vxge-main.c 128.2 KB
Newer Older
1 2 3 4 5 6 7 8 9
/******************************************************************************
* This software may be used and distributed according to the terms of
* the GNU General Public License (GPL), incorporated herein by reference.
* Drivers based on or derived from this code fall under the GPL and must
* retain the authorship, copyright and license notice.  This file is not
* a complete program and may only be used when the entire operating
* system is licensed under the GPL.
* See the file COPYING in this distribution for more information.
*
J
Jon Mason 已提交
10
* vxge-main.c: Driver for Exar Corp's X3100 Series 10GbE PCIe I/O
11
*              Virtualized Server Adapter.
J
Jon Mason 已提交
12
* Copyright(c) 2002-2010 Exar Corp.
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
*
* The module loadable parameters that are supported by the driver and a brief
* explanation of all the variables:
* vlan_tag_strip:
*	Strip VLAN Tag enable/disable. Instructs the device to remove
*	the VLAN tag from all received tagged frames that are not
*	replicated at the internal L2 switch.
*		0 - Do not strip the VLAN tag.
*		1 - Strip the VLAN tag.
*
* addr_learn_en:
*	Enable learning the mac address of the guest OS interface in
*	a virtualization environment.
*		0 - DISABLE
*		1 - ENABLE
*
* max_config_port:
*	Maximum number of port to be supported.
*		MIN -1 and MAX - 2
*
* max_config_vpath:
*	This configures the maximum no of VPATH configures for each
* 	device function.
*		MIN - 1 and MAX - 17
*
* max_config_dev:
*	This configures maximum no of Device function to be enabled.
*		MIN - 1 and MAX - 17
*
******************************************************************************/

44 45
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

J
Jiri Pirko 已提交
46
#include <linux/bitops.h>
47
#include <linux/if_vlan.h>
48
#include <linux/interrupt.h>
49
#include <linux/pci.h>
50
#include <linux/slab.h>
A
Alexander Beregalov 已提交
51
#include <linux/tcp.h>
52 53 54
#include <net/ip.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
55
#include <linux/firmware.h>
56
#include <linux/net_tstamp.h>
57
#include <linux/prefetch.h>
58 59 60 61 62 63 64
#include "vxge-main.h"
#include "vxge-reg.h"

MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("Neterion's X3100 Series 10GbE PCIe I/O"
	"Virtualized Server Adapter");

65
static DEFINE_PCI_DEVICE_TABLE(vxge_id_table) = {
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
	{PCI_VENDOR_ID_S2IO, PCI_DEVICE_ID_TITAN_WIN, PCI_ANY_ID,
	PCI_ANY_ID},
	{PCI_VENDOR_ID_S2IO, PCI_DEVICE_ID_TITAN_UNI, PCI_ANY_ID,
	PCI_ANY_ID},
	{0}
};

MODULE_DEVICE_TABLE(pci, vxge_id_table);

VXGE_MODULE_PARAM_INT(vlan_tag_strip, VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE);
VXGE_MODULE_PARAM_INT(addr_learn_en, VXGE_HW_MAC_ADDR_LEARN_DEFAULT);
VXGE_MODULE_PARAM_INT(max_config_port, VXGE_MAX_CONFIG_PORT);
VXGE_MODULE_PARAM_INT(max_config_vpath, VXGE_USE_DEFAULT);
VXGE_MODULE_PARAM_INT(max_mac_vpath, VXGE_MAX_MAC_ADDR_COUNT);
VXGE_MODULE_PARAM_INT(max_config_dev, VXGE_MAX_CONFIG_DEV);

static u16 vpath_selector[VXGE_HW_MAX_VIRTUAL_PATHS] =
		{0, 1, 3, 3, 7, 7, 7, 7, 15, 15, 15, 15, 15, 15, 15, 15, 31};
static unsigned int bw_percentage[VXGE_HW_MAX_VIRTUAL_PATHS] =
	{[0 ...(VXGE_HW_MAX_VIRTUAL_PATHS - 1)] = 0xFF};
module_param_array(bw_percentage, uint, NULL, 0);

static struct vxge_drv_config *driver_config;

static inline int is_vxge_card_up(struct vxgedev *vdev)
{
	return test_bit(__VXGE_STATE_CARD_UP, &vdev->state);
}

static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo)
{
97 98 99 100 101
	struct sk_buff **skb_ptr = NULL;
	struct sk_buff **temp;
#define NR_SKB_COMPLETED 128
	struct sk_buff *completed[NR_SKB_COMPLETED];
	int more;
102

103 104 105 106
	do {
		more = 0;
		skb_ptr = completed;

J
Jon Mason 已提交
107
		if (__netif_tx_trylock(fifo->txq)) {
108 109
			vxge_hw_vpath_poll_tx(fifo->handle, &skb_ptr,
						NR_SKB_COMPLETED, &more);
J
Jon Mason 已提交
110
			__netif_tx_unlock(fifo->txq);
111
		}
J
Jon Mason 已提交
112

113 114 115
		/* free SKBs */
		for (temp = completed; temp != skb_ptr; temp++)
			dev_kfree_skb_irq(*temp);
J
Jon Mason 已提交
116
	} while (more);
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
}

static inline void VXGE_COMPLETE_ALL_TX(struct vxgedev *vdev)
{
	int i;

	/* Complete all transmits */
	for (i = 0; i < vdev->no_of_vpath; i++)
		VXGE_COMPLETE_VPATH_TX(&vdev->vpaths[i].fifo);
}

static inline void VXGE_COMPLETE_ALL_RX(struct vxgedev *vdev)
{
	int i;
	struct vxge_ring *ring;

	/* Complete all receives*/
	for (i = 0; i < vdev->no_of_vpath; i++) {
		ring = &vdev->vpaths[i].ring;
		vxge_hw_vpath_poll_rx(ring->handle);
	}
}

/*
 * vxge_callback_link_up
 *
 * This function is called during interrupt context to notify link up state
 * change.
 */
J
Jon Mason 已提交
146
static void vxge_callback_link_up(struct __vxge_hw_device *hldev)
147 148
{
	struct net_device *dev = hldev->ndev;
149
	struct vxgedev *vdev = netdev_priv(dev);
150 151 152

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		vdev->ndev->name, __func__, __LINE__);
153
	netdev_notice(vdev->ndev, "Link Up\n");
154 155 156
	vdev->stats.link_up++;

	netif_carrier_on(vdev->ndev);
J
Jon Mason 已提交
157
	netif_tx_wake_all_queues(vdev->ndev);
158 159 160 161 162 163 164 165 166 167 168

	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", vdev->ndev->name, __func__, __LINE__);
}

/*
 * vxge_callback_link_down
 *
 * This function is called during interrupt context to notify link down state
 * change.
 */
J
Jon Mason 已提交
169
static void vxge_callback_link_down(struct __vxge_hw_device *hldev)
170 171
{
	struct net_device *dev = hldev->ndev;
172
	struct vxgedev *vdev = netdev_priv(dev);
173 174 175

	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d", vdev->ndev->name, __func__, __LINE__);
176
	netdev_notice(vdev->ndev, "Link Down\n");
177 178 179

	vdev->stats.link_down++;
	netif_carrier_off(vdev->ndev);
J
Jon Mason 已提交
180
	netif_tx_stop_all_queues(vdev->ndev);
181 182 183 184 185 186 187 188 189 190

	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", vdev->ndev->name, __func__, __LINE__);
}

/*
 * vxge_rx_alloc
 *
 * Allocate SKB.
 */
J
Jon Mason 已提交
191
static struct sk_buff *
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
vxge_rx_alloc(void *dtrh, struct vxge_ring *ring, const int skb_size)
{
	struct net_device    *dev;
	struct sk_buff       *skb;
	struct vxge_rx_priv *rx_priv;

	dev = ring->ndev;
	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		ring->ndev->name, __func__, __LINE__);

	rx_priv = vxge_hw_ring_rxd_private_get(dtrh);

	/* try to allocate skb first. this one may fail */
	skb = netdev_alloc_skb(dev, skb_size +
	VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
	if (skb == NULL) {
		vxge_debug_mem(VXGE_ERR,
			"%s: out of memory to allocate SKB", dev->name);
		ring->stats.skb_alloc_fail++;
		return NULL;
	}

	vxge_debug_mem(VXGE_TRACE,
		"%s: %s:%d  Skb : 0x%p", ring->ndev->name,
		__func__, __LINE__, skb);

	skb_reserve(skb, VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);

	rx_priv->skb = skb;
B
Benjamin LaHaise 已提交
221
	rx_priv->skb_data = NULL;
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
	rx_priv->data_size = skb_size;
	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);

	return skb;
}

/*
 * vxge_rx_map
 */
static int vxge_rx_map(void *dtrh, struct vxge_ring *ring)
{
	struct vxge_rx_priv *rx_priv;
	dma_addr_t dma_addr;

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		ring->ndev->name, __func__, __LINE__);
	rx_priv = vxge_hw_ring_rxd_private_get(dtrh);

B
Benjamin LaHaise 已提交
241 242
	rx_priv->skb_data = rx_priv->skb->data;
	dma_addr = pci_map_single(ring->pdev, rx_priv->skb_data,
243 244
				rx_priv->data_size, PCI_DMA_FROMDEVICE);

245
	if (unlikely(pci_dma_mapping_error(ring->pdev, dma_addr))) {
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
		ring->stats.pci_map_fail++;
		return -EIO;
	}
	vxge_debug_mem(VXGE_TRACE,
		"%s: %s:%d  1 buffer mode dma_addr = 0x%llx",
		ring->ndev->name, __func__, __LINE__,
		(unsigned long long)dma_addr);
	vxge_hw_ring_rxd_1b_set(dtrh, dma_addr, rx_priv->data_size);

	rx_priv->data_dma = dma_addr;
	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);

	return 0;
}

/*
 * vxge_rx_initial_replenish
 * Allocation of RxD as an initial replenish procedure.
 */
static enum vxge_hw_status
vxge_rx_initial_replenish(void *dtrh, void *userdata)
{
	struct vxge_ring *ring = (struct vxge_ring *)userdata;
	struct vxge_rx_priv *rx_priv;

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		ring->ndev->name, __func__, __LINE__);
	if (vxge_rx_alloc(dtrh, ring,
			  VXGE_LL_MAX_FRAME_SIZE(ring->ndev)) == NULL)
		return VXGE_HW_FAIL;

	if (vxge_rx_map(dtrh, ring)) {
		rx_priv = vxge_hw_ring_rxd_private_get(dtrh);
		dev_kfree_skb(rx_priv->skb);

		return VXGE_HW_FAIL;
	}
	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);

	return VXGE_HW_OK;
}

static inline void
vxge_rx_complete(struct vxge_ring *ring, struct sk_buff *skb, u16 vlan,
		 int pkt_length, struct vxge_hw_ring_rxd_info *ext_info)
{

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
			ring->ndev->name, __func__, __LINE__);
	skb_record_rx_queue(skb, ring->driver_id);
	skb->protocol = eth_type_trans(skb, ring->ndev);

300
	u64_stats_update_begin(&ring->stats.syncp);
301 302 303 304 305
	ring->stats.rx_frms++;
	ring->stats.rx_bytes += pkt_length;

	if (skb->pkt_type == PACKET_MULTICAST)
		ring->stats.rx_mcast++;
306
	u64_stats_update_end(&ring->stats.syncp);
307 308 309 310 311

	vxge_debug_rx(VXGE_TRACE,
		"%s: %s:%d  skb protocol = %d",
		ring->ndev->name, __func__, __LINE__, skb->protocol);

J
Jiri Pirko 已提交
312 313 314 315
	if (ext_info->vlan &&
	    ring->vlan_tag_strip == VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE)
		__vlan_hwaccel_put_tag(skb, ext_info->vlan);
	napi_gro_receive(ring->napi_p, skb);
316

317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);
}

static inline void vxge_re_pre_post(void *dtr, struct vxge_ring *ring,
				    struct vxge_rx_priv *rx_priv)
{
	pci_dma_sync_single_for_device(ring->pdev,
		rx_priv->data_dma, rx_priv->data_size, PCI_DMA_FROMDEVICE);

	vxge_hw_ring_rxd_1b_set(dtr, rx_priv->data_dma, rx_priv->data_size);
	vxge_hw_ring_rxd_pre_post(ring->handle, dtr);
}

static inline void vxge_post(int *dtr_cnt, void **first_dtr,
			     void *post_dtr, struct __vxge_hw_ring *ringh)
{
	int dtr_count = *dtr_cnt;
	if ((*dtr_cnt % VXGE_HW_RXSYNC_FREQ_CNT) == 0) {
		if (*first_dtr)
			vxge_hw_ring_rxd_post_post_wmb(ringh, *first_dtr);
		*first_dtr = post_dtr;
	} else
		vxge_hw_ring_rxd_post_post(ringh, post_dtr);
	dtr_count++;
	*dtr_cnt = dtr_count;
}

/*
 * vxge_rx_1b_compl
 *
 * If the interrupt is because of a received frame or if the receive ring
 * contains fresh as yet un-processed frames, this function is called.
 */
351
static enum vxge_hw_status
352 353 354 355
vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
		 u8 t_code, void *userdata)
{
	struct vxge_ring *ring = (struct vxge_ring *)userdata;
356
	struct net_device *dev = ring->ndev;
357 358 359 360 361 362 363 364 365 366 367 368 369
	unsigned int dma_sizes;
	void *first_dtr = NULL;
	int dtr_cnt = 0;
	int data_size;
	dma_addr_t data_dma;
	int pkt_length;
	struct sk_buff *skb;
	struct vxge_rx_priv *rx_priv;
	struct vxge_hw_ring_rxd_info ext_info;
	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		ring->ndev->name, __func__, __LINE__);

	do {
370
		prefetch((char *)dtr + L1_CACHE_BYTES);
371 372 373 374
		rx_priv = vxge_hw_ring_rxd_private_get(dtr);
		skb = rx_priv->skb;
		data_size = rx_priv->data_size;
		data_dma = rx_priv->data_dma;
B
Benjamin LaHaise 已提交
375
		prefetch(rx_priv->skb_data);
376 377 378 379 380 381 382 383

		vxge_debug_rx(VXGE_TRACE,
			"%s: %s:%d  skb = 0x%p",
			ring->ndev->name, __func__, __LINE__, skb);

		vxge_hw_ring_rxd_1b_get(ringh, dtr, &dma_sizes);
		pkt_length = dma_sizes;

S
Sreenivasa Honnur 已提交
384 385
		pkt_length -= ETH_FCS_LEN;

386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
		vxge_debug_rx(VXGE_TRACE,
			"%s: %s:%d  Packet Length = %d",
			ring->ndev->name, __func__, __LINE__, pkt_length);

		vxge_hw_ring_rxd_1b_info_get(ringh, dtr, &ext_info);

		/* check skb validity */
		vxge_assert(skb);

		prefetch((char *)skb + L1_CACHE_BYTES);
		if (unlikely(t_code)) {
			if (vxge_hw_ring_handle_tcode(ringh, dtr, t_code) !=
				VXGE_HW_OK) {

				ring->stats.rx_errors++;
				vxge_debug_rx(VXGE_TRACE,
					"%s: %s :%d Rx T_code is %d",
					ring->ndev->name, __func__,
					__LINE__, t_code);

				/* If the t_code is not supported and if the
				 * t_code is other than 0x5 (unparseable packet
				 * such as unknown UPV6 header), Drop it !!!
				 */
				vxge_re_pre_post(dtr, ring, rx_priv);

				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
				ring->stats.rx_dropped++;
				continue;
			}
		}

		if (pkt_length > VXGE_LL_RX_COPY_THRESHOLD) {
			if (vxge_rx_alloc(dtr, ring, data_size) != NULL) {
				if (!vxge_rx_map(dtr, ring)) {
					skb_put(skb, pkt_length);

					pci_unmap_single(ring->pdev, data_dma,
						data_size, PCI_DMA_FROMDEVICE);

					vxge_hw_ring_rxd_pre_post(ringh, dtr);
					vxge_post(&dtr_cnt, &first_dtr, dtr,
						ringh);
				} else {
					dev_kfree_skb(rx_priv->skb);
					rx_priv->skb = skb;
					rx_priv->data_size = data_size;
					vxge_re_pre_post(dtr, ring, rx_priv);

					vxge_post(&dtr_cnt, &first_dtr, dtr,
						ringh);
					ring->stats.rx_dropped++;
					break;
				}
			} else {
				vxge_re_pre_post(dtr, ring, rx_priv);

				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
				ring->stats.rx_dropped++;
				break;
			}
		} else {
			struct sk_buff *skb_up;

			skb_up = netdev_alloc_skb(dev, pkt_length +
				VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
			if (skb_up != NULL) {
				skb_reserve(skb_up,
				    VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);

				pci_dma_sync_single_for_cpu(ring->pdev,
					data_dma, data_size,
					PCI_DMA_FROMDEVICE);

				vxge_debug_mem(VXGE_TRACE,
					"%s: %s:%d  skb_up = %p",
					ring->ndev->name, __func__,
					__LINE__, skb);
				memcpy(skb_up->data, skb->data, pkt_length);

				vxge_re_pre_post(dtr, ring, rx_priv);

				vxge_post(&dtr_cnt, &first_dtr, dtr,
					ringh);
				/* will netif_rx small SKB instead */
				skb = skb_up;
				skb_put(skb, pkt_length);
			} else {
				vxge_re_pre_post(dtr, ring, rx_priv);

				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
				vxge_debug_rx(VXGE_ERR,
					"%s: vxge_rx_1b_compl: out of "
					"memory", dev->name);
				ring->stats.skb_alloc_fail++;
				break;
			}
		}

		if ((ext_info.proto & VXGE_HW_FRAME_PROTO_TCP_OR_UDP) &&
		    !(ext_info.proto & VXGE_HW_FRAME_PROTO_IP_FRAG) &&
487
		    (dev->features & NETIF_F_RXCSUM) && /* Offload Rx side CSUM */
488 489 490 491
		    ext_info.l3_cksum == VXGE_HW_L3_CKSUM_OK &&
		    ext_info.l4_cksum == VXGE_HW_L4_CKSUM_OK)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
		else
492
			skb_checksum_none_assert(skb);
493

494 495 496 497 498 499 500 501 502 503

		if (ring->rx_hwts) {
			struct skb_shared_hwtstamps *skb_hwts;
			u32 ns = *(u32 *)(skb->head + pkt_length);

			skb_hwts = skb_hwtstamps(skb);
			skb_hwts->hwtstamp = ns_to_ktime(ns);
			skb_hwts->syststamp.tv64 = 0;
		}

J
Jon Mason 已提交
504 505 506 507 508 509 510
		/* rth_hash_type and rth_it_hit are non-zero regardless of
		 * whether rss is enabled.  Only the rth_value is zero/non-zero
		 * if rss is disabled/enabled, so key off of that.
		 */
		if (ext_info.rth_value)
			skb->rxhash = ext_info.rth_value;

511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538
		vxge_rx_complete(ring, skb, ext_info.vlan,
			pkt_length, &ext_info);

		ring->budget--;
		ring->pkts_processed++;
		if (!ring->budget)
			break;

	} while (vxge_hw_ring_rxd_next_completed(ringh, &dtr,
		&t_code) == VXGE_HW_OK);

	if (first_dtr)
		vxge_hw_ring_rxd_post_post_wmb(ringh, first_dtr);

	vxge_debug_entryexit(VXGE_TRACE,
				"%s:%d  Exiting...",
				__func__, __LINE__);
	return VXGE_HW_OK;
}

/*
 * vxge_xmit_compl
 *
 * If an interrupt was raised to indicate DMA complete of the Tx packet,
 * this function is called. It identifies the last TxD whose buffer was
 * freed and frees all skbs whose data have already DMA'ed into the NICs
 * internal memory.
 */
539
static enum vxge_hw_status
540 541
vxge_xmit_compl(struct __vxge_hw_fifo *fifo_hw, void *dtr,
		enum vxge_hw_fifo_tcode t_code, void *userdata,
542
		struct sk_buff ***skb_ptr, int nr_skb, int *more)
543 544
{
	struct vxge_fifo *fifo = (struct vxge_fifo *)userdata;
545
	struct sk_buff *skb, **done_skb = *skb_ptr;
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594
	int pkt_cnt = 0;

	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d Entered....", __func__, __LINE__);

	do {
		int frg_cnt;
		skb_frag_t *frag;
		int i = 0, j;
		struct vxge_tx_priv *txd_priv =
			vxge_hw_fifo_txdl_private_get(dtr);

		skb = txd_priv->skb;
		frg_cnt = skb_shinfo(skb)->nr_frags;
		frag = &skb_shinfo(skb)->frags[0];

		vxge_debug_tx(VXGE_TRACE,
				"%s: %s:%d fifo_hw = %p dtr = %p "
				"tcode = 0x%x", fifo->ndev->name, __func__,
				__LINE__, fifo_hw, dtr, t_code);
		/* check skb validity */
		vxge_assert(skb);
		vxge_debug_tx(VXGE_TRACE,
			"%s: %s:%d skb = %p itxd_priv = %p frg_cnt = %d",
			fifo->ndev->name, __func__, __LINE__,
			skb, txd_priv, frg_cnt);
		if (unlikely(t_code)) {
			fifo->stats.tx_errors++;
			vxge_debug_tx(VXGE_ERR,
				"%s: tx: dtr %p completed due to "
				"error t_code %01x", fifo->ndev->name,
				dtr, t_code);
			vxge_hw_fifo_handle_tcode(fifo_hw, dtr, t_code);
		}

		/*  for unfragmented skb */
		pci_unmap_single(fifo->pdev, txd_priv->dma_buffers[i++],
				skb_headlen(skb), PCI_DMA_TODEVICE);

		for (j = 0; j < frg_cnt; j++) {
			pci_unmap_page(fifo->pdev,
					txd_priv->dma_buffers[i++],
					frag->size, PCI_DMA_TODEVICE);
			frag += 1;
		}

		vxge_hw_fifo_txdl_free(fifo_hw, dtr);

		/* Updating the statistics block */
595
		u64_stats_update_begin(&fifo->stats.syncp);
596 597
		fifo->stats.tx_frms++;
		fifo->stats.tx_bytes += skb->len;
598
		u64_stats_update_end(&fifo->stats.syncp);
599

600 601 602 603 604 605
		*done_skb++ = skb;

		if (--nr_skb <= 0) {
			*more = 1;
			break;
		}
606 607 608 609 610 611 612 613

		pkt_cnt++;
		if (pkt_cnt > fifo->indicate_max_pkts)
			break;

	} while (vxge_hw_fifo_txdl_next_completed(fifo_hw,
				&dtr, &t_code) == VXGE_HW_OK);

614
	*skb_ptr = done_skb;
J
Jon Mason 已提交
615 616
	if (netif_tx_queue_stopped(fifo->txq))
		netif_tx_wake_queue(fifo->txq);
617 618 619 620 621 622 623

	vxge_debug_entryexit(VXGE_TRACE,
				"%s: %s:%d  Exiting...",
				fifo->ndev->name, __func__, __LINE__);
	return VXGE_HW_OK;
}

624
/* select a vpath to transmit the packet */
J
Jon Mason 已提交
625
static u32 vxge_get_vpath_no(struct vxgedev *vdev, struct sk_buff *skb)
626 627 628 629 630 631 632 633
{
	u16 queue_len, counter = 0;
	if (skb->protocol == htons(ETH_P_IP)) {
		struct iphdr *ip;
		struct tcphdr *th;

		ip = ip_hdr(skb);

634
		if (!ip_is_fragment(ip)) {
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659
			th = (struct tcphdr *)(((unsigned char *)ip) +
					ip->ihl*4);

			queue_len = vdev->no_of_vpath;
			counter = (ntohs(th->source) +
				ntohs(th->dest)) &
				vdev->vpath_selector[queue_len - 1];
			if (counter >= queue_len)
				counter = queue_len - 1;
		}
	}
	return counter;
}

static enum vxge_hw_status vxge_search_mac_addr_in_list(
	struct vxge_vpath *vpath, u64 del_mac)
{
	struct list_head *entry, *next;
	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
		if (((struct vxge_mac_addrs *)entry)->macaddr == del_mac)
			return TRUE;
	}
	return FALSE;
}

J
Jon Mason 已提交
660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
static int vxge_mac_list_add(struct vxge_vpath *vpath, struct macInfo *mac)
{
	struct vxge_mac_addrs *new_mac_entry;
	u8 *mac_address = NULL;

	if (vpath->mac_addr_cnt >= VXGE_MAX_LEARN_MAC_ADDR_CNT)
		return TRUE;

	new_mac_entry = kzalloc(sizeof(struct vxge_mac_addrs), GFP_ATOMIC);
	if (!new_mac_entry) {
		vxge_debug_mem(VXGE_ERR,
			"%s: memory allocation failed",
			VXGE_DRIVER_NAME);
		return FALSE;
	}

	list_add(&new_mac_entry->item, &vpath->mac_addr_list);

	/* Copy the new mac address to the list */
	mac_address = (u8 *)&new_mac_entry->macaddr;
	memcpy(mac_address, mac->macaddr, ETH_ALEN);

	new_mac_entry->state = mac->state;
	vpath->mac_addr_cnt++;

685
	if (is_multicast_ether_addr(mac->macaddr))
J
Jon Mason 已提交
686 687 688 689 690 691 692 693 694 695 696 697 698
		vpath->mcast_addr_cnt++;

	return TRUE;
}

/* Add a mac address to DA table */
static enum vxge_hw_status
vxge_add_mac_addr(struct vxgedev *vdev, struct macInfo *mac)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxge_vpath *vpath;
	enum vxge_hw_vpath_mac_addr_add_mode duplicate_mode;

699
	if (is_multicast_ether_addr(mac->macaddr))
J
Jon Mason 已提交
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717
		duplicate_mode = VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE;
	else
		duplicate_mode = VXGE_HW_VPATH_MAC_ADDR_REPLACE_DUPLICATE;

	vpath = &vdev->vpaths[mac->vpath_no];
	status = vxge_hw_vpath_mac_addr_add(vpath->handle, mac->macaddr,
						mac->macmask, duplicate_mode);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"DA config add entry failed for vpath:%d",
			vpath->device_id);
	} else
		if (FALSE == vxge_mac_list_add(vpath, mac))
			status = -EPERM;

	return status;
}

718 719 720 721 722 723 724 725 726 727
static int vxge_learn_mac(struct vxgedev *vdev, u8 *mac_header)
{
	struct macInfo mac_info;
	u8 *mac_address = NULL;
	u64 mac_addr = 0, vpath_vector = 0;
	int vpath_idx = 0;
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxge_vpath *vpath = NULL;
	struct __vxge_hw_device *hldev;

728
	hldev = pci_get_drvdata(vdev->pdev);
729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798

	mac_address = (u8 *)&mac_addr;
	memcpy(mac_address, mac_header, ETH_ALEN);

	/* Is this mac address already in the list? */
	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
		vpath = &vdev->vpaths[vpath_idx];
		if (vxge_search_mac_addr_in_list(vpath, mac_addr))
			return vpath_idx;
	}

	memset(&mac_info, 0, sizeof(struct macInfo));
	memcpy(mac_info.macaddr, mac_header, ETH_ALEN);

	/* Any vpath has room to add mac address to its da table? */
	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
		vpath = &vdev->vpaths[vpath_idx];
		if (vpath->mac_addr_cnt < vpath->max_mac_addr_cnt) {
			/* Add this mac address to this vpath */
			mac_info.vpath_no = vpath_idx;
			mac_info.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
			status = vxge_add_mac_addr(vdev, &mac_info);
			if (status != VXGE_HW_OK)
				return -EPERM;
			return vpath_idx;
		}
	}

	mac_info.state = VXGE_LL_MAC_ADDR_IN_LIST;
	vpath_idx = 0;
	mac_info.vpath_no = vpath_idx;
	/* Is the first vpath already selected as catch-basin ? */
	vpath = &vdev->vpaths[vpath_idx];
	if (vpath->mac_addr_cnt > vpath->max_mac_addr_cnt) {
		/* Add this mac address to this vpath */
		if (FALSE == vxge_mac_list_add(vpath, &mac_info))
			return -EPERM;
		return vpath_idx;
	}

	/* Select first vpath as catch-basin */
	vpath_vector = vxge_mBIT(vpath->device_id);
	status = vxge_hw_mgmt_reg_write(vpath->vdev->devh,
				vxge_hw_mgmt_reg_type_mrpcim,
				0,
				(ulong)offsetof(
					struct vxge_hw_mrpcim_reg,
					rts_mgr_cbasin_cfg),
				vpath_vector);
	if (status != VXGE_HW_OK) {
		vxge_debug_tx(VXGE_ERR,
			"%s: Unable to set the vpath-%d in catch-basin mode",
			VXGE_DRIVER_NAME, vpath->device_id);
		return -EPERM;
	}

	if (FALSE == vxge_mac_list_add(vpath, &mac_info))
		return -EPERM;

	return vpath_idx;
}

/**
 * vxge_xmit
 * @skb : the socket buffer containing the Tx data.
 * @dev : device pointer.
 *
 * This function is the Tx entry point of the driver. Neterion NIC supports
 * certain protocol assist features on Tx side, namely  CSO, S/G, LSO.
*/
799
static netdev_tx_t
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826
vxge_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct vxge_fifo *fifo = NULL;
	void *dtr_priv;
	void *dtr = NULL;
	struct vxgedev *vdev = NULL;
	enum vxge_hw_status status;
	int frg_cnt, first_frg_len;
	skb_frag_t *frag;
	int i = 0, j = 0, avail;
	u64 dma_pointer;
	struct vxge_tx_priv *txdl_priv = NULL;
	struct __vxge_hw_fifo *fifo_hw;
	int offload_type;
	int vpath_no = 0;

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
			dev->name, __func__, __LINE__);

	/* A buffer with no data will be dropped */
	if (unlikely(skb->len <= 0)) {
		vxge_debug_tx(VXGE_ERR,
			"%s: Buffer has no data..", dev->name);
		dev_kfree_skb(skb);
		return NETDEV_TX_OK;
	}

827
	vdev = netdev_priv(dev);
828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849

	if (unlikely(!is_vxge_card_up(vdev))) {
		vxge_debug_tx(VXGE_ERR,
			"%s: vdev not initialized", dev->name);
		dev_kfree_skb(skb);
		return NETDEV_TX_OK;
	}

	if (vdev->config.addr_learn_en) {
		vpath_no = vxge_learn_mac(vdev, skb->data + ETH_ALEN);
		if (vpath_no == -EPERM) {
			vxge_debug_tx(VXGE_ERR,
				"%s: Failed to store the mac address",
				dev->name);
			dev_kfree_skb(skb);
			return NETDEV_TX_OK;
		}
	}

	if (vdev->config.tx_steering_type == TX_MULTIQ_STEERING)
		vpath_no = skb_get_queue_mapping(skb);
	else if (vdev->config.tx_steering_type == TX_PORT_STEERING)
J
Jon Mason 已提交
850
		vpath_no = vxge_get_vpath_no(vdev, skb);
851 852 853 854 855 856 857 858 859

	vxge_debug_tx(VXGE_TRACE, "%s: vpath_no= %d", dev->name, vpath_no);

	if (vpath_no >= vdev->no_of_vpath)
		vpath_no = 0;

	fifo = &vdev->vpaths[vpath_no].fifo;
	fifo_hw = fifo->handle;

J
Jon Mason 已提交
860
	if (netif_tx_queue_stopped(fifo->txq))
J
Jon Mason 已提交
861 862
		return NETDEV_TX_BUSY;

863 864 865 866 867
	avail = vxge_hw_fifo_free_txdl_count_get(fifo_hw);
	if (avail == 0) {
		vxge_debug_tx(VXGE_ERR,
			"%s: No free TXDs available", dev->name);
		fifo->stats.txd_not_free++;
J
Jon Mason 已提交
868
		goto _exit0;
869 870
	}

871 872 873 874
	/* Last TXD?  Stop tx queue to avoid dropping packets.  TX
	 * completion will resume the queue.
	 */
	if (avail == 1)
J
Jon Mason 已提交
875
		netif_tx_stop_queue(fifo->txq);
876

877 878 879 880 881
	status = vxge_hw_fifo_txdl_reserve(fifo_hw, &dtr, &dtr_priv);
	if (unlikely(status != VXGE_HW_OK)) {
		vxge_debug_tx(VXGE_ERR,
		   "%s: Out of descriptors .", dev->name);
		fifo->stats.txd_out_of_desc++;
J
Jon Mason 已提交
882
		goto _exit0;
883 884 885 886 887 888 889
	}

	vxge_debug_tx(VXGE_TRACE,
		"%s: %s:%d fifo_hw = %p dtr = %p dtr_priv = %p",
		dev->name, __func__, __LINE__,
		fifo_hw, dtr, dtr_priv);

890
	if (vlan_tx_tag_present(skb)) {
891 892 893 894 895 896 897 898 899 900 901 902
		u16 vlan_tag = vlan_tx_tag_get(skb);
		vxge_hw_fifo_txdl_vlan_set(dtr, vlan_tag);
	}

	first_frg_len = skb_headlen(skb);

	dma_pointer = pci_map_single(fifo->pdev, skb->data, first_frg_len,
				PCI_DMA_TODEVICE);

	if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer))) {
		vxge_hw_fifo_txdl_free(fifo_hw, dtr);
		fifo->stats.pci_map_fail++;
J
Jon Mason 已提交
903
		goto _exit0;
904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925
	}

	txdl_priv = vxge_hw_fifo_txdl_private_get(dtr);
	txdl_priv->skb = skb;
	txdl_priv->dma_buffers[j] = dma_pointer;

	frg_cnt = skb_shinfo(skb)->nr_frags;
	vxge_debug_tx(VXGE_TRACE,
			"%s: %s:%d skb = %p txdl_priv = %p "
			"frag_cnt = %d dma_pointer = 0x%llx", dev->name,
			__func__, __LINE__, skb, txdl_priv,
			frg_cnt, (unsigned long long)dma_pointer);

	vxge_hw_fifo_txdl_buffer_set(fifo_hw, dtr, j++, dma_pointer,
		first_frg_len);

	frag = &skb_shinfo(skb)->frags[0];
	for (i = 0; i < frg_cnt; i++) {
		/* ignore 0 length fragment */
		if (!frag->size)
			continue;

J
Jon Mason 已提交
926
		dma_pointer = (u64) pci_map_page(fifo->pdev, frag->page,
927 928 929 930
				frag->page_offset, frag->size,
				PCI_DMA_TODEVICE);

		if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer)))
J
Jon Mason 已提交
931
			goto _exit2;
932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947
		vxge_debug_tx(VXGE_TRACE,
			"%s: %s:%d frag = %d dma_pointer = 0x%llx",
				dev->name, __func__, __LINE__, i,
				(unsigned long long)dma_pointer);

		txdl_priv->dma_buffers[j] = dma_pointer;
		vxge_hw_fifo_txdl_buffer_set(fifo_hw, dtr, j++, dma_pointer,
					frag->size);
		frag += 1;
	}

	offload_type = vxge_offload_type(skb);

	if (offload_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
		int mss = vxge_tcp_mss(skb);
		if (mss) {
J
Jon Mason 已提交
948
			vxge_debug_tx(VXGE_TRACE, "%s: %s:%d mss = %d",
949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968
				dev->name, __func__, __LINE__, mss);
			vxge_hw_fifo_txdl_mss_set(dtr, mss);
		} else {
			vxge_assert(skb->len <=
				dev->mtu + VXGE_HW_MAC_HEADER_MAX_SIZE);
			vxge_assert(0);
			goto _exit1;
		}
	}

	if (skb->ip_summed == CHECKSUM_PARTIAL)
		vxge_hw_fifo_txdl_cksum_set_bits(dtr,
					VXGE_HW_FIFO_TXD_TX_CKO_IPV4_EN |
					VXGE_HW_FIFO_TXD_TX_CKO_TCP_EN |
					VXGE_HW_FIFO_TXD_TX_CKO_UDP_EN);

	vxge_hw_fifo_txdl_post(fifo_hw, dtr);

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d  Exiting...",
		dev->name, __func__, __LINE__);
969
	return NETDEV_TX_OK;
970

J
Jon Mason 已提交
971
_exit2:
972 973 974 975 976 977 978 979 980 981 982 983 984 985 986
	vxge_debug_tx(VXGE_TRACE, "%s: pci_map_page failed", dev->name);
_exit1:
	j = 0;
	frag = &skb_shinfo(skb)->frags[0];

	pci_unmap_single(fifo->pdev, txdl_priv->dma_buffers[j++],
			skb_headlen(skb), PCI_DMA_TODEVICE);

	for (; j < i; j++) {
		pci_unmap_page(fifo->pdev, txdl_priv->dma_buffers[j],
			frag->size, PCI_DMA_TODEVICE);
		frag += 1;
	}

	vxge_hw_fifo_txdl_free(fifo_hw, dtr);
J
Jon Mason 已提交
987 988
_exit0:
	netif_tx_stop_queue(fifo->txq);
989 990
	dev_kfree_skb(skb);

991
	return NETDEV_TX_OK;
992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
}

/*
 * vxge_rx_term
 *
 * Function will be called by hw function to abort all outstanding receive
 * descriptors.
 */
static void
vxge_rx_term(void *dtrh, enum vxge_hw_rxd_state state, void *userdata)
{
	struct vxge_ring *ring = (struct vxge_ring *)userdata;
	struct vxge_rx_priv *rx_priv =
		vxge_hw_ring_rxd_private_get(dtrh);

	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
			ring->ndev->name, __func__, __LINE__);
	if (state != VXGE_HW_RXD_STATE_POSTED)
		return;

	pci_unmap_single(ring->pdev, rx_priv->data_dma,
		rx_priv->data_size, PCI_DMA_FROMDEVICE);

	dev_kfree_skb(rx_priv->skb);
B
Benjamin LaHaise 已提交
1016
	rx_priv->skb_data = NULL;
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062

	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d  Exiting...",
		ring->ndev->name, __func__, __LINE__);
}

/*
 * vxge_tx_term
 *
 * Function will be called to abort all outstanding tx descriptors
 */
static void
vxge_tx_term(void *dtrh, enum vxge_hw_txdl_state state, void *userdata)
{
	struct vxge_fifo *fifo = (struct vxge_fifo *)userdata;
	skb_frag_t *frag;
	int i = 0, j, frg_cnt;
	struct vxge_tx_priv *txd_priv = vxge_hw_fifo_txdl_private_get(dtrh);
	struct sk_buff *skb = txd_priv->skb;

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

	if (state != VXGE_HW_TXDL_STATE_POSTED)
		return;

	/* check skb validity */
	vxge_assert(skb);
	frg_cnt = skb_shinfo(skb)->nr_frags;
	frag = &skb_shinfo(skb)->frags[0];

	/*  for unfragmented skb */
	pci_unmap_single(fifo->pdev, txd_priv->dma_buffers[i++],
		skb_headlen(skb), PCI_DMA_TODEVICE);

	for (j = 0; j < frg_cnt; j++) {
		pci_unmap_page(fifo->pdev, txd_priv->dma_buffers[i++],
			       frag->size, PCI_DMA_TODEVICE);
		frag += 1;
	}

	dev_kfree_skb(skb);

	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);
}

J
Jon Mason 已提交
1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077
static int vxge_mac_list_del(struct vxge_vpath *vpath, struct macInfo *mac)
{
	struct list_head *entry, *next;
	u64 del_mac = 0;
	u8 *mac_address = (u8 *) (&del_mac);

	/* Copy the mac address to delete from the list */
	memcpy(mac_address, mac->macaddr, ETH_ALEN);

	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
		if (((struct vxge_mac_addrs *)entry)->macaddr == del_mac) {
			list_del(entry);
			kfree((struct vxge_mac_addrs *)entry);
			vpath->mac_addr_cnt--;

1078
			if (is_multicast_ether_addr(mac->macaddr))
J
Jon Mason 已提交
1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
				vpath->mcast_addr_cnt--;
			return TRUE;
		}
	}

	return FALSE;
}

/* delete a mac address from DA table */
static enum vxge_hw_status
vxge_del_mac_addr(struct vxgedev *vdev, struct macInfo *mac)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxge_vpath *vpath;

	vpath = &vdev->vpaths[mac->vpath_no];
	status = vxge_hw_vpath_mac_addr_delete(vpath->handle, mac->macaddr,
						mac->macmask);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"DA config delete entry failed for vpath:%d",
			vpath->device_id);
	} else
		vxge_mac_list_del(vpath, mac);
	return status;
}

1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
/**
 * vxge_set_multicast
 * @dev: pointer to the device structure
 *
 * Entry point for multicast address enable/disable
 * This function is a driver entry point which gets called by the kernel
 * whenever multicast addresses must be enabled/disabled. This also gets
 * called to set/reset promiscuous mode. Depending on the deivce flag, we
 * determine, if multicast address must be enabled or if promiscuous mode
 * is to be disabled etc.
 */
static void vxge_set_multicast(struct net_device *dev)
{
1119
	struct netdev_hw_addr *ha;
1120 1121
	struct vxgedev *vdev;
	int i, mcast_cnt = 0;
J
Jon Mason 已提交
1122 1123
	struct __vxge_hw_device *hldev;
	struct vxge_vpath *vpath;
1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
	enum vxge_hw_status status = VXGE_HW_OK;
	struct macInfo mac_info;
	int vpath_idx = 0;
	struct vxge_mac_addrs *mac_entry;
	struct list_head *list_head;
	struct list_head *entry, *next;
	u8 *mac_address = NULL;

	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d", __func__, __LINE__);

1135
	vdev = netdev_priv(dev);
1136 1137 1138 1139 1140 1141 1142
	hldev = (struct __vxge_hw_device  *)vdev->devh;

	if (unlikely(!is_vxge_card_up(vdev)))
		return;

	if ((dev->flags & IFF_ALLMULTI) && (!vdev->all_multi_flg)) {
		for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
1143 1144 1145 1146 1147 1148
			vpath = &vdev->vpaths[i];
			vxge_assert(vpath->is_open);
			status = vxge_hw_vpath_mcast_enable(vpath->handle);
			if (status != VXGE_HW_OK)
				vxge_debug_init(VXGE_ERR, "failed to enable "
						"multicast, status %d", status);
1149 1150
			vdev->all_multi_flg = 1;
		}
J
Jon Mason 已提交
1151
	} else if (!(dev->flags & IFF_ALLMULTI) && (vdev->all_multi_flg)) {
1152
		for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
1153 1154 1155 1156 1157 1158 1159
			vpath = &vdev->vpaths[i];
			vxge_assert(vpath->is_open);
			status = vxge_hw_vpath_mcast_disable(vpath->handle);
			if (status != VXGE_HW_OK)
				vxge_debug_init(VXGE_ERR, "failed to disable "
						"multicast, status %d", status);
			vdev->all_multi_flg = 0;
1160 1161 1162 1163 1164
		}
	}


	if (!vdev->config.addr_learn_en) {
J
Jon Mason 已提交
1165 1166 1167 1168 1169
		for (i = 0; i < vdev->no_of_vpath; i++) {
			vpath = &vdev->vpaths[i];
			vxge_assert(vpath->is_open);

			if (dev->flags & IFF_PROMISC)
1170
				status = vxge_hw_vpath_promisc_enable(
J
Jon Mason 已提交
1171 1172
					vpath->handle);
			else
1173
				status = vxge_hw_vpath_promisc_disable(
J
Jon Mason 已提交
1174 1175 1176 1177 1178
					vpath->handle);
			if (status != VXGE_HW_OK)
				vxge_debug_init(VXGE_ERR, "failed to %s promisc"
					", status %d", dev->flags&IFF_PROMISC ?
					"enable" : "disable", status);
1179 1180 1181 1182 1183
		}
	}

	memset(&mac_info, 0, sizeof(struct macInfo));
	/* Update individual M_CAST address list */
1184
	if ((!vdev->all_multi_flg) && netdev_mc_count(dev)) {
1185 1186
		mcast_cnt = vdev->vpaths[0].mcast_addr_cnt;
		list_head = &vdev->vpaths[0].mac_addr_list;
1187
		if ((netdev_mc_count(dev) +
1188 1189 1190 1191 1192 1193 1194
			(vdev->vpaths[0].mac_addr_cnt - mcast_cnt)) >
				vdev->vpaths[0].max_mac_addr_cnt)
			goto _set_all_mcast;

		/* Delete previous MC's */
		for (i = 0; i < mcast_cnt; i++) {
			list_for_each_safe(entry, next, list_head) {
J
Jon Mason 已提交
1195
				mac_entry = (struct vxge_mac_addrs *)entry;
1196 1197 1198 1199
				/* Copy the mac address to delete */
				mac_address = (u8 *)&mac_entry->macaddr;
				memcpy(mac_info.macaddr, mac_address, ETH_ALEN);

1200
				if (is_multicast_ether_addr(mac_info.macaddr)) {
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213
					for (vpath_idx = 0; vpath_idx <
						vdev->no_of_vpath;
						vpath_idx++) {
						mac_info.vpath_no = vpath_idx;
						status = vxge_del_mac_addr(
								vdev,
								&mac_info);
					}
				}
			}
		}

		/* Add new ones */
1214 1215
		netdev_for_each_mc_addr(ha, dev) {
			memcpy(mac_info.macaddr, ha->addr, ETH_ALEN);
1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
			for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath;
					vpath_idx++) {
				mac_info.vpath_no = vpath_idx;
				mac_info.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
				status = vxge_add_mac_addr(vdev, &mac_info);
				if (status != VXGE_HW_OK) {
					vxge_debug_init(VXGE_ERR,
						"%s:%d Setting individual"
						"multicast address failed",
						__func__, __LINE__);
					goto _set_all_mcast;
				}
			}
		}

		return;
_set_all_mcast:
		mcast_cnt = vdev->vpaths[0].mcast_addr_cnt;
		/* Delete previous MC's */
		for (i = 0; i < mcast_cnt; i++) {
			list_for_each_safe(entry, next, list_head) {
J
Jon Mason 已提交
1237
				mac_entry = (struct vxge_mac_addrs *)entry;
1238 1239 1240 1241
				/* Copy the mac address to delete */
				mac_address = (u8 *)&mac_entry->macaddr;
				memcpy(mac_info.macaddr, mac_address, ETH_ALEN);

1242
				if (is_multicast_ether_addr(mac_info.macaddr))
1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254
					break;
			}

			for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath;
					vpath_idx++) {
				mac_info.vpath_no = vpath_idx;
				status = vxge_del_mac_addr(vdev, &mac_info);
			}
		}

		/* Enable all multicast */
		for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
1255 1256 1257 1258
			vpath = &vdev->vpaths[i];
			vxge_assert(vpath->is_open);

			status = vxge_hw_vpath_mcast_enable(vpath->handle);
1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282
			if (status != VXGE_HW_OK) {
				vxge_debug_init(VXGE_ERR,
					"%s:%d Enabling all multicasts failed",
					 __func__, __LINE__);
			}
			vdev->all_multi_flg = 1;
		}
		dev->flags |= IFF_ALLMULTI;
	}

	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);
}

/**
 * vxge_set_mac_addr
 * @dev: pointer to the device structure
 *
 * Update entry "0" (default MAC addr)
 */
static int vxge_set_mac_addr(struct net_device *dev, void *p)
{
	struct sockaddr *addr = p;
	struct vxgedev *vdev;
J
Jon Mason 已提交
1283
	struct __vxge_hw_device *hldev;
1284 1285 1286 1287 1288 1289
	enum vxge_hw_status status = VXGE_HW_OK;
	struct macInfo mac_info_new, mac_info_old;
	int vpath_idx = 0;

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

1290
	vdev = netdev_priv(dev);
1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354
	hldev = vdev->devh;

	if (!is_valid_ether_addr(addr->sa_data))
		return -EINVAL;

	memset(&mac_info_new, 0, sizeof(struct macInfo));
	memset(&mac_info_old, 0, sizeof(struct macInfo));

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d  Exiting...",
		__func__, __LINE__);

	/* Get the old address */
	memcpy(mac_info_old.macaddr, dev->dev_addr, dev->addr_len);

	/* Copy the new address */
	memcpy(mac_info_new.macaddr, addr->sa_data, dev->addr_len);

	/* First delete the old mac address from all the vpaths
	as we can't specify the index while adding new mac address */
	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
		struct vxge_vpath *vpath = &vdev->vpaths[vpath_idx];
		if (!vpath->is_open) {
			/* This can happen when this interface is added/removed
			to the bonding interface. Delete this station address
			from the linked list */
			vxge_mac_list_del(vpath, &mac_info_old);

			/* Add this new address to the linked list
			for later restoring */
			vxge_mac_list_add(vpath, &mac_info_new);

			continue;
		}
		/* Delete the station address */
		mac_info_old.vpath_no = vpath_idx;
		status = vxge_del_mac_addr(vdev, &mac_info_old);
	}

	if (unlikely(!is_vxge_card_up(vdev))) {
		memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
		return VXGE_HW_OK;
	}

	/* Set this mac address to all the vpaths */
	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
		mac_info_new.vpath_no = vpath_idx;
		mac_info_new.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
		status = vxge_add_mac_addr(vdev, &mac_info_new);
		if (status != VXGE_HW_OK)
			return -EINVAL;
	}

	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);

	return status;
}

/*
 * vxge_vpath_intr_enable
 * @vdev: pointer to vdev
 * @vp_id: vpath for which to enable the interrupts
 *
 * Enables the interrupts for the vpath
*/
1355
static void vxge_vpath_intr_enable(struct vxgedev *vdev, int vp_id)
1356 1357
{
	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
1358 1359 1360
	int msix_id = 0;
	int tim_msix_id[4] = {0, 1, 0, 0};
	int alarm_msix_id = VXGE_ALARM_MSIX_ID;
1361 1362 1363 1364 1365 1366 1367 1368 1369

	vxge_hw_vpath_intr_enable(vpath->handle);

	if (vdev->config.intr_type == INTA)
		vxge_hw_vpath_inta_unmask_tx_rx(vpath->handle);
	else {
		vxge_hw_vpath_msix_set(vpath->handle, tim_msix_id,
			alarm_msix_id);

1370
		msix_id = vpath->device_id * VXGE_HW_VPATH_MSIX_ACTIVE;
1371 1372 1373 1374
		vxge_hw_vpath_msix_unmask(vpath->handle, msix_id);
		vxge_hw_vpath_msix_unmask(vpath->handle, msix_id + 1);

		/* enable the alarm vector */
1375 1376 1377
		msix_id = (vpath->handle->vpath->hldev->first_vp_id *
			VXGE_HW_VPATH_MSIX_ACTIVE) + alarm_msix_id;
		vxge_hw_vpath_msix_unmask(vpath->handle, msix_id);
1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
	}
}

/*
 * vxge_vpath_intr_disable
 * @vdev: pointer to vdev
 * @vp_id: vpath for which to disable the interrupts
 *
 * Disables the interrupts for the vpath
*/
1388
static void vxge_vpath_intr_disable(struct vxgedev *vdev, int vp_id)
1389 1390
{
	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
1391
	struct __vxge_hw_device *hldev;
1392 1393
	int msix_id;

1394
	hldev = pci_get_drvdata(vdev->pdev);
1395 1396 1397

	vxge_hw_vpath_wait_receive_idle(hldev, vpath->device_id);

1398 1399 1400 1401 1402
	vxge_hw_vpath_intr_disable(vpath->handle);

	if (vdev->config.intr_type == INTA)
		vxge_hw_vpath_inta_mask_tx_rx(vpath->handle);
	else {
1403
		msix_id = vpath->device_id * VXGE_HW_VPATH_MSIX_ACTIVE;
1404 1405 1406 1407
		vxge_hw_vpath_msix_mask(vpath->handle, msix_id);
		vxge_hw_vpath_msix_mask(vpath->handle, msix_id + 1);

		/* disable the alarm vector */
1408 1409
		msix_id = (vpath->handle->vpath->hldev->first_vp_id *
			VXGE_HW_VPATH_MSIX_ACTIVE) + VXGE_ALARM_MSIX_ID;
1410 1411 1412 1413
		vxge_hw_vpath_msix_mask(vpath->handle, msix_id);
	}
}

J
Jon Mason 已提交
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489
/* list all mac addresses from DA table */
static enum vxge_hw_status
vxge_search_mac_addr_in_da_table(struct vxge_vpath *vpath, struct macInfo *mac)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	unsigned char macmask[ETH_ALEN];
	unsigned char macaddr[ETH_ALEN];

	status = vxge_hw_vpath_mac_addr_get(vpath->handle,
				macaddr, macmask);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"DA config list entry failed for vpath:%d",
			vpath->device_id);
		return status;
	}

	while (memcmp(mac->macaddr, macaddr, ETH_ALEN)) {
		status = vxge_hw_vpath_mac_addr_get_next(vpath->handle,
				macaddr, macmask);
		if (status != VXGE_HW_OK)
			break;
	}

	return status;
}

/* Store all mac addresses from the list to the DA table */
static enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	struct macInfo mac_info;
	u8 *mac_address = NULL;
	struct list_head *entry, *next;

	memset(&mac_info, 0, sizeof(struct macInfo));

	if (vpath->is_open) {
		list_for_each_safe(entry, next, &vpath->mac_addr_list) {
			mac_address =
				(u8 *)&
				((struct vxge_mac_addrs *)entry)->macaddr;
			memcpy(mac_info.macaddr, mac_address, ETH_ALEN);
			((struct vxge_mac_addrs *)entry)->state =
				VXGE_LL_MAC_ADDR_IN_DA_TABLE;
			/* does this mac address already exist in da table? */
			status = vxge_search_mac_addr_in_da_table(vpath,
				&mac_info);
			if (status != VXGE_HW_OK) {
				/* Add this mac address to the DA table */
				status = vxge_hw_vpath_mac_addr_add(
					vpath->handle, mac_info.macaddr,
					mac_info.macmask,
				    VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE);
				if (status != VXGE_HW_OK) {
					vxge_debug_init(VXGE_ERR,
					    "DA add entry failed for vpath:%d",
					    vpath->device_id);
					((struct vxge_mac_addrs *)entry)->state
						= VXGE_LL_MAC_ADDR_IN_LIST;
				}
			}
		}
	}

	return status;
}

/* Store all vlan ids from the list to the vid table */
static enum vxge_hw_status
vxge_restore_vpath_vid_table(struct vxge_vpath *vpath)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxgedev *vdev = vpath->vdev;
	u16 vid;

J
Jiri Pirko 已提交
1490 1491
	if (!vpath->is_open)
		return status;
J
Jon Mason 已提交
1492

J
Jiri Pirko 已提交
1493 1494
	for_each_set_bit(vid, vdev->active_vlans, VLAN_N_VID)
		status = vxge_hw_vpath_vid_add(vpath->handle, vid);
J
Jon Mason 已提交
1495 1496 1497 1498

	return status;
}

1499 1500 1501 1502 1503 1504 1505 1506 1507 1508
/*
 * vxge_reset_vpath
 * @vdev: pointer to vdev
 * @vp_id: vpath to reset
 *
 * Resets the vpath
*/
static int vxge_reset_vpath(struct vxgedev *vdev, int vp_id)
{
	enum vxge_hw_status status = VXGE_HW_OK;
J
Jon Mason 已提交
1509
	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
1510 1511 1512 1513 1514 1515 1516 1517 1518 1519
	int ret = 0;

	/* check if device is down already */
	if (unlikely(!is_vxge_card_up(vdev)))
		return 0;

	/* is device reset already scheduled */
	if (test_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
		return 0;

J
Jon Mason 已提交
1520 1521
	if (vpath->handle) {
		if (vxge_hw_vpath_reset(vpath->handle) == VXGE_HW_OK) {
1522
			if (is_vxge_card_up(vdev) &&
J
Jon Mason 已提交
1523
				vxge_hw_vpath_recover_from_reset(vpath->handle)
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538
					!= VXGE_HW_OK) {
				vxge_debug_init(VXGE_ERR,
					"vxge_hw_vpath_recover_from_reset"
					"failed for vpath:%d", vp_id);
				return status;
			}
		} else {
			vxge_debug_init(VXGE_ERR,
				"vxge_hw_vpath_reset failed for"
				"vpath:%d", vp_id);
				return status;
		}
	} else
		return VXGE_HW_FAIL;

J
Jon Mason 已提交
1539 1540
	vxge_restore_vpath_mac_addr(vpath);
	vxge_restore_vpath_vid_table(vpath);
1541 1542

	/* Enable all broadcast */
J
Jon Mason 已提交
1543 1544 1545 1546 1547 1548 1549 1550 1551 1552
	vxge_hw_vpath_bcast_enable(vpath->handle);

	/* Enable all multicast */
	if (vdev->all_multi_flg) {
		status = vxge_hw_vpath_mcast_enable(vpath->handle);
		if (status != VXGE_HW_OK)
			vxge_debug_init(VXGE_ERR,
				"%s:%d Enabling multicast failed",
				__func__, __LINE__);
	}
1553 1554 1555 1556 1557 1558 1559

	/* Enable the interrupts */
	vxge_vpath_intr_enable(vdev, vp_id);

	smp_wmb();

	/* Enable the flow of traffic through the vpath */
J
Jon Mason 已提交
1560
	vxge_hw_vpath_enable(vpath->handle);
1561 1562

	smp_wmb();
J
Jon Mason 已提交
1563 1564
	vxge_hw_vpath_rx_doorbell_init(vpath->handle);
	vpath->ring.last_status = VXGE_HW_OK;
1565 1566 1567 1568 1569

	/* Vpath reset done */
	clear_bit(vp_id, &vdev->vp_reset);

	/* Start the vpath queue */
J
Jon Mason 已提交
1570 1571
	if (netif_tx_queue_stopped(vpath->fifo.txq))
		netif_tx_wake_queue(vpath->fifo.txq);
1572 1573 1574 1575

	return ret;
}

J
Jon Mason 已提交
1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
/* Configure CI */
static void vxge_config_ci_for_tti_rti(struct vxgedev *vdev)
{
	int i = 0;

	/* Enable CI for RTI */
	if (vdev->config.intr_type == MSI_X) {
		for (i = 0; i < vdev->no_of_vpath; i++) {
			struct __vxge_hw_ring *hw_ring;

			hw_ring = vdev->vpaths[i].ring.handle;
			vxge_hw_vpath_dynamic_rti_ci_set(hw_ring);
		}
	}

	/* Enable CI for TTI */
	for (i = 0; i < vdev->no_of_vpath; i++) {
		struct __vxge_hw_fifo *hw_fifo = vdev->vpaths[i].fifo.handle;
		vxge_hw_vpath_tti_ci_set(hw_fifo);
		/*
		 * For Inta (with or without napi), Set CI ON for only one
		 * vpath. (Have only one free running timer).
		 */
		if ((vdev->config.intr_type == INTA) && (i == 0))
			break;
	}

	return;
}

1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623
static int do_vxge_reset(struct vxgedev *vdev, int event)
{
	enum vxge_hw_status status;
	int ret = 0, vp_id, i;

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_START_RESET)) {
		/* check if device is down already */
		if (unlikely(!is_vxge_card_up(vdev)))
			return 0;

		/* is reset already scheduled */
		if (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
			return 0;
	}

	if (event == VXGE_LL_FULL_RESET) {
J
Jon Mason 已提交
1624 1625
		netif_carrier_off(vdev->ndev);

1626 1627 1628 1629 1630 1631
		/* wait for all the vpath reset to complete */
		for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
			while (test_bit(vp_id, &vdev->vp_reset))
				msleep(50);
		}

J
Jon Mason 已提交
1632 1633
		netif_carrier_on(vdev->ndev);

1634 1635 1636 1637 1638
		/* if execution mode is set to debug, don't reset the adapter */
		if (unlikely(vdev->exec_mode)) {
			vxge_debug_init(VXGE_ERR,
				"%s: execution mode is debug, returning..",
				vdev->ndev->name);
J
Jon Mason 已提交
1639 1640 1641
			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
			netif_tx_stop_all_queues(vdev->ndev);
			return 0;
1642 1643 1644 1645
		}
	}

	if (event == VXGE_LL_FULL_RESET) {
1646
		vxge_hw_device_wait_receive_idle(vdev->devh);
1647 1648 1649 1650
		vxge_hw_device_intr_disable(vdev->devh);

		switch (vdev->cric_err_event) {
		case VXGE_HW_EVENT_UNKNOWN:
J
Jon Mason 已提交
1651
			netif_tx_stop_all_queues(vdev->ndev);
1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671
			vxge_debug_init(VXGE_ERR,
				"fatal: %s: Disabling device due to"
				"unknown error",
				vdev->ndev->name);
			ret = -EPERM;
			goto out;
		case VXGE_HW_EVENT_RESET_START:
			break;
		case VXGE_HW_EVENT_RESET_COMPLETE:
		case VXGE_HW_EVENT_LINK_DOWN:
		case VXGE_HW_EVENT_LINK_UP:
		case VXGE_HW_EVENT_ALARM_CLEARED:
		case VXGE_HW_EVENT_ECCERR:
		case VXGE_HW_EVENT_MRPCIM_ECCERR:
			ret = -EPERM;
			goto out;
		case VXGE_HW_EVENT_FIFO_ERR:
		case VXGE_HW_EVENT_VPATH_ERR:
			break;
		case VXGE_HW_EVENT_CRITICAL_ERR:
J
Jon Mason 已提交
1672
			netif_tx_stop_all_queues(vdev->ndev);
1673 1674 1675 1676 1677 1678 1679 1680 1681
			vxge_debug_init(VXGE_ERR,
				"fatal: %s: Disabling device due to"
				"serious error",
				vdev->ndev->name);
			/* SOP or device reset required */
			/* This event is not currently used */
			ret = -EPERM;
			goto out;
		case VXGE_HW_EVENT_SERR:
J
Jon Mason 已提交
1682
			netif_tx_stop_all_queues(vdev->ndev);
1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693
			vxge_debug_init(VXGE_ERR,
				"fatal: %s: Disabling device due to"
				"serious error",
				vdev->ndev->name);
			ret = -EPERM;
			goto out;
		case VXGE_HW_EVENT_SRPCIM_SERR:
		case VXGE_HW_EVENT_MRPCIM_SERR:
			ret = -EPERM;
			goto out;
		case VXGE_HW_EVENT_SLOT_FREEZE:
J
Jon Mason 已提交
1694
			netif_tx_stop_all_queues(vdev->ndev);
1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707
			vxge_debug_init(VXGE_ERR,
				"fatal: %s: Disabling device due to"
				"slot freeze",
				vdev->ndev->name);
			ret = -EPERM;
			goto out;
		default:
			break;

		}
	}

	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_START_RESET))
J
Jon Mason 已提交
1708
		netif_tx_stop_all_queues(vdev->ndev);
1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767

	if (event == VXGE_LL_FULL_RESET) {
		status = vxge_reset_all_vpaths(vdev);
		if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR,
				"fatal: %s: can not reset vpaths",
				vdev->ndev->name);
			ret = -EPERM;
			goto out;
		}
	}

	if (event == VXGE_LL_COMPL_RESET) {
		for (i = 0; i < vdev->no_of_vpath; i++)
			if (vdev->vpaths[i].handle) {
				if (vxge_hw_vpath_recover_from_reset(
					vdev->vpaths[i].handle)
						!= VXGE_HW_OK) {
					vxge_debug_init(VXGE_ERR,
						"vxge_hw_vpath_recover_"
						"from_reset failed for vpath: "
						"%d", i);
					ret = -EPERM;
					goto out;
				}
				} else {
					vxge_debug_init(VXGE_ERR,
					"vxge_hw_vpath_reset failed for "
						"vpath:%d", i);
					ret = -EPERM;
					goto out;
				}
	}

	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_COMPL_RESET)) {
		/* Reprogram the DA table with populated mac addresses */
		for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
			vxge_restore_vpath_mac_addr(&vdev->vpaths[vp_id]);
			vxge_restore_vpath_vid_table(&vdev->vpaths[vp_id]);
		}

		/* enable vpath interrupts */
		for (i = 0; i < vdev->no_of_vpath; i++)
			vxge_vpath_intr_enable(vdev, i);

		vxge_hw_device_intr_enable(vdev->devh);

		smp_wmb();

		/* Indicate card up */
		set_bit(__VXGE_STATE_CARD_UP, &vdev->state);

		/* Get the traffic to flow through the vpaths */
		for (i = 0; i < vdev->no_of_vpath; i++) {
			vxge_hw_vpath_enable(vdev->vpaths[i].handle);
			smp_wmb();
			vxge_hw_vpath_rx_doorbell_init(vdev->vpaths[i].handle);
		}

J
Jon Mason 已提交
1768
		netif_tx_wake_all_queues(vdev->ndev);
1769 1770
	}

J
Jon Mason 已提交
1771 1772 1773
	/* configure CI */
	vxge_config_ci_for_tti_rti(vdev);

1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789
out:
	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);

	/* Indicate reset done */
	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_COMPL_RESET))
		clear_bit(__VXGE_STATE_RESET_CARD, &vdev->state);
	return ret;
}

/*
 * vxge_reset
 * @vdev: pointer to ll device
 *
 * driver may reset the chip on events of serr, eccerr, etc
 */
J
Jon Mason 已提交
1790
static void vxge_reset(struct work_struct *work)
1791
{
J
Jon Mason 已提交
1792 1793 1794 1795 1796 1797
	struct vxgedev *vdev = container_of(work, struct vxgedev, reset_task);

	if (!netif_running(vdev->ndev))
		return;

	do_vxge_reset(vdev, VXGE_LL_FULL_RESET);
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813
}

/**
 * vxge_poll - Receive handler when Receive Polling is used.
 * @dev: pointer to the device structure.
 * @budget: Number of packets budgeted to be processed in this iteration.
 *
 * This function comes into picture only if Receive side is being handled
 * through polling (called NAPI in linux). It mostly does what the normal
 * Rx interrupt handler does in terms of descriptor and packet processing
 * but not in an interrupt context. Also it will process a specified number
 * of packets at most in one iteration. This value is passed down by the
 * kernel as the function argument 'budget'.
 */
static int vxge_poll_msix(struct napi_struct *napi, int budget)
{
J
Jon Mason 已提交
1814 1815
	struct vxge_ring *ring = container_of(napi, struct vxge_ring, napi);
	int pkts_processed;
1816 1817
	int budget_org = budget;

J
Jon Mason 已提交
1818 1819
	ring->budget = budget;
	ring->pkts_processed = 0;
1820
	vxge_hw_vpath_poll_rx(ring->handle);
J
Jon Mason 已提交
1821
	pkts_processed = ring->pkts_processed;
1822 1823 1824

	if (ring->pkts_processed < budget_org) {
		napi_complete(napi);
J
Jon Mason 已提交
1825

1826 1827 1828 1829
		/* Re enable the Rx interrupts for the vpath */
		vxge_hw_channel_msix_unmask(
				(struct __vxge_hw_channel *)ring->handle,
				ring->rx_vector_no);
J
Jon Mason 已提交
1830
		mmiowb();
1831 1832
	}

J
Jon Mason 已提交
1833 1834 1835 1836
	/* We are copying and returning the local variable, in case if after
	 * clearing the msix interrupt above, if the interrupt fires right
	 * away which can preempt this NAPI thread */
	return pkts_processed;
1837 1838 1839 1840 1841 1842 1843 1844 1845 1846
}

static int vxge_poll_inta(struct napi_struct *napi, int budget)
{
	struct vxgedev *vdev = container_of(napi, struct vxgedev, napi);
	int pkts_processed = 0;
	int i;
	int budget_org = budget;
	struct vxge_ring *ring;

1847
	struct __vxge_hw_device *hldev = pci_get_drvdata(vdev->pdev);
1848 1849 1850 1851

	for (i = 0; i < vdev->no_of_vpath; i++) {
		ring = &vdev->vpaths[i].ring;
		ring->budget = budget;
J
Jon Mason 已提交
1852
		ring->pkts_processed = 0;
1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883
		vxge_hw_vpath_poll_rx(ring->handle);
		pkts_processed += ring->pkts_processed;
		budget -= ring->pkts_processed;
		if (budget <= 0)
			break;
	}

	VXGE_COMPLETE_ALL_TX(vdev);

	if (pkts_processed < budget_org) {
		napi_complete(napi);
		/* Re enable the Rx interrupts for the ring */
		vxge_hw_device_unmask_all(hldev);
		vxge_hw_device_flush_io(hldev);
	}

	return pkts_processed;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
/**
 * vxge_netpoll - netpoll event handler entry point
 * @dev : pointer to the device structure.
 * Description:
 *      This function will be called by upper layer to check for events on the
 * interface in situations where interrupts are disabled. It is used for
 * specific in-kernel networking tasks, such as remote consoles and kernel
 * debugging over the network (example netdump in RedHat).
 */
static void vxge_netpoll(struct net_device *dev)
{
J
Jon Mason 已提交
1884
	struct __vxge_hw_device *hldev;
1885 1886
	struct vxgedev *vdev;

1887
	vdev = netdev_priv(dev);
1888
	hldev = pci_get_drvdata(vdev->pdev);
1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

	if (pci_channel_offline(vdev->pdev))
		return;

	disable_irq(dev->irq);
	vxge_hw_device_clear_tx_rx(hldev);

	vxge_hw_device_clear_tx_rx(hldev);
	VXGE_COMPLETE_ALL_RX(vdev);
	VXGE_COMPLETE_ALL_TX(vdev);

	enable_irq(dev->irq);

	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);
}
#endif

/* RTH configuration */
static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev)
{
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxge_hw_rth_hash_types hash_types;
	u8 itable[256] = {0}; /* indirection table */
	u8 mtable[256] = {0}; /* CPU to vpath mapping  */
	int index;

	/*
	 * Filling
	 * 	- itable with bucket numbers
	 * 	- mtable with bucket-to-vpath mapping
	 */
	for (index = 0; index < (1 << vdev->config.rth_bkt_sz); index++) {
		itable[index] = index;
		mtable[index] = index % vdev->no_of_vpath;
	}

	/* set indirection table, bucket-to-vpath mapping */
	status = vxge_hw_vpath_rts_rth_itable_set(vdev->vp_handles,
						vdev->no_of_vpath,
						mtable, itable,
						vdev->config.rth_bkt_sz);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"RTH indirection table configuration failed "
			"for vpath:%d", vdev->vpaths[0].device_id);
		return status;
	}

J
Jon Mason 已提交
1940 1941 1942 1943 1944 1945 1946 1947 1948
	/* Fill RTH hash types */
	hash_types.hash_type_tcpipv4_en   = vdev->config.rth_hash_type_tcpipv4;
	hash_types.hash_type_ipv4_en      = vdev->config.rth_hash_type_ipv4;
	hash_types.hash_type_tcpipv6_en   = vdev->config.rth_hash_type_tcpipv6;
	hash_types.hash_type_ipv6_en      = vdev->config.rth_hash_type_ipv6;
	hash_types.hash_type_tcpipv6ex_en =
					vdev->config.rth_hash_type_tcpipv6ex;
	hash_types.hash_type_ipv6ex_en    = vdev->config.rth_hash_type_ipv6ex;

1949
	/*
J
Jon Mason 已提交
1950 1951 1952 1953 1954
	 * Because the itable_set() method uses the active_table field
	 * for the target virtual path the RTH config should be updated
	 * for all VPATHs. The h/w only uses the lowest numbered VPATH
	 * when steering frames.
	 */
1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972
	 for (index = 0; index < vdev->no_of_vpath; index++) {
		status = vxge_hw_vpath_rts_rth_set(
				vdev->vpaths[index].handle,
				vdev->config.rth_algorithm,
				&hash_types,
				vdev->config.rth_bkt_sz);
		 if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR,
				"RTH configuration failed for vpath:%d",
				vdev->vpaths[index].device_id);
			return status;
		 }
	 }

	return status;
}

/* reset vpaths */
1973
enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev)
1974 1975
{
	enum vxge_hw_status status = VXGE_HW_OK;
J
Jon Mason 已提交
1976 1977
	struct vxge_vpath *vpath;
	int i;
1978

J
Jon Mason 已提交
1979 1980 1981 1982
	for (i = 0; i < vdev->no_of_vpath; i++) {
		vpath = &vdev->vpaths[i];
		if (vpath->handle) {
			if (vxge_hw_vpath_reset(vpath->handle) == VXGE_HW_OK) {
1983 1984
				if (is_vxge_card_up(vdev) &&
					vxge_hw_vpath_recover_from_reset(
J
Jon Mason 已提交
1985
						vpath->handle) != VXGE_HW_OK) {
1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998
					vxge_debug_init(VXGE_ERR,
						"vxge_hw_vpath_recover_"
						"from_reset failed for vpath: "
						"%d", i);
					return status;
				}
			} else {
				vxge_debug_init(VXGE_ERR,
					"vxge_hw_vpath_reset failed for "
					"vpath:%d", i);
					return status;
			}
		}
J
Jon Mason 已提交
1999 2000
	}

2001 2002 2003 2004
	return status;
}

/* close vpaths */
2005
static void vxge_close_vpaths(struct vxgedev *vdev, int index)
2006
{
J
Jon Mason 已提交
2007
	struct vxge_vpath *vpath;
2008
	int i;
J
Jon Mason 已提交
2009

2010
	for (i = index; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2011 2012 2013 2014
		vpath = &vdev->vpaths[i];

		if (vpath->handle && vpath->is_open) {
			vxge_hw_vpath_close(vpath->handle);
2015 2016
			vdev->stats.vpaths_open--;
		}
J
Jon Mason 已提交
2017 2018
		vpath->is_open = 0;
		vpath->handle = NULL;
2019 2020 2021 2022
	}
}

/* open vpaths */
2023
static int vxge_open_vpaths(struct vxgedev *vdev)
2024
{
J
Jon Mason 已提交
2025
	struct vxge_hw_vpath_attr attr;
2026
	enum vxge_hw_status status;
J
Jon Mason 已提交
2027
	struct vxge_vpath *vpath;
2028
	u32 vp_id = 0;
J
Jon Mason 已提交
2029
	int i;
2030 2031

	for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2032 2033
		vpath = &vdev->vpaths[i];
		vxge_assert(vpath->is_configured);
J
Jon Mason 已提交
2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049

		if (!vdev->titan1) {
			struct vxge_hw_vp_config *vcfg;
			vcfg = &vdev->devh->config.vp_config[vpath->device_id];

			vcfg->rti.urange_a = RTI_T1A_RX_URANGE_A;
			vcfg->rti.urange_b = RTI_T1A_RX_URANGE_B;
			vcfg->rti.urange_c = RTI_T1A_RX_URANGE_C;
			vcfg->tti.uec_a = TTI_T1A_TX_UFC_A;
			vcfg->tti.uec_b = TTI_T1A_TX_UFC_B;
			vcfg->tti.uec_c = TTI_T1A_TX_UFC_C(vdev->mtu);
			vcfg->tti.uec_d = TTI_T1A_TX_UFC_D(vdev->mtu);
			vcfg->tti.ltimer_val = VXGE_T1A_TTI_LTIMER_VAL;
			vcfg->tti.rtimer_val = VXGE_T1A_TTI_RTIMER_VAL;
		}

J
Jon Mason 已提交
2050
		attr.vp_id = vpath->device_id;
2051 2052 2053
		attr.fifo_attr.callback = vxge_xmit_compl;
		attr.fifo_attr.txdl_term = vxge_tx_term;
		attr.fifo_attr.per_txdl_space = sizeof(struct vxge_tx_priv);
J
Jon Mason 已提交
2054
		attr.fifo_attr.userdata = &vpath->fifo;
2055 2056 2057 2058 2059

		attr.ring_attr.callback = vxge_rx_1b_compl;
		attr.ring_attr.rxd_init = vxge_rx_initial_replenish;
		attr.ring_attr.rxd_term = vxge_rx_term;
		attr.ring_attr.per_rxd_space = sizeof(struct vxge_rx_priv);
J
Jon Mason 已提交
2060
		attr.ring_attr.userdata = &vpath->ring;
2061

J
Jon Mason 已提交
2062 2063
		vpath->ring.ndev = vdev->ndev;
		vpath->ring.pdev = vdev->pdev;
J
Jon Mason 已提交
2064

J
Jon Mason 已提交
2065
		status = vxge_hw_vpath_open(vdev->devh, &attr, &vpath->handle);
2066
		if (status == VXGE_HW_OK) {
J
Jon Mason 已提交
2067
			vpath->fifo.handle =
2068
			    (struct __vxge_hw_fifo *)attr.fifo_attr.userdata;
J
Jon Mason 已提交
2069
			vpath->ring.handle =
2070
			    (struct __vxge_hw_ring *)attr.ring_attr.userdata;
J
Jon Mason 已提交
2071
			vpath->fifo.tx_steering_type =
2072
				vdev->config.tx_steering_type;
J
Jon Mason 已提交
2073 2074
			vpath->fifo.ndev = vdev->ndev;
			vpath->fifo.pdev = vdev->pdev;
J
Jon Mason 已提交
2075 2076 2077 2078 2079 2080
			if (vdev->config.tx_steering_type)
				vpath->fifo.txq =
					netdev_get_tx_queue(vdev->ndev, i);
			else
				vpath->fifo.txq =
					netdev_get_tx_queue(vdev->ndev, 0);
J
Jon Mason 已提交
2081
			vpath->fifo.indicate_max_pkts =
2082
				vdev->config.fifo_indicate_max_pkts;
J
Jon Mason 已提交
2083
			vpath->fifo.tx_vector_no = 0;
J
Jon Mason 已提交
2084
			vpath->ring.rx_vector_no = 0;
2085
			vpath->ring.rx_hwts = vdev->rx_hwts;
J
Jon Mason 已提交
2086 2087 2088
			vpath->is_open = 1;
			vdev->vp_handles[i] = vpath->handle;
			vpath->ring.vlan_tag_strip = vdev->vlan_tag_strip;
2089 2090 2091
			vdev->stats.vpaths_open++;
		} else {
			vdev->stats.vpath_open_fail++;
J
Jon Mason 已提交
2092 2093 2094 2095
			vxge_debug_init(VXGE_ERR, "%s: vpath: %d failed to "
					"open with status: %d",
					vdev->ndev->name, vpath->device_id,
					status);
2096 2097 2098 2099
			vxge_close_vpaths(vdev, 0);
			return -EPERM;
		}

J
Jon Mason 已提交
2100
		vp_id = vpath->handle->vpath->vp_id;
2101 2102
		vdev->vpaths_deployed |= vxge_mBIT(vp_id);
	}
J
Jon Mason 已提交
2103

2104 2105 2106
	return VXGE_HW_OK;
}

J
Jon Mason 已提交
2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161
/**
 *  adaptive_coalesce_tx_interrupts - Changes the interrupt coalescing
 *  if the interrupts are not within a range
 *  @fifo: pointer to transmit fifo structure
 *  Description: The function changes boundary timer and restriction timer
 *  value depends on the traffic
 *  Return Value: None
 */
static void adaptive_coalesce_tx_interrupts(struct vxge_fifo *fifo)
{
	fifo->interrupt_count++;
	if (jiffies > fifo->jiffies + HZ / 100) {
		struct __vxge_hw_fifo *hw_fifo = fifo->handle;

		fifo->jiffies = jiffies;
		if (fifo->interrupt_count > VXGE_T1A_MAX_TX_INTERRUPT_COUNT &&
		    hw_fifo->rtimer != VXGE_TTI_RTIMER_ADAPT_VAL) {
			hw_fifo->rtimer = VXGE_TTI_RTIMER_ADAPT_VAL;
			vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo);
		} else if (hw_fifo->rtimer != 0) {
			hw_fifo->rtimer = 0;
			vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo);
		}
		fifo->interrupt_count = 0;
	}
}

/**
 *  adaptive_coalesce_rx_interrupts - Changes the interrupt coalescing
 *  if the interrupts are not within a range
 *  @ring: pointer to receive ring structure
 *  Description: The function increases of decreases the packet counts within
 *  the ranges of traffic utilization, if the interrupts due to this ring are
 *  not within a fixed range.
 *  Return Value: Nothing
 */
static void adaptive_coalesce_rx_interrupts(struct vxge_ring *ring)
{
	ring->interrupt_count++;
	if (jiffies > ring->jiffies + HZ / 100) {
		struct __vxge_hw_ring *hw_ring = ring->handle;

		ring->jiffies = jiffies;
		if (ring->interrupt_count > VXGE_T1A_MAX_INTERRUPT_COUNT &&
		    hw_ring->rtimer != VXGE_RTI_RTIMER_ADAPT_VAL) {
			hw_ring->rtimer = VXGE_RTI_RTIMER_ADAPT_VAL;
			vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring);
		} else if (hw_ring->rtimer != 0) {
			hw_ring->rtimer = 0;
			vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring);
		}
		ring->interrupt_count = 0;
	}
}

2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174
/*
 *  vxge_isr_napi
 *  @irq: the irq of the device.
 *  @dev_id: a void pointer to the hldev structure of the Titan device
 *  @ptregs: pointer to the registers pushed on the stack.
 *
 *  This function is the ISR handler of the device when napi is enabled. It
 *  identifies the reason for the interrupt and calls the relevant service
 *  routines.
 */
static irqreturn_t vxge_isr_napi(int irq, void *dev_id)
{
	struct net_device *dev;
S
Sreenivasa Honnur 已提交
2175
	struct __vxge_hw_device *hldev;
2176 2177
	u64 reason;
	enum vxge_hw_status status;
J
Jon Mason 已提交
2178
	struct vxgedev *vdev = (struct vxgedev *)dev_id;
2179 2180 2181

	vxge_debug_intr(VXGE_TRACE, "%s:%d", __func__, __LINE__);

S
Sreenivasa Honnur 已提交
2182
	dev = vdev->ndev;
2183
	hldev = pci_get_drvdata(vdev->pdev);
2184 2185 2186 2187 2188

	if (pci_channel_offline(vdev->pdev))
		return IRQ_NONE;

	if (unlikely(!is_vxge_card_up(vdev)))
2189
		return IRQ_HANDLED;
2190

J
Jon Mason 已提交
2191
	status = vxge_hw_device_begin_irq(hldev, vdev->exec_mode, &reason);
2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221
	if (status == VXGE_HW_OK) {
		vxge_hw_device_mask_all(hldev);

		if (reason &
			VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_TRAFFIC_INT(
			vdev->vpaths_deployed >>
			(64 - VXGE_HW_MAX_VIRTUAL_PATHS))) {

			vxge_hw_device_clear_tx_rx(hldev);
			napi_schedule(&vdev->napi);
			vxge_debug_intr(VXGE_TRACE,
				"%s:%d  Exiting...", __func__, __LINE__);
			return IRQ_HANDLED;
		} else
			vxge_hw_device_unmask_all(hldev);
	} else if (unlikely((status == VXGE_HW_ERR_VPATH) ||
		(status == VXGE_HW_ERR_CRITICAL) ||
		(status == VXGE_HW_ERR_FIFO))) {
		vxge_hw_device_mask_all(hldev);
		vxge_hw_device_flush_io(hldev);
		return IRQ_HANDLED;
	} else if (unlikely(status == VXGE_HW_ERR_SLOT_FREEZE))
		return IRQ_HANDLED;

	vxge_debug_intr(VXGE_TRACE, "%s:%d  Exiting...", __func__, __LINE__);
	return IRQ_NONE;
}

#ifdef CONFIG_PCI_MSI

J
Jon Mason 已提交
2222
static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
2223 2224 2225
{
	struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id;

J
Jon Mason 已提交
2226 2227 2228 2229 2230 2231 2232 2233
	adaptive_coalesce_tx_interrupts(fifo);

	vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)fifo->handle,
				  fifo->tx_vector_no);

	vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)fifo->handle,
				   fifo->tx_vector_no);

2234 2235
	VXGE_COMPLETE_VPATH_TX(fifo);

J
Jon Mason 已提交
2236 2237 2238 2239 2240
	vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle,
				    fifo->tx_vector_no);

	mmiowb();

2241 2242 2243
	return IRQ_HANDLED;
}

J
Jon Mason 已提交
2244
static irqreturn_t vxge_rx_msix_napi_handle(int irq, void *dev_id)
2245 2246 2247
{
	struct vxge_ring *ring = (struct vxge_ring *)dev_id;

J
Jon Mason 已提交
2248 2249
	adaptive_coalesce_rx_interrupts(ring);

2250
	vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)ring->handle,
J
Jon Mason 已提交
2251 2252 2253 2254
				  ring->rx_vector_no);

	vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)ring->handle,
				   ring->rx_vector_no);
2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266

	napi_schedule(&ring->napi);
	return IRQ_HANDLED;
}

static irqreturn_t
vxge_alarm_msix_handle(int irq, void *dev_id)
{
	int i;
	enum vxge_hw_status status;
	struct vxge_vpath *vpath = (struct vxge_vpath *)dev_id;
	struct vxgedev *vdev = vpath->vdev;
2267 2268
	int msix_id = (vpath->handle->vpath->vp_id *
		VXGE_HW_VPATH_MSIX_ACTIVE) + VXGE_ALARM_MSIX_ID;
2269 2270

	for (i = 0; i < vdev->no_of_vpath; i++) {
L
Lucas De Marchi 已提交
2271
		/* Reduce the chance of losing alarm interrupts by masking
J
Jon Mason 已提交
2272 2273 2274
		 * the vector. A pending bit will be set if an alarm is
		 * generated and on unmask the interrupt will be fired.
		 */
2275
		vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id);
J
Jon Mason 已提交
2276 2277
		vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id);
		mmiowb();
2278 2279 2280 2281 2282

		status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle,
			vdev->exec_mode);
		if (status == VXGE_HW_OK) {
			vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle,
J
Jon Mason 已提交
2283 2284
						  msix_id);
			mmiowb();
2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296
			continue;
		}
		vxge_debug_intr(VXGE_ERR,
			"%s: vxge_hw_vpath_alarm_process failed %x ",
			VXGE_DRIVER_NAME, status);
	}
	return IRQ_HANDLED;
}

static int vxge_alloc_msix(struct vxgedev *vdev)
{
	int j, i, ret = 0;
2297
	int msix_intr_vect = 0, temp;
2298 2299
	vdev->intr_cnt = 0;

2300
start:
2301 2302 2303 2304 2305 2306
	/* Tx/Rx MSIX Vectors count */
	vdev->intr_cnt = vdev->no_of_vpath * 2;

	/* Alarm MSIX Vectors count */
	vdev->intr_cnt++;

2307 2308
	vdev->entries = kcalloc(vdev->intr_cnt, sizeof(struct msix_entry),
				GFP_KERNEL);
2309 2310 2311 2312
	if (!vdev->entries) {
		vxge_debug_init(VXGE_ERR,
			"%s: memory allocation failed",
			VXGE_DRIVER_NAME);
2313 2314
		ret = -ENOMEM;
		goto alloc_entries_failed;
2315 2316
	}

2317 2318 2319
	vdev->vxge_entries = kcalloc(vdev->intr_cnt,
				     sizeof(struct vxge_msix_entry),
				     GFP_KERNEL);
2320 2321 2322
	if (!vdev->vxge_entries) {
		vxge_debug_init(VXGE_ERR, "%s: memory allocation failed",
			VXGE_DRIVER_NAME);
2323 2324
		ret = -ENOMEM;
		goto alloc_vxge_entries_failed;
2325 2326
	}

2327
	for (i = 0, j = 0; i < vdev->no_of_vpath; i++) {
2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344

		msix_intr_vect = i * VXGE_HW_VPATH_MSIX_ACTIVE;

		/* Initialize the fifo vector */
		vdev->entries[j].entry = msix_intr_vect;
		vdev->vxge_entries[j].entry = msix_intr_vect;
		vdev->vxge_entries[j].in_use = 0;
		j++;

		/* Initialize the ring vector */
		vdev->entries[j].entry = msix_intr_vect + 1;
		vdev->vxge_entries[j].entry = msix_intr_vect + 1;
		vdev->vxge_entries[j].in_use = 0;
		j++;
	}

	/* Initialize the alarm vector */
2345 2346
	vdev->entries[j].entry = VXGE_ALARM_MSIX_ID;
	vdev->vxge_entries[j].entry = VXGE_ALARM_MSIX_ID;
2347 2348
	vdev->vxge_entries[j].in_use = 0;

2349 2350
	ret = pci_enable_msix(vdev->pdev, vdev->entries, vdev->intr_cnt);
	if (ret > 0) {
2351 2352
		vxge_debug_init(VXGE_ERR,
			"%s: MSI-X enable failed for %d vectors, ret: %d",
2353
			VXGE_DRIVER_NAME, vdev->intr_cnt, ret);
2354 2355 2356 2357 2358
		if ((max_config_vpath != VXGE_USE_DEFAULT) || (ret < 3)) {
			ret = -ENODEV;
			goto enable_msix_failed;
		}

2359 2360 2361 2362
		kfree(vdev->entries);
		kfree(vdev->vxge_entries);
		vdev->entries = NULL;
		vdev->vxge_entries = NULL;
2363 2364 2365 2366 2367
		/* Try with less no of vector by reducing no of vpaths count */
		temp = (ret - 1)/2;
		vxge_close_vpaths(vdev, temp);
		vdev->no_of_vpath = temp;
		goto start;
2368 2369 2370 2371
	} else if (ret < 0) {
		ret = -ENODEV;
		goto enable_msix_failed;
	}
2372
	return 0;
2373 2374 2375 2376 2377 2378 2379

enable_msix_failed:
	kfree(vdev->vxge_entries);
alloc_vxge_entries_failed:
	kfree(vdev->entries);
alloc_entries_failed:
	return ret;
2380 2381 2382 2383 2384 2385 2386
}

static int vxge_enable_msix(struct vxgedev *vdev)
{

	int i, ret = 0;
	/* 0 - Tx, 1 - Rx  */
2387 2388
	int tim_msix_id[4] = {0, 1, 0, 0};

2389 2390 2391 2392 2393 2394
	vdev->intr_cnt = 0;

	/* allocate msix vectors */
	ret = vxge_alloc_msix(vdev);
	if (!ret) {
		for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2395
			struct vxge_vpath *vpath = &vdev->vpaths[i];
2396

J
Jon Mason 已提交
2397 2398 2399 2400 2401
			/* If fifo or ring are not enabled, the MSIX vector for
			 * it should be set to 0.
			 */
			vpath->ring.rx_vector_no = (vpath->device_id *
						VXGE_HW_VPATH_MSIX_ACTIVE) + 1;
2402

J
Jon Mason 已提交
2403 2404 2405
			vpath->fifo.tx_vector_no = (vpath->device_id *
						VXGE_HW_VPATH_MSIX_ACTIVE);

J
Jon Mason 已提交
2406 2407
			vxge_hw_vpath_msix_set(vpath->handle, tim_msix_id,
					       VXGE_ALARM_MSIX_ID);
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417
		}
	}

	return ret;
}

static void vxge_rem_msix_isr(struct vxgedev *vdev)
{
	int intr_cnt;

2418
	for (intr_cnt = 0; intr_cnt < (vdev->no_of_vpath * 2 + 1);
2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439
		intr_cnt++) {
		if (vdev->vxge_entries[intr_cnt].in_use) {
			synchronize_irq(vdev->entries[intr_cnt].vector);
			free_irq(vdev->entries[intr_cnt].vector,
				vdev->vxge_entries[intr_cnt].arg);
			vdev->vxge_entries[intr_cnt].in_use = 0;
		}
	}

	kfree(vdev->entries);
	kfree(vdev->vxge_entries);
	vdev->entries = NULL;
	vdev->vxge_entries = NULL;

	if (vdev->config.intr_type == MSI_X)
		pci_disable_msix(vdev->pdev);
}
#endif

static void vxge_rem_isr(struct vxgedev *vdev)
{
J
Jon Mason 已提交
2440
	struct __vxge_hw_device *hldev;
2441
	hldev = pci_get_drvdata(vdev->pdev);
2442 2443 2444 2445 2446 2447 2448 2449

#ifdef CONFIG_PCI_MSI
	if (vdev->config.intr_type == MSI_X) {
		vxge_rem_msix_isr(vdev);
	} else
#endif
	if (vdev->config.intr_type == INTA) {
			synchronize_irq(vdev->pdev->irq);
S
Sreenivasa Honnur 已提交
2450
			free_irq(vdev->pdev->irq, vdev);
2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466
	}
}

static int vxge_add_isr(struct vxgedev *vdev)
{
	int ret = 0;
#ifdef CONFIG_PCI_MSI
	int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0;
	int pci_fun = PCI_FUNC(vdev->pdev->devfn);

	if (vdev->config.intr_type == MSI_X)
		ret = vxge_enable_msix(vdev);

	if (ret) {
		vxge_debug_init(VXGE_ERR,
			"%s: Enabling MSI-X Failed", VXGE_DRIVER_NAME);
2467 2468 2469
		vxge_debug_init(VXGE_ERR,
			"%s: Defaulting to INTA", VXGE_DRIVER_NAME);
		vdev->config.intr_type = INTA;
2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482
	}

	if (vdev->config.intr_type == MSI_X) {
		for (intr_idx = 0;
		     intr_idx < (vdev->no_of_vpath *
			VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) {

			msix_idx = intr_idx % VXGE_HW_VPATH_MSIX_ACTIVE;
			irq_req = 0;

			switch (msix_idx) {
			case 0:
				snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
2483 2484 2485 2486
				"%s:vxge:MSI-X %d - Tx - fn:%d vpath:%d",
					vdev->ndev->name,
					vdev->entries[intr_cnt].entry,
					pci_fun, vp_idx);
2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497
				ret = request_irq(
				    vdev->entries[intr_cnt].vector,
					vxge_tx_msix_handle, 0,
					vdev->desc[intr_cnt],
					&vdev->vpaths[vp_idx].fifo);
					vdev->vxge_entries[intr_cnt].arg =
						&vdev->vpaths[vp_idx].fifo;
				irq_req = 1;
				break;
			case 1:
				snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
2498 2499 2500 2501
				"%s:vxge:MSI-X %d - Rx - fn:%d vpath:%d",
					vdev->ndev->name,
					vdev->entries[intr_cnt].entry,
					pci_fun, vp_idx);
2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518
				ret = request_irq(
				    vdev->entries[intr_cnt].vector,
					vxge_rx_msix_napi_handle,
					0,
					vdev->desc[intr_cnt],
					&vdev->vpaths[vp_idx].ring);
					vdev->vxge_entries[intr_cnt].arg =
						&vdev->vpaths[vp_idx].ring;
				irq_req = 1;
				break;
			}

			if (ret) {
				vxge_debug_init(VXGE_ERR,
					"%s: MSIX - %d  Registration failed",
					vdev->ndev->name, intr_cnt);
				vxge_rem_msix_isr(vdev);
2519 2520 2521 2522
				vdev->config.intr_type = INTA;
				vxge_debug_init(VXGE_ERR,
					"%s: Defaulting to INTA"
					, vdev->ndev->name);
2523 2524 2525 2526 2527 2528
					goto INTA_MODE;
			}

			if (irq_req) {
				/* We requested for this msix interrupt */
				vdev->vxge_entries[intr_cnt].in_use = 1;
2529 2530
				msix_idx +=  vdev->vpaths[vp_idx].device_id *
					VXGE_HW_VPATH_MSIX_ACTIVE;
2531 2532
				vxge_hw_vpath_msix_unmask(
					vdev->vpaths[vp_idx].handle,
2533
					msix_idx);
2534 2535 2536 2537
				intr_cnt++;
			}

			/* Point to next vpath handler */
2538 2539 2540
			if (((intr_idx + 1) % VXGE_HW_VPATH_MSIX_ACTIVE == 0) &&
			    (vp_idx < (vdev->no_of_vpath - 1)))
				vp_idx++;
2541 2542
		}

2543
		intr_cnt = vdev->no_of_vpath * 2;
2544
		snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
2545 2546 2547 2548
			"%s:vxge:MSI-X %d - Alarm - fn:%d",
			vdev->ndev->name,
			vdev->entries[intr_cnt].entry,
			pci_fun);
2549 2550 2551 2552
		/* For Alarm interrupts */
		ret = request_irq(vdev->entries[intr_cnt].vector,
					vxge_alarm_msix_handle, 0,
					vdev->desc[intr_cnt],
2553
					&vdev->vpaths[0]);
2554 2555 2556 2557 2558
		if (ret) {
			vxge_debug_init(VXGE_ERR,
				"%s: MSIX - %d Registration failed",
				vdev->ndev->name, intr_cnt);
			vxge_rem_msix_isr(vdev);
2559 2560 2561 2562
			vdev->config.intr_type = INTA;
			vxge_debug_init(VXGE_ERR,
				"%s: Defaulting to INTA",
				vdev->ndev->name);
2563 2564 2565
				goto INTA_MODE;
		}

2566 2567
		msix_idx = (vdev->vpaths[0].handle->vpath->vp_id *
			VXGE_HW_VPATH_MSIX_ACTIVE) + VXGE_ALARM_MSIX_ID;
2568
		vxge_hw_vpath_msix_unmask(vdev->vpaths[vp_idx].handle,
2569
					msix_idx);
2570
		vdev->vxge_entries[intr_cnt].in_use = 1;
2571
		vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[0];
2572 2573 2574 2575 2576
	}
INTA_MODE:
#endif

	if (vdev->config.intr_type == INTA) {
2577 2578
		snprintf(vdev->desc[0], VXGE_INTR_STRLEN,
			"%s:vxge:INTA", vdev->ndev->name);
2579 2580
		vxge_hw_device_set_intr_type(vdev->devh,
			VXGE_HW_INTR_MODE_IRQLINE);
J
Jon Mason 已提交
2581 2582 2583

		vxge_hw_vpath_tti_ci_set(vdev->vpaths[0].fifo.handle);

2584 2585
		ret = request_irq((int) vdev->pdev->irq,
			vxge_isr_napi,
S
Sreenivasa Honnur 已提交
2586
			IRQF_SHARED, vdev->desc[0], vdev);
2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623
		if (ret) {
			vxge_debug_init(VXGE_ERR,
				"%s %s-%d: ISR registration failed",
				VXGE_DRIVER_NAME, "IRQ", vdev->pdev->irq);
			return -ENODEV;
		}
		vxge_debug_init(VXGE_TRACE,
			"new %s-%d line allocated",
			"IRQ", vdev->pdev->irq);
	}

	return VXGE_HW_OK;
}

static void vxge_poll_vp_reset(unsigned long data)
{
	struct vxgedev *vdev = (struct vxgedev *)data;
	int i, j = 0;

	for (i = 0; i < vdev->no_of_vpath; i++) {
		if (test_bit(i, &vdev->vp_reset)) {
			vxge_reset_vpath(vdev, i);
			j++;
		}
	}
	if (j && (vdev->config.intr_type != MSI_X)) {
		vxge_hw_device_unmask_all(vdev->devh);
		vxge_hw_device_flush_io(vdev->devh);
	}

	mod_timer(&vdev->vp_reset_timer, jiffies + HZ / 2);
}

static void vxge_poll_vp_lockup(unsigned long data)
{
	struct vxgedev *vdev = (struct vxgedev *)data;
	enum vxge_hw_status status = VXGE_HW_OK;
J
Jon Mason 已提交
2624 2625 2626
	struct vxge_vpath *vpath;
	struct vxge_ring *ring;
	int i;
2627
	unsigned long rx_frms;
2628 2629 2630

	for (i = 0; i < vdev->no_of_vpath; i++) {
		ring = &vdev->vpaths[i].ring;
2631 2632 2633 2634

		/* Truncated to machine word size number of frames */
		rx_frms = ACCESS_ONCE(ring->stats.rx_frms);

2635
		/* Did this vpath received any packets */
2636
		if (ring->stats.prev_rx_frms == rx_frms) {
2637 2638 2639 2640 2641 2642 2643 2644
			status = vxge_hw_vpath_check_leak(ring->handle);

			/* Did it received any packets last time */
			if ((VXGE_HW_FAIL == status) &&
				(VXGE_HW_FAIL == ring->last_status)) {

				/* schedule vpath reset */
				if (!test_and_set_bit(i, &vdev->vp_reset)) {
J
Jon Mason 已提交
2645
					vpath = &vdev->vpaths[i];
2646 2647 2648 2649 2650

					/* disable interrupts for this vpath */
					vxge_vpath_intr_disable(vdev, i);

					/* stop the queue for this vpath */
J
Jon Mason 已提交
2651
					netif_tx_stop_queue(vpath->fifo.txq);
2652 2653 2654 2655
					continue;
				}
			}
		}
2656
		ring->stats.prev_rx_frms = rx_frms;
2657 2658 2659 2660 2661 2662 2663
		ring->last_status = status;
	}

	/* Check every 1 milli second */
	mod_timer(&vdev->vp_lockup_timer, jiffies + HZ / 1000);
}

2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697
static u32 vxge_fix_features(struct net_device *dev, u32 features)
{
	u32 changed = dev->features ^ features;

	/* Enabling RTH requires some of the logic in vxge_device_register and a
	 * vpath reset.  Due to these restrictions, only allow modification
	 * while the interface is down.
	 */
	if ((changed & NETIF_F_RXHASH) && netif_running(dev))
		features ^= NETIF_F_RXHASH;

	return features;
}

static int vxge_set_features(struct net_device *dev, u32 features)
{
	struct vxgedev *vdev = netdev_priv(dev);
	u32 changed = dev->features ^ features;

	if (!(changed & NETIF_F_RXHASH))
		return 0;

	/* !netif_running() ensured by vxge_fix_features() */

	vdev->devh->config.rth_en = !!(features & NETIF_F_RXHASH);
	if (vxge_reset_all_vpaths(vdev) != VXGE_HW_OK) {
		dev->features = features ^ NETIF_F_RXHASH;
		vdev->devh->config.rth_en = !!(dev->features & NETIF_F_RXHASH);
		return -EIO;
	}

	return 0;
}

2698 2699 2700 2701 2702 2703 2704 2705 2706 2707
/**
 * vxge_open
 * @dev: pointer to the device structure.
 *
 * This function is the open entry point of the driver. It mainly calls a
 * function to allocate Rx buffers and inserts them into the buffer
 * descriptors and then enables the Rx part of the NIC.
 * Return value: '0' on success and an appropriate (-)ve integer as
 * defined in errno.h file on failure.
 */
J
Jon Mason 已提交
2708
static int vxge_open(struct net_device *dev)
2709 2710 2711 2712
{
	enum vxge_hw_status status;
	struct vxgedev *vdev;
	struct __vxge_hw_device *hldev;
J
Jon Mason 已提交
2713
	struct vxge_vpath *vpath;
2714 2715 2716
	int ret = 0;
	int i;
	u64 val64, function_mode;
J
Jon Mason 已提交
2717

2718 2719 2720
	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d", dev->name, __func__, __LINE__);

2721
	vdev = netdev_priv(dev);
2722
	hldev = pci_get_drvdata(vdev->pdev);
2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751
	function_mode = vdev->config.device_hw_info.function_mode;

	/* make sure you have link off by default every time Nic is
	 * initialized */
	netif_carrier_off(dev);

	/* Open VPATHs */
	status = vxge_open_vpaths(vdev);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"%s: fatal: Vpath open failed", vdev->ndev->name);
		ret = -EPERM;
		goto out0;
	}

	vdev->mtu = dev->mtu;

	status = vxge_add_isr(vdev);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"%s: fatal: ISR add failed", dev->name);
		ret = -EPERM;
		goto out1;
	}

	if (vdev->config.intr_type != MSI_X) {
		netif_napi_add(dev, &vdev->napi, vxge_poll_inta,
			vdev->config.napi_weight);
		napi_enable(&vdev->napi);
J
Jon Mason 已提交
2752 2753 2754 2755
		for (i = 0; i < vdev->no_of_vpath; i++) {
			vpath = &vdev->vpaths[i];
			vpath->ring.napi_p = &vdev->napi;
		}
2756 2757
	} else {
		for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2758 2759
			vpath = &vdev->vpaths[i];
			netif_napi_add(dev, &vpath->ring.napi,
2760
			    vxge_poll_msix, vdev->config.napi_weight);
J
Jon Mason 已提交
2761 2762
			napi_enable(&vpath->ring.napi);
			vpath->ring.napi_p = &vpath->ring.napi;
2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776
		}
	}

	/* configure RTH */
	if (vdev->config.rth_steering) {
		status = vxge_rth_configure(vdev);
		if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR,
				"%s: fatal: RTH configuration failed",
				dev->name);
			ret = -EPERM;
			goto out2;
		}
	}
J
Jon Mason 已提交
2777 2778
	printk(KERN_INFO "%s: Receive Hashing Offload %s\n", dev->name,
	       hldev->config.rth_en ? "enabled" : "disabled");
2779 2780

	for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2781 2782
		vpath = &vdev->vpaths[i];

2783
		/* set initial mtu before enabling the device */
J
Jon Mason 已提交
2784
		status = vxge_hw_vpath_mtu_set(vpath->handle, vdev->mtu);
2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797
		if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR,
				"%s: fatal: can not set new MTU", dev->name);
			ret = -EPERM;
			goto out2;
		}
	}

	VXGE_DEVICE_DEBUG_LEVEL_SET(VXGE_TRACE, VXGE_COMPONENT_LL, vdev);
	vxge_debug_init(vdev->level_trace,
		"%s: MTU is %d", vdev->ndev->name, vdev->mtu);
	VXGE_DEVICE_DEBUG_LEVEL_SET(VXGE_ERR, VXGE_COMPONENT_LL, vdev);

J
Jon Mason 已提交
2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812
	/* Restore the DA, VID table and also multicast and promiscuous mode
	 * states
	 */
	if (vdev->all_multi_flg) {
		for (i = 0; i < vdev->no_of_vpath; i++) {
			vpath = &vdev->vpaths[i];
			vxge_restore_vpath_mac_addr(vpath);
			vxge_restore_vpath_vid_table(vpath);

			status = vxge_hw_vpath_mcast_enable(vpath->handle);
			if (status != VXGE_HW_OK)
				vxge_debug_init(VXGE_ERR,
					"%s:%d Enabling multicast failed",
					__func__, __LINE__);
		}
2813 2814 2815
	}

	/* Enable vpath to sniff all unicast/multicast traffic that not
L
Lucas De Marchi 已提交
2816
	 * addressed to them. We allow promiscuous mode for PF only
2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840
	 */

	val64 = 0;
	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
		val64 |= VXGE_HW_RXMAC_AUTHORIZE_ALL_ADDR_VP(i);

	vxge_hw_mgmt_reg_write(vdev->devh,
		vxge_hw_mgmt_reg_type_mrpcim,
		0,
		(ulong)offsetof(struct vxge_hw_mrpcim_reg,
			rxmac_authorize_all_addr),
		val64);

	vxge_hw_mgmt_reg_write(vdev->devh,
		vxge_hw_mgmt_reg_type_mrpcim,
		0,
		(ulong)offsetof(struct vxge_hw_mrpcim_reg,
			rxmac_authorize_all_vid),
		val64);

	vxge_set_multicast(dev);

	/* Enabling Bcast and mcast for all vpath */
	for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2841 2842
		vpath = &vdev->vpaths[i];
		status = vxge_hw_vpath_bcast_enable(vpath->handle);
2843 2844 2845 2846 2847
		if (status != VXGE_HW_OK)
			vxge_debug_init(VXGE_ERR,
				"%s : Can not enable bcast for vpath "
				"id %d", dev->name, i);
		if (vdev->config.addr_learn_en) {
J
Jon Mason 已提交
2848
			status = vxge_hw_vpath_mcast_enable(vpath->handle);
2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863
			if (status != VXGE_HW_OK)
				vxge_debug_init(VXGE_ERR,
					"%s : Can not enable mcast for vpath "
					"id %d", dev->name, i);
		}
	}

	vxge_hw_device_setpause_data(vdev->devh, 0,
		vdev->config.tx_pause_enable,
		vdev->config.rx_pause_enable);

	if (vdev->vp_reset_timer.function == NULL)
		vxge_os_timer(vdev->vp_reset_timer,
			vxge_poll_vp_reset, vdev, (HZ/2));

J
Jon Mason 已提交
2864 2865 2866 2867
	/* There is no need to check for RxD leak and RxD lookup on Titan1A */
	if (vdev->titan1 && vdev->vp_lockup_timer.function == NULL)
		vxge_os_timer(vdev->vp_lockup_timer, vxge_poll_vp_lockup, vdev,
			      HZ / 2);
2868 2869 2870 2871 2872 2873 2874

	set_bit(__VXGE_STATE_CARD_UP, &vdev->state);

	smp_wmb();

	if (vxge_hw_device_link_state_get(vdev->devh) == VXGE_HW_LINK_UP) {
		netif_carrier_on(vdev->ndev);
2875
		netdev_notice(vdev->ndev, "Link Up\n");
2876 2877 2878 2879 2880 2881 2882 2883
		vdev->stats.link_up++;
	}

	vxge_hw_device_intr_enable(vdev->devh);

	smp_wmb();

	for (i = 0; i < vdev->no_of_vpath; i++) {
J
Jon Mason 已提交
2884 2885 2886
		vpath = &vdev->vpaths[i];

		vxge_hw_vpath_enable(vpath->handle);
2887
		smp_wmb();
J
Jon Mason 已提交
2888
		vxge_hw_vpath_rx_doorbell_init(vpath->handle);
2889 2890
	}

J
Jon Mason 已提交
2891
	netif_tx_start_all_queues(vdev->ndev);
J
Jon Mason 已提交
2892 2893 2894 2895

	/* configure CI */
	vxge_config_ci_for_tti_rti(vdev);

2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917
	goto out0;

out2:
	vxge_rem_isr(vdev);

	/* Disable napi */
	if (vdev->config.intr_type != MSI_X)
		napi_disable(&vdev->napi);
	else {
		for (i = 0; i < vdev->no_of_vpath; i++)
			napi_disable(&vdev->vpaths[i].ring.napi);
	}

out1:
	vxge_close_vpaths(vdev, 0);
out0:
	vxge_debug_entryexit(VXGE_TRACE,
				"%s: %s:%d  Exiting...",
				dev->name, __func__, __LINE__);
	return ret;
}

L
Lucas De Marchi 已提交
2918
/* Loop through the mac address list and delete all the entries */
2919
static void vxge_free_mac_add_list(struct vxge_vpath *vpath)
2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942
{

	struct list_head *entry, *next;
	if (list_empty(&vpath->mac_addr_list))
		return;

	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
		list_del(entry);
		kfree((struct vxge_mac_addrs *)entry);
	}
}

static void vxge_napi_del_all(struct vxgedev *vdev)
{
	int i;
	if (vdev->config.intr_type != MSI_X)
		netif_napi_del(&vdev->napi);
	else {
		for (i = 0; i < vdev->no_of_vpath; i++)
			netif_napi_del(&vdev->vpaths[i].ring.napi);
	}
}

2943
static int do_vxge_close(struct net_device *dev, int do_io)
2944 2945 2946 2947 2948 2949 2950 2951 2952
{
	enum vxge_hw_status status;
	struct vxgedev *vdev;
	struct __vxge_hw_device *hldev;
	int i;
	u64 val64, vpath_vector;
	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
		dev->name, __func__, __LINE__);

2953
	vdev = netdev_priv(dev);
2954
	hldev = pci_get_drvdata(vdev->pdev);
2955

2956 2957 2958
	if (unlikely(!is_vxge_card_up(vdev)))
		return 0;

2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984
	/* If vxge_handle_crit_err task is executing,
	 * wait till it completes. */
	while (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
		msleep(50);

	if (do_io) {
		/* Put the vpath back in normal mode */
		vpath_vector = vxge_mBIT(vdev->vpaths[0].device_id);
		status = vxge_hw_mgmt_reg_read(vdev->devh,
				vxge_hw_mgmt_reg_type_mrpcim,
				0,
				(ulong)offsetof(
					struct vxge_hw_mrpcim_reg,
					rts_mgr_cbasin_cfg),
				&val64);
		if (status == VXGE_HW_OK) {
			val64 &= ~vpath_vector;
			status = vxge_hw_mgmt_reg_write(vdev->devh,
					vxge_hw_mgmt_reg_type_mrpcim,
					0,
					(ulong)offsetof(
						struct vxge_hw_mrpcim_reg,
						rts_mgr_cbasin_cfg),
					val64);
		}

L
Lucas De Marchi 已提交
2985
		/* Remove the function 0 from promiscuous mode */
2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001
		vxge_hw_mgmt_reg_write(vdev->devh,
			vxge_hw_mgmt_reg_type_mrpcim,
			0,
			(ulong)offsetof(struct vxge_hw_mrpcim_reg,
				rxmac_authorize_all_addr),
			0);

		vxge_hw_mgmt_reg_write(vdev->devh,
			vxge_hw_mgmt_reg_type_mrpcim,
			0,
			(ulong)offsetof(struct vxge_hw_mrpcim_reg,
				rxmac_authorize_all_vid),
			0);

		smp_wmb();
	}
J
Jon Mason 已提交
3002 3003 3004

	if (vdev->titan1)
		del_timer_sync(&vdev->vp_lockup_timer);
3005 3006 3007

	del_timer_sync(&vdev->vp_reset_timer);

3008 3009 3010 3011 3012
	if (do_io)
		vxge_hw_device_wait_receive_idle(hldev);

	clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);

3013 3014 3015 3016 3017 3018 3019 3020 3021
	/* Disable napi */
	if (vdev->config.intr_type != MSI_X)
		napi_disable(&vdev->napi);
	else {
		for (i = 0; i < vdev->no_of_vpath; i++)
			napi_disable(&vdev->vpaths[i].ring.napi);
	}

	netif_carrier_off(vdev->ndev);
3022
	netdev_notice(vdev->ndev, "Link Down\n");
J
Jon Mason 已提交
3023
	netif_tx_stop_all_queues(vdev->ndev);
3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056

	/* Note that at this point xmit() is stopped by upper layer */
	if (do_io)
		vxge_hw_device_intr_disable(vdev->devh);

	vxge_rem_isr(vdev);

	vxge_napi_del_all(vdev);

	if (do_io)
		vxge_reset_all_vpaths(vdev);

	vxge_close_vpaths(vdev, 0);

	vxge_debug_entryexit(VXGE_TRACE,
		"%s: %s:%d  Exiting...", dev->name, __func__, __LINE__);

	clear_bit(__VXGE_STATE_RESET_CARD, &vdev->state);

	return 0;
}

/**
 * vxge_close
 * @dev: device pointer.
 *
 * This is the stop entry point of the driver. It needs to undo exactly
 * whatever was done by the open entry point, thus it's usually referred to
 * as the close function.Among other things this function mainly stops the
 * Rx side of the NIC and frees all the Rx buffers in the Rx rings.
 * Return value: '0' on success and an appropriate (-)ve integer as
 * defined in errno.h file on failure.
 */
J
Jon Mason 已提交
3057
static int vxge_close(struct net_device *dev)
3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113
{
	do_vxge_close(dev, 1);
	return 0;
}

/**
 * vxge_change_mtu
 * @dev: net device pointer.
 * @new_mtu :the new MTU size for the device.
 *
 * A driver entry point to change MTU size for the device. Before changing
 * the MTU the device must be stopped.
 */
static int vxge_change_mtu(struct net_device *dev, int new_mtu)
{
	struct vxgedev *vdev = netdev_priv(dev);

	vxge_debug_entryexit(vdev->level_trace,
		"%s:%d", __func__, __LINE__);
	if ((new_mtu < VXGE_HW_MIN_MTU) || (new_mtu > VXGE_HW_MAX_MTU)) {
		vxge_debug_init(vdev->level_err,
			"%s: mtu size is invalid", dev->name);
		return -EPERM;
	}

	/* check if device is down already */
	if (unlikely(!is_vxge_card_up(vdev))) {
		/* just store new value, will use later on open() */
		dev->mtu = new_mtu;
		vxge_debug_init(vdev->level_err,
			"%s", "device is down on MTU change");
		return 0;
	}

	vxge_debug_init(vdev->level_trace,
		"trying to apply new MTU %d", new_mtu);

	if (vxge_close(dev))
		return -EIO;

	dev->mtu = new_mtu;
	vdev->mtu = new_mtu;

	if (vxge_open(dev))
		return -EIO;

	vxge_debug_init(vdev->level_trace,
		"%s: MTU changed to %d", vdev->ndev->name, new_mtu);

	vxge_debug_entryexit(vdev->level_trace,
		"%s:%d  Exiting...", __func__, __LINE__);

	return 0;
}

/**
E
Eric Dumazet 已提交
3114
 * vxge_get_stats64
3115
 * @dev: pointer to the device structure
E
Eric Dumazet 已提交
3116
 * @stats: pointer to struct rtnl_link_stats64
3117 3118
 *
 */
E
Eric Dumazet 已提交
3119 3120
static struct rtnl_link_stats64 *
vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
3121
{
E
Eric Dumazet 已提交
3122
	struct vxgedev *vdev = netdev_priv(dev);
3123 3124
	int k;

E
Eric Dumazet 已提交
3125
	/* net_stats already zeroed by caller */
3126
	for (k = 0; k < vdev->no_of_vpath; k++) {
3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156
		struct vxge_ring_stats *rxstats = &vdev->vpaths[k].ring.stats;
		struct vxge_fifo_stats *txstats = &vdev->vpaths[k].fifo.stats;
		unsigned int start;
		u64 packets, bytes, multicast;

		do {
			start = u64_stats_fetch_begin(&rxstats->syncp);

			packets   = rxstats->rx_frms;
			multicast = rxstats->rx_mcast;
			bytes     = rxstats->rx_bytes;
		} while (u64_stats_fetch_retry(&rxstats->syncp, start));

		net_stats->rx_packets += packets;
		net_stats->rx_bytes += bytes;
		net_stats->multicast += multicast;

		net_stats->rx_errors += rxstats->rx_errors;
		net_stats->rx_dropped += rxstats->rx_dropped;

		do {
			start = u64_stats_fetch_begin(&txstats->syncp);

			packets = txstats->tx_frms;
			bytes   = txstats->tx_bytes;
		} while (u64_stats_fetch_retry(&txstats->syncp, start));

		net_stats->tx_packets += packets;
		net_stats->tx_bytes += bytes;
		net_stats->tx_errors += txstats->tx_errors;
3157 3158 3159 3160 3161
	}

	return net_stats;
}

3162
static enum vxge_hw_status vxge_timestamp_config(struct __vxge_hw_device *devh)
3163 3164 3165 3166 3167 3168 3169 3170 3171
{
	enum vxge_hw_status status;
	u64 val64;

	/* Timestamp is passed to the driver via the FCS, therefore we
	 * must disable the FCS stripping by the adapter.  Since this is
	 * required for the driver to load (due to a hardware bug),
	 * there is no need to do anything special here.
	 */
3172 3173 3174
	val64 = VXGE_HW_XMAC_TIMESTAMP_EN |
		VXGE_HW_XMAC_TIMESTAMP_USE_LINK_ID(0) |
		VXGE_HW_XMAC_TIMESTAMP_INTERVAL(0);
3175

3176
	status = vxge_hw_mgmt_reg_write(devh,
3177 3178 3179 3180 3181
					vxge_hw_mgmt_reg_type_mrpcim,
					0,
					offsetof(struct vxge_hw_mrpcim_reg,
						 xmac_timestamp),
					val64);
3182 3183
	vxge_hw_device_flush_io(devh);
	devh->config.hwts_en = VXGE_HW_HWTS_ENABLE;
3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227
	return status;
}

static int vxge_hwtstamp_ioctl(struct vxgedev *vdev, void __user *data)
{
	struct hwtstamp_config config;
	int i;

	if (copy_from_user(&config, data, sizeof(config)))
		return -EFAULT;

	/* reserved for future extensions */
	if (config.flags)
		return -EINVAL;

	/* Transmit HW Timestamp not supported */
	switch (config.tx_type) {
	case HWTSTAMP_TX_OFF:
		break;
	case HWTSTAMP_TX_ON:
	default:
		return -ERANGE;
	}

	switch (config.rx_filter) {
	case HWTSTAMP_FILTER_NONE:
		vdev->rx_hwts = 0;
		config.rx_filter = HWTSTAMP_FILTER_NONE;
		break;

	case HWTSTAMP_FILTER_ALL:
	case HWTSTAMP_FILTER_SOME:
	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
	case HWTSTAMP_FILTER_PTP_V2_EVENT:
	case HWTSTAMP_FILTER_PTP_V2_SYNC:
	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
3228
		if (vdev->devh->config.hwts_en != VXGE_HW_HWTS_ENABLE)
3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247
			return -EFAULT;

		vdev->rx_hwts = 1;
		config.rx_filter = HWTSTAMP_FILTER_ALL;
		break;

	default:
		 return -ERANGE;
	}

	for (i = 0; i < vdev->no_of_vpath; i++)
		vdev->vpaths[i].ring.rx_hwts = vdev->rx_hwts;

	if (copy_to_user(data, &config, sizeof(config)))
		return -EFAULT;

	return 0;
}

3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259
/**
 * vxge_ioctl
 * @dev: Device pointer.
 * @ifr: An IOCTL specific structure, that can contain a pointer to
 *       a proprietary structure used to pass information to the driver.
 * @cmd: This is used to distinguish between the different commands that
 *       can be passed to the IOCTL functions.
 *
 * Entry point for the Ioctl.
 */
static int vxge_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273
	struct vxgedev *vdev = netdev_priv(dev);
	int ret;

	switch (cmd) {
	case SIOCSHWTSTAMP:
		ret = vxge_hwtstamp_ioctl(vdev, rq->ifr_data);
		if (ret)
			return ret;
		break;
	default:
		return -EOPNOTSUPP;
	}

	return 0;
3274 3275 3276 3277 3278 3279 3280 3281 3282 3283
}

/**
 * vxge_tx_watchdog
 * @dev: pointer to net device structure
 *
 * Watchdog for transmit side.
 * This function is triggered if the Tx Queue is stopped
 * for a pre-defined amount of time when the Interface is still up.
 */
J
Jon Mason 已提交
3284
static void vxge_tx_watchdog(struct net_device *dev)
3285 3286 3287 3288 3289
{
	struct vxgedev *vdev;

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

3290
	vdev = netdev_priv(dev);
3291 3292 3293

	vdev->cric_err_event = VXGE_HW_EVENT_RESET_START;

J
Jon Mason 已提交
3294
	schedule_work(&vdev->reset_task);
3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308
	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);
}

/**
 * vxge_vlan_rx_add_vid
 * @dev: net device pointer.
 * @vid: vid
 *
 * Add the vlan id to the devices vlan id table
 */
static void
vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
{
J
Jiri Pirko 已提交
3309
	struct vxgedev *vdev = netdev_priv(dev);
3310 3311 3312 3313 3314 3315 3316 3317 3318 3319
	struct vxge_vpath *vpath;
	int vp_id;

	/* Add these vlan to the vid table */
	for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
		vpath = &vdev->vpaths[vp_id];
		if (!vpath->is_open)
			continue;
		vxge_hw_vpath_vid_add(vpath->handle, vid);
	}
J
Jiri Pirko 已提交
3320
	set_bit(vid, vdev->active_vlans);
3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332
}

/**
 * vxge_vlan_rx_add_vid
 * @dev: net device pointer.
 * @vid: vid
 *
 * Remove the vlan id from the device's vlan id table
 */
static void
vxge_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
{
J
Jiri Pirko 已提交
3333
	struct vxgedev *vdev = netdev_priv(dev);
3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347
	struct vxge_vpath *vpath;
	int vp_id;

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);

	/* Delete this vlan from the vid table */
	for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
		vpath = &vdev->vpaths[vp_id];
		if (!vpath->is_open)
			continue;
		vxge_hw_vpath_vid_delete(vpath->handle, vid);
	}
	vxge_debug_entryexit(VXGE_TRACE,
		"%s:%d  Exiting...", __func__, __LINE__);
J
Jiri Pirko 已提交
3348
	clear_bit(vid, vdev->active_vlans);
3349 3350 3351 3352 3353
}

static const struct net_device_ops vxge_netdev_ops = {
	.ndo_open               = vxge_open,
	.ndo_stop               = vxge_close,
E
Eric Dumazet 已提交
3354
	.ndo_get_stats64        = vxge_get_stats64,
3355 3356 3357 3358 3359 3360
	.ndo_start_xmit         = vxge_xmit,
	.ndo_validate_addr      = eth_validate_addr,
	.ndo_set_multicast_list = vxge_set_multicast,
	.ndo_do_ioctl           = vxge_ioctl,
	.ndo_set_mac_address    = vxge_set_mac_addr,
	.ndo_change_mtu         = vxge_change_mtu,
3361 3362
	.ndo_fix_features	= vxge_fix_features,
	.ndo_set_features	= vxge_set_features,
3363 3364 3365 3366 3367 3368 3369 3370
	.ndo_vlan_rx_kill_vid   = vxge_vlan_rx_kill_vid,
	.ndo_vlan_rx_add_vid	= vxge_vlan_rx_add_vid,
	.ndo_tx_timeout         = vxge_tx_watchdog,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller    = vxge_netpoll,
#endif
};

3371 3372 3373 3374
static int __devinit vxge_device_register(struct __vxge_hw_device *hldev,
					  struct vxge_config *config,
					  int high_dma, int no_of_vpath,
					  struct vxgedev **vdev_out)
3375 3376 3377 3378
{
	struct net_device *ndev;
	enum vxge_hw_status status = VXGE_HW_OK;
	struct vxgedev *vdev;
J
Jon Mason 已提交
3379
	int ret = 0, no_of_queue = 1;
3380 3381 3382
	u64 stat;

	*vdev_out = NULL;
J
Jon Mason 已提交
3383
	if (config->tx_steering_type)
3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407
		no_of_queue = no_of_vpath;

	ndev = alloc_etherdev_mq(sizeof(struct vxgedev),
			no_of_queue);
	if (ndev == NULL) {
		vxge_debug_init(
			vxge_hw_device_trace_level_get(hldev),
		"%s : device allocation failed", __func__);
		ret = -ENODEV;
		goto _out0;
	}

	vxge_debug_entryexit(
		vxge_hw_device_trace_level_get(hldev),
		"%s: %s:%d  Entering...",
		ndev->name, __func__, __LINE__);

	vdev = netdev_priv(ndev);
	memset(vdev, 0, sizeof(struct vxgedev));

	vdev->ndev = ndev;
	vdev->devh = hldev;
	vdev->pdev = hldev->pdev;
	memcpy(&vdev->config, config, sizeof(struct vxge_config));
3408
	vdev->rx_hwts = 0;
3409
	vdev->titan1 = (vdev->pdev->revision == VXGE_HW_TITAN1_PCI_REVISION);
J
Jon Mason 已提交
3410

3411 3412
	SET_NETDEV_DEV(ndev, &vdev->pdev->dev);

3413 3414 3415 3416 3417 3418 3419 3420 3421 3422
	ndev->hw_features = NETIF_F_RXCSUM | NETIF_F_SG |
		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
		NETIF_F_TSO | NETIF_F_TSO6 |
		NETIF_F_HW_VLAN_TX;
	if (vdev->config.rth_steering != NO_STEERING)
		ndev->hw_features |= NETIF_F_RXHASH;

	ndev->features |= ndev->hw_features |
		NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER;

3423 3424 3425 3426 3427 3428 3429
	/*  Driver entry points */
	ndev->irq = vdev->pdev->irq;
	ndev->base_addr = (unsigned long) hldev->bar0;

	ndev->netdev_ops = &vxge_netdev_ops;

	ndev->watchdog_timeo = VXGE_LL_WATCH_DOG_TIMEOUT;
J
Jon Mason 已提交
3430
	INIT_WORK(&vdev->reset_task, vxge_reset);
3431

3432
	vxge_initialize_ethtool_ops(ndev);
3433 3434 3435 3436 3437 3438 3439 3440

	/* Allocate memory for vpath */
	vdev->vpaths = kzalloc((sizeof(struct vxge_vpath)) *
				no_of_vpath, GFP_KERNEL);
	if (!vdev->vpaths) {
		vxge_debug_init(VXGE_ERR,
			"%s: vpath memory allocation failed",
			vdev->ndev->name);
J
Jon Mason 已提交
3441
		ret = -ENOMEM;
3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453
		goto _out1;
	}

	vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
		"%s : checksuming enabled", __func__);

	if (high_dma) {
		ndev->features |= NETIF_F_HIGHDMA;
		vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
			"%s : using High DMA", __func__);
	}

J
Jon Mason 已提交
3454 3455
	ret = register_netdev(ndev);
	if (ret) {
3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474
		vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
			"%s: %s : device registration failed!",
			ndev->name, __func__);
		goto _out2;
	}

	/*  Set the factory defined MAC address initially */
	ndev->addr_len = ETH_ALEN;

	/* Make Link state as off at this point, when the Link change
	 * interrupt comes the state will be automatically changed to
	 * the right state.
	 */
	netif_carrier_off(ndev);

	vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
		"%s: Ethernet device registered",
		ndev->name);

3475
	hldev->ndev = ndev;
3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509
	*vdev_out = vdev;

	/* Resetting the Device stats */
	status = vxge_hw_mrpcim_stats_access(
				hldev,
				VXGE_HW_STATS_OP_CLEAR_ALL_STATS,
				0,
				0,
				&stat);

	if (status == VXGE_HW_ERR_PRIVILAGED_OPEARATION)
		vxge_debug_init(
			vxge_hw_device_trace_level_get(hldev),
			"%s: device stats clear returns"
			"VXGE_HW_ERR_PRIVILAGED_OPEARATION", ndev->name);

	vxge_debug_entryexit(vxge_hw_device_trace_level_get(hldev),
		"%s: %s:%d  Exiting...",
		ndev->name, __func__, __LINE__);

	return ret;
_out2:
	kfree(vdev->vpaths);
_out1:
	free_netdev(ndev);
_out0:
	return ret;
}

/*
 * vxge_device_unregister
 *
 * This function will unregister and free network device
 */
J
Jon Mason 已提交
3510
static void vxge_device_unregister(struct __vxge_hw_device *hldev)
3511 3512 3513 3514 3515 3516 3517 3518
{
	struct vxgedev *vdev;
	struct net_device *dev;
	char buf[IFNAMSIZ];

	dev = hldev->ndev;
	vdev = netdev_priv(dev);

J
Jon Mason 已提交
3519 3520 3521
	vxge_debug_entryexit(vdev->level_trace,	"%s: %s:%d", vdev->ndev->name,
			     __func__, __LINE__);

J
Jon Mason 已提交
3522
	strncpy(buf, dev->name, IFNAMSIZ);
3523

T
Tejun Heo 已提交
3524 3525
	flush_work_sync(&vdev->reset_task);

3526 3527 3528
	/* in 2.6 will call stop() if device is up */
	unregister_netdev(dev);

J
Jon Mason 已提交
3529 3530 3531 3532 3533
	kfree(vdev->vpaths);

	/* we are safe to free it now */
	free_netdev(dev);

J
Jon Mason 已提交
3534 3535 3536 3537
	vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered",
			buf);
	vxge_debug_entryexit(vdev->level_trace,	"%s: %s:%d  Exiting...", buf,
			     __func__, __LINE__);
3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550
}

/*
 * vxge_callback_crit_err
 *
 * This function is called by the alarm handler in interrupt context.
 * Driver must analyze it based on the event type.
 */
static void
vxge_callback_crit_err(struct __vxge_hw_device *hldev,
			enum vxge_hw_event type, u64 vp_id)
{
	struct net_device *dev = hldev->ndev;
3551
	struct vxgedev *vdev = netdev_priv(dev);
J
Jon Mason 已提交
3552
	struct vxge_vpath *vpath = NULL;
3553 3554 3555 3556 3557 3558 3559 3560 3561 3562
	int vpath_idx;

	vxge_debug_entryexit(vdev->level_trace,
		"%s: %s:%d", vdev->ndev->name, __func__, __LINE__);

	/* Note: This event type should be used for device wide
	 * indications only - Serious errors, Slot freeze and critical errors
	 */
	vdev->cric_err_event = type;

J
Jon Mason 已提交
3563 3564 3565
	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
		vpath = &vdev->vpaths[vpath_idx];
		if (vpath->device_id == vp_id)
3566
			break;
J
Jon Mason 已提交
3567
	}
3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603

	if (!test_bit(__VXGE_STATE_RESET_CARD, &vdev->state)) {
		if (type == VXGE_HW_EVENT_SLOT_FREEZE) {
			vxge_debug_init(VXGE_ERR,
				"%s: Slot is frozen", vdev->ndev->name);
		} else if (type == VXGE_HW_EVENT_SERR) {
			vxge_debug_init(VXGE_ERR,
				"%s: Encountered Serious Error",
				vdev->ndev->name);
		} else if (type == VXGE_HW_EVENT_CRITICAL_ERR)
			vxge_debug_init(VXGE_ERR,
				"%s: Encountered Critical Error",
				vdev->ndev->name);
	}

	if ((type == VXGE_HW_EVENT_SERR) ||
		(type == VXGE_HW_EVENT_SLOT_FREEZE)) {
		if (unlikely(vdev->exec_mode))
			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
	} else if (type == VXGE_HW_EVENT_CRITICAL_ERR) {
		vxge_hw_device_mask_all(hldev);
		if (unlikely(vdev->exec_mode))
			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
	} else if ((type == VXGE_HW_EVENT_FIFO_ERR) ||
		  (type == VXGE_HW_EVENT_VPATH_ERR)) {

		if (unlikely(vdev->exec_mode))
			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
		else {
			/* check if this vpath is already set for reset */
			if (!test_and_set_bit(vpath_idx, &vdev->vp_reset)) {

				/* disable interrupts for this vpath */
				vxge_vpath_intr_disable(vdev, vpath_idx);

				/* stop the queue for this vpath */
J
Jon Mason 已提交
3604
				netif_tx_stop_queue(vpath->fifo.txq);
3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749
			}
		}
	}

	vxge_debug_entryexit(vdev->level_trace,
		"%s: %s:%d  Exiting...",
		vdev->ndev->name, __func__, __LINE__);
}

static void verify_bandwidth(void)
{
	int i, band_width, total = 0, equal_priority = 0;

	/* 1. If user enters 0 for some fifo, give equal priority to all */
	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
		if (bw_percentage[i] == 0) {
			equal_priority = 1;
			break;
		}
	}

	if (!equal_priority) {
		/* 2. If sum exceeds 100, give equal priority to all */
		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
			if (bw_percentage[i] == 0xFF)
				break;

			total += bw_percentage[i];
			if (total > VXGE_HW_VPATH_BANDWIDTH_MAX) {
				equal_priority = 1;
				break;
			}
		}
	}

	if (!equal_priority) {
		/* Is all the bandwidth consumed? */
		if (total < VXGE_HW_VPATH_BANDWIDTH_MAX) {
			if (i < VXGE_HW_MAX_VIRTUAL_PATHS) {
				/* Split rest of bw equally among next VPs*/
				band_width =
				  (VXGE_HW_VPATH_BANDWIDTH_MAX  - total) /
					(VXGE_HW_MAX_VIRTUAL_PATHS - i);
				if (band_width < 2) /* min of 2% */
					equal_priority = 1;
				else {
					for (; i < VXGE_HW_MAX_VIRTUAL_PATHS;
						i++)
						bw_percentage[i] =
							band_width;
				}
			}
		} else if (i < VXGE_HW_MAX_VIRTUAL_PATHS)
			equal_priority = 1;
	}

	if (equal_priority) {
		vxge_debug_init(VXGE_ERR,
			"%s: Assigning equal bandwidth to all the vpaths",
			VXGE_DRIVER_NAME);
		bw_percentage[0] = VXGE_HW_VPATH_BANDWIDTH_MAX /
					VXGE_HW_MAX_VIRTUAL_PATHS;
		for (i = 1; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
			bw_percentage[i] = bw_percentage[0];
	}
}

/*
 * Vpath configuration
 */
static int __devinit vxge_config_vpaths(
			struct vxge_hw_device_config *device_config,
			u64 vpath_mask, struct vxge_config *config_param)
{
	int i, no_of_vpaths = 0, default_no_vpath = 0, temp;
	u32 txdl_size, txdl_per_memblock;

	temp = driver_config->vpath_per_dev;
	if ((driver_config->vpath_per_dev == VXGE_USE_DEFAULT) &&
		(max_config_dev == VXGE_MAX_CONFIG_DEV)) {
		/* No more CPU. Return vpath number as zero.*/
		if (driver_config->g_no_cpus == -1)
			return 0;

		if (!driver_config->g_no_cpus)
			driver_config->g_no_cpus = num_online_cpus();

		driver_config->vpath_per_dev = driver_config->g_no_cpus >> 1;
		if (!driver_config->vpath_per_dev)
			driver_config->vpath_per_dev = 1;

		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
			if (!vxge_bVALn(vpath_mask, i, 1))
				continue;
			else
				default_no_vpath++;
		if (default_no_vpath < driver_config->vpath_per_dev)
			driver_config->vpath_per_dev = default_no_vpath;

		driver_config->g_no_cpus = driver_config->g_no_cpus -
				(driver_config->vpath_per_dev * 2);
		if (driver_config->g_no_cpus <= 0)
			driver_config->g_no_cpus = -1;
	}

	if (driver_config->vpath_per_dev == 1) {
		vxge_debug_ll_config(VXGE_TRACE,
			"%s: Disable tx and rx steering, "
			"as single vpath is configured", VXGE_DRIVER_NAME);
		config_param->rth_steering = NO_STEERING;
		config_param->tx_steering_type = NO_STEERING;
		device_config->rth_en = 0;
	}

	/* configure bandwidth */
	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
		device_config->vp_config[i].min_bandwidth = bw_percentage[i];

	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
		device_config->vp_config[i].vp_id = i;
		device_config->vp_config[i].mtu = VXGE_HW_DEFAULT_MTU;
		if (no_of_vpaths < driver_config->vpath_per_dev) {
			if (!vxge_bVALn(vpath_mask, i, 1)) {
				vxge_debug_ll_config(VXGE_TRACE,
					"%s: vpath: %d is not available",
					VXGE_DRIVER_NAME, i);
				continue;
			} else {
				vxge_debug_ll_config(VXGE_TRACE,
					"%s: vpath: %d available",
					VXGE_DRIVER_NAME, i);
				no_of_vpaths++;
			}
		} else {
			vxge_debug_ll_config(VXGE_TRACE,
				"%s: vpath: %d is not configured, "
				"max_config_vpath exceeded",
				VXGE_DRIVER_NAME, i);
			break;
		}

		/* Configure Tx fifo's */
		device_config->vp_config[i].fifo.enable =
						VXGE_HW_FIFO_ENABLE;
		device_config->vp_config[i].fifo.max_frags =
3750
				MAX_SKB_FRAGS + 1;
3751 3752 3753
		device_config->vp_config[i].fifo.memblock_size =
			VXGE_HW_MIN_FIFO_MEMBLOCK_SIZE;

3754 3755
		txdl_size = device_config->vp_config[i].fifo.max_frags *
				sizeof(struct vxge_hw_fifo_txd);
3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773
		txdl_per_memblock = VXGE_HW_MIN_FIFO_MEMBLOCK_SIZE / txdl_size;

		device_config->vp_config[i].fifo.fifo_blocks =
			((VXGE_DEF_FIFO_LENGTH - 1) / txdl_per_memblock) + 1;

		device_config->vp_config[i].fifo.intr =
				VXGE_HW_FIFO_QUEUE_INTR_DISABLE;

		/* Configure tti properties */
		device_config->vp_config[i].tti.intr_enable =
					VXGE_HW_TIM_INTR_ENABLE;

		device_config->vp_config[i].tti.btimer_val =
			(VXGE_TTI_BTIMER_VAL * 1000) / 272;

		device_config->vp_config[i].tti.timer_ac_en =
				VXGE_HW_TIM_TIMER_AC_ENABLE;

J
Jon Mason 已提交
3774 3775 3776
		/* For msi-x with napi (each vector has a handler of its own) -
		 * Set CI to OFF for all vpaths
		 */
3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805
		device_config->vp_config[i].tti.timer_ci_en =
			VXGE_HW_TIM_TIMER_CI_DISABLE;

		device_config->vp_config[i].tti.timer_ri_en =
				VXGE_HW_TIM_TIMER_RI_DISABLE;

		device_config->vp_config[i].tti.util_sel =
			VXGE_HW_TIM_UTIL_SEL_LEGACY_TX_NET_UTIL;

		device_config->vp_config[i].tti.ltimer_val =
			(VXGE_TTI_LTIMER_VAL * 1000) / 272;

		device_config->vp_config[i].tti.rtimer_val =
			(VXGE_TTI_RTIMER_VAL * 1000) / 272;

		device_config->vp_config[i].tti.urange_a = TTI_TX_URANGE_A;
		device_config->vp_config[i].tti.urange_b = TTI_TX_URANGE_B;
		device_config->vp_config[i].tti.urange_c = TTI_TX_URANGE_C;
		device_config->vp_config[i].tti.uec_a = TTI_TX_UFC_A;
		device_config->vp_config[i].tti.uec_b = TTI_TX_UFC_B;
		device_config->vp_config[i].tti.uec_c = TTI_TX_UFC_C;
		device_config->vp_config[i].tti.uec_d = TTI_TX_UFC_D;

		/* Configure Rx rings */
		device_config->vp_config[i].ring.enable  =
						VXGE_HW_RING_ENABLE;

		device_config->vp_config[i].ring.ring_blocks  =
						VXGE_HW_DEF_RING_BLOCKS;
J
Jon Mason 已提交
3806

3807 3808
		device_config->vp_config[i].ring.buffer_mode =
			VXGE_HW_RING_RXD_BUFFER_MODE_1;
J
Jon Mason 已提交
3809

3810 3811
		device_config->vp_config[i].ring.rxds_limit  =
				VXGE_HW_DEF_RING_RXDS_LIMIT;
J
Jon Mason 已提交
3812

3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888
		device_config->vp_config[i].ring.scatter_mode =
					VXGE_HW_RING_SCATTER_MODE_A;

		/* Configure rti properties */
		device_config->vp_config[i].rti.intr_enable =
					VXGE_HW_TIM_INTR_ENABLE;

		device_config->vp_config[i].rti.btimer_val =
			(VXGE_RTI_BTIMER_VAL * 1000)/272;

		device_config->vp_config[i].rti.timer_ac_en =
						VXGE_HW_TIM_TIMER_AC_ENABLE;

		device_config->vp_config[i].rti.timer_ci_en =
						VXGE_HW_TIM_TIMER_CI_DISABLE;

		device_config->vp_config[i].rti.timer_ri_en =
						VXGE_HW_TIM_TIMER_RI_DISABLE;

		device_config->vp_config[i].rti.util_sel =
				VXGE_HW_TIM_UTIL_SEL_LEGACY_RX_NET_UTIL;

		device_config->vp_config[i].rti.urange_a =
						RTI_RX_URANGE_A;
		device_config->vp_config[i].rti.urange_b =
						RTI_RX_URANGE_B;
		device_config->vp_config[i].rti.urange_c =
						RTI_RX_URANGE_C;
		device_config->vp_config[i].rti.uec_a = RTI_RX_UFC_A;
		device_config->vp_config[i].rti.uec_b = RTI_RX_UFC_B;
		device_config->vp_config[i].rti.uec_c = RTI_RX_UFC_C;
		device_config->vp_config[i].rti.uec_d = RTI_RX_UFC_D;

		device_config->vp_config[i].rti.rtimer_val =
			(VXGE_RTI_RTIMER_VAL * 1000) / 272;

		device_config->vp_config[i].rti.ltimer_val =
			(VXGE_RTI_LTIMER_VAL * 1000) / 272;

		device_config->vp_config[i].rpa_strip_vlan_tag =
			vlan_tag_strip;
	}

	driver_config->vpath_per_dev = temp;
	return no_of_vpaths;
}

/* initialize device configuratrions */
static void __devinit vxge_device_config_init(
				struct vxge_hw_device_config *device_config,
				int *intr_type)
{
	/* Used for CQRQ/SRQ. */
	device_config->dma_blockpool_initial =
			VXGE_HW_INITIAL_DMA_BLOCK_POOL_SIZE;

	device_config->dma_blockpool_max =
			VXGE_HW_MAX_DMA_BLOCK_POOL_SIZE;

	if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT)
		max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT;

#ifndef CONFIG_PCI_MSI
	vxge_debug_init(VXGE_ERR,
		"%s: This Kernel does not support "
		"MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
	*intr_type = INTA;
#endif

	/* Configure whether MSI-X or IRQL. */
	switch (*intr_type) {
	case INTA:
		device_config->intr_mode = VXGE_HW_INTR_MODE_IRQLINE;
		break;

	case MSI_X:
J
Jon Mason 已提交
3889
		device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX_ONE_SHOT;
3890 3891
		break;
	}
J
Jon Mason 已提交
3892

3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037
	/* Timer period between device poll */
	device_config->device_poll_millis = VXGE_TIMER_DELAY;

	/* Configure mac based steering. */
	device_config->rts_mac_en = addr_learn_en;

	/* Configure Vpaths */
	device_config->rth_it_type = VXGE_HW_RTH_IT_TYPE_MULTI_IT;

	vxge_debug_ll_config(VXGE_TRACE, "%s : Device Config Params ",
			__func__);
	vxge_debug_ll_config(VXGE_TRACE, "intr_mode : %d",
			device_config->intr_mode);
	vxge_debug_ll_config(VXGE_TRACE, "device_poll_millis : %d",
			device_config->device_poll_millis);
	vxge_debug_ll_config(VXGE_TRACE, "rth_en : %d",
			device_config->rth_en);
	vxge_debug_ll_config(VXGE_TRACE, "rth_it_type : %d",
			device_config->rth_it_type);
}

static void __devinit vxge_print_parm(struct vxgedev *vdev, u64 vpath_mask)
{
	int i;

	vxge_debug_init(VXGE_TRACE,
		"%s: %d Vpath(s) opened",
		vdev->ndev->name, vdev->no_of_vpath);

	switch (vdev->config.intr_type) {
	case INTA:
		vxge_debug_init(VXGE_TRACE,
			"%s: Interrupt type INTA", vdev->ndev->name);
		break;

	case MSI_X:
		vxge_debug_init(VXGE_TRACE,
			"%s: Interrupt type MSI-X", vdev->ndev->name);
		break;
	}

	if (vdev->config.rth_steering) {
		vxge_debug_init(VXGE_TRACE,
			"%s: RTH steering enabled for TCP_IPV4",
			vdev->ndev->name);
	} else {
		vxge_debug_init(VXGE_TRACE,
			"%s: RTH steering disabled", vdev->ndev->name);
	}

	switch (vdev->config.tx_steering_type) {
	case NO_STEERING:
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx steering disabled", vdev->ndev->name);
		break;
	case TX_PRIORITY_STEERING:
		vxge_debug_init(VXGE_TRACE,
			"%s: Unsupported tx steering option",
			vdev->ndev->name);
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx steering disabled", vdev->ndev->name);
		vdev->config.tx_steering_type = 0;
		break;
	case TX_VLAN_STEERING:
		vxge_debug_init(VXGE_TRACE,
			"%s: Unsupported tx steering option",
			vdev->ndev->name);
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx steering disabled", vdev->ndev->name);
		vdev->config.tx_steering_type = 0;
		break;
	case TX_MULTIQ_STEERING:
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx multiqueue steering enabled",
			vdev->ndev->name);
		break;
	case TX_PORT_STEERING:
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx port steering enabled",
			vdev->ndev->name);
		break;
	default:
		vxge_debug_init(VXGE_ERR,
			"%s: Unsupported tx steering type",
			vdev->ndev->name);
		vxge_debug_init(VXGE_TRACE,
			"%s: Tx steering disabled", vdev->ndev->name);
		vdev->config.tx_steering_type = 0;
	}

	if (vdev->config.addr_learn_en)
		vxge_debug_init(VXGE_TRACE,
			"%s: MAC Address learning enabled", vdev->ndev->name);

	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
		if (!vxge_bVALn(vpath_mask, i, 1))
			continue;
		vxge_debug_ll_config(VXGE_TRACE,
			"%s: MTU size - %d", vdev->ndev->name,
			((struct __vxge_hw_device  *)(vdev->devh))->
				config.vp_config[i].mtu);
		vxge_debug_init(VXGE_TRACE,
			"%s: VLAN tag stripping %s", vdev->ndev->name,
			((struct __vxge_hw_device  *)(vdev->devh))->
				config.vp_config[i].rpa_strip_vlan_tag
			? "Enabled" : "Disabled");
		vxge_debug_ll_config(VXGE_TRACE,
			"%s: Max frags : %d", vdev->ndev->name,
			((struct __vxge_hw_device  *)(vdev->devh))->
				config.vp_config[i].fifo.max_frags);
		break;
	}
}

#ifdef CONFIG_PM
/**
 * vxge_pm_suspend - vxge power management suspend entry point
 *
 */
static int vxge_pm_suspend(struct pci_dev *pdev, pm_message_t state)
{
	return -ENOSYS;
}
/**
 * vxge_pm_resume - vxge power management resume entry point
 *
 */
static int vxge_pm_resume(struct pci_dev *pdev)
{
	return -ENOSYS;
}

#endif

/**
 * vxge_io_error_detected - called when PCI error is detected
 * @pdev: Pointer to PCI device
 * @state: The current pci connection state
 *
 * This function is called after a PCI bus error affecting
 * this device has been detected.
 */
static pci_ers_result_t vxge_io_error_detected(struct pci_dev *pdev,
						pci_channel_state_t state)
{
4038
	struct __vxge_hw_device *hldev = pci_get_drvdata(pdev);
4039 4040 4041 4042
	struct net_device *netdev = hldev->ndev;

	netif_device_detach(netdev);

4043 4044 4045
	if (state == pci_channel_io_perm_failure)
		return PCI_ERS_RESULT_DISCONNECT;

4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066
	if (netif_running(netdev)) {
		/* Bring down the card, while avoiding PCI I/O */
		do_vxge_close(netdev, 0);
	}

	pci_disable_device(pdev);

	return PCI_ERS_RESULT_NEED_RESET;
}

/**
 * vxge_io_slot_reset - called after the pci bus has been reset.
 * @pdev: Pointer to PCI device
 *
 * Restart the card from scratch, as if from a cold-boot.
 * At this point, the card has exprienced a hard reset,
 * followed by fixups by BIOS, and has its config space
 * set up identically to what it was at cold boot.
 */
static pci_ers_result_t vxge_io_slot_reset(struct pci_dev *pdev)
{
4067
	struct __vxge_hw_device *hldev = pci_get_drvdata(pdev);
4068 4069 4070 4071 4072
	struct net_device *netdev = hldev->ndev;

	struct vxgedev *vdev = netdev_priv(netdev);

	if (pci_enable_device(pdev)) {
4073
		netdev_err(netdev, "Cannot re-enable device after reset\n");
4074 4075 4076 4077
		return PCI_ERS_RESULT_DISCONNECT;
	}

	pci_set_master(pdev);
J
Jon Mason 已提交
4078
	do_vxge_reset(vdev, VXGE_LL_FULL_RESET);
4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091

	return PCI_ERS_RESULT_RECOVERED;
}

/**
 * vxge_io_resume - called when traffic can start flowing again.
 * @pdev: Pointer to PCI device
 *
 * This callback is called when the error recovery driver tells
 * us that its OK to resume normal operation.
 */
static void vxge_io_resume(struct pci_dev *pdev)
{
4092
	struct __vxge_hw_device *hldev = pci_get_drvdata(pdev);
4093 4094 4095 4096
	struct net_device *netdev = hldev->ndev;

	if (netif_running(netdev)) {
		if (vxge_open(netdev)) {
4097 4098
			netdev_err(netdev,
				   "Can't bring device back up after reset\n");
4099 4100 4101 4102 4103 4104 4105
			return;
		}
	}

	netif_device_attach(netdev);
}

4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135
static inline u32 vxge_get_num_vfs(u64 function_mode)
{
	u32 num_functions = 0;

	switch (function_mode) {
	case VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION:
	case VXGE_HW_FUNCTION_MODE_SRIOV_8:
		num_functions = 8;
		break;
	case VXGE_HW_FUNCTION_MODE_SINGLE_FUNCTION:
		num_functions = 1;
		break;
	case VXGE_HW_FUNCTION_MODE_SRIOV:
	case VXGE_HW_FUNCTION_MODE_MRIOV:
	case VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION_17:
		num_functions = 17;
		break;
	case VXGE_HW_FUNCTION_MODE_SRIOV_4:
		num_functions = 4;
		break;
	case VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION_2:
		num_functions = 2;
		break;
	case VXGE_HW_FUNCTION_MODE_MRIOV_8:
		num_functions = 8; /* TODO */
		break;
	}
	return num_functions;
}

4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200
int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override)
{
	struct __vxge_hw_device *hldev = vdev->devh;
	u32 maj, min, bld, cmaj, cmin, cbld;
	enum vxge_hw_status status;
	const struct firmware *fw;
	int ret;

	ret = request_firmware(&fw, fw_name, &vdev->pdev->dev);
	if (ret) {
		vxge_debug_init(VXGE_ERR, "%s: Firmware file '%s' not found",
				VXGE_DRIVER_NAME, fw_name);
		goto out;
	}

	/* Load the new firmware onto the adapter */
	status = vxge_update_fw_image(hldev, fw->data, fw->size);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
				"%s: FW image download to adapter failed '%s'.",
				VXGE_DRIVER_NAME, fw_name);
		ret = -EIO;
		goto out;
	}

	/* Read the version of the new firmware */
	status = vxge_hw_upgrade_read_version(hldev, &maj, &min, &bld);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
				"%s: Upgrade read version failed '%s'.",
				VXGE_DRIVER_NAME, fw_name);
		ret = -EIO;
		goto out;
	}

	cmaj = vdev->config.device_hw_info.fw_version.major;
	cmin = vdev->config.device_hw_info.fw_version.minor;
	cbld = vdev->config.device_hw_info.fw_version.build;
	/* It's possible the version in /lib/firmware is not the latest version.
	 * If so, we could get into a loop of trying to upgrade to the latest
	 * and flashing the older version.
	 */
	if (VXGE_FW_VER(maj, min, bld) == VXGE_FW_VER(cmaj, cmin, cbld) &&
	    !override) {
		ret = -EINVAL;
		goto out;
	}

	printk(KERN_NOTICE "Upgrade to firmware version %d.%d.%d commencing\n",
	       maj, min, bld);

	/* Flash the adapter with the new firmware */
	status = vxge_hw_flash_fw(hldev);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR, "%s: Upgrade commit failed '%s'.",
				VXGE_DRIVER_NAME, fw_name);
		ret = -EIO;
		goto out;
	}

	printk(KERN_NOTICE "Upgrade of firmware successful!  Adapter must be "
	       "hard reset before using, thus requiring a system reboot or a "
	       "hotplug event.\n");

out:
4201
	release_firmware(fw);
4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272
	return ret;
}

static int vxge_probe_fw_update(struct vxgedev *vdev)
{
	u32 maj, min, bld;
	int ret, gpxe = 0;
	char *fw_name;

	maj = vdev->config.device_hw_info.fw_version.major;
	min = vdev->config.device_hw_info.fw_version.minor;
	bld = vdev->config.device_hw_info.fw_version.build;

	if (VXGE_FW_VER(maj, min, bld) == VXGE_CERT_FW_VER)
		return 0;

	/* Ignore the build number when determining if the current firmware is
	 * "too new" to load the driver
	 */
	if (VXGE_FW_VER(maj, min, 0) > VXGE_CERT_FW_VER) {
		vxge_debug_init(VXGE_ERR, "%s: Firmware newer than last known "
				"version, unable to load driver\n",
				VXGE_DRIVER_NAME);
		return -EINVAL;
	}

	/* Firmware 1.4.4 and older cannot be upgraded, and is too ancient to
	 * work with this driver.
	 */
	if (VXGE_FW_VER(maj, min, bld) <= VXGE_FW_DEAD_VER) {
		vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d cannot be "
				"upgraded\n", VXGE_DRIVER_NAME, maj, min, bld);
		return -EINVAL;
	}

	/* If file not specified, determine gPXE or not */
	if (VXGE_FW_VER(maj, min, bld) >= VXGE_EPROM_FW_VER) {
		int i;
		for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++)
			if (vdev->devh->eprom_versions[i]) {
				gpxe = 1;
				break;
			}
	}
	if (gpxe)
		fw_name = "vxge/X3fw-pxe.ncf";
	else
		fw_name = "vxge/X3fw.ncf";

	ret = vxge_fw_upgrade(vdev, fw_name, 0);
	/* -EINVAL and -ENOENT are not fatal errors for flashing firmware on
	 * probe, so ignore them
	 */
	if (ret != -EINVAL && ret != -ENOENT)
		return -EIO;
	else
		ret = 0;

	if (VXGE_FW_VER(VXGE_CERT_FW_VER_MAJOR, VXGE_CERT_FW_VER_MINOR, 0) >
	    VXGE_FW_VER(maj, min, 0)) {
		vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d is too old to"
				" be used with this driver.\n"
				"Please get the latest version from "
				"ftp://ftp.s2io.com/pub/X3100-Drivers/FIRMWARE",
				VXGE_DRIVER_NAME, maj, min, bld);
		return -EINVAL;
	}

	return ret;
}

4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286
static int __devinit is_sriov_initialized(struct pci_dev *pdev)
{
	int pos;
	u16 ctrl;

	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
	if (pos) {
		pci_read_config_word(pdev, pos + PCI_SRIOV_CTRL, &ctrl);
		if (ctrl & PCI_SRIOV_CTRL_VFE)
			return 1;
	}
	return 0;
}

4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300
/**
 * vxge_probe
 * @pdev : structure containing the PCI related information of the device.
 * @pre: List of PCI devices supported by the driver listed in vxge_id_table.
 * Description:
 * This function is called when a new PCI device gets detected and initializes
 * it.
 * Return value:
 * returns 0 on success and negative on failure.
 *
 */
static int __devinit
vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
{
J
Jon Mason 已提交
4301
	struct __vxge_hw_device *hldev;
4302 4303 4304 4305 4306
	enum vxge_hw_status status;
	int ret;
	int high_dma = 0;
	u64 vpath_mask = 0;
	struct vxgedev *vdev;
4307
	struct vxge_config *ll_config = NULL;
4308 4309 4310 4311 4312 4313
	struct vxge_hw_device_config *device_config = NULL;
	struct vxge_hw_device_attr attr;
	int i, j, no_of_vpath = 0, max_vpath_supported = 0;
	u8 *macaddr;
	struct vxge_mac_addrs *entry;
	static int bus = -1, device = -1;
4314
	u32 host_type;
4315
	u8 new_device = 0;
4316 4317 4318
	enum vxge_hw_status is_privileged;
	u32 function_mode;
	u32 num_vfs = 0;
4319 4320 4321 4322

	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
	attr.pdev = pdev;

4323
	/* In SRIOV-17 mode, functions of the same adapter
J
Jon Mason 已提交
4324 4325 4326 4327
	 * can be deployed on different buses
	 */
	if (((bus != pdev->bus->number) || (device != PCI_SLOT(pdev->devfn))) &&
	    !pdev->is_virtfn)
4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344
		new_device = 1;

	bus = pdev->bus->number;
	device = PCI_SLOT(pdev->devfn);

	if (new_device) {
		if (driver_config->config_dev_cnt &&
		   (driver_config->config_dev_cnt !=
			driver_config->total_dev_cnt))
			vxge_debug_init(VXGE_ERR,
				"%s: Configured %d of %d devices",
				VXGE_DRIVER_NAME,
				driver_config->config_dev_cnt,
				driver_config->total_dev_cnt);
		driver_config->config_dev_cnt = 0;
		driver_config->total_dev_cnt = 0;
	}
J
Jon Mason 已提交
4345

4346 4347 4348 4349
	/* Now making the CPU based no of vpath calculation
	 * applicable for individual functions as well.
	 */
	driver_config->g_no_cpus = 0;
4350 4351
	driver_config->vpath_per_dev = max_config_vpath;

4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367
	driver_config->total_dev_cnt++;
	if (++driver_config->config_dev_cnt > max_config_dev) {
		ret = 0;
		goto _exit0;
	}

	device_config = kzalloc(sizeof(struct vxge_hw_device_config),
		GFP_KERNEL);
	if (!device_config) {
		ret = -ENOMEM;
		vxge_debug_init(VXGE_ERR,
			"device_config : malloc failed %s %d",
			__FILE__, __LINE__);
		goto _exit0;
	}

J
Jon Mason 已提交
4368
	ll_config = kzalloc(sizeof(struct vxge_config), GFP_KERNEL);
4369 4370 4371
	if (!ll_config) {
		ret = -ENOMEM;
		vxge_debug_init(VXGE_ERR,
J
Jon Mason 已提交
4372
			"device_config : malloc failed %s %d",
4373 4374 4375 4376 4377 4378 4379
			__FILE__, __LINE__);
		goto _exit0;
	}
	ll_config->tx_steering_type = TX_MULTIQ_STEERING;
	ll_config->intr_type = MSI_X;
	ll_config->napi_weight = NEW_NAPI_WEIGHT;
	ll_config->rth_steering = RTH_STEERING;
4380 4381 4382 4383 4384

	/* get the default configuration parameters */
	vxge_hw_device_config_default_get(device_config);

	/* initialize configuration parameters */
4385
	vxge_device_config_init(device_config, &ll_config->intr_type);
4386 4387 4388 4389 4390 4391 4392 4393

	ret = pci_enable_device(pdev);
	if (ret) {
		vxge_debug_init(VXGE_ERR,
			"%s : can not enable PCI device", __func__);
		goto _exit0;
	}

4394
	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
4395 4396 4397 4398 4399 4400
		vxge_debug_ll_config(VXGE_TRACE,
			"%s : using 64bit DMA", __func__);

		high_dma = 1;

		if (pci_set_consistent_dma_mask(pdev,
4401
						DMA_BIT_MASK(64))) {
4402 4403 4404 4405 4406 4407
			vxge_debug_init(VXGE_ERR,
				"%s : unable to obtain 64bit DMA for "
				"consistent allocations", __func__);
			ret = -ENOMEM;
			goto _exit1;
		}
4408
	} else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
4409 4410 4411 4412 4413 4414 4415
		vxge_debug_ll_config(VXGE_TRACE,
			"%s : using 32bit DMA", __func__);
	} else {
		ret = -ENOMEM;
		goto _exit1;
	}

J
Jon Mason 已提交
4416 4417
	ret = pci_request_region(pdev, 0, VXGE_DRIVER_NAME);
	if (ret) {
4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437
		vxge_debug_init(VXGE_ERR,
			"%s : request regions failed", __func__);
		goto _exit1;
	}

	pci_set_master(pdev);

	attr.bar0 = pci_ioremap_bar(pdev, 0);
	if (!attr.bar0) {
		vxge_debug_init(VXGE_ERR,
			"%s : cannot remap io memory bar0", __func__);
		ret = -ENODEV;
		goto _exit2;
	}
	vxge_debug_ll_config(VXGE_TRACE,
		"pci ioremap bar0: %p:0x%llx",
		attr.bar0,
		(unsigned long long)pci_resource_start(pdev, 0));

	status = vxge_hw_device_hw_info_get(attr.bar0,
4438
			&ll_config->device_hw_info);
4439 4440 4441 4442 4443
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"%s: Reading of hardware info failed."
			"Please try upgrading the firmware.", VXGE_DRIVER_NAME);
		ret = -EINVAL;
4444
		goto _exit3;
4445 4446
	}

4447
	vpath_mask = ll_config->device_hw_info.vpath_mask;
4448 4449 4450 4451
	if (vpath_mask == 0) {
		vxge_debug_ll_config(VXGE_TRACE,
			"%s: No vpaths available in device", VXGE_DRIVER_NAME);
		ret = -EINVAL;
4452
		goto _exit3;
4453 4454 4455 4456 4457 4458
	}

	vxge_debug_ll_config(VXGE_TRACE,
		"%s:%d  Vpath mask = %llx", __func__, __LINE__,
		(unsigned long long)vpath_mask);

4459 4460
	function_mode = ll_config->device_hw_info.function_mode;
	host_type = ll_config->device_hw_info.host_type;
4461
	is_privileged = __vxge_hw_device_is_privilaged(host_type,
4462
		ll_config->device_hw_info.func_id);
4463

4464 4465 4466 4467 4468 4469 4470
	/* Check how many vpaths are available */
	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
		if (!((vpath_mask) & vxge_mBIT(i)))
			continue;
		max_vpath_supported++;
	}

4471 4472 4473
	if (new_device)
		num_vfs = vxge_get_num_vfs(function_mode) - 1;

4474
	/* Enable SRIOV mode, if firmware has SRIOV support and if it is a PF */
4475 4476 4477
	if (is_sriov(function_mode) && !is_sriov_initialized(pdev) &&
	   (ll_config->intr_type != INTA)) {
		ret = pci_enable_sriov(pdev, num_vfs);
4478 4479 4480
		if (ret)
			vxge_debug_ll_config(VXGE_ERR,
				"Failed in enabling SRIOV mode: %d\n", ret);
4481
			/* No need to fail out, as an error here is non-fatal */
4482 4483
	}

4484 4485 4486 4487
	/*
	 * Configure vpaths and get driver configured number of vpaths
	 * which is less than or equal to the maximum vpaths per function.
	 */
4488
	no_of_vpath = vxge_config_vpaths(device_config, vpath_mask, ll_config);
4489 4490 4491 4492
	if (!no_of_vpath) {
		vxge_debug_ll_config(VXGE_ERR,
			"%s: No more vpaths to configure", VXGE_DRIVER_NAME);
		ret = 0;
4493
		goto _exit3;
4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505
	}

	/* Setting driver callbacks */
	attr.uld_callbacks.link_up = vxge_callback_link_up;
	attr.uld_callbacks.link_down = vxge_callback_link_down;
	attr.uld_callbacks.crit_err = vxge_callback_crit_err;

	status = vxge_hw_device_initialize(&hldev, &attr, device_config);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR,
			"Failed to initialize device (%d)", status);
			ret = -EINVAL;
4506
			goto _exit3;
4507 4508
	}

4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526
	if (VXGE_FW_VER(ll_config->device_hw_info.fw_version.major,
			ll_config->device_hw_info.fw_version.minor,
			ll_config->device_hw_info.fw_version.build) >=
	    VXGE_EPROM_FW_VER) {
		struct eprom_image img[VXGE_HW_MAX_ROM_IMAGES];

		status = vxge_hw_vpath_eprom_img_ver_get(hldev, img);
		if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR, "%s: Reading of EPROM failed",
					VXGE_DRIVER_NAME);
			/* This is a non-fatal error, continue */
		}

		for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) {
			hldev->eprom_versions[i] = img[i].version;
			if (!img[i].is_valid)
				break;
			vxge_debug_init(VXGE_TRACE, "%s: EPROM %d, version "
4527
					"%d.%d.%d.%d", VXGE_DRIVER_NAME, i,
4528 4529 4530 4531 4532 4533 4534
					VXGE_EPROM_IMG_MAJOR(img[i].version),
					VXGE_EPROM_IMG_MINOR(img[i].version),
					VXGE_EPROM_IMG_FIX(img[i].version),
					VXGE_EPROM_IMG_BUILD(img[i].version));
		}
	}

4535
	/* if FCS stripping is not disabled in MAC fail driver load */
4536 4537 4538 4539
	status = vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask);
	if (status != VXGE_HW_OK) {
		vxge_debug_init(VXGE_ERR, "%s: FCS stripping is enabled in MAC"
				" failing driver load", VXGE_DRIVER_NAME);
4540 4541 4542 4543
		ret = -EINVAL;
		goto _exit4;
	}

4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561
	/* Always enable HWTS.  This will always cause the FCS to be invalid,
	 * due to the fact that HWTS is using the FCS as the location of the
	 * timestamp.  The HW FCS checking will still correctly determine if
	 * there is a valid checksum, and the FCS is being removed by the driver
	 * anyway.  So no fucntionality is being lost.  Since it is always
	 * enabled, we now simply use the ioctl call to set whether or not the
	 * driver should be paying attention to the HWTS.
	 */
	if (is_privileged == VXGE_HW_OK) {
		status = vxge_timestamp_config(hldev);
		if (status != VXGE_HW_OK) {
			vxge_debug_init(VXGE_ERR, "%s: HWTS enable failed",
					VXGE_DRIVER_NAME);
			ret = -EFAULT;
			goto _exit4;
		}
	}

4562 4563 4564 4565 4566
	vxge_hw_device_debug_set(hldev, VXGE_ERR, VXGE_COMPONENT_LL);

	/* set private device info */
	pci_set_drvdata(pdev, hldev);

4567 4568 4569
	ll_config->fifo_indicate_max_pkts = VXGE_FIFO_INDICATE_MAX_PKTS;
	ll_config->addr_learn_en = addr_learn_en;
	ll_config->rth_algorithm = RTH_ALG_JENKINS;
J
Jon Mason 已提交
4570 4571 4572 4573 4574 4575
	ll_config->rth_hash_type_tcpipv4 = 1;
	ll_config->rth_hash_type_ipv4 = 0;
	ll_config->rth_hash_type_tcpipv6 = 0;
	ll_config->rth_hash_type_ipv6 = 0;
	ll_config->rth_hash_type_tcpipv6ex = 0;
	ll_config->rth_hash_type_ipv6ex = 0;
4576 4577 4578 4579
	ll_config->rth_bkt_sz = RTH_BUCKET_SIZE;
	ll_config->tx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
	ll_config->rx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;

4580 4581 4582
	ret = vxge_device_register(hldev, ll_config, high_dma, no_of_vpath,
				   &vdev);
	if (ret) {
4583
		ret = -EINVAL;
4584
		goto _exit4;
4585 4586
	}

4587 4588 4589 4590
	ret = vxge_probe_fw_update(vdev);
	if (ret)
		goto _exit5;

4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613
	vxge_hw_device_debug_set(hldev, VXGE_TRACE, VXGE_COMPONENT_LL);
	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev),
		vxge_hw_device_trace_level_get(hldev));

	/* set private HW device info */
	vdev->mtu = VXGE_HW_DEFAULT_MTU;
	vdev->bar0 = attr.bar0;
	vdev->max_vpath_supported = max_vpath_supported;
	vdev->no_of_vpath = no_of_vpath;

	/* Virtual Path count */
	for (i = 0, j = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
		if (!vxge_bVALn(vpath_mask, i, 1))
			continue;
		if (j >= vdev->no_of_vpath)
			break;

		vdev->vpaths[j].is_configured = 1;
		vdev->vpaths[j].device_id = i;
		vdev->vpaths[j].ring.driver_id = j;
		vdev->vpaths[j].vdev = vdev;
		vdev->vpaths[j].max_mac_addr_cnt = max_mac_vpath;
		memcpy((u8 *)vdev->vpaths[j].macaddr,
4614
				ll_config->device_hw_info.mac_addrs[i],
4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634
				ETH_ALEN);

		/* Initialize the mac address list header */
		INIT_LIST_HEAD(&vdev->vpaths[j].mac_addr_list);

		vdev->vpaths[j].mac_addr_cnt = 0;
		vdev->vpaths[j].mcast_addr_cnt = 0;
		j++;
	}
	vdev->exec_mode = VXGE_EXEC_MODE_DISABLE;
	vdev->max_config_port = max_config_port;

	vdev->vlan_tag_strip = vlan_tag_strip;

	/* map the hashing selector table to the configured vpaths */
	for (i = 0; i < vdev->no_of_vpath; i++)
		vdev->vpath_selector[i] = vpath_selector[i];

	macaddr = (u8 *)vdev->vpaths[0].macaddr;

4635 4636 4637
	ll_config->device_hw_info.serial_number[VXGE_HW_INFO_LEN - 1] = '\0';
	ll_config->device_hw_info.product_desc[VXGE_HW_INFO_LEN - 1] = '\0';
	ll_config->device_hw_info.part_number[VXGE_HW_INFO_LEN - 1] = '\0';
4638 4639

	vxge_debug_init(VXGE_TRACE, "%s: SERIAL NUMBER: %s",
4640
		vdev->ndev->name, ll_config->device_hw_info.serial_number);
4641 4642

	vxge_debug_init(VXGE_TRACE, "%s: PART NUMBER: %s",
4643
		vdev->ndev->name, ll_config->device_hw_info.part_number);
4644 4645

	vxge_debug_init(VXGE_TRACE, "%s: Neterion %s Server Adapter",
4646
		vdev->ndev->name, ll_config->device_hw_info.product_desc);
4647

4648 4649
	vxge_debug_init(VXGE_TRACE, "%s: MAC ADDR: %pM",
		vdev->ndev->name, macaddr);
4650 4651 4652 4653 4654 4655

	vxge_debug_init(VXGE_TRACE, "%s: Link Width x%d",
		vdev->ndev->name, vxge_hw_device_link_width_get(hldev));

	vxge_debug_init(VXGE_TRACE,
		"%s: Firmware version : %s Date : %s", vdev->ndev->name,
4656 4657
		ll_config->device_hw_info.fw_version.version,
		ll_config->device_hw_info.fw_date.date);
4658

4659
	if (new_device) {
4660
		switch (ll_config->device_hw_info.function_mode) {
4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679
		case VXGE_HW_FUNCTION_MODE_SINGLE_FUNCTION:
			vxge_debug_init(VXGE_TRACE,
			"%s: Single Function Mode Enabled", vdev->ndev->name);
		break;
		case VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION:
			vxge_debug_init(VXGE_TRACE,
			"%s: Multi Function Mode Enabled", vdev->ndev->name);
		break;
		case VXGE_HW_FUNCTION_MODE_SRIOV:
			vxge_debug_init(VXGE_TRACE,
			"%s: Single Root IOV Mode Enabled", vdev->ndev->name);
		break;
		case VXGE_HW_FUNCTION_MODE_MRIOV:
			vxge_debug_init(VXGE_TRACE,
			"%s: Multi Root IOV Mode Enabled", vdev->ndev->name);
		break;
		}
	}

4680 4681 4682
	vxge_print_parm(vdev, vpath_mask);

	/* Store the fw version for ethttool option */
4683
	strcpy(vdev->fw_version, ll_config->device_hw_info.fw_version.version);
4684 4685 4686 4687 4688
	memcpy(vdev->ndev->dev_addr, (u8 *)vdev->vpaths[0].macaddr, ETH_ALEN);
	memcpy(vdev->ndev->perm_addr, vdev->ndev->dev_addr, ETH_ALEN);

	/* Copy the station mac address to the list */
	for (i = 0; i < vdev->no_of_vpath; i++) {
4689
		entry =	kzalloc(sizeof(struct vxge_mac_addrs), GFP_KERNEL);
4690 4691 4692 4693 4694
		if (NULL == entry) {
			vxge_debug_init(VXGE_ERR,
				"%s: mac_addr_list : memory allocation failed",
				vdev->ndev->name);
			ret = -EPERM;
4695
			goto _exit6;
4696 4697 4698 4699 4700 4701 4702
		}
		macaddr = (u8 *)&entry->macaddr;
		memcpy(macaddr, vdev->ndev->dev_addr, ETH_ALEN);
		list_add(&entry->item, &vdev->vpaths[i].mac_addr_list);
		vdev->vpaths[i].mac_addr_cnt = 1;
	}

4703
	kfree(device_config);
4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719

	/*
	 * INTA is shared in multi-function mode. This is unlike the INTA
	 * implementation in MR mode, where each VH has its own INTA message.
	 * - INTA is masked (disabled) as long as at least one function sets
	 * its TITAN_MASK_ALL_INT.ALARM bit.
	 * - INTA is unmasked (enabled) when all enabled functions have cleared
	 * their own TITAN_MASK_ALL_INT.ALARM bit.
	 * The TITAN_MASK_ALL_INT ALARM & TRAFFIC bits are cleared on power up.
	 * Though this driver leaves the top level interrupts unmasked while
	 * leaving the required module interrupt bits masked on exit, there
	 * could be a rougue driver around that does not follow this procedure
	 * resulting in a failure to generate interrupts. The following code is
	 * present to prevent such a failure.
	 */

4720
	if (ll_config->device_hw_info.function_mode ==
4721 4722 4723 4724
		VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION)
		if (vdev->config.intr_type == INTA)
			vxge_hw_device_unmask_all(hldev);

4725 4726 4727 4728 4729 4730 4731
	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d  Exiting...",
		vdev->ndev->name, __func__, __LINE__);

	vxge_hw_device_debug_set(hldev, VXGE_ERR, VXGE_COMPONENT_LL);
	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev),
		vxge_hw_device_trace_level_get(hldev));

4732
	kfree(ll_config);
4733 4734
	return 0;

4735
_exit6:
4736 4737
	for (i = 0; i < vdev->no_of_vpath; i++)
		vxge_free_mac_add_list(&vdev->vpaths[i]);
4738
_exit5:
4739
	vxge_device_unregister(hldev);
4740
_exit4:
J
Jon Mason 已提交
4741
	pci_set_drvdata(pdev, NULL);
4742
	vxge_hw_device_terminate(hldev);
J
Jon Mason 已提交
4743
	pci_disable_sriov(pdev);
4744 4745 4746
_exit3:
	iounmap(attr.bar0);
_exit2:
J
Jon Mason 已提交
4747
	pci_release_region(pdev, 0);
4748 4749 4750
_exit1:
	pci_disable_device(pdev);
_exit0:
4751
	kfree(ll_config);
4752 4753
	kfree(device_config);
	driver_config->config_dev_cnt--;
J
Jon Mason 已提交
4754
	driver_config->total_dev_cnt--;
4755 4756 4757 4758 4759 4760 4761 4762 4763
	return ret;
}

/**
 * vxge_rem_nic - Free the PCI device
 * @pdev: structure containing the PCI related information of the device.
 * Description: This function is called by the Pci subsystem to release a
 * PCI device and free up all resource held up by the device.
 */
J
Jon Mason 已提交
4764
static void __devexit vxge_remove(struct pci_dev *pdev)
4765
{
J
Jon Mason 已提交
4766
	struct __vxge_hw_device *hldev;
J
Jon Mason 已提交
4767 4768
	struct vxgedev *vdev;
	int i;
4769

4770
	hldev = pci_get_drvdata(pdev);
4771 4772
	if (hldev == NULL)
		return;
J
Jon Mason 已提交
4773

J
Jon Mason 已提交
4774
	vdev = netdev_priv(hldev->ndev);
4775

J
Jon Mason 已提交
4776 4777 4778
	vxge_debug_entryexit(vdev->level_trace,	"%s:%d", __func__, __LINE__);
	vxge_debug_init(vdev->level_trace, "%s : removing PCI device...",
			__func__);
4779

J
Jon Mason 已提交
4780
	for (i = 0; i < vdev->no_of_vpath; i++)
4781 4782
		vxge_free_mac_add_list(&vdev->vpaths[i]);

J
Jon Mason 已提交
4783 4784 4785 4786
	vxge_device_unregister(hldev);
	pci_set_drvdata(pdev, NULL);
	/* Do not call pci_disable_sriov here, as it will break child devices */
	vxge_hw_device_terminate(hldev);
4787
	iounmap(vdev->bar0);
J
Jon Mason 已提交
4788 4789 4790 4791
	pci_release_region(pdev, 0);
	pci_disable_device(pdev);
	driver_config->config_dev_cnt--;
	driver_config->total_dev_cnt--;
4792

J
Jon Mason 已提交
4793 4794 4795 4796
	vxge_debug_init(vdev->level_trace, "%s:%d Device unregistered",
			__func__, __LINE__);
	vxge_debug_entryexit(vdev->level_trace,	"%s:%d  Exiting...", __func__,
			     __LINE__);
4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821
}

static struct pci_error_handlers vxge_err_handler = {
	.error_detected = vxge_io_error_detected,
	.slot_reset = vxge_io_slot_reset,
	.resume = vxge_io_resume,
};

static struct pci_driver vxge_driver = {
	.name = VXGE_DRIVER_NAME,
	.id_table = vxge_id_table,
	.probe = vxge_probe,
	.remove = __devexit_p(vxge_remove),
#ifdef CONFIG_PM
	.suspend = vxge_pm_suspend,
	.resume = vxge_pm_resume,
#endif
	.err_handler = &vxge_err_handler,
};

static int __init
vxge_starter(void)
{
	int ret = 0;

4822 4823
	pr_info("Copyright(c) 2002-2010 Exar Corp.\n");
	pr_info("Driver version: %s\n", DRV_VERSION);
4824 4825 4826 4827 4828 4829 4830 4831

	verify_bandwidth();

	driver_config = kzalloc(sizeof(struct vxge_drv_config), GFP_KERNEL);
	if (!driver_config)
		return -ENOMEM;

	ret = pci_register_driver(&vxge_driver);
J
Jon Mason 已提交
4832 4833 4834 4835
	if (ret) {
		kfree(driver_config);
		goto err;
	}
4836 4837 4838 4839 4840 4841 4842

	if (driver_config->config_dev_cnt &&
	   (driver_config->config_dev_cnt != driver_config->total_dev_cnt))
		vxge_debug_init(VXGE_ERR,
			"%s: Configured %d of %d devices",
			VXGE_DRIVER_NAME, driver_config->config_dev_cnt,
			driver_config->total_dev_cnt);
J
Jon Mason 已提交
4843
err:
4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854
	return ret;
}

static void __exit
vxge_closer(void)
{
	pci_unregister_driver(&vxge_driver);
	kfree(driver_config);
}
module_init(vxge_starter);
module_exit(vxge_closer);