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
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
|
From f21366d964bd41a2b823beed36a7c3e7a728857b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 19 Oct 2019 10:13:24 +0200
Subject: [PATCH 4/7] net: mvneta: add basic XDP support
Add basic XDP support to mvneta driver for devices that rely on software
buffer management. Currently supported verdicts are:
- XDP_DROP
- XDP_PASS
- XDP_REDIRECT
- XDP_ABORTED
- iptables drop:
$iptables -t raw -I PREROUTING -p udp --dport 9 -j DROP
$nstat -n && sleep 1 && nstat
IpInReceives 151169 0.0
IpExtInOctets 6953544 0.0
IpExtInNoECTPkts 151165 0.0
- XDP_DROP via xdp1
$./samples/bpf/xdp1 3
proto 0: 421419 pkt/s
proto 0: 421444 pkt/s
proto 0: 421393 pkt/s
proto 0: 421440 pkt/s
proto 0: 421184 pkt/s
Tested-by: Matteo Croce <mcroce@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/mvneta.c | 148 ++++++++++++++++++++++++--
1 file changed, 139 insertions(+), 9 deletions(-)
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -38,6 +38,7 @@
#include <net/ipv6.h>
#include <net/tso.h>
#include <net/page_pool.h>
+#include <linux/bpf_trace.h>
/* Registers */
#define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2))
@@ -325,8 +326,10 @@
ETH_HLEN + ETH_FCS_LEN, \
cache_line_size())
+#define MVNETA_SKB_HEADROOM (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
+ NET_IP_ALIGN)
#define MVNETA_SKB_PAD (SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \
- NET_SKB_PAD))
+ MVNETA_SKB_HEADROOM))
#define MVNETA_SKB_SIZE(len) (SKB_DATA_ALIGN(len) + MVNETA_SKB_PAD)
#define MVNETA_MAX_RX_BUF_SIZE (PAGE_SIZE - MVNETA_SKB_PAD)
@@ -354,6 +357,11 @@ struct mvneta_statistic {
#define T_REG_64 64
#define T_SW 1
+#define MVNETA_XDP_PASS BIT(0)
+#define MVNETA_XDP_DROPPED BIT(1)
+#define MVNETA_XDP_TX BIT(2)
+#define MVNETA_XDP_REDIR BIT(3)
+
static const struct mvneta_statistic mvneta_statistics[] = {
{ 0x3000, T_REG_64, "good_octets_received", },
{ 0x3010, T_REG_32, "good_frames_received", },
@@ -435,6 +443,8 @@ struct mvneta_port {
u32 cause_rx_tx;
struct napi_struct napi;
+ struct bpf_prog *xdp_prog;
+
/* Core clock */
struct clk *clk;
/* AXI clock */
@@ -1965,10 +1975,50 @@ int mvneta_rx_refill_queue(struct mvneta
}
static int
+mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
+ struct bpf_prog *prog, struct xdp_buff *xdp)
+{
+ u32 ret, act = bpf_prog_run_xdp(prog, xdp);
+
+ switch (act) {
+ case XDP_PASS:
+ ret = MVNETA_XDP_PASS;
+ break;
+ case XDP_REDIRECT: {
+ int err;
+
+ err = xdp_do_redirect(pp->dev, xdp, prog);
+ if (err) {
+ ret = MVNETA_XDP_DROPPED;
+ xdp_return_buff(xdp);
+ } else {
+ ret = MVNETA_XDP_REDIR;
+ }
+ break;
+ }
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(pp->dev, prog, act);
+ /* fall through */
+ case XDP_DROP:
+ page_pool_recycle_direct(rxq->page_pool,
+ virt_to_head_page(xdp->data));
+ ret = MVNETA_XDP_DROPPED;
+ break;
+ }
+
+ return ret;
+}
+
+static int
mvneta_swbm_rx_frame(struct mvneta_port *pp,
struct mvneta_rx_desc *rx_desc,
struct mvneta_rx_queue *rxq,
- struct page *page)
+ struct xdp_buff *xdp,
+ struct bpf_prog *xdp_prog,
+ struct page *page, u32 *xdp_ret)
{
unsigned char *data = page_address(page);
int data_len = -MVNETA_MH_SIZE, len;
@@ -1988,7 +2038,26 @@ mvneta_swbm_rx_frame(struct mvneta_port
rx_desc->buf_phys_addr,
len, dma_dir);
- rxq->skb = build_skb(data, PAGE_SIZE);
+ xdp->data_hard_start = data;
+ xdp->data = data + MVNETA_SKB_HEADROOM + MVNETA_MH_SIZE;
+ xdp->data_end = xdp->data + data_len;
+ xdp_set_data_meta_invalid(xdp);
+
+ if (xdp_prog) {
+ u32 ret;
+
+ ret = mvneta_run_xdp(pp, rxq, xdp_prog, xdp);
+ if (ret != MVNETA_XDP_PASS) {
+ mvneta_update_stats(pp, 1,
+ xdp->data_end - xdp->data,
+ false);
+ rx_desc->buf_phys_addr = 0;
+ *xdp_ret |= ret;
+ return ret;
+ }
+ }
+
+ rxq->skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
if (unlikely(!rxq->skb)) {
netdev_err(dev,
"Can't allocate skb on queue %d\n",
@@ -1999,8 +2068,9 @@ mvneta_swbm_rx_frame(struct mvneta_port
}
page_pool_release_page(rxq->page_pool, page);
- skb_reserve(rxq->skb, MVNETA_MH_SIZE + NET_SKB_PAD);
- skb_put(rxq->skb, data_len);
+ skb_reserve(rxq->skb,
+ xdp->data - xdp->data_hard_start);
+ skb_put(rxq->skb, xdp->data_end - xdp->data);
mvneta_rx_csum(pp, rx_desc->status, rxq->skb);
rxq->left_size = rx_desc->data_size - len;
@@ -2034,7 +2104,7 @@ mvneta_swbm_add_rx_fragment(struct mvnet
/* refill descriptor with new buffer later */
skb_add_rx_frag(rxq->skb,
skb_shinfo(rxq->skb)->nr_frags,
- page, NET_SKB_PAD, data_len,
+ page, MVNETA_SKB_HEADROOM, data_len,
PAGE_SIZE);
}
page_pool_release_page(rxq->page_pool, page);
@@ -2049,11 +2119,18 @@ static int mvneta_rx_swbm(struct napi_st
{
int rcvd_pkts = 0, rcvd_bytes = 0, rx_proc = 0;
struct net_device *dev = pp->dev;
+ struct bpf_prog *xdp_prog;
+ struct xdp_buff xdp_buf;
int rx_todo, refill;
+ u32 xdp_ret = 0;
/* Get number of received packets */
rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
+ rcu_read_lock();
+ xdp_prog = READ_ONCE(pp->xdp_prog);
+ xdp_buf.rxq = &rxq->xdp_rxq;
+
/* Fairness NAPI loop */
while (rx_proc < budget && rx_proc < rx_todo) {
struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
@@ -2081,7 +2158,8 @@ static int mvneta_rx_swbm(struct napi_st
continue;
}
- err = mvneta_swbm_rx_frame(pp, rx_desc, rxq, page);
+ err = mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf,
+ xdp_prog, page, &xdp_ret);
if (err)
continue;
} else {
@@ -2116,6 +2194,10 @@ static int mvneta_rx_swbm(struct napi_st
/* clean uncomplete skb pointer in queue */
rxq->skb = NULL;
}
+ rcu_read_unlock();
+
+ if (xdp_ret & MVNETA_XDP_REDIR)
+ xdp_do_flush_map();
if (rcvd_pkts)
mvneta_update_stats(pp, rcvd_pkts, rcvd_bytes, false);
@@ -2857,13 +2939,14 @@ static int mvneta_poll(struct napi_struc
static int mvneta_create_page_pool(struct mvneta_port *pp,
struct mvneta_rx_queue *rxq, int size)
{
+ struct bpf_prog *xdp_prog = READ_ONCE(pp->xdp_prog);
struct page_pool_params pp_params = {
.order = 0,
.flags = PP_FLAG_DMA_MAP,
.pool_size = size,
.nid = cpu_to_node(0),
.dev = pp->dev->dev.parent,
- .dma_dir = DMA_FROM_DEVICE,
+ .dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
};
int err;
@@ -3364,6 +3447,11 @@ static int mvneta_change_mtu(struct net_
mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8);
}
+ if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) {
+ netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu);
+ return -EINVAL;
+ }
+
dev->mtu = mtu;
if (!netif_running(dev)) {
@@ -4029,6 +4117,47 @@ static int mvneta_ioctl(struct net_devic
return phylink_mii_ioctl(pp->phylink, ifr, cmd);
}
+static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack)
+{
+ bool need_update, running = netif_running(dev);
+ struct mvneta_port *pp = netdev_priv(dev);
+ struct bpf_prog *old_prog;
+
+ if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
+ NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+ return -EOPNOTSUPP;
+ }
+
+ need_update = !!pp->xdp_prog != !!prog;
+ if (running && need_update)
+ mvneta_stop(dev);
+
+ old_prog = xchg(&pp->xdp_prog, prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (running && need_update)
+ return mvneta_open(dev);
+
+ return 0;
+}
+
+static int mvneta_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+ struct mvneta_port *pp = netdev_priv(dev);
+
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return mvneta_xdp_setup(dev, xdp->prog, xdp->extack);
+ case XDP_QUERY_PROG:
+ xdp->prog_id = pp->xdp_prog ? pp->xdp_prog->aux->id : 0;
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
/* Ethtool methods */
/* Set link ksettings (phy address, speed) for ethtools */
@@ -4425,6 +4554,7 @@ static const struct net_device_ops mvnet
.ndo_fix_features = mvneta_fix_features,
.ndo_get_stats64 = mvneta_get_stats64,
.ndo_do_ioctl = mvneta_ioctl,
+ .ndo_bpf = mvneta_xdp,
};
static const struct ethtool_ops mvneta_eth_tool_ops = {
@@ -4713,7 +4843,7 @@ static int mvneta_probe(struct platform_
SET_NETDEV_DEV(dev, &pdev->dev);
pp->id = global_port_id++;
- pp->rx_offset_correction = NET_SKB_PAD;
+ pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
/* Obtain access to BM resources if enabled and already initialized */
bm_node = of_parse_phandle(dn, "buffer-manager", 0);
|