X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Fmlx5_flow_tcf.c;h=fb817b23119ac00f690acc0d150c2d21683eccb3;hb=1ccdc31793aff57d5fe34041c7fa0aa9c00c7f5c;hp=252ddc0432cc8fd8a17369184294053f5106663b;hpb=95a464cecc2155d347d1fc4379432c443a653541;p=dpdk.git diff --git a/drivers/net/mlx5/mlx5_flow_tcf.c b/drivers/net/mlx5/mlx5_flow_tcf.c index 252ddc0432..fb817b2311 100644 --- a/drivers/net/mlx5/mlx5_flow_tcf.c +++ b/drivers/net/mlx5/mlx5_flow_tcf.c @@ -530,7 +530,15 @@ struct flow_tcf_ptoi { /* Due to a limitation on driver/FW. */ #define MLX5_TCF_GROUP_ID_MAX 3 -#define MLX5_TCF_GROUP_PRIORITY_MAX 14 + +/* + * Due to a limitation on driver/FW, priority ranges from 1 to 16 in kernel. + * Priority in rte_flow attribute starts from 0 and is added by 1 in + * translation. This is subject to be changed to determine the max priority + * based on trial-and-error like Verbs driver once the restriction is lifted or + * the range is extended. + */ +#define MLX5_TCF_GROUP_PRIORITY_MAX 15 #define MLX5_TCF_FATE_ACTIONS \ (MLX5_FLOW_ACTION_DROP | MLX5_FLOW_ACTION_PORT_ID | \ @@ -1091,19 +1099,13 @@ flow_tcf_validate_attributes(const struct rte_flow_attr *attr, "group ID larger than " RTE_STR(MLX5_TCF_GROUP_ID_MAX) " isn't supported"); - else if (attr->group > 0 && - attr->priority > MLX5_TCF_GROUP_PRIORITY_MAX) + else if (attr->priority > MLX5_TCF_GROUP_PRIORITY_MAX) return rte_flow_error_set(error, ENOTSUP, RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, attr, - "lowest priority level is " + "priority more than " RTE_STR(MLX5_TCF_GROUP_PRIORITY_MAX) - " when group is configured"); - else if (attr->priority > 0xfffe) - return rte_flow_error_set(error, ENOTSUP, - RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, - attr, - "lowest priority level is 0xfffe"); + " is not supported"); if (!attr->ingress) return rte_flow_error_set(error, EINVAL, RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, @@ -2368,24 +2370,21 @@ flow_tcf_validate(struct rte_eth_dev *dev, } /** - * Calculate maximum size of memory for flow items of Linux TC flower and - * extract specified items. + * Calculate maximum size of memory for flow items of Linux TC flower. * + * @param[in] attr + * Pointer to the flow attributes. * @param[in] items * Pointer to the list of items. - * @param[out] item_flags - * Pointer to the detected items. * * @return * Maximum size of memory for items. */ static int -flow_tcf_get_items_and_size(const struct rte_flow_attr *attr, - const struct rte_flow_item items[], - uint64_t *item_flags) +flow_tcf_get_items_size(const struct rte_flow_attr *attr, + const struct rte_flow_item items[]) { int size = 0; - uint64_t flags = 0; size += SZ_NLATTR_STRZ_OF("flower") + SZ_NLATTR_NEST + /* TCA_OPTIONS. */ @@ -2402,7 +2401,6 @@ flow_tcf_get_items_and_size(const struct rte_flow_attr *attr, size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */ SZ_NLATTR_DATA_OF(ETHER_ADDR_LEN) * 4; /* dst/src MAC addr and mask. */ - flags |= MLX5_FLOW_LAYER_OUTER_L2; break; case RTE_FLOW_ITEM_TYPE_VLAN: size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */ @@ -2410,37 +2408,31 @@ flow_tcf_get_items_and_size(const struct rte_flow_attr *attr, /* VLAN Ether type. */ SZ_NLATTR_TYPE_OF(uint8_t) + /* VLAN prio. */ SZ_NLATTR_TYPE_OF(uint16_t); /* VLAN ID. */ - flags |= MLX5_FLOW_LAYER_OUTER_VLAN; break; case RTE_FLOW_ITEM_TYPE_IPV4: size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */ SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */ SZ_NLATTR_TYPE_OF(uint32_t) * 4; /* dst/src IP addr and mask. */ - flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV4; break; case RTE_FLOW_ITEM_TYPE_IPV6: size += SZ_NLATTR_TYPE_OF(uint16_t) + /* Ether type. */ SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */ SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) * 4; /* dst/src IP addr and mask. */ - flags |= MLX5_FLOW_LAYER_OUTER_L3_IPV6; break; case RTE_FLOW_ITEM_TYPE_UDP: size += SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */ SZ_NLATTR_TYPE_OF(uint16_t) * 4; /* dst/src port and mask. */ - flags |= MLX5_FLOW_LAYER_OUTER_L4_UDP; break; case RTE_FLOW_ITEM_TYPE_TCP: size += SZ_NLATTR_TYPE_OF(uint8_t) + /* IP proto. */ SZ_NLATTR_TYPE_OF(uint16_t) * 4; /* dst/src port and mask. */ - flags |= MLX5_FLOW_LAYER_OUTER_L4_TCP; break; case RTE_FLOW_ITEM_TYPE_VXLAN: size += SZ_NLATTR_TYPE_OF(uint32_t); - flags |= MLX5_FLOW_LAYER_VXLAN; break; default: DRV_LOG(WARNING, @@ -2450,7 +2442,6 @@ flow_tcf_get_items_and_size(const struct rte_flow_attr *attr, break; } } - *item_flags = flags; return size; } @@ -2666,10 +2657,6 @@ flow_tcf_nl_brand(struct nlmsghdr *nlh, uint32_t handle) * Pointer to the list of items. * @param[in] actions * Pointer to the list of actions. - * @param[out] item_flags - * Pointer to bit mask of all items detected. - * @param[out] action_flags - * Pointer to bit mask of all actions detected. * @param[out] error * Pointer to the error structure. * @@ -2681,7 +2668,6 @@ static struct mlx5_flow * flow_tcf_prepare(const struct rte_flow_attr *attr, const struct rte_flow_item items[], const struct rte_flow_action actions[], - uint64_t *item_flags, uint64_t *action_flags, struct rte_flow_error *error) { size_t size = RTE_ALIGN_CEIL @@ -2690,12 +2676,13 @@ flow_tcf_prepare(const struct rte_flow_attr *attr, MNL_ALIGN(sizeof(struct nlmsghdr)) + MNL_ALIGN(sizeof(struct tcmsg)); struct mlx5_flow *dev_flow; + uint64_t action_flags = 0; struct nlmsghdr *nlh; struct tcmsg *tcm; uint8_t *sp, *tun = NULL; - size += flow_tcf_get_items_and_size(attr, items, item_flags); - size += flow_tcf_get_actions_and_size(actions, action_flags); + size += flow_tcf_get_items_size(attr, items); + size += flow_tcf_get_actions_and_size(actions, &action_flags); dev_flow = rte_zmalloc(__func__, size, MNL_ALIGNTO); if (!dev_flow) { rte_flow_error_set(error, ENOMEM, @@ -2704,7 +2691,7 @@ flow_tcf_prepare(const struct rte_flow_attr *attr, return NULL; } sp = (uint8_t *)(dev_flow + 1); - if (*action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) { + if (action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) { sp = RTE_PTR_ALIGN (sp, alignof(struct flow_tcf_tunnel_hdr)); tun = sp; @@ -2716,7 +2703,7 @@ flow_tcf_prepare(const struct rte_flow_attr *attr, (sizeof(struct flow_tcf_vxlan_encap), MNL_ALIGNTO); #endif - } else if (*action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) { + } else if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) { sp = RTE_PTR_ALIGN (sp, alignof(struct flow_tcf_tunnel_hdr)); tun = sp; @@ -2745,9 +2732,9 @@ flow_tcf_prepare(const struct rte_flow_attr *attr, .tcm = tcm, }, }; - if (*action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) + if (action_flags & MLX5_FLOW_ACTION_VXLAN_DECAP) dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_DECAP; - else if (*action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) + else if (action_flags & MLX5_FLOW_ACTION_VXLAN_ENCAP) dev_flow->tcf.tunnel->type = FLOW_TCF_TUNACT_VXLAN_ENCAP; /* * Generate a reasonably unique handle based on the address of the @@ -3803,6 +3790,863 @@ flow_tcf_nl_ack(struct mlx5_flow_tcf_context *tcf, #define MNL_REQUEST_SIZE RTE_MIN(RTE_MAX(sysconf(_SC_PAGESIZE), \ MNL_REQUEST_SIZE_MIN), MNL_REQUEST_SIZE_MAX) +/* Data structures used by flow_tcf_xxx_cb() routines. */ +struct tcf_nlcb_buf { + LIST_ENTRY(tcf_nlcb_buf) next; + uint32_t size; + alignas(struct nlmsghdr) + uint8_t msg[]; /**< Netlink message data. */ +}; + +struct tcf_nlcb_context { + unsigned int ifindex; /**< Base interface index. */ + uint32_t bufsize; + LIST_HEAD(, tcf_nlcb_buf) nlbuf; +}; + +/** + * Allocate space for netlink command in buffer list + * + * @param[in, out] ctx + * Pointer to callback context with command buffers list. + * @param[in] size + * Required size of data buffer to be allocated. + * + * @return + * Pointer to allocated memory, aligned as message header. + * NULL if some error occurred. + */ +static struct nlmsghdr * +flow_tcf_alloc_nlcmd(struct tcf_nlcb_context *ctx, uint32_t size) +{ + struct tcf_nlcb_buf *buf; + struct nlmsghdr *nlh; + + size = NLMSG_ALIGN(size); + buf = LIST_FIRST(&ctx->nlbuf); + if (buf && (buf->size + size) <= ctx->bufsize) { + nlh = (struct nlmsghdr *)&buf->msg[buf->size]; + buf->size += size; + return nlh; + } + if (size > ctx->bufsize) { + DRV_LOG(WARNING, "netlink: too long command buffer requested"); + return NULL; + } + buf = rte_malloc(__func__, + ctx->bufsize + sizeof(struct tcf_nlcb_buf), + alignof(struct tcf_nlcb_buf)); + if (!buf) { + DRV_LOG(WARNING, "netlink: no memory for command buffer"); + return NULL; + } + LIST_INSERT_HEAD(&ctx->nlbuf, buf, next); + buf->size = size; + nlh = (struct nlmsghdr *)&buf->msg[0]; + return nlh; +} + +/** + * Set NLM_F_ACK flags in the last netlink command in buffer. + * Only last command in the buffer will be acked by system. + * + * @param[in, out] buf + * Pointer to buffer with netlink commands. + */ +static void +flow_tcf_setack_nlcmd(struct tcf_nlcb_buf *buf) +{ + struct nlmsghdr *nlh; + uint32_t size = 0; + + assert(buf->size); + do { + nlh = (struct nlmsghdr *)&buf->msg[size]; + size += NLMSG_ALIGN(nlh->nlmsg_len); + if (size >= buf->size) { + nlh->nlmsg_flags |= NLM_F_ACK; + break; + } + } while (true); +} + +/** + * Send the buffers with prepared netlink commands. Scans the list and + * sends all found buffers. Buffers are sent and freed anyway in order + * to prevent memory leakage if some every message in received packet. + * + * @param[in] tcf + * Context object initialized by mlx5_flow_tcf_context_create(). + * @param[in, out] ctx + * Pointer to callback context with command buffers list. + * + * @return + * Zero value on success, negative errno value otherwise + * and rte_errno is set. + */ +static int +flow_tcf_send_nlcmd(struct mlx5_flow_tcf_context *tcf, + struct tcf_nlcb_context *ctx) +{ + struct tcf_nlcb_buf *bc, *bn; + struct nlmsghdr *nlh; + int ret = 0; + + bc = LIST_FIRST(&ctx->nlbuf); + while (bc) { + int rc; + + bn = LIST_NEXT(bc, next); + if (bc->size) { + flow_tcf_setack_nlcmd(bc); + nlh = (struct nlmsghdr *)&bc->msg; + rc = flow_tcf_nl_ack(tcf, nlh, bc->size, NULL, NULL); + if (rc && !ret) + ret = rc; + } + rte_free(bc); + bc = bn; + } + LIST_INIT(&ctx->nlbuf); + return ret; +} + +/** + * Collect local IP address rules with scope link attribute on specified + * network device. This is callback routine called by libmnl mnl_cb_run() + * in loop for every message in received packet. + * + * @param[in] nlh + * Pointer to reply header. + * @param[in, out] arg + * Opaque data pointer for this callback. + * + * @return + * A positive, nonzero value on success, negative errno value otherwise + * and rte_errno is set. + */ +static int +flow_tcf_collect_local_cb(const struct nlmsghdr *nlh, void *arg) +{ + struct tcf_nlcb_context *ctx = arg; + struct nlmsghdr *cmd; + struct ifaddrmsg *ifa; + struct nlattr *na; + struct nlattr *na_local = NULL; + struct nlattr *na_peer = NULL; + unsigned char family; + + if (nlh->nlmsg_type != RTM_NEWADDR) { + rte_errno = EINVAL; + return -rte_errno; + } + ifa = mnl_nlmsg_get_payload(nlh); + family = ifa->ifa_family; + if (ifa->ifa_index != ctx->ifindex || + ifa->ifa_scope != RT_SCOPE_LINK || + !(ifa->ifa_flags & IFA_F_PERMANENT) || + (family != AF_INET && family != AF_INET6)) + return 1; + mnl_attr_for_each(na, nlh, sizeof(*ifa)) { + switch (mnl_attr_get_type(na)) { + case IFA_LOCAL: + na_local = na; + break; + case IFA_ADDRESS: + na_peer = na; + break; + } + if (na_local && na_peer) + break; + } + if (!na_local || !na_peer) + return 1; + /* Local rule found with scope link, permanent and assigned peer. */ + cmd = flow_tcf_alloc_nlcmd(ctx, MNL_ALIGN(sizeof(struct nlmsghdr)) + + MNL_ALIGN(sizeof(struct ifaddrmsg)) + + (family == AF_INET6 + ? 2 * SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) + : 2 * SZ_NLATTR_TYPE_OF(uint32_t))); + if (!cmd) { + rte_errno = ENOMEM; + return -rte_errno; + } + cmd = mnl_nlmsg_put_header(cmd); + cmd->nlmsg_type = RTM_DELADDR; + cmd->nlmsg_flags = NLM_F_REQUEST; + ifa = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifa)); + ifa->ifa_flags = IFA_F_PERMANENT; + ifa->ifa_scope = RT_SCOPE_LINK; + ifa->ifa_index = ctx->ifindex; + if (family == AF_INET) { + ifa->ifa_family = AF_INET; + ifa->ifa_prefixlen = 32; + mnl_attr_put_u32(cmd, IFA_LOCAL, mnl_attr_get_u32(na_local)); + mnl_attr_put_u32(cmd, IFA_ADDRESS, mnl_attr_get_u32(na_peer)); + } else { + ifa->ifa_family = AF_INET6; + ifa->ifa_prefixlen = 128; + mnl_attr_put(cmd, IFA_LOCAL, IPV6_ADDR_LEN, + mnl_attr_get_payload(na_local)); + mnl_attr_put(cmd, IFA_ADDRESS, IPV6_ADDR_LEN, + mnl_attr_get_payload(na_peer)); + } + return 1; +} + +/** + * Cleanup the local IP addresses on outer interface. + * + * @param[in] tcf + * Context object initialized by mlx5_flow_tcf_context_create(). + * @param[in] ifindex + * Network inferface index to perform cleanup. + */ +static void +flow_tcf_encap_local_cleanup(struct mlx5_flow_tcf_context *tcf, + unsigned int ifindex) +{ + struct nlmsghdr *nlh; + struct ifaddrmsg *ifa; + struct tcf_nlcb_context ctx = { + .ifindex = ifindex, + .bufsize = MNL_REQUEST_SIZE, + .nlbuf = LIST_HEAD_INITIALIZER(), + }; + int ret; + + assert(ifindex); + /* + * Seek and destroy leftovers of local IP addresses with + * matching properties "scope link". + */ + nlh = mnl_nlmsg_put_header(tcf->buf); + nlh->nlmsg_type = RTM_GETADDR; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa)); + ifa->ifa_family = AF_UNSPEC; + ifa->ifa_index = ifindex; + ifa->ifa_scope = RT_SCOPE_LINK; + ret = flow_tcf_nl_ack(tcf, nlh, 0, flow_tcf_collect_local_cb, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: query device list error %d", ret); + ret = flow_tcf_send_nlcmd(tcf, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: device delete error %d", ret); +} + +/** + * Collect neigh permament rules on specified network device. + * This is callback routine called by libmnl mnl_cb_run() in loop for + * every message in received packet. + * + * @param[in] nlh + * Pointer to reply header. + * @param[in, out] arg + * Opaque data pointer for this callback. + * + * @return + * A positive, nonzero value on success, negative errno value otherwise + * and rte_errno is set. + */ +static int +flow_tcf_collect_neigh_cb(const struct nlmsghdr *nlh, void *arg) +{ + struct tcf_nlcb_context *ctx = arg; + struct nlmsghdr *cmd; + struct ndmsg *ndm; + struct nlattr *na; + struct nlattr *na_ip = NULL; + struct nlattr *na_mac = NULL; + unsigned char family; + + if (nlh->nlmsg_type != RTM_NEWNEIGH) { + rte_errno = EINVAL; + return -rte_errno; + } + ndm = mnl_nlmsg_get_payload(nlh); + family = ndm->ndm_family; + if (ndm->ndm_ifindex != (int)ctx->ifindex || + !(ndm->ndm_state & NUD_PERMANENT) || + (family != AF_INET && family != AF_INET6)) + return 1; + mnl_attr_for_each(na, nlh, sizeof(*ndm)) { + switch (mnl_attr_get_type(na)) { + case NDA_DST: + na_ip = na; + break; + case NDA_LLADDR: + na_mac = na; + break; + } + if (na_mac && na_ip) + break; + } + if (!na_mac || !na_ip) + return 1; + /* Neigh rule with permenent attribute found. */ + cmd = flow_tcf_alloc_nlcmd(ctx, MNL_ALIGN(sizeof(struct nlmsghdr)) + + MNL_ALIGN(sizeof(struct ndmsg)) + + SZ_NLATTR_DATA_OF(ETHER_ADDR_LEN) + + (family == AF_INET6 + ? SZ_NLATTR_DATA_OF(IPV6_ADDR_LEN) + : SZ_NLATTR_TYPE_OF(uint32_t))); + if (!cmd) { + rte_errno = ENOMEM; + return -rte_errno; + } + cmd = mnl_nlmsg_put_header(cmd); + cmd->nlmsg_type = RTM_DELNEIGH; + cmd->nlmsg_flags = NLM_F_REQUEST; + ndm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ndm)); + ndm->ndm_ifindex = ctx->ifindex; + ndm->ndm_state = NUD_PERMANENT; + ndm->ndm_flags = 0; + ndm->ndm_type = 0; + if (family == AF_INET) { + ndm->ndm_family = AF_INET; + mnl_attr_put_u32(cmd, NDA_DST, mnl_attr_get_u32(na_ip)); + } else { + ndm->ndm_family = AF_INET6; + mnl_attr_put(cmd, NDA_DST, IPV6_ADDR_LEN, + mnl_attr_get_payload(na_ip)); + } + mnl_attr_put(cmd, NDA_LLADDR, ETHER_ADDR_LEN, + mnl_attr_get_payload(na_mac)); + return 1; +} + +/** + * Cleanup the neigh rules on outer interface. + * + * @param[in] tcf + * Context object initialized by mlx5_flow_tcf_context_create(). + * @param[in] ifindex + * Network inferface index to perform cleanup. + */ +static void +flow_tcf_encap_neigh_cleanup(struct mlx5_flow_tcf_context *tcf, + unsigned int ifindex) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + struct tcf_nlcb_context ctx = { + .ifindex = ifindex, + .bufsize = MNL_REQUEST_SIZE, + .nlbuf = LIST_HEAD_INITIALIZER(), + }; + int ret; + + assert(ifindex); + /* Seek and destroy leftovers of neigh rules. */ + nlh = mnl_nlmsg_put_header(tcf->buf); + nlh->nlmsg_type = RTM_GETNEIGH; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm)); + ndm->ndm_family = AF_UNSPEC; + ndm->ndm_ifindex = ifindex; + ndm->ndm_state = NUD_PERMANENT; + ret = flow_tcf_nl_ack(tcf, nlh, 0, flow_tcf_collect_neigh_cb, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: query device list error %d", ret); + ret = flow_tcf_send_nlcmd(tcf, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: device delete error %d", ret); +} + +/** + * Collect indices of VXLAN encap/decap interfaces associated with device. + * This is callback routine called by libmnl mnl_cb_run() in loop for + * every message in received packet. + * + * @param[in] nlh + * Pointer to reply header. + * @param[in, out] arg + * Opaque data pointer for this callback. + * + * @return + * A positive, nonzero value on success, negative errno value otherwise + * and rte_errno is set. + */ +static int +flow_tcf_collect_vxlan_cb(const struct nlmsghdr *nlh, void *arg) +{ + struct tcf_nlcb_context *ctx = arg; + struct nlmsghdr *cmd; + struct ifinfomsg *ifm; + struct nlattr *na; + struct nlattr *na_info = NULL; + struct nlattr *na_vxlan = NULL; + bool found = false; + unsigned int vxindex; + + if (nlh->nlmsg_type != RTM_NEWLINK) { + rte_errno = EINVAL; + return -rte_errno; + } + ifm = mnl_nlmsg_get_payload(nlh); + if (!ifm->ifi_index) { + rte_errno = EINVAL; + return -rte_errno; + } + mnl_attr_for_each(na, nlh, sizeof(*ifm)) + if (mnl_attr_get_type(na) == IFLA_LINKINFO) { + na_info = na; + break; + } + if (!na_info) + return 1; + mnl_attr_for_each_nested(na, na_info) { + switch (mnl_attr_get_type(na)) { + case IFLA_INFO_KIND: + if (!strncmp("vxlan", mnl_attr_get_str(na), + mnl_attr_get_len(na))) + found = true; + break; + case IFLA_INFO_DATA: + na_vxlan = na; + break; + } + if (found && na_vxlan) + break; + } + if (!found || !na_vxlan) + return 1; + found = false; + mnl_attr_for_each_nested(na, na_vxlan) { + if (mnl_attr_get_type(na) == IFLA_VXLAN_LINK && + mnl_attr_get_u32(na) == ctx->ifindex) { + found = true; + break; + } + } + if (!found) + return 1; + /* Attached VXLAN device found, store the command to delete. */ + vxindex = ifm->ifi_index; + cmd = flow_tcf_alloc_nlcmd(ctx, MNL_ALIGN(sizeof(struct nlmsghdr)) + + MNL_ALIGN(sizeof(struct ifinfomsg))); + if (!nlh) { + rte_errno = ENOMEM; + return -rte_errno; + } + cmd = mnl_nlmsg_put_header(cmd); + cmd->nlmsg_type = RTM_DELLINK; + cmd->nlmsg_flags = NLM_F_REQUEST; + ifm = mnl_nlmsg_put_extra_header(cmd, sizeof(*ifm)); + ifm->ifi_family = AF_UNSPEC; + ifm->ifi_index = vxindex; + return 1; +} + +/** + * Cleanup the outer interface. Removes all found vxlan devices + * attached to specified index, flushes the meigh and local IP + * datavase. + * + * @param[in] tcf + * Context object initialized by mlx5_flow_tcf_context_create(). + * @param[in] ifindex + * Network inferface index to perform cleanup. + */ +static void +flow_tcf_encap_iface_cleanup(struct mlx5_flow_tcf_context *tcf, + unsigned int ifindex) +{ + struct nlmsghdr *nlh; + struct ifinfomsg *ifm; + struct tcf_nlcb_context ctx = { + .ifindex = ifindex, + .bufsize = MNL_REQUEST_SIZE, + .nlbuf = LIST_HEAD_INITIALIZER(), + }; + int ret; + + assert(ifindex); + /* + * Seek and destroy leftover VXLAN encap/decap interfaces with + * matching properties. + */ + nlh = mnl_nlmsg_put_header(tcf->buf); + nlh->nlmsg_type = RTM_GETLINK; + nlh->nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP; + ifm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifm)); + ifm->ifi_family = AF_UNSPEC; + ret = flow_tcf_nl_ack(tcf, nlh, 0, flow_tcf_collect_vxlan_cb, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: query device list error %d", ret); + ret = flow_tcf_send_nlcmd(tcf, &ctx); + if (ret) + DRV_LOG(WARNING, "netlink: device delete error %d", ret); +} + +/** + * Emit Netlink message to add/remove local address to the outer device. + * The address being added is visible within the link only (scope link). + * + * Note that an implicit route is maintained by the kernel due to the + * presence of a peer address (IFA_ADDRESS). + * + * These rules are used for encapsultion only and allow to assign + * the outer tunnel source IP address. + * + * @param[in] tcf + * Libmnl socket context object. + * @param[in] encap + * Encapsulation properties (source address and its peer). + * @param[in] ifindex + * Network interface to apply rule. + * @param[in] enable + * Toggle between add and remove. + * @param[out] error + * Perform verbose error reporting if not NULL. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +flow_tcf_rule_local(struct mlx5_flow_tcf_context *tcf, + const struct flow_tcf_vxlan_encap *encap, + unsigned int ifindex, + bool enable, + struct rte_flow_error *error) +{ + struct nlmsghdr *nlh; + struct ifaddrmsg *ifa; + alignas(struct nlmsghdr) + uint8_t buf[mnl_nlmsg_size(sizeof(*ifa) + 128)]; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = enable ? RTM_NEWADDR : RTM_DELADDR; + nlh->nlmsg_flags = + NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0); + nlh->nlmsg_seq = 0; + ifa = mnl_nlmsg_put_extra_header(nlh, sizeof(*ifa)); + ifa->ifa_flags = IFA_F_PERMANENT; + ifa->ifa_scope = RT_SCOPE_LINK; + ifa->ifa_index = ifindex; + if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) { + ifa->ifa_family = AF_INET; + ifa->ifa_prefixlen = 32; + mnl_attr_put_u32(nlh, IFA_LOCAL, encap->ipv4.src); + if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) + mnl_attr_put_u32(nlh, IFA_ADDRESS, + encap->ipv4.dst); + } else { + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC); + ifa->ifa_family = AF_INET6; + ifa->ifa_prefixlen = 128; + mnl_attr_put(nlh, IFA_LOCAL, + sizeof(encap->ipv6.src), + &encap->ipv6.src); + if (encap->mask & FLOW_TCF_ENCAP_IPV6_DST) + mnl_attr_put(nlh, IFA_ADDRESS, + sizeof(encap->ipv6.dst), + &encap->ipv6.dst); + } + if (!flow_tcf_nl_ack(tcf, nlh, 0, NULL, NULL)) + return 0; + return rte_flow_error_set(error, rte_errno, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "netlink: cannot complete IFA request" + " (ip addr add)"); +} + +/** + * Emit Netlink message to add/remove neighbor. + * + * @param[in] tcf + * Libmnl socket context object. + * @param[in] encap + * Encapsulation properties (destination address). + * @param[in] ifindex + * Network interface. + * @param[in] enable + * Toggle between add and remove. + * @param[out] error + * Perform verbose error reporting if not NULL. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +flow_tcf_rule_neigh(struct mlx5_flow_tcf_context *tcf, + const struct flow_tcf_vxlan_encap *encap, + unsigned int ifindex, + bool enable, + struct rte_flow_error *error) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + alignas(struct nlmsghdr) + uint8_t buf[mnl_nlmsg_size(sizeof(*ndm) + 128)]; + + nlh = mnl_nlmsg_put_header(buf); + nlh->nlmsg_type = enable ? RTM_NEWNEIGH : RTM_DELNEIGH; + nlh->nlmsg_flags = + NLM_F_REQUEST | (enable ? NLM_F_CREATE | NLM_F_REPLACE : 0); + nlh->nlmsg_seq = 0; + ndm = mnl_nlmsg_put_extra_header(nlh, sizeof(*ndm)); + ndm->ndm_ifindex = ifindex; + ndm->ndm_state = NUD_PERMANENT; + ndm->ndm_flags = 0; + ndm->ndm_type = 0; + if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) { + ndm->ndm_family = AF_INET; + mnl_attr_put_u32(nlh, NDA_DST, encap->ipv4.dst); + } else { + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST); + ndm->ndm_family = AF_INET6; + mnl_attr_put(nlh, NDA_DST, sizeof(encap->ipv6.dst), + &encap->ipv6.dst); + } + if (encap->mask & FLOW_TCF_ENCAP_ETH_SRC && enable) + DRV_LOG(WARNING, + "outer ethernet source address cannot be " + "forced for VXLAN encapsulation"); + if (encap->mask & FLOW_TCF_ENCAP_ETH_DST) + mnl_attr_put(nlh, NDA_LLADDR, sizeof(encap->eth.dst), + &encap->eth.dst); + if (!flow_tcf_nl_ack(tcf, nlh, 0, NULL, NULL)) + return 0; + return rte_flow_error_set(error, rte_errno, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "netlink: cannot complete ND request" + " (ip neigh)"); +} + +/** + * Manage the local IP addresses and their peers IP addresses on the + * outer interface for encapsulation purposes. The kernel searches the + * appropriate device for tunnel egress traffic using the outer source + * IP, this IP should be assigned to the outer network device, otherwise + * kernel rejects the rule. + * + * Adds or removes the addresses using the Netlink command like this: + * ip addr add peer scope link dev + * + * The addresses are local to the netdev ("scope link"), this reduces + * the risk of conflicts. Note that an implicit route is maintained by + * the kernel due to the presence of a peer address (IFA_ADDRESS). + * + * @param[in] tcf + * Libmnl socket context object. + * @param[in] vtep + * VTEP object, contains rule database and ifouter index. + * @param[in] dev_flow + * Flow object, contains the tunnel parameters (for encap only). + * @param[in] enable + * Toggle between add and remove. + * @param[out] error + * Perform verbose error reporting if not NULL. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +flow_tcf_encap_local(struct mlx5_flow_tcf_context *tcf, + struct tcf_vtep *vtep, + struct mlx5_flow *dev_flow, + bool enable, + struct rte_flow_error *error) +{ + const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap; + struct tcf_local_rule *rule; + bool found = false; + int ret; + + assert(encap); + assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP); + if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) { + assert(encap->mask & FLOW_TCF_ENCAP_IPV4_DST); + LIST_FOREACH(rule, &vtep->local, next) { + if (rule->mask & FLOW_TCF_ENCAP_IPV4_SRC && + encap->ipv4.src == rule->ipv4.src && + encap->ipv4.dst == rule->ipv4.dst) { + found = true; + break; + } + } + } else { + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC); + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST); + LIST_FOREACH(rule, &vtep->local, next) { + if (rule->mask & FLOW_TCF_ENCAP_IPV6_SRC && + !memcmp(&encap->ipv6.src, &rule->ipv6.src, + sizeof(encap->ipv6.src)) && + !memcmp(&encap->ipv6.dst, &rule->ipv6.dst, + sizeof(encap->ipv6.dst))) { + found = true; + break; + } + } + } + if (found) { + if (enable) { + rule->refcnt++; + return 0; + } + if (!rule->refcnt || !--rule->refcnt) { + LIST_REMOVE(rule, next); + return flow_tcf_rule_local(tcf, encap, + vtep->ifouter, false, error); + } + return 0; + } + if (!enable) { + DRV_LOG(WARNING, "disabling not existing local rule"); + rte_flow_error_set(error, ENOENT, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "disabling not existing local rule"); + return -ENOENT; + } + rule = rte_zmalloc(__func__, sizeof(struct tcf_local_rule), + alignof(struct tcf_local_rule)); + if (!rule) { + rte_flow_error_set(error, ENOMEM, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "unable to allocate memory for local rule"); + return -rte_errno; + } + *rule = (struct tcf_local_rule){.refcnt = 0, + .mask = 0, + }; + if (encap->mask & FLOW_TCF_ENCAP_IPV4_SRC) { + rule->mask = FLOW_TCF_ENCAP_IPV4_SRC + | FLOW_TCF_ENCAP_IPV4_DST; + rule->ipv4.src = encap->ipv4.src; + rule->ipv4.dst = encap->ipv4.dst; + } else { + rule->mask = FLOW_TCF_ENCAP_IPV6_SRC + | FLOW_TCF_ENCAP_IPV6_DST; + memcpy(&rule->ipv6.src, &encap->ipv6.src, IPV6_ADDR_LEN); + memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN); + } + ret = flow_tcf_rule_local(tcf, encap, vtep->ifouter, true, error); + if (ret) { + rte_free(rule); + return ret; + } + rule->refcnt++; + LIST_INSERT_HEAD(&vtep->local, rule, next); + return 0; +} + +/** + * Manage the destination MAC/IP addresses neigh database, kernel uses + * this one to determine the destination MAC address within encapsulation + * header. Adds or removes the entries using the Netlink command like this: + * ip neigh add dev lladdr to nud permanent + * + * @param[in] tcf + * Libmnl socket context object. + * @param[in] vtep + * VTEP object, contains rule database and ifouter index. + * @param[in] dev_flow + * Flow object, contains the tunnel parameters (for encap only). + * @param[in] enable + * Toggle between add and remove. + * @param[out] error + * Perform verbose error reporting if not NULL. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +flow_tcf_encap_neigh(struct mlx5_flow_tcf_context *tcf, + struct tcf_vtep *vtep, + struct mlx5_flow *dev_flow, + bool enable, + struct rte_flow_error *error) +{ + const struct flow_tcf_vxlan_encap *encap = dev_flow->tcf.vxlan_encap; + struct tcf_neigh_rule *rule; + bool found = false; + int ret; + + assert(encap); + assert(encap->hdr.type == FLOW_TCF_TUNACT_VXLAN_ENCAP); + if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) { + assert(encap->mask & FLOW_TCF_ENCAP_IPV4_SRC); + LIST_FOREACH(rule, &vtep->neigh, next) { + if (rule->mask & FLOW_TCF_ENCAP_IPV4_DST && + encap->ipv4.dst == rule->ipv4.dst) { + found = true; + break; + } + } + } else { + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_SRC); + assert(encap->mask & FLOW_TCF_ENCAP_IPV6_DST); + LIST_FOREACH(rule, &vtep->neigh, next) { + if (rule->mask & FLOW_TCF_ENCAP_IPV6_DST && + !memcmp(&encap->ipv6.dst, &rule->ipv6.dst, + sizeof(encap->ipv6.dst))) { + found = true; + break; + } + } + } + if (found) { + if (memcmp(&encap->eth.dst, &rule->eth, + sizeof(encap->eth.dst))) { + DRV_LOG(WARNING, "Destination MAC differs" + " in neigh rule"); + rte_flow_error_set(error, EEXIST, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, + NULL, "Different MAC address" + " neigh rule for the same" + " destination IP"); + return -EEXIST; + } + if (enable) { + rule->refcnt++; + return 0; + } + if (!rule->refcnt || !--rule->refcnt) { + LIST_REMOVE(rule, next); + return flow_tcf_rule_neigh(tcf, encap, + vtep->ifouter, + false, error); + } + return 0; + } + if (!enable) { + DRV_LOG(WARNING, "Disabling not existing neigh rule"); + rte_flow_error_set(error, ENOENT, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "unable to allocate memory for neigh rule"); + return -ENOENT; + } + rule = rte_zmalloc(__func__, sizeof(struct tcf_neigh_rule), + alignof(struct tcf_neigh_rule)); + if (!rule) { + rte_flow_error_set(error, ENOMEM, + RTE_FLOW_ERROR_TYPE_UNSPECIFIED, NULL, + "unable to allocate memory for neigh rule"); + return -rte_errno; + } + *rule = (struct tcf_neigh_rule){.refcnt = 0, + .mask = 0, + }; + if (encap->mask & FLOW_TCF_ENCAP_IPV4_DST) { + rule->mask = FLOW_TCF_ENCAP_IPV4_DST; + rule->ipv4.dst = encap->ipv4.dst; + } else { + rule->mask = FLOW_TCF_ENCAP_IPV6_DST; + memcpy(&rule->ipv6.dst, &encap->ipv6.dst, IPV6_ADDR_LEN); + } + memcpy(&rule->eth, &encap->eth.dst, sizeof(rule->eth)); + ret = flow_tcf_rule_neigh(tcf, encap, vtep->ifouter, true, error); + if (ret) { + rte_free(rule); + return ret; + } + rule->refcnt++; + LIST_INSERT_HEAD(&vtep->neigh, rule, next); + return 0; +} + /* VTEP device list is shared between PMD port instances. */ static LIST_HEAD(, tcf_vtep) vtep_list_vxlan = LIST_HEAD_INITIALIZER(); static pthread_mutex_t vtep_list_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -4079,6 +4923,7 @@ flow_tcf_encap_vtep_acquire(struct mlx5_flow_tcf_context *tcf, { static uint16_t encap_port = MLX5_VXLAN_PORT_MIN - 1; struct tcf_vtep *vtep; + int ret; assert(ifouter); /* Look whether the attached VTEP for encap is created. */ @@ -4093,6 +4938,9 @@ flow_tcf_encap_vtep_acquire(struct mlx5_flow_tcf_context *tcf, uint16_t pcnt; /* Not found, we should create the new attached VTEP. */ + flow_tcf_encap_iface_cleanup(tcf, ifouter); + flow_tcf_encap_local_cleanup(tcf, ifouter); + flow_tcf_encap_neigh_cleanup(tcf, ifouter); for (pcnt = 0; pcnt <= (MLX5_VXLAN_PORT_MAX - MLX5_VXLAN_PORT_MIN); pcnt++) { encap_port++; @@ -4124,6 +4972,20 @@ flow_tcf_encap_vtep_acquire(struct mlx5_flow_tcf_context *tcf, } assert(vtep->ifouter == ifouter); assert(vtep->ifindex); + /* Create local ipaddr with peer to specify the outer IPs. */ + ret = flow_tcf_encap_local(tcf, vtep, dev_flow, true, error); + if (!ret) { + /* Create neigh rule to specify outer destination MAC. */ + ret = flow_tcf_encap_neigh(tcf, vtep, dev_flow, true, error); + if (ret) + flow_tcf_encap_local(tcf, vtep, + dev_flow, false, error); + } + if (ret) { + if (--vtep->refcnt == 0) + flow_tcf_vtep_delete(tcf, vtep); + return NULL; + } return vtep; } @@ -4193,6 +5055,9 @@ flow_tcf_vtep_release(struct mlx5_flow_tcf_context *tcf, case FLOW_TCF_TUNACT_VXLAN_DECAP: break; case FLOW_TCF_TUNACT_VXLAN_ENCAP: + /* Remove the encap ancillary rules first. */ + flow_tcf_encap_neigh(tcf, vtep, dev_flow, false, NULL); + flow_tcf_encap_local(tcf, vtep, dev_flow, false, NULL); break; default: assert(false);