From 20048d0a12b1080f688ff9b82696134df1aa3607 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Wed, 27 Feb 2013 15:05:47 +0100 Subject: [PATCH 1/7] net: use socket_set_nodelay() for -netdev socket Reduce -netdev socket latency by disabling the Nagle algorithm on SOCK_STREAM sockets in net/socket.c. Since we are tunelling Ethernet over TCP we shouldn't artificially delay outgoing packets, let the guest decide packet scheduling. I already get sub-millisecond -netdev socket ping times on localhost, so there was no measurable difference in my testing. This won't hurt though and may improve remote socket performance. Signed-off-by: Stefan Hajnoczi Reviewed-by: Benoit Canet Reviewed-by: Daniel P. Berrange --- net/socket.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/socket.c b/net/socket.c index d8b35a23cb..b0c83e022c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -438,6 +438,9 @@ static NetSocketState *net_socket_fd_init_stream(NetClientState *peer, s->fd = fd; s->listen_fd = -1; + /* Disable Nagle algorithm on TCP sockets to reduce latency */ + socket_set_nodelay(fd); + if (is_connected) { net_socket_connect(s); } else { From 5acf5ea4bc1535657692c509092caddec3d719ff Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Sat, 9 Mar 2013 11:21:02 +0200 Subject: [PATCH 2/7] Checksum-related utility functions net_checksum_add_cont() checksum calculation for scattered data with odd chunk sizes net_raw_checksum() checksum calculation for a buffer Signed-off-by: Dmitry Fleytman Signed-off-by: Yan Vugenfirer Signed-off-by: Stefan Hajnoczi --- include/net/checksum.h | 14 +++++++++++++- net/checksum.c | 13 +++++++------ 2 files changed, 20 insertions(+), 7 deletions(-) diff --git a/include/net/checksum.h b/include/net/checksum.h index 1f052986e6..3e7b93d094 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -20,10 +20,22 @@ #include -uint32_t net_checksum_add(int len, uint8_t *buf); +uint32_t net_checksum_add_cont(int len, uint8_t *buf, int seq); uint16_t net_checksum_finish(uint32_t sum); uint16_t net_checksum_tcpudp(uint16_t length, uint16_t proto, uint8_t *addrs, uint8_t *buf); void net_checksum_calculate(uint8_t *data, int length); +static inline uint32_t +net_checksum_add(int len, uint8_t *buf) +{ + return net_checksum_add_cont(len, buf, 0); +} + +static inline uint16_t +net_raw_checksum(uint8_t *data, int length) +{ + return net_checksum_finish(net_checksum_add(length, data)); +} + #endif /* QEMU_NET_CHECKSUM_H */ diff --git a/net/checksum.c b/net/checksum.c index 9919b2e5fd..4fa5563e7c 100644 --- a/net/checksum.c +++ b/net/checksum.c @@ -20,16 +20,17 @@ #define PROTO_TCP 6 #define PROTO_UDP 17 -uint32_t net_checksum_add(int len, uint8_t *buf) +uint32_t net_checksum_add_cont(int len, uint8_t *buf, int seq) { uint32_t sum = 0; int i; - for (i = 0; i < len; i++) { - if (i & 1) - sum += (uint32_t)buf[i]; - else - sum += (uint32_t)buf[i] << 8; + for (i = seq; i < seq + len; i++) { + if (i & 1) { + sum += (uint32_t)buf[i - seq]; + } else { + sum += (uint32_t)buf[i - seq] << 8; + } } return sum; } From 84026301694b98dd08272e613da3497b17023d5c Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Sat, 9 Mar 2013 11:21:03 +0200 Subject: [PATCH 3/7] net: iovec checksum calculator Signed-off-by: Dmitry Fleytman Signed-off-by: Yan Vugenfirer Signed-off-by: Stefan Hajnoczi --- include/net/checksum.h | 12 ++++++++++++ net/checksum.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) diff --git a/include/net/checksum.h b/include/net/checksum.h index 3e7b93d094..80203fb6e0 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -38,4 +38,16 @@ net_raw_checksum(uint8_t *data, int length) return net_checksum_finish(net_checksum_add(length, data)); } +/** + * net_checksum_add_iov: scatter-gather vector checksumming + * + * @iov: input scatter-gather array + * @iov_cnt: number of array elements + * @iov_off: starting iov offset for checksumming + * @size: length of data to be checksummed + */ +uint32_t net_checksum_add_iov(const struct iovec *iov, + const unsigned int iov_cnt, + uint32_t iov_off, uint32_t size); + #endif /* QEMU_NET_CHECKSUM_H */ diff --git a/net/checksum.c b/net/checksum.c index 4fa5563e7c..14c08550e0 100644 --- a/net/checksum.c +++ b/net/checksum.c @@ -15,6 +15,7 @@ * along with this program; if not, see . */ +#include "qemu-common.h" #include "net/checksum.h" #define PROTO_TCP 6 @@ -84,3 +85,31 @@ void net_checksum_calculate(uint8_t *data, int length) data[14+hlen+csum_offset] = csum >> 8; data[14+hlen+csum_offset+1] = csum & 0xff; } + +uint32_t +net_checksum_add_iov(const struct iovec *iov, const unsigned int iov_cnt, + uint32_t iov_off, uint32_t size) +{ + size_t iovec_off, buf_off; + unsigned int i; + uint32_t res = 0; + uint32_t seq = 0; + + iovec_off = 0; + buf_off = 0; + for (i = 0; i < iov_cnt && size; i++) { + if (iov_off < (iovec_off + iov[i].iov_len)) { + size_t len = MIN((iovec_off + iov[i].iov_len) - iov_off , size); + void *chunk_buf = iov[i].iov_base + (iov_off - iovec_off); + + res += net_checksum_add_cont(len, chunk_buf, seq); + seq += len; + + buf_off += len; + iov_off += len; + size -= len; + } + iovec_off += iov[i].iov_len; + } + return res; +} From 75020a7021513ad4cbad2aa5f6de5d390016f099 Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Sat, 9 Mar 2013 11:21:04 +0200 Subject: [PATCH 4/7] Common definitions for VMWARE devices Signed-off-by: Dmitry Fleytman Signed-off-by: Yan Vugenfirer Signed-off-by: Stefan Hajnoczi --- hw/vmware_utils.h | 143 +++++++++++++++++++ hw/vmxnet_debug.h | 115 +++++++++++++++ include/net/eth.h | 347 ++++++++++++++++++++++++++++++++++++++++++++++ net/Makefile.objs | 1 + net/eth.c | 217 +++++++++++++++++++++++++++++ 5 files changed, 823 insertions(+) create mode 100644 hw/vmware_utils.h create mode 100644 hw/vmxnet_debug.h create mode 100644 include/net/eth.h create mode 100644 net/eth.c diff --git a/hw/vmware_utils.h b/hw/vmware_utils.h new file mode 100644 index 0000000000..5307e2ccc9 --- /dev/null +++ b/hw/vmware_utils.h @@ -0,0 +1,143 @@ +/* + * QEMU VMWARE paravirtual devices - auxiliary code + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef VMWARE_UTILS_H +#define VMWARE_UTILS_H + +#include "qemu/range.h" + +#ifndef VMW_SHPRN +#define VMW_SHPRN(fmt, ...) do {} while (0) +#endif + +/* + * Shared memory access functions with byte swap support + * Each function contains printout for reverse-engineering needs + * + */ +static inline void +vmw_shmem_read(hwaddr addr, void *buf, int len) +{ + VMW_SHPRN("SHMEM r: %" PRIx64 ", len: %d to %p", addr, len, buf); + cpu_physical_memory_read(addr, buf, len); +} + +static inline void +vmw_shmem_write(hwaddr addr, void *buf, int len) +{ + VMW_SHPRN("SHMEM w: %" PRIx64 ", len: %d to %p", addr, len, buf); + cpu_physical_memory_write(addr, buf, len); +} + +static inline void +vmw_shmem_rw(hwaddr addr, void *buf, int len, int is_write) +{ + VMW_SHPRN("SHMEM r/w: %" PRIx64 ", len: %d (to %p), is write: %d", + addr, len, buf, is_write); + + cpu_physical_memory_rw(addr, buf, len, is_write); +} + +static inline void +vmw_shmem_set(hwaddr addr, uint8 val, int len) +{ + int i; + VMW_SHPRN("SHMEM set: %" PRIx64 ", len: %d (value 0x%X)", addr, len, val); + + for (i = 0; i < len; i++) { + cpu_physical_memory_write(addr + i, &val, 1); + } +} + +static inline uint32_t +vmw_shmem_ld8(hwaddr addr) +{ + uint8_t res = ldub_phys(addr); + VMW_SHPRN("SHMEM load8: %" PRIx64 " (value 0x%X)", addr, res); + return res; +} + +static inline void +vmw_shmem_st8(hwaddr addr, uint8_t value) +{ + VMW_SHPRN("SHMEM store8: %" PRIx64 " (value 0x%X)", addr, value); + stb_phys(addr, value); +} + +static inline uint32_t +vmw_shmem_ld16(hwaddr addr) +{ + uint16_t res = lduw_le_phys(addr); + VMW_SHPRN("SHMEM load16: %" PRIx64 " (value 0x%X)", addr, res); + return res; +} + +static inline void +vmw_shmem_st16(hwaddr addr, uint16_t value) +{ + VMW_SHPRN("SHMEM store16: %" PRIx64 " (value 0x%X)", addr, value); + stw_le_phys(addr, value); +} + +static inline uint32_t +vmw_shmem_ld32(hwaddr addr) +{ + uint32_t res = ldl_le_phys(addr); + VMW_SHPRN("SHMEM load32: %" PRIx64 " (value 0x%X)", addr, res); + return res; +} + +static inline void +vmw_shmem_st32(hwaddr addr, uint32_t value) +{ + VMW_SHPRN("SHMEM store32: %" PRIx64 " (value 0x%X)", addr, value); + stl_le_phys(addr, value); +} + +static inline uint64_t +vmw_shmem_ld64(hwaddr addr) +{ + uint64_t res = ldq_le_phys(addr); + VMW_SHPRN("SHMEM load64: %" PRIx64 " (value %" PRIx64 ")", addr, res); + return res; +} + +static inline void +vmw_shmem_st64(hwaddr addr, uint64_t value) +{ + VMW_SHPRN("SHMEM store64: %" PRIx64 " (value %" PRIx64 ")", addr, value); + stq_le_phys(addr, value); +} + +/* Macros for simplification of operations on array-style registers */ + +/* + * Whether lies inside of array-style register defined by , + * number of elements () and element size () + * +*/ +#define VMW_IS_MULTIREG_ADDR(addr, base, cnt, regsize) \ + range_covers_byte(base, cnt * regsize, addr) + +/* + * Returns index of given register () in array-style register defined by + * and element size () + * +*/ +#define VMW_MULTIREG_IDX_BY_ADDR(addr, base, regsize) \ + (((addr) - (base)) / (regsize)) + +#endif diff --git a/hw/vmxnet_debug.h b/hw/vmxnet_debug.h new file mode 100644 index 0000000000..96dae0f916 --- /dev/null +++ b/hw/vmxnet_debug.h @@ -0,0 +1,115 @@ +/* + * QEMU VMWARE VMXNET* paravirtual NICs - debugging facilities + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef _QEMU_VMXNET_DEBUG_H +#define _QEMU_VMXNET_DEBUG_H + +#define VMXNET_DEVICE_NAME "vmxnet3" + +/* #define VMXNET_DEBUG_CB */ +#define VMXNET_DEBUG_WARNINGS +#define VMXNET_DEBUG_ERRORS +/* #define VMXNET_DEBUG_INTERRUPTS */ +/* #define VMXNET_DEBUG_CONFIG */ +/* #define VMXNET_DEBUG_RINGS */ +/* #define VMXNET_DEBUG_PACKETS */ +/* #define VMXNET_DEBUG_SHMEM_ACCESS */ + +#ifdef VMXNET_DEBUG_SHMEM_ACCESS +#define VMW_SHPRN(fmt, ...) \ + do { \ + printf("[%s][SH][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_SHPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_CB +#define VMW_CBPRN(fmt, ...) \ + do { \ + printf("[%s][CB][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_CBPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_PACKETS +#define VMW_PKPRN(fmt, ...) \ + do { \ + printf("[%s][PK][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_PKPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_WARNINGS +#define VMW_WRPRN(fmt, ...) \ + do { \ + printf("[%s][WR][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_WRPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_ERRORS +#define VMW_ERPRN(fmt, ...) \ + do { \ + printf("[%s][ER][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_ERPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_INTERRUPTS +#define VMW_IRPRN(fmt, ...) \ + do { \ + printf("[%s][IR][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_IRPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_CONFIG +#define VMW_CFPRN(fmt, ...) \ + do { \ + printf("[%s][CF][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_CFPRN(fmt, ...) do {} while (0) +#endif + +#ifdef VMXNET_DEBUG_RINGS +#define VMW_RIPRN(fmt, ...) \ + do { \ + printf("[%s][RI][%s]: " fmt "\n", VMXNET_DEVICE_NAME, __func__, \ + ## __VA_ARGS__); \ + } while (0) +#else +#define VMW_RIPRN(fmt, ...) do {} while (0) +#endif + +#define VMXNET_MF "%02X:%02X:%02X:%02X:%02X:%02X" +#define VMXNET_MA(a) (a)[0], (a)[1], (a)[2], (a)[3], (a)[4], (a)[5] + +#endif /* _QEMU_VMXNET3_DEBUG_H */ diff --git a/include/net/eth.h b/include/net/eth.h new file mode 100644 index 0000000000..1d48e06b22 --- /dev/null +++ b/include/net/eth.h @@ -0,0 +1,347 @@ +/* + * QEMU network structures definitions and helper functions + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Portions developed by Free Software Foundation, Inc + * Copyright (C) 1991-1997, 2001, 2003, 2006 Free Software Foundation, Inc. + * See netinet/ip6.h and netinet/in.h (GNU C Library) + * + * Portions developed by Igor Kovalenko + * Copyright (c) 2006 Igor Kovalenko + * See hw/rtl8139.c (QEMU) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_ETH_H +#define QEMU_ETH_H + +#include +#include +#include "qemu/bswap.h" +#include "qemu/iov.h" + +#define ETH_ALEN 6 + +struct eth_header { + uint8_t h_dest[ETH_ALEN]; /* destination eth addr */ + uint8_t h_source[ETH_ALEN]; /* source ether addr */ + uint16_t h_proto; /* packet type ID field */ +}; + +struct vlan_header { + uint16_t h_tci; /* priority and VLAN ID */ + uint16_t h_proto; /* encapsulated protocol */ +}; + +struct ip_header { + uint8_t ip_ver_len; /* version and header length */ + uint8_t ip_tos; /* type of service */ + uint16_t ip_len; /* total length */ + uint16_t ip_id; /* identification */ + uint16_t ip_off; /* fragment offset field */ + uint8_t ip_ttl; /* time to live */ + uint8_t ip_p; /* protocol */ + uint16_t ip_sum; /* checksum */ + uint32_t ip_src, ip_dst; /* source and destination address */ +}; + +typedef struct tcp_header { + uint16_t th_sport; /* source port */ + uint16_t th_dport; /* destination port */ + uint32_t th_seq; /* sequence number */ + uint32_t th_ack; /* acknowledgment number */ + uint16_t th_offset_flags; /* data offset, reserved 6 bits, */ + /* TCP protocol flags */ + uint16_t th_win; /* window */ + uint16_t th_sum; /* checksum */ + uint16_t th_urp; /* urgent pointer */ +} tcp_header; + +typedef struct udp_header { + uint16_t uh_sport; /* source port */ + uint16_t uh_dport; /* destination port */ + uint16_t uh_ulen; /* udp length */ + uint16_t uh_sum; /* udp checksum */ +} udp_header; + +typedef struct ip_pseudo_header { + uint32_t ip_src; + uint32_t ip_dst; + uint8_t zeros; + uint8_t ip_proto; + uint16_t ip_payload; +} ip_pseudo_header; + +/* IPv6 address */ +struct in6_addr { + union { + uint8_t __u6_addr8[16]; + } __in6_u; +}; + +struct ip6_header { + union { + struct ip6_hdrctl { + uint32_t ip6_un1_flow; /* 4 bits version, 8 bits TC, + 20 bits flow-ID */ + uint16_t ip6_un1_plen; /* payload length */ + uint8_t ip6_un1_nxt; /* next header */ + uint8_t ip6_un1_hlim; /* hop limit */ + } ip6_un1; + uint8_t ip6_un2_vfc; /* 4 bits version, top 4 bits tclass */ + struct ip6_ecn_access { + uint8_t ip6_un3_vfc; /* 4 bits version, top 4 bits tclass */ + uint8_t ip6_un3_ecn; /* 2 bits ECN, top 6 bits payload length */ + } ip6_un3; + } ip6_ctlun; + struct in6_addr ip6_src; /* source address */ + struct in6_addr ip6_dst; /* destination address */ +}; + +struct ip6_ext_hdr { + uint8_t ip6r_nxt; /* next header */ + uint8_t ip6r_len; /* length in units of 8 octets */ +}; + +struct udp_hdr { + uint16_t uh_sport; /* source port */ + uint16_t uh_dport; /* destination port */ + uint16_t uh_ulen; /* udp length */ + uint16_t uh_sum; /* udp checksum */ +}; + +struct tcp_hdr { + u_short th_sport; /* source port */ + u_short th_dport; /* destination port */ + uint32_t th_seq; /* sequence number */ + uint32_t th_ack; /* acknowledgment number */ +#ifdef HOST_WORDS_BIGENDIAN + u_char th_off : 4, /* data offset */ + th_x2:4; /* (unused) */ +#else + u_char th_x2 : 4, /* (unused) */ + th_off:4; /* data offset */ +#endif + +#define TH_ELN 0x1 /* explicit loss notification */ +#define TH_ECN 0x2 /* explicit congestion notification */ +#define TH_FS 0x4 /* fast start */ + + u_char th_flags; +#define TH_FIN 0x01 +#define TH_SYN 0x02 +#define TH_RST 0x04 +#define TH_PUSH 0x08 +#define TH_ACK 0x10 +#define TH_URG 0x20 + u_short th_win; /* window */ + u_short th_sum; /* checksum */ + u_short th_urp; /* urgent pointer */ +}; + +#define ip6_nxt ip6_ctlun.ip6_un1.ip6_un1_nxt +#define ip6_ecn_acc ip6_ctlun.ip6_un3.ip6_un3_ecn + +#define PKT_GET_ETH_HDR(p) \ + ((struct eth_header *)(p)) +#define PKT_GET_VLAN_HDR(p) \ + ((struct vlan_header *) (((uint8_t *)(p)) + sizeof(struct eth_header))) +#define PKT_GET_DVLAN_HDR(p) \ + (PKT_GET_VLAN_HDR(p) + 1) +#define PKT_GET_IP_HDR(p) \ + ((struct ip_header *)(((uint8_t *)(p)) + eth_get_l2_hdr_length(p))) +#define IP_HDR_GET_LEN(p) \ + ((((struct ip_header *)p)->ip_ver_len & 0x0F) << 2) +#define PKT_GET_IP_HDR_LEN(p) \ + (IP_HDR_GET_LEN(PKT_GET_IP_HDR(p))) +#define PKT_GET_IP6_HDR(p) \ + ((struct ip6_header *) (((uint8_t *)(p)) + eth_get_l2_hdr_length(p))) +#define IP_HEADER_VERSION(ip) \ + ((ip->ip_ver_len >> 4)&0xf) + +#define ETH_P_IP (0x0800) +#define ETH_P_IPV6 (0x86dd) +#define ETH_P_VLAN (0x8100) +#define ETH_P_DVLAN (0x88a8) +#define VLAN_VID_MASK 0x0fff +#define IP_HEADER_VERSION_4 (4) +#define IP_HEADER_VERSION_6 (6) +#define IP_PROTO_TCP (6) +#define IP_PROTO_UDP (17) +#define IPTOS_ECN_MASK 0x03 +#define IPTOS_ECN(x) ((x) & IPTOS_ECN_MASK) +#define IPTOS_ECN_CE 0x03 +#define IP6_ECN_MASK 0xC0 +#define IP6_ECN(x) ((x) & IP6_ECN_MASK) +#define IP6_ECN_CE 0xC0 +#define IP4_DONT_FRAGMENT_FLAG (1 << 14) + +#define IS_SPECIAL_VLAN_ID(x) \ + (((x) == 0) || ((x) == 0xFFF)) + +#define ETH_MAX_L2_HDR_LEN \ + (sizeof(struct eth_header) + 2 * sizeof(struct vlan_header)) + +#define ETH_MAX_IP4_HDR_LEN (60) +#define ETH_MAX_IP_DGRAM_LEN (0xFFFF) + +#define IP_FRAG_UNIT_SIZE (8) +#define IP_FRAG_ALIGN_SIZE(x) ((x) & ~0x7) +#define IP_RF 0x8000 /* reserved fragment flag */ +#define IP_DF 0x4000 /* don't fragment flag */ +#define IP_MF 0x2000 /* more fragments flag */ +#define IP_OFFMASK 0x1fff /* mask for fragmenting bits */ + +#define IP6_EXT_GRANULARITY (8) /* Size granularity for + IPv6 extension headers */ + +/* IP6 extension header types */ +#define IP6_HOP_BY_HOP (0) +#define IP6_ROUTING (43) +#define IP6_FRAGMENT (44) +#define IP6_ESP (50) +#define IP6_AUTHENTICATION (51) +#define IP6_NONE (59) +#define IP6_DESTINATON (60) +#define IP6_MOBILITY (135) + +static inline int is_multicast_ether_addr(const uint8_t *addr) +{ + return 0x01 & addr[0]; +} + +static inline int is_broadcast_ether_addr(const uint8_t *addr) +{ + return (addr[0] & addr[1] & addr[2] & addr[3] & addr[4] & addr[5]) == 0xff; +} + +static inline int is_unicast_ether_addr(const uint8_t *addr) +{ + return !is_multicast_ether_addr(addr); +} + +typedef enum { + ETH_PKT_UCAST = 0xAABBCC00, + ETH_PKT_BCAST, + ETH_PKT_MCAST +} eth_pkt_types_e; + +static inline eth_pkt_types_e +get_eth_packet_type(const struct eth_header *ehdr) +{ + if (is_broadcast_ether_addr(ehdr->h_dest)) { + return ETH_PKT_BCAST; + } else if (is_multicast_ether_addr(ehdr->h_dest)) { + return ETH_PKT_MCAST; + } else { /* unicast */ + return ETH_PKT_UCAST; + } +} + +static inline uint32_t +eth_get_l2_hdr_length(const void *p) +{ + uint16_t proto = be16_to_cpu(PKT_GET_ETH_HDR(p)->h_proto); + struct vlan_header *hvlan = PKT_GET_VLAN_HDR(p); + switch (proto) { + case ETH_P_VLAN: + return sizeof(struct eth_header) + sizeof(struct vlan_header); + case ETH_P_DVLAN: + if (hvlan->h_proto == ETH_P_VLAN) { + return sizeof(struct eth_header) + 2 * sizeof(struct vlan_header); + } else { + return sizeof(struct eth_header) + sizeof(struct vlan_header); + } + default: + return sizeof(struct eth_header); + } +} + +static inline uint16_t +eth_get_pkt_tci(const void *p) +{ + uint16_t proto = be16_to_cpu(PKT_GET_ETH_HDR(p)->h_proto); + struct vlan_header *hvlan = PKT_GET_VLAN_HDR(p); + switch (proto) { + case ETH_P_VLAN: + case ETH_P_DVLAN: + return be16_to_cpu(hvlan->h_tci); + default: + return 0; + } +} + +static inline bool +eth_strip_vlan(const void *p, uint8_t *new_ehdr_buf, + uint16_t *payload_offset, uint16_t *tci) +{ + uint16_t proto = be16_to_cpu(PKT_GET_ETH_HDR(p)->h_proto); + struct vlan_header *hvlan = PKT_GET_VLAN_HDR(p); + struct eth_header *new_ehdr = (struct eth_header *) new_ehdr_buf; + + switch (proto) { + case ETH_P_VLAN: + case ETH_P_DVLAN: + memcpy(new_ehdr->h_source, PKT_GET_ETH_HDR(p)->h_source, ETH_ALEN); + memcpy(new_ehdr->h_dest, PKT_GET_ETH_HDR(p)->h_dest, ETH_ALEN); + new_ehdr->h_proto = hvlan->h_proto; + *tci = be16_to_cpu(hvlan->h_tci); + *payload_offset = + sizeof(struct eth_header) + sizeof(struct vlan_header); + if (be16_to_cpu(new_ehdr->h_proto) == ETH_P_VLAN) { + memcpy(PKT_GET_VLAN_HDR(new_ehdr), + PKT_GET_DVLAN_HDR(p), + sizeof(struct vlan_header)); + *payload_offset += sizeof(struct vlan_header); + } + return true; + default: + return false; + } +} + +static inline uint16_t +eth_get_l3_proto(const void *l2hdr, size_t l2hdr_len) +{ + uint8_t *proto_ptr = (uint8_t *) l2hdr + l2hdr_len - sizeof(uint16_t); + return be16_to_cpup((uint16_t *)proto_ptr); +} + +void eth_setup_vlan_headers(struct eth_header *ehdr, uint16_t vlan_tag, + bool *is_new); + +uint8_t eth_get_gso_type(uint16_t l3_proto, uint8_t *l3_hdr, uint8_t l4proto); + +void eth_get_protocols(const uint8_t *headers, + uint32_t hdr_length, + bool *isip4, bool *isip6, + bool *isudp, bool *istcp); + +void eth_setup_ip4_fragmentation(const void *l2hdr, size_t l2hdr_len, + void *l3hdr, size_t l3hdr_len, + size_t l3payload_len, + size_t frag_offset, bool more_frags); + +void +eth_fix_ip4_checksum(void *l3hdr, size_t l3hdr_len); + +uint32_t +eth_calc_pseudo_hdr_csum(struct ip_header *iphdr, uint16_t csl); + +bool +eth_parse_ipv6_hdr(struct iovec *pkt, int pkt_frags, + size_t ip6hdr_off, uint8_t *l4proto, + size_t *full_hdr_len); + +#endif diff --git a/net/Makefile.objs b/net/Makefile.objs index a08cd14e2e..4854a14fe4 100644 --- a/net/Makefile.objs +++ b/net/Makefile.objs @@ -1,6 +1,7 @@ common-obj-y = net.o queue.o checksum.o util.o hub.o common-obj-y += socket.o common-obj-y += dump.o +common-obj-y += eth.o common-obj-$(CONFIG_POSIX) += tap.o common-obj-$(CONFIG_LINUX) += tap-linux.o common-obj-$(CONFIG_WIN32) += tap-win32.o diff --git a/net/eth.c b/net/eth.c new file mode 100644 index 0000000000..1d7494d5e5 --- /dev/null +++ b/net/eth.c @@ -0,0 +1,217 @@ +/* + * QEMU network structures definitions and helper functions + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "net/eth.h" +#include "net/checksum.h" +#include "qemu-common.h" +#include "net/tap.h" + +void eth_setup_vlan_headers(struct eth_header *ehdr, uint16_t vlan_tag, + bool *is_new) +{ + struct vlan_header *vhdr = PKT_GET_VLAN_HDR(ehdr); + + switch (be16_to_cpu(ehdr->h_proto)) { + case ETH_P_VLAN: + case ETH_P_DVLAN: + /* vlan hdr exists */ + *is_new = false; + break; + + default: + /* No VLAN header, put a new one */ + vhdr->h_proto = ehdr->h_proto; + ehdr->h_proto = cpu_to_be16(ETH_P_VLAN); + *is_new = true; + break; + } + vhdr->h_tci = cpu_to_be16(vlan_tag); +} + +uint8_t +eth_get_gso_type(uint16_t l3_proto, uint8_t *l3_hdr, uint8_t l4proto) +{ + uint8_t ecn_state = 0; + + if (l3_proto == ETH_P_IP) { + struct ip_header *iphdr = (struct ip_header *) l3_hdr; + + if (IP_HEADER_VERSION(iphdr) == IP_HEADER_VERSION_4) { + if (IPTOS_ECN(iphdr->ip_tos) == IPTOS_ECN_CE) { + ecn_state = VIRTIO_NET_HDR_GSO_ECN; + } + if (l4proto == IP_PROTO_TCP) { + return VIRTIO_NET_HDR_GSO_TCPV4 | ecn_state; + } else if (l4proto == IP_PROTO_UDP) { + return VIRTIO_NET_HDR_GSO_UDP | ecn_state; + } + } + } else if (l3_proto == ETH_P_IPV6) { + struct ip6_header *ip6hdr = (struct ip6_header *) l3_hdr; + + if (IP6_ECN(ip6hdr->ip6_ecn_acc) == IP6_ECN_CE) { + ecn_state = VIRTIO_NET_HDR_GSO_ECN; + } + + if (l4proto == IP_PROTO_TCP) { + return VIRTIO_NET_HDR_GSO_TCPV6 | ecn_state; + } + } + + /* Unsupported offload */ + assert(false); + + return VIRTIO_NET_HDR_GSO_NONE | ecn_state; +} + +void eth_get_protocols(const uint8_t *headers, + uint32_t hdr_length, + bool *isip4, bool *isip6, + bool *isudp, bool *istcp) +{ + int proto; + size_t l2hdr_len = eth_get_l2_hdr_length(headers); + assert(hdr_length >= eth_get_l2_hdr_length(headers)); + *isip4 = *isip6 = *isudp = *istcp = false; + + proto = eth_get_l3_proto(headers, l2hdr_len); + if (proto == ETH_P_IP) { + *isip4 = true; + + struct ip_header *iphdr; + + assert(hdr_length >= + eth_get_l2_hdr_length(headers) + sizeof(struct ip_header)); + + iphdr = PKT_GET_IP_HDR(headers); + + if (IP_HEADER_VERSION(iphdr) == IP_HEADER_VERSION_4) { + if (iphdr->ip_p == IP_PROTO_TCP) { + *istcp = true; + } else if (iphdr->ip_p == IP_PROTO_UDP) { + *isudp = true; + } + } + } else if (proto == ETH_P_IPV6) { + uint8_t l4proto; + size_t full_ip6hdr_len; + + struct iovec hdr_vec; + hdr_vec.iov_base = (void *) headers; + hdr_vec.iov_len = hdr_length; + + *isip6 = true; + if (eth_parse_ipv6_hdr(&hdr_vec, 1, l2hdr_len, + &l4proto, &full_ip6hdr_len)) { + if (l4proto == IP_PROTO_TCP) { + *istcp = true; + } else if (l4proto == IP_PROTO_UDP) { + *isudp = true; + } + } + } +} + +void +eth_setup_ip4_fragmentation(const void *l2hdr, size_t l2hdr_len, + void *l3hdr, size_t l3hdr_len, + size_t l3payload_len, + size_t frag_offset, bool more_frags) +{ + if (eth_get_l3_proto(l2hdr, l2hdr_len) == ETH_P_IP) { + uint16_t orig_flags; + struct ip_header *iphdr = (struct ip_header *) l3hdr; + uint16_t frag_off_units = frag_offset / IP_FRAG_UNIT_SIZE; + uint16_t new_ip_off; + + assert(frag_offset % IP_FRAG_UNIT_SIZE == 0); + assert((frag_off_units & ~IP_OFFMASK) == 0); + + orig_flags = be16_to_cpu(iphdr->ip_off) & ~(IP_OFFMASK|IP_MF); + new_ip_off = frag_off_units | orig_flags | (more_frags ? IP_MF : 0); + iphdr->ip_off = cpu_to_be16(new_ip_off); + iphdr->ip_len = cpu_to_be16(l3payload_len + l3hdr_len); + } +} + +void +eth_fix_ip4_checksum(void *l3hdr, size_t l3hdr_len) +{ + struct ip_header *iphdr = (struct ip_header *) l3hdr; + iphdr->ip_sum = 0; + iphdr->ip_sum = cpu_to_be16(net_raw_checksum(l3hdr, l3hdr_len)); +} + +uint32_t +eth_calc_pseudo_hdr_csum(struct ip_header *iphdr, uint16_t csl) +{ + struct ip_pseudo_header ipph; + ipph.ip_src = iphdr->ip_src; + ipph.ip_dst = iphdr->ip_dst; + ipph.ip_payload = cpu_to_be16(csl); + ipph.ip_proto = iphdr->ip_p; + ipph.zeros = 0; + return net_checksum_add(sizeof(ipph), (uint8_t *) &ipph); +} + +static bool +eth_is_ip6_extension_header_type(uint8_t hdr_type) +{ + switch (hdr_type) { + case IP6_HOP_BY_HOP: + case IP6_ROUTING: + case IP6_FRAGMENT: + case IP6_ESP: + case IP6_AUTHENTICATION: + case IP6_DESTINATON: + case IP6_MOBILITY: + return true; + default: + return false; + } +} + +bool eth_parse_ipv6_hdr(struct iovec *pkt, int pkt_frags, + size_t ip6hdr_off, uint8_t *l4proto, + size_t *full_hdr_len) +{ + struct ip6_header ip6_hdr; + struct ip6_ext_hdr ext_hdr; + size_t bytes_read; + + bytes_read = iov_to_buf(pkt, pkt_frags, ip6hdr_off, + &ip6_hdr, sizeof(ip6_hdr)); + if (bytes_read < sizeof(ip6_hdr)) { + return false; + } + + *full_hdr_len = sizeof(struct ip6_header); + + if (!eth_is_ip6_extension_header_type(ip6_hdr.ip6_nxt)) { + *l4proto = ip6_hdr.ip6_nxt; + return true; + } + + do { + bytes_read = iov_to_buf(pkt, pkt_frags, ip6hdr_off + *full_hdr_len, + &ext_hdr, sizeof(ext_hdr)); + *full_hdr_len += (ext_hdr.ip6r_len + 1) * IP6_EXT_GRANULARITY; + } while (eth_is_ip6_extension_header_type(ext_hdr.ip6r_nxt)); + + *l4proto = ext_hdr.ip6r_nxt; + return true; +} From e263cd49c73c595af0917c83dc004234660e0c71 Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Sat, 9 Mar 2013 11:21:05 +0200 Subject: [PATCH 5/7] Packet abstraction for VMWARE network devices Signed-off-by: Dmitry Fleytman Signed-off-by: Yan Vugenfirer Signed-off-by: Stefan Hajnoczi --- hw/Makefile.objs | 1 + hw/vmxnet_rx_pkt.c | 187 +++++++++++++++ hw/vmxnet_rx_pkt.h | 174 ++++++++++++++ hw/vmxnet_tx_pkt.c | 567 +++++++++++++++++++++++++++++++++++++++++++++ hw/vmxnet_tx_pkt.h | 148 ++++++++++++ 5 files changed, 1077 insertions(+) create mode 100644 hw/vmxnet_rx_pkt.c create mode 100644 hw/vmxnet_rx_pkt.h create mode 100644 hw/vmxnet_tx_pkt.c create mode 100644 hw/vmxnet_tx_pkt.h diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 11812c6a4e..1a988cad96 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -119,6 +119,7 @@ common-obj-$(CONFIG_PCNET_PCI) += pcnet-pci.o common-obj-$(CONFIG_PCNET_COMMON) += pcnet.o common-obj-$(CONFIG_E1000_PCI) += e1000.o common-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o +common-obj-$(CONFIG_VMXNET3_PCI) += vmxnet_tx_pkt.o vmxnet_rx_pkt.o common-obj-$(CONFIG_SMC91C111) += smc91c111.o common-obj-$(CONFIG_LAN9118) += lan9118.o diff --git a/hw/vmxnet_rx_pkt.c b/hw/vmxnet_rx_pkt.c new file mode 100644 index 0000000000..a40e346293 --- /dev/null +++ b/hw/vmxnet_rx_pkt.c @@ -0,0 +1,187 @@ +/* + * QEMU VMWARE VMXNET* paravirtual NICs - RX packets abstractions + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "vmxnet_rx_pkt.h" +#include "net/eth.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "net/checksum.h" +#include "net/tap.h" + +/* + * RX packet may contain up to 2 fragments - rebuilt eth header + * in case of VLAN tag stripping + * and payload received from QEMU - in any case + */ +#define VMXNET_MAX_RX_PACKET_FRAGMENTS (2) + +struct VmxnetRxPkt { + struct virtio_net_hdr virt_hdr; + uint8_t ehdr_buf[ETH_MAX_L2_HDR_LEN]; + struct iovec vec[VMXNET_MAX_RX_PACKET_FRAGMENTS]; + uint16_t vec_len; + uint32_t tot_len; + uint16_t tci; + bool vlan_stripped; + bool has_virt_hdr; + eth_pkt_types_e packet_type; + + /* Analysis results */ + bool isip4; + bool isip6; + bool isudp; + bool istcp; +}; + +void vmxnet_rx_pkt_init(struct VmxnetRxPkt **pkt, bool has_virt_hdr) +{ + struct VmxnetRxPkt *p = g_malloc0(sizeof *p); + p->has_virt_hdr = has_virt_hdr; + *pkt = p; +} + +void vmxnet_rx_pkt_uninit(struct VmxnetRxPkt *pkt) +{ + g_free(pkt); +} + +struct virtio_net_hdr *vmxnet_rx_pkt_get_vhdr(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + return &pkt->virt_hdr; +} + +void vmxnet_rx_pkt_attach_data(struct VmxnetRxPkt *pkt, const void *data, + size_t len, bool strip_vlan) +{ + uint16_t tci = 0; + uint16_t ploff; + assert(pkt); + pkt->vlan_stripped = false; + + if (strip_vlan) { + pkt->vlan_stripped = eth_strip_vlan(data, pkt->ehdr_buf, &ploff, &tci); + } + + if (pkt->vlan_stripped) { + pkt->vec[0].iov_base = pkt->ehdr_buf; + pkt->vec[0].iov_len = ploff - sizeof(struct vlan_header); + pkt->vec[1].iov_base = (uint8_t *) data + ploff; + pkt->vec[1].iov_len = len - ploff; + pkt->vec_len = 2; + pkt->tot_len = len - ploff + sizeof(struct eth_header); + } else { + pkt->vec[0].iov_base = (void *)data; + pkt->vec[0].iov_len = len; + pkt->vec_len = 1; + pkt->tot_len = len; + } + + pkt->tci = tci; + + eth_get_protocols(data, len, &pkt->isip4, &pkt->isip6, + &pkt->isudp, &pkt->istcp); +} + +void vmxnet_rx_pkt_dump(struct VmxnetRxPkt *pkt) +{ +#ifdef VMXNET_RX_PKT_DEBUG + VmxnetRxPkt *pkt = (VmxnetRxPkt *)pkt; + assert(pkt); + + printf("RX PKT: tot_len: %d, vlan_stripped: %d, vlan_tag: %d\n", + pkt->tot_len, pkt->vlan_stripped, pkt->tci); +#endif +} + +void vmxnet_rx_pkt_set_packet_type(struct VmxnetRxPkt *pkt, + eth_pkt_types_e packet_type) +{ + assert(pkt); + + pkt->packet_type = packet_type; + +} + +eth_pkt_types_e vmxnet_rx_pkt_get_packet_type(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->packet_type; +} + +size_t vmxnet_rx_pkt_get_total_len(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->tot_len; +} + +void vmxnet_rx_pkt_get_protocols(struct VmxnetRxPkt *pkt, + bool *isip4, bool *isip6, + bool *isudp, bool *istcp) +{ + assert(pkt); + + *isip4 = pkt->isip4; + *isip6 = pkt->isip6; + *isudp = pkt->isudp; + *istcp = pkt->istcp; +} + +struct iovec *vmxnet_rx_pkt_get_iovec(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->vec; +} + +void vmxnet_rx_pkt_set_vhdr(struct VmxnetRxPkt *pkt, + struct virtio_net_hdr *vhdr) +{ + assert(pkt); + + memcpy(&pkt->virt_hdr, vhdr, sizeof pkt->virt_hdr); +} + +bool vmxnet_rx_pkt_is_vlan_stripped(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->vlan_stripped; +} + +bool vmxnet_rx_pkt_has_virt_hdr(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->has_virt_hdr; +} + +uint16_t vmxnet_rx_pkt_get_num_frags(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->vec_len; +} + +uint16_t vmxnet_rx_pkt_get_vlan_tag(struct VmxnetRxPkt *pkt) +{ + assert(pkt); + + return pkt->tci; +} diff --git a/hw/vmxnet_rx_pkt.h b/hw/vmxnet_rx_pkt.h new file mode 100644 index 0000000000..6b2c60ef10 --- /dev/null +++ b/hw/vmxnet_rx_pkt.h @@ -0,0 +1,174 @@ +/* + * QEMU VMWARE VMXNET* paravirtual NICs - RX packets abstraction + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef VMXNET_RX_PKT_H +#define VMXNET_RX_PKT_H + +#include "stdint.h" +#include "stdbool.h" +#include "net/eth.h" + +/* defines to enable packet dump functions */ +/*#define VMXNET_RX_PKT_DEBUG*/ + +struct VmxnetRxPkt; + +/** + * Clean all rx packet resources + * + * @pkt: packet + * + */ +void vmxnet_rx_pkt_uninit(struct VmxnetRxPkt *pkt); + +/** + * Init function for rx packet functionality + * + * @pkt: packet pointer + * @has_virt_hdr: device uses virtio header + * + */ +void vmxnet_rx_pkt_init(struct VmxnetRxPkt **pkt, bool has_virt_hdr); + +/** + * returns total length of data attached to rx context + * + * @pkt: packet + * + * Return: nothing + * + */ +size_t vmxnet_rx_pkt_get_total_len(struct VmxnetRxPkt *pkt); + +/** + * fetches packet analysis results + * + * @pkt: packet + * @isip4: whether the packet given is IPv4 + * @isip6: whether the packet given is IPv6 + * @isudp: whether the packet given is UDP + * @istcp: whether the packet given is TCP + * + */ +void vmxnet_rx_pkt_get_protocols(struct VmxnetRxPkt *pkt, + bool *isip4, bool *isip6, + bool *isudp, bool *istcp); + +/** + * returns virtio header stored in rx context + * + * @pkt: packet + * @ret: virtio header + * + */ +struct virtio_net_hdr *vmxnet_rx_pkt_get_vhdr(struct VmxnetRxPkt *pkt); + +/** + * returns packet type + * + * @pkt: packet + * @ret: packet type + * + */ +eth_pkt_types_e vmxnet_rx_pkt_get_packet_type(struct VmxnetRxPkt *pkt); + +/** + * returns vlan tag + * + * @pkt: packet + * @ret: VLAN tag + * + */ +uint16_t vmxnet_rx_pkt_get_vlan_tag(struct VmxnetRxPkt *pkt); + +/** + * tells whether vlan was stripped from the packet + * + * @pkt: packet + * @ret: VLAN stripped sign + * + */ +bool vmxnet_rx_pkt_is_vlan_stripped(struct VmxnetRxPkt *pkt); + +/** + * notifies caller if the packet has virtio header + * + * @pkt: packet + * @ret: true if packet has virtio header, false otherwize + * + */ +bool vmxnet_rx_pkt_has_virt_hdr(struct VmxnetRxPkt *pkt); + +/** + * returns number of frags attached to the packet + * + * @pkt: packet + * @ret: number of frags + * + */ +uint16_t vmxnet_rx_pkt_get_num_frags(struct VmxnetRxPkt *pkt); + +/** + * attach data to rx packet + * + * @pkt: packet + * @data: pointer to the data buffer + * @len: data length + * @strip_vlan: should the module strip vlan from data + * + */ +void vmxnet_rx_pkt_attach_data(struct VmxnetRxPkt *pkt, const void *data, + size_t len, bool strip_vlan); + +/** + * returns io vector that holds the attached data + * + * @pkt: packet + * @ret: pointer to IOVec + * + */ +struct iovec *vmxnet_rx_pkt_get_iovec(struct VmxnetRxPkt *pkt); + +/** + * prints rx packet data if debug is enabled + * + * @pkt: packet + * + */ +void vmxnet_rx_pkt_dump(struct VmxnetRxPkt *pkt); + +/** + * copy passed vhdr data to packet context + * + * @pkt: packet + * @vhdr: VHDR buffer + * + */ +void vmxnet_rx_pkt_set_vhdr(struct VmxnetRxPkt *pkt, + struct virtio_net_hdr *vhdr); + +/** + * save packet type in packet context + * + * @pkt: packet + * @packet_type: the packet type + * + */ +void vmxnet_rx_pkt_set_packet_type(struct VmxnetRxPkt *pkt, + eth_pkt_types_e packet_type); + +#endif diff --git a/hw/vmxnet_tx_pkt.c b/hw/vmxnet_tx_pkt.c new file mode 100644 index 0000000000..b1e795b3b2 --- /dev/null +++ b/hw/vmxnet_tx_pkt.c @@ -0,0 +1,567 @@ +/* + * QEMU VMWARE VMXNET* paravirtual NICs - TX packets abstractions + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "vmxnet_tx_pkt.h" +#include "net/eth.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "net/checksum.h" +#include "net/tap.h" +#include "net/net.h" +#include "exec/cpu-common.h" + +enum { + VMXNET_TX_PKT_VHDR_FRAG = 0, + VMXNET_TX_PKT_L2HDR_FRAG, + VMXNET_TX_PKT_L3HDR_FRAG, + VMXNET_TX_PKT_PL_START_FRAG +}; + +/* TX packet private context */ +struct VmxnetTxPkt { + struct virtio_net_hdr virt_hdr; + bool has_virt_hdr; + + struct iovec *raw; + uint32_t raw_frags; + uint32_t max_raw_frags; + + struct iovec *vec; + + uint8_t l2_hdr[ETH_MAX_L2_HDR_LEN]; + + uint32_t payload_len; + + uint32_t payload_frags; + uint32_t max_payload_frags; + + uint16_t hdr_len; + eth_pkt_types_e packet_type; + uint8_t l4proto; +}; + +void vmxnet_tx_pkt_init(struct VmxnetTxPkt **pkt, uint32_t max_frags, + bool has_virt_hdr) +{ + struct VmxnetTxPkt *p = g_malloc0(sizeof *p); + + p->vec = g_malloc((sizeof *p->vec) * + (max_frags + VMXNET_TX_PKT_PL_START_FRAG)); + + p->raw = g_malloc((sizeof *p->raw) * max_frags); + + p->max_payload_frags = max_frags; + p->max_raw_frags = max_frags; + p->has_virt_hdr = has_virt_hdr; + p->vec[VMXNET_TX_PKT_VHDR_FRAG].iov_base = &p->virt_hdr; + p->vec[VMXNET_TX_PKT_VHDR_FRAG].iov_len = + p->has_virt_hdr ? sizeof p->virt_hdr : 0; + p->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_base = &p->l2_hdr; + p->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base = NULL; + p->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len = 0; + + *pkt = p; +} + +void vmxnet_tx_pkt_uninit(struct VmxnetTxPkt *pkt) +{ + if (pkt) { + g_free(pkt->vec); + g_free(pkt->raw); + g_free(pkt); + } +} + +void vmxnet_tx_pkt_update_ip_checksums(struct VmxnetTxPkt *pkt) +{ + uint16_t csum; + uint32_t ph_raw_csum; + assert(pkt); + uint8_t gso_type = pkt->virt_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN; + struct ip_header *ip_hdr; + + if (VIRTIO_NET_HDR_GSO_TCPV4 != gso_type && + VIRTIO_NET_HDR_GSO_UDP != gso_type) { + return; + } + + ip_hdr = pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base; + + if (pkt->payload_len + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len > + ETH_MAX_IP_DGRAM_LEN) { + return; + } + + ip_hdr->ip_len = cpu_to_be16(pkt->payload_len + + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len); + + /* Calculate IP header checksum */ + ip_hdr->ip_sum = 0; + csum = net_raw_checksum((uint8_t *)ip_hdr, + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len); + ip_hdr->ip_sum = cpu_to_be16(csum); + + /* Calculate IP pseudo header checksum */ + ph_raw_csum = eth_calc_pseudo_hdr_csum(ip_hdr, pkt->payload_len); + csum = cpu_to_be16(~net_checksum_finish(ph_raw_csum)); + iov_from_buf(&pkt->vec[VMXNET_TX_PKT_PL_START_FRAG], pkt->payload_frags, + pkt->virt_hdr.csum_offset, &csum, sizeof(csum)); +} + +static void vmxnet_tx_pkt_calculate_hdr_len(struct VmxnetTxPkt *pkt) +{ + pkt->hdr_len = pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_len + + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len; +} + +static bool vmxnet_tx_pkt_parse_headers(struct VmxnetTxPkt *pkt) +{ + struct iovec *l2_hdr, *l3_hdr; + size_t bytes_read; + size_t full_ip6hdr_len; + uint16_t l3_proto; + + assert(pkt); + + l2_hdr = &pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG]; + l3_hdr = &pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG]; + + bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, 0, l2_hdr->iov_base, + ETH_MAX_L2_HDR_LEN); + if (bytes_read < ETH_MAX_L2_HDR_LEN) { + l2_hdr->iov_len = 0; + return false; + } else { + l2_hdr->iov_len = eth_get_l2_hdr_length(l2_hdr->iov_base); + } + + l3_proto = eth_get_l3_proto(l2_hdr->iov_base, l2_hdr->iov_len); + + switch (l3_proto) { + case ETH_P_IP: + l3_hdr->iov_base = g_malloc(ETH_MAX_IP4_HDR_LEN); + + bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, l2_hdr->iov_len, + l3_hdr->iov_base, sizeof(struct ip_header)); + + if (bytes_read < sizeof(struct ip_header)) { + l3_hdr->iov_len = 0; + return false; + } + + l3_hdr->iov_len = IP_HDR_GET_LEN(l3_hdr->iov_base); + pkt->l4proto = ((struct ip_header *) l3_hdr->iov_base)->ip_p; + + /* copy optional IPv4 header data */ + bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, + l2_hdr->iov_len + sizeof(struct ip_header), + l3_hdr->iov_base + sizeof(struct ip_header), + l3_hdr->iov_len - sizeof(struct ip_header)); + if (bytes_read < l3_hdr->iov_len - sizeof(struct ip_header)) { + l3_hdr->iov_len = 0; + return false; + } + break; + + case ETH_P_IPV6: + if (!eth_parse_ipv6_hdr(pkt->raw, pkt->raw_frags, l2_hdr->iov_len, + &pkt->l4proto, &full_ip6hdr_len)) { + l3_hdr->iov_len = 0; + return false; + } + + l3_hdr->iov_base = g_malloc(full_ip6hdr_len); + + bytes_read = iov_to_buf(pkt->raw, pkt->raw_frags, l2_hdr->iov_len, + l3_hdr->iov_base, full_ip6hdr_len); + + if (bytes_read < full_ip6hdr_len) { + l3_hdr->iov_len = 0; + return false; + } else { + l3_hdr->iov_len = full_ip6hdr_len; + } + break; + + default: + l3_hdr->iov_len = 0; + break; + } + + vmxnet_tx_pkt_calculate_hdr_len(pkt); + pkt->packet_type = get_eth_packet_type(l2_hdr->iov_base); + return true; +} + +static bool vmxnet_tx_pkt_rebuild_payload(struct VmxnetTxPkt *pkt) +{ + size_t payload_len = iov_size(pkt->raw, pkt->raw_frags) - pkt->hdr_len; + + pkt->payload_frags = iov_copy(&pkt->vec[VMXNET_TX_PKT_PL_START_FRAG], + pkt->max_payload_frags, + pkt->raw, pkt->raw_frags, + pkt->hdr_len, payload_len); + + if (pkt->payload_frags != (uint32_t) -1) { + pkt->payload_len = payload_len; + return true; + } else { + return false; + } +} + +bool vmxnet_tx_pkt_parse(struct VmxnetTxPkt *pkt) +{ + return vmxnet_tx_pkt_parse_headers(pkt) && + vmxnet_tx_pkt_rebuild_payload(pkt); +} + +struct virtio_net_hdr *vmxnet_tx_pkt_get_vhdr(struct VmxnetTxPkt *pkt) +{ + assert(pkt); + return &pkt->virt_hdr; +} + +static uint8_t vmxnet_tx_pkt_get_gso_type(struct VmxnetTxPkt *pkt, + bool tso_enable) +{ + uint8_t rc = VIRTIO_NET_HDR_GSO_NONE; + uint16_t l3_proto; + + l3_proto = eth_get_l3_proto(pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_base, + pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_len); + + if (!tso_enable) { + goto func_exit; + } + + rc = eth_get_gso_type(l3_proto, pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base, + pkt->l4proto); + +func_exit: + return rc; +} + +void vmxnet_tx_pkt_build_vheader(struct VmxnetTxPkt *pkt, bool tso_enable, + bool csum_enable, uint32_t gso_size) +{ + struct tcp_hdr l4hdr; + assert(pkt); + + /* csum has to be enabled if tso is. */ + assert(csum_enable || !tso_enable); + + pkt->virt_hdr.gso_type = vmxnet_tx_pkt_get_gso_type(pkt, tso_enable); + + switch (pkt->virt_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_NONE: + pkt->virt_hdr.hdr_len = 0; + pkt->virt_hdr.gso_size = 0; + break; + + case VIRTIO_NET_HDR_GSO_UDP: + pkt->virt_hdr.gso_size = IP_FRAG_ALIGN_SIZE(gso_size); + pkt->virt_hdr.hdr_len = pkt->hdr_len + sizeof(struct udp_header); + break; + + case VIRTIO_NET_HDR_GSO_TCPV4: + case VIRTIO_NET_HDR_GSO_TCPV6: + iov_to_buf(&pkt->vec[VMXNET_TX_PKT_PL_START_FRAG], pkt->payload_frags, + 0, &l4hdr, sizeof(l4hdr)); + pkt->virt_hdr.hdr_len = pkt->hdr_len + l4hdr.th_off * sizeof(uint32_t); + pkt->virt_hdr.gso_size = IP_FRAG_ALIGN_SIZE(gso_size); + break; + + default: + assert(false); + } + + if (csum_enable) { + switch (pkt->l4proto) { + case IP_PROTO_TCP: + pkt->virt_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + pkt->virt_hdr.csum_start = pkt->hdr_len; + pkt->virt_hdr.csum_offset = offsetof(struct tcp_hdr, th_sum); + break; + case IP_PROTO_UDP: + pkt->virt_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + pkt->virt_hdr.csum_start = pkt->hdr_len; + pkt->virt_hdr.csum_offset = offsetof(struct udp_hdr, uh_sum); + break; + default: + break; + } + } +} + +void vmxnet_tx_pkt_setup_vlan_header(struct VmxnetTxPkt *pkt, uint16_t vlan) +{ + bool is_new; + assert(pkt); + + eth_setup_vlan_headers(pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_base, + vlan, &is_new); + + /* update l2hdrlen */ + if (is_new) { + pkt->hdr_len += sizeof(struct vlan_header); + pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_len += + sizeof(struct vlan_header); + } +} + +bool vmxnet_tx_pkt_add_raw_fragment(struct VmxnetTxPkt *pkt, hwaddr pa, + size_t len) +{ + hwaddr mapped_len = 0; + struct iovec *ventry; + assert(pkt); + assert(pkt->max_raw_frags > pkt->raw_frags); + + if (!len) { + return true; + } + + ventry = &pkt->raw[pkt->raw_frags]; + mapped_len = len; + + ventry->iov_base = cpu_physical_memory_map(pa, &mapped_len, false); + ventry->iov_len = mapped_len; + pkt->raw_frags += !!ventry->iov_base; + + if ((ventry->iov_base == NULL) || (len != mapped_len)) { + return false; + } + + return true; +} + +eth_pkt_types_e vmxnet_tx_pkt_get_packet_type(struct VmxnetTxPkt *pkt) +{ + assert(pkt); + + return pkt->packet_type; +} + +size_t vmxnet_tx_pkt_get_total_len(struct VmxnetTxPkt *pkt) +{ + assert(pkt); + + return pkt->hdr_len + pkt->payload_len; +} + +void vmxnet_tx_pkt_dump(struct VmxnetTxPkt *pkt) +{ +#ifdef VMXNET_TX_PKT_DEBUG + assert(pkt); + + printf("TX PKT: hdr_len: %d, pkt_type: 0x%X, l2hdr_len: %lu, " + "l3hdr_len: %lu, payload_len: %u\n", pkt->hdr_len, pkt->packet_type, + pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_len, + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len, pkt->payload_len); +#endif +} + +void vmxnet_tx_pkt_reset(struct VmxnetTxPkt *pkt) +{ + int i; + + /* no assert, as reset can be called before tx_pkt_init */ + if (!pkt) { + return; + } + + memset(&pkt->virt_hdr, 0, sizeof(pkt->virt_hdr)); + + g_free(pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base); + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base = NULL; + + assert(pkt->vec); + for (i = VMXNET_TX_PKT_L2HDR_FRAG; + i < pkt->payload_frags + VMXNET_TX_PKT_PL_START_FRAG; i++) { + pkt->vec[i].iov_len = 0; + } + pkt->payload_len = 0; + pkt->payload_frags = 0; + + assert(pkt->raw); + for (i = 0; i < pkt->raw_frags; i++) { + assert(pkt->raw[i].iov_base); + cpu_physical_memory_unmap(pkt->raw[i].iov_base, pkt->raw[i].iov_len, + false, pkt->raw[i].iov_len); + pkt->raw[i].iov_len = 0; + } + pkt->raw_frags = 0; + + pkt->hdr_len = 0; + pkt->packet_type = 0; + pkt->l4proto = 0; +} + +static void vmxnet_tx_pkt_do_sw_csum(struct VmxnetTxPkt *pkt) +{ + struct iovec *iov = &pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG]; + uint32_t csum_cntr; + uint16_t csum = 0; + /* num of iovec without vhdr */ + uint32_t iov_len = pkt->payload_frags + VMXNET_TX_PKT_PL_START_FRAG - 1; + uint16_t csl; + struct ip_header *iphdr; + size_t csum_offset = pkt->virt_hdr.csum_start + pkt->virt_hdr.csum_offset; + + /* Put zero to checksum field */ + iov_from_buf(iov, iov_len, csum_offset, &csum, sizeof csum); + + /* Calculate L4 TCP/UDP checksum */ + csl = pkt->payload_len; + + /* data checksum */ + csum_cntr = + net_checksum_add_iov(iov, iov_len, pkt->virt_hdr.csum_start, csl); + /* add pseudo header to csum */ + iphdr = pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base; + csum_cntr += eth_calc_pseudo_hdr_csum(iphdr, csl); + + /* Put the checksum obtained into the packet */ + csum = cpu_to_be16(net_checksum_finish(csum_cntr)); + iov_from_buf(iov, iov_len, csum_offset, &csum, sizeof csum); +} + +enum { + VMXNET_TX_PKT_FRAGMENT_L2_HDR_POS = 0, + VMXNET_TX_PKT_FRAGMENT_L3_HDR_POS, + VMXNET_TX_PKT_FRAGMENT_HEADER_NUM +}; + +#define VMXNET_MAX_FRAG_SG_LIST (64) + +static size_t vmxnet_tx_pkt_fetch_fragment(struct VmxnetTxPkt *pkt, + int *src_idx, size_t *src_offset, struct iovec *dst, int *dst_idx) +{ + size_t fetched = 0; + struct iovec *src = pkt->vec; + + *dst_idx = VMXNET_TX_PKT_FRAGMENT_HEADER_NUM; + + while (fetched < pkt->virt_hdr.gso_size) { + + /* no more place in fragment iov */ + if (*dst_idx == VMXNET_MAX_FRAG_SG_LIST) { + break; + } + + /* no more data in iovec */ + if (*src_idx == (pkt->payload_frags + VMXNET_TX_PKT_PL_START_FRAG)) { + break; + } + + + dst[*dst_idx].iov_base = src[*src_idx].iov_base + *src_offset; + dst[*dst_idx].iov_len = MIN(src[*src_idx].iov_len - *src_offset, + pkt->virt_hdr.gso_size - fetched); + + *src_offset += dst[*dst_idx].iov_len; + fetched += dst[*dst_idx].iov_len; + + if (*src_offset == src[*src_idx].iov_len) { + *src_offset = 0; + (*src_idx)++; + } + + (*dst_idx)++; + } + + return fetched; +} + +static bool vmxnet_tx_pkt_do_sw_fragmentation(struct VmxnetTxPkt *pkt, + NetClientState *nc) +{ + struct iovec fragment[VMXNET_MAX_FRAG_SG_LIST]; + size_t fragment_len = 0; + bool more_frags = false; + + /* some pointers for shorter code */ + void *l2_iov_base, *l3_iov_base; + size_t l2_iov_len, l3_iov_len; + int src_idx = VMXNET_TX_PKT_PL_START_FRAG, dst_idx; + size_t src_offset = 0; + size_t fragment_offset = 0; + + l2_iov_base = pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_base; + l2_iov_len = pkt->vec[VMXNET_TX_PKT_L2HDR_FRAG].iov_len; + l3_iov_base = pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_base; + l3_iov_len = pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len; + + /* Copy headers */ + fragment[VMXNET_TX_PKT_FRAGMENT_L2_HDR_POS].iov_base = l2_iov_base; + fragment[VMXNET_TX_PKT_FRAGMENT_L2_HDR_POS].iov_len = l2_iov_len; + fragment[VMXNET_TX_PKT_FRAGMENT_L3_HDR_POS].iov_base = l3_iov_base; + fragment[VMXNET_TX_PKT_FRAGMENT_L3_HDR_POS].iov_len = l3_iov_len; + + + /* Put as much data as possible and send */ + do { + fragment_len = vmxnet_tx_pkt_fetch_fragment(pkt, &src_idx, &src_offset, + fragment, &dst_idx); + + more_frags = (fragment_offset + fragment_len < pkt->payload_len); + + eth_setup_ip4_fragmentation(l2_iov_base, l2_iov_len, l3_iov_base, + l3_iov_len, fragment_len, fragment_offset, more_frags); + + eth_fix_ip4_checksum(l3_iov_base, l3_iov_len); + + qemu_sendv_packet(nc, fragment, dst_idx); + + fragment_offset += fragment_len; + + } while (more_frags); + + return true; +} + +bool vmxnet_tx_pkt_send(struct VmxnetTxPkt *pkt, NetClientState *nc) +{ + assert(pkt); + + if (!pkt->has_virt_hdr && + pkt->virt_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + vmxnet_tx_pkt_do_sw_csum(pkt); + } + + /* + * Since underlying infrastructure does not support IP datagrams longer + * than 64K we should drop such packets and don't even try to send + */ + if (VIRTIO_NET_HDR_GSO_NONE != pkt->virt_hdr.gso_type) { + if (pkt->payload_len > + ETH_MAX_IP_DGRAM_LEN - + pkt->vec[VMXNET_TX_PKT_L3HDR_FRAG].iov_len) { + return false; + } + } + + if (pkt->has_virt_hdr || + pkt->virt_hdr.gso_type == VIRTIO_NET_HDR_GSO_NONE) { + qemu_sendv_packet(nc, pkt->vec, + pkt->payload_frags + VMXNET_TX_PKT_PL_START_FRAG); + return true; + } + + return vmxnet_tx_pkt_do_sw_fragmentation(pkt, nc); +} diff --git a/hw/vmxnet_tx_pkt.h b/hw/vmxnet_tx_pkt.h new file mode 100644 index 0000000000..57121a6fe5 --- /dev/null +++ b/hw/vmxnet_tx_pkt.h @@ -0,0 +1,148 @@ +/* + * QEMU VMWARE VMXNET* paravirtual NICs - TX packets abstraction + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef VMXNET_TX_PKT_H +#define VMXNET_TX_PKT_H + +#include "stdint.h" +#include "stdbool.h" +#include "net/eth.h" +#include "exec/hwaddr.h" + +/* define to enable packet dump functions */ +/*#define VMXNET_TX_PKT_DEBUG*/ + +struct VmxnetTxPkt; + +/** + * Init function for tx packet functionality + * + * @pkt: packet pointer + * @max_frags: max tx ip fragments + * @has_virt_hdr: device uses virtio header. + */ +void vmxnet_tx_pkt_init(struct VmxnetTxPkt **pkt, uint32_t max_frags, + bool has_virt_hdr); + +/** + * Clean all tx packet resources. + * + * @pkt: packet. + */ +void vmxnet_tx_pkt_uninit(struct VmxnetTxPkt *pkt); + +/** + * get virtio header + * + * @pkt: packet + * @ret: virtio header + */ +struct virtio_net_hdr *vmxnet_tx_pkt_get_vhdr(struct VmxnetTxPkt *pkt); + +/** + * build virtio header (will be stored in module context) + * + * @pkt: packet + * @tso_enable: TSO enabled + * @csum_enable: CSO enabled + * @gso_size: MSS size for TSO + * + */ +void vmxnet_tx_pkt_build_vheader(struct VmxnetTxPkt *pkt, bool tso_enable, + bool csum_enable, uint32_t gso_size); + +/** + * updates vlan tag, and adds vlan header in case it is missing + * + * @pkt: packet + * @vlan: VLAN tag + * + */ +void vmxnet_tx_pkt_setup_vlan_header(struct VmxnetTxPkt *pkt, uint16_t vlan); + +/** + * populate data fragment into pkt context. + * + * @pkt: packet + * @pa: physical address of fragment + * @len: length of fragment + * + */ +bool vmxnet_tx_pkt_add_raw_fragment(struct VmxnetTxPkt *pkt, hwaddr pa, + size_t len); + +/** + * fix ip header fields and calculate checksums needed. + * + * @pkt: packet + * + */ +void vmxnet_tx_pkt_update_ip_checksums(struct VmxnetTxPkt *pkt); + +/** + * get length of all populated data. + * + * @pkt: packet + * @ret: total data length + * + */ +size_t vmxnet_tx_pkt_get_total_len(struct VmxnetTxPkt *pkt); + +/** + * get packet type + * + * @pkt: packet + * @ret: packet type + * + */ +eth_pkt_types_e vmxnet_tx_pkt_get_packet_type(struct VmxnetTxPkt *pkt); + +/** + * prints packet data if debug is enabled + * + * @pkt: packet + * + */ +void vmxnet_tx_pkt_dump(struct VmxnetTxPkt *pkt); + +/** + * reset tx packet private context (needed to be called between packets) + * + * @pkt: packet + * + */ +void vmxnet_tx_pkt_reset(struct VmxnetTxPkt *pkt); + +/** + * Send packet to qemu. handles sw offloads if vhdr is not supported. + * + * @pkt: packet + * @nc: NetClientState + * @ret: operation result + * + */ +bool vmxnet_tx_pkt_send(struct VmxnetTxPkt *pkt, NetClientState *nc); + +/** + * parse raw packet data and analyze offload requirements. + * + * @pkt: packet + * + */ +bool vmxnet_tx_pkt_parse(struct VmxnetTxPkt *pkt); + +#endif From 786fd2b0f87baded8c9e55307b99719eea3e016e Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Sat, 9 Mar 2013 11:21:06 +0200 Subject: [PATCH 6/7] VMXNET3 device implementation Signed-off-by: Dmitry Fleytman Signed-off-by: Yan Vugenfirer Signed-off-by: Stefan Hajnoczi --- default-configs/pci.mak | 1 + hw/Makefile.objs | 1 + hw/pci/pci.h | 1 + hw/vmxnet3.c | 2461 +++++++++++++++++++++++++++++++++++++++ hw/vmxnet3.h | 760 ++++++++++++ 5 files changed, 3224 insertions(+) create mode 100644 hw/vmxnet3.c create mode 100644 hw/vmxnet3.h diff --git a/default-configs/pci.mak b/default-configs/pci.mak index ee2d18d5f2..ce56d58055 100644 --- a/default-configs/pci.mak +++ b/default-configs/pci.mak @@ -13,6 +13,7 @@ CONFIG_LSI_SCSI_PCI=y CONFIG_MEGASAS_SCSI_PCI=y CONFIG_RTL8139_PCI=y CONFIG_E1000_PCI=y +CONFIG_VMXNET3_PCI=y CONFIG_IDE_CORE=y CONFIG_IDE_QDEV=y CONFIG_IDE_PCI=y diff --git a/hw/Makefile.objs b/hw/Makefile.objs index 1a988cad96..d0b2ecb97f 100644 --- a/hw/Makefile.objs +++ b/hw/Makefile.objs @@ -120,6 +120,7 @@ common-obj-$(CONFIG_PCNET_COMMON) += pcnet.o common-obj-$(CONFIG_E1000_PCI) += e1000.o common-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o common-obj-$(CONFIG_VMXNET3_PCI) += vmxnet_tx_pkt.o vmxnet_rx_pkt.o +common-obj-$(CONFIG_VMXNET3_PCI) += vmxnet3.o common-obj-$(CONFIG_SMC91C111) += smc91c111.o common-obj-$(CONFIG_LAN9118) += lan9118.o diff --git a/hw/pci/pci.h b/hw/pci/pci.h index f340fe57c9..3beb70bf9a 100644 --- a/hw/pci/pci.h +++ b/hw/pci/pci.h @@ -60,6 +60,7 @@ #define PCI_DEVICE_ID_VMWARE_NET 0x0720 #define PCI_DEVICE_ID_VMWARE_SCSI 0x0730 #define PCI_DEVICE_ID_VMWARE_IDE 0x1729 +#define PCI_DEVICE_ID_VMWARE_VMXNET3 0x07B0 /* Intel (0x8086) */ #define PCI_DEVICE_ID_INTEL_82551IT 0x1209 diff --git a/hw/vmxnet3.c b/hw/vmxnet3.c new file mode 100644 index 0000000000..925be8084a --- /dev/null +++ b/hw/vmxnet3.c @@ -0,0 +1,2461 @@ +/* + * QEMU VMWARE VMXNET3 paravirtual NIC + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + * + */ + +#include "hw.h" +#include "pci/pci.h" +#include "net/net.h" +#include "virtio-net.h" +#include "net/tap.h" +#include "net/checksum.h" +#include "sysemu/sysemu.h" +#include "qemu-common.h" +#include "qemu/bswap.h" +#include "pci/msix.h" +#include "pci/msi.h" + +#include "vmxnet3.h" +#include "vmxnet_debug.h" +#include "vmware_utils.h" +#include "vmxnet_tx_pkt.h" +#include "vmxnet_rx_pkt.h" + +#define PCI_DEVICE_ID_VMWARE_VMXNET3_REVISION 0x1 +#define VMXNET3_MSIX_BAR_SIZE 0x2000 + +#define VMXNET3_BAR0_IDX (0) +#define VMXNET3_BAR1_IDX (1) +#define VMXNET3_MSIX_BAR_IDX (2) + +#define VMXNET3_OFF_MSIX_TABLE (0x000) +#define VMXNET3_OFF_MSIX_PBA (0x800) + +/* Link speed in Mbps should be shifted by 16 */ +#define VMXNET3_LINK_SPEED (1000 << 16) + +/* Link status: 1 - up, 0 - down. */ +#define VMXNET3_LINK_STATUS_UP 0x1 + +/* Least significant bit should be set for revision and version */ +#define VMXNET3_DEVICE_VERSION 0x1 +#define VMXNET3_DEVICE_REVISION 0x1 + +/* Macros for rings descriptors access */ +#define VMXNET3_READ_TX_QUEUE_DESCR8(dpa, field) \ + (vmw_shmem_ld8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field))) + +#define VMXNET3_WRITE_TX_QUEUE_DESCR8(dpa, field, value) \ + (vmw_shmem_st8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field, value))) + +#define VMXNET3_READ_TX_QUEUE_DESCR32(dpa, field) \ + (vmw_shmem_ld32(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field))) + +#define VMXNET3_WRITE_TX_QUEUE_DESCR32(dpa, field, value) \ + (vmw_shmem_st32(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field), value)) + +#define VMXNET3_READ_TX_QUEUE_DESCR64(dpa, field) \ + (vmw_shmem_ld64(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field))) + +#define VMXNET3_WRITE_TX_QUEUE_DESCR64(dpa, field, value) \ + (vmw_shmem_st64(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field), value)) + +#define VMXNET3_READ_RX_QUEUE_DESCR64(dpa, field) \ + (vmw_shmem_ld64(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field))) + +#define VMXNET3_READ_RX_QUEUE_DESCR32(dpa, field) \ + (vmw_shmem_ld32(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field))) + +#define VMXNET3_WRITE_RX_QUEUE_DESCR64(dpa, field, value) \ + (vmw_shmem_st64(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field), value)) + +#define VMXNET3_WRITE_RX_QUEUE_DESCR8(dpa, field, value) \ + (vmw_shmem_st8(dpa + offsetof(struct Vmxnet3_RxQueueDesc, field), value)) + +/* Macros for guest driver shared area access */ +#define VMXNET3_READ_DRV_SHARED64(shpa, field) \ + (vmw_shmem_ld64(shpa + offsetof(struct Vmxnet3_DriverShared, field))) + +#define VMXNET3_READ_DRV_SHARED32(shpa, field) \ + (vmw_shmem_ld32(shpa + offsetof(struct Vmxnet3_DriverShared, field))) + +#define VMXNET3_WRITE_DRV_SHARED32(shpa, field, val) \ + (vmw_shmem_st32(shpa + offsetof(struct Vmxnet3_DriverShared, field), val)) + +#define VMXNET3_READ_DRV_SHARED16(shpa, field) \ + (vmw_shmem_ld16(shpa + offsetof(struct Vmxnet3_DriverShared, field))) + +#define VMXNET3_READ_DRV_SHARED8(shpa, field) \ + (vmw_shmem_ld8(shpa + offsetof(struct Vmxnet3_DriverShared, field))) + +#define VMXNET3_READ_DRV_SHARED(shpa, field, b, l) \ + (vmw_shmem_read(shpa + offsetof(struct Vmxnet3_DriverShared, field), b, l)) + +#define VMXNET_FLAG_IS_SET(field, flag) (((field) & (flag)) == (flag)) + +#define TYPE_VMXNET3 "vmxnet3" +#define VMXNET3(obj) OBJECT_CHECK(VMXNET3State, (obj), TYPE_VMXNET3) + +/* Cyclic ring abstraction */ +typedef struct { + hwaddr pa; + size_t size; + size_t cell_size; + size_t next; + uint8_t gen; +} Vmxnet3Ring; + +static inline void vmxnet3_ring_init(Vmxnet3Ring *ring, + hwaddr pa, + size_t size, + size_t cell_size, + bool zero_region) +{ + ring->pa = pa; + ring->size = size; + ring->cell_size = cell_size; + ring->gen = VMXNET3_INIT_GEN; + ring->next = 0; + + if (zero_region) { + vmw_shmem_set(pa, 0, size * cell_size); + } +} + +#define VMXNET3_RING_DUMP(macro, ring_name, ridx, r) \ + macro("%s#%d: base %" PRIx64 " size %lu cell_size %lu gen %d next %lu", \ + (ring_name), (ridx), \ + (r)->pa, (r)->size, (r)->cell_size, (r)->gen, (r)->next) + +static inline void vmxnet3_ring_inc(Vmxnet3Ring *ring) +{ + if (++ring->next >= ring->size) { + ring->next = 0; + ring->gen ^= 1; + } +} + +static inline void vmxnet3_ring_dec(Vmxnet3Ring *ring) +{ + if (ring->next-- == 0) { + ring->next = ring->size - 1; + ring->gen ^= 1; + } +} + +static inline hwaddr vmxnet3_ring_curr_cell_pa(Vmxnet3Ring *ring) +{ + return ring->pa + ring->next * ring->cell_size; +} + +static inline void vmxnet3_ring_read_curr_cell(Vmxnet3Ring *ring, void *buff) +{ + vmw_shmem_read(vmxnet3_ring_curr_cell_pa(ring), buff, ring->cell_size); +} + +static inline void vmxnet3_ring_write_curr_cell(Vmxnet3Ring *ring, void *buff) +{ + vmw_shmem_write(vmxnet3_ring_curr_cell_pa(ring), buff, ring->cell_size); +} + +static inline size_t vmxnet3_ring_curr_cell_idx(Vmxnet3Ring *ring) +{ + return ring->next; +} + +static inline uint8_t vmxnet3_ring_curr_gen(Vmxnet3Ring *ring) +{ + return ring->gen; +} + +/* Debug trace-related functions */ +static inline void +vmxnet3_dump_tx_descr(struct Vmxnet3_TxDesc *descr) +{ + VMW_PKPRN("TX DESCR: " + "addr %" PRIx64 ", len: %d, gen: %d, rsvd: %d, " + "dtype: %d, ext1: %d, msscof: %d, hlen: %d, om: %d, " + "eop: %d, cq: %d, ext2: %d, ti: %d, tci: %d", + le64_to_cpu(descr->addr), descr->len, descr->gen, descr->rsvd, + descr->dtype, descr->ext1, descr->msscof, descr->hlen, descr->om, + descr->eop, descr->cq, descr->ext2, descr->ti, descr->tci); +} + +static inline void +vmxnet3_dump_virt_hdr(struct virtio_net_hdr *vhdr) +{ + VMW_PKPRN("VHDR: flags 0x%x, gso_type: 0x%x, hdr_len: %d, gso_size: %d, " + "csum_start: %d, csum_offset: %d", + vhdr->flags, vhdr->gso_type, vhdr->hdr_len, vhdr->gso_size, + vhdr->csum_start, vhdr->csum_offset); +} + +static inline void +vmxnet3_dump_rx_descr(struct Vmxnet3_RxDesc *descr) +{ + VMW_PKPRN("RX DESCR: addr %" PRIx64 ", len: %d, gen: %d, rsvd: %d, " + "dtype: %d, ext1: %d, btype: %d", + le64_to_cpu(descr->addr), descr->len, descr->gen, + descr->rsvd, descr->dtype, descr->ext1, descr->btype); +} + +/* Device state and helper functions */ +#define VMXNET3_RX_RINGS_PER_QUEUE (2) + +typedef struct { + Vmxnet3Ring tx_ring; + Vmxnet3Ring comp_ring; + + uint8_t intr_idx; + hwaddr tx_stats_pa; + struct UPT1_TxStats txq_stats; +} Vmxnet3TxqDescr; + +typedef struct { + Vmxnet3Ring rx_ring[VMXNET3_RX_RINGS_PER_QUEUE]; + Vmxnet3Ring comp_ring; + uint8_t intr_idx; + hwaddr rx_stats_pa; + struct UPT1_RxStats rxq_stats; +} Vmxnet3RxqDescr; + +typedef struct { + bool is_masked; + bool is_pending; + bool is_asserted; +} Vmxnet3IntState; + +typedef struct { + PCIDevice parent_obj; + NICState *nic; + NICConf conf; + MemoryRegion bar0; + MemoryRegion bar1; + MemoryRegion msix_bar; + + Vmxnet3RxqDescr rxq_descr[VMXNET3_DEVICE_MAX_RX_QUEUES]; + Vmxnet3TxqDescr txq_descr[VMXNET3_DEVICE_MAX_TX_QUEUES]; + + /* Whether MSI-X support was installed successfully */ + bool msix_used; + /* Whether MSI support was installed successfully */ + bool msi_used; + hwaddr drv_shmem; + hwaddr temp_shared_guest_driver_memory; + + uint8_t txq_num; + + /* This boolean tells whether RX packet being indicated has to */ + /* be split into head and body chunks from different RX rings */ + bool rx_packets_compound; + + bool rx_vlan_stripping; + bool lro_supported; + + uint8_t rxq_num; + + /* Network MTU */ + uint32_t mtu; + + /* Maximum number of fragments for indicated TX packets */ + uint32_t max_tx_frags; + + /* Maximum number of fragments for indicated RX packets */ + uint16_t max_rx_frags; + + /* Index for events interrupt */ + uint8_t event_int_idx; + + /* Whether automatic interrupts masking enabled */ + bool auto_int_masking; + + bool peer_has_vhdr; + + /* TX packets to QEMU interface */ + struct VmxnetTxPkt *tx_pkt; + uint32_t offload_mode; + uint32_t cso_or_gso_size; + uint16_t tci; + bool needs_vlan; + + struct VmxnetRxPkt *rx_pkt; + + bool tx_sop; + bool skip_current_tx_pkt; + + uint32_t device_active; + uint32_t last_command; + + uint32_t link_status_and_speed; + + Vmxnet3IntState interrupt_states[VMXNET3_MAX_INTRS]; + + uint32_t temp_mac; /* To store the low part first */ + + MACAddr perm_mac; + uint32_t vlan_table[VMXNET3_VFT_SIZE]; + uint32_t rx_mode; + MACAddr *mcast_list; + uint32_t mcast_list_len; + uint32_t mcast_list_buff_size; /* needed for live migration. */ +} VMXNET3State; + +/* Interrupt management */ + +/* + *This function returns sign whether interrupt line is in asserted state + * This depends on the type of interrupt used. For INTX interrupt line will + * be asserted until explicit deassertion, for MSI(X) interrupt line will + * be deasserted automatically due to notification semantics of the MSI(X) + * interrupts + */ +static bool _vmxnet3_assert_interrupt_line(VMXNET3State *s, uint32_t int_idx) +{ + PCIDevice *d = PCI_DEVICE(s); + + if (s->msix_used && msix_enabled(d)) { + VMW_IRPRN("Sending MSI-X notification for vector %u", int_idx); + msix_notify(d, int_idx); + return false; + } + if (s->msi_used && msi_enabled(d)) { + VMW_IRPRN("Sending MSI notification for vector %u", int_idx); + msi_notify(d, int_idx); + return false; + } + + VMW_IRPRN("Asserting line for interrupt %u", int_idx); + qemu_set_irq(d->irq[int_idx], 1); + return true; +} + +static void _vmxnet3_deassert_interrupt_line(VMXNET3State *s, int lidx) +{ + PCIDevice *d = PCI_DEVICE(s); + + /* + * This function should never be called for MSI(X) interrupts + * because deassertion never required for message interrupts + */ + assert(!s->msix_used || !msix_enabled(d)); + /* + * This function should never be called for MSI(X) interrupts + * because deassertion never required for message interrupts + */ + assert(!s->msi_used || !msi_enabled(d)); + + VMW_IRPRN("Deasserting line for interrupt %u", lidx); + qemu_set_irq(d->irq[lidx], 0); +} + +static void vmxnet3_update_interrupt_line_state(VMXNET3State *s, int lidx) +{ + if (!s->interrupt_states[lidx].is_pending && + s->interrupt_states[lidx].is_asserted) { + VMW_IRPRN("New interrupt line state for index %d is DOWN", lidx); + _vmxnet3_deassert_interrupt_line(s, lidx); + s->interrupt_states[lidx].is_asserted = false; + return; + } + + if (s->interrupt_states[lidx].is_pending && + !s->interrupt_states[lidx].is_masked && + !s->interrupt_states[lidx].is_asserted) { + VMW_IRPRN("New interrupt line state for index %d is UP", lidx); + s->interrupt_states[lidx].is_asserted = + _vmxnet3_assert_interrupt_line(s, lidx); + s->interrupt_states[lidx].is_pending = false; + return; + } +} + +static void vmxnet3_trigger_interrupt(VMXNET3State *s, int lidx) +{ + PCIDevice *d = PCI_DEVICE(s); + s->interrupt_states[lidx].is_pending = true; + vmxnet3_update_interrupt_line_state(s, lidx); + + if (s->msix_used && msix_enabled(d) && s->auto_int_masking) { + goto do_automask; + } + + if (s->msi_used && msi_enabled(d) && s->auto_int_masking) { + goto do_automask; + } + + return; + +do_automask: + s->interrupt_states[lidx].is_masked = true; + vmxnet3_update_interrupt_line_state(s, lidx); +} + +static bool vmxnet3_interrupt_asserted(VMXNET3State *s, int lidx) +{ + return s->interrupt_states[lidx].is_asserted; +} + +static void vmxnet3_clear_interrupt(VMXNET3State *s, int int_idx) +{ + s->interrupt_states[int_idx].is_pending = false; + if (s->auto_int_masking) { + s->interrupt_states[int_idx].is_masked = true; + } + vmxnet3_update_interrupt_line_state(s, int_idx); +} + +static void +vmxnet3_on_interrupt_mask_changed(VMXNET3State *s, int lidx, bool is_masked) +{ + s->interrupt_states[lidx].is_masked = is_masked; + vmxnet3_update_interrupt_line_state(s, lidx); +} + +static bool vmxnet3_verify_driver_magic(hwaddr dshmem) +{ + return (VMXNET3_READ_DRV_SHARED32(dshmem, magic) == VMXNET3_REV1_MAGIC); +} + +#define VMXNET3_GET_BYTE(x, byte_num) (((x) >> (byte_num)*8) & 0xFF) +#define VMXNET3_MAKE_BYTE(byte_num, val) \ + (((uint32_t)((val) & 0xFF)) << (byte_num)*8) + +static void vmxnet3_set_variable_mac(VMXNET3State *s, uint32_t h, uint32_t l) +{ + s->conf.macaddr.a[0] = VMXNET3_GET_BYTE(l, 0); + s->conf.macaddr.a[1] = VMXNET3_GET_BYTE(l, 1); + s->conf.macaddr.a[2] = VMXNET3_GET_BYTE(l, 2); + s->conf.macaddr.a[3] = VMXNET3_GET_BYTE(l, 3); + s->conf.macaddr.a[4] = VMXNET3_GET_BYTE(h, 0); + s->conf.macaddr.a[5] = VMXNET3_GET_BYTE(h, 1); + + VMW_CFPRN("Variable MAC: " VMXNET_MF, VMXNET_MA(s->conf.macaddr.a)); + + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static uint64_t vmxnet3_get_mac_low(MACAddr *addr) +{ + return VMXNET3_MAKE_BYTE(0, addr->a[0]) | + VMXNET3_MAKE_BYTE(1, addr->a[1]) | + VMXNET3_MAKE_BYTE(2, addr->a[2]) | + VMXNET3_MAKE_BYTE(3, addr->a[3]); +} + +static uint64_t vmxnet3_get_mac_high(MACAddr *addr) +{ + return VMXNET3_MAKE_BYTE(0, addr->a[4]) | + VMXNET3_MAKE_BYTE(1, addr->a[5]); +} + +static void +vmxnet3_inc_tx_consumption_counter(VMXNET3State *s, int qidx) +{ + vmxnet3_ring_inc(&s->txq_descr[qidx].tx_ring); +} + +static inline void +vmxnet3_inc_rx_consumption_counter(VMXNET3State *s, int qidx, int ridx) +{ + vmxnet3_ring_inc(&s->rxq_descr[qidx].rx_ring[ridx]); +} + +static inline void +vmxnet3_inc_tx_completion_counter(VMXNET3State *s, int qidx) +{ + vmxnet3_ring_inc(&s->txq_descr[qidx].comp_ring); +} + +static void +vmxnet3_inc_rx_completion_counter(VMXNET3State *s, int qidx) +{ + vmxnet3_ring_inc(&s->rxq_descr[qidx].comp_ring); +} + +static void +vmxnet3_dec_rx_completion_counter(VMXNET3State *s, int qidx) +{ + vmxnet3_ring_dec(&s->rxq_descr[qidx].comp_ring); +} + +static void vmxnet3_complete_packet(VMXNET3State *s, int qidx, uint32 tx_ridx) +{ + struct Vmxnet3_TxCompDesc txcq_descr; + + VMXNET3_RING_DUMP(VMW_RIPRN, "TXC", qidx, &s->txq_descr[qidx].comp_ring); + + txcq_descr.txdIdx = tx_ridx; + txcq_descr.gen = vmxnet3_ring_curr_gen(&s->txq_descr[qidx].comp_ring); + + vmxnet3_ring_write_curr_cell(&s->txq_descr[qidx].comp_ring, &txcq_descr); + + /* Flush changes in TX descriptor before changing the counter value */ + smp_wmb(); + + vmxnet3_inc_tx_completion_counter(s, qidx); + vmxnet3_trigger_interrupt(s, s->txq_descr[qidx].intr_idx); +} + +static bool +vmxnet3_setup_tx_offloads(VMXNET3State *s) +{ + switch (s->offload_mode) { + case VMXNET3_OM_NONE: + vmxnet_tx_pkt_build_vheader(s->tx_pkt, false, false, 0); + break; + + case VMXNET3_OM_CSUM: + vmxnet_tx_pkt_build_vheader(s->tx_pkt, false, true, 0); + VMW_PKPRN("L4 CSO requested\n"); + break; + + case VMXNET3_OM_TSO: + vmxnet_tx_pkt_build_vheader(s->tx_pkt, true, true, + s->cso_or_gso_size); + vmxnet_tx_pkt_update_ip_checksums(s->tx_pkt); + VMW_PKPRN("GSO offload requested."); + break; + + default: + assert(false); + return false; + } + + return true; +} + +static void +vmxnet3_tx_retrieve_metadata(VMXNET3State *s, + const struct Vmxnet3_TxDesc *txd) +{ + s->offload_mode = txd->om; + s->cso_or_gso_size = txd->msscof; + s->tci = txd->tci; + s->needs_vlan = txd->ti; +} + +typedef enum { + VMXNET3_PKT_STATUS_OK, + VMXNET3_PKT_STATUS_ERROR, + VMXNET3_PKT_STATUS_DISCARD,/* only for tx */ + VMXNET3_PKT_STATUS_OUT_OF_BUF /* only for rx */ +} Vmxnet3PktStatus; + +static void +vmxnet3_on_tx_done_update_stats(VMXNET3State *s, int qidx, + Vmxnet3PktStatus status) +{ + size_t tot_len = vmxnet_tx_pkt_get_total_len(s->tx_pkt); + struct UPT1_TxStats *stats = &s->txq_descr[qidx].txq_stats; + + switch (status) { + case VMXNET3_PKT_STATUS_OK: + switch (vmxnet_tx_pkt_get_packet_type(s->tx_pkt)) { + case ETH_PKT_BCAST: + stats->bcastPktsTxOK++; + stats->bcastBytesTxOK += tot_len; + break; + case ETH_PKT_MCAST: + stats->mcastPktsTxOK++; + stats->mcastBytesTxOK += tot_len; + break; + case ETH_PKT_UCAST: + stats->ucastPktsTxOK++; + stats->ucastBytesTxOK += tot_len; + break; + default: + assert(false); + } + + if (s->offload_mode == VMXNET3_OM_TSO) { + /* + * According to VMWARE headers this statistic is a number + * of packets after segmentation but since we don't have + * this information in QEMU model, the best we can do is to + * provide number of non-segmented packets + */ + stats->TSOPktsTxOK++; + stats->TSOBytesTxOK += tot_len; + } + break; + + case VMXNET3_PKT_STATUS_DISCARD: + stats->pktsTxDiscard++; + break; + + case VMXNET3_PKT_STATUS_ERROR: + stats->pktsTxError++; + break; + + default: + assert(false); + } +} + +static void +vmxnet3_on_rx_done_update_stats(VMXNET3State *s, + int qidx, + Vmxnet3PktStatus status) +{ + struct UPT1_RxStats *stats = &s->rxq_descr[qidx].rxq_stats; + size_t tot_len = vmxnet_rx_pkt_get_total_len(s->rx_pkt); + + switch (status) { + case VMXNET3_PKT_STATUS_OUT_OF_BUF: + stats->pktsRxOutOfBuf++; + break; + + case VMXNET3_PKT_STATUS_ERROR: + stats->pktsRxError++; + break; + case VMXNET3_PKT_STATUS_OK: + switch (vmxnet_rx_pkt_get_packet_type(s->rx_pkt)) { + case ETH_PKT_BCAST: + stats->bcastPktsRxOK++; + stats->bcastBytesRxOK += tot_len; + break; + case ETH_PKT_MCAST: + stats->mcastPktsRxOK++; + stats->mcastBytesRxOK += tot_len; + break; + case ETH_PKT_UCAST: + stats->ucastPktsRxOK++; + stats->ucastBytesRxOK += tot_len; + break; + default: + assert(false); + } + + if (tot_len > s->mtu) { + stats->LROPktsRxOK++; + stats->LROBytesRxOK += tot_len; + } + break; + default: + assert(false); + } +} + +static inline bool +vmxnet3_pop_next_tx_descr(VMXNET3State *s, + int qidx, + struct Vmxnet3_TxDesc *txd, + uint32_t *descr_idx) +{ + Vmxnet3Ring *ring = &s->txq_descr[qidx].tx_ring; + + vmxnet3_ring_read_curr_cell(ring, txd); + if (txd->gen == vmxnet3_ring_curr_gen(ring)) { + /* Only read after generation field verification */ + smp_rmb(); + /* Re-read to be sure we got the latest version */ + vmxnet3_ring_read_curr_cell(ring, txd); + VMXNET3_RING_DUMP(VMW_RIPRN, "TX", qidx, ring); + *descr_idx = vmxnet3_ring_curr_cell_idx(ring); + vmxnet3_inc_tx_consumption_counter(s, qidx); + return true; + } + + return false; +} + +static bool +vmxnet3_send_packet(VMXNET3State *s, uint32_t qidx) +{ + Vmxnet3PktStatus status = VMXNET3_PKT_STATUS_OK; + + if (!vmxnet3_setup_tx_offloads(s)) { + status = VMXNET3_PKT_STATUS_ERROR; + goto func_exit; + } + + /* debug prints */ + vmxnet3_dump_virt_hdr(vmxnet_tx_pkt_get_vhdr(s->tx_pkt)); + vmxnet_tx_pkt_dump(s->tx_pkt); + + if (!vmxnet_tx_pkt_send(s->tx_pkt, qemu_get_queue(s->nic))) { + status = VMXNET3_PKT_STATUS_DISCARD; + goto func_exit; + } + +func_exit: + vmxnet3_on_tx_done_update_stats(s, qidx, status); + return (status == VMXNET3_PKT_STATUS_OK); +} + +static void vmxnet3_process_tx_queue(VMXNET3State *s, int qidx) +{ + struct Vmxnet3_TxDesc txd; + uint32_t txd_idx; + uint32_t data_len; + hwaddr data_pa; + + for (;;) { + if (!vmxnet3_pop_next_tx_descr(s, qidx, &txd, &txd_idx)) { + break; + } + + vmxnet3_dump_tx_descr(&txd); + + if (!s->skip_current_tx_pkt) { + data_len = (txd.len > 0) ? txd.len : VMXNET3_MAX_TX_BUF_SIZE; + data_pa = le64_to_cpu(txd.addr); + + if (!vmxnet_tx_pkt_add_raw_fragment(s->tx_pkt, + data_pa, + data_len)) { + s->skip_current_tx_pkt = true; + } + } + + if (s->tx_sop) { + vmxnet3_tx_retrieve_metadata(s, &txd); + s->tx_sop = false; + } + + if (txd.eop) { + if (!s->skip_current_tx_pkt) { + vmxnet_tx_pkt_parse(s->tx_pkt); + + if (s->needs_vlan) { + vmxnet_tx_pkt_setup_vlan_header(s->tx_pkt, s->tci); + } + + vmxnet3_send_packet(s, qidx); + } else { + vmxnet3_on_tx_done_update_stats(s, qidx, + VMXNET3_PKT_STATUS_ERROR); + } + + vmxnet3_complete_packet(s, qidx, txd_idx); + s->tx_sop = true; + s->skip_current_tx_pkt = false; + vmxnet_tx_pkt_reset(s->tx_pkt); + } + } +} + +static inline void +vmxnet3_read_next_rx_descr(VMXNET3State *s, int qidx, int ridx, + struct Vmxnet3_RxDesc *dbuf, uint32_t *didx) +{ + Vmxnet3Ring *ring = &s->rxq_descr[qidx].rx_ring[ridx]; + *didx = vmxnet3_ring_curr_cell_idx(ring); + vmxnet3_ring_read_curr_cell(ring, dbuf); +} + +static inline uint8_t +vmxnet3_get_rx_ring_gen(VMXNET3State *s, int qidx, int ridx) +{ + return s->rxq_descr[qidx].rx_ring[ridx].gen; +} + +static inline hwaddr +vmxnet3_pop_rxc_descr(VMXNET3State *s, int qidx, uint32_t *descr_gen) +{ + uint8_t ring_gen; + struct Vmxnet3_RxCompDesc rxcd; + + hwaddr daddr = + vmxnet3_ring_curr_cell_pa(&s->rxq_descr[qidx].comp_ring); + + cpu_physical_memory_read(daddr, &rxcd, sizeof(struct Vmxnet3_RxCompDesc)); + ring_gen = vmxnet3_ring_curr_gen(&s->rxq_descr[qidx].comp_ring); + + if (rxcd.gen != ring_gen) { + *descr_gen = ring_gen; + vmxnet3_inc_rx_completion_counter(s, qidx); + return daddr; + } + + return 0; +} + +static inline void +vmxnet3_revert_rxc_descr(VMXNET3State *s, int qidx) +{ + vmxnet3_dec_rx_completion_counter(s, qidx); +} + +#define RXQ_IDX (0) +#define RX_HEAD_BODY_RING (0) +#define RX_BODY_ONLY_RING (1) + +static bool +vmxnet3_get_next_head_rx_descr(VMXNET3State *s, + struct Vmxnet3_RxDesc *descr_buf, + uint32_t *descr_idx, + uint32_t *ridx) +{ + for (;;) { + uint32_t ring_gen; + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING, + descr_buf, descr_idx); + + /* If no more free descriptors - return */ + ring_gen = vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_HEAD_BODY_RING); + if (descr_buf->gen != ring_gen) { + return false; + } + + /* Only read after generation field verification */ + smp_rmb(); + /* Re-read to be sure we got the latest version */ + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING, + descr_buf, descr_idx); + + /* Mark current descriptor as used/skipped */ + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_HEAD_BODY_RING); + + /* If this is what we are looking for - return */ + if (descr_buf->btype == VMXNET3_RXD_BTYPE_HEAD) { + *ridx = RX_HEAD_BODY_RING; + return true; + } + } +} + +static bool +vmxnet3_get_next_body_rx_descr(VMXNET3State *s, + struct Vmxnet3_RxDesc *d, + uint32_t *didx, + uint32_t *ridx) +{ + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING, d, didx); + + /* Try to find corresponding descriptor in head/body ring */ + if (d->gen == vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_HEAD_BODY_RING)) { + /* Only read after generation field verification */ + smp_rmb(); + /* Re-read to be sure we got the latest version */ + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_HEAD_BODY_RING, d, didx); + if (d->btype == VMXNET3_RXD_BTYPE_BODY) { + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_HEAD_BODY_RING); + *ridx = RX_HEAD_BODY_RING; + return true; + } + } + + /* + * If there is no free descriptors on head/body ring or next free + * descriptor is a head descriptor switch to body only ring + */ + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_BODY_ONLY_RING, d, didx); + + /* If no more free descriptors - return */ + if (d->gen == vmxnet3_get_rx_ring_gen(s, RXQ_IDX, RX_BODY_ONLY_RING)) { + /* Only read after generation field verification */ + smp_rmb(); + /* Re-read to be sure we got the latest version */ + vmxnet3_read_next_rx_descr(s, RXQ_IDX, RX_BODY_ONLY_RING, d, didx); + assert(d->btype == VMXNET3_RXD_BTYPE_BODY); + *ridx = RX_BODY_ONLY_RING; + vmxnet3_inc_rx_consumption_counter(s, RXQ_IDX, RX_BODY_ONLY_RING); + return true; + } + + return false; +} + +static inline bool +vmxnet3_get_next_rx_descr(VMXNET3State *s, bool is_head, + struct Vmxnet3_RxDesc *descr_buf, + uint32_t *descr_idx, + uint32_t *ridx) +{ + if (is_head || !s->rx_packets_compound) { + return vmxnet3_get_next_head_rx_descr(s, descr_buf, descr_idx, ridx); + } else { + return vmxnet3_get_next_body_rx_descr(s, descr_buf, descr_idx, ridx); + } +} + +static void vmxnet3_rx_update_descr(struct VmxnetRxPkt *pkt, + struct Vmxnet3_RxCompDesc *rxcd) +{ + int csum_ok, is_gso; + bool isip4, isip6, istcp, isudp; + struct virtio_net_hdr *vhdr; + uint8_t offload_type; + + if (vmxnet_rx_pkt_is_vlan_stripped(pkt)) { + rxcd->ts = 1; + rxcd->tci = vmxnet_rx_pkt_get_vlan_tag(pkt); + } + + if (!vmxnet_rx_pkt_has_virt_hdr(pkt)) { + goto nocsum; + } + + vhdr = vmxnet_rx_pkt_get_vhdr(pkt); + /* + * Checksum is valid when lower level tell so or when lower level + * requires checksum offload telling that packet produced/bridged + * locally and did travel over network after last checksum calculation + * or production + */ + csum_ok = VMXNET_FLAG_IS_SET(vhdr->flags, VIRTIO_NET_HDR_F_DATA_VALID) || + VMXNET_FLAG_IS_SET(vhdr->flags, VIRTIO_NET_HDR_F_NEEDS_CSUM); + + offload_type = vhdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN; + is_gso = (offload_type != VIRTIO_NET_HDR_GSO_NONE) ? 1 : 0; + + if (!csum_ok && !is_gso) { + goto nocsum; + } + + vmxnet_rx_pkt_get_protocols(pkt, &isip4, &isip6, &isudp, &istcp); + if ((!istcp && !isudp) || (!isip4 && !isip6)) { + goto nocsum; + } + + rxcd->cnc = 0; + rxcd->v4 = isip4 ? 1 : 0; + rxcd->v6 = isip6 ? 1 : 0; + rxcd->tcp = istcp ? 1 : 0; + rxcd->udp = isudp ? 1 : 0; + rxcd->fcs = rxcd->tuc = rxcd->ipc = 1; + return; + +nocsum: + rxcd->cnc = 1; + return; +} + +static void +vmxnet3_physical_memory_writev(const struct iovec *iov, + size_t start_iov_off, + hwaddr target_addr, + size_t bytes_to_copy) +{ + size_t curr_off = 0; + size_t copied = 0; + + while (bytes_to_copy) { + if (start_iov_off < (curr_off + iov->iov_len)) { + size_t chunk_len = + MIN((curr_off + iov->iov_len) - start_iov_off, bytes_to_copy); + + cpu_physical_memory_write(target_addr + copied, + iov->iov_base + start_iov_off - curr_off, + chunk_len); + + copied += chunk_len; + start_iov_off += chunk_len; + curr_off = start_iov_off; + bytes_to_copy -= chunk_len; + } else { + curr_off += iov->iov_len; + } + iov++; + } +} + +static bool +vmxnet3_indicate_packet(VMXNET3State *s) +{ + struct Vmxnet3_RxDesc rxd; + bool is_head = true; + uint32_t rxd_idx; + uint32_t rx_ridx; + + struct Vmxnet3_RxCompDesc rxcd; + uint32_t new_rxcd_gen = VMXNET3_INIT_GEN; + hwaddr new_rxcd_pa = 0; + hwaddr ready_rxcd_pa = 0; + struct iovec *data = vmxnet_rx_pkt_get_iovec(s->rx_pkt); + size_t bytes_copied = 0; + size_t bytes_left = vmxnet_rx_pkt_get_total_len(s->rx_pkt); + uint16_t num_frags = 0; + size_t chunk_size; + + vmxnet_rx_pkt_dump(s->rx_pkt); + + while (bytes_left > 0) { + + /* cannot add more frags to packet */ + if (num_frags == s->max_rx_frags) { + break; + } + + new_rxcd_pa = vmxnet3_pop_rxc_descr(s, RXQ_IDX, &new_rxcd_gen); + if (!new_rxcd_pa) { + break; + } + + if (!vmxnet3_get_next_rx_descr(s, is_head, &rxd, &rxd_idx, &rx_ridx)) { + break; + } + + chunk_size = MIN(bytes_left, rxd.len); + vmxnet3_physical_memory_writev(data, bytes_copied, + le64_to_cpu(rxd.addr), chunk_size); + bytes_copied += chunk_size; + bytes_left -= chunk_size; + + vmxnet3_dump_rx_descr(&rxd); + + if (0 != ready_rxcd_pa) { + cpu_physical_memory_write(ready_rxcd_pa, &rxcd, sizeof(rxcd)); + } + + memset(&rxcd, 0, sizeof(struct Vmxnet3_RxCompDesc)); + rxcd.rxdIdx = rxd_idx; + rxcd.len = chunk_size; + rxcd.sop = is_head; + rxcd.gen = new_rxcd_gen; + rxcd.rqID = RXQ_IDX + rx_ridx * s->rxq_num; + + if (0 == bytes_left) { + vmxnet3_rx_update_descr(s->rx_pkt, &rxcd); + } + + VMW_RIPRN("RX Completion descriptor: rxRing: %lu rxIdx %lu len %lu " + "sop %d csum_correct %lu", + (unsigned long) rx_ridx, + (unsigned long) rxcd.rxdIdx, + (unsigned long) rxcd.len, + (int) rxcd.sop, + (unsigned long) rxcd.tuc); + + is_head = false; + ready_rxcd_pa = new_rxcd_pa; + new_rxcd_pa = 0; + } + + if (0 != ready_rxcd_pa) { + rxcd.eop = 1; + rxcd.err = (0 != bytes_left); + cpu_physical_memory_write(ready_rxcd_pa, &rxcd, sizeof(rxcd)); + + /* Flush RX descriptor changes */ + smp_wmb(); + } + + if (0 != new_rxcd_pa) { + vmxnet3_revert_rxc_descr(s, RXQ_IDX); + } + + vmxnet3_trigger_interrupt(s, s->rxq_descr[RXQ_IDX].intr_idx); + + if (bytes_left == 0) { + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX, VMXNET3_PKT_STATUS_OK); + return true; + } else if (num_frags == s->max_rx_frags) { + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX, VMXNET3_PKT_STATUS_ERROR); + return false; + } else { + vmxnet3_on_rx_done_update_stats(s, RXQ_IDX, + VMXNET3_PKT_STATUS_OUT_OF_BUF); + return false; + } +} + +static void +vmxnet3_io_bar0_write(void *opaque, hwaddr addr, + uint64_t val, unsigned size) +{ + VMXNET3State *s = opaque; + + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_TXPROD, + VMXNET3_DEVICE_MAX_TX_QUEUES, VMXNET3_REG_ALIGN)) { + int tx_queue_idx = + VMW_MULTIREG_IDX_BY_ADDR(addr, VMXNET3_REG_TXPROD, + VMXNET3_REG_ALIGN); + assert(tx_queue_idx <= s->txq_num); + vmxnet3_process_tx_queue(s, tx_queue_idx); + return; + } + + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_IMR, + VMXNET3_MAX_INTRS, VMXNET3_REG_ALIGN)) { + int l = VMW_MULTIREG_IDX_BY_ADDR(addr, VMXNET3_REG_IMR, + VMXNET3_REG_ALIGN); + + VMW_CBPRN("Interrupt mask for line %d written: 0x%" PRIx64, l, val); + + vmxnet3_on_interrupt_mask_changed(s, l, val); + return; + } + + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_RXPROD, + VMXNET3_DEVICE_MAX_RX_QUEUES, VMXNET3_REG_ALIGN) || + VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_RXPROD2, + VMXNET3_DEVICE_MAX_RX_QUEUES, VMXNET3_REG_ALIGN)) { + return; + } + + VMW_WRPRN("BAR0 unknown write [%" PRIx64 "] = %" PRIx64 ", size %d", + (uint64_t) addr, val, size); +} + +static uint64_t +vmxnet3_io_bar0_read(void *opaque, hwaddr addr, unsigned size) +{ + if (VMW_IS_MULTIREG_ADDR(addr, VMXNET3_REG_IMR, + VMXNET3_MAX_INTRS, VMXNET3_REG_ALIGN)) { + assert(false); + } + + VMW_CBPRN("BAR0 unknown read [%" PRIx64 "], size %d", addr, size); + return 0; +} + +static void vmxnet3_reset_interrupt_states(VMXNET3State *s) +{ + int i; + for (i = 0; i < ARRAY_SIZE(s->interrupt_states); i++) { + s->interrupt_states[i].is_asserted = false; + s->interrupt_states[i].is_pending = false; + s->interrupt_states[i].is_masked = true; + } +} + +static void vmxnet3_reset_mac(VMXNET3State *s) +{ + memcpy(&s->conf.macaddr.a, &s->perm_mac.a, sizeof(s->perm_mac.a)); + VMW_CFPRN("MAC address set to: " VMXNET_MF, VMXNET_MA(s->conf.macaddr.a)); +} + +static void vmxnet3_deactivate_device(VMXNET3State *s) +{ + VMW_CBPRN("Deactivating vmxnet3..."); + s->device_active = false; +} + +static void vmxnet3_reset(VMXNET3State *s) +{ + VMW_CBPRN("Resetting vmxnet3..."); + + vmxnet3_deactivate_device(s); + vmxnet3_reset_interrupt_states(s); + vmxnet_tx_pkt_reset(s->tx_pkt); + s->drv_shmem = 0; + s->tx_sop = true; + s->skip_current_tx_pkt = false; +} + +static void vmxnet3_update_rx_mode(VMXNET3State *s) +{ + s->rx_mode = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, + devRead.rxFilterConf.rxMode); + VMW_CFPRN("RX mode: 0x%08X", s->rx_mode); +} + +static void vmxnet3_update_vlan_filters(VMXNET3State *s) +{ + int i; + + /* Copy configuration from shared memory */ + VMXNET3_READ_DRV_SHARED(s->drv_shmem, + devRead.rxFilterConf.vfTable, + s->vlan_table, + sizeof(s->vlan_table)); + + /* Invert byte order when needed */ + for (i = 0; i < ARRAY_SIZE(s->vlan_table); i++) { + s->vlan_table[i] = le32_to_cpu(s->vlan_table[i]); + } + + /* Dump configuration for debugging purposes */ + VMW_CFPRN("Configured VLANs:"); + for (i = 0; i < sizeof(s->vlan_table) * 8; i++) { + if (VMXNET3_VFTABLE_ENTRY_IS_SET(s->vlan_table, i)) { + VMW_CFPRN("\tVLAN %d is present", i); + } + } +} + +static void vmxnet3_update_mcast_filters(VMXNET3State *s) +{ + uint16_t list_bytes = + VMXNET3_READ_DRV_SHARED16(s->drv_shmem, + devRead.rxFilterConf.mfTableLen); + + s->mcast_list_len = list_bytes / sizeof(s->mcast_list[0]); + + s->mcast_list = g_realloc(s->mcast_list, list_bytes); + if (NULL == s->mcast_list) { + if (0 == s->mcast_list_len) { + VMW_CFPRN("Current multicast list is empty"); + } else { + VMW_ERPRN("Failed to allocate multicast list of %d elements", + s->mcast_list_len); + } + s->mcast_list_len = 0; + } else { + int i; + hwaddr mcast_list_pa = + VMXNET3_READ_DRV_SHARED64(s->drv_shmem, + devRead.rxFilterConf.mfTablePA); + + cpu_physical_memory_read(mcast_list_pa, s->mcast_list, list_bytes); + VMW_CFPRN("Current multicast list len is %d:", s->mcast_list_len); + for (i = 0; i < s->mcast_list_len; i++) { + VMW_CFPRN("\t" VMXNET_MF, VMXNET_MA(s->mcast_list[i].a)); + } + } +} + +static void vmxnet3_setup_rx_filtering(VMXNET3State *s) +{ + vmxnet3_update_rx_mode(s); + vmxnet3_update_vlan_filters(s); + vmxnet3_update_mcast_filters(s); +} + +static uint32_t vmxnet3_get_interrupt_config(VMXNET3State *s) +{ + uint32_t interrupt_mode = VMXNET3_IT_AUTO | (VMXNET3_IMM_AUTO << 2); + VMW_CFPRN("Interrupt config is 0x%X", interrupt_mode); + return interrupt_mode; +} + +static void vmxnet3_fill_stats(VMXNET3State *s) +{ + int i; + for (i = 0; i < s->txq_num; i++) { + cpu_physical_memory_write(s->txq_descr[i].tx_stats_pa, + &s->txq_descr[i].txq_stats, + sizeof(s->txq_descr[i].txq_stats)); + } + + for (i = 0; i < s->rxq_num; i++) { + cpu_physical_memory_write(s->rxq_descr[i].rx_stats_pa, + &s->rxq_descr[i].rxq_stats, + sizeof(s->rxq_descr[i].rxq_stats)); + } +} + +static void vmxnet3_adjust_by_guest_type(VMXNET3State *s) +{ + struct Vmxnet3_GOSInfo gos; + + VMXNET3_READ_DRV_SHARED(s->drv_shmem, devRead.misc.driverInfo.gos, + &gos, sizeof(gos)); + s->rx_packets_compound = + (gos.gosType == VMXNET3_GOS_TYPE_WIN) ? false : true; + + VMW_CFPRN("Guest type specifics: RXCOMPOUND: %d", s->rx_packets_compound); +} + +static void +vmxnet3_dump_conf_descr(const char *name, + struct Vmxnet3_VariableLenConfDesc *pm_descr) +{ + VMW_CFPRN("%s descriptor dump: Version %u, Length %u", + name, pm_descr->confVer, pm_descr->confLen); + +}; + +static void vmxnet3_update_pm_state(VMXNET3State *s) +{ + struct Vmxnet3_VariableLenConfDesc pm_descr; + + pm_descr.confLen = + VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.pmConfDesc.confLen); + pm_descr.confVer = + VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.pmConfDesc.confVer); + pm_descr.confPA = + VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.pmConfDesc.confPA); + + vmxnet3_dump_conf_descr("PM State", &pm_descr); +} + +static void vmxnet3_update_features(VMXNET3State *s) +{ + uint32_t guest_features; + int rxcso_supported; + + guest_features = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, + devRead.misc.uptFeatures); + + rxcso_supported = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_RXCSUM); + s->rx_vlan_stripping = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_RXVLAN); + s->lro_supported = VMXNET_FLAG_IS_SET(guest_features, UPT1_F_LRO); + + VMW_CFPRN("Features configuration: LRO: %d, RXCSUM: %d, VLANSTRIP: %d", + s->lro_supported, rxcso_supported, + s->rx_vlan_stripping); + if (s->peer_has_vhdr) { + tap_set_offload(qemu_get_queue(s->nic)->peer, + rxcso_supported, + s->lro_supported, + s->lro_supported, + 0, + 0); + } +} + +static void vmxnet3_activate_device(VMXNET3State *s) +{ + int i; + static const uint32_t VMXNET3_DEF_TX_THRESHOLD = 1; + hwaddr qdescr_table_pa; + uint64_t pa; + uint32_t size; + + /* Verify configuration consistency */ + if (!vmxnet3_verify_driver_magic(s->drv_shmem)) { + VMW_ERPRN("Device configuration received from driver is invalid"); + return; + } + + vmxnet3_adjust_by_guest_type(s); + vmxnet3_update_features(s); + vmxnet3_update_pm_state(s); + vmxnet3_setup_rx_filtering(s); + /* Cache fields from shared memory */ + s->mtu = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, devRead.misc.mtu); + VMW_CFPRN("MTU is %u", s->mtu); + + s->max_rx_frags = + VMXNET3_READ_DRV_SHARED16(s->drv_shmem, devRead.misc.maxNumRxSG); + + VMW_CFPRN("Max RX fragments is %u", s->max_rx_frags); + + s->event_int_idx = + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.intrConf.eventIntrIdx); + VMW_CFPRN("Events interrupt line is %u", s->event_int_idx); + + s->auto_int_masking = + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.intrConf.autoMask); + VMW_CFPRN("Automatic interrupt masking is %d", (int)s->auto_int_masking); + + s->txq_num = + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numTxQueues); + s->rxq_num = + VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numRxQueues); + + VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num); + assert(s->txq_num <= VMXNET3_DEVICE_MAX_TX_QUEUES); + + qdescr_table_pa = + VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.misc.queueDescPA); + VMW_CFPRN("TX queues descriptors table is at 0x%" PRIx64, qdescr_table_pa); + + /* + * Worst-case scenario is a packet that holds all TX rings space so + * we calculate total size of all TX rings for max TX fragments number + */ + s->max_tx_frags = 0; + + /* TX queues */ + for (i = 0; i < s->txq_num; i++) { + hwaddr qdescr_pa = + qdescr_table_pa + i * sizeof(struct Vmxnet3_TxQueueDesc); + + /* Read interrupt number for this TX queue */ + s->txq_descr[i].intr_idx = + VMXNET3_READ_TX_QUEUE_DESCR8(qdescr_pa, conf.intrIdx); + + VMW_CFPRN("TX Queue %d interrupt: %d", i, s->txq_descr[i].intr_idx); + + /* Read rings memory locations for TX queues */ + pa = VMXNET3_READ_TX_QUEUE_DESCR64(qdescr_pa, conf.txRingBasePA); + size = VMXNET3_READ_TX_QUEUE_DESCR32(qdescr_pa, conf.txRingSize); + + vmxnet3_ring_init(&s->txq_descr[i].tx_ring, pa, size, + sizeof(struct Vmxnet3_TxDesc), false); + VMXNET3_RING_DUMP(VMW_CFPRN, "TX", i, &s->txq_descr[i].tx_ring); + + s->max_tx_frags += size; + + /* TXC ring */ + pa = VMXNET3_READ_TX_QUEUE_DESCR64(qdescr_pa, conf.compRingBasePA); + size = VMXNET3_READ_TX_QUEUE_DESCR32(qdescr_pa, conf.compRingSize); + vmxnet3_ring_init(&s->txq_descr[i].comp_ring, pa, size, + sizeof(struct Vmxnet3_TxCompDesc), true); + VMXNET3_RING_DUMP(VMW_CFPRN, "TXC", i, &s->txq_descr[i].comp_ring); + + s->txq_descr[i].tx_stats_pa = + qdescr_pa + offsetof(struct Vmxnet3_TxQueueDesc, stats); + + memset(&s->txq_descr[i].txq_stats, 0, + sizeof(s->txq_descr[i].txq_stats)); + + /* Fill device-managed parameters for queues */ + VMXNET3_WRITE_TX_QUEUE_DESCR32(qdescr_pa, + ctrl.txThreshold, + VMXNET3_DEF_TX_THRESHOLD); + } + + /* Preallocate TX packet wrapper */ + VMW_CFPRN("Max TX fragments is %u", s->max_tx_frags); + vmxnet_tx_pkt_init(&s->tx_pkt, s->max_tx_frags, s->peer_has_vhdr); + vmxnet_rx_pkt_init(&s->rx_pkt, s->peer_has_vhdr); + + /* Read rings memory locations for RX queues */ + for (i = 0; i < s->rxq_num; i++) { + int j; + hwaddr qd_pa = + qdescr_table_pa + s->txq_num * sizeof(struct Vmxnet3_TxQueueDesc) + + i * sizeof(struct Vmxnet3_RxQueueDesc); + + /* Read interrupt number for this RX queue */ + s->rxq_descr[i].intr_idx = + VMXNET3_READ_TX_QUEUE_DESCR8(qd_pa, conf.intrIdx); + + VMW_CFPRN("RX Queue %d interrupt: %d", i, s->rxq_descr[i].intr_idx); + + /* Read rings memory locations */ + for (j = 0; j < VMXNET3_RX_RINGS_PER_QUEUE; j++) { + /* RX rings */ + pa = VMXNET3_READ_RX_QUEUE_DESCR64(qd_pa, conf.rxRingBasePA[j]); + size = VMXNET3_READ_RX_QUEUE_DESCR32(qd_pa, conf.rxRingSize[j]); + vmxnet3_ring_init(&s->rxq_descr[i].rx_ring[j], pa, size, + sizeof(struct Vmxnet3_RxDesc), false); + VMW_CFPRN("RX queue %d:%d: Base: %" PRIx64 ", Size: %d", + i, j, pa, size); + } + + /* RXC ring */ + pa = VMXNET3_READ_RX_QUEUE_DESCR64(qd_pa, conf.compRingBasePA); + size = VMXNET3_READ_RX_QUEUE_DESCR32(qd_pa, conf.compRingSize); + vmxnet3_ring_init(&s->rxq_descr[i].comp_ring, pa, size, + sizeof(struct Vmxnet3_RxCompDesc), true); + VMW_CFPRN("RXC queue %d: Base: %" PRIx64 ", Size: %d", i, pa, size); + + s->rxq_descr[i].rx_stats_pa = + qd_pa + offsetof(struct Vmxnet3_RxQueueDesc, stats); + memset(&s->rxq_descr[i].rxq_stats, 0, + sizeof(s->rxq_descr[i].rxq_stats)); + } + + /* Make sure everything is in place before device activation */ + smp_wmb(); + + vmxnet3_reset_mac(s); + + s->device_active = true; +} + +static void vmxnet3_handle_command(VMXNET3State *s, uint64_t cmd) +{ + s->last_command = cmd; + + switch (cmd) { + case VMXNET3_CMD_GET_PERM_MAC_HI: + VMW_CBPRN("Set: Get upper part of permanent MAC"); + break; + + case VMXNET3_CMD_GET_PERM_MAC_LO: + VMW_CBPRN("Set: Get lower part of permanent MAC"); + break; + + case VMXNET3_CMD_GET_STATS: + VMW_CBPRN("Set: Get device statistics"); + vmxnet3_fill_stats(s); + break; + + case VMXNET3_CMD_ACTIVATE_DEV: + VMW_CBPRN("Set: Activating vmxnet3 device"); + vmxnet3_activate_device(s); + break; + + case VMXNET3_CMD_UPDATE_RX_MODE: + VMW_CBPRN("Set: Update rx mode"); + vmxnet3_update_rx_mode(s); + break; + + case VMXNET3_CMD_UPDATE_VLAN_FILTERS: + VMW_CBPRN("Set: Update VLAN filters"); + vmxnet3_update_vlan_filters(s); + break; + + case VMXNET3_CMD_UPDATE_MAC_FILTERS: + VMW_CBPRN("Set: Update MAC filters"); + vmxnet3_update_mcast_filters(s); + break; + + case VMXNET3_CMD_UPDATE_FEATURE: + VMW_CBPRN("Set: Update features"); + vmxnet3_update_features(s); + break; + + case VMXNET3_CMD_UPDATE_PMCFG: + VMW_CBPRN("Set: Update power management config"); + vmxnet3_update_pm_state(s); + break; + + case VMXNET3_CMD_GET_LINK: + VMW_CBPRN("Set: Get link"); + break; + + case VMXNET3_CMD_RESET_DEV: + VMW_CBPRN("Set: Reset device"); + vmxnet3_reset(s); + break; + + case VMXNET3_CMD_QUIESCE_DEV: + VMW_CBPRN("Set: VMXNET3_CMD_QUIESCE_DEV - pause the device"); + vmxnet3_deactivate_device(s); + break; + + case VMXNET3_CMD_GET_CONF_INTR: + VMW_CBPRN("Set: VMXNET3_CMD_GET_CONF_INTR - interrupt configuration"); + break; + + default: + VMW_CBPRN("Received unknown command: %" PRIx64, cmd); + break; + } +} + +static uint64_t vmxnet3_get_command_status(VMXNET3State *s) +{ + uint64_t ret; + + switch (s->last_command) { + case VMXNET3_CMD_ACTIVATE_DEV: + ret = (s->device_active) ? 0 : -1; + VMW_CFPRN("Device active: %" PRIx64, ret); + break; + + case VMXNET3_CMD_GET_LINK: + ret = s->link_status_and_speed; + VMW_CFPRN("Link and speed: %" PRIx64, ret); + break; + + case VMXNET3_CMD_GET_PERM_MAC_LO: + ret = vmxnet3_get_mac_low(&s->perm_mac); + break; + + case VMXNET3_CMD_GET_PERM_MAC_HI: + ret = vmxnet3_get_mac_high(&s->perm_mac); + break; + + case VMXNET3_CMD_GET_CONF_INTR: + ret = vmxnet3_get_interrupt_config(s); + break; + + default: + VMW_WRPRN("Received request for unknown command: %x", s->last_command); + ret = -1; + break; + } + + return ret; +} + +static void vmxnet3_set_events(VMXNET3State *s, uint32_t val) +{ + uint32_t events; + + VMW_CBPRN("Setting events: 0x%x", val); + events = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, ecr) | val; + VMXNET3_WRITE_DRV_SHARED32(s->drv_shmem, ecr, events); +} + +static void vmxnet3_ack_events(VMXNET3State *s, uint32_t val) +{ + uint32_t events; + + VMW_CBPRN("Clearing events: 0x%x", val); + events = VMXNET3_READ_DRV_SHARED32(s->drv_shmem, ecr) & ~val; + VMXNET3_WRITE_DRV_SHARED32(s->drv_shmem, ecr, events); +} + +static void +vmxnet3_io_bar1_write(void *opaque, + hwaddr addr, + uint64_t val, + unsigned size) +{ + VMXNET3State *s = opaque; + + switch (addr) { + /* Vmxnet3 Revision Report Selection */ + case VMXNET3_REG_VRRS: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_VRRS] = %" PRIx64 ", size %d", + val, size); + break; + + /* UPT Version Report Selection */ + case VMXNET3_REG_UVRS: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_UVRS] = %" PRIx64 ", size %d", + val, size); + break; + + /* Driver Shared Address Low */ + case VMXNET3_REG_DSAL: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_DSAL] = %" PRIx64 ", size %d", + val, size); + /* + * Guest driver will first write the low part of the shared + * memory address. We save it to temp variable and set the + * shared address only after we get the high part + */ + if (0 == val) { + s->device_active = false; + } + s->temp_shared_guest_driver_memory = val; + s->drv_shmem = 0; + break; + + /* Driver Shared Address High */ + case VMXNET3_REG_DSAH: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_DSAH] = %" PRIx64 ", size %d", + val, size); + /* + * Set the shared memory between guest driver and device. + * We already should have low address part. + */ + s->drv_shmem = s->temp_shared_guest_driver_memory | (val << 32); + break; + + /* Command */ + case VMXNET3_REG_CMD: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_CMD] = %" PRIx64 ", size %d", + val, size); + vmxnet3_handle_command(s, val); + break; + + /* MAC Address Low */ + case VMXNET3_REG_MACL: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_MACL] = %" PRIx64 ", size %d", + val, size); + s->temp_mac = val; + break; + + /* MAC Address High */ + case VMXNET3_REG_MACH: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_MACH] = %" PRIx64 ", size %d", + val, size); + vmxnet3_set_variable_mac(s, val, s->temp_mac); + break; + + /* Interrupt Cause Register */ + case VMXNET3_REG_ICR: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_ICR] = %" PRIx64 ", size %d", + val, size); + assert(false); + break; + + /* Event Cause Register */ + case VMXNET3_REG_ECR: + VMW_CBPRN("Write BAR1 [VMXNET3_REG_ECR] = %" PRIx64 ", size %d", + val, size); + vmxnet3_ack_events(s, val); + break; + + default: + VMW_CBPRN("Unknown Write to BAR1 [%" PRIx64 "] = %" PRIx64 ", size %d", + addr, val, size); + break; + } +} + +static uint64_t +vmxnet3_io_bar1_read(void *opaque, hwaddr addr, unsigned size) +{ + VMXNET3State *s = opaque; + uint64_t ret = 0; + + switch (addr) { + /* Vmxnet3 Revision Report Selection */ + case VMXNET3_REG_VRRS: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_VRRS], size %d", size); + ret = VMXNET3_DEVICE_REVISION; + break; + + /* UPT Version Report Selection */ + case VMXNET3_REG_UVRS: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_UVRS], size %d", size); + ret = VMXNET3_DEVICE_VERSION; + break; + + /* Command */ + case VMXNET3_REG_CMD: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_CMD], size %d", size); + ret = vmxnet3_get_command_status(s); + break; + + /* MAC Address Low */ + case VMXNET3_REG_MACL: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_MACL], size %d", size); + ret = vmxnet3_get_mac_low(&s->conf.macaddr); + break; + + /* MAC Address High */ + case VMXNET3_REG_MACH: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_MACH], size %d", size); + ret = vmxnet3_get_mac_high(&s->conf.macaddr); + break; + + /* + * Interrupt Cause Register + * Used for legacy interrupts only so interrupt index always 0 + */ + case VMXNET3_REG_ICR: + VMW_CBPRN("Read BAR1 [VMXNET3_REG_ICR], size %d", size); + if (vmxnet3_interrupt_asserted(s, 0)) { + vmxnet3_clear_interrupt(s, 0); + ret = true; + } else { + ret = false; + } + break; + + default: + VMW_CBPRN("Unknow read BAR1[%" PRIx64 "], %d bytes", addr, size); + break; + } + + return ret; +} + +static int +vmxnet3_can_receive(NetClientState *nc) +{ + VMXNET3State *s = qemu_get_nic_opaque(nc); + return s->device_active && + VMXNET_FLAG_IS_SET(s->link_status_and_speed, VMXNET3_LINK_STATUS_UP); +} + +static inline bool +vmxnet3_is_registered_vlan(VMXNET3State *s, const void *data) +{ + uint16_t vlan_tag = eth_get_pkt_tci(data) & VLAN_VID_MASK; + if (IS_SPECIAL_VLAN_ID(vlan_tag)) { + return true; + } + + return VMXNET3_VFTABLE_ENTRY_IS_SET(s->vlan_table, vlan_tag); +} + +static bool +vmxnet3_is_allowed_mcast_group(VMXNET3State *s, const uint8_t *group_mac) +{ + int i; + for (i = 0; i < s->mcast_list_len; i++) { + if (!memcmp(group_mac, s->mcast_list[i].a, sizeof(s->mcast_list[i]))) { + return true; + } + } + return false; +} + +static bool +vmxnet3_rx_filter_may_indicate(VMXNET3State *s, const void *data, + size_t size) +{ + struct eth_header *ehdr = PKT_GET_ETH_HDR(data); + + if (VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_PROMISC)) { + return true; + } + + if (!vmxnet3_is_registered_vlan(s, data)) { + return false; + } + + switch (vmxnet_rx_pkt_get_packet_type(s->rx_pkt)) { + case ETH_PKT_UCAST: + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_UCAST)) { + return false; + } + if (memcmp(s->conf.macaddr.a, ehdr->h_dest, ETH_ALEN)) { + return false; + } + break; + + case ETH_PKT_BCAST: + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_BCAST)) { + return false; + } + break; + + case ETH_PKT_MCAST: + if (VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_ALL_MULTI)) { + return true; + } + if (!VMXNET_FLAG_IS_SET(s->rx_mode, VMXNET3_RXM_MCAST)) { + return false; + } + if (!vmxnet3_is_allowed_mcast_group(s, ehdr->h_dest)) { + return false; + } + break; + + default: + assert(false); + } + + return true; +} + +static ssize_t +vmxnet3_receive(NetClientState *nc, const uint8_t *buf, size_t size) +{ + VMXNET3State *s = qemu_get_nic_opaque(nc); + size_t bytes_indicated; + + if (!vmxnet3_can_receive(nc)) { + VMW_PKPRN("Cannot receive now"); + return -1; + } + + if (s->peer_has_vhdr) { + vmxnet_rx_pkt_set_vhdr(s->rx_pkt, (struct virtio_net_hdr *)buf); + buf += sizeof(struct virtio_net_hdr); + size -= sizeof(struct virtio_net_hdr); + } + + vmxnet_rx_pkt_set_packet_type(s->rx_pkt, + get_eth_packet_type(PKT_GET_ETH_HDR(buf))); + + if (vmxnet3_rx_filter_may_indicate(s, buf, size)) { + vmxnet_rx_pkt_attach_data(s->rx_pkt, buf, size, s->rx_vlan_stripping); + bytes_indicated = vmxnet3_indicate_packet(s) ? size : -1; + if (bytes_indicated < size) { + VMW_PKPRN("RX: %lu of %lu bytes indicated", bytes_indicated, size); + } + } else { + VMW_PKPRN("Packet dropped by RX filter"); + bytes_indicated = size; + } + + assert(size > 0); + assert(bytes_indicated != 0); + return bytes_indicated; +} + +static void vmxnet3_cleanup(NetClientState *nc) +{ + VMXNET3State *s = qemu_get_nic_opaque(nc); + s->nic = NULL; +} + +static void vmxnet3_set_link_status(NetClientState *nc) +{ + VMXNET3State *s = qemu_get_nic_opaque(nc); + + if (nc->link_down) { + s->link_status_and_speed &= ~VMXNET3_LINK_STATUS_UP; + } else { + s->link_status_and_speed |= VMXNET3_LINK_STATUS_UP; + } + + vmxnet3_set_events(s, VMXNET3_ECR_LINK); + vmxnet3_trigger_interrupt(s, s->event_int_idx); +} + +static NetClientInfo net_vmxnet3_info = { + .type = NET_CLIENT_OPTIONS_KIND_NIC, + .size = sizeof(NICState), + .can_receive = vmxnet3_can_receive, + .receive = vmxnet3_receive, + .cleanup = vmxnet3_cleanup, + .link_status_changed = vmxnet3_set_link_status, +}; + +static bool vmxnet3_peer_has_vnet_hdr(VMXNET3State *s) +{ + NetClientState *peer = qemu_get_queue(s->nic)->peer; + + if ((NULL != peer) && + (peer->info->type == NET_CLIENT_OPTIONS_KIND_TAP) && + tap_has_vnet_hdr(peer)) { + return true; + } + + VMW_WRPRN("Peer has no virtio extension. Task offloads will be emulated."); + return false; +} + +static void vmxnet3_net_uninit(VMXNET3State *s) +{ + g_free(s->mcast_list); + vmxnet_tx_pkt_reset(s->tx_pkt); + vmxnet_tx_pkt_uninit(s->tx_pkt); + vmxnet_rx_pkt_uninit(s->rx_pkt); + qemu_del_net_client(qemu_get_queue(s->nic)); +} + +static void vmxnet3_net_init(VMXNET3State *s) +{ + DeviceState *d = DEVICE(s); + + VMW_CBPRN("vmxnet3_net_init called..."); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + + /* Windows guest will query the address that was set on init */ + memcpy(&s->perm_mac.a, &s->conf.macaddr.a, sizeof(s->perm_mac.a)); + + s->mcast_list = NULL; + s->mcast_list_len = 0; + + s->link_status_and_speed = VMXNET3_LINK_SPEED | VMXNET3_LINK_STATUS_UP; + + VMW_CFPRN("Permanent MAC: " MAC_FMT, MAC_ARG(s->perm_mac.a)); + + s->nic = qemu_new_nic(&net_vmxnet3_info, &s->conf, + object_get_typename(OBJECT(s)), + d->id, s); + + s->peer_has_vhdr = vmxnet3_peer_has_vnet_hdr(s); + s->tx_sop = true; + s->skip_current_tx_pkt = false; + s->tx_pkt = NULL; + s->rx_pkt = NULL; + s->rx_vlan_stripping = false; + s->lro_supported = false; + + if (s->peer_has_vhdr) { + tap_set_vnet_hdr_len(qemu_get_queue(s->nic)->peer, + sizeof(struct virtio_net_hdr)); + + tap_using_vnet_hdr(qemu_get_queue(s->nic)->peer, 1); + } + + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static void +vmxnet3_unuse_msix_vectors(VMXNET3State *s, int num_vectors) +{ + PCIDevice *d = PCI_DEVICE(s); + int i; + for (i = 0; i < num_vectors; i++) { + msix_vector_unuse(d, i); + } +} + +static bool +vmxnet3_use_msix_vectors(VMXNET3State *s, int num_vectors) +{ + PCIDevice *d = PCI_DEVICE(s); + int i; + for (i = 0; i < num_vectors; i++) { + int res = msix_vector_use(d, i); + if (0 > res) { + VMW_WRPRN("Failed to use MSI-X vector %d, error %d", i, res); + vmxnet3_unuse_msix_vectors(s, i); + return false; + } + } + return true; +} + +static bool +vmxnet3_init_msix(VMXNET3State *s) +{ + PCIDevice *d = PCI_DEVICE(s); + int res = msix_init(d, VMXNET3_MAX_INTRS, + &s->msix_bar, + VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_TABLE, + &s->msix_bar, + VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_PBA, + 0); + + if (0 > res) { + VMW_WRPRN("Failed to initialize MSI-X, error %d", res); + s->msix_used = false; + } else { + if (!vmxnet3_use_msix_vectors(s, VMXNET3_MAX_INTRS)) { + VMW_WRPRN("Failed to use MSI-X vectors, error %d", res); + msix_uninit(d, &s->msix_bar, &s->msix_bar); + s->msix_used = false; + } else { + s->msix_used = true; + } + } + return s->msix_used; +} + +static void +vmxnet3_cleanup_msix(VMXNET3State *s) +{ + PCIDevice *d = PCI_DEVICE(s); + + if (s->msix_used) { + msix_vector_unuse(d, VMXNET3_MAX_INTRS); + msix_uninit(d, &s->msix_bar, &s->msix_bar); + } +} + +#define VMXNET3_MSI_NUM_VECTORS (1) +#define VMXNET3_MSI_OFFSET (0x50) +#define VMXNET3_USE_64BIT (true) +#define VMXNET3_PER_VECTOR_MASK (false) + +static bool +vmxnet3_init_msi(VMXNET3State *s) +{ + PCIDevice *d = PCI_DEVICE(s); + int res; + + res = msi_init(d, VMXNET3_MSI_OFFSET, VMXNET3_MSI_NUM_VECTORS, + VMXNET3_USE_64BIT, VMXNET3_PER_VECTOR_MASK); + if (0 > res) { + VMW_WRPRN("Failed to initialize MSI, error %d", res); + s->msi_used = false; + } else { + s->msi_used = true; + } + + return s->msi_used; +} + +static void +vmxnet3_cleanup_msi(VMXNET3State *s) +{ + PCIDevice *d = PCI_DEVICE(s); + + if (s->msi_used) { + msi_uninit(d); + } +} + +static void +vmxnet3_msix_save(QEMUFile *f, void *opaque) +{ + PCIDevice *d = PCI_DEVICE(opaque); + msix_save(d, f); +} + +static int +vmxnet3_msix_load(QEMUFile *f, void *opaque, int version_id) +{ + PCIDevice *d = PCI_DEVICE(opaque); + msix_load(d, f); + return 0; +} + +static const MemoryRegionOps b0_ops = { + .read = vmxnet3_io_bar0_read, + .write = vmxnet3_io_bar0_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static const MemoryRegionOps b1_ops = { + .read = vmxnet3_io_bar1_read, + .write = vmxnet3_io_bar1_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static int vmxnet3_pci_init(PCIDevice *pci_dev) +{ + DeviceState *dev = DEVICE(pci_dev); + VMXNET3State *s = VMXNET3(pci_dev); + + VMW_CBPRN("Starting init..."); + + memory_region_init_io(&s->bar0, &b0_ops, s, + "vmxnet3-b0", VMXNET3_PT_REG_SIZE); + pci_register_bar(pci_dev, VMXNET3_BAR0_IDX, + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar0); + + memory_region_init_io(&s->bar1, &b1_ops, s, + "vmxnet3-b1", VMXNET3_VD_REG_SIZE); + pci_register_bar(pci_dev, VMXNET3_BAR1_IDX, + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar1); + + memory_region_init(&s->msix_bar, "vmxnet3-msix-bar", + VMXNET3_MSIX_BAR_SIZE); + pci_register_bar(pci_dev, VMXNET3_MSIX_BAR_IDX, + PCI_BASE_ADDRESS_SPACE_MEMORY, &s->msix_bar); + + vmxnet3_reset_interrupt_states(s); + + /* Interrupt pin A */ + pci_dev->config[PCI_INTERRUPT_PIN] = 0x01; + + if (!vmxnet3_init_msix(s)) { + VMW_WRPRN("Failed to initialize MSI-X, configuration is inconsistent."); + } + + if (!vmxnet3_init_msi(s)) { + VMW_WRPRN("Failed to initialize MSI, configuration is inconsistent."); + } + + vmxnet3_net_init(s); + + register_savevm(dev, "vmxnet3-msix", -1, 1, + vmxnet3_msix_save, vmxnet3_msix_load, s); + + add_boot_device_path(s->conf.bootindex, dev, "/ethernet-phy@0"); + + return 0; +} + + +static void vmxnet3_pci_uninit(PCIDevice *pci_dev) +{ + DeviceState *dev = DEVICE(pci_dev); + VMXNET3State *s = VMXNET3(pci_dev); + + VMW_CBPRN("Starting uninit..."); + + unregister_savevm(dev, "vmxnet3-msix", s); + + vmxnet3_net_uninit(s); + + vmxnet3_cleanup_msix(s); + + vmxnet3_cleanup_msi(s); + + memory_region_destroy(&s->bar0); + memory_region_destroy(&s->bar1); + memory_region_destroy(&s->msix_bar); +} + +static void vmxnet3_qdev_reset(DeviceState *dev) +{ + PCIDevice *d = PCI_DEVICE(dev); + VMXNET3State *s = VMXNET3(d); + + VMW_CBPRN("Starting QDEV reset..."); + vmxnet3_reset(s); +} + +static bool vmxnet3_mc_list_needed(void *opaque) +{ + return true; +} + +static int vmxnet3_mcast_list_pre_load(void *opaque) +{ + VMXNET3State *s = opaque; + + s->mcast_list = g_malloc(s->mcast_list_buff_size); + + return 0; +} + + +static void vmxnet3_pre_save(void *opaque) +{ + VMXNET3State *s = opaque; + + s->mcast_list_buff_size = s->mcast_list_len * sizeof(MACAddr); +} + +static const VMStateDescription vmxstate_vmxnet3_mcast_list = { + .name = "vmxnet3/mcast_list", + .version_id = 1, + .minimum_version_id = 1, + .minimum_version_id_old = 1, + .pre_load = vmxnet3_mcast_list_pre_load, + .fields = (VMStateField[]) { + VMSTATE_VBUFFER_UINT32(mcast_list, VMXNET3State, 0, NULL, 0, + mcast_list_buff_size), + VMSTATE_END_OF_LIST() + } +}; + +static void vmxnet3_get_ring_from_file(QEMUFile *f, Vmxnet3Ring *r) +{ + r->pa = qemu_get_be64(f); + r->size = qemu_get_be32(f); + r->cell_size = qemu_get_be32(f); + r->next = qemu_get_be32(f); + r->gen = qemu_get_byte(f); +} + +static void vmxnet3_put_ring_to_file(QEMUFile *f, Vmxnet3Ring *r) +{ + qemu_put_be64(f, r->pa); + qemu_put_be32(f, r->size); + qemu_put_be32(f, r->cell_size); + qemu_put_be32(f, r->next); + qemu_put_byte(f, r->gen); +} + +static void vmxnet3_get_tx_stats_from_file(QEMUFile *f, + struct UPT1_TxStats *tx_stat) +{ + tx_stat->TSOPktsTxOK = qemu_get_be64(f); + tx_stat->TSOBytesTxOK = qemu_get_be64(f); + tx_stat->ucastPktsTxOK = qemu_get_be64(f); + tx_stat->ucastBytesTxOK = qemu_get_be64(f); + tx_stat->mcastPktsTxOK = qemu_get_be64(f); + tx_stat->mcastBytesTxOK = qemu_get_be64(f); + tx_stat->bcastPktsTxOK = qemu_get_be64(f); + tx_stat->bcastBytesTxOK = qemu_get_be64(f); + tx_stat->pktsTxError = qemu_get_be64(f); + tx_stat->pktsTxDiscard = qemu_get_be64(f); +} + +static void vmxnet3_put_tx_stats_to_file(QEMUFile *f, + struct UPT1_TxStats *tx_stat) +{ + qemu_put_be64(f, tx_stat->TSOPktsTxOK); + qemu_put_be64(f, tx_stat->TSOBytesTxOK); + qemu_put_be64(f, tx_stat->ucastPktsTxOK); + qemu_put_be64(f, tx_stat->ucastBytesTxOK); + qemu_put_be64(f, tx_stat->mcastPktsTxOK); + qemu_put_be64(f, tx_stat->mcastBytesTxOK); + qemu_put_be64(f, tx_stat->bcastPktsTxOK); + qemu_put_be64(f, tx_stat->bcastBytesTxOK); + qemu_put_be64(f, tx_stat->pktsTxError); + qemu_put_be64(f, tx_stat->pktsTxDiscard); +} + +static int vmxnet3_get_txq_descr(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3TxqDescr *r = pv; + + vmxnet3_get_ring_from_file(f, &r->tx_ring); + vmxnet3_get_ring_from_file(f, &r->comp_ring); + r->intr_idx = qemu_get_byte(f); + r->tx_stats_pa = qemu_get_be64(f); + + vmxnet3_get_tx_stats_from_file(f, &r->txq_stats); + + return 0; +} + +static void vmxnet3_put_txq_descr(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3TxqDescr *r = pv; + + vmxnet3_put_ring_to_file(f, &r->tx_ring); + vmxnet3_put_ring_to_file(f, &r->comp_ring); + qemu_put_byte(f, r->intr_idx); + qemu_put_be64(f, r->tx_stats_pa); + vmxnet3_put_tx_stats_to_file(f, &r->txq_stats); +} + +const VMStateInfo txq_descr_info = { + .name = "txq_descr", + .get = vmxnet3_get_txq_descr, + .put = vmxnet3_put_txq_descr +}; + +static void vmxnet3_get_rx_stats_from_file(QEMUFile *f, + struct UPT1_RxStats *rx_stat) +{ + rx_stat->LROPktsRxOK = qemu_get_be64(f); + rx_stat->LROBytesRxOK = qemu_get_be64(f); + rx_stat->ucastPktsRxOK = qemu_get_be64(f); + rx_stat->ucastBytesRxOK = qemu_get_be64(f); + rx_stat->mcastPktsRxOK = qemu_get_be64(f); + rx_stat->mcastBytesRxOK = qemu_get_be64(f); + rx_stat->bcastPktsRxOK = qemu_get_be64(f); + rx_stat->bcastBytesRxOK = qemu_get_be64(f); + rx_stat->pktsRxOutOfBuf = qemu_get_be64(f); + rx_stat->pktsRxError = qemu_get_be64(f); +} + +static void vmxnet3_put_rx_stats_to_file(QEMUFile *f, + struct UPT1_RxStats *rx_stat) +{ + qemu_put_be64(f, rx_stat->LROPktsRxOK); + qemu_put_be64(f, rx_stat->LROBytesRxOK); + qemu_put_be64(f, rx_stat->ucastPktsRxOK); + qemu_put_be64(f, rx_stat->ucastBytesRxOK); + qemu_put_be64(f, rx_stat->mcastPktsRxOK); + qemu_put_be64(f, rx_stat->mcastBytesRxOK); + qemu_put_be64(f, rx_stat->bcastPktsRxOK); + qemu_put_be64(f, rx_stat->bcastBytesRxOK); + qemu_put_be64(f, rx_stat->pktsRxOutOfBuf); + qemu_put_be64(f, rx_stat->pktsRxError); +} + +static int vmxnet3_get_rxq_descr(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3RxqDescr *r = pv; + int i; + + for (i = 0; i < VMXNET3_RX_RINGS_PER_QUEUE; i++) { + vmxnet3_get_ring_from_file(f, &r->rx_ring[i]); + } + + vmxnet3_get_ring_from_file(f, &r->comp_ring); + r->intr_idx = qemu_get_byte(f); + r->rx_stats_pa = qemu_get_be64(f); + + vmxnet3_get_rx_stats_from_file(f, &r->rxq_stats); + + return 0; +} + +static void vmxnet3_put_rxq_descr(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3RxqDescr *r = pv; + int i; + + for (i = 0; i < VMXNET3_RX_RINGS_PER_QUEUE; i++) { + vmxnet3_put_ring_to_file(f, &r->rx_ring[i]); + } + + vmxnet3_put_ring_to_file(f, &r->comp_ring); + qemu_put_byte(f, r->intr_idx); + qemu_put_be64(f, r->rx_stats_pa); + vmxnet3_put_rx_stats_to_file(f, &r->rxq_stats); +} + +static int vmxnet3_post_load(void *opaque, int version_id) +{ + VMXNET3State *s = opaque; + PCIDevice *d = PCI_DEVICE(s); + + vmxnet_tx_pkt_init(&s->tx_pkt, s->max_tx_frags, s->peer_has_vhdr); + vmxnet_rx_pkt_init(&s->rx_pkt, s->peer_has_vhdr); + + if (s->msix_used) { + if (!vmxnet3_use_msix_vectors(s, VMXNET3_MAX_INTRS)) { + VMW_WRPRN("Failed to re-use MSI-X vectors"); + msix_uninit(d, &s->msix_bar, &s->msix_bar); + s->msix_used = false; + return -1; + } + } + + return 0; +} + +const VMStateInfo rxq_descr_info = { + .name = "rxq_descr", + .get = vmxnet3_get_rxq_descr, + .put = vmxnet3_put_rxq_descr +}; + +static int vmxnet3_get_int_state(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3IntState *r = pv; + + r->is_masked = qemu_get_byte(f); + r->is_pending = qemu_get_byte(f); + r->is_asserted = qemu_get_byte(f); + + return 0; +} + +static void vmxnet3_put_int_state(QEMUFile *f, void *pv, size_t size) +{ + Vmxnet3IntState *r = pv; + + qemu_put_byte(f, r->is_masked); + qemu_put_byte(f, r->is_pending); + qemu_put_byte(f, r->is_asserted); +} + +const VMStateInfo int_state_info = { + .name = "int_state", + .get = vmxnet3_get_int_state, + .put = vmxnet3_put_int_state +}; + +static const VMStateDescription vmstate_vmxnet3 = { + .name = "vmxnet3", + .version_id = 1, + .minimum_version_id = 1, + .minimum_version_id_old = 1, + .pre_save = vmxnet3_pre_save, + .post_load = vmxnet3_post_load, + .fields = (VMStateField[]) { + VMSTATE_PCI_DEVICE(parent_obj, VMXNET3State), + VMSTATE_BOOL(rx_packets_compound, VMXNET3State), + VMSTATE_BOOL(rx_vlan_stripping, VMXNET3State), + VMSTATE_BOOL(lro_supported, VMXNET3State), + VMSTATE_UINT32(rx_mode, VMXNET3State), + VMSTATE_UINT32(mcast_list_len, VMXNET3State), + VMSTATE_UINT32(mcast_list_buff_size, VMXNET3State), + VMSTATE_UINT32_ARRAY(vlan_table, VMXNET3State, VMXNET3_VFT_SIZE), + VMSTATE_UINT32(mtu, VMXNET3State), + VMSTATE_UINT16(max_rx_frags, VMXNET3State), + VMSTATE_UINT32(max_tx_frags, VMXNET3State), + VMSTATE_UINT8(event_int_idx, VMXNET3State), + VMSTATE_BOOL(auto_int_masking, VMXNET3State), + VMSTATE_UINT8(txq_num, VMXNET3State), + VMSTATE_UINT8(rxq_num, VMXNET3State), + VMSTATE_UINT32(device_active, VMXNET3State), + VMSTATE_UINT32(last_command, VMXNET3State), + VMSTATE_UINT32(link_status_and_speed, VMXNET3State), + VMSTATE_UINT32(temp_mac, VMXNET3State), + VMSTATE_UINT64(drv_shmem, VMXNET3State), + VMSTATE_UINT64(temp_shared_guest_driver_memory, VMXNET3State), + + VMSTATE_ARRAY(txq_descr, VMXNET3State, + VMXNET3_DEVICE_MAX_TX_QUEUES, 0, txq_descr_info, + Vmxnet3TxqDescr), + VMSTATE_ARRAY(rxq_descr, VMXNET3State, + VMXNET3_DEVICE_MAX_RX_QUEUES, 0, rxq_descr_info, + Vmxnet3RxqDescr), + VMSTATE_ARRAY(interrupt_states, VMXNET3State, VMXNET3_MAX_INTRS, + 0, int_state_info, Vmxnet3IntState), + + VMSTATE_END_OF_LIST() + }, + .subsections = (VMStateSubsection[]) { + { + .vmsd = &vmxstate_vmxnet3_mcast_list, + .needed = vmxnet3_mc_list_needed + }, + { + /* empty element. */ + } + } +}; + +static void +vmxnet3_write_config(PCIDevice *pci_dev, uint32_t addr, uint32_t val, int len) +{ + pci_default_write_config(pci_dev, addr, val, len); + msix_write_config(pci_dev, addr, val, len); + msi_write_config(pci_dev, addr, val, len); +} + +static Property vmxnet3_properties[] = { + DEFINE_NIC_PROPERTIES(VMXNET3State, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static void vmxnet3_class_init(ObjectClass *class, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(class); + PCIDeviceClass *c = PCI_DEVICE_CLASS(class); + + c->init = vmxnet3_pci_init; + c->exit = vmxnet3_pci_uninit; + c->vendor_id = PCI_VENDOR_ID_VMWARE; + c->device_id = PCI_DEVICE_ID_VMWARE_VMXNET3; + c->revision = PCI_DEVICE_ID_VMWARE_VMXNET3_REVISION; + c->class_id = PCI_CLASS_NETWORK_ETHERNET; + c->subsystem_vendor_id = PCI_VENDOR_ID_VMWARE; + c->subsystem_id = PCI_DEVICE_ID_VMWARE_VMXNET3; + c->config_write = vmxnet3_write_config, + dc->desc = "VMWare Paravirtualized Ethernet v3"; + dc->reset = vmxnet3_qdev_reset; + dc->vmsd = &vmstate_vmxnet3; + dc->props = vmxnet3_properties; +} + +static const TypeInfo vmxnet3_info = { + .name = TYPE_VMXNET3, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(VMXNET3State), + .class_init = vmxnet3_class_init, +}; + +static void vmxnet3_register_types(void) +{ + VMW_CBPRN("vmxnet3_register_types called..."); + type_register_static(&vmxnet3_info); +} + +type_init(vmxnet3_register_types) diff --git a/hw/vmxnet3.h b/hw/vmxnet3.h new file mode 100644 index 0000000000..7db0c8f5e0 --- /dev/null +++ b/hw/vmxnet3.h @@ -0,0 +1,760 @@ +/* + * QEMU VMWARE VMXNET3 paravirtual NIC interface definitions + * + * Copyright (c) 2012 Ravello Systems LTD (http://ravellosystems.com) + * + * Developed by Daynix Computing LTD (http://www.daynix.com) + * + * Authors: + * Dmitry Fleytman + * Tamir Shomer + * Yan Vugenfirer + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef _QEMU_VMXNET3_H +#define _QEMU_VMXNET3_H + +#define VMXNET3_DEVICE_MAX_TX_QUEUES 8 +#define VMXNET3_DEVICE_MAX_RX_QUEUES 8 /* Keep this value as a power of 2 */ + +/* + * VMWARE headers we got from Linux kernel do not fully comply QEMU coding + * standards in sense of types and defines used. + * Since we didn't want to change VMWARE code, following set of typedefs + * and defines needed to compile these headers with QEMU introduced. + */ +#define u64 uint64_t +#define u32 uint32_t +#define u16 uint16_t +#define u8 uint8_t +#define __le16 uint16_t +#define __le32 uint32_t +#define __le64 uint64_t +#define __packed QEMU_PACKED + +#if defined(HOST_WORDS_BIGENDIAN) +#define const_cpu_to_le64(x) bswap_64(x) +#define __BIG_ENDIAN_BITFIELD +#else +#define const_cpu_to_le64(x) (x) +#endif + +/* + * Following is an interface definition for + * VMXNET3 device as provided by VMWARE + * See original copyright from Linux kernel v3.2.8 + * header file drivers/net/vmxnet3/vmxnet3_defs.h below. + */ + +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License and no later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Maintained by: Shreyas Bhatewara + * + */ + +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 = const_cpu_to_le64(0x0001), /* rx csum verification */ + UPT1_F_RSS = const_cpu_to_le64(0x0002), + UPT1_F_RXVLAN = const_cpu_to_le64(0x0004), /* VLAN tag stripping */ + UPT1_F_LRO = const_cpu_to_le64(0x0008), +}; + +/* all registers are 32 bit wide */ +/* BAR 1 */ +enum { + VMXNET3_REG_VRRS = 0x0, /* Vmxnet3 Revision Report Selection */ + VMXNET3_REG_UVRS = 0x8, /* UPT Version Report Selection */ + VMXNET3_REG_DSAL = 0x10, /* Driver Shared Address Low */ + VMXNET3_REG_DSAH = 0x18, /* Driver Shared Address High */ + VMXNET3_REG_CMD = 0x20, /* Command */ + VMXNET3_REG_MACL = 0x28, /* MAC Address Low */ + VMXNET3_REG_MACH = 0x30, /* MAC Address High */ + VMXNET3_REG_ICR = 0x38, /* Interrupt Cause Register */ + VMXNET3_REG_ECR = 0x40 /* Event Cause Register */ +}; + +/* BAR 0 */ +enum { + VMXNET3_REG_IMR = 0x0, /* Interrupt Mask Register */ + VMXNET3_REG_TXPROD = 0x600, /* Tx Producer Index */ + VMXNET3_REG_RXPROD = 0x800, /* Rx Producer Index for ring 1 */ + VMXNET3_REG_RXPROD2 = 0xA00 /* Rx Producer Index for ring 2 */ +}; + +#define VMXNET3_PT_REG_SIZE 4096 /* BAR 0 */ +#define VMXNET3_VD_REG_SIZE 4096 /* BAR 1 */ + +#define VMXNET3_REG_ALIGN 8 /* All registers are 8-byte aligned. */ +#define VMXNET3_REG_ALIGN_MASK 0x7 + +/* I/O Mapped access to registers */ +#define VMXNET3_IO_TYPE_PT 0 +#define VMXNET3_IO_TYPE_VD 1 +#define VMXNET3_IO_ADDR(type, reg) (((type) << 24) | ((reg) & 0xFFFFFF)) +#define VMXNET3_IO_TYPE(addr) ((addr) >> 24) +#define VMXNET3_IO_REG(addr) ((addr) & 0xFFFFFF) + +enum { + VMXNET3_CMD_FIRST_SET = 0xCAFE0000, + VMXNET3_CMD_ACTIVATE_DEV = VMXNET3_CMD_FIRST_SET, /* 0xCAFE0000 */ + VMXNET3_CMD_QUIESCE_DEV, /* 0xCAFE0001 */ + VMXNET3_CMD_RESET_DEV, /* 0xCAFE0002 */ + VMXNET3_CMD_UPDATE_RX_MODE, /* 0xCAFE0003 */ + VMXNET3_CMD_UPDATE_MAC_FILTERS, /* 0xCAFE0004 */ + VMXNET3_CMD_UPDATE_VLAN_FILTERS, /* 0xCAFE0005 */ + VMXNET3_CMD_UPDATE_RSSIDT, /* 0xCAFE0006 */ + VMXNET3_CMD_UPDATE_IML, /* 0xCAFE0007 */ + VMXNET3_CMD_UPDATE_PMCFG, /* 0xCAFE0008 */ + VMXNET3_CMD_UPDATE_FEATURE, /* 0xCAFE0009 */ + VMXNET3_CMD_LOAD_PLUGIN, /* 0xCAFE000A */ + + VMXNET3_CMD_FIRST_GET = 0xF00D0000, + VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET, /* 0xF00D0000 */ + VMXNET3_CMD_GET_STATS, /* 0xF00D0001 */ + VMXNET3_CMD_GET_LINK, /* 0xF00D0002 */ + VMXNET3_CMD_GET_PERM_MAC_LO, /* 0xF00D0003 */ + VMXNET3_CMD_GET_PERM_MAC_HI, /* 0xF00D0004 */ + VMXNET3_CMD_GET_DID_LO, /* 0xF00D0005 */ + VMXNET3_CMD_GET_DID_HI, /* 0xF00D0006 */ + VMXNET3_CMD_GET_DEV_EXTRA_INFO, /* 0xF00D0007 */ + VMXNET3_CMD_GET_CONF_INTR /* 0xF00D0008 */ +}; + +/* + * Little Endian layout of bitfields - + * Byte 0 : 7.....len.....0 + * Byte 1 : rsvd 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 : rsvd 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; + u32 dtype:1; /* descriptor type */ + u32 rsvd:1; + u32 gen:1; /* generation bit */ + u32 len:14; +#else + u32 len:14; + u32 gen:1; /* generation bit */ + u32 rsvd:1; + u32 dtype:1; /* descriptor type */ + u32 ext1:1; + u32 msscof:14; /* MSS, checksum offset, flags */ +#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_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]; +}; + +#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 + +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; + u32 rxdIdx:12; /* Index of the RxDesc */ +#else + u32 rxdIdx:12; /* Index of the RxDesc */ + u32 ext1:2; + u32 eop:1; /* End of Packet */ + u32 sop:1; /* Start of Packet */ + u32 rqID:10; /* rx queue/ring ID */ + u32 rssType:4; /* RSS hash type used */ + u32 cnc:1; /* Checksum Not Calculated */ + u32 ext2:1; +#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 */ +}; + +/* 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 */ +enum { + VMXNET3_RCD_RSS_TYPE_NONE = 0, + VMXNET3_RCD_RSS_TYPE_IPV4 = 1, + VMXNET3_RCD_RSS_TYPE_TCPIPV4 = 2, + VMXNET3_RCD_RSS_TYPE_IPV6 = 3, + VMXNET3_RCD_RSS_TYPE_TCPIPV6 = 4, +}; + + +/* a union for accessing all cmd/completion descriptors */ +union Vmxnet3_GenericDesc { + __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; +}; + +#define VMXNET3_INIT_GEN 1 + +/* Max size of a single tx buffer */ +#define VMXNET3_MAX_TX_BUF_SIZE (1 << 14) + +/* # of tx desc needed for a tx buffer size */ +#define VMXNET3_TXD_NEEDED(size) (((size) + VMXNET3_MAX_TX_BUF_SIZE - 1) / \ + VMXNET3_MAX_TX_BUF_SIZE) + +/* max # of tx descs for a non-tso pkt */ +#define VMXNET3_MAX_TXD_PER_PKT 16 + +/* Max size of a single rx buffer */ +#define VMXNET3_MAX_RX_BUF_SIZE ((1 << 14) - 1) +/* Minimum size of a type 0 buffer */ +#define VMXNET3_MIN_T0_BUF_SIZE 128 +#define VMXNET3_MAX_CSUM_OFFSET 1024 + +/* Ring base address alignment */ +#define VMXNET3_RING_BA_ALIGN 512 +#define VMXNET3_RING_BA_MASK (VMXNET3_RING_BA_ALIGN - 1) + +/* Ring size must be a multiple of 32 */ +#define VMXNET3_RING_SIZE_ALIGN 32 +#define VMXNET3_RING_SIZE_MASK (VMXNET3_RING_SIZE_ALIGN - 1) + +/* Max ring size */ +#define VMXNET3_TX_RING_MAX_SIZE 4096 +#define VMXNET3_TC_RING_MAX_SIZE 4096 +#define VMXNET3_RX_RING_MAX_SIZE 4096 +#define VMXNET3_RC_RING_MAX_SIZE 8192 + +/* a list of reasons for queue stop */ + +enum { + VMXNET3_ERR_NOEOP = 0x80000000, /* cannot find the EOP desc of a pkt */ + VMXNET3_ERR_TXD_REUSE = 0x80000001, /* reuse TxDesc before tx completion */ + VMXNET3_ERR_BIG_PKT = 0x80000002, /* too many TxDesc for a pkt */ + VMXNET3_ERR_DESC_NOT_SPT = 0x80000003, /* descriptor type not supported */ + VMXNET3_ERR_SMALL_BUF = 0x80000004, /* type 0 buffer too small */ + VMXNET3_ERR_STRESS = 0x80000005, /* stress option firing in vmkernel */ + VMXNET3_ERR_SWITCH = 0x80000006, /* mode switch failure */ + VMXNET3_ERR_TXD_INVALID = 0x80000007, /* invalid TxDesc */ +}; + +/* completion descriptor types */ +#define VMXNET3_CDTYPE_TXCOMP 0 /* Tx Completion Descriptor */ +#define VMXNET3_CDTYPE_RXCOMP 3 /* Rx Completion Descriptor */ + +enum { + VMXNET3_GOS_BITS_UNK = 0, /* unknown */ + VMXNET3_GOS_BITS_32 = 1, + VMXNET3_GOS_BITS_64 = 2, +}; + +#define VMXNET3_GOS_TYPE_UNK 0 /* unknown */ +#define VMXNET3_GOS_TYPE_LINUX 1 +#define VMXNET3_GOS_TYPE_WIN 2 +#define VMXNET3_GOS_TYPE_SOLARIS 3 +#define VMXNET3_GOS_TYPE_FREEBSD 4 +#define VMXNET3_GOS_TYPE_PXE 5 + +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 0xbabefee1 + +/* + * QueueDescPA must be 128 bytes aligned. It points to an array of + * Vmxnet3_TxQueueDesc followed by an array of Vmxnet3_RxQueueDesc. + * The number of Vmxnet3_TxQueueDesc/Vmxnet3_RxQueueDesc are specified by + * Vmxnet3_MiscConf.numTxQueues/numRxQueues, respectively. + */ +#define VMXNET3_QUEUE_DESC_ALIGN 128 + + +struct Vmxnet3_MiscConf { + struct Vmxnet3_DriverInfo driverInfo; + __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 _pad[7]; +}; + + +struct Vmxnet3_RxQueueConf { + __le64 rxRingBasePA[2]; + __le64 compRingBasePA; + __le64 ddPA; /* driver data */ + __le64 reserved; + __le32 rxRingSize[2]; /* # of rx desc */ + __le32 compRingSize; /* # of rx comp desc */ + __le32 ddLen; /* size of driver data */ + u8 intrIdx; + u8 _pad[7]; +}; + + +enum vmxnet3_intr_mask_mode { + VMXNET3_IMM_AUTO = 0, + VMXNET3_IMM_ACTIVE = 1, + VMXNET3_IMM_LAZY = 2 +}; + +enum vmxnet3_intr_type { + VMXNET3_IT_AUTO = 0, + VMXNET3_IT_INTX = 1, + VMXNET3_IT_MSI = 2, + VMXNET3_IT_MSIX = 3 +}; + +#define VMXNET3_MAX_TX_QUEUES 8 +#define VMXNET3_MAX_RX_QUEUES 16 +/* addition 1 for events */ +#define VMXNET3_MAX_INTRS 25 + +/* 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]; +}; + +/* one bit per VLAN ID, the size is in the units of u32 */ +#define VMXNET3_VFT_SIZE (4096/(sizeof(uint32_t)*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_DSDevRead { + /* read-only region for device, read by dev in response to a SET cmd */ + struct Vmxnet3_MiscConf misc; + struct Vmxnet3_IntrConf intrConf; + struct Vmxnet3_RxFilterConf rxFilterConf; + struct Vmxnet3_VariableLenConfDesc rssConfDesc; + struct Vmxnet3_VariableLenConfDesc pmConfDesc; + struct Vmxnet3_VariableLenConfDesc pluginConfDesc; +}; + +/* All structures in DriverShared are padded to multiples of 8 bytes */ +struct Vmxnet3_DriverShared { + __le32 magic; + /* make devRead start at 64bit boundaries */ + __le32 pad; + struct Vmxnet3_DSDevRead devRead; + __le32 ecr; + __le32 reserved[5]; +}; + + +#define VMXNET3_ECR_RQERR (1 << 0) +#define VMXNET3_ECR_TQERR (1 << 1) +#define VMXNET3_ECR_LINK (1 << 2) +#define VMXNET3_ECR_DIC (1 << 3) +#define VMXNET3_ECR_DEBUG (1 << 4) + +/* flip the gen bit of a ring */ +#define VMXNET3_FLIP_RING_GEN(gen) ((gen) = (gen) ^ 0x1) + +/* only use this if moving the idx won't affect the gen bit */ +#define VMXNET3_INC_RING_IDX_ONLY(idx, ring_size) \ + do {\ + (idx)++;\ + if (unlikely((idx) == (ring_size))) {\ + (idx) = 0;\ + } \ + } while (0) + +#define VMXNET3_SET_VFTABLE_ENTRY(vfTable, vid) \ + (vfTable[vid >> 5] |= (1 << (vid & 31))) +#define VMXNET3_CLEAR_VFTABLE_ENTRY(vfTable, vid) \ + (vfTable[vid >> 5] &= ~(1 << (vid & 31))) + +#define VMXNET3_VFTABLE_ENTRY_IS_SET(vfTable, vid) \ + ((vfTable[vid >> 5] & (1 << (vid & 31))) != 0) + +#define VMXNET3_MAX_MTU 9000 +#define VMXNET3_MIN_MTU 60 + +#define VMXNET3_LINK_UP (10000 << 16 | 1) /* 10 Gbps, up */ +#define VMXNET3_LINK_DOWN 0 + +#undef u64 +#undef u32 +#undef u16 +#undef u8 +#undef __le16 +#undef __le32 +#undef __le64 +#undef __packed +#undef const_cpu_to_le64 +#if defined(HOST_WORDS_BIGENDIAN) +#undef __BIG_ENDIAN_BITFIELD +#endif + +#endif From d32fcad366e5f45d33dab2ee4de0e5729439680b Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Mon, 18 Mar 2013 11:43:44 -0700 Subject: [PATCH 7/7] net: increase buffer size to accommodate Jumbo frame pkts Socket buffer sizes were hard-coded to 4K for VDE and socket netdevs. Bump this up to 68K (ala tap netdev) to handle maximum GSO packet size (64k) plus plenty of room for the ethernet and virtio_net headers. Originally, ran into this limitation when using -netdev UDP sockets to connect VM-to-VM, where VM interface is configure with MTU=9000. (Using virtio_net NIC model). Test is simple: ping -M do -s 8500 . This test will attempt to ping with unfragmented packet of given size. Without patch, size is limited to < 4K (minus protocol hdrs). With patch, ping test works with pkt size up to 9000 (again, minus protocol hdrs). v2: per Stefan, increase buf size to (4096+65536) as done in tap and apply to vde and socket netdevs. v1: increase buf size to 12K just for -netdev UDP sockets Signed-off-by: Scott Feldman Signed-off-by: Stefan Hajnoczi --- include/net/net.h | 5 +++++ net/net.c | 2 +- net/socket.c | 4 ++-- net/tap.c | 7 +------ net/vde.c | 2 +- 5 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/net/net.h b/include/net/net.h index cb049a16a3..43d85a16eb 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -11,6 +11,11 @@ #define MAX_QUEUE_NUM 1024 +/* Maximum GSO packet size (64k) plus plenty of room for + * the ethernet and virtio_net headers + */ +#define NET_BUFSIZE (4096 + 65536) + struct MACAddr { uint8_t a[6]; }; diff --git a/net/net.c b/net/net.c index f3d67f8322..7869161d8d 100644 --- a/net/net.c +++ b/net/net.c @@ -497,7 +497,7 @@ ssize_t qemu_send_packet_raw(NetClientState *nc, const uint8_t *buf, int size) static ssize_t nc_sendv_compat(NetClientState *nc, const struct iovec *iov, int iovcnt) { - uint8_t buffer[4096]; + uint8_t buffer[NET_BUFSIZE]; size_t offset; offset = iov_to_buf(iov, iovcnt, 0, buffer, sizeof(buffer)); diff --git a/net/socket.c b/net/socket.c index b0c83e022c..6c3752b88a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -40,7 +40,7 @@ typedef struct NetSocketState { unsigned int index; unsigned int packet_len; unsigned int send_index; /* number of bytes sent (only SOCK_STREAM) */ - uint8_t buf[4096]; + uint8_t buf[NET_BUFSIZE]; struct sockaddr_in dgram_dst; /* contains inet host and port destination iff connectionless (SOCK_DGRAM) */ IOHandler *send_fn; /* differs between SOCK_STREAM/SOCK_DGRAM */ bool read_poll; /* waiting to receive data? */ @@ -146,7 +146,7 @@ static void net_socket_send(void *opaque) NetSocketState *s = opaque; int size, err; unsigned l; - uint8_t buf1[4096]; + uint8_t buf1[NET_BUFSIZE]; const uint8_t *buf; size = qemu_recv(s->fd, buf1, sizeof(buf1), 0); diff --git a/net/tap.c b/net/tap.c index ce796997a3..e7c84811ac 100644 --- a/net/tap.c +++ b/net/tap.c @@ -44,17 +44,12 @@ #include "hw/vhost_net.h" -/* Maximum GSO packet size (64k) plus plenty of room for - * the ethernet and virtio_net headers - */ -#define TAP_BUFSIZE (4096 + 65536) - typedef struct TAPState { NetClientState nc; int fd; char down_script[1024]; char down_script_arg[128]; - uint8_t buf[TAP_BUFSIZE]; + uint8_t buf[NET_BUFSIZE]; bool read_poll; bool write_poll; bool using_vnet_hdr; diff --git a/net/vde.c b/net/vde.c index 4dea32d07a..2a619fbc81 100644 --- a/net/vde.c +++ b/net/vde.c @@ -39,7 +39,7 @@ typedef struct VDEState { static void vde_to_qemu(void *opaque) { VDEState *s = opaque; - uint8_t buf[4096]; + uint8_t buf[NET_BUFSIZE]; int size; size = vde_recv(s->vde, (char *)buf, sizeof(buf), 0);