summaryrefslogtreecommitdiff
path: root/drivers/net/hyperv/hyperv_net.h
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/hyperv/hyperv_net.h')
-rw-r--r--drivers/net/hyperv/hyperv_net.h291
1 files changed, 217 insertions, 74 deletions
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index ef6f766f6389..7397c693f984 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -1,24 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
*
* Copyright (c) 2011, Microsoft Corporation.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, see <http://www.gnu.org/licenses/>.
- *
* Authors:
* Haiyang Zhang <haiyangz@microsoft.com>
* Hank Janssen <hjanssen@microsoft.com>
* K. Y. Srinivasan <kys@microsoft.com>
- *
*/
#ifndef _HYPERV_NET_H
@@ -27,6 +15,8 @@
#include <linux/list.h>
#include <linux/hyperv.h>
#include <linux/rndis.h>
+#include <linux/jhash.h>
+#include <net/xdp.h>
/* RSS related */
#define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203 /* query only */
@@ -85,6 +75,7 @@ struct ndis_recv_scale_cap { /* NDIS_RECEIVE_SCALE_CAPABILITIES */
#define NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2 40
#define ITAB_NUM 128
+#define ITAB_NUM_MAX 256
struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */
struct ndis_obj_header hdr;
@@ -117,9 +108,43 @@ struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */
u32 processor_masks_entry_size;
};
-/* Fwd declaration */
-struct ndis_tcp_ip_checksum_info;
-struct ndis_pkt_8021q_info;
+struct ndis_tcp_ip_checksum_info {
+ union {
+ struct {
+ u32 is_ipv4:1;
+ u32 is_ipv6:1;
+ u32 tcp_checksum:1;
+ u32 udp_checksum:1;
+ u32 ip_header_checksum:1;
+ u32 reserved:11;
+ u32 tcp_header_offset:10;
+ } transmit;
+ struct {
+ u32 tcp_checksum_failed:1;
+ u32 udp_checksum_failed:1;
+ u32 ip_checksum_failed:1;
+ u32 tcp_checksum_succeeded:1;
+ u32 udp_checksum_succeeded:1;
+ u32 ip_checksum_succeeded:1;
+ u32 loopback:1;
+ u32 tcp_checksum_value_invalid:1;
+ u32 ip_checksum_value_invalid:1;
+ } receive;
+ u32 value;
+ };
+};
+
+struct ndis_pkt_8021q_info {
+ union {
+ struct {
+ u32 pri:3; /* User Priority */
+ u32 cfi:1; /* Canonical Format ID */
+ u32 vlanid:12; /* VLAN ID */
+ u32 reserved:16;
+ };
+ u32 value;
+ };
+};
/*
* Represent netvsc packet which contains 1 RNDIS and 1 ethernet frame
@@ -133,7 +158,6 @@ struct hv_netvsc_packet {
u8 cp_partial; /* partial copy into send buffer */
u8 rmsg_size; /* RNDIS header and PPI size */
- u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */
u8 page_buf_cnt;
u16 q_idx;
@@ -142,8 +166,11 @@ struct hv_netvsc_packet {
u32 total_bytes;
u32 send_buf_index;
u32 total_data_buflen;
+ struct hv_dma_range *dma_range;
};
+#define NETVSC_HASH_KEYLEN 40
+
struct netvsc_device_info {
unsigned char mac_adr[ETH_ALEN];
u32 num_chn;
@@ -151,6 +178,10 @@ struct netvsc_device_info {
u32 recv_sections;
u32 send_section_size;
u32 recv_section_size;
+
+ struct bpf_prog *bprog;
+
+ u8 rss_key[NETVSC_HASH_KEYLEN];
};
enum rndis_device_state {
@@ -160,8 +191,6 @@ enum rndis_device_state {
RNDIS_DEV_DATAINITIALIZED,
};
-#define NETVSC_HASH_KEYLEN 40
-
struct rndis_device {
struct net_device *ndev;
@@ -179,7 +208,6 @@ struct rndis_device {
u8 hw_mac_adr[ETH_ALEN];
u8 rss_key[NETVSC_HASH_KEYLEN];
- u16 rx_table[ITAB_NUM];
};
@@ -200,16 +228,33 @@ int netvsc_send(struct net_device *net,
struct hv_netvsc_packet *packet,
struct rndis_message *rndis_msg,
struct hv_page_buffer *page_buffer,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ bool xdp_tx);
void netvsc_linkstatus_callback(struct net_device *net,
- struct rndis_message *resp);
+ struct rndis_message *resp,
+ void *data, u32 data_buflen);
int netvsc_recv_callback(struct net_device *net,
struct netvsc_device *nvdev,
struct netvsc_channel *nvchan);
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
-int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
+void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev);
+u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan,
+ struct xdp_buff *xdp);
+unsigned int netvsc_xdp_fraglen(unsigned int len);
+struct bpf_prog *netvsc_xdp_get(struct netvsc_device *nvdev);
+int netvsc_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack,
+ struct netvsc_device *nvdev);
+int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog);
+int netvsc_bpf(struct net_device *dev, struct netdev_bpf *bpf);
+int netvsc_ndoxdp_xmit(struct net_device *ndev, int n,
+ struct xdp_frame **frames, u32 flags);
+
+int rndis_set_subchannel(struct net_device *ndev,
+ struct netvsc_device *nvdev,
+ struct netvsc_device_info *dev_info);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
@@ -230,7 +275,7 @@ int rndis_filter_receive(struct net_device *ndev,
int rndis_filter_set_device_mac(struct netvsc_device *ndev,
const char *mac);
-void netvsc_switch_datapath(struct net_device *nv_dev, bool vf);
+int netvsc_switch_datapath(struct net_device *nv_dev, bool vf);
#define NVSP_INVALID_PROTOCOL_VERSION ((u32)0xFFFFFFFF)
@@ -418,7 +463,7 @@ struct nvsp_1_message_send_receive_buffer_complete {
* LargeOffset SmallOffset
*/
- struct nvsp_1_receive_buffer_section sections[1];
+ struct nvsp_1_receive_buffer_section sections[];
} __packed;
/*
@@ -617,7 +662,8 @@ struct nvsp_5_send_indirect_table {
/* The number of entries in the send indirection table */
u32 count;
- /* The offset of the send indirection table from top of this struct.
+ /* The offset of the send indirection table from the beginning of
+ * struct nvsp_message.
* The send indirection table tells which channel to put the send
* traffic on. Each entry is a channel number.
*/
@@ -830,15 +876,54 @@ struct nvsp_message {
#define NETVSC_SUPPORTED_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | \
NETIF_F_TSO | NETIF_F_IPV6_CSUM | \
- NETIF_F_TSO6 | NETIF_F_LRO)
+ NETIF_F_TSO6 | NETIF_F_LRO | \
+ NETIF_F_SG | NETIF_F_RXHASH)
#define VRSS_SEND_TAB_SIZE 16 /* must be power of 2 */
#define VRSS_CHANNEL_MAX 64
-#define VRSS_CHANNEL_DEFAULT 8
+#define VRSS_CHANNEL_DEFAULT 16
#define RNDIS_MAX_PKT_DEFAULT 8
#define RNDIS_PKT_ALIGN_DEFAULT 8
+#define NETVSC_XDP_HDRM 256
+
+#define NETVSC_MIN_OUT_MSG_SIZE (sizeof(struct vmpacket_descriptor) + \
+ sizeof(struct nvsp_message))
+#define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
+
+/* Maximum # of contiguous data ranges that can make up a trasmitted packet.
+ * Typically it's the max SKB fragments plus 2 for the rndis packet and the
+ * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may
+ * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries
+ * in a GPA direct packet sent to netvsp over VMBus.
+ */
+#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT
+#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2)
+#else
+#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT
+#endif
+
+/* Estimated requestor size:
+ * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
+ */
+static inline u32 netvsc_rqstor_size(unsigned long ringbytes)
+{
+ return ringbytes / NETVSC_MIN_OUT_MSG_SIZE +
+ ringbytes / NETVSC_MIN_IN_MSG_SIZE;
+}
+
+/* XFER PAGE packets can specify a maximum of 375 ranges for NDIS >= 6.0
+ * and a maximum of 64 ranges for NDIS < 6.0 with no RSC; with RSC, this
+ * limit is raised to 562 (= NVSP_RSC_MAX).
+ */
+#define NETVSC_MAX_XFER_PAGE_RANGES NVSP_RSC_MAX
+#define NETVSC_XFER_HEADER_SIZE(rng_cnt) \
+ (offsetof(struct vmtransfer_page_packet_header, ranges) + \
+ (rng_cnt) * sizeof(struct vmtransfer_page_range))
+#define NETVSC_MAX_PKT_SIZE (NETVSC_XFER_HEADER_SIZE(NETVSC_MAX_XFER_PAGE_RANGES) + \
+ sizeof(struct nvsp_message) + (sizeof(u32) * VRSS_SEND_TAB_SIZE))
+
struct multi_send_data {
struct sk_buff *skb; /* skb containing the pkt */
struct hv_netvsc_packet *pkt; /* netvsc pkt pending */
@@ -859,8 +944,10 @@ struct multi_recv_comp {
#define NVSP_RSC_MAX 562 /* Max #RSC frags in a vmbus xfer page pkt */
struct nvsc_rsc {
- const struct ndis_pkt_8021q_info *vlan;
- const struct ndis_tcp_ip_checksum_info *csum_info;
+ struct ndis_pkt_8021q_info vlan;
+ struct ndis_tcp_ip_checksum_info csum_info;
+ u32 hash_info;
+ u8 ppi_flags; /* valid/present bits for the above PPIs */
u8 is_last; /* last RNDIS msg in a vmtransfer_page */
u32 cnt; /* #fragments in an RSC packet */
u32 pktlen; /* Full packet length */
@@ -868,11 +955,25 @@ struct nvsc_rsc {
u32 len[NVSP_RSC_MAX];
};
-struct netvsc_stats {
+#define NVSC_RSC_VLAN BIT(0) /* valid/present bit for 'vlan' */
+#define NVSC_RSC_CSUM_INFO BIT(1) /* valid/present bit for 'csum_info' */
+#define NVSC_RSC_HASH_INFO BIT(2) /* valid/present bit for 'hash_info' */
+
+struct netvsc_stats_tx {
+ u64 packets;
+ u64 bytes;
+ u64 xdp_xmit;
+ struct u64_stats_sync syncp;
+};
+
+struct netvsc_stats_rx {
u64 packets;
u64 bytes;
u64 broadcast;
u64 multicast;
+ u64 xdp_drop;
+ u64 xdp_redirect;
+ u64 xdp_tx;
struct u64_stats_sync syncp;
};
@@ -887,6 +988,7 @@ struct netvsc_ethtool_stats {
unsigned long rx_no_memory;
unsigned long stop_queue;
unsigned long wake_queue;
+ unsigned long vlan_error;
};
struct netvsc_ethtool_pcpu_stats {
@@ -945,6 +1047,10 @@ struct net_device_context {
u32 tx_table[VRSS_SEND_TAB_SIZE];
+ u16 *rx_table;
+
+ u32 rx_table_sz;
+
/* Ethtool settings */
u8 duplex;
u32 speed;
@@ -955,17 +1061,77 @@ struct net_device_context {
struct net_device __rcu *vf_netdev;
struct netvsc_vf_pcpu_stats __percpu *vf_stats;
struct delayed_work vf_takeover;
+ struct delayed_work vfns_work;
/* 1: allocated, serial number is valid. 0: not allocated */
u32 vf_alloc;
/* Serial number of the VF to team with */
u32 vf_serial;
+ /* completion variable to confirm vf association */
+ struct completion vf_add;
+ /* Is the current data path through the VF NIC? */
+ bool data_path_is_vf;
+
+ /* Used to temporarily save the config info across hibernation */
+ struct netvsc_device_info *saved_netvsc_dev_info;
};
+void netvsc_vfns_work(struct work_struct *w);
+
+/* Azure hosts don't support non-TCP port numbers in hashing for fragmented
+ * packets. We can use ethtool to change UDP hash level when necessary.
+ */
+static inline u32 netvsc_get_hash(struct sk_buff *skb,
+ const struct net_device_context *ndc)
+{
+ struct flow_keys flow;
+ u32 hash, pkt_proto = 0;
+ static u32 hashrnd __read_mostly;
+
+ net_get_random_once(&hashrnd, sizeof(hashrnd));
+
+ if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
+ return 0;
+
+ switch (flow.basic.ip_proto) {
+ case IPPROTO_TCP:
+ if (flow.basic.n_proto == htons(ETH_P_IP))
+ pkt_proto = HV_TCP4_L4HASH;
+ else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+ pkt_proto = HV_TCP6_L4HASH;
+
+ break;
+
+ case IPPROTO_UDP:
+ if (flow.basic.n_proto == htons(ETH_P_IP))
+ pkt_proto = HV_UDP4_L4HASH;
+ else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+ pkt_proto = HV_UDP6_L4HASH;
+
+ break;
+ }
+
+ if (pkt_proto & ndc->l4_hash) {
+ return skb_get_hash(skb);
+ } else {
+ if (flow.basic.n_proto == htons(ETH_P_IP))
+ hash = jhash2((u32 *)&flow.addrs.v4addrs, 2, hashrnd);
+ else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+ hash = jhash2((u32 *)&flow.addrs.v6addrs, 8, hashrnd);
+ else
+ return 0;
+
+ __skb_set_sw_hash(skb, hash, false);
+ }
+
+ return hash;
+}
+
/* Per channel data */
struct netvsc_channel {
struct vmbus_channel *channel;
struct netvsc_device *net_device;
+ void *recv_buf; /* buffer to copy packets out from the receive buffer */
const struct vmpacket_descriptor *desc;
struct napi_struct napi;
struct multi_send_data msd;
@@ -973,8 +1139,12 @@ struct netvsc_channel {
atomic_t queue_sends;
struct nvsc_rsc rsc;
- struct netvsc_stats tx_stats;
- struct netvsc_stats rx_stats;
+ struct bpf_prog __rcu *bpf_prog;
+ struct xdp_rxq_info xdp_rxq;
+ bool xdp_flush;
+
+ struct netvsc_stats_tx tx_stats;
+ struct netvsc_stats_rx rx_stats;
};
/* Per netvsc device */
@@ -983,18 +1153,20 @@ struct netvsc_device {
wait_queue_head_t wait_drain;
bool destroy;
+ bool tx_disable; /* if true, do not wake up queue again */
/* Receive buffer allocated by us but manages by NetVSP */
void *recv_buf;
u32 recv_buf_size; /* allocated bytes */
- u32 recv_buf_gpadl_handle;
+ struct vmbus_gpadl recv_buf_gpadl_handle;
u32 recv_section_cnt;
u32 recv_section_size;
u32 recv_completion_cnt;
/* Send buffer allocated by us */
void *send_buf;
- u32 send_buf_gpadl_handle;
+ u32 send_buf_size;
+ struct vmbus_gpadl send_buf_gpadl_handle;
u32 send_section_cnt;
u32 send_section_size;
unsigned long *send_section_map;
@@ -1008,6 +1180,8 @@ struct netvsc_device {
u32 max_chn;
u32 num_chn;
+ u32 netvsc_gso_max_size;
+
atomic_t open_chn;
struct work_struct subchan_work;
wait_queue_head_t subchan_open;
@@ -1082,6 +1256,7 @@ struct rndis_set_request {
u32 info_buflen;
u32 info_buf_offset;
u32 dev_vc_handle;
+ u8 info_buf[];
};
/* Response to NdisSetRequest */
@@ -1177,7 +1352,7 @@ enum ndis_per_pkt_info_type {
enum rndis_per_pkt_info_interal_type {
RNDIS_PKTINFO_ID = 1,
- /* Add more memebers here */
+ /* Add more members here */
RNDIS_PKTINFO_MAX
};
@@ -1194,18 +1369,6 @@ struct rndis_pktinfo_id {
u16 pkt_id;
};
-struct ndis_pkt_8021q_info {
- union {
- struct {
- u32 pri:3; /* User Priority */
- u32 cfi:1; /* Canonical Format ID */
- u32 vlanid:12; /* VLAN ID */
- u32 reserved:16;
- };
- u32 value;
- };
-};
-
struct ndis_object_header {
u8 type;
u8 revision;
@@ -1396,32 +1559,6 @@ struct ndis_offload_params {
};
};
-struct ndis_tcp_ip_checksum_info {
- union {
- struct {
- u32 is_ipv4:1;
- u32 is_ipv6:1;
- u32 tcp_checksum:1;
- u32 udp_checksum:1;
- u32 ip_header_checksum:1;
- u32 reserved:11;
- u32 tcp_header_offset:10;
- } transmit;
- struct {
- u32 tcp_checksum_failed:1;
- u32 udp_checksum_failed:1;
- u32 ip_checksum_failed:1;
- u32 tcp_checksum_succeeded:1;
- u32 udp_checksum_succeeded:1;
- u32 ip_checksum_succeeded:1;
- u32 loopback:1;
- u32 tcp_checksum_value_invalid:1;
- u32 ip_checksum_value_invalid:1;
- } receive;
- u32 value;
- };
-};
-
struct ndis_tcp_lso_info {
union {
struct {
@@ -1675,4 +1812,10 @@ struct rndis_message {
#define TRANSPORT_INFO_IPV6_TCP 0x10
#define TRANSPORT_INFO_IPV6_UDP 0x20
+#define RETRY_US_LO 5000
+#define RETRY_US_HI 10000
+#define RETRY_MAX 2000 /* >10 sec */
+
+void netvsc_dma_unmap(struct hv_device *hv_dev,
+ struct hv_netvsc_packet *packet);
#endif /* _HYPERV_NET_H */
generated by cgit (git 2.34.1) at 2025-12-22 09:32:37 +0000