aboutsummaryrefslogtreecommitdiffstats
path: root/target/linux/mvebu/patches-4.4/033-net-mvneta-Associate-RX-queues-with-each-CPU.patch
blob: 636c6cf364336fb3c6f7064a40944dc61f572e20 (plain)
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
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Wed, 9 Dec 2015 18:23:49 +0100
Subject: [PATCH] net: mvneta: Associate RX queues with each CPU

We enable the percpu interrupt for all the CPU and we just associate a
CPU to a few queue at the neta level. The mapping between the CPUs and
the queues is static. The queues are associated to the CPU module the
number of CPUs. However currently we only use on RX queue for a given
Ethernet port.

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---

--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -110,9 +110,16 @@
 #define MVNETA_CPU_MAP(cpu)                      (0x2540 + ((cpu) << 2))
 #define      MVNETA_CPU_RXQ_ACCESS_ALL_MASK      0x000000ff
 #define      MVNETA_CPU_TXQ_ACCESS_ALL_MASK      0x0000ff00
+#define      MVNETA_CPU_RXQ_ACCESS(rxq)		 BIT(rxq)
 #define MVNETA_RXQ_TIME_COAL_REG(q)              (0x2580 + ((q) << 2))
 
-/* Exception Interrupt Port/Queue Cause register */
+/* Exception Interrupt Port/Queue Cause register
+ *
+ * Their behavior depend of the mapping done using the PCPX2Q
+ * registers. For a given CPU if the bit associated to a queue is not
+ * set, then for the register a read from this CPU will always return
+ * 0 and a write won't do anything
+ */
 
 #define MVNETA_INTR_NEW_CAUSE                    0x25a0
 #define MVNETA_INTR_NEW_MASK                     0x25a4
@@ -820,7 +827,13 @@ static void mvneta_port_up(struct mvneta
 	mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
 
 	/* Enable all initialized RXQs. */
-	mvreg_write(pp, MVNETA_RXQ_CMD, BIT(pp->rxq_def));
+	for (queue = 0; queue < rxq_number; queue++) {
+		struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+
+		if (rxq->descs != NULL)
+			q_map |= (1 << queue);
+	}
+	mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
 }
 
 /* Stop the Ethernet port activity */
@@ -1026,6 +1039,7 @@ static void mvneta_defaults_set(struct m
 	int cpu;
 	int queue;
 	u32 val;
+	int max_cpu = num_present_cpus();
 
 	/* Clear all Cause registers */
 	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
@@ -1041,13 +1055,23 @@ static void mvneta_defaults_set(struct m
 	/* Enable MBUS Retry bit16 */
 	mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);
 
-	/* Set CPU queue access map - all CPUs have access to all RX
-	 * queues and to all TX queues
+	/* Set CPU queue access map. CPUs are assigned to the RX
+	 * queues modulo their number and all the TX queues are
+	 * assigned to the CPU associated to the default RX queue.
 	 */
-	for_each_present_cpu(cpu)
-		mvreg_write(pp, MVNETA_CPU_MAP(cpu),
-			    (MVNETA_CPU_RXQ_ACCESS_ALL_MASK |
-			     MVNETA_CPU_TXQ_ACCESS_ALL_MASK));
+	for_each_present_cpu(cpu) {
+		int rxq_map = 0, txq_map = 0;
+		int rxq;
+
+		for (rxq = 0; rxq < rxq_number; rxq++)
+			if ((rxq % max_cpu) == cpu)
+				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+		if (cpu == rxq_def)
+			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+
+		mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
+	}
 
 	/* Reset RX and TX DMAs */
 	mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET);
@@ -2174,6 +2198,7 @@ static int mvneta_poll(struct napi_struc
 {
 	int rx_done = 0;
 	u32 cause_rx_tx;
+	int rx_queue;
 	struct mvneta_port *pp = netdev_priv(napi->dev);
 	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 
@@ -2205,8 +2230,15 @@ static int mvneta_poll(struct napi_struc
 	/* For the case where the last mvneta_poll did not process all
 	 * RX packets
 	 */
+	rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
+
 	cause_rx_tx |= port->cause_rx_tx;
-	rx_done = mvneta_rx(pp, budget, &pp->rxqs[pp->rxq_def]);
+
+	if (rx_queue) {
+		rx_queue = rx_queue - 1;
+		rx_done = mvneta_rx(pp, budget, &pp->rxqs[rx_queue]);
+	}
+
 	budget -= rx_done;
 
 	if (budget > 0) {
@@ -2419,19 +2451,27 @@ static void mvneta_cleanup_txqs(struct m
 /* Cleanup all Rx queues */
 static void mvneta_cleanup_rxqs(struct mvneta_port *pp)
 {
-	mvneta_rxq_deinit(pp, &pp->rxqs[pp->rxq_def]);
+	int queue;
+
+	for (queue = 0; queue < txq_number; queue++)
+		mvneta_rxq_deinit(pp, &pp->rxqs[queue]);
 }
 
 
 /* Init all Rx queues */
 static int mvneta_setup_rxqs(struct mvneta_port *pp)
 {
-	int err = mvneta_rxq_init(pp, &pp->rxqs[pp->rxq_def]);
-	if (err) {
-		netdev_err(pp->dev, "%s: can't create rxq=%d\n",
-			   __func__, pp->rxq_def);
-		mvneta_cleanup_rxqs(pp);
-		return err;
+	int queue;
+
+	for (queue = 0; queue < rxq_number; queue++) {
+		int err = mvneta_rxq_init(pp, &pp->rxqs[queue]);
+
+		if (err) {
+			netdev_err(pp->dev, "%s: can't create rxq=%d\n",
+				   __func__, queue);
+			mvneta_cleanup_rxqs(pp);
+			return err;
+		}
 	}
 
 	return 0;
@@ -2455,6 +2495,19 @@ static int mvneta_setup_txqs(struct mvne
 	return 0;
 }
 
+static void mvneta_percpu_unmask_interrupt(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are unmasked, but actually only the ones
+	 * maped to this CPU will be unmasked
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+		    MVNETA_RX_INTR_MASK_ALL |
+		    MVNETA_TX_INTR_MASK_ALL |
+		    MVNETA_MISCINTR_INTR_MASK);
+}
+
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
 	unsigned int cpu;
@@ -2472,11 +2525,10 @@ static void mvneta_start_dev(struct mvne
 		napi_enable(&port->napi);
 	}
 
-	/* Unmask interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-		    MVNETA_RX_INTR_MASK(rxq_number) |
-		    MVNETA_TX_INTR_MASK(txq_number) |
-		    MVNETA_MISCINTR_INTR_MASK);
+	/* Unmask interrupts. It has to be done from each CPU */
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
+					 pp, true);
 	mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 		    MVNETA_CAUSE_PHY_STATUS_CHANGE |
 		    MVNETA_CAUSE_LINK_CHANGE |
@@ -2752,22 +2804,35 @@ static void mvneta_percpu_disable(void *
 
 static void mvneta_percpu_elect(struct mvneta_port *pp)
 {
-	int online_cpu_idx, cpu, i = 0;
+	int online_cpu_idx, max_cpu, cpu, i = 0;
 
 	online_cpu_idx = pp->rxq_def % num_online_cpus();
+	max_cpu = num_present_cpus();
 
 	for_each_online_cpu(cpu) {
-		if (i == online_cpu_idx)
-			/* Enable per-CPU interrupt on the one CPU we
-			 * just elected
+		int rxq_map = 0, txq_map = 0;
+		int rxq;
+
+		for (rxq = 0; rxq < rxq_number; rxq++)
+			if ((rxq % max_cpu) == cpu)
+				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+		if (i == online_cpu_idx) {
+			/* Map the default receive queue and transmit
+			 * queue to the elected CPU
 			 */
-			smp_call_function_single(cpu, mvneta_percpu_enable,
-						pp, true);
-		else
-			/* Disable per-CPU interrupt on all the other CPU */
-			smp_call_function_single(cpu, mvneta_percpu_disable,
-						pp, true);
+			rxq_map |= MVNETA_CPU_RXQ_ACCESS(pp->rxq_def);
+			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+		}
+		mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
+
+		/* Update the interrupt mask on each CPU according the
+		 * new mapping
+		 */
+		smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
+					 pp, true);
 		i++;
+
 	}
 };
 
@@ -2802,12 +2867,22 @@ static int mvneta_percpu_notifier(struct
 		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
 		napi_enable(&port->napi);
 
+
+		/* Enable per-CPU interrupts on the CPU that is
+		 * brought up.
+		 */
+		smp_call_function_single(cpu, mvneta_percpu_enable,
+					 pp, true);
+
 		/* Enable per-CPU interrupt on the one CPU we care
 		 * about.
 		 */
 		mvneta_percpu_elect(pp);
 
-		/* Unmask all ethernet port interrupts */
+		/* Unmask all ethernet port interrupts, as this
+		 * notifier is called for each CPU then the CPU to
+		 * Queue mapping is applied
+		 */
 		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
 			MVNETA_RX_INTR_MASK(rxq_number) |
 			MVNETA_TX_INTR_MASK(txq_number) |
@@ -2858,7 +2933,7 @@ static int mvneta_percpu_notifier(struct
 static int mvneta_open(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int ret;
+	int ret, cpu;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
 	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
@@ -2888,8 +2963,13 @@ static int mvneta_open(struct net_device
 	 */
 	mvneta_percpu_disable(pp);
 
-	/* Elect a CPU to handle our RX queue interrupt */
-	mvneta_percpu_elect(pp);
+	/* Enable per-CPU interrupt on all the CPU to handle our RX
+	 * queue interrupts
+	 */
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, mvneta_percpu_enable,
+					 pp, true);
+
 
 	/* Register a CPU notifier to handle the case where our CPU
 	 * might be taken offline.