYPE_IPV6 3 +#define VMXNET3_RCD_RSS_TYPE_TCPIPV6 4 +#define VMXNET3_RCD_RSS_TYPE_UDPIPV4 5 +#define VMXNET3_RCD_RSS_TYPE_UDPIPV6 6 +#define VMXNET3_RCD_RSS_TYPE_ESPIPV4 7 +#define VMXNET3_RCD_RSS_TYPE_ESPIPV6 8 + + +/* a union for accessing all cmd/completion descriptors */ +union Vmxnet3_GenericDesc { + __le64 qword[2]; + __le32 dword[4]; + __le16 word[8]; + struct Vmxnet3_TxDesc txd; + struct Vmxnet3_RxDesc rxd; + struct Vmxnet3_TxCompDesc tcd; + struct Vmxnet3_RxCompDesc rcd; + struct Vmxnet3_RxCompDescExt rcdExt; +}; + +#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 # of tx descs for a tso pkt */ +#define VMXNET3_MAX_TSO_TXD_PER_PKT 24 + +/* 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) + +/* Tx Data Ring buffer size must be a multiple of 64 */ +#define VMXNET3_TXDATA_DESC_SIZE_ALIGN 64 +#define VMXNET3_TXDATA_DESC_SIZE_MASK (VMXNET3_TXDATA_DESC_SIZE_ALIGN - 1) + +/* Rx Data Ring buffer size must be a multiple of 64 */ +#define VMXNET3_RXDATA_DESC_SIZE_ALIGN 64 +#define VMXNET3_RXDATA_DESC_SIZE_MASK (VMXNET3_RXDATA_DESC_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_RX_RING2_MAX_SIZE 4096 +#define VMXNET3_RC_RING_MAX_SIZE 8192 + +#define VMXNET3_TXDATA_DESC_MIN_SIZE 128 +#define VMXNET3_TXDATA_DESC_MAX_SIZE 2048 + +#define VMXNET3_RXDATA_DESC_MAX_SIZE 2048 + +/* 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 */ +#define VMXNET3_CDTYPE_RXCOMP_LRO 4 /* Rx Completion Descriptor for LRO */ + +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 { +#ifdef __BIG_ENDIAN_BITFIELD + u32 gosMisc:10; /* other info about gos */ + u32 gosVer:16; /* gos version */ + u32 gosType:4; /* which guest */ + u32 gosBits:2; /* 32-bit or 64-bit? */ +#else + 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 */ +#endif /* __BIG_ENDIAN_BITFIELD */ +}; + +struct Vmxnet3_DriverInfo { + __le32 version; + struct Vmxnet3_GOSInfo gos; + __le32 vmxnet3RevSpt; + __le32 uptVerSpt; +}; + + +#define VMXNET3_REV1_MAGIC 3133079265u + +/* + * 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; + __le64 uptFeatures; + __le64 ddPA; /* driver data PA */ + __le64 queueDescPA; /* queue descriptor table PA */ + __le32 ddLen; /* driver data len */ + __le32 queueDescLen; /* queue desc. table len in bytes */ + __le32 mtu; + __le16 maxNumRxSG; + u8 numTxQueues; + u8 numRxQueues; + __le32 reserved[4]; +}; + + +struct Vmxnet3_TxQueueConf { + __le64 txRingBasePA; + __le64 dataRingBasePA; + __le64 compRingBasePA; + __le64 ddPA; /* driver data */ + __le64 reserved; + __le32 txRingSize; /* # of tx desc */ + __le32 dataRingSize; /* # of data desc */ + __le32 compRingSize; /* # of comp desc */ + __le32 ddLen; /* size of driver data */ + u8 intrIdx; + u8 _pad1[1]; + __le16 txDataRingDescSize; + u8 _pad2[4]; +}; + + +struct Vmxnet3_RxQueueConf { + __le64 rxRingBasePA[2]; + __le64 compRingBasePA; + __le64 ddPA; /* driver data */ + __le64 rxDataRingBasePA; + __le32 rxRingSize[2]; /* # of rx desc */ + __le32 compRingSize; /* # of rx comp desc */ + __le32 ddLen; /* size of driver data */ + u8 intrIdx; + u8 _pad1[1]; + __le16 rxDataRingDescSize; /* size of rx data ring buffer */ + u8 _pad2[4]; +}; + + +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 + +/* Version 6 and later will use below macros */ +#define VMXNET3_EXT_MAX_TX_QUEUES 32 +#define VMXNET3_EXT_MAX_RX_QUEUES 32 +/* addition 1 for events */ +#define VMXNET3_EXT_MAX_INTRS 65 +#define VMXNET3_FIRST_SET_INTRS 64 + +/* value of intrCtrl */ +#define VMXNET3_IC_DISABLE_ALL 0x1 /* bit 0 */ + + +struct Vmxnet3_IntrConf { + bool autoMask; + u8 numIntrs; /* # of interrupts */ + u8 eventIntrIdx; + u8 modLevels[VMXNET3_MAX_INTRS]; /* moderation level for + * each intr */ + __le32 intrCtrl; + __le32 reserved[2]; +}; + +struct Vmxnet3_IntrConfExt { + u8 autoMask; + u8 numIntrs; /* # of interrupts */ + u8 eventIntrIdx; + u8 reserved; + __le32 intrCtrl; + __le32 reserved1; + u8 modLevels[VMXNET3_EXT_MAX_INTRS]; /* moderation level for + * each intr + */ + u8 reserved2[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]; + __le32 error; +}; + + +struct Vmxnet3_TxQueueCtrl { + __le32 txNumDeferred; + __le32 txThreshold; + __le64 reserved; +}; + + +struct Vmxnet3_RxQueueCtrl { + bool updateRxProd; + u8 _pad[7]; + __le64 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 { + __le32 rxMode; /* VMXNET3_RXM_xxx */ + __le16 mfTableLen; /* size of the multicast filter table */ + __le16 _pad1; + __le64 mfTablePA; /* PA of the multicast filters table */ + __le32 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 cpu_to_le16(0x01) /* wake up on magic pkts */ +#define VMXNET3_PM_WAKEUP_FILTER cpu_to_le16(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 { + __le16 wakeUpEvents; /* VMXNET3_PM_WAKEUP_xxx */ + u8 numFilters; + u8 pad[5]; + struct Vmxnet3_PM_PktFilter filters[VMXNET3_PM_MAX_FILTERS]; +}; + + +struct Vmxnet3_VariableLenConfDesc { + __le32 confVer; + __le32 confLen; + __le64 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_SetPolling { + u8 enablePolling; +}; + +#define VMXNET3_COAL_STATIC_MAX_DEPTH 128 +#define VMXNET3_COAL_RBC_MIN_RATE 100 +#define VMXNET3_COAL_RBC_MAX_RATE 100000 + +enum Vmxnet3_CoalesceMode { + VMXNET3_COALESCE_DISABLED = 0, + VMXNET3_COALESCE_ADAPT = 1, + VMXNET3_COALESCE_STATIC = 2, + VMXNET3_COALESCE_RBC = 3 +}; + +struct Vmxnet3_CoalesceRbc { + u32 rbc_rate; +}; + +struct Vmxnet3_CoalesceStatic { + u32 tx_depth; + u32 tx_comp_depth; + u32 rx_depth; +}; + +struct Vmxnet3_CoalesceScheme { + enum Vmxnet3_CoalesceMode coalMode; + union { + struct Vmxnet3_CoalesceRbc coalRbc; + struct Vmxnet3_CoalesceStatic coalStatic; + } coalPara; +}; + +struct Vmxnet3_MemoryRegion { + __le64 startPA; + __le32 length; + __le16 txQueueBits; + __le16 rxQueueBits; +}; + +#define MAX_MEMORY_REGION_PER_QUEUE 16 +#define MAX_MEMORY_REGION_PER_DEVICE 256 + +struct Vmxnet3_MemRegs { + __le16 numRegs; + __le16 pad[3]; + struct Vmxnet3_MemoryRegion memRegs[1]; +}; + +enum Vmxnet3_RSSField { + VMXNET3_RSS_FIELDS_TCPIP4 = 0x0001, + VMXNET3_RSS_FIELDS_TCPIP6 = 0x0002, + VMXNET3_RSS_FIELDS_UDPIP4 = 0x0004, + VMXNET3_RSS_FIELDS_UDPIP6 = 0x0008, + VMXNET3_RSS_FIELDS_ESPIP4 = 0x0010, + VMXNET3_RSS_FIELDS_ESPIP6 = 0x0020, +}; + +struct Vmxnet3_RingBufferSize { + __le16 ring1BufSizeType0; + __le16 ring1BufSizeType1; + __le16 ring2BufSizeType1; + __le16 pad; +}; + +/* If the command data <= 16 bytes, use the shared memory directly. + * otherwise, use variable length configuration descriptor. + */ +union Vmxnet3_CmdInfo { + struct Vmxnet3_VariableLenConfDesc varConf; + struct Vmxnet3_SetPolling setPolling; + enum Vmxnet3_RSSField setRssFields; + struct Vmxnet3_RingBufferSize ringBufSize; + __le64 data[2]; +}; + +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; +}; + +struct Vmxnet3_DSDevReadExt { + /* read-only region for device, read by dev in response to a SET cmd */ + struct Vmxnet3_IntrConfExt intrConfExt; +}; + +/* All structures in DriverShared are padded to multiples of 8 bytes */ +struct Vmxnet3_DriverShared { + __le32 magic; + /* make devRead start at 64bit boundaries */ + __le32 size; /* size of DriverShared */ + struct Vmxnet3_DSDevRead devRead; + __le32 ecr; + __le32 reserved; + union { + __le32 reserved1[4]; + union Vmxnet3_CmdInfo cmdInfo; /* only valid in the context of + * executing the relevant + * command + */ + } cu; + struct Vmxnet3_DSDevReadExt devReadExt; +}; + + +#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_V6_MAX_MTU 9190 +#define VMXNET3_MIN_MTU 60 + +#define VMXNET3_LINK_UP (10000 << 16 | 1) /* 10 Gbps, up */ +#define VMXNET3_LINK_DOWN 0 + +#define VMXNET3_DCR_ERROR 31 /* error when bit 31 of DCR is set */ +#define VMXNET3_CAP_UDP_RSS 0 /* bit 0 of DCR 0 */ +#define VMXNET3_CAP_ESP_RSS_IPV4 1 /* bit 1 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD 2 /* bit 2 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_TSO 3 /* bit 3 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD 4 /* bit 4 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_TSO 5 /* bit 5 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD 6 /* bit 6 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD 7 /* bit 7 of DCR 0 */ +#define VMXNET3_CAP_PKT_STEERING_IPV4 8 /* bit 8 of DCR 0 */ +#define VMXNET3_CAP_VERSION_4_MAX VMXNET3_CAP_PKT_STEERING_IPV4 +#define VMXNET3_CAP_ESP_RSS_IPV6 9 /* bit 9 of DCR 0 */ +#define VMXNET3_CAP_VERSION_5_MAX VMXNET3_CAP_ESP_RSS_IPV6 +#define VMXNET3_CAP_ESP_OVER_UDP_RSS 10 /* bit 10 of DCR 0 */ +#define VMXNET3_CAP_INNER_RSS 11 /* bit 11 of DCR 0 */ +#define VMXNET3_CAP_INNER_ESP_RSS 12 /* bit 12 of DCR 0 */ +#define VMXNET3_CAP_CRC32_HASH_FUNC 13 /* bit 13 of DCR 0 */ +#define VMXNET3_CAP_VERSION_6_MAX VMXNET3_CAP_CRC32_HASH_FUNC +#define VMXNET3_CAP_OAM_FILTER 14 /* bit 14 of DCR 0 */ +#define VMXNET3_CAP_ESP_QS 15 /* bit 15 of DCR 0 */ +#define VMXNET3_CAP_LARGE_BAR 16 /* bit 16 of DCR 0 */ +#define VMXNET3_CAP_OOORX_COMP 17 /* bit 17 of DCR 0 */ +#define VMXNET3_CAP_VERSION_7_MAX 18 +/* when new capability is introduced, update VMXNET3_CAP_MAX */ +#define VMXNET3_CAP_MAX VMXNET3_CAP_VERSION_7_MAX + +#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 0000000000..0578864792 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -0,0 +1,4442 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, 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: pv-drivers@vmware.com + * + */ + +#include <linux/module.h> +#include <net/ip6_checksum.h> + +#include "vmxnet3_int.h" +#include "vmxnet3_xdp.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 int enable_mq = 1; + +static void +vmxnet3_write_mac_addr(struct vmxnet3_adapter *adapter, const u8 *mac); + +/* + * 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); + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl &= + cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl &= + cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } +} + + +static void +vmxnet3_disable_all_intrs(struct vmxnet3_adapter *adapter) +{ + int i; + + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl |= + cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl |= + cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } + 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 tq->stopped; +} + + +static void +vmxnet3_tq_start(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = false; + netif_start_subqueue(adapter->netdev, tq - adapter->tx_queue); +} + + +static void +vmxnet3_tq_wake(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = false; + netif_wake_subqueue(adapter->netdev, (tq - adapter->tx_queue)); +} + + +static void +vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) +{ + tq->stopped = true; + tq->num_stop++; + netif_stop_subqueue(adapter->netdev, (tq - adapter->tx_queue)); +} + +/* Check if capability is supported by UPT device or + * UPT is even requested + */ +bool +vmxnet3_check_ptcapability(u32 cap_supported, u32 cap) +{ + if (cap_supported & (1UL << VMXNET3_DCR_ERROR) || + cap_supported & (1UL << cap)) { + return true; + } + + return false; +} + + +/* + * Check the link state. This may start or stop the tx queue. + */ +static void +vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) +{ + u32 ret; + int i; + unsigned long flags; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_LINK); + ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + adapter->link_speed = ret >> 16; + if (ret & 1) { /* Link is up. */ + netdev_info(adapter->netdev, "NIC Link is Up %d Mbps\n", + adapter->link_speed); + netif_carrier_on(adapter->netdev); + + if (affectTxQueue) { + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_start(&adapter->tx_queue[i], + adapter); + } + } else { + netdev_info(adapter->netdev, "NIC Link is Down\n"); + netif_carrier_off(adapter->netdev); + + if (affectTxQueue) { + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_stop(&adapter->tx_queue[i], adapter); + } + } +} + +static void +vmxnet3_process_events(struct vmxnet3_adapter *adapter) +{ + int i; + unsigned long flags; + u32 events = le32_to_cpu(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, true); + + /* Check if there is an error on xmit/recv queues */ + if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_QUEUE_STATUS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tqd_start[i].status.stopped) + dev_err(&adapter->netdev->dev, + "%s: tq[%d] error 0x%x\n", + adapter->netdev->name, i, le32_to_cpu( + adapter->tqd_start[i].status.error)); + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rqd_start[i].status.stopped) + dev_err(&adapter->netdev->dev, + "%s: rq[%d] error 0x%x\n", + adapter->netdev->name, i, + adapter->rqd_start[i].status.error); + + schedule_work(&adapter->work); + } +} + +#ifdef __BIG_ENDIAN_BITFIELD +/* + * The device expects the bitfields in shared structures to be written in + * little endian. When CPU is big endian, the following routines are used to + * correctly read and write into ABI. + * The general technique used here is : double word bitfields are defined in + * opposite order for big endian architecture. Then before reading them in + * driver the complete double word is translated using le32_to_cpu. Similarly + * After the driver writes into bitfields, cpu_to_le32 is used to translate the + * double words into required format. + * In order to avoid touching bits in shared structure more than once, temporary + * descriptors are used. These are passed as srcDesc to following functions. + */ +static void vmxnet3_RxDescToCPU(const struct Vmxnet3_RxDesc *srcDesc, + struct Vmxnet3_RxDesc *dstDesc) +{ + u32 *src = (u32 *)srcDesc + 2; + u32 *dst = (u32 *)dstDesc + 2; + dstDesc->addr = le64_to_cpu(srcDesc->addr); + *dst = le32_to_cpu(*src); + dstDesc->ext1 = le32_to_cpu(srcDesc->ext1); +} + +static void vmxnet3_TxDescToLe(const struct Vmxnet3_TxDesc *srcDesc, + struct Vmxnet3_TxDesc *dstDesc) +{ + int i; + u32 *src = (u32 *)(srcDesc + 1); + u32 *dst = (u32 *)(dstDesc + 1); + + /* Working backwards so that the gen bit is set at the end. */ + for (i = 2; i > 0; i--) { + src--; + dst--; + *dst = cpu_to_le32(*src); + } +} + + +static void vmxnet3_RxCompToCPU(const struct Vmxnet3_RxCompDesc *srcDesc, + struct Vmxnet3_RxCompDesc *dstDesc) +{ + int i = 0; + u32 *src = (u32 *)srcDesc; + u32 *dst = (u32 *)dstDesc; + for (i = 0; i < sizeof(struct Vmxnet3_RxCompDesc) / sizeof(u32); i++) { + *dst = le32_to_cpu(*src); + src++; + dst++; + } +} + + +/* Used to read bitfield values from double words. */ +static u32 get_bitfield32(const __le32 *bitfield, u32 pos, u32 size) +{ + u32 temp = le32_to_cpu(*bitfield); + u32 mask = ((1 << size) - 1) << pos; + temp &= mask; + temp >>= pos; + return temp; +} + + + +#endif /* __BIG_ENDIAN_BITFIELD */ + +#ifdef __BIG_ENDIAN_BITFIELD + +# define VMXNET3_TXDESC_GET_GEN(txdesc) get_bitfield32(((const __le32 *) \ + txdesc) + VMXNET3_TXD_GEN_DWORD_SHIFT, \ + VMXNET3_TXD_GEN_SHIFT, VMXNET3_TXD_GEN_SIZE) +# define VMXNET3_TXDESC_GET_EOP(txdesc) get_bitfield32(((const __le32 *) \ + txdesc) + VMXNET3_TXD_EOP_DWORD_SHIFT, \ + VMXNET3_TXD_EOP_SHIFT, VMXNET3_TXD_EOP_SIZE) +# define VMXNET3_TCD_GET_GEN(tcd) get_bitfield32(((const __le32 *)tcd) + \ + VMXNET3_TCD_GEN_DWORD_SHIFT, VMXNET3_TCD_GEN_SHIFT, \ + VMXNET3_TCD_GEN_SIZE) +# define VMXNET3_TCD_GET_TXIDX(tcd) get_bitfield32((const __le32 *)tcd, \ + VMXNET3_TCD_TXIDX_SHIFT, VMXNET3_TCD_TXIDX_SIZE) +# define vmxnet3_getRxComp(dstrcd, rcd, tmp) do { \ + (dstrcd) = (tmp); \ + vmxnet3_RxCompToCPU((rcd), (tmp)); \ + } while (0) +# define vmxnet3_getRxDesc(dstrxd, rxd, tmp) do { \ + (dstrxd) = (tmp); \ + vmxnet3_RxDescToCPU((rxd), (tmp)); \ + } while (0) + +#else + +# define VMXNET3_TXDESC_GET_GEN(txdesc) ((txdesc)->gen) +# define VMXNET3_TXDESC_GET_EOP(txdesc) ((txdesc)->eop) +# define VMXNET3_TCD_GET_GEN(tcd) ((tcd)->gen) +# define VMXNET3_TCD_GET_TXIDX(tcd) ((tcd)->txdIdx) +# define vmxnet3_getRxComp(dstrcd, rcd, tmp) (dstrcd) = (rcd) +# define vmxnet3_getRxDesc(dstrxd, rxd, tmp) (dstrxd) = (rxd) + +#endif /* __BIG_ENDIAN_BITFIELD */ + + +static void +vmxnet3_unmap_tx_buf(struct vmxnet3_tx_buf_info *tbi, + struct pci_dev *pdev) +{ + u32 map_type = tbi->map_type; + + if (map_type & VMXNET3_MAP_SINGLE) + dma_unmap_single(&pdev->dev, tbi->dma_addr, tbi->len, + DMA_TO_DEVICE); + else if (map_type & VMXNET3_MAP_PAGE) + dma_unmap_page(&pdev->dev, tbi->dma_addr, tbi->len, + DMA_TO_DEVICE); + else + BUG_ON(map_type & ~VMXNET3_MAP_XDP); + + 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 xdp_frame_bulk *bq) +{ + struct vmxnet3_tx_buf_info *tbi; + int entries = 0; + u32 map_type; + + /* no out of order completion */ + BUG_ON(tq->buf_info[eop_idx].sop_idx != tq->tx_ring.next2comp); + BUG_ON(VMXNET3_TXDESC_GET_EOP(&(tq->tx_ring.base[eop_idx].txd)) != 1); + + tbi = &tq->buf_info[eop_idx]; + BUG_ON(!tbi->skb); + map_type = tbi->map_type; + 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++; + } + + if (map_type & VMXNET3_MAP_XDP) + xdp_return_frame_bulk(tbi->xdpf, bq); + else + dev_kfree_skb_any(tbi->skb); + + /* xdpf and skb are in an anonymous union. */ + tbi->skb = NULL; + + return entries; +} + + +static int +vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + union Vmxnet3_GenericDesc *gdesc; + struct xdp_frame_bulk bq; + int completed = 0; + + xdp_frame_bulk_init(&bq); + rcu_read_lock(); + + gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; + while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) { + /* Prevent any &gdesc->tcd field from being (speculatively) + * read before (&gdesc->tcd)->gen is read. + */ + dma_rmb(); + + completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX( + &gdesc->tcd), tq, adapter->pdev, + adapter, &bq); + + vmxnet3_comp_ring_adv_next2proc(&tq->comp_ring); + gdesc = tq->comp_ring.base + tq->comp_ring.next2proc; + } + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); + + 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) +{ + struct xdp_frame_bulk bq; + u32 map_type; + int i; + + xdp_frame_bulk_init(&bq); + rcu_read_lock(); + + while (tq->tx_ring.next2comp != tq->tx_ring.next2fill) { + struct vmxnet3_tx_buf_info *tbi; + + tbi = tq->buf_info + tq->tx_ring.next2comp; + map_type = tbi->map_type; + + vmxnet3_unmap_tx_buf(tbi, adapter->pdev); + if (tbi->skb) { + if (map_type & VMXNET3_MAP_XDP) + xdp_return_frame_bulk(tbi->xdpf, &bq); + else + dev_kfree_skb_any(tbi->skb); + tbi->skb = NULL; + } + vmxnet3_cmd_ring_adv_next2comp(&tq->tx_ring); + } + + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); + + /* sanity check, verify all buffers are indeed unmapped */ + for (i = 0; i < tq->tx_ring.size; i++) + BUG_ON(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; +} + + +static void +vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter) +{ + if (tq->tx_ring.base) { + dma_free_coherent(&adapter->pdev->dev, 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) { + dma_free_coherent(&adapter->pdev->dev, + tq->data_ring.size * tq->txdata_desc_size, + tq->data_ring.base, tq->data_ring.basePA); + tq->data_ring.base = NULL; + } + if (tq->comp_ring.base) { + dma_free_coherent(&adapter->pdev->dev, 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; +} + + +/* Destroy all tx queues */ +void +vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_destroy(&adapter->tx_queue[i], adapter); +} + + +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 * tq->txdata_desc_size); + + /* 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 = dma_alloc_coherent(&adapter->pdev->dev, + tq->tx_ring.size * sizeof(struct Vmxnet3_TxDesc), + &tq->tx_ring.basePA, GFP_KERNEL); + if (!tq->tx_ring.base) { + netdev_err(adapter->netdev, "failed to allocate tx ring\n"); + goto err; + } + + tq->data_ring.base = dma_alloc_coherent(&adapter->pdev->dev, + tq->data_ring.size * tq->txdata_desc_size, + &tq->data_ring.basePA, GFP_KERNEL); + if (!tq->data_ring.base) { + netdev_err(adapter->netdev, "failed to allocate tx data ring\n"); + goto err; + } + + tq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, + tq->comp_ring.size * sizeof(struct Vmxnet3_TxCompDesc), + &tq->comp_ring.basePA, GFP_KERNEL); + if (!tq->comp_ring.base) { + netdev_err(adapter->netdev, "failed to allocate tx comp ring\n"); + goto err; + } + + tq->buf_info = kcalloc_node(tq->tx_ring.size, sizeof(tq->buf_info[0]), + GFP_KERNEL, + dev_to_node(&adapter->pdev->dev)); + if (!tq->buf_info) + goto err; + + return 0; + +err: + vmxnet3_tq_destroy(tq, adapter); + return -ENOMEM; +} + +static void +vmxnet3_tq_cleanup_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_cleanup(&adapter->tx_queue[i], adapter); +} + +/* + * starting from ring->next2fill, allocate rx buffers for the given ring + * of the rx queue and update the rx desc. stop after @num_to_alloc buffers + * are allocated or allocation fails + */ + +static int +vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, + int num_to_alloc, struct vmxnet3_adapter *adapter) +{ + int num_allocated = 0; + struct vmxnet3_rx_buf_info *rbi_base = rq->buf_info[ring_idx]; + struct vmxnet3_cmd_ring *ring = &rq->rx_ring[ring_idx]; + u32 val; + + while (num_allocated <= num_to_alloc) { + struct vmxnet3_rx_buf_info *rbi; + union Vmxnet3_GenericDesc *gd; + + rbi = rbi_base + ring->next2fill; + gd = ring->base + ring->next2fill; + rbi->comp_state = VMXNET3_RXD_COMP_PENDING; + + if (rbi->buf_type == VMXNET3_RX_BUF_XDP) { + void *data = vmxnet3_pp_get_buff(rq->page_pool, + &rbi->dma_addr, + GFP_KERNEL); + if (!data) { + rq->stats.rx_buf_alloc_failure++; + break; + } + rbi->page = virt_to_page(data); + val = VMXNET3_RXD_BTYPE_HEAD << VMXNET3_RXD_BTYPE_SHIFT; + } else if (rbi->buf_type == VMXNET3_RX_BUF_SKB) { + if (rbi->skb == NULL) { + rbi->skb = __netdev_alloc_skb_ip_align(adapter->netdev, + rbi->len, + GFP_KERNEL); + if (unlikely(rbi->skb == NULL)) { + rq->stats.rx_buf_alloc_failure++; + break; + } + + rbi->dma_addr = dma_map_single( + &adapter->pdev->dev, + rbi->skb->data, rbi->len, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + rbi->dma_addr)) { + dev_kfree_skb_any(rbi->skb); + rbi->skb = NULL; + rq->stats.rx_buf_alloc_failure++; + break; + } + } else { + /* rx buffer skipped by the device */ + } + val = VMXNET3_RXD_BTYPE_HEAD << VMXNET3_RXD_BTYPE_SHIFT; + } else { + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_PAGE || + rbi->len != PAGE_SIZE); + + if (rbi->page == NULL) { + rbi->page = alloc_page(GFP_ATOMIC); + if (unlikely(rbi->page == NULL)) { + rq->stats.rx_buf_alloc_failure++; + break; + } + rbi->dma_addr = dma_map_page( + &adapter->pdev->dev, + rbi->page, 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + rbi->dma_addr)) { + put_page(rbi->page); + rbi->page = NULL; + rq->stats.rx_buf_alloc_failure++; + break; + } + } else { + /* rx buffers skipped by the device */ + } + val = VMXNET3_RXD_BTYPE_BODY << VMXNET3_RXD_BTYPE_SHIFT; + } + + gd->rxd.addr = cpu_to_le64(rbi->dma_addr); + gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT) + | val | rbi->len); + + /* Fill the last buffer but dont mark it ready, or else the + * device will think that the queue is full */ + if (num_allocated == num_to_alloc) { + rbi->comp_state = VMXNET3_RXD_COMP_DONE; + break; + } + + gd->dword[2] |= cpu_to_le32(ring->gen << VMXNET3_RXD_GEN_SHIFT); + num_allocated++; + vmxnet3_cmd_ring_adv_next2fill(ring); + } + + netdev_dbg(adapter->netdev, + "alloc_rx_buf: %d allocated, next2fill %u, next2comp %u\n", + num_allocated, ring->next2fill, ring->next2comp); + + /* so that the device can distinguish a full ring and an empty ring */ + BUG_ON(num_allocated != 0 && ring->next2fill == ring->next2comp); + + return num_allocated; +} + + +static void +vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_buf_info *rbi) +{ + skb_frag_t *frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; + + BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); + + skb_frag_fill_page_desc(frag, rbi->page, 0, rcd->len); + skb->data_len += rcd->len; + skb->truesize += PAGE_SIZE; + skb_shinfo(skb)->nr_frags++; +} + + +static int +vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_tx_queue *tq, struct pci_dev *pdev, + struct vmxnet3_adapter *adapter) +{ + u32 dw2, len; + unsigned long buf_offset; + int i; + union Vmxnet3_GenericDesc *gdesc; + struct vmxnet3_tx_buf_info *tbi = NULL; + + BUG_ON(ctx->copy_size > skb_headlen(skb)); + + /* use the previous gen bit for the SOP desc */ + dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT; + + ctx->sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill; + gdesc = ctx->sop_txd; /* both loops below can be skipped */ + + /* no need to map the buffer if headers are copied */ + if (ctx->copy_size) { + ctx->sop_txd->txd.addr = cpu_to_le64(tq->data_ring.basePA + + tq->tx_ring.next2fill * + tq->txdata_desc_size); + ctx->sop_txd->dword[2] = cpu_to_le32(dw2 | ctx->copy_size); + ctx->sop_txd->dword[3] = 0; + + tbi = tq->buf_info + tq->tx_ring.next2fill; + tbi->map_type = VMXNET3_MAP_NONE; + + netdev_dbg(adapter->netdev, + "txd[%u]: 0x%Lx 0x%x 0x%x\n", + tq->tx_ring.next2fill, + le64_to_cpu(ctx->sop_txd->txd.addr), + ctx->sop_txd->dword[2], ctx->sop_txd->dword[3]); + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + + /* use the right gen for non-SOP desc */ + dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT; + } + + /* linear part can use multiple tx desc if it's big */ + len = skb_headlen(skb) - ctx->copy_size; + buf_offset = ctx->copy_size; + while (len) { + u32 buf_size; + + if (len < VMXNET3_MAX_TX_BUF_SIZE) { + buf_size = len; + dw2 |= len; + } else { + buf_size = VMXNET3_MAX_TX_BUF_SIZE; + /* spec says that for TxDesc.len, 0 == 2^14 */ + } + + tbi = tq->buf_info + tq->tx_ring.next2fill; + tbi->map_type = VMXNET3_MAP_SINGLE; + tbi->dma_addr = dma_map_single(&adapter->pdev->dev, + skb->data + buf_offset, buf_size, + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) + return -EFAULT; + + tbi->len = buf_size; + + gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; + BUG_ON(gdesc->txd.gen == tq->tx_ring.gen); + + gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); + gdesc->dword[2] = cpu_to_le32(dw2); + gdesc->dword[3] = 0; + + netdev_dbg(adapter->netdev, + "txd[%u]: 0x%Lx 0x%x 0x%x\n", + tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr), + le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]); + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT; + + len -= buf_size; + buf_offset += buf_size; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + u32 buf_size; + + buf_offset = 0; + len = skb_frag_size(frag); + while (len) { + tbi = tq->buf_info + tq->tx_ring.next2fill; + if (len < VMXNET3_MAX_TX_BUF_SIZE) { + buf_size = len; + dw2 |= len; + } else { + buf_size = VMXNET3_MAX_TX_BUF_SIZE; + /* spec says that for TxDesc.len, 0 == 2^14 */ + } + tbi->map_type = VMXNET3_MAP_PAGE; + tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag, + buf_offset, buf_size, + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) + return -EFAULT; + + tbi->len = buf_size; + + gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; + BUG_ON(gdesc->txd.gen == tq->tx_ring.gen); + + gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); + gdesc->dword[2] = cpu_to_le32(dw2); + gdesc->dword[3] = 0; + + netdev_dbg(adapter->netdev, + "txd[%u]: 0x%llx %u %u\n", + tq->tx_ring.next2fill, le64_to_cpu(gdesc->txd.addr), + le32_to_cpu(gdesc->dword[2]), gdesc->dword[3]); + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + dw2 = tq->tx_ring.gen << VMXNET3_TXD_GEN_SHIFT; + + len -= buf_size; + buf_offset += buf_size; + } + } + + ctx->eop_txd = gdesc; + + /* set the last buf_info for the pkt */ + tbi->skb = skb; + tbi->sop_idx = ctx->sop_txd - tq->tx_ring.base; + + return 0; +} + + +/* Init all tx queues */ +static void +vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_init(&adapter->tx_queue[i], adapter); +} + + +/* + * parse relevant protocol headers: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * Returns: + * -1: error happens during parsing + * 0: protocol headers parsed, but too big to be copied + * 1: protocol headers parsed and copied + * + * Other effects: + * 1. related *ctx fields are updated. + * 2. ctx->copy_size is # of bytes copied + * 3. the portion to be copied is guaranteed to be in the linear part + * + */ +static int +vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + u8 protocol = 0; + + if (ctx->mss) { /* TSO */ + if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation) { + ctx->l4_offset = skb_inner_transport_offset(skb); + ctx->l4_hdr_size = inner_tcp_hdrlen(skb); + ctx->copy_size = ctx->l4_offset + ctx->l4_hdr_size; + } else { + ctx->l4_offset = skb_transport_offset(skb); + ctx->l4_hdr_size = tcp_hdrlen(skb); + ctx->copy_size = ctx->l4_offset + ctx->l4_hdr_size; + } + } else { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* For encap packets, skb_checksum_start_offset refers + * to inner L4 offset. Thus, below works for encap as + * well as non-encap case + */ + ctx->l4_offset = skb_checksum_start_offset(skb); + + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation) { + struct iphdr *iph = inner_ip_hdr(skb); + + if (iph->version == 4) { + protocol = iph->protocol; + } else { + const struct ipv6hdr *ipv6h; + + ipv6h = inner_ipv6_hdr(skb); + protocol = ipv6h->nexthdr; + } + } else { + if (ctx->ipv4) { + const struct iphdr *iph = ip_hdr(skb); + + protocol = iph->protocol; + } else if (ctx->ipv6) { + const struct ipv6hdr *ipv6h; + + ipv6h = ipv6_hdr(skb); + protocol = ipv6h->nexthdr; + } + } + + switch (protocol) { + case IPPROTO_TCP: + ctx->l4_hdr_size = skb->encapsulation ? inner_tcp_hdrlen(skb) : + tcp_hdrlen(skb); + break; + case IPPROTO_UDP: + ctx->l4_hdr_size = sizeof(struct udphdr); + break; + default: + ctx->l4_hdr_size = 0; + break; + } + + ctx->copy_size = min(ctx->l4_offset + + ctx->l4_hdr_size, skb->len); + } else { + ctx->l4_offset = 0; + ctx->l4_hdr_size = 0; + /* copy as much as allowed */ + ctx->copy_size = min_t(unsigned int, + tq->txdata_desc_size, + skb_headlen(skb)); + } + + if (skb->len <= VMXNET3_HDR_COPY_SIZE) + ctx->copy_size = skb->len; + + /* make sure headers are accessible directly */ + if (unlikely(!pskb_may_pull(skb, ctx->copy_size))) + goto err; + } + + if (unlikely(ctx->copy_size > tq->txdata_desc_size)) { + tq->stats.oversized_hdr++; + ctx->copy_size = 0; + return 0; + } + + return 1; +err: + return -1; +} + +/* + * copy relevant protocol headers to the transmit ring: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * + * Note that this requires that vmxnet3_parse_hdr be called first to set the + * appropriate bits in ctx first + */ +static void +vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_TxDataDesc *tdd; + + tdd = (struct Vmxnet3_TxDataDesc *)((u8 *)tq->data_ring.base + + tq->tx_ring.next2fill * + tq->txdata_desc_size); + + memcpy(tdd->data, skb->data, ctx->copy_size); + netdev_dbg(adapter->netdev, + "copy %u bytes to dataRing[%u]\n", + ctx->copy_size, tq->tx_ring.next2fill); +} + + +static void +vmxnet3_prepare_inner_tso(struct sk_buff *skb, + struct vmxnet3_tx_ctx *ctx) +{ + struct tcphdr *tcph = inner_tcp_hdr(skb); + struct iphdr *iph = inner_ip_hdr(skb); + + if (iph->version == 4) { + iph->check = 0; + tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0, + IPPROTO_TCP, 0); + } else { + struct ipv6hdr *iph = inner_ipv6_hdr(skb); + + tcph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, 0, + IPPROTO_TCP, 0); + } +} + +static void +vmxnet3_prepare_tso(struct sk_buff *skb, + struct vmxnet3_tx_ctx *ctx) +{ + struct tcphdr *tcph = tcp_hdr(skb); + + if (ctx->ipv4) { + struct iphdr *iph = ip_hdr(skb); + + iph->check = 0; + tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0, + IPPROTO_TCP, 0); + } else if (ctx->ipv6) { + tcp_v6_gso_csum_prep(skb); + } +} + +static int txd_estimate(const struct sk_buff *skb) +{ + int count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1; + int i; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + count += VMXNET3_TXD_NEEDED(skb_frag_size(frag)); + } + return count; +} + +/* + * Transmits a pkt thru a given tq + * Returns: + * NETDEV_TX_OK: descriptors are setup successfully + * NETDEV_TX_OK: error occurred, the pkt is dropped + * NETDEV_TX_BUSY: tx ring is full, queue is stopped + * + * Side-effects: + * 1. tx ring may be changed + * 2. tq stats may be updated accordingly + * 3. shared->txNumDeferred may be updated + */ + +static int +vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_adapter *adapter, struct net_device *netdev) +{ + int ret; + u32 count; + int num_pkts; + int tx_num_deferred; + unsigned long flags; + struct vmxnet3_tx_ctx ctx; + union Vmxnet3_GenericDesc *gdesc; +#ifdef __BIG_ENDIAN_BITFIELD + /* Use temporary descriptor to avoid touching bits multiple times */ + union Vmxnet3_GenericDesc tempTxDesc; +#endif + + count = txd_estimate(skb); + + ctx.ipv4 = (vlan_get_protocol(skb) == cpu_to_be16(ETH_P_IP)); + ctx.ipv6 = (vlan_get_protocol(skb) == cpu_to_be16(ETH_P_IPV6)); + + ctx.mss = skb_shinfo(skb)->gso_size; + if (ctx.mss) { + if (skb_header_cloned(skb)) { + if (unlikely(pskb_expand_head(skb, 0, 0, + GFP_ATOMIC) != 0)) { + tq->stats.drop_tso++; + goto drop_pkt; + } + tq->stats.copy_skb_header++; + } + if (unlikely(count > VMXNET3_MAX_TSO_TXD_PER_PKT)) { + /* tso pkts must not use more than + * VMXNET3_MAX_TSO_TXD_PER_PKT entries + */ + if (skb_linearize(skb) != 0) { + tq->stats.drop_too_many_frags++; + goto drop_pkt; + } + tq->stats.linearized++; + + /* recalculate the # of descriptors to use */ + count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1; + if (unlikely(count > VMXNET3_MAX_TSO_TXD_PER_PKT)) { + tq->stats.drop_too_many_frags++; + goto drop_pkt; + } + } + if (skb->encapsulation) { + vmxnet3_prepare_inner_tso(skb, &ctx); + } else { + vmxnet3_prepare_tso(skb, &ctx); + } + } else { + if (unlikely(count > VMXNET3_MAX_TXD_PER_PKT)) { + + /* non-tso pkts must not use more than + * VMXNET3_MAX_TXD_PER_PKT entries + */ + if (skb_linearize(skb) != 0) { + tq->stats.drop_too_many_frags++; + goto drop_pkt; + } + tq->stats.linearized++; + + /* recalculate the # of descriptors to use */ + count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1; + } + } + + ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter); + if (ret >= 0) { + BUG_ON(ret <= 0 && ctx.copy_size != 0); + /* hdrs parsed, check against other limits */ + if (ctx.mss) { + if (unlikely(ctx.l4_offset + ctx.l4_hdr_size > + VMXNET3_MAX_TX_BUF_SIZE)) { + tq->stats.drop_oversized_hdr++; + goto drop_pkt; + } + } else { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (unlikely(ctx.l4_offset + + skb->csum_offset > + VMXNET3_MAX_CSUM_OFFSET)) { + tq->stats.drop_oversized_hdr++; + goto drop_pkt; + } + } + } + } else { + tq->stats.drop_hdr_inspect_err++; + goto drop_pkt; + } + + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + + vmxnet3_copy_hdr(skb, tq, &ctx, adapter); + + /* fill tx descs related to addr & len */ + if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter)) + goto unlock_drop_pkt; + + /* setup the EOP desc */ + ctx.eop_txd->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP); + + /* setup the SOP desc */ +#ifdef __BIG_ENDIAN_BITFIELD + gdesc = &tempTxDesc; + gdesc->dword[2] = ctx.sop_txd->dword[2]; + gdesc->dword[3] = ctx.sop_txd->dword[3]; +#else + gdesc = ctx.sop_txd; +#endif + tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred); + if (ctx.mss) { + if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation) { + gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; + if (VMXNET3_VERSION_GE_7(adapter)) { + gdesc->txd.om = VMXNET3_OM_TSO; + gdesc->txd.ext1 = 1; + } else { + gdesc->txd.om = VMXNET3_OM_ENCAP; + } + gdesc->txd.msscof = ctx.mss; + + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) + gdesc->txd.oco = 1; + } else { + gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; + gdesc->txd.om = VMXNET3_OM_TSO; + gdesc->txd.msscof = ctx.mss; + } + num_pkts = (skb->len - gdesc->txd.hlen + ctx.mss - 1) / ctx.mss; + } else { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation) { + gdesc->txd.hlen = ctx.l4_offset + + ctx.l4_hdr_size; + if (VMXNET3_VERSION_GE_7(adapter)) { + gdesc->txd.om = VMXNET3_OM_CSUM; + gdesc->txd.msscof = ctx.l4_offset + + skb->csum_offset; + gdesc->txd.ext1 = 1; + } else { + gdesc->txd.om = VMXNET3_OM_ENCAP; + gdesc->txd.msscof = 0; /* Reserved */ + } + } else { + gdesc->txd.hlen = ctx.l4_offset; + gdesc->txd.om = VMXNET3_OM_CSUM; + gdesc->txd.msscof = ctx.l4_offset + + skb->csum_offset; + } + } else { + gdesc->txd.om = 0; + gdesc->txd.msscof = 0; + } + num_pkts = 1; + } + le32_add_cpu(&tq->shared->txNumDeferred, num_pkts); + tx_num_deferred += num_pkts; + + if (skb_vlan_tag_present(skb)) { + gdesc->txd.ti = 1; + gdesc->txd.tci = skb_vlan_tag_get(skb); + } + + /* Ensure that the write to (&gdesc->txd)->gen will be observed after + * all other writes to &gdesc->txd. + */ + dma_wmb(); + + /* finally flips the GEN bit of the SOP desc. */ + gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^ + VMXNET3_TXD_GEN); +#ifdef __BIG_ENDIAN_BITFIELD + /* Finished updating in bitfields of Tx Desc, so write them in original + * place. + */ + vmxnet3_TxDescToLe((struct Vmxnet3_TxDesc *)gdesc, + (struct Vmxnet3_TxDesc *)ctx.sop_txd); + gdesc = ctx.sop_txd; +#endif + netdev_dbg(adapter->netdev, + "txd[%u]: SOP 0x%Lx 0x%x 0x%x\n", + (u32)(ctx.sop_txd - + tq->tx_ring.base), le64_to_cpu(gdesc->txd.addr), + le32_to_cpu(gdesc->dword[2]), le32_to_cpu(gdesc->dword[3])); + + spin_unlock_irqrestore(&tq->tx_lock, flags); + + if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) { + tq->shared->txNumDeferred = 0; + VMXNET3_WRITE_BAR0_REG(adapter, + adapter->tx_prod_offset + tq->qid * 8, + tq->tx_ring.next2fill); + } + + return NETDEV_TX_OK; + +unlock_drop_pkt: + spin_unlock_irqrestore(&tq->tx_lock, flags); +drop_pkt: + tq->stats.drop_total++; + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; +} + +static int +vmxnet3_create_pp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, int size) +{ + bool xdp_prog = vmxnet3_xdp_enabled(adapter); + const struct page_pool_params pp_params = { + .order = 0, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = size, + .nid = NUMA_NO_NODE, + .dev = &adapter->pdev->dev, + .offset = VMXNET3_XDP_RX_OFFSET, + .max_len = VMXNET3_XDP_MAX_FRSIZE, + .dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE, + }; + struct page_pool *pp; + int err; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) + return PTR_ERR(pp); + + err = xdp_rxq_info_reg(&rq->xdp_rxq, adapter->netdev, rq->qid, + rq->napi.napi_id); + if (err < 0) + goto err_free_pp; + + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, pp); + if (err) + goto err_unregister_rxq; + + rq->page_pool = pp; + + return 0; + +err_unregister_rxq: + xdp_rxq_info_unreg(&rq->xdp_rxq); +err_free_pp: + page_pool_destroy(pp); + + return err; +} + +void * +vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr, + gfp_t gfp_mask) +{ + struct page *page; + + page = page_pool_alloc_pages(pp, gfp_mask | __GFP_NOWARN); + if (unlikely(!page)) + return NULL; + + *dma_addr = page_pool_get_dma_addr(page) + pp->p.offset; + + return page_address(page); +} + +static netdev_tx_t +vmxnet3_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + BUG_ON(skb->queue_mapping > adapter->num_tx_queues); + return vmxnet3_tq_xmit(skb, + &adapter->tx_queue[skb->queue_mapping], + adapter, netdev); +} + + +static void +vmxnet3_rx_csum(struct vmxnet3_adapter *adapter, + struct sk_buff *skb, + union Vmxnet3_GenericDesc *gdesc) +{ + if (!gdesc->rcd.cnc && adapter->netdev->features & NETIF_F_RXCSUM) { + if (gdesc->rcd.v4 && + (le32_to_cpu(gdesc->dword[3]) & + VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + if ((le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) { + skb->csum_level = 1; + } + WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) && + !(le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); + WARN_ON_ONCE(gdesc->rcd.frg && + !(le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); + } else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) & + (1 << VMXNET3_RCD_TUC_SHIFT))) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + if ((le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) { + skb->csum_level = 1; + } + WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) && + !(le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); + WARN_ON_ONCE(gdesc->rcd.frg && + !(le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))); + } else { + if (gdesc->rcd.csum) { + skb->csum = htons(gdesc->rcd.csum); + skb->ip_summed = CHECKSUM_PARTIAL; + } else { + skb_checksum_none_assert(skb); + } + } + } else { + skb_checksum_none_assert(skb); + } +} + + +static void +vmxnet3_rx_error(struct vmxnet3_rx_queue *rq, struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_ctx *ctx, struct vmxnet3_adapter *adapter) +{ + rq->stats.drop_err++; + if (!rcd->fcs) + rq->stats.drop_fcs++; + + rq->stats.drop_total++; + + /* + * We do not unmap and chain the rx buffer to the skb. + * We basically pretend this buffer is not used and will be recycled + * by vmxnet3_rq_alloc_rx_buf() + */ + + /* + * ctx->skb may be NULL if this is the first and the only one + * desc for the pkt + */ + if (ctx->skb) + dev_kfree_skb_irq(ctx->skb); + + ctx->skb = NULL; +} + + +static u32 +vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb, + union Vmxnet3_GenericDesc *gdesc) +{ + u32 hlen, maplen; + union { + void *ptr; + struct ethhdr *eth; + struct vlan_ethhdr *veth; + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + struct tcphdr *tcp; + } hdr; + BUG_ON(gdesc->rcd.tcp == 0); + + maplen = skb_headlen(skb); + if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen)) + return 0; + + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) + hlen = sizeof(struct vlan_ethhdr); + else + hlen = sizeof(struct ethhdr); + + hdr.eth = eth_hdr(skb); + if (gdesc->rcd.v4) { + BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP) && + hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IP)); + hdr.ptr += hlen; + BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP); + hlen = hdr.ipv4->ihl << 2; + hdr.ptr += hdr.ipv4->ihl << 2; + } else if (gdesc->rcd.v6) { + BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6) && + hdr.veth->h_vlan_encapsulated_proto != htons(ETH_P_IPV6)); + hdr.ptr += hlen; + /* Use an estimated value, since we also need to handle + * TSO case. + */ + if (hdr.ipv6->nexthdr != IPPROTO_TCP) + return sizeof(struct ipv6hdr) + sizeof(struct tcphdr); + hlen = sizeof(struct ipv6hdr); + hdr.ptr += sizeof(struct ipv6hdr); + } else { + /* Non-IP pkt, dont estimate header length */ + return 0; + } + + if (hlen + sizeof(struct tcphdr) > maplen) + return 0; + + return (hlen + (hdr.tcp->doff << 2)); +} + +static int +vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, + struct vmxnet3_adapter *adapter, int quota) +{ + u32 rxprod_reg[2] = { + adapter->rx_prod_offset, adapter->rx_prod2_offset + }; + u32 num_pkts = 0; + bool skip_page_frags = false; + bool encap_lro = false; + struct Vmxnet3_RxCompDesc *rcd; + struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; + u16 segCnt = 0, mss = 0; + int comp_offset, fill_offset; +#ifdef __BIG_ENDIAN_BITFIELD + struct Vmxnet3_RxDesc rxCmdDesc; + struct Vmxnet3_RxCompDesc rxComp; +#endif + bool need_flush = false; + + vmxnet3_getRxComp(rcd, &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, + &rxComp); + while (rcd->gen == rq->comp_ring.gen) { + struct vmxnet3_rx_buf_info *rbi; + struct sk_buff *skb, *new_skb = NULL; + struct page *new_page = NULL; + dma_addr_t new_dma_addr; + int num_to_alloc; + struct Vmxnet3_RxDesc *rxd; + u32 idx, ring_idx; + struct vmxnet3_cmd_ring *ring = NULL; + if (num_pkts >= quota) { + /* we may stop even before we see the EOP desc of + * the current pkt + */ + break; + } + + /* Prevent any rcd field from being (speculatively) read before + * rcd->gen is read. + */ + dma_rmb(); + + BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 && + rcd->rqID != rq->dataRingQid); + idx = rcd->rxdIdx; + ring_idx = VMXNET3_GET_RING_IDX(adapter, rcd->rqID); + ring = rq->rx_ring + ring_idx; + vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd, + &rxCmdDesc); + rbi = rq->buf_info[ring_idx] + idx; + + BUG_ON(rxd->addr != rbi->dma_addr || + rxd->len != rbi->len); + + if (unlikely(rcd->eop && rcd->err)) { + vmxnet3_rx_error(rq, rcd, ctx, adapter); + goto rcd_done; + } + + if (rcd->sop && rcd->eop && vmxnet3_xdp_enabled(adapter)) { + struct sk_buff *skb_xdp_pass; + int act; + + if (VMXNET3_RX_DATA_RING(adapter, rcd->rqID)) { + ctx->skb = NULL; + goto skip_xdp; /* Handle it later. */ + } + + if (rbi->buf_type != VMXNET3_RX_BUF_XDP) + goto rcd_done; + + act = vmxnet3_process_xdp(adapter, rq, rcd, rbi, rxd, + &skb_xdp_pass); + if (act == XDP_PASS) { + ctx->skb = skb_xdp_pass; + goto sop_done; + } + ctx->skb = NULL; + need_flush |= act == XDP_REDIRECT; + + goto rcd_done; + } +skip_xdp: + + if (rcd->sop) { /* first buf of the pkt */ + bool rxDataRingUsed; + u16 len; + + BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_HEAD || + (rcd->rqID != rq->qid && + rcd->rqID != rq->dataRingQid)); + + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB && + rbi->buf_type != VMXNET3_RX_BUF_XDP); + BUG_ON(ctx->skb != NULL || rbi->skb == NULL); + + if (unlikely(rcd->len == 0)) { + /* Pretend the rx buffer is skipped. */ + BUG_ON(!(rcd->sop && rcd->eop)); + netdev_dbg(adapter->netdev, + "rxRing[%u][%u] 0 length\n", + ring_idx, idx); + goto rcd_done; + } + + skip_page_frags = false; + ctx->skb = rbi->skb; + + rxDataRingUsed = + VMXNET3_RX_DATA_RING(adapter, rcd->rqID); + len = rxDataRingUsed ? rcd->len : rbi->len; + + if (rxDataRingUsed && vmxnet3_xdp_enabled(adapter)) { + struct sk_buff *skb_xdp_pass; + size_t sz; + int act; + + sz = rcd->rxdIdx * rq->data_ring.desc_size; + act = vmxnet3_process_xdp_small(adapter, rq, + &rq->data_ring.base[sz], + rcd->len, + &skb_xdp_pass); + if (act == XDP_PASS) { + ctx->skb = skb_xdp_pass; + goto sop_done; + } + need_flush |= act == XDP_REDIRECT; + + goto rcd_done; + } + new_skb = netdev_alloc_skb_ip_align(adapter->netdev, + len); + if (new_skb == NULL) { + /* Skb allocation failed, do not handover this + * skb to stack. Reuse it. Drop the existing pkt + */ + rq->stats.rx_buf_alloc_failure++; + ctx->skb = NULL; + rq->stats.drop_total++; + skip_page_frags = true; + goto rcd_done; + } + + if (rxDataRingUsed && adapter->rxdataring_enabled) { + size_t sz; + + BUG_ON(rcd->len > rq->data_ring.desc_size); + + ctx->skb = new_skb; + sz = rcd->rxdIdx * rq->data_ring.desc_size; + memcpy(new_skb->data, + &rq->data_ring.base[sz], rcd->len); + } else { + ctx->skb = rbi->skb; + + new_dma_addr = + dma_map_single(&adapter->pdev->dev, + new_skb->data, rbi->len, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + new_dma_addr)) { + dev_kfree_skb(new_skb); + /* Skb allocation failed, do not + * handover this skb to stack. Reuse + * it. Drop the existing pkt. + */ + rq->stats.rx_buf_alloc_failure++; + ctx->skb = NULL; + rq->stats.drop_total++; + skip_page_frags = true; + goto rcd_done; + } + + dma_unmap_single(&adapter->pdev->dev, + rbi->dma_addr, + rbi->len, + DMA_FROM_DEVICE); + + /* Immediate refill */ + rbi->skb = new_skb; + rbi->dma_addr = new_dma_addr; + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + } + + skb_record_rx_queue(ctx->skb, rq->qid); + skb_put(ctx->skb, rcd->len); + + if (VMXNET3_VERSION_GE_2(adapter) && + rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) { + struct Vmxnet3_RxCompDescExt *rcdlro; + union Vmxnet3_GenericDesc *gdesc; + + rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd; + gdesc = (union Vmxnet3_GenericDesc *)rcd; + + segCnt = rcdlro->segCnt; + WARN_ON_ONCE(segCnt == 0); + mss = rcdlro->mss; + if (unlikely(segCnt <= 1)) + segCnt = 0; + encap_lro = (le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)); + } else { + segCnt = 0; + } + } else { + BUG_ON(ctx->skb == NULL && !skip_page_frags); + + /* non SOP buffer must be type 1 in most cases */ + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_PAGE); + BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_BODY); + + /* If an sop buffer was dropped, skip all + * following non-sop fragments. They will be reused. + */ + if (skip_page_frags) + goto rcd_done; + + if (rcd->len) { + new_page = alloc_page(GFP_ATOMIC); + /* Replacement page frag could not be allocated. + * Reuse this page. Drop the pkt and free the + * skb which contained this page as a frag. Skip + * processing all the following non-sop frags. + */ + if (unlikely(!new_page)) { + rq->stats.rx_buf_alloc_failure++; + dev_kfree_skb(ctx->skb); + ctx->skb = NULL; + skip_page_frags = true; + goto rcd_done; + } + new_dma_addr = dma_map_page(&adapter->pdev->dev, + new_page, + 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + new_dma_addr)) { + put_page(new_page); + rq->stats.rx_buf_alloc_failure++; + dev_kfree_skb(ctx->skb); + ctx->skb = NULL; + skip_page_frags = true; + goto rcd_done; + } + + dma_unmap_page(&adapter->pdev->dev, + rbi->dma_addr, rbi->len, + DMA_FROM_DEVICE); + + vmxnet3_append_frag(ctx->skb, rcd, rbi); + + /* Immediate refill */ + rbi->page = new_page; + rbi->dma_addr = new_dma_addr; + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + } + } + + +sop_done: + skb = ctx->skb; + if (rcd->eop) { + u32 mtu = adapter->netdev->mtu; + skb->len += skb->data_len; + +#ifdef VMXNET3_RSS + if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE && + (adapter->netdev->features & NETIF_F_RXHASH)) { + enum pkt_hash_types hash_type; + + switch (rcd->rssType) { + case VMXNET3_RCD_RSS_TYPE_IPV4: + case VMXNET3_RCD_RSS_TYPE_IPV6: + hash_type = PKT_HASH_TYPE_L3; + break; + case VMXNET3_RCD_RSS_TYPE_TCPIPV4: + case VMXNET3_RCD_RSS_TYPE_TCPIPV6: + case VMXNET3_RCD_RSS_TYPE_UDPIPV4: + case VMXNET3_RCD_RSS_TYPE_UDPIPV6: + hash_type = PKT_HASH_TYPE_L4; + break; + default: + hash_type = PKT_HASH_TYPE_L3; + break; + } + skb_set_hash(skb, + le32_to_cpu(rcd->rssHash), + hash_type); + } +#endif + vmxnet3_rx_csum(adapter, skb, + (union Vmxnet3_GenericDesc *)rcd); + skb->protocol = eth_type_trans(skb, adapter->netdev); + if ((!rcd->tcp && !encap_lro) || + !(adapter->netdev->features & NETIF_F_LRO)) + goto not_lro; + + if (segCnt != 0 && mss != 0) { + skb_shinfo(skb)->gso_type = rcd->v4 ? + SKB_GSO_TCPV4 : SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_size = mss; + skb_shinfo(skb)->gso_segs = segCnt; + } else if ((segCnt != 0 || skb->len > mtu) && !encap_lro) { + u32 hlen; + + hlen = vmxnet3_get_hdr_len(adapter, skb, + (union Vmxnet3_GenericDesc *)rcd); + if (hlen == 0) + goto not_lro; + + skb_shinfo(skb)->gso_type = + rcd->v4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6; + if (segCnt != 0) { + skb_shinfo(skb)->gso_segs = segCnt; + skb_shinfo(skb)->gso_size = + DIV_ROUND_UP(skb->len - + hlen, segCnt); + } else { + skb_shinfo(skb)->gso_size = mtu - hlen; + } + } +not_lro: + if (unlikely(rcd->ts)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rcd->tci); + + /* Use GRO callback if UPT is enabled */ + if ((adapter->netdev->features & NETIF_F_LRO) && + !rq->shared->updateRxProd) + netif_receive_skb(skb); + else + napi_gro_receive(&rq->napi, skb); + + ctx->skb = NULL; + encap_lro = false; + num_pkts++; + } + +rcd_done: + /* device may have skipped some rx descs */ + ring = rq->rx_ring + ring_idx; + rbi->comp_state = VMXNET3_RXD_COMP_DONE; + + comp_offset = vmxnet3_cmd_ring_desc_avail(ring); + fill_offset = (idx > ring->next2fill ? 0 : ring->size) + + idx - ring->next2fill - 1; + if (!ring->isOutOfOrder || fill_offset >= comp_offset) + ring->next2comp = idx; + num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring); + + /* Ensure that the writes to rxd->gen bits will be observed + * after all other writes to rxd objects. + */ + dma_wmb(); + + while (num_to_alloc) { + rbi = rq->buf_info[ring_idx] + ring->next2fill; + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_OOORX_COMP))) + goto refill_buf; + if (ring_idx == 0) { + /* ring0 Type1 buffers can get skipped; re-fill them */ + if (rbi->buf_type != VMXNET3_RX_BUF_SKB) + goto refill_buf; + } + if (rbi->comp_state == VMXNET3_RXD_COMP_DONE) { +refill_buf: + vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd, + &rxCmdDesc); + WARN_ON(!rxd->addr); + + /* Recv desc is ready to be used by the device */ + rxd->gen = ring->gen; + vmxnet3_cmd_ring_adv_next2fill(ring); + rbi->comp_state = VMXNET3_RXD_COMP_PENDING; + num_to_alloc--; + } else { + /* rx completion hasn't occurred */ + ring->isOutOfOrder = 1; + break; + } + } + + if (num_to_alloc == 0) { + ring->isOutOfOrder = 0; + } + + /* if needed, update the register */ + if (unlikely(rq->shared->updateRxProd) && (ring->next2fill & 0xf) == 0) { + VMXNET3_WRITE_BAR0_REG(adapter, + rxprod_reg[ring_idx] + rq->qid * 8, + ring->next2fill); + } + + vmxnet3_comp_ring_adv_next2proc(&rq->comp_ring); + vmxnet3_getRxComp(rcd, + &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp); + } + if (need_flush) + xdp_do_flush(); + + return num_pkts; +} + + +static void +vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq, + struct vmxnet3_adapter *adapter) +{ + u32 i, ring_idx; + struct Vmxnet3_RxDesc *rxd; + + /* ring has already been cleaned up */ + if (!rq->rx_ring[0].base) + return; + + for (ring_idx = 0; ring_idx < 2; ring_idx++) { + for (i = 0; i < rq->rx_ring[ring_idx].size; i++) { + struct vmxnet3_rx_buf_info *rbi; +#ifdef __BIG_ENDIAN_BITFIELD + struct Vmxnet3_RxDesc rxDesc; +#endif + + rbi = &rq->buf_info[ring_idx][i]; + vmxnet3_getRxDesc(rxd, + &rq->rx_ring[ring_idx].base[i].rxd, &rxDesc); + + if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD && + rbi->page && rbi->buf_type == VMXNET3_RX_BUF_XDP) { + page_pool_recycle_direct(rq->page_pool, + rbi->page); + rbi->page = NULL; + } else if (rxd->btype == VMXNET3_RXD_BTYPE_HEAD && + rbi->skb) { + dma_unmap_single(&adapter->pdev->dev, rxd->addr, + rxd->len, DMA_FROM_DEVICE); + dev_kfree_skb(rbi->skb); + rbi->skb = NULL; + } else if (rxd->btype == VMXNET3_RXD_BTYPE_BODY && + rbi->page) { + dma_unmap_page(&adapter->pdev->dev, rxd->addr, + rxd->len, DMA_FROM_DEVICE); + put_page(rbi->page); + rbi->page = NULL; + } + } + + rq->rx_ring[ring_idx].gen = VMXNET3_INIT_GEN; + rq->rx_ring[ring_idx].next2fill = + rq->rx_ring[ring_idx].next2comp = 0; + } + + rq->comp_ring.gen = VMXNET3_INIT_GEN; + rq->comp_ring.next2proc = 0; +} + + +static void +vmxnet3_rq_cleanup_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_rq_cleanup(&adapter->rx_queue[i], adapter); + rcu_assign_pointer(adapter->xdp_bpf_prog, NULL); +} + + +static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, + struct vmxnet3_adapter *adapter) +{ + int i; + int j; + + /* all rx buffers must have already been freed */ + for (i = 0; i < 2; i++) { + if (rq->buf_info[i]) { + for (j = 0; j < rq->rx_ring[i].size; j++) + BUG_ON(rq->buf_info[i][j].page != NULL); + } + } + + + for (i = 0; i < 2; i++) { + if (rq->rx_ring[i].base) { + dma_free_coherent(&adapter->pdev->dev, + rq->rx_ring[i].size + * sizeof(struct Vmxnet3_RxDesc), + rq->rx_ring[i].base, + rq->rx_ring[i].basePA); + rq->rx_ring[i].base = NULL; + } + } + + if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) + xdp_rxq_info_unreg(&rq->xdp_rxq); + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + + if (rq->data_ring.base) { + dma_free_coherent(&adapter->pdev->dev, + rq->rx_ring[0].size * rq->data_ring.desc_size, + rq->data_ring.base, rq->data_ring.basePA); + rq->data_ring.base = NULL; + } + + if (rq->comp_ring.base) { + dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size + * sizeof(struct Vmxnet3_RxCompDesc), + rq->comp_ring.base, rq->comp_ring.basePA); + rq->comp_ring.base = NULL; + } + + kfree(rq->buf_info[0]); + rq->buf_info[0] = NULL; + rq->buf_info[1] = NULL; +} + +static void +vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + + if (rq->data_ring.base) { + dma_free_coherent(&adapter->pdev->dev, + (rq->rx_ring[0].size * + rq->data_ring.desc_size), + rq->data_ring.base, + rq->data_ring.basePA); + rq->data_ring.base = NULL; + rq->data_ring.desc_size = 0; + } + } +} + +static int +vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, + struct vmxnet3_adapter *adapter) +{ + int i, err; + + /* initialize buf_info */ + for (i = 0; i < rq->rx_ring[0].size; i++) { + + /* 1st buf for a pkt is skbuff or xdp page */ + if (i % adapter->rx_buf_per_pkt == 0) { + rq->buf_info[0][i].buf_type = vmxnet3_xdp_enabled(adapter) ? + VMXNET3_RX_BUF_XDP : + VMXNET3_RX_BUF_SKB; + rq->buf_info[0][i].len = adapter->skb_buf_size; + } else { /* subsequent bufs for a pkt is frag */ + rq->buf_info[0][i].buf_type = VMXNET3_RX_BUF_PAGE; + rq->buf_info[0][i].len = PAGE_SIZE; + } + } + for (i = 0; i < rq->rx_ring[1].size; i++) { + rq->buf_info[1][i].buf_type = VMXNET3_RX_BUF_PAGE; + rq->buf_info[1][i].len = PAGE_SIZE; + } + + /* reset internal state and allocate buffers for both rings */ + for (i = 0; i < 2; i++) { + rq->rx_ring[i].next2fill = rq->rx_ring[i].next2comp = 0; + + memset(rq->rx_ring[i].base, 0, rq->rx_ring[i].size * + sizeof(struct Vmxnet3_RxDesc)); + rq->rx_ring[i].gen = VMXNET3_INIT_GEN; + rq->rx_ring[i].isOutOfOrder = 0; + } + + err = vmxnet3_create_pp(adapter, rq, + rq->rx_ring[0].size + rq->rx_ring[1].size); + if (err) + return err; + + if (vmxnet3_rq_alloc_rx_buf(rq, 0, rq->rx_ring[0].size - 1, + adapter) == 0) { + xdp_rxq_info_unreg(&rq->xdp_rxq); + page_pool_destroy(rq->page_pool); + rq->page_pool = NULL; + + /* at least has 1 rx buffer for the 1st ring */ + return -ENOMEM; + } + vmxnet3_rq_alloc_rx_buf(rq, 1, rq->rx_ring[1].size - 1, adapter); + + /* reset the comp ring */ + rq->comp_ring.next2proc = 0; + memset(rq->comp_ring.base, 0, rq->comp_ring.size * + sizeof(struct Vmxnet3_RxCompDesc)); + rq->comp_ring.gen = VMXNET3_INIT_GEN; + + /* reset rxctx */ + rq->rx_ctx.skb = NULL; + + /* stats are not reset */ + return 0; +} + + +static int +vmxnet3_rq_init_all(struct vmxnet3_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = vmxnet3_rq_init(&adapter->rx_queue[i], adapter); + if (unlikely(err)) { + dev_err(&adapter->netdev->dev, "%s: failed to " + "initialize rx queue%i\n", + adapter->netdev->name, i); + break; + } + } + return err; + +} + + +static int +vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter) +{ + int i; + size_t sz; + struct vmxnet3_rx_buf_info *bi; + + for (i = 0; i < 2; i++) { + + sz = rq->rx_ring[i].size * sizeof(struct Vmxnet3_RxDesc); + rq->rx_ring[i].base = dma_alloc_coherent( + &adapter->pdev->dev, sz, + &rq->rx_ring[i].basePA, + GFP_KERNEL); + if (!rq->rx_ring[i].base) { + netdev_err(adapter->netdev, + "failed to allocate rx ring %d\n", i); + goto err; + } + } + + if ((adapter->rxdataring_enabled) && (rq->data_ring.desc_size != 0)) { + sz = rq->rx_ring[0].size * rq->data_ring.desc_size; + rq->data_ring.base = + dma_alloc_coherent(&adapter->pdev->dev, sz, + &rq->data_ring.basePA, + GFP_KERNEL); + if (!rq->data_ring.base) { + netdev_err(adapter->netdev, + "rx data ring will be disabled\n"); + adapter->rxdataring_enabled = false; + } + } else { + rq->data_ring.base = NULL; + rq->data_ring.desc_size = 0; + } + + sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc); + rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz, + &rq->comp_ring.basePA, + GFP_KERNEL); + if (!rq->comp_ring.base) { + netdev_err(adapter->netdev, "failed to allocate rx comp ring\n"); + goto err; + } + + bi = kcalloc_node(rq->rx_ring[0].size + rq->rx_ring[1].size, + sizeof(rq->buf_info[0][0]), GFP_KERNEL, + dev_to_node(&adapter->pdev->dev)); + if (!bi) + goto err; + + rq->buf_info[0] = bi; + rq->buf_info[1] = bi + rq->rx_ring[0].size; + + return 0; + +err: + vmxnet3_rq_destroy(rq, adapter); + return -ENOMEM; +} + + +int +vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter) +{ + int i, err = 0; + + adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter); + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter); + if (unlikely(err)) { + dev_err(&adapter->netdev->dev, + "%s: failed to create rx queue%i\n", + adapter->netdev->name, i); + goto err_out; + } + } + + if (!adapter->rxdataring_enabled) + vmxnet3_rq_destroy_all_rxdataring(adapter); + + return err; +err_out: + vmxnet3_rq_destroy_all(adapter); + return err; + +} + +/* Multiple queue aware polling function for tx and rx */ + +static int +vmxnet3_do_poll(struct vmxnet3_adapter *adapter, int budget) +{ + int rcd_done = 0, i; + if (unlikely(adapter->shared->ecr)) + vmxnet3_process_events(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) + vmxnet3_tq_tx_complete(&adapter->tx_queue[i], adapter); + + for (i = 0; i < adapter->num_rx_queues; i++) + rcd_done += vmxnet3_rq_rx_complete(&adapter->rx_queue[i], + adapter, budget); + return rcd_done; +} + + +static int +vmxnet3_poll(struct napi_struct *napi, int budget) +{ + struct vmxnet3_rx_queue *rx_queue = container_of(napi, + struct vmxnet3_rx_queue, napi); + int rxd_done; + + rxd_done = vmxnet3_do_poll(rx_queue->adapter, budget); + + if (rxd_done < budget) { + napi_complete_done(napi, rxd_done); + vmxnet3_enable_all_intrs(rx_queue->adapter); + } + return rxd_done; +} + +/* + * NAPI polling function for MSI-X mode with multiple Rx queues + * Returns the # of the NAPI credit consumed (# of rx descriptors processed) + */ + +static int +vmxnet3_poll_rx_only(struct napi_struct *napi, int budget) +{ + struct vmxnet3_rx_queue *rq = container_of(napi, + struct vmxnet3_rx_queue, napi); + struct vmxnet3_adapter *adapter = rq->adapter; + int rxd_done; + + /* When sharing interrupt with corresponding tx queue, process + * tx completions in that queue as well + */ + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) { + struct vmxnet3_tx_queue *tq = + &adapter->tx_queue[rq - adapter->rx_queue]; + vmxnet3_tq_tx_complete(tq, adapter); + } + + rxd_done = vmxnet3_rq_rx_complete(rq, adapter, budget); + + if (rxd_done < budget) { + napi_complete_done(napi, rxd_done); + vmxnet3_enable_intr(adapter, rq->comp_ring.intr_idx); + } + return rxd_done; +} + + +#ifdef CONFIG_PCI_MSI + +/* + * Handle completion interrupts on tx queues + * Returns whether or not the intr is handled + */ + +static irqreturn_t +vmxnet3_msix_tx(int irq, void *data) +{ + struct vmxnet3_tx_queue *tq = data; + struct vmxnet3_adapter *adapter = tq->adapter; + + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, tq->comp_ring.intr_idx); + + /* Handle the case where only one irq is allocate for all tx queues */ + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) { + int i; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *txq = &adapter->tx_queue[i]; + vmxnet3_tq_tx_complete(txq, adapter); + } + } else { + vmxnet3_tq_tx_complete(tq, adapter); + } + vmxnet3_enable_intr(adapter, tq->comp_ring.intr_idx); + + return IRQ_HANDLED; +} + + +/* + * Handle completion interrupts on rx queues. Returns whether or not the + * intr is handled + */ + +static irqreturn_t +vmxnet3_msix_rx(int irq, void *data) +{ + struct vmxnet3_rx_queue *rq = data; + struct vmxnet3_adapter *adapter = rq->adapter; + + /* disable intr if needed */ + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, rq->comp_ring.intr_idx); + napi_schedule(&rq->napi); + + return IRQ_HANDLED; +} + +/* + *---------------------------------------------------------------------------- + * + * vmxnet3_msix_event -- + * + * vmxnet3 msix event intr handler + * + * Result: + * whether or not the intr is handled + * + *---------------------------------------------------------------------------- + */ + +static irqreturn_t +vmxnet3_msix_event(int irq, void *data) +{ + struct net_device *dev = data; + struct vmxnet3_adapter *adapter = netdev_priv(dev); + + /* disable intr if needed */ + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_intr(adapter, adapter->intr.event_intr_idx); + + if (adapter->shared->ecr) + vmxnet3_process_events(adapter); + + vmxnet3_enable_intr(adapter, adapter->intr.event_intr_idx); + + return IRQ_HANDLED; +} + +#endif /* CONFIG_PCI_MSI */ + + +/* Interrupt handler for vmxnet3 */ +static irqreturn_t +vmxnet3_intr(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct vmxnet3_adapter *adapter = netdev_priv(dev); + + if (adapter->intr.type == VMXNET3_IT_INTX) { + u32 icr = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR); + if (unlikely(icr == 0)) + /* not ours */ + return IRQ_NONE; + } + + + /* disable intr if needed */ + if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE) + vmxnet3_disable_all_intrs(adapter); + + napi_schedule(&adapter->rx_queue[0].napi); + + return IRQ_HANDLED; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER + +/* netpoll callback. */ +static void +vmxnet3_netpoll(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + switch (adapter->intr.type) { +#ifdef CONFIG_PCI_MSI + case VMXNET3_IT_MSIX: { + int i; + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_msix_rx(0, &adapter->rx_queue[i]); + break; + } +#endif + case VMXNET3_IT_MSI: + default: + vmxnet3_intr(0, adapter->netdev); + break; + } + +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +static int +vmxnet3_request_irqs(struct vmxnet3_adapter *adapter) +{ + struct vmxnet3_intr *intr = &adapter->intr; + int err = 0, i; + int vector = 0; + +#ifdef CONFIG_PCI_MSI + if (adapter->intr.type == VMXNET3_IT_MSIX) { + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) { + sprintf(adapter->tx_queue[i].name, "%s-tx-%d", + adapter->netdev->name, vector); + err = request_irq( + intr->msix_entries[vector].vector, + vmxnet3_msix_tx, 0, + adapter->tx_queue[i].name, + &adapter->tx_queue[i]); + } else { + sprintf(adapter->tx_queue[i].name, "%s-rxtx-%d", + adapter->netdev->name, vector); + } + if (err) { + dev_err(&adapter->netdev->dev, + "Failed to request irq for MSIX, %s, " + "error %d\n", + adapter->tx_queue[i].name, err); + return err; + } + + /* Handle the case where only 1 MSIx was allocated for + * all tx queues */ + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) { + for (; i < adapter->num_tx_queues; i++) + adapter->tx_queue[i].comp_ring.intr_idx + = vector; + vector++; + break; + } else { + adapter->tx_queue[i].comp_ring.intr_idx + = vector++; + } + } + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) + vector = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) + sprintf(adapter->rx_queue[i].name, "%s-rx-%d", + adapter->netdev->name, vector); + else + sprintf(adapter->rx_queue[i].name, "%s-rxtx-%d", + adapter->netdev->name, vector); + err = request_irq(intr->msix_entries[vector].vector, + vmxnet3_msix_rx, 0, + adapter->rx_queue[i].name, + &(adapter->rx_queue[i])); + if (err) { + netdev_err(adapter->netdev, + "Failed to request irq for MSIX, " + "%s, error %d\n", + adapter->rx_queue[i].name, err); + return err; + } + + adapter->rx_queue[i].comp_ring.intr_idx = vector++; + } + + sprintf(intr->event_msi_vector_name, "%s-event-%d", + adapter->netdev->name, vector); + err = request_irq(intr->msix_entries[vector].vector, + vmxnet3_msix_event, 0, + intr->event_msi_vector_name, adapter->netdev); + intr->event_intr_idx = vector; + + } else if (intr->type == VMXNET3_IT_MSI) { + adapter->num_rx_queues = 1; + err = request_irq(adapter->pdev->irq, vmxnet3_intr, 0, + adapter->netdev->name, adapter->netdev); + } else { +#endif + adapter->num_rx_queues = 1; + err = request_irq(adapter->pdev->irq, vmxnet3_intr, + IRQF_SHARED, adapter->netdev->name, + adapter->netdev); +#ifdef CONFIG_PCI_MSI + } +#endif + intr->num_intrs = vector + 1; + if (err) { + netdev_err(adapter->netdev, + "Failed to request irq (intr type:%d), error %d\n", + intr->type, err); + } else { + /* Number of rx queues will not change after this */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + rq->qid = i; + rq->qid2 = i + adapter->num_rx_queues; + rq->dataRingQid = i + 2 * adapter->num_rx_queues; + } + + /* init our intr settings */ + for (i = 0; i < intr->num_intrs; i++) + intr->mod_levels[i] = UPT1_IML_ADAPTIVE; + if (adapter->intr.type != VMXNET3_IT_MSIX) { + adapter->intr.event_intr_idx = 0; + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_queue[i].comp_ring.intr_idx = 0; + adapter->rx_queue[0].comp_ring.intr_idx = 0; + } + + netdev_info(adapter->netdev, + "intr type %u, mode %u, %u vectors allocated\n", + intr->type, intr->mask_mode, intr->num_intrs); + } + + return err; +} + + +static void +vmxnet3_free_irqs(struct vmxnet3_adapter *adapter) +{ + struct vmxnet3_intr *intr = &adapter->intr; + BUG_ON(intr->type == VMXNET3_IT_AUTO || intr->num_intrs <= 0); + + switch (intr->type) { +#ifdef CONFIG_PCI_MSI + case VMXNET3_IT_MSIX: + { + int i, vector = 0; + + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) { + for (i = 0; i < adapter->num_tx_queues; i++) { + free_irq(intr->msix_entries[vector++].vector, + &(adapter->tx_queue[i])); + if (adapter->share_intr == VMXNET3_INTR_TXSHARE) + break; + } + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + free_irq(intr->msix_entries[vector++].vector, + &(adapter->rx_queue[i])); + } + + free_irq(intr->msix_entries[vector].vector, + adapter->netdev); + BUG_ON(vector >= intr->num_intrs); + break; + } +#endif + case VMXNET3_IT_MSI: + free_irq(adapter->pdev->irq, adapter->netdev); + break; + case VMXNET3_IT_INTX: + free_irq(adapter->pdev->irq, adapter->netdev); + break; + default: + BUG(); + } +} + + +static void +vmxnet3_restore_vlan(struct vmxnet3_adapter *adapter) +{ + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + u16 vid; + + /* allow untagged pkts */ + VMXNET3_SET_VFTABLE_ENTRY(vfTable, 0); + + for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) + VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); +} + + +static int +vmxnet3_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!(netdev->flags & IFF_PROMISC)) { + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + unsigned long flags; + + VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + set_bit(vid, adapter->active_vlans); + + return 0; +} + + +static int +vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!(netdev->flags & IFF_PROMISC)) { + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + unsigned long flags; + + VMXNET3_CLEAR_VFTABLE_ENTRY(vfTable, vid); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + clear_bit(vid, adapter->active_vlans); + + return 0; +} + + +static u8 * +vmxnet3_copy_mc(struct net_device *netdev) +{ + u8 *buf = NULL; + u32 sz = netdev_mc_count(netdev) * ETH_ALEN; + + /* struct Vmxnet3_RxFilterConf.mfTableLen is u16. */ + if (sz <= 0xffff) { + /* We may be called with BH disabled */ + buf = kmalloc(sz, GFP_ATOMIC); + if (buf) { + struct netdev_hw_addr *ha; + int i = 0; + + netdev_for_each_mc_addr(ha, netdev) + memcpy(buf + i++ * ETH_ALEN, ha->addr, + ETH_ALEN); + } + } + return buf; +} + + +static void +vmxnet3_set_mc(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + struct Vmxnet3_RxFilterConf *rxConf = + &adapter->shared->devRead.rxFilterConf; + u8 *new_table = NULL; + dma_addr_t new_table_pa = 0; + bool new_table_pa_valid = false; + u32 new_mode = VMXNET3_RXM_UCAST; + + if (netdev->flags & IFF_PROMISC) { + u32 *vfTable = adapter->shared->devRead.rxFilterConf.vfTable; + memset(vfTable, 0, VMXNET3_VFT_SIZE * sizeof(*vfTable)); + + new_mode |= VMXNET3_RXM_PROMISC; + } else { + vmxnet3_restore_vlan(adapter); + } + + if (netdev->flags & IFF_BROADCAST) + new_mode |= VMXNET3_RXM_BCAST; + + if (netdev->flags & IFF_ALLMULTI) + new_mode |= VMXNET3_RXM_ALL_MULTI; + else + if (!netdev_mc_empty(netdev)) { + new_table = vmxnet3_copy_mc(netdev); + if (new_table) { + size_t sz = netdev_mc_count(netdev) * ETH_ALEN; + + rxConf->mfTableLen = cpu_to_le16(sz); + new_table_pa = dma_map_single( + &adapter->pdev->dev, + new_table, + sz, + DMA_TO_DEVICE); + if (!dma_mapping_error(&adapter->pdev->dev, + new_table_pa)) { + new_mode |= VMXNET3_RXM_MCAST; + new_table_pa_valid = true; + rxConf->mfTablePA = cpu_to_le64( + new_table_pa); + } + } + if (!new_table_pa_valid) { + netdev_info(netdev, + "failed to copy mcast list, setting ALL_MULTI\n"); + new_mode |= VMXNET3_RXM_ALL_MULTI; + } + } + + if (!(new_mode & VMXNET3_RXM_MCAST)) { + rxConf->mfTableLen = 0; + rxConf->mfTablePA = 0; + } + + spin_lock_irqsave(&adapter->cmd_lock, flags); + if (new_mode != rxConf->rxMode) { + rxConf->rxMode = cpu_to_le32(new_mode); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_RX_MODE); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_VLAN_FILTERS); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_MAC_FILTERS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (new_table_pa_valid) + dma_unmap_single(&adapter->pdev->dev, new_table_pa, + rxConf->mfTableLen, DMA_TO_DEVICE); + kfree(new_table); +} + +void +vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + vmxnet3_rq_destroy(&adapter->rx_queue[i], adapter); +} + + +/* + * Set up driver_shared based on settings in adapter. + */ + +static void +vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + struct Vmxnet3_DSDevRead *devRead = &shared->devRead; + struct Vmxnet3_DSDevReadExt *devReadExt = &shared->devReadExt; + struct Vmxnet3_TxQueueConf *tqc; + struct Vmxnet3_RxQueueConf *rqc; + int i; + + memset(shared, 0, sizeof(*shared)); + + /* driver settings */ + shared->magic = cpu_to_le32(VMXNET3_REV1_MAGIC); + devRead->misc.driverInfo.version = cpu_to_le32( + VMXNET3_DRIVER_VERSION_NUM); + devRead->misc.driverInfo.gos.gosBits = (sizeof(void *) == 4 ? + VMXNET3_GOS_BITS_32 : VMXNET3_GOS_BITS_64); + devRead->misc.driverInfo.gos.gosType = VMXNET3_GOS_TYPE_LINUX; + *((u32 *)&devRead->misc.driverInfo.gos) = cpu_to_le32( + *((u32 *)&devRead->misc.driverInfo.gos)); + devRead->misc.driverInfo.vmxnet3RevSpt = cpu_to_le32(1); + devRead->misc.driverInfo.uptVerSpt = cpu_to_le32(1); + + devRead->misc.ddPA = cpu_to_le64(adapter->adapter_pa); + devRead->misc.ddLen = cpu_to_le32(sizeof(struct vmxnet3_adapter)); + + /* set up feature flags */ + if (adapter->netdev->features & NETIF_F_RXCSUM) + devRead->misc.uptFeatures |= UPT1_F_RXCSUM; + + if (adapter->netdev->features & NETIF_F_LRO) { + devRead->misc.uptFeatures |= UPT1_F_LRO; + devRead->misc.maxNumRxSG = cpu_to_le16(1 + MAX_SKB_FRAGS); + } + if (adapter->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) + devRead->misc.uptFeatures |= UPT1_F_RXVLAN; + + if (adapter->netdev->features & (NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM)) + devRead->misc.uptFeatures |= UPT1_F_RXINNEROFLD; + + devRead->misc.mtu = cpu_to_le32(adapter->netdev->mtu); + devRead->misc.queueDescPA = cpu_to_le64(adapter->queue_desc_pa); + devRead->misc.queueDescLen = cpu_to_le32( + adapter->num_tx_queues * sizeof(struct Vmxnet3_TxQueueDesc) + + adapter->num_rx_queues * sizeof(struct Vmxnet3_RxQueueDesc)); + + /* tx queue settings */ + devRead->misc.numTxQueues = adapter->num_tx_queues; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + BUG_ON(adapter->tx_queue[i].tx_ring.base == NULL); + tqc = &adapter->tqd_start[i].conf; + tqc->txRingBasePA = cpu_to_le64(tq->tx_ring.basePA); + tqc->dataRingBasePA = cpu_to_le64(tq->data_ring.basePA); + tqc->compRingBasePA = cpu_to_le64(tq->comp_ring.basePA); + tqc->ddPA = cpu_to_le64(~0ULL); + tqc->txRingSize = cpu_to_le32(tq->tx_ring.size); + tqc->dataRingSize = cpu_to_le32(tq->data_ring.size); + tqc->txDataRingDescSize = cpu_to_le32(tq->txdata_desc_size); + tqc->compRingSize = cpu_to_le32(tq->comp_ring.size); + tqc->ddLen = cpu_to_le32(0); + tqc->intrIdx = tq->comp_ring.intr_idx; + } + + /* rx queue settings */ + devRead->misc.numRxQueues = adapter->num_rx_queues; + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + rqc = &adapter->rqd_start[i].conf; + rqc->rxRingBasePA[0] = cpu_to_le64(rq->rx_ring[0].basePA); + rqc->rxRingBasePA[1] = cpu_to_le64(rq->rx_ring[1].basePA); + rqc->compRingBasePA = cpu_to_le64(rq->comp_ring.basePA); + rqc->ddPA = cpu_to_le64(~0ULL); + rqc->rxRingSize[0] = cpu_to_le32(rq->rx_ring[0].size); + rqc->rxRingSize[1] = cpu_to_le32(rq->rx_ring[1].size); + rqc->compRingSize = cpu_to_le32(rq->comp_ring.size); + rqc->ddLen = cpu_to_le32(0); + rqc->intrIdx = rq->comp_ring.intr_idx; + if (VMXNET3_VERSION_GE_3(adapter)) { + rqc->rxDataRingBasePA = + cpu_to_le64(rq->data_ring.basePA); + rqc->rxDataRingDescSize = + cpu_to_le16(rq->data_ring.desc_size); + } + } + +#ifdef VMXNET3_RSS + memset(adapter->rss_conf, 0, sizeof(*adapter->rss_conf)); + + if (adapter->rss) { + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + devRead->misc.uptFeatures |= UPT1_F_RSS; + devRead->misc.numRxQueues = adapter->num_rx_queues; + rssConf->hashType = UPT1_RSS_HASH_TYPE_TCP_IPV4 | + UPT1_RSS_HASH_TYPE_IPV4 | + UPT1_RSS_HASH_TYPE_TCP_IPV6 | + UPT1_RSS_HASH_TYPE_IPV6; + rssConf->hashFunc = UPT1_RSS_HASH_FUNC_TOEPLITZ; + rssConf->hashKeySize = UPT1_RSS_MAX_KEY_SIZE; + rssConf->indTableSize = VMXNET3_RSS_IND_TABLE_SIZE; + netdev_rss_key_fill(rssConf->hashKey, sizeof(rssConf->hashKey)); + + for (i = 0; i < rssConf->indTableSize; i++) + rssConf->indTable[i] = ethtool_rxfh_indir_default( + i, adapter->num_rx_queues); + + devRead->rssConfDesc.confVer = 1; + devRead->rssConfDesc.confLen = cpu_to_le32(sizeof(*rssConf)); + devRead->rssConfDesc.confPA = + cpu_to_le64(adapter->rss_conf_pa); + } + +#endif /* VMXNET3_RSS */ + + /* intr settings */ + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + devRead->intrConf.autoMask = adapter->intr.mask_mode == + VMXNET3_IMM_AUTO; + devRead->intrConf.numIntrs = adapter->intr.num_intrs; + for (i = 0; i < adapter->intr.num_intrs; i++) + devRead->intrConf.modLevels[i] = adapter->intr.mod_levels[i]; + + devRead->intrConf.eventIntrIdx = adapter->intr.event_intr_idx; + devRead->intrConf.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } else { + devReadExt->intrConfExt.autoMask = adapter->intr.mask_mode == + VMXNET3_IMM_AUTO; + devReadExt->intrConfExt.numIntrs = adapter->intr.num_intrs; + for (i = 0; i < adapter->intr.num_intrs; i++) + devReadExt->intrConfExt.modLevels[i] = adapter->intr.mod_levels[i]; + + devReadExt->intrConfExt.eventIntrIdx = adapter->intr.event_intr_idx; + devReadExt->intrConfExt.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } + + /* rx filter settings */ + devRead->rxFilterConf.rxMode = 0; + vmxnet3_restore_vlan(adapter); + vmxnet3_write_mac_addr(adapter, adapter->netdev->dev_addr); + + /* the rest are already zeroed */ +} + +static void +vmxnet3_init_bufsize(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_7(adapter)) + return; + + cmdInfo->ringBufSize = adapter->ringBufSize; + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_RING_BUFFER_SIZE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); +} + +static void +vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_3(adapter)) + return; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + cmdInfo->varConf.confVer = 1; + cmdInfo->varConf.confLen = + cpu_to_le32(sizeof(*adapter->coal_conf)); + cmdInfo->varConf.confPA = cpu_to_le64(adapter->coal_conf_pa); + + if (adapter->default_coal_mode) { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_COALESCE); + } else { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_COALESCE); + } + + spin_unlock_irqrestore(&adapter->cmd_lock, flags); +} + +static void +vmxnet3_init_rssfields(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_4(adapter)) + return; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + + if (adapter->default_rss_fields) { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + adapter->rss_fields = + VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + } else { + if (VMXNET3_VERSION_GE_7(adapter)) { + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_UDPIP4 || + adapter->rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_UDP_RSS)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_UDP_RSS; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_UDP_RSS); + } + + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV4)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV4; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV4); + } + + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_ESPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV6)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV6; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV6); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + } + cmdInfo->setRssFields = adapter->rss_fields; + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_RSS_FIELDS); + /* Not all requested RSS may get applied, so get and + * cache what was actually applied. + */ + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + adapter->rss_fields = + VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + } + + spin_unlock_irqrestore(&adapter->cmd_lock, flags); +} + +int +vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) +{ + int err, i; + u32 ret; + unsigned long flags; + + netdev_dbg(adapter->netdev, "%s: skb_buf_size %d, rx_buf_per_pkt %d," + " ring sizes %u %u %u\n", adapter->netdev->name, + adapter->skb_buf_size, adapter->rx_buf_per_pkt, + adapter->tx_queue[0].tx_ring.size, + adapter->rx_queue[0].rx_ring[0].size, + adapter->rx_queue[0].rx_ring[1].size); + + vmxnet3_tq_init_all(adapter); + err = vmxnet3_rq_init_all(adapter); + if (err) { + netdev_err(adapter->netdev, + "Failed to init rx queue error %d\n", err); + goto rq_err; + } + + err = vmxnet3_request_irqs(adapter); + if (err) { + netdev_err(adapter->netdev, + "Failed to setup irq for error %d\n", err); + goto irq_err; + } + + vmxnet3_setup_driver_shared(adapter); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DSAL, VMXNET3_GET_ADDR_LO( + adapter->shared_pa)); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DSAH, VMXNET3_GET_ADDR_HI( + adapter->shared_pa)); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_ACTIVATE_DEV); + ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (ret != 0) { + netdev_err(adapter->netdev, + "Failed to activate dev: error %u\n", ret); + err = -EINVAL; + goto activate_err; + } + + vmxnet3_init_bufsize(adapter); + vmxnet3_init_coalesce(adapter); + vmxnet3_init_rssfields(adapter); + + for (i = 0; i < adapter->num_rx_queues; i++) { + VMXNET3_WRITE_BAR0_REG(adapter, + adapter->rx_prod_offset + i * VMXNET3_REG_ALIGN, + adapter->rx_queue[i].rx_ring[0].next2fill); + VMXNET3_WRITE_BAR0_REG(adapter, (adapter->rx_prod2_offset + + (i * VMXNET3_REG_ALIGN)), + adapter->rx_queue[i].rx_ring[1].next2fill); + } + + /* Apply the rx filter settins last. */ + vmxnet3_set_mc(adapter->netdev); + + /* + * Check link state when first activating device. It will start the + * tx queue if the link is up. + */ + vmxnet3_check_link(adapter, true); + netif_tx_wake_all_queues(adapter->netdev); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_queue[i].napi); + vmxnet3_enable_all_intrs(adapter); + clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); + return 0; + +activate_err: + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DSAL, 0); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DSAH, 0); + vmxnet3_free_irqs(adapter); +irq_err: +rq_err: + /* free up buffers we allocated */ + vmxnet3_rq_cleanup_all(adapter); + return err; +} + + +void +vmxnet3_reset_dev(struct vmxnet3_adapter *adapter) +{ + unsigned long flags; + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_RESET_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); +} + + +int +vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter) +{ + int i; + unsigned long flags; + if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)) + return 0; + + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_QUIESCE_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + vmxnet3_disable_all_intrs(adapter); + + for (i = 0; i < adapter->num_rx_queues; i++) + napi_disable(&adapter->rx_queue[i].napi); + netif_tx_disable(adapter->netdev); + adapter->link_speed = 0; + netif_carrier_off(adapter->netdev); + + vmxnet3_tq_cleanup_all(adapter); + vmxnet3_rq_cleanup_all(adapter); + vmxnet3_free_irqs(adapter); + return 0; +} + + +static void +vmxnet3_write_mac_addr(struct vmxnet3_adapter *adapter, const u8 *mac) +{ + u32 tmp; + + tmp = *(u32 *)mac; + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_MACL, tmp); + + tmp = (mac[5] << 8) | mac[4]; + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_MACH, tmp); +} + + +static int +vmxnet3_set_mac_addr(struct net_device *netdev, void *p) +{ + struct sockaddr *addr = p; + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + dev_addr_set(netdev, addr->sa_data); + vmxnet3_write_mac_addr(adapter, addr->sa_data); + + return 0; +} + + +/* ==================== initialization and cleanup routines ============ */ + +static int +vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter) +{ + int err; + unsigned long mmio_start, mmio_len; + struct pci_dev *pdev = adapter->pdev; + + err = pci_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, "Failed to enable adapter: error %d\n", err); + return err; + } + + err = pci_request_selected_regions(pdev, (1 << 2) - 1, + vmxnet3_driver_name); + if (err) { + dev_err(&pdev->dev, + "Failed to request region for adapter: error %d\n", err); + goto err_enable_device; + } + + pci_set_master(pdev); + + mmio_start = pci_resource_start(pdev, 0); + mmio_len = pci_resource_len(pdev, 0); + adapter->hw_addr0 = ioremap(mmio_start, mmio_len); + if (!adapter->hw_addr0) { + dev_err(&pdev->dev, "Failed to map bar0\n"); + err = -EIO; + goto err_ioremap; + } + + mmio_start = pci_resource_start(pdev, 1); + mmio_len = pci_resource_len(pdev, 1); + adapter->hw_addr1 = ioremap(mmio_start, mmio_len); + if (!adapter->hw_addr1) { + dev_err(&pdev->dev, "Failed to map bar1\n"); + err = -EIO; + goto err_bar1; + } + return 0; + +err_bar1: + iounmap(adapter->hw_addr0); +err_ioremap: + pci_release_selected_regions(pdev, (1 << 2) - 1); +err_enable_device: + pci_disable_device(pdev); + return err; +} + + +static void +vmxnet3_free_pci_resources(struct vmxnet3_adapter *adapter) +{ + BUG_ON(!adapter->pdev); + + iounmap(adapter->hw_addr0); + iounmap(adapter->hw_addr1); + pci_release_selected_regions(adapter->pdev, (1 << 2) - 1); + pci_disable_device(adapter->pdev); +} + + +void +vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) +{ + size_t sz, i, ring0_size, ring1_size, comp_size; + /* With version7 ring1 will have only T0 buffers */ + if (!VMXNET3_VERSION_GE_7(adapter)) { + if (adapter->netdev->mtu <= VMXNET3_MAX_SKB_BUF_SIZE - + VMXNET3_MAX_ETH_HDR_SIZE) { + adapter->skb_buf_size = adapter->netdev->mtu + + VMXNET3_MAX_ETH_HDR_SIZE; + if (adapter->skb_buf_size < VMXNET3_MIN_T0_BUF_SIZE) + adapter->skb_buf_size = VMXNET3_MIN_T0_BUF_SIZE; + + adapter->rx_buf_per_pkt = 1; + } else { + adapter->skb_buf_size = VMXNET3_MAX_SKB_BUF_SIZE; + sz = adapter->netdev->mtu - VMXNET3_MAX_SKB_BUF_SIZE + + VMXNET3_MAX_ETH_HDR_SIZE; + adapter->rx_buf_per_pkt = 1 + (sz + PAGE_SIZE - 1) / PAGE_SIZE; + } + } else { + adapter->skb_buf_size = min((int)adapter->netdev->mtu + VMXNET3_MAX_ETH_HDR_SIZE, + VMXNET3_MAX_SKB_BUF_SIZE); + adapter->rx_buf_per_pkt = 1; + adapter->ringBufSize.ring1BufSizeType0 = cpu_to_le16(adapter->skb_buf_size); + adapter->ringBufSize.ring1BufSizeType1 = 0; + adapter->ringBufSize.ring2BufSizeType1 = cpu_to_le16(PAGE_SIZE); + } + + /* + * for simplicity, force the ring0 size to be a multiple of + * rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN + */ + sz = adapter->rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN; + ring0_size = adapter->rx_queue[0].rx_ring[0].size; + ring0_size = (ring0_size + sz - 1) / sz * sz; + ring0_size = min_t(u32, ring0_size, VMXNET3_RX_RING_MAX_SIZE / + sz * sz); + ring1_size = adapter->rx_queue[0].rx_ring[1].size; + ring1_size = (ring1_size + sz - 1) / sz * sz; + ring1_size = min_t(u32, ring1_size, VMXNET3_RX_RING2_MAX_SIZE / + sz * sz); + /* For v7 and later, keep ring size power of 2 for UPT */ + if (VMXNET3_VERSION_GE_7(adapter)) { + ring0_size = rounddown_pow_of_two(ring0_size); + ring1_size = rounddown_pow_of_two(ring1_size); + } + comp_size = ring0_size + ring1_size; + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + + rq->rx_ring[0].size = ring0_size; + rq->rx_ring[1].size = ring1_size; + rq->comp_ring.size = comp_size; + } +} + + +int +vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size, + u32 rx_ring_size, u32 rx_ring2_size, + u16 txdata_desc_size, u16 rxdata_desc_size) +{ + int err = 0, i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + tq->tx_ring.size = tx_ring_size; + tq->data_ring.size = tx_ring_size; + tq->comp_ring.size = tx_ring_size; + tq->txdata_desc_size = txdata_desc_size; + tq->shared = &adapter->tqd_start[i].ctrl; + tq->stopped = true; + tq->adapter = adapter; + tq->qid = i; + err = vmxnet3_tq_create(tq, adapter); + /* + * Too late to change num_tx_queues. We cannot do away with + * lesser number of queues than what we asked for + */ + if (err) + goto queue_err; + } + + adapter->rx_queue[0].rx_ring[0].size = rx_ring_size; + adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size; + vmxnet3_adjust_rx_ring_size(adapter); + + adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + /* qid and qid2 for rx queues will be assigned later when num + * of rx queues is finalized after allocating intrs */ + rq->shared = &adapter->rqd_start[i].ctrl; + rq->adapter = adapter; + rq->data_ring.desc_size = rxdata_desc_size; + err = vmxnet3_rq_create(rq, adapter); + if (err) { + if (i == 0) { + netdev_err(adapter->netdev, + "Could not allocate any rx queues. " + "Aborting.\n"); + goto queue_err; + } else { + netdev_info(adapter->netdev, + "Number of rx queues changed " + "to : %d.\n", i); + adapter->num_rx_queues = i; + err = 0; + break; + } + } + } + + if (!adapter->rxdataring_enabled) + vmxnet3_rq_destroy_all_rxdataring(adapter); + + return err; +queue_err: + vmxnet3_tq_destroy_all(adapter); + return err; +} + +static int +vmxnet3_open(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter; + int err, i; + + adapter = netdev_priv(netdev); + + for (i = 0; i < adapter->num_tx_queues; i++) + spin_lock_init(&adapter->tx_queue[i].tx_lock); + + if (VMXNET3_VERSION_GE_3(adapter)) { + unsigned long flags; + u16 txdata_desc_size; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_TXDATA_DESC_SIZE); + txdata_desc_size = VMXNET3_READ_BAR1_REG(adapter, + VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if ((txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE) || + (txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE) || + (txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK)) { + adapter->txdata_desc_size = + sizeof(struct Vmxnet3_TxDataDesc); + } else { + adapter->txdata_desc_size = txdata_desc_size; + } + } else { + adapter->txdata_desc_size = sizeof(struct Vmxnet3_TxDataDesc); + } + + err = vmxnet3_create_queues(adapter, + adapter->tx_ring_size, + adapter->rx_ring_size, + adapter->rx_ring2_size, + adapter->txdata_desc_size, + adapter->rxdata_desc_size); + if (err) + goto queue_err; + + err = vmxnet3_activate_dev(adapter); + if (err) + goto activate_err; + + return 0; + +activate_err: + vmxnet3_rq_destroy_all(adapter); + vmxnet3_tq_destroy_all(adapter); +queue_err: + return err; +} + + +static int +vmxnet3_close(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* + * Reset_work may be in the middle of resetting the device, wait for its + * completion. + */ + while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + vmxnet3_quiesce_dev(adapter); + + vmxnet3_rq_destroy_all(adapter); + vmxnet3_tq_destroy_all(adapter); + + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + + + return 0; +} + + +void +vmxnet3_force_close(struct vmxnet3_adapter *adapter) +{ + int i; + + /* + * we must clear VMXNET3_STATE_BIT_RESETTING, otherwise + * vmxnet3_close() will deadlock. + */ + BUG_ON(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)); + + /* we need to enable NAPI, otherwise dev_close will deadlock */ + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_queue[i].napi); + /* + * Need to clear the quiesce bit to ensure that vmxnet3_close + * can quiesce the device properly + */ + clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); + dev_close(adapter->netdev); +} + + +static int +vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int err = 0; + + netdev->mtu = new_mtu; + + /* + * Reset_work may be in the middle of resetting the device, wait for its + * completion. + */ + while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(netdev)) { + vmxnet3_quiesce_dev(adapter); + vmxnet3_reset_dev(adapter); + + /* we need to re-create the rx queue based on the new mtu */ + vmxnet3_rq_destroy_all(adapter); + vmxnet3_adjust_rx_ring_size(adapter); + err = vmxnet3_rq_create_all(adapter); + if (err) { + netdev_err(netdev, + "failed to re-create rx queues, " + " error %d. Closing it.\n", err); + goto out; + } + + err = vmxnet3_activate_dev(adapter); + if (err) { + netdev_err(netdev, + "failed to re-activate, error %d. " + "Closing it\n", err); + goto out; + } + } + +out: + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + if (err) + vmxnet3_force_close(adapter); + + return err; +} + + +static void +vmxnet3_declare_features(struct vmxnet3_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO | NETIF_F_HIGHDMA; + + if (VMXNET3_VERSION_GE_4(adapter)) { + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_enc_features = NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD; + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_TSO)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_TSO))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL; + } + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } + + netdev->vlan_features = netdev->hw_features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; +} + + +static void +vmxnet3_read_mac_addr(struct vmxnet3_adapter *adapter, u8 *mac) +{ + u32 tmp; + + tmp = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACL); + *(u32 *)mac = tmp; + + tmp = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACH); + mac[4] = tmp & 0xff; + mac[5] = (tmp >> 8) & 0xff; +} + +#ifdef CONFIG_PCI_MSI + +/* + * Enable MSIx vectors. + * Returns : + * VMXNET3_LINUX_MIN_MSIX_VECT when only minimum number of vectors required + * were enabled. + * number of vectors which were enabled otherwise (this number is greater + * than VMXNET3_LINUX_MIN_MSIX_VECT) + */ + +static int +vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter, int nvec) +{ + int ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, nvec, nvec); + + if (ret == -ENOSPC && nvec > VMXNET3_LINUX_MIN_MSIX_VECT) { + dev_err(&adapter->netdev->dev, + "Failed to enable %d MSI-X, trying %d\n", + nvec, VMXNET3_LINUX_MIN_MSIX_VECT); + + ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, + VMXNET3_LINUX_MIN_MSIX_VECT, + VMXNET3_LINUX_MIN_MSIX_VECT); + } + + if (ret < 0) { + dev_err(&adapter->netdev->dev, + "Failed to enable MSI-X, error: %d\n", ret); + } + + return ret; +} + + +#endif /* CONFIG_PCI_MSI */ + +static void +vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) +{ + u32 cfg; + unsigned long flags; + + /* intr settings */ + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_CONF_INTR); + cfg = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + adapter->intr.type = cfg & 0x3; + adapter->intr.mask_mode = (cfg >> 2) & 0x3; + + if (adapter->intr.type == VMXNET3_IT_AUTO) { + adapter->intr.type = VMXNET3_IT_MSIX; + } + +#ifdef CONFIG_PCI_MSI + if (adapter->intr.type == VMXNET3_IT_MSIX) { + int i, nvec, nvec_allocated; + + nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ? + 1 : adapter->num_tx_queues; + nvec += adapter->share_intr == VMXNET3_INTR_BUDDYSHARE ? + 0 : adapter->num_rx_queues; + nvec += 1; /* for link event */ + nvec = nvec > VMXNET3_LINUX_MIN_MSIX_VECT ? + nvec : VMXNET3_LINUX_MIN_MSIX_VECT; + + for (i = 0; i < nvec; i++) + adapter->intr.msix_entries[i].entry = i; + + nvec_allocated = vmxnet3_acquire_msix_vectors(adapter, nvec); + if (nvec_allocated < 0) + goto msix_err; + + /* If we cannot allocate one MSIx vector per queue + * then limit the number of rx queues to 1 + */ + if (nvec_allocated == VMXNET3_LINUX_MIN_MSIX_VECT && + nvec != VMXNET3_LINUX_MIN_MSIX_VECT) { + if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE + || adapter->num_rx_queues != 1) { + adapter->share_intr = VMXNET3_INTR_TXSHARE; + netdev_err(adapter->netdev, + "Number of rx queues : 1\n"); + adapter->num_rx_queues = 1; + } + } + + adapter->intr.num_intrs = nvec_allocated; + return; + +msix_err: + /* If we cannot allocate MSIx vectors use only one rx queue */ + dev_info(&adapter->pdev->dev, + "Failed to enable MSI-X, error %d. " + "Limiting #rx queues to 1, try MSI.\n", nvec_allocated); + + adapter->intr.type = VMXNET3_IT_MSI; + } + + if (adapter->intr.type == VMXNET3_IT_MSI) { + if (!pci_enable_msi(adapter->pdev)) { + adapter->num_rx_queues = 1; + adapter->intr.num_intrs = 1; + return; + } + } +#endif /* CONFIG_PCI_MSI */ + + adapter->num_rx_queues = 1; + dev_info(&adapter->netdev->dev, + "Using INTx interrupt, #Rx queues: 1.\n"); + adapter->intr.type = VMXNET3_IT_INTX; + + /* INT-X related setting */ + adapter->intr.num_intrs = 1; +} + + +static void +vmxnet3_free_intr_resources(struct vmxnet3_adapter *adapter) +{ + if (adapter->intr.type == VMXNET3_IT_MSIX) + pci_disable_msix(adapter->pdev); + else if (adapter->intr.type == VMXNET3_IT_MSI) + pci_disable_msi(adapter->pdev); + else + BUG_ON(adapter->intr.type != VMXNET3_IT_INTX); +} + + +static void +vmxnet3_tx_timeout(struct net_device *netdev, unsigned int txqueue) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + adapter->tx_timeout_count++; + + netdev_err(adapter->netdev, "tx hang\n"); + schedule_work(&adapter->work); +} + + +static void +vmxnet3_reset_work(struct work_struct *data) +{ + struct vmxnet3_adapter *adapter; + + adapter = container_of(data, struct vmxnet3_adapter, work); + + /* if another thread is resetting the device, no need to proceed */ + if (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + return; + + /* if the device is closed, we must leave it alone */ + rtnl_lock(); + if (netif_running(adapter->netdev)) { + netdev_notice(adapter->netdev, "resetting\n"); + vmxnet3_quiesce_dev(adapter); + vmxnet3_reset_dev(adapter); + vmxnet3_activate_dev(adapter); + } else { + netdev_info(adapter->netdev, "already closed\n"); + } + rtnl_unlock(); + + netif_wake_queue(adapter->netdev); + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); +} + + +static int +vmxnet3_probe_device(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + static const struct net_device_ops vmxnet3_netdev_ops = { + .ndo_open = vmxnet3_open, + .ndo_stop = vmxnet3_close, + .ndo_start_xmit = vmxnet3_xmit_frame, + .ndo_set_mac_address = vmxnet3_set_mac_addr, + .ndo_change_mtu = vmxnet3_change_mtu, + .ndo_fix_features = vmxnet3_fix_features, + .ndo_set_features = vmxnet3_set_features, + .ndo_features_check = vmxnet3_features_check, + .ndo_get_stats64 = vmxnet3_get_stats64, + .ndo_tx_timeout = vmxnet3_tx_timeout, + .ndo_set_rx_mode = vmxnet3_set_mc, + .ndo_vlan_rx_add_vid = vmxnet3_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = vmxnet3_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = vmxnet3_netpoll, +#endif + .ndo_bpf = vmxnet3_xdp, + .ndo_xdp_xmit = vmxnet3_xdp_xmit, + }; + int err; + u32 ver; + struct net_device *netdev; + struct vmxnet3_adapter *adapter; + u8 mac[ETH_ALEN]; + int size; + int num_tx_queues; + int num_rx_queues; + int queues; + unsigned long flags; + + if (!pci_msi_enabled()) + enable_mq = 0; + +#ifdef VMXNET3_RSS + if (enable_mq) + num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES, + (int)num_online_cpus()); + else +#endif + num_rx_queues = 1; + + if (enable_mq) + num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES, + (int)num_online_cpus()); + else + num_tx_queues = 1; + + netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter), + max(num_tx_queues, num_rx_queues)); + if (!netdev) + return -ENOMEM; + + pci_set_drvdata(pdev, netdev); + adapter = netdev_priv(netdev); + adapter->netdev = netdev; + adapter->pdev = pdev; + + adapter->tx_ring_size = VMXNET3_DEF_TX_RING_SIZE; + adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE; + adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE; + + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, "dma_set_mask failed\n"); + goto err_set_mask; + } + + spin_lock_init(&adapter->cmd_lock); + adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter, + sizeof(struct vmxnet3_adapter), + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) { + dev_err(&pdev->dev, "Failed to map dma\n"); + err = -EFAULT; + goto err_set_mask; + } + adapter->shared = dma_alloc_coherent( + &adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + &adapter->shared_pa, GFP_KERNEL); + if (!adapter->shared) { + dev_err(&pdev->dev, "Failed to allocate memory\n"); + err = -ENOMEM; + goto err_alloc_shared; + } + + err = vmxnet3_alloc_pci_resources(adapter); + if (err < 0) + goto err_alloc_pci; + + ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS); + if (ver & (1 << VMXNET3_REV_7)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_7); + adapter->version = VMXNET3_REV_7 + 1; + } else if (ver & (1 << VMXNET3_REV_6)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_6); + adapter->version = VMXNET3_REV_6 + 1; + } else if (ver & (1 << VMXNET3_REV_5)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_5); + adapter->version = VMXNET3_REV_5 + 1; + } else if (ver & (1 << VMXNET3_REV_4)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_4); + adapter->version = VMXNET3_REV_4 + 1; + } else if (ver & (1 << VMXNET3_REV_3)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_3); + adapter->version = VMXNET3_REV_3 + 1; + } else if (ver & (1 << VMXNET3_REV_2)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_2); + adapter->version = VMXNET3_REV_2 + 1; + } else if (ver & (1 << VMXNET3_REV_1)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_1); + adapter->version = VMXNET3_REV_1 + 1; + } else { + dev_err(&pdev->dev, + "Incompatible h/w version (0x%x) for adapter\n", ver); + err = -EBUSY; + goto err_ver; + } + dev_dbg(&pdev->dev, "Using device version %d\n", adapter->version); + + ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS); + if (ver & 1) { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_UVRS, 1); + } else { + dev_err(&pdev->dev, + "Incompatible upt version (0x%x) for adapter\n", ver); + err = -EBUSY; + goto err_ver; + } + + if (VMXNET3_VERSION_GE_7(adapter)) { + adapter->devcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DCR); + adapter->ptcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_PTCR); + if (adapter->devcap_supported[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) { + adapter->dev_caps[0] = adapter->devcap_supported[0] & + (1UL << VMXNET3_CAP_LARGE_BAR); + } + if (!(adapter->ptcap_supported[0] & (1UL << VMXNET3_DCR_ERROR)) && + adapter->ptcap_supported[0] & (1UL << VMXNET3_CAP_OOORX_COMP) && + adapter->devcap_supported[0] & (1UL << VMXNET3_CAP_OOORX_COMP)) { + adapter->dev_caps[0] |= adapter->devcap_supported[0] & + (1UL << VMXNET3_CAP_OOORX_COMP); + } + if (adapter->dev_caps[0]) + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + if (VMXNET3_VERSION_GE_7(adapter) && + adapter->dev_caps[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) { + adapter->tx_prod_offset = VMXNET3_REG_LB_TXPROD; + adapter->rx_prod_offset = VMXNET3_REG_LB_RXPROD; + adapter->rx_prod2_offset = VMXNET3_REG_LB_RXPROD2; + } else { + adapter->tx_prod_offset = VMXNET3_REG_TXPROD; + adapter->rx_prod_offset = VMXNET3_REG_RXPROD; + adapter->rx_prod2_offset = VMXNET3_REG_RXPROD2; + } + + if (VMXNET3_VERSION_GE_6(adapter)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_MAX_QUEUES_CONF); + queues = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + if (queues > 0) { + adapter->num_rx_queues = min(num_rx_queues, ((queues >> 8) & 0xff)); + adapter->num_tx_queues = min(num_tx_queues, (queues & 0xff)); + } else { + adapter->num_rx_queues = min(num_rx_queues, + VMXNET3_DEVICE_DEFAULT_RX_QUEUES); + adapter->num_tx_queues = min(num_tx_queues, + VMXNET3_DEVICE_DEFAULT_TX_QUEUES); + } + if (adapter->num_rx_queues > VMXNET3_MAX_RX_QUEUES || + adapter->num_tx_queues > VMXNET3_MAX_TX_QUEUES) { + adapter->queuesExtEnabled = true; + } else { + adapter->queuesExtEnabled = false; + } + } else { + adapter->queuesExtEnabled = false; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); + num_tx_queues = rounddown_pow_of_two(num_tx_queues); + adapter->num_rx_queues = min(num_rx_queues, + VMXNET3_DEVICE_DEFAULT_RX_QUEUES); + adapter->num_tx_queues = min(num_tx_queues, + VMXNET3_DEVICE_DEFAULT_TX_QUEUES); + } + dev_info(&pdev->dev, + "# of Tx queues : %d, # of Rx queues : %d\n", + adapter->num_tx_queues, adapter->num_rx_queues); + + adapter->rx_buf_per_pkt = 1; + + size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues; + size += sizeof(struct Vmxnet3_RxQueueDesc) * adapter->num_rx_queues; + adapter->tqd_start = dma_alloc_coherent(&adapter->pdev->dev, size, + &adapter->queue_desc_pa, + GFP_KERNEL); + + if (!adapter->tqd_start) { + dev_err(&pdev->dev, "Failed to allocate memory\n"); + err = -ENOMEM; + goto err_ver; + } + adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start + + adapter->num_tx_queues); + + adapter->pm_conf = dma_alloc_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_PMConf), + &adapter->pm_conf_pa, + GFP_KERNEL); + if (adapter->pm_conf == NULL) { + err = -ENOMEM; + goto err_alloc_pm; + } + +#ifdef VMXNET3_RSS + + adapter->rss_conf = dma_alloc_coherent(&adapter->pdev->dev, + sizeof(struct UPT1_RSSConf), + &adapter->rss_conf_pa, + GFP_KERNEL); + if (adapter->rss_conf == NULL) { + err = -ENOMEM; + goto err_alloc_rss; + } +#endif /* VMXNET3_RSS */ + + if (VMXNET3_VERSION_GE_3(adapter)) { + adapter->coal_conf = + dma_alloc_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_CoalesceScheme) + , + &adapter->coal_conf_pa, + GFP_KERNEL); + if (!adapter->coal_conf) { + err = -ENOMEM; + goto err_coal_conf; + } + adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED; + adapter->default_coal_mode = true; + } + + if (VMXNET3_VERSION_GE_4(adapter)) { + adapter->default_rss_fields = true; + adapter->rss_fields = VMXNET3_RSS_FIELDS_DEFAULT; + } + + SET_NETDEV_DEV(netdev, &pdev->dev); + vmxnet3_declare_features(adapter); + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + + adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ? + VMXNET3_DEF_RXDATA_DESC_SIZE : 0; + + if (adapter->num_tx_queues == adapter->num_rx_queues) + adapter->share_intr = VMXNET3_INTR_BUDDYSHARE; + else + adapter->share_intr = VMXNET3_INTR_DONTSHARE; + + vmxnet3_alloc_intr_resources(adapter); + +#ifdef VMXNET3_RSS + if (adapter->num_rx_queues > 1 && + adapter->intr.type == VMXNET3_IT_MSIX) { + adapter->rss = true; + netdev->hw_features |= NETIF_F_RXHASH; + netdev->features |= NETIF_F_RXHASH; + dev_dbg(&pdev->dev, "RSS is enabled.\n"); + } else { + adapter->rss = false; + } +#endif + + vmxnet3_read_mac_addr(adapter, mac); + dev_addr_set(netdev, mac); + + netdev->netdev_ops = &vmxnet3_netdev_ops; + vmxnet3_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + + /* MTU range: 60 - 9190 */ + netdev->min_mtu = VMXNET3_MIN_MTU; + if (VMXNET3_VERSION_GE_6(adapter)) + netdev->max_mtu = VMXNET3_V6_MAX_MTU; + else + netdev->max_mtu = VMXNET3_MAX_MTU; + + INIT_WORK(&adapter->work, vmxnet3_reset_work); + set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state); + + if (adapter->intr.type == VMXNET3_IT_MSIX) { + int i; + for (i = 0; i < adapter->num_rx_queues; i++) { + netif_napi_add(adapter->netdev, + &adapter->rx_queue[i].napi, + vmxnet3_poll_rx_only); + } + } else { + netif_napi_add(adapter->netdev, &adapter->rx_queue[0].napi, + vmxnet3_poll); + } + + netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); + netif_set_real_num_rx_queues(adapter->netdev, adapter->num_rx_queues); + + netif_carrier_off(netdev); + err = register_netdev(netdev); + + if (err) { + dev_err(&pdev->dev, "Failed to register adapter\n"); + goto err_register; + } + + vmxnet3_check_link(adapter, false); + return 0; + +err_register: + if (VMXNET3_VERSION_GE_3(adapter)) { + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_CoalesceScheme), + adapter->coal_conf, adapter->coal_conf_pa); + } + vmxnet3_free_intr_resources(adapter); +err_coal_conf: +#ifdef VMXNET3_RSS + dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf), + adapter->rss_conf, adapter->rss_conf_pa); +err_alloc_rss: +#endif + dma_free_coherent(&adapter->pdev->dev, sizeof(struct Vmxnet3_PMConf), + adapter->pm_conf, adapter->pm_conf_pa); +err_alloc_pm: + dma_free_coherent(&adapter->pdev->dev, size, adapter->tqd_start, + adapter->queue_desc_pa); +err_ver: + vmxnet3_free_pci_resources(adapter); +err_alloc_pci: + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + adapter->shared, adapter->shared_pa); +err_alloc_shared: + dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa, + sizeof(struct vmxnet3_adapter), DMA_TO_DEVICE); +err_set_mask: + free_netdev(netdev); + return err; +} + + +static void +vmxnet3_remove_device(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int size = 0; + int num_rx_queues, rx_queues; + unsigned long flags; + +#ifdef VMXNET3_RSS + if (enable_mq) + num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES, + (int)num_online_cpus()); + else +#endif + num_rx_queues = 1; + if (!VMXNET3_VERSION_GE_6(adapter)) { + num_rx_queues = rounddown_pow_of_two(num_rx_queues); + } + if (VMXNET3_VERSION_GE_6(adapter)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_MAX_QUEUES_CONF); + rx_queues = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + if (rx_queues > 0) + rx_queues = (rx_queues >> 8) & 0xff; + else + rx_queues = min(num_rx_queues, VMXNET3_DEVICE_DEFAULT_RX_QUEUES); + num_rx_queues = min(num_rx_queues, rx_queues); + } else { + num_rx_queues = min(num_rx_queues, + VMXNET3_DEVICE_DEFAULT_RX_QUEUES); + } + + cancel_work_sync(&adapter->work); + + unregister_netdev(netdev); + + vmxnet3_free_intr_resources(adapter); + vmxnet3_free_pci_resources(adapter); + if (VMXNET3_VERSION_GE_3(adapter)) { + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_CoalesceScheme), + adapter->coal_conf, adapter->coal_conf_pa); + } +#ifdef VMXNET3_RSS + dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf), + adapter->rss_conf, adapter->rss_conf_pa); +#endif + dma_free_coherent(&adapter->pdev->dev, sizeof(struct Vmxnet3_PMConf), + adapter->pm_conf, adapter->pm_conf_pa); + + size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues; + size += sizeof(struct Vmxnet3_RxQueueDesc) * num_rx_queues; + dma_free_coherent(&adapter->pdev->dev, size, adapter->tqd_start, + adapter->queue_desc_pa); + dma_free_coherent(&adapter->pdev->dev, + sizeof(struct Vmxnet3_DriverShared), + adapter->shared, adapter->shared_pa); + dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa, + sizeof(struct vmxnet3_adapter), DMA_TO_DEVICE); + free_netdev(netdev); +} + +static void vmxnet3_shutdown_device(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + + /* Reset_work may be in the middle of resetting the device, wait for its + * completion. + */ + while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED, + &adapter->state)) { + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + return; + } + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_QUIESCE_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + vmxnet3_disable_all_intrs(adapter); + + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); +} + + +#ifdef CONFIG_PM + +static int +vmxnet3_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct net_device *netdev = pci_get_drvdata(pdev); + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct Vmxnet3_PMConf *pmConf; + struct ethhdr *ehdr; + struct arphdr *ahdr; + u8 *arpreq; + struct in_device *in_dev; + struct in_ifaddr *ifa; + unsigned long flags; + int i = 0; + + if (!netif_running(netdev)) + return 0; + + for (i = 0; i < adapter->num_rx_queues; i++) + napi_disable(&adapter->rx_queue[i].napi); + + vmxnet3_disable_all_intrs(adapter); + vmxnet3_free_irqs(adapter); + vmxnet3_free_intr_resources(adapter); + + netif_device_detach(netdev); + + /* Create wake-up filters. */ + pmConf = adapter->pm_conf; + memset(pmConf, 0, sizeof(*pmConf)); + + if (adapter->wol & WAKE_UCAST) { + pmConf->filters[i].patternSize = ETH_ALEN; + pmConf->filters[i].maskSize = 1; + memcpy(pmConf->filters[i].pattern, netdev->dev_addr, ETH_ALEN); + pmConf->filters[i].mask[0] = 0x3F; /* LSB ETH_ALEN bits */ + + pmConf->wakeUpEvents |= VMXNET3_PM_WAKEUP_FILTER; + i++; + } + + if (adapter->wol & WAKE_ARP) { + rcu_read_lock(); + + in_dev = __in_dev_get_rcu(netdev); + if (!in_dev) { + rcu_read_unlock(); + goto skip_arp; + } + + ifa = rcu_dereference(in_dev->ifa_list); + if (!ifa) { + rcu_read_unlock(); + goto skip_arp; + } + + pmConf->filters[i].patternSize = ETH_HLEN + /* Ethernet header*/ + sizeof(struct arphdr) + /* ARP header */ + 2 * ETH_ALEN + /* 2 Ethernet addresses*/ + 2 * sizeof(u32); /*2 IPv4 addresses */ + pmConf->filters[i].maskSize = + (pmConf->filters[i].patternSize - 1) / 8 + 1; + + /* ETH_P_ARP in Ethernet header. */ + ehdr = (struct ethhdr *)pmConf->filters[i].pattern; + ehdr->h_proto = htons(ETH_P_ARP); + + /* ARPOP_REQUEST in ARP header. */ + ahdr = (struct arphdr *)&pmConf->filters[i].pattern[ETH_HLEN]; + ahdr->ar_op = htons(ARPOP_REQUEST); + arpreq = (u8 *)(ahdr + 1); + + /* The Unicast IPv4 address in 'tip' field. */ + arpreq += 2 * ETH_ALEN + sizeof(u32); + *(__be32 *)arpreq = ifa->ifa_address; + + rcu_read_unlock(); + + /* The mask for the relevant bits. */ + pmConf->filters[i].mask[0] = 0x00; + pmConf->filters[i].mask[1] = 0x30; /* ETH_P_ARP */ + pmConf->filters[i].mask[2] = 0x30; /* ARPOP_REQUEST */ + pmConf->filters[i].mask[3] = 0x00; + pmConf->filters[i].mask[4] = 0xC0; /* IPv4 TIP */ + pmConf->filters[i].mask[5] = 0x03; /* IPv4 TIP */ + + pmConf->wakeUpEvents |= VMXNET3_PM_WAKEUP_FILTER; + i++; + } + +skip_arp: + if (adapter->wol & WAKE_MAGIC) + pmConf->wakeUpEvents |= VMXNET3_PM_WAKEUP_MAGIC; + + pmConf->numFilters = i; + + adapter->shared->devRead.pmConfDesc.confVer = cpu_to_le32(1); + adapter->shared->devRead.pmConfDesc.confLen = cpu_to_le32(sizeof( + *pmConf)); + adapter->shared->devRead.pmConfDesc.confPA = + cpu_to_le64(adapter->pm_conf_pa); + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_PMCFG); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + pci_save_state(pdev); + pci_enable_wake(pdev, pci_choose_state(pdev, PMSG_SUSPEND), + adapter->wol); + pci_disable_device(pdev); + pci_set_power_state(pdev, pci_choose_state(pdev, PMSG_SUSPEND)); + + return 0; +} + + +static int +vmxnet3_resume(struct device *device) +{ + int err; + unsigned long flags; + struct pci_dev *pdev = to_pci_dev(device); + struct net_device *netdev = pci_get_drvdata(pdev); + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!netif_running(netdev)) + return 0; + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + err = pci_enable_device_mem(pdev); + if (err != 0) + return err; + + pci_enable_wake(pdev, PCI_D0, 0); + + vmxnet3_alloc_intr_resources(adapter); + + /* During hibernate and suspend, device has to be reinitialized as the + * device state need not be preserved. + */ + + /* Need not check adapter state as other reset tasks cannot run during + * device resume. + */ + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_QUIESCE_DEV); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + vmxnet3_tq_cleanup_all(adapter); + vmxnet3_rq_cleanup_all(adapter); + + vmxnet3_reset_dev(adapter); + err = vmxnet3_activate_dev(adapter); + if (err != 0) { + netdev_err(netdev, + "failed to re-activate on resume, error: %d", err); + vmxnet3_force_close(adapter); + return err; + } + netif_device_attach(netdev); + + return 0; +} + +static const struct dev_pm_ops vmxnet3_pm_ops = { + .suspend = vmxnet3_suspend, + .resume = vmxnet3_resume, + .freeze = vmxnet3_suspend, + .restore = vmxnet3_resume, +}; +#endif + +static struct pci_driver vmxnet3_driver = { + .name = vmxnet3_driver_name, + .id_table = vmxnet3_pciid_table, + .probe = vmxnet3_probe_device, + .remove = vmxnet3_remove_device, + .shutdown = vmxnet3_shutdown_device, +#ifdef CONFIG_PM + .driver.pm = &vmxnet3_pm_ops, +#endif +}; + + +static int __init +vmxnet3_init_module(void) +{ + pr_info("%s - version %s\n", VMXNET3_DRIVER_DESC, + VMXNET3_DRIVER_VERSION_REPORT); + return pci_register_driver(&vmxnet3_driver); +} + +module_init(vmxnet3_init_module); + + +static void +vmxnet3_exit_module(void) +{ + pci_unregister_driver(&vmxnet3_driver); +} + +module_exit(vmxnet3_exit_module); + +MODULE_AUTHOR("VMware, Inc."); +MODULE_DESCRIPTION(VMXNET3_DRIVER_DESC); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION(VMXNET3_DRIVER_VERSION_STRING); diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c new file mode 100644 index 0000000000..98c22d7d87 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -0,0 +1,1377 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, 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: pv-drivers@vmware.com + * + */ + + +#include "vmxnet3_int.h" +#include <net/vxlan.h> +#include <net/geneve.h> +#include "vmxnet3_xdp.h" + +#define VXLAN_UDP_PORT 8472 + +struct vmxnet3_stat_desc { + char desc[ETH_GSTRING_LEN]; + int offset; +}; + + +/* per tq stats maintained by the device */ +static const struct vmxnet3_stat_desc +vmxnet3_tq_dev_stats[] = { + /* description, offset */ + { "Tx Queue#", 0 }, + { " TSO pkts tx", offsetof(struct UPT1_TxStats, TSOPktsTxOK) }, + { " TSO bytes tx", offsetof(struct UPT1_TxStats, TSOBytesTxOK) }, + { " ucast pkts tx", offsetof(struct UPT1_TxStats, ucastPktsTxOK) }, + { " ucast bytes tx", offsetof(struct UPT1_TxStats, ucastBytesTxOK) }, + { " mcast pkts tx", offsetof(struct UPT1_TxStats, mcastPktsTxOK) }, + { " mcast bytes tx", offsetof(struct UPT1_TxStats, mcastBytesTxOK) }, + { " bcast pkts tx", offsetof(struct UPT1_TxStats, bcastPktsTxOK) }, + { " bcast bytes tx", offsetof(struct UPT1_TxStats, bcastBytesTxOK) }, + { " pkts tx err", offsetof(struct UPT1_TxStats, pktsTxError) }, + { " pkts tx discard", offsetof(struct UPT1_TxStats, pktsTxDiscard) }, +}; + +/* per tq stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_tq_driver_stats[] = { + /* description, offset */ + {" drv dropped tx total", offsetof(struct vmxnet3_tq_driver_stats, + drop_total) }, + { " too many frags", offsetof(struct vmxnet3_tq_driver_stats, + drop_too_many_frags) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + drop_oversized_hdr) }, + { " hdr err", offsetof(struct vmxnet3_tq_driver_stats, + drop_hdr_inspect_err) }, + { " tso", offsetof(struct vmxnet3_tq_driver_stats, + drop_tso) }, + { " ring full", offsetof(struct vmxnet3_tq_driver_stats, + tx_ring_full) }, + { " pkts linearized", offsetof(struct vmxnet3_tq_driver_stats, + linearized) }, + { " hdr cloned", offsetof(struct vmxnet3_tq_driver_stats, + copy_skb_header) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + oversized_hdr) }, + { " xdp xmit", offsetof(struct vmxnet3_tq_driver_stats, + xdp_xmit) }, + { " xdp xmit err", offsetof(struct vmxnet3_tq_driver_stats, + xdp_xmit_err) }, +}; + +/* per rq stats maintained by the device */ +static const struct vmxnet3_stat_desc +vmxnet3_rq_dev_stats[] = { + { "Rx Queue#", 0 }, + { " LRO pkts rx", offsetof(struct UPT1_RxStats, LROPktsRxOK) }, + { " LRO byte rx", offsetof(struct UPT1_RxStats, LROBytesRxOK) }, + { " ucast pkts rx", offsetof(struct UPT1_RxStats, ucastPktsRxOK) }, + { " ucast bytes rx", offsetof(struct UPT1_RxStats, ucastBytesRxOK) }, + { " mcast pkts rx", offsetof(struct UPT1_RxStats, mcastPktsRxOK) }, + { " mcast bytes rx", offsetof(struct UPT1_RxStats, mcastBytesRxOK) }, + { " bcast pkts rx", offsetof(struct UPT1_RxStats, bcastPktsRxOK) }, + { " bcast bytes rx", offsetof(struct UPT1_RxStats, bcastBytesRxOK) }, + { " pkts rx OOB", offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) }, + { " pkts rx err", offsetof(struct UPT1_RxStats, pktsRxError) }, +}; + +/* per rq stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_rq_driver_stats[] = { + /* description, offset */ + { " drv dropped rx total", offsetof(struct vmxnet3_rq_driver_stats, + drop_total) }, + { " err", offsetof(struct vmxnet3_rq_driver_stats, + drop_err) }, + { " fcs", offsetof(struct vmxnet3_rq_driver_stats, + drop_fcs) }, + { " rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats, + rx_buf_alloc_failure) }, + { " xdp packets", offsetof(struct vmxnet3_rq_driver_stats, + xdp_packets) }, + { " xdp tx", offsetof(struct vmxnet3_rq_driver_stats, + xdp_tx) }, + { " xdp redirects", offsetof(struct vmxnet3_rq_driver_stats, + xdp_redirects) }, + { " xdp drops", offsetof(struct vmxnet3_rq_driver_stats, + xdp_drops) }, + { " xdp aborted", offsetof(struct vmxnet3_rq_driver_stats, + xdp_aborted) }, +}; + +/* global stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_global_stats[] = { + /* description, offset */ + { "tx timeout count", offsetof(struct vmxnet3_adapter, + tx_timeout_count) } +}; + + +void +vmxnet3_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct vmxnet3_adapter *adapter; + struct vmxnet3_tq_driver_stats *drvTxStats; + struct vmxnet3_rq_driver_stats *drvRxStats; + struct UPT1_TxStats *devTxStats; + struct UPT1_RxStats *devRxStats; + unsigned long flags; + int i; + + adapter = netdev_priv(netdev); + + /* Collect the dev stats into the shared area */ + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + for (i = 0; i < adapter->num_tx_queues; i++) { + devTxStats = &adapter->tqd_start[i].stats; + drvTxStats = &adapter->tx_queue[i].stats; + stats->tx_packets += devTxStats->ucastPktsTxOK + + devTxStats->mcastPktsTxOK + + devTxStats->bcastPktsTxOK; + stats->tx_bytes += devTxStats->ucastBytesTxOK + + devTxStats->mcastBytesTxOK + + devTxStats->bcastBytesTxOK; + stats->tx_errors += devTxStats->pktsTxError; + stats->tx_dropped += drvTxStats->drop_total; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + devRxStats = &adapter->rqd_start[i].stats; + drvRxStats = &adapter->rx_queue[i].stats; + stats->rx_packets += devRxStats->ucastPktsRxOK + + devRxStats->mcastPktsRxOK + + devRxStats->bcastPktsRxOK; + + stats->rx_bytes += devRxStats->ucastBytesRxOK + + devRxStats->mcastBytesRxOK + + devRxStats->bcastBytesRxOK; + + stats->rx_errors += devRxStats->pktsRxError; + stats->rx_dropped += drvRxStats->drop_total; + stats->multicast += devRxStats->mcastPktsRxOK; + } +} + +static int +vmxnet3_get_sset_count(struct net_device *netdev, int sset) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + switch (sset) { + case ETH_SS_STATS: + return (ARRAY_SIZE(vmxnet3_tq_dev_stats) + + ARRAY_SIZE(vmxnet3_tq_driver_stats)) * + adapter->num_tx_queues + + (ARRAY_SIZE(vmxnet3_rq_dev_stats) + + ARRAY_SIZE(vmxnet3_rq_driver_stats)) * + adapter->num_rx_queues + + ARRAY_SIZE(vmxnet3_global_stats); + default: + return -EOPNOTSUPP; + } +} + + +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ +static int +vmxnet3_get_regs_len(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + return ((9 /* BAR1 registers */ + + (1 + adapter->intr.num_intrs) + + (1 + adapter->num_tx_queues * 17 /* Tx queue registers */) + + (1 + adapter->num_rx_queues * 23 /* Rx queue registers */)) * + sizeof(u32)); +} + + +static void +vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + strscpy(drvinfo->driver, vmxnet3_driver_name, sizeof(drvinfo->driver)); + + strscpy(drvinfo->version, VMXNET3_DRIVER_VERSION_REPORT, + sizeof(drvinfo->version)); + + strscpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); +} + + +static void +vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int i, j; + + if (stringset != ETH_SS_STATS) + return; + + for (j = 0; j < adapter->num_tx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) + ethtool_sprintf(&buf, vmxnet3_tq_dev_stats[i].desc); + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) + ethtool_sprintf(&buf, vmxnet3_tq_driver_stats[i].desc); + } + + for (j = 0; j < adapter->num_rx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) + ethtool_sprintf(&buf, vmxnet3_rq_dev_stats[i].desc); + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) + ethtool_sprintf(&buf, vmxnet3_rq_driver_stats[i].desc); + } + + for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) + ethtool_sprintf(&buf, vmxnet3_global_stats[i].desc); +} + +netdev_features_t vmxnet3_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* If Rx checksum is disabled, then LRO should also be disabled */ + if (!(features & NETIF_F_RXCSUM)) + features &= ~NETIF_F_LRO; + + /* If XDP is enabled, then LRO should not be enabled */ + if (vmxnet3_xdp_enabled(adapter) && (features & NETIF_F_LRO)) { + netdev_err(netdev, "LRO is not supported with XDP"); + features &= ~NETIF_F_LRO; + } + + return features; +} + +netdev_features_t vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* Validate if the tunneled packet is being offloaded by the device */ + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { + u8 l4_proto = 0; + u16 port; + struct udphdr *udph; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + l4_proto = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + l4_proto = ipv6_hdr(skb)->nexthdr; + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + + switch (l4_proto) { + case IPPROTO_UDP: + udph = udp_hdr(skb); + port = be16_to_cpu(udph->dest); + /* Check if offloaded port is supported */ + if (port != GENEVE_UDP_PORT && + port != IANA_VXLAN_UDP_PORT && + port != VXLAN_UDP_PORT) { + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + } + return features; +} + +static void vmxnet3_enable_encap_offloads(struct net_device *netdev, netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (VMXNET3_VERSION_GE_4(adapter)) { + netdev->hw_enc_features |= NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO; + if (features & NETIF_F_GSO_UDP_TUNNEL) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD; + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_TSO)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_TSO))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL; + } + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } +} + +static void vmxnet3_disable_encap_offloads(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (VMXNET3_VERSION_GE_4(adapter)) { + netdev->hw_enc_features &= ~(NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM); + } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_GENEVE_TSO | + 1UL << VMXNET3_CAP_VXLAN_TSO | + 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } +} + +int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + netdev_features_t changed = features ^ netdev->features; + netdev_features_t tun_offload_mask = NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + u8 udp_tun_enabled = (netdev->features & tun_offload_mask) != 0; + + if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO | + NETIF_F_HW_VLAN_CTAG_RX | tun_offload_mask)) { + if (features & NETIF_F_RXCSUM) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXCSUM; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXCSUM; + + /* update hardware LRO capability accordingly */ + if (features & NETIF_F_LRO) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_LRO; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_LRO; + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXVLAN; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXVLAN; + + if ((features & tun_offload_mask) != 0) { + vmxnet3_enable_encap_offloads(netdev, features); + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXINNEROFLD; + } else if ((features & tun_offload_mask) == 0 && + udp_tun_enabled) { + vmxnet3_disable_encap_offloads(netdev); + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXINNEROFLD; + } + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_FEATURE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + return 0; +} + +static void +vmxnet3_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *buf) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + u8 *base; + int i; + int j = 0; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + /* this does assume each counter is 64-bit wide */ + for (j = 0; j < adapter->num_tx_queues; j++) { + base = (u8 *)&adapter->tqd_start[j].stats; + *buf++ = (u64)j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_dev_stats[i].offset); + + base = (u8 *)&adapter->tx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_driver_stats[i].offset); + } + + for (j = 0; j < adapter->num_rx_queues; j++) { + base = (u8 *)&adapter->rqd_start[j].stats; + *buf++ = (u64) j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_dev_stats[i].offset); + + base = (u8 *)&adapter->rx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_driver_stats[i].offset); + } + + base = (u8 *)adapter; + for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) + *buf++ = *(u64 *)(base + vmxnet3_global_stats[i].offset); +} + + +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ +static void +vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + u32 *buf = p; + int i = 0, j = 0; + + memset(p, 0, vmxnet3_get_regs_len(netdev)); + + regs->version = 2; + + /* Update vmxnet3_get_regs_len if we want to dump more registers */ + + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ECR); + + buf[j++] = adapter->intr.num_intrs; + for (i = 0; i < adapter->intr.num_intrs; i++) { + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_IMR + + i * VMXNET3_REG_ALIGN); + } + + buf[j++] = adapter->num_tx_queues; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->tx_prod_offset + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->tx_ring.basePA); + buf[j++] = tq->tx_ring.size; + buf[j++] = tq->tx_ring.next2fill; + buf[j++] = tq->tx_ring.next2comp; + buf[j++] = tq->tx_ring.gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA); + buf[j++] = tq->data_ring.size; + buf[j++] = tq->txdata_desc_size; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA); + buf[j++] = tq->comp_ring.size; + buf[j++] = tq->comp_ring.next2proc; + buf[j++] = tq->comp_ring.gen; + + buf[j++] = tq->stopped; + } + + buf[j++] = adapter->num_rx_queues; + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod_offset + + i * VMXNET3_REG_ALIGN); + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod2_offset + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[0].basePA); + buf[j++] = rq->rx_ring[0].size; + buf[j++] = rq->rx_ring[0].next2fill; + buf[j++] = rq->rx_ring[0].next2comp; + buf[j++] = rq->rx_ring[0].gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[1].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[1].basePA); + buf[j++] = rq->rx_ring[1].size; + buf[j++] = rq->rx_ring[1].next2fill; + buf[j++] = rq->rx_ring[1].next2comp; + buf[j++] = rq->rx_ring[1].gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->data_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->data_ring.basePA); + buf[j++] = rq->rx_ring[0].size; + buf[j++] = rq->data_ring.desc_size; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA); + buf[j++] = rq->comp_ring.size; + buf[j++] = rq->comp_ring.next2proc; + buf[j++] = rq->comp_ring.gen; + } +} + + +static void +vmxnet3_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + wol->supported = WAKE_UCAST | WAKE_ARP | WAKE_MAGIC; + wol->wolopts = adapter->wol; +} + + +static int +vmxnet3_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & (WAKE_PHY | WAKE_MCAST | WAKE_BCAST | + WAKE_MAGICSECURE)) { + return -EOPNOTSUPP; + } + + adapter->wol = wol->wolopts; + + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + + +static int +vmxnet3_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ecmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ecmd, supported, TP); + ethtool_link_ksettings_zero_link_mode(ecmd, advertising); + ethtool_link_ksettings_add_link_mode(ecmd, advertising, TP); + ecmd->base.port = PORT_TP; + + if (adapter->link_speed) { + ecmd->base.speed = adapter->link_speed; + ecmd->base.duplex = DUPLEX_FULL; + } else { + ecmd->base.speed = SPEED_UNKNOWN; + ecmd->base.duplex = DUPLEX_UNKNOWN; + } + return 0; +} + +static void +vmxnet3_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + param->rx_max_pending = VMXNET3_RX_RING_MAX_SIZE; + param->tx_max_pending = VMXNET3_TX_RING_MAX_SIZE; + param->rx_mini_max_pending = VMXNET3_VERSION_GE_3(adapter) ? + VMXNET3_RXDATA_DESC_MAX_SIZE : 0; + param->rx_jumbo_max_pending = VMXNET3_RX_RING2_MAX_SIZE; + + param->rx_pending = adapter->rx_ring_size; + param->tx_pending = adapter->tx_ring_size; + param->rx_mini_pending = VMXNET3_VERSION_GE_3(adapter) ? + adapter->rxdata_desc_size : 0; + param->rx_jumbo_pending = adapter->rx_ring2_size; +} + +static int +vmxnet3_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size; + u16 new_rxdata_desc_size; + u32 sz; + int err = 0; + + if (param->tx_pending == 0 || param->tx_pending > + VMXNET3_TX_RING_MAX_SIZE) + return -EINVAL; + + if (param->rx_pending == 0 || param->rx_pending > + VMXNET3_RX_RING_MAX_SIZE) + return -EINVAL; + + if (param->rx_jumbo_pending == 0 || + param->rx_jumbo_pending > VMXNET3_RX_RING2_MAX_SIZE) + return -EINVAL; + + /* if adapter not yet initialized, do nothing */ + if (adapter->rx_buf_per_pkt == 0) { + netdev_err(netdev, "adapter not completely initialized, " + "ring size cannot be changed yet\n"); + return -EOPNOTSUPP; + } + + if (VMXNET3_VERSION_GE_3(adapter)) { + if (param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) + return -EINVAL; + } else if (param->rx_mini_pending != 0) { + return -EINVAL; + } + + /* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */ + new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) & + ~VMXNET3_RING_SIZE_MASK; + new_tx_ring_size = min_t(u32, new_tx_ring_size, + VMXNET3_TX_RING_MAX_SIZE); + if (new_tx_ring_size > VMXNET3_TX_RING_MAX_SIZE || (new_tx_ring_size % + VMXNET3_RING_SIZE_ALIGN) != 0) + return -EINVAL; + + /* ring0 has to be a multiple of + * rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN + */ + sz = adapter->rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN; + new_rx_ring_size = (param->rx_pending + sz - 1) / sz * sz; + new_rx_ring_size = min_t(u32, new_rx_ring_size, + VMXNET3_RX_RING_MAX_SIZE / sz * sz); + if (new_rx_ring_size > VMXNET3_RX_RING_MAX_SIZE || (new_rx_ring_size % + sz) != 0) + return -EINVAL; + + /* ring2 has to be a multiple of VMXNET3_RING_SIZE_ALIGN */ + new_rx_ring2_size = (param->rx_jumbo_pending + VMXNET3_RING_SIZE_MASK) & + ~VMXNET3_RING_SIZE_MASK; + new_rx_ring2_size = min_t(u32, new_rx_ring2_size, + VMXNET3_RX_RING2_MAX_SIZE); + + /* For v7 and later, keep ring size power of 2 for UPT */ + if (VMXNET3_VERSION_GE_7(adapter)) { + new_tx_ring_size = rounddown_pow_of_two(new_tx_ring_size); + new_rx_ring_size = rounddown_pow_of_two(new_rx_ring_size); + new_rx_ring2_size = rounddown_pow_of_two(new_rx_ring2_size); + } + + /* rx data ring buffer size has to be a multiple of + * VMXNET3_RXDATA_DESC_SIZE_ALIGN + */ + new_rxdata_desc_size = + (param->rx_mini_pending + VMXNET3_RXDATA_DESC_SIZE_MASK) & + ~VMXNET3_RXDATA_DESC_SIZE_MASK; + new_rxdata_desc_size = min_t(u16, new_rxdata_desc_size, + VMXNET3_RXDATA_DESC_MAX_SIZE); + + if (new_tx_ring_size == adapter->tx_ring_size && + new_rx_ring_size == adapter->rx_ring_size && + new_rx_ring2_size == adapter->rx_ring2_size && + new_rxdata_desc_size == adapter->rxdata_desc_size) { + return 0; + } + + /* + * Reset_work may be in the middle of resetting the device, wait for its + * completion. + */ + while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(netdev)) { + vmxnet3_quiesce_dev(adapter); + vmxnet3_reset_dev(adapter); + + /* recreate the rx queue and the tx queue based on the + * new sizes */ + vmxnet3_tq_destroy_all(adapter); + vmxnet3_rq_destroy_all(adapter); + + err = vmxnet3_create_queues(adapter, new_tx_ring_size, + new_rx_ring_size, new_rx_ring2_size, + adapter->txdata_desc_size, + new_rxdata_desc_size); + if (err) { + /* failed, most likely because of OOM, try default + * size */ + netdev_err(netdev, "failed to apply new sizes, " + "try the default ones\n"); + new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE; + new_rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE; + new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE; + new_rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ? + VMXNET3_DEF_RXDATA_DESC_SIZE : 0; + + err = vmxnet3_create_queues(adapter, + new_tx_ring_size, + new_rx_ring_size, + new_rx_ring2_size, + adapter->txdata_desc_size, + new_rxdata_desc_size); + if (err) { + netdev_err(netdev, "failed to create queues " + "with default sizes. Closing it\n"); + goto out; + } + } + + err = vmxnet3_activate_dev(adapter); + if (err) + netdev_err(netdev, "failed to re-activate, error %d." + " Closing it\n", err); + } + adapter->tx_ring_size = new_tx_ring_size; + adapter->rx_ring_size = new_rx_ring_size; + adapter->rx_ring2_size = new_rx_ring2_size; + adapter->rxdata_desc_size = new_rxdata_desc_size; + +out: + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + if (err) + vmxnet3_force_close(adapter); + + return err; +} + +static int +vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter, + struct ethtool_rxnfc *info) +{ + enum Vmxnet3_RSSField rss_fields; + + if (netif_running(adapter->netdev)) { + unsigned long flags; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + rss_fields = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } else { + rss_fields = adapter->rss_fields; + } + + info->data = 0; + + /* Report default options for RSS on vmxnet3 */ + switch (info->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 | + RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V4_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP4) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V4_FLOW: + case IPV4_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V6_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + if (VMXNET3_VERSION_GE_6(adapter) && + (rss_fields & VMXNET3_RSS_FIELDS_ESPIP6)) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V6_FLOW: + case IPV6_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +vmxnet3_set_rss_hash_opt(struct net_device *netdev, + struct vmxnet3_adapter *adapter, + struct ethtool_rxnfc *nfc) +{ + enum Vmxnet3_RSSField rss_fields = adapter->rss_fields; + + /* RSS does not support anything other than hashing + * to queues on src and dst IPs and ports + */ + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + !(nfc->data & RXH_L4_B_0_1) || + !(nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + case UDP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP4; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_UDPIP4; + break; + default: + return -EINVAL; + } + break; + case UDP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP6; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_UDPIP6; + break; + default: + return -EINVAL; + } + break; + case ESP_V4_FLOW: + case AH_V4_FLOW: + case AH_ESP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP4; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_ESPIP4; + break; + default: + return -EINVAL; + } + break; + case ESP_V6_FLOW: + case AH_V6_FLOW: + case AH_ESP_V6_FLOW: + if (!VMXNET3_VERSION_GE_6(adapter)) + return -EOPNOTSUPP; + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP6; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_ESPIP6; + break; + default: + return -EINVAL; + } + break; + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + (nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* if we changed something we need to update flags */ + if (rss_fields != adapter->rss_fields) { + adapter->default_rss_fields = false; + if (netif_running(netdev)) { + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (VMXNET3_VERSION_GE_7(adapter)) { + if ((rss_fields & VMXNET3_RSS_FIELDS_UDPIP4 || + rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_UDP_RSS)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_UDP_RSS; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_UDP_RSS); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV4)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV4; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV4); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV6)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV6; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV6); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, + adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, + VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + spin_lock_irqsave(&adapter->cmd_lock, flags); + cmdInfo->setRssFields = rss_fields; + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_RSS_FIELDS); + + /* Not all requested RSS may get applied, so get and + * cache what was actually applied. + */ + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + adapter->rss_fields = + VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } else { + /* When the device is activated, we will try to apply + * these rules and cache the applied value later. + */ + adapter->rss_fields = rss_fields; + } + } + return 0; +} + +static int +vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, + u32 *rules) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int err = 0; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = adapter->num_rx_queues; + break; + case ETHTOOL_GRXFH: + if (!VMXNET3_VERSION_GE_4(adapter)) { + err = -EOPNOTSUPP; + break; + } +#ifdef VMXNET3_RSS + if (!adapter->rss) { + err = -EOPNOTSUPP; + break; + } +#endif + err = vmxnet3_get_rss_hash_opts(adapter, info); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int +vmxnet3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int err = 0; + + if (!VMXNET3_VERSION_GE_4(adapter)) { + err = -EOPNOTSUPP; + goto done; + } +#ifdef VMXNET3_RSS + if (!adapter->rss) { + err = -EOPNOTSUPP; + goto done; + } +#endif + + switch (info->cmd) { + case ETHTOOL_SRXFH: + err = vmxnet3_set_rss_hash_opt(netdev, adapter, info); + break; + default: + err = -EOPNOTSUPP; + break; + } + +done: + return err; +} + +#ifdef VMXNET3_RSS +static u32 +vmxnet3_get_rss_indir_size(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + return rssConf->indTableSize; +} + +static int +vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + unsigned int n = rssConf->indTableSize; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!p) + return 0; + if (n > UPT1_RSS_MAX_IND_TABLE_SIZE) + return 0; + while (n--) + p[n] = rssConf->indTable[n]; + return 0; + +} + +static int +vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key, + const u8 hfunc) +{ + unsigned int i; + unsigned long flags; + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!p) + return 0; + for (i = 0; i < rssConf->indTableSize; i++) + rssConf->indTable[i] = p[i]; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_RSSIDT); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + return 0; + +} +#endif + +static int vmxnet3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!VMXNET3_VERSION_GE_3(adapter)) + return -EOPNOTSUPP; + + switch (adapter->coal_conf->coalMode) { + case VMXNET3_COALESCE_DISABLED: + /* struct ethtool_coalesce is already initialized to 0 */ + break; + case VMXNET3_COALESCE_ADAPT: + ec->use_adaptive_rx_coalesce = true; + break; + case VMXNET3_COALESCE_STATIC: + ec->tx_max_coalesced_frames = + adapter->coal_conf->coalPara.coalStatic.tx_comp_depth; + ec->rx_max_coalesced_frames = + adapter->coal_conf->coalPara.coalStatic.rx_depth; + break; + case VMXNET3_COALESCE_RBC: { + u32 rbc_rate; + + rbc_rate = adapter->coal_conf->coalPara.coalRbc.rbc_rate; + ec->rx_coalesce_usecs = VMXNET3_COAL_RBC_USECS(rbc_rate); + } + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int vmxnet3_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_3(adapter)) + return -EOPNOTSUPP; + + if ((ec->rx_coalesce_usecs == 0) && + (ec->use_adaptive_rx_coalesce == 0) && + (ec->tx_max_coalesced_frames == 0) && + (ec->rx_max_coalesced_frames == 0)) { + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED; + goto done; + } + + if (ec->rx_coalesce_usecs != 0) { + u32 rbc_rate; + + if ((ec->use_adaptive_rx_coalesce != 0) || + (ec->tx_max_coalesced_frames != 0) || + (ec->rx_max_coalesced_frames != 0)) { + return -EINVAL; + } + + rbc_rate = VMXNET3_COAL_RBC_RATE(ec->rx_coalesce_usecs); + if (rbc_rate < VMXNET3_COAL_RBC_MIN_RATE || + rbc_rate > VMXNET3_COAL_RBC_MAX_RATE) { + return -EINVAL; + } + + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_RBC; + adapter->coal_conf->coalPara.coalRbc.rbc_rate = rbc_rate; + goto done; + } + + if (ec->use_adaptive_rx_coalesce != 0) { + if (ec->tx_max_coalesced_frames != 0 || + ec->rx_max_coalesced_frames != 0) { + return -EINVAL; + } + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_ADAPT; + goto done; + } + + if ((ec->tx_max_coalesced_frames != 0) || + (ec->rx_max_coalesced_frames != 0)) { + if ((ec->tx_max_coalesced_frames > + VMXNET3_COAL_STATIC_MAX_DEPTH) || + (ec->rx_max_coalesced_frames > + VMXNET3_COAL_STATIC_MAX_DEPTH)) { + return -EINVAL; + } + + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_STATIC; + + adapter->coal_conf->coalPara.coalStatic.tx_comp_depth = + (ec->tx_max_coalesced_frames ? + ec->tx_max_coalesced_frames : + VMXNET3_COAL_STATIC_DEFAULT_DEPTH); + + adapter->coal_conf->coalPara.coalStatic.rx_depth = + (ec->rx_max_coalesced_frames ? + ec->rx_max_coalesced_frames : + VMXNET3_COAL_STATIC_DEFAULT_DEPTH); + + adapter->coal_conf->coalPara.coalStatic.tx_depth = + VMXNET3_COAL_STATIC_DEFAULT_DEPTH; + goto done; + } + +done: + adapter->default_coal_mode = false; + if (netif_running(netdev)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); + cmdInfo->varConf.confVer = 1; + cmdInfo->varConf.confLen = + cpu_to_le32(sizeof(*adapter->coal_conf)); + cmdInfo->varConf.confPA = cpu_to_le64(adapter->coal_conf_pa); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_COALESCE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + return 0; +} + +static void vmxnet3_get_channels(struct net_device *netdev, + struct ethtool_channels *ec) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (IS_ENABLED(CONFIG_PCI_MSI) && adapter->intr.type == VMXNET3_IT_MSIX) { + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) { + ec->combined_count = adapter->num_tx_queues; + } else { + ec->rx_count = adapter->num_rx_queues; + ec->tx_count = + adapter->share_intr == VMXNET3_INTR_TXSHARE ? + 1 : adapter->num_tx_queues; + } + } else { + ec->combined_count = 1; + } + + ec->other_count = 1; + + /* Number of interrupts cannot be changed on the fly */ + /* Just set maximums to actual values */ + ec->max_rx = ec->rx_count; + ec->max_tx = ec->tx_count; + ec->max_combined = ec->combined_count; + ec->max_other = ec->other_count; +} + +static const struct ethtool_ops vmxnet3_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, + .get_drvinfo = vmxnet3_get_drvinfo, + .get_regs_len = vmxnet3_get_regs_len, + .get_regs = vmxnet3_get_regs, + .get_wol = vmxnet3_get_wol, + .set_wol = vmxnet3_set_wol, + .get_link = ethtool_op_get_link, + .get_coalesce = vmxnet3_get_coalesce, + .set_coalesce = vmxnet3_set_coalesce, + .get_strings = vmxnet3_get_strings, + .get_sset_count = vmxnet3_get_sset_count, + .get_ethtool_stats = vmxnet3_get_ethtool_stats, + .get_ringparam = vmxnet3_get_ringparam, + .set_ringparam = vmxnet3_set_ringparam, + .get_rxnfc = vmxnet3_get_rxnfc, + .set_rxnfc = vmxnet3_set_rxnfc, +#ifdef VMXNET3_RSS + .get_rxfh_indir_size = vmxnet3_get_rss_indir_size, + .get_rxfh = vmxnet3_get_rss, + .set_rxfh = vmxnet3_set_rss, +#endif + .get_link_ksettings = vmxnet3_get_link_ksettings, + .get_channels = vmxnet3_get_channels, +}; + +void vmxnet3_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &vmxnet3_ethtool_ops; +} diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h new file mode 100644 index 0000000000..915aaf18c4 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -0,0 +1,538 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, 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: pv-drivers@vmware.com + * + */ + +#ifndef _VMXNET3_INT_H +#define _VMXNET3_INT_H + +#include <linux/bitops.h> +#include <linux/ethtool.h> +#include <linux/delay.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/compiler.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/ioport.h> +#include <linux/highmem.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/interrupt.h> +#include <linux/workqueue.h> +#include <linux/uaccess.h> +#include <asm/dma.h> +#include <asm/page.h> + +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/etherdevice.h> +#include <asm/checksum.h> +#include <linux/if_vlan.h> +#include <linux/if_arp.h> +#include <linux/inetdevice.h> +#include <linux/log2.h> +#include <linux/bpf.h> +#include <net/page_pool/helpers.h> +#include <net/xdp.h> + +#include "vmxnet3_defs.h" + +#ifdef DEBUG +# define VMXNET3_DRIVER_VERSION_REPORT VMXNET3_DRIVER_VERSION_STRING"-NAPI(debug)" +#else +# define VMXNET3_DRIVER_VERSION_REPORT VMXNET3_DRIVER_VERSION_STRING"-NAPI" +#endif + + +/* + * Version numbers + */ +#define VMXNET3_DRIVER_VERSION_STRING "1.7.0.0-k" + +/* Each byte of this 32-bit integer encodes a version number in + * VMXNET3_DRIVER_VERSION_STRING. + */ +#define VMXNET3_DRIVER_VERSION_NUM 0x01070000 + +#if defined(CONFIG_PCI_MSI) + /* RSS only makes sense if MSI-X is supported. */ + #define VMXNET3_RSS +#endif + +#define VMXNET3_REV_7 6 /* Vmxnet3 Rev. 7 */ +#define VMXNET3_REV_6 5 /* Vmxnet3 Rev. 6 */ +#define VMXNET3_REV_5 4 /* Vmxnet3 Rev. 5 */ +#define VMXNET3_REV_4 3 /* Vmxnet3 Rev. 4 */ +#define VMXNET3_REV_3 2 /* Vmxnet3 Rev. 3 */ +#define VMXNET3_REV_2 1 /* Vmxnet3 Rev. 2 */ +#define VMXNET3_REV_1 0 /* Vmxnet3 Rev. 1 */ + +/* + * Capabilities + */ + +enum { + VMNET_CAP_SG = 0x0001, /* Can do scatter-gather transmits. */ + VMNET_CAP_IP4_CSUM = 0x0002, /* Can checksum only TCP/UDP over + * IPv4 */ + VMNET_CAP_HW_CSUM = 0x0004, /* Can checksum all packets. */ + VMNET_CAP_HIGH_DMA = 0x0008, /* Can DMA to high memory. */ + VMNET_CAP_TOE = 0x0010, /* Supports TCP/IP offload. */ + VMNET_CAP_TSO = 0x0020, /* Supports TCP Segmentation + * offload */ + VMNET_CAP_SW_TSO = 0x0040, /* Supports SW TCP Segmentation */ + VMNET_CAP_VMXNET_APROM = 0x0080, /* Vmxnet APROM support */ + VMNET_CAP_HW_TX_VLAN = 0x0100, /* Can we do VLAN tagging in HW */ + VMNET_CAP_HW_RX_VLAN = 0x0200, /* Can we do VLAN untagging in HW */ + VMNET_CAP_SW_VLAN = 0x0400, /* VLAN tagging/untagging in SW */ + VMNET_CAP_WAKE_PCKT_RCV = 0x0800, /* Can wake on network packet recv? */ + VMNET_CAP_ENABLE_INT_INLINE = 0x1000, /* Enable Interrupt Inline */ + VMNET_CAP_ENABLE_HEADER_COPY = 0x2000, /* copy header for vmkernel */ + VMNET_CAP_TX_CHAIN = 0x4000, /* Guest can use multiple tx entries + * for a pkt */ + VMNET_CAP_RX_CHAIN = 0x8000, /* pkt can span multiple rx entries */ + VMNET_CAP_LPD = 0x10000, /* large pkt delivery */ + VMNET_CAP_BPF = 0x20000, /* BPF Support in VMXNET Virtual HW*/ + VMNET_CAP_SG_SPAN_PAGES = 0x40000, /* Scatter-gather can span multiple*/ + /* pages transmits */ + VMNET_CAP_IP6_CSUM = 0x80000, /* Can do IPv6 csum offload. */ + VMNET_CAP_TSO6 = 0x100000, /* TSO seg. offload for IPv6 pkts. */ + VMNET_CAP_TSO256k = 0x200000, /* Can do TSO seg offload for */ + /* pkts up to 256kB. */ + VMNET_CAP_UPT = 0x400000 /* Support UPT */ +}; + +/* + * Maximum devices supported. + */ +#define MAX_ETHERNET_CARDS 10 +#define MAX_PCI_PASSTHRU_DEVICE 6 + +struct vmxnet3_cmd_ring { + union Vmxnet3_GenericDesc *base; + u32 size; + u32 next2fill; + u32 next2comp; + u8 gen; + u8 isOutOfOrder; + dma_addr_t basePA; +}; + +static inline void +vmxnet3_cmd_ring_adv_next2fill(struct vmxnet3_cmd_ring *ring) +{ + ring->next2fill++; + if (unlikely(ring->next2fill == ring->size)) { + ring->next2fill = 0; + VMXNET3_FLIP_RING_GEN(ring->gen); + } +} + +static inline void +vmxnet3_cmd_ring_adv_next2comp(struct vmxnet3_cmd_ring *ring) +{ + VMXNET3_INC_RING_IDX_ONLY(ring->next2comp, ring->size); +} + +static inline int +vmxnet3_cmd_ring_desc_avail(struct vmxnet3_cmd_ring *ring) +{ + return (ring->next2comp > ring->next2fill ? 0 : ring->size) + + ring->next2comp - ring->next2fill - 1; +} + +struct vmxnet3_comp_ring { + union Vmxnet3_GenericDesc *base; + u32 size; + u32 next2proc; + u8 gen; + u8 intr_idx; + dma_addr_t basePA; +}; + +static inline void +vmxnet3_comp_ring_adv_next2proc(struct vmxnet3_comp_ring *ring) +{ + ring->next2proc++; + if (unlikely(ring->next2proc == ring->size)) { + ring->next2proc = 0; + VMXNET3_FLIP_RING_GEN(ring->gen); + } +} + +struct vmxnet3_tx_data_ring { + struct Vmxnet3_TxDataDesc *base; + u32 size; + dma_addr_t basePA; +}; + +#define VMXNET3_MAP_NONE 0 +#define VMXNET3_MAP_SINGLE BIT(0) +#define VMXNET3_MAP_PAGE BIT(1) +#define VMXNET3_MAP_XDP BIT(2) + +struct vmxnet3_tx_buf_info { + u32 map_type; + u16 len; + u16 sop_idx; + dma_addr_t dma_addr; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; +}; + +struct vmxnet3_tq_driver_stats { + u64 drop_total; /* # of pkts dropped by the driver, the + * counters below track droppings due to + * different reasons + */ + u64 drop_too_many_frags; + u64 drop_oversized_hdr; + u64 drop_hdr_inspect_err; + u64 drop_tso; + + u64 tx_ring_full; + u64 linearized; /* # of pkts linearized */ + u64 copy_skb_header; /* # of times we have to copy skb header */ + u64 oversized_hdr; + + u64 xdp_xmit; + u64 xdp_xmit_err; +}; + +struct vmxnet3_tx_ctx { + bool ipv4; + bool ipv6; + u16 mss; + u32 l4_offset; /* only valid for pkts requesting tso or csum + * offloading. For encap offload, it refers to + * inner L4 offset i.e. it includes outer header + * encap header and inner eth and ip header size + */ + + u32 l4_hdr_size; /* only valid if mss != 0 + * Refers to inner L4 hdr size for encap + * offload + */ + u32 copy_size; /* # of bytes copied into the data ring */ + union Vmxnet3_GenericDesc *sop_txd; + union Vmxnet3_GenericDesc *eop_txd; +}; + +struct vmxnet3_tx_queue { + char name[IFNAMSIZ+8]; /* To identify interrupt */ + struct vmxnet3_adapter *adapter; + spinlock_t tx_lock; + struct vmxnet3_cmd_ring tx_ring; + struct vmxnet3_tx_buf_info *buf_info; + struct vmxnet3_tx_data_ring data_ring; + struct vmxnet3_comp_ring comp_ring; + struct Vmxnet3_TxQueueCtrl *shared; + struct vmxnet3_tq_driver_stats stats; + bool stopped; + int num_stop; /* # of times the queue is + * stopped */ + int qid; + u16 txdata_desc_size; +} ____cacheline_aligned; + +enum vmxnet3_rx_buf_type { + VMXNET3_RX_BUF_NONE = 0, + VMXNET3_RX_BUF_SKB = 1, + VMXNET3_RX_BUF_PAGE = 2, + VMXNET3_RX_BUF_XDP = 3, +}; + +#define VMXNET3_RXD_COMP_PENDING 0 +#define VMXNET3_RXD_COMP_DONE 1 + +struct vmxnet3_rx_buf_info { + enum vmxnet3_rx_buf_type buf_type; + u16 len; + u8 comp_state; + union { + struct sk_buff *skb; + struct page *page; + }; + dma_addr_t dma_addr; +}; + +struct vmxnet3_rx_ctx { + struct sk_buff *skb; + u32 sop_idx; +}; + +struct vmxnet3_rq_driver_stats { + u64 drop_total; + u64 drop_err; + u64 drop_fcs; + u64 rx_buf_alloc_failure; + + u64 xdp_packets; /* Total packets processed by XDP. */ + u64 xdp_tx; + u64 xdp_redirects; + u64 xdp_drops; + u64 xdp_aborted; +}; + +struct vmxnet3_rx_data_ring { + Vmxnet3_RxDataDesc *base; + dma_addr_t basePA; + u16 desc_size; +}; + +struct vmxnet3_rx_queue { + char name[IFNAMSIZ + 8]; /* To identify interrupt */ + struct vmxnet3_adapter *adapter; + struct napi_struct napi; + struct vmxnet3_cmd_ring rx_ring[2]; + struct vmxnet3_rx_data_ring data_ring; + struct vmxnet3_comp_ring comp_ring; + struct vmxnet3_rx_ctx rx_ctx; + u32 qid; /* rqID in RCD for buffer from 1st ring */ + u32 qid2; /* rqID in RCD for buffer from 2nd ring */ + u32 dataRingQid; /* rqID in RCD for buffer from data ring */ + struct vmxnet3_rx_buf_info *buf_info[2]; + struct Vmxnet3_RxQueueCtrl *shared; + struct vmxnet3_rq_driver_stats stats; + struct page_pool *page_pool; + struct xdp_rxq_info xdp_rxq; +} ____cacheline_aligned; + +#define VMXNET3_DEVICE_MAX_TX_QUEUES 32 +#define VMXNET3_DEVICE_MAX_RX_QUEUES 32 /* Keep this value as a power of 2 */ + +#define VMXNET3_DEVICE_DEFAULT_TX_QUEUES 8 +#define VMXNET3_DEVICE_DEFAULT_RX_QUEUES 8 /* Keep this value as a power of 2 */ + +/* Should be less than UPT1_RSS_MAX_IND_TABLE_SIZE */ +#define VMXNET3_RSS_IND_TABLE_SIZE (VMXNET3_DEVICE_MAX_RX_QUEUES * 4) + +#define VMXNET3_LINUX_MAX_MSIX_VECT (VMXNET3_DEVICE_MAX_TX_QUEUES + \ + VMXNET3_DEVICE_MAX_RX_QUEUES + 1) +#define VMXNET3_LINUX_MIN_MSIX_VECT 3 /* 1 for tx, 1 for rx pair and 1 for event */ + + +struct vmxnet3_intr { + enum vmxnet3_intr_mask_mode mask_mode; + enum vmxnet3_intr_type type; /* MSI-X, MSI, or INTx? */ + u8 num_intrs; /* # of intr vectors */ + u8 event_intr_idx; /* idx of the intr vector for event */ + u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ + char event_msi_vector_name[IFNAMSIZ+17]; +#ifdef CONFIG_PCI_MSI + struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; +#endif +}; + +/* Interrupt sharing schemes, share_intr */ +#define VMXNET3_INTR_BUDDYSHARE 0 /* Corresponding tx,rx queues share irq */ +#define VMXNET3_INTR_TXSHARE 1 /* All tx queues share one irq */ +#define VMXNET3_INTR_DONTSHARE 2 /* each queue has its own irq */ + + +#define VMXNET3_STATE_BIT_RESETTING 0 +#define VMXNET3_STATE_BIT_QUIESCED 1 +struct vmxnet3_adapter { + struct vmxnet3_tx_queue tx_queue[VMXNET3_DEVICE_MAX_TX_QUEUES]; + struct vmxnet3_rx_queue rx_queue[VMXNET3_DEVICE_MAX_RX_QUEUES]; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct vmxnet3_intr intr; + spinlock_t cmd_lock; + struct Vmxnet3_DriverShared *shared; + struct Vmxnet3_PMConf *pm_conf; + struct Vmxnet3_TxQueueDesc *tqd_start; /* all tx queue desc */ + struct Vmxnet3_RxQueueDesc *rqd_start; /* all rx queue desc */ + struct net_device *netdev; + struct pci_dev *pdev; + + u8 __iomem *hw_addr0; /* for BAR 0 */ + u8 __iomem *hw_addr1; /* for BAR 1 */ + u8 version; + +#ifdef VMXNET3_RSS + struct UPT1_RSSConf *rss_conf; + bool rss; +#endif + u32 num_rx_queues; + u32 num_tx_queues; + + /* rx buffer related */ + unsigned skb_buf_size; + int rx_buf_per_pkt; /* only apply to the 1st ring */ + dma_addr_t shared_pa; + dma_addr_t queue_desc_pa; + dma_addr_t coal_conf_pa; + + /* Wake-on-LAN */ + u32 wol; + + /* Link speed */ + u32 link_speed; /* in mbps */ + + u64 tx_timeout_count; + + /* Ring sizes */ + u32 tx_ring_size; + u32 rx_ring_size; + u32 rx_ring2_size; + + /* Size of buffer in the data ring */ + u16 txdata_desc_size; + u16 rxdata_desc_size; + + bool rxdataring_enabled; + bool default_rss_fields; + enum Vmxnet3_RSSField rss_fields; + + struct work_struct work; + + unsigned long state; /* VMXNET3_STATE_BIT_xxx */ + + int share_intr; + + struct Vmxnet3_CoalesceScheme *coal_conf; + bool default_coal_mode; + + dma_addr_t adapter_pa; + dma_addr_t pm_conf_pa; + dma_addr_t rss_conf_pa; + bool queuesExtEnabled; + struct Vmxnet3_RingBufferSize ringBufSize; + u32 devcap_supported[8]; + u32 ptcap_supported[8]; + u32 dev_caps[8]; + u16 tx_prod_offset; + u16 rx_prod_offset; + u16 rx_prod2_offset; + struct bpf_prog __rcu *xdp_bpf_prog; +}; + +#define VMXNET3_WRITE_BAR0_REG(adapter, reg, val) \ + writel((val), (adapter)->hw_addr0 + (reg)) +#define VMXNET3_READ_BAR0_REG(adapter, reg) \ + readl((adapter)->hw_addr0 + (reg)) + +#define VMXNET3_WRITE_BAR1_REG(adapter, reg, val) \ + writel((val), (adapter)->hw_addr1 + (reg)) +#define VMXNET3_READ_BAR1_REG(adapter, reg) \ + readl((adapter)->hw_addr1 + (reg)) + +#define VMXNET3_WAKE_QUEUE_THRESHOLD(tq) (5) +#define VMXNET3_RX_ALLOC_THRESHOLD(rq, ring_idx, adapter) \ + ((rq)->rx_ring[ring_idx].size >> 3) + +#define VMXNET3_GET_ADDR_LO(dma) ((u32)(dma)) +#define VMXNET3_GET_ADDR_HI(dma) ((u32)(((u64)(dma)) >> 32)) + +#define VMXNET3_VERSION_GE_2(adapter) \ + (adapter->version >= VMXNET3_REV_2 + 1) +#define VMXNET3_VERSION_GE_3(adapter) \ + (adapter->version >= VMXNET3_REV_3 + 1) +#define VMXNET3_VERSION_GE_4(adapter) \ + (adapter->version >= VMXNET3_REV_4 + 1) +#define VMXNET3_VERSION_GE_5(adapter) \ + (adapter->version >= VMXNET3_REV_5 + 1) +#define VMXNET3_VERSION_GE_6(adapter) \ + (adapter->version >= VMXNET3_REV_6 + 1) +#define VMXNET3_VERSION_GE_7(adapter) \ + (adapter->version >= VMXNET3_REV_7 + 1) + +/* must be a multiple of VMXNET3_RING_SIZE_ALIGN */ +#define VMXNET3_DEF_TX_RING_SIZE 512 +#define VMXNET3_DEF_RX_RING_SIZE 1024 +#define VMXNET3_DEF_RX_RING2_SIZE 512 + +#define VMXNET3_DEF_RXDATA_DESC_SIZE 128 + +#define VMXNET3_MAX_ETH_HDR_SIZE 22 +#define VMXNET3_MAX_SKB_BUF_SIZE (3*1024) + +#define VMXNET3_GET_RING_IDX(adapter, rqID) \ + ((rqID >= adapter->num_rx_queues && \ + rqID < 2 * adapter->num_rx_queues) ? 1 : 0) \ + +#define VMXNET3_RX_DATA_RING(adapter, rqID) \ + (rqID >= 2 * adapter->num_rx_queues && \ + rqID < 3 * adapter->num_rx_queues) \ + +#define VMXNET3_COAL_STATIC_DEFAULT_DEPTH 64 + +#define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs) +#define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate) +#define VMXNET3_RSS_FIELDS_DEFAULT (VMXNET3_RSS_FIELDS_TCPIP4 | \ + VMXNET3_RSS_FIELDS_TCPIP6) + +int +vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter); + +int +vmxnet3_activate_dev(struct vmxnet3_adapter *adapter); + +void +vmxnet3_force_close(struct vmxnet3_adapter *adapter); + +void +vmxnet3_reset_dev(struct vmxnet3_adapter *adapter); + +void +vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter); + +void +vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter); + +int +vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter); + +void +vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter); + +netdev_features_t +vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features); + +netdev_features_t +vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, netdev_features_t features); + +int +vmxnet3_set_features(struct net_device *netdev, netdev_features_t features); + +int +vmxnet3_create_queues(struct vmxnet3_adapter *adapter, + u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size, + u16 txdata_desc_size, u16 rxdata_desc_size); + +void vmxnet3_set_ethtool_ops(struct net_device *netdev); + +void vmxnet3_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats); +bool vmxnet3_check_ptcapability(u32 cap_supported, u32 cap); + +extern char vmxnet3_driver_name[]; +#endif diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c new file mode 100644 index 0000000000..80ddaff759 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -0,0 +1,419 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved. + * Maintained by: pv-drivers@vmware.com + * + */ + +#include "vmxnet3_int.h" +#include "vmxnet3_xdp.h" + +static void +vmxnet3_xdp_exchange_program(struct vmxnet3_adapter *adapter, + struct bpf_prog *prog) +{ + rcu_assign_pointer(adapter->xdp_bpf_prog, prog); +} + +static inline struct vmxnet3_tx_queue * +vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter) +{ + struct vmxnet3_tx_queue *tq; + int tq_number; + int cpu; + + tq_number = adapter->num_tx_queues; + cpu = smp_processor_id(); + if (likely(cpu < tq_number)) + tq = &adapter->tx_queue[cpu]; + else + tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)]; + + return tq; +} + +static int +vmxnet3_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct bpf_prog *new_bpf_prog = bpf->prog; + struct bpf_prog *old_bpf_prog; + bool need_update; + bool running; + int err; + + if (new_bpf_prog && netdev->mtu > VMXNET3_XDP_MAX_MTU) { + NL_SET_ERR_MSG_FMT_MOD(extack, "MTU %u too large for XDP", + netdev->mtu); + return -EOPNOTSUPP; + } + + if (adapter->netdev->features & NETIF_F_LRO) { + NL_SET_ERR_MSG_MOD(extack, "LRO is not supported with XDP"); + adapter->netdev->features &= ~NETIF_F_LRO; + } + + old_bpf_prog = rcu_dereference(adapter->xdp_bpf_prog); + if (!new_bpf_prog && !old_bpf_prog) + return 0; + + running = netif_running(netdev); + need_update = !!old_bpf_prog != !!new_bpf_prog; + + if (running && need_update) + vmxnet3_quiesce_dev(adapter); + + vmxnet3_xdp_exchange_program(adapter, new_bpf_prog); + if (old_bpf_prog) + bpf_prog_put(old_bpf_prog); + + if (!running || !need_update) + return 0; + + if (new_bpf_prog) + xdp_features_set_redirect_target(netdev, false); + else + xdp_features_clear_redirect_target(netdev); + + vmxnet3_reset_dev(adapter); + vmxnet3_rq_destroy_all(adapter); + vmxnet3_adjust_rx_ring_size(adapter); + err = vmxnet3_rq_create_all(adapter); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "failed to re-create rx queues for XDP."); + return -EOPNOTSUPP; + } + err = vmxnet3_activate_dev(adapter); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "failed to activate device for XDP."); + return -EOPNOTSUPP; + } + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + + return 0; +} + +/* This is the main xdp call used by kernel to set/unset eBPF program. */ +int +vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf) +{ + switch (bpf->command) { + case XDP_SETUP_PROG: + return vmxnet3_xdp_set(netdev, bpf, bpf->extack); + default: + return -EINVAL; + } + + return 0; +} + +static int +vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, + struct xdp_frame *xdpf, + struct vmxnet3_tx_queue *tq, bool dma_map) +{ + struct vmxnet3_tx_buf_info *tbi = NULL; + union Vmxnet3_GenericDesc *gdesc; + struct vmxnet3_tx_ctx ctx; + int tx_num_deferred; + struct page *page; + u32 buf_size; + u32 dw2; + + dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT; + dw2 |= xdpf->len; + ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill; + gdesc = ctx.sop_txd; + + buf_size = xdpf->len; + tbi = tq->buf_info + tq->tx_ring.next2fill; + + if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) { + tq->stats.tx_ring_full++; + return -ENOSPC; + } + + tbi->map_type = VMXNET3_MAP_XDP; + if (dma_map) { /* ndo_xdp_xmit */ + tbi->dma_addr = dma_map_single(&adapter->pdev->dev, + xdpf->data, buf_size, + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) + return -EFAULT; + tbi->map_type |= VMXNET3_MAP_SINGLE; + } else { /* XDP buffer from page pool */ + page = virt_to_page(xdpf->data); + tbi->dma_addr = page_pool_get_dma_addr(page) + + VMXNET3_XDP_HEADROOM; + dma_sync_single_for_device(&adapter->pdev->dev, + tbi->dma_addr, buf_size, + DMA_TO_DEVICE); + } + tbi->xdpf = xdpf; + tbi->len = buf_size; + + gdesc = tq->tx_ring.base + tq->tx_ring.next2fill; + WARN_ON_ONCE(gdesc->txd.gen == tq->tx_ring.gen); + + gdesc->txd.addr = cpu_to_le64(tbi->dma_addr); + gdesc->dword[2] = cpu_to_le32(dw2); + + /* Setup the EOP desc */ + gdesc->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP); + + gdesc->txd.om = 0; + gdesc->txd.msscof = 0; + gdesc->txd.hlen = 0; + gdesc->txd.ti = 0; + + tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred); + le32_add_cpu(&tq->shared->txNumDeferred, 1); + tx_num_deferred++; + + vmxnet3_cmd_ring_adv_next2fill(&tq->tx_ring); + + /* set the last buf_info for the pkt */ + tbi->sop_idx = ctx.sop_txd - tq->tx_ring.base; + + dma_wmb(); + gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^ + VMXNET3_TXD_GEN); + + /* No need to handle the case when tx_num_deferred doesn't reach + * threshold. Backend driver at hypervisor side will poll and reset + * tq->shared->txNumDeferred to 0. + */ + if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) { + tq->shared->txNumDeferred = 0; + VMXNET3_WRITE_BAR0_REG(adapter, + VMXNET3_REG_TXPROD + tq->qid * 8, + tq->tx_ring.next2fill); + } + + return 0; +} + +static int +vmxnet3_xdp_xmit_back(struct vmxnet3_adapter *adapter, + struct xdp_frame *xdpf) +{ + struct vmxnet3_tx_queue *tq; + struct netdev_queue *nq; + int err; + + tq = vmxnet3_xdp_get_tq(adapter); + if (tq->stopped) + return -ENETDOWN; + + nq = netdev_get_tx_queue(adapter->netdev, tq->qid); + + __netif_tx_lock(nq, smp_processor_id()); + err = vmxnet3_xdp_xmit_frame(adapter, xdpf, tq, false); + __netif_tx_unlock(nq); + + return err; +} + +/* ndo_xdp_xmit */ +int +vmxnet3_xdp_xmit(struct net_device *dev, + int n, struct xdp_frame **frames, u32 flags) +{ + struct vmxnet3_adapter *adapter = netdev_priv(dev); + struct vmxnet3_tx_queue *tq; + int i; + + if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state))) + return -ENETDOWN; + if (unlikely(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))) + return -EINVAL; + + tq = vmxnet3_xdp_get_tq(adapter); + if (tq->stopped) + return -ENETDOWN; + + for (i = 0; i < n; i++) { + if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) { + tq->stats.xdp_xmit_err++; + break; + } + } + tq->stats.xdp_xmit += i; + + return i; +} + +static int +vmxnet3_run_xdp(struct vmxnet3_rx_queue *rq, struct xdp_buff *xdp, + struct bpf_prog *prog) +{ + struct xdp_frame *xdpf; + struct page *page; + int err; + u32 act; + + rq->stats.xdp_packets++; + act = bpf_prog_run_xdp(prog, xdp); + page = virt_to_page(xdp->data_hard_start); + + switch (act) { + case XDP_PASS: + return act; + case XDP_REDIRECT: + err = xdp_do_redirect(rq->adapter->netdev, xdp, prog); + if (!err) { + rq->stats.xdp_redirects++; + } else { + rq->stats.xdp_drops++; + page_pool_recycle_direct(rq->page_pool, page); + } + return act; + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf || + vmxnet3_xdp_xmit_back(rq->adapter, xdpf))) { + rq->stats.xdp_drops++; + page_pool_recycle_direct(rq->page_pool, page); + } else { + rq->stats.xdp_tx++; + } + return act; + default: + bpf_warn_invalid_xdp_action(rq->adapter->netdev, prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(rq->adapter->netdev, prog, act); + rq->stats.xdp_aborted++; + break; + case XDP_DROP: + rq->stats.xdp_drops++; + break; + } + + page_pool_recycle_direct(rq->page_pool, page); + + return act; +} + +static struct sk_buff * +vmxnet3_build_skb(struct vmxnet3_rx_queue *rq, struct page *page, + const struct xdp_buff *xdp) +{ + struct sk_buff *skb; + + skb = build_skb(page_address(page), PAGE_SIZE); + if (unlikely(!skb)) { + page_pool_recycle_direct(rq->page_pool, page); + rq->stats.rx_buf_alloc_failure++; + return NULL; + } + + /* bpf prog might change len and data position. */ + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + skb_mark_for_recycle(skb); + + return skb; +} + +/* Handle packets from DataRing. */ +int +vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + void *data, int len, + struct sk_buff **skb_xdp_pass) +{ + struct bpf_prog *xdp_prog; + struct xdp_buff xdp; + struct page *page; + int act; + + page = page_pool_alloc_pages(rq->page_pool, GFP_ATOMIC); + if (unlikely(!page)) { + rq->stats.rx_buf_alloc_failure++; + return XDP_DROP; + } + + xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, + len, false); + xdp_buff_clear_frags_flag(&xdp); + + /* Must copy the data because it's at dataring. */ + memcpy(xdp.data, data, len); + + xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); + if (!xdp_prog) { + act = XDP_PASS; + goto out_skb; + } + act = vmxnet3_run_xdp(rq, &xdp, xdp_prog); + if (act != XDP_PASS) + return act; + +out_skb: + *skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp); + if (!*skb_xdp_pass) + return XDP_DROP; + + /* No need to refill. */ + return likely(*skb_xdp_pass) ? act : XDP_DROP; +} + +int +vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_buf_info *rbi, + struct Vmxnet3_RxDesc *rxd, + struct sk_buff **skb_xdp_pass) +{ + struct bpf_prog *xdp_prog; + dma_addr_t new_dma_addr; + struct xdp_buff xdp; + struct page *page; + void *new_data; + int act; + + page = rbi->page; + dma_sync_single_for_cpu(&adapter->pdev->dev, + page_pool_get_dma_addr(page) + + rq->page_pool->p.offset, rcd->len, + page_pool_get_dma_dir(rq->page_pool)); + + xdp_init_buff(&xdp, rbi->len, &rq->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, + rcd->len, false); + xdp_buff_clear_frags_flag(&xdp); + + xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); + if (!xdp_prog) { + act = XDP_PASS; + goto out_skb; + } + act = vmxnet3_run_xdp(rq, &xdp, xdp_prog); + + if (act == XDP_PASS) { +out_skb: + *skb_xdp_pass = vmxnet3_build_skb(rq, page, &xdp); + if (!*skb_xdp_pass) + act = XDP_DROP; + } + + new_data = vmxnet3_pp_get_buff(rq->page_pool, &new_dma_addr, + GFP_ATOMIC); + if (!new_data) { + rq->stats.rx_buf_alloc_failure++; + return XDP_DROP; + } + rbi->page = virt_to_page(new_data); + rbi->dma_addr = new_dma_addr; + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + + return act; +} diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.h b/drivers/net/vmxnet3/vmxnet3_xdp.h new file mode 100644 index 0000000000..f9d843e060 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_xdp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * Linux driver for VMware's vmxnet3 ethernet NIC. + * Copyright (C) 2008-2023, VMware, Inc. All Rights Reserved. + * Maintained by: pv-drivers@vmware.com + * + */ + +#ifndef _VMXNET3_XDP_H +#define _VMXNET3_XDP_H + +#include <linux/filter.h> +#include <linux/bpf_trace.h> +#include <linux/netlink.h> + +#include "vmxnet3_int.h" + +#define VMXNET3_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) +#define VMXNET3_XDP_RX_TAILROOM SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +#define VMXNET3_XDP_RX_OFFSET VMXNET3_XDP_HEADROOM +#define VMXNET3_XDP_MAX_FRSIZE (PAGE_SIZE - VMXNET3_XDP_HEADROOM - \ + VMXNET3_XDP_RX_TAILROOM) +#define VMXNET3_XDP_MAX_MTU (VMXNET3_XDP_MAX_FRSIZE - ETH_HLEN - \ + 2 * VLAN_HLEN - ETH_FCS_LEN) + +int vmxnet3_xdp(struct net_device *netdev, struct netdev_bpf *bpf); +int vmxnet3_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); +int vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + struct Vmxnet3_RxCompDesc *rcd, + struct vmxnet3_rx_buf_info *rbi, + struct Vmxnet3_RxDesc *rxd, + struct sk_buff **skb_xdp_pass); +int vmxnet3_process_xdp_small(struct vmxnet3_adapter *adapter, + struct vmxnet3_rx_queue *rq, + void *data, int len, + struct sk_buff **skb_xdp_pass); +void *vmxnet3_pp_get_buff(struct page_pool *pp, dma_addr_t *dma_addr, + gfp_t gfp_mask); + +static inline bool vmxnet3_xdp_enabled(struct vmxnet3_adapter *adapter) +{ + return !!rcu_access_pointer(adapter->xdp_bpf_prog); +} + +#endif |