1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019, Intel Corporation. */
#include "ice_txrx_lib.h"
/**
* ice_release_rx_desc - Store the new tail and head values
* @rx_ring: ring to bump
* @val: new head index
*/
void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
{
u16 prev_ntu = rx_ring->next_to_use & ~0x7;
rx_ring->next_to_use = val;
/* update next to alloc since we have filled the ring */
rx_ring->next_to_alloc = val;
/* QRX_TAIL will be updated with any tail value, but hardware ignores
* the lower 3 bits. This makes it so we only bump tail on meaningful
* boundaries. Also, this allows us to bump tail on intervals of 8 up to
* the budget depending on the current traffic load.
*/
val &= ~0x7;
if (prev_ntu != val) {
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
* applicable for weak-ordered memory model archs,
* such as IA-64).
*/
wmb();
writel(val, rx_ring->tail);
}
}
/**
* ice_ptype_to_htype - get a hash type
* @ptype: the ptype value from the descriptor
*
* Returns a hash type to be used by skb_set_hash
*/
static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype)
{
return PKT_HASH_TYPE_NONE;
}
/**
* ice_rx_hash - set the hash value in the skb
* @rx_ring: descriptor ring
* @rx_desc: specific descriptor
* @skb: pointer to current skb
* @rx_ptype: the ptype value from the descriptor
*/
static void
ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
struct sk_buff *skb, u8 rx_ptype)
{
struct ice_32b_rx_flex_desc_nic *nic_mdid;
u32 hash;
if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
return;
if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
return;
nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
hash = le32_to_cpu(nic_mdid->rss_hash);
skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
}
/**
* ice_rx_csum - Indicate in skb if checksum is good
* @ring: the ring we care about
* @skb: skb currently being received and modified
* @rx_desc: the receive descriptor
* @ptype: the packet type decoded by hardware
*
* skb->protocol must be set before this function is called
*/
static void
ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb,
union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
{
struct ice_rx_ptype_decoded decoded;
u32 rx_error, rx_status;
bool ipv4, ipv6;
rx_status = le16_to_cpu(rx_desc->wb.status_error0);
rx_error = rx_status;
decoded = ice_decode_rx_desc_ptype(ptype);
/* Start with CHECKSUM_NONE and by default csum_level = 0 */
skb->ip_summed = CHECKSUM_NONE;
skb_checksum_none_assert(skb);
/* check if Rx checksum is enabled */
if (!(ring->netdev->features & NETIF_F_RXCSUM))
return;
/* check if HW has decoded the packet and checksum */
if (!(rx_status & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
return;
if (!(decoded.known && decoded.outer_ip))
return;
ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
(decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4);
ipv6 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
(decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV6);
if (ipv4 && (rx_error & (BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |
BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S))))
goto checksum_fail;
else if (ipv6 && (rx_status &
(BIT(ICE_RX_FLEX_DESC_STATUS0_IPV6EXADD_S))))
goto checksum_fail;
/* check for L4 errors and handle packets that were not able to be
* checksummed due to arrival speed
*/
if (rx_error & BIT(ICE_RX_FLEX_DESC_STATUS0_XSUM_L4E_S))
goto checksum_fail;
/* Only report checksum unnecessary for TCP, UDP, or SCTP */
switch (decoded.inner_prot) {
case ICE_RX_PTYPE_INNER_PROT_TCP:
case ICE_RX_PTYPE_INNER_PROT_UDP:
case ICE_RX_PTYPE_INNER_PROT_SCTP:
skb->ip_summed = CHECKSUM_UNNECESSARY;
default:
break;
}
return;
checksum_fail:
ring->vsi->back->hw_csum_rx_error++;
}
/**
* ice_process_skb_fields - Populate skb header fields from Rx descriptor
* @rx_ring: Rx descriptor ring packet is being transacted on
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being populated
* @ptype: the packet type decoded by hardware
*
* This function checks the ring, descriptor, and packet information in
* order to populate the hash, checksum, VLAN, protocol, and
* other fields within the skb.
*/
void
ice_process_skb_fields(struct ice_ring *rx_ring,
union ice_32b_rx_flex_desc *rx_desc,
struct sk_buff *skb, u8 ptype)
{
ice_rx_hash(rx_ring, rx_desc, skb, ptype);
/* modifies the skb - consumes the enet header */
skb->protocol = eth_type_trans(skb, rx_ring->netdev);
ice_rx_csum(rx_ring, skb, rx_desc, ptype);
}
/**
* ice_receive_skb - Send a completed packet up the stack
* @rx_ring: Rx ring in play
* @skb: packet to send up
* @vlan_tag: VLAN tag for packet
*
* This function sends the completed packet (via. skb) up the stack using
* gro receive functions (with/without VLAN tag)
*/
void
ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
{
if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
(vlan_tag & VLAN_VID_MASK))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
napi_gro_receive(&rx_ring->q_vector->napi, skb);
}
/**
* ice_xmit_xdp_ring - submit single packet to XDP ring for transmission
* @data: packet data pointer
* @size: packet data size
* @xdp_ring: XDP ring for transmission
*/
int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring)
{
u16 i = xdp_ring->next_to_use;
struct ice_tx_desc *tx_desc;
struct ice_tx_buf *tx_buf;
dma_addr_t dma;
if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) {
xdp_ring->tx_stats.tx_busy++;
return ICE_XDP_CONSUMED;
}
dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
if (dma_mapping_error(xdp_ring->dev, dma))
return ICE_XDP_CONSUMED;
tx_buf = &xdp_ring->tx_buf[i];
tx_buf->bytecount = size;
tx_buf->gso_segs = 1;
tx_buf->raw_buf = data;
/* record length, and DMA address */
dma_unmap_len_set(tx_buf, len, size);
dma_unmap_addr_set(tx_buf, dma, dma);
tx_desc = ICE_TX_DESC(xdp_ring, i);
tx_desc->buf_addr = cpu_to_le64(dma);
tx_desc->cmd_type_offset_bsz = build_ctob(ICE_TXD_LAST_DESC_CMD, 0,
size, 0);
/* Make certain all of the status bits have been updated
* before next_to_watch is written.
*/
smp_wmb();
i++;
if (i == xdp_ring->count)
i = 0;
tx_buf->next_to_watch = tx_desc;
xdp_ring->next_to_use = i;
return ICE_XDP_TX;
}
/**
* ice_xmit_xdp_buff - convert an XDP buffer to an XDP frame and send it
* @xdp: XDP buffer
* @xdp_ring: XDP Tx ring
*
* Returns negative on failure, 0 on success.
*/
int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring)
{
struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return ICE_XDP_CONSUMED;
return ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
}
/**
* ice_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map
* @rx_ring: Rx ring
* @xdp_res: Result of the receive batch
*
* This function bumps XDP Tx tail and/or flush redirect map, and
* should be called when a batch of packets has been processed in the
* napi loop.
*/
void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res)
{
if (xdp_res & ICE_XDP_REDIR)
xdp_do_flush_map();
if (xdp_res & ICE_XDP_TX) {
struct ice_ring *xdp_ring =
rx_ring->vsi->xdp_rings[rx_ring->q_index];
ice_xdp_ring_update_tail(xdp_ring);
}
}
|