ibmvnic.c 98.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
/**************************************************************************/
/*                                                                        */
/*  IBM System i and System p Virtual NIC Device Driver                   */
/*  Copyright (C) 2014 IBM Corp.                                          */
/*  Santiago Leon (santi_leon@yahoo.com)                                  */
/*  Thomas Falcon (tlfalcon@linux.vnet.ibm.com)                           */
/*  John Allen (jallen@linux.vnet.ibm.com)                                */
/*                                                                        */
/*  This program is free software; you can redistribute it and/or modify  */
/*  it under the terms of the GNU General Public License as published by  */
/*  the Free Software Foundation; either version 2 of the License, or     */
/*  (at your option) any later version.                                   */
/*                                                                        */
/*  This program is distributed in the hope that it will be useful,       */
/*  but WITHOUT ANY WARRANTY; without even the implied warranty of        */
/*  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         */
/*  GNU General Public License for more details.                          */
/*                                                                        */
/*  You should have received a copy of the GNU General Public License     */
/*  along with this program.                                              */
/*                                                                        */
/* This module contains the implementation of a virtual ethernet device   */
/* for use with IBM i/p Series LPAR Linux. It utilizes the logical LAN    */
/* option of the RS/6000 Platform Architecture to interface with virtual  */
/* ethernet NICs that are presented to the partition by the hypervisor.   */
/*									   */
/* Messages are passed between the VNIC driver and the VNIC server using  */
/* Command/Response Queues (CRQs) and sub CRQs (sCRQs). CRQs are used to  */
/* issue and receive commands that initiate communication with the server */
/* on driver initialization. Sub CRQs (sCRQs) are similar to CRQs, but    */
/* are used by the driver to notify the server that a packet is           */
/* ready for transmission or that a buffer has been added to receive a    */
/* packet. Subsequently, sCRQs are used by the server to notify the       */
/* driver that a packet transmission has been completed or that a packet  */
/* has been received and placed in a waiting buffer.                      */
/*                                                                        */
/* In lieu of a more conventional "on-the-fly" DMA mapping strategy in    */
/* which skbs are DMA mapped and immediately unmapped when the transmit   */
/* or receive has been completed, the VNIC driver is required to use      */
/* "long term mapping". This entails that large, continuous DMA mapped    */
/* buffers are allocated on driver initialization and these buffers are   */
/* then continuously reused to pass skbs to and from the VNIC server.     */
/*                                                                        */
/**************************************************************************/

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/completion.h>
#include <linux/ioport.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/ethtool.h>
#include <linux/proc_fs.h>
#include <linux/in.h>
#include <linux/ip.h>
64
#include <linux/ipv6.h>
65 66 67 68 69 70 71 72 73 74 75
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <net/net_namespace.h>
#include <asm/hvcall.h>
#include <linux/atomic.h>
#include <asm/vio.h>
#include <asm/iommu.h>
#include <linux/uaccess.h>
#include <asm/firmware.h>
76
#include <linux/workqueue.h>
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96

#include "ibmvnic.h"

static const char ibmvnic_driver_name[] = "ibmvnic";
static const char ibmvnic_driver_string[] = "IBM System i/p Virtual NIC Driver";

MODULE_AUTHOR("Santiago Leon <santi_leon@yahoo.com>");
MODULE_DESCRIPTION("IBM System i/p Virtual NIC Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(IBMVNIC_DRIVER_VERSION);

static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
static int ibmvnic_remove(struct vio_dev *);
static void release_sub_crqs(struct ibmvnic_adapter *);
static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *);
static int ibmvnic_send_crq(struct ibmvnic_adapter *, union ibmvnic_crq *);
static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
		       union sub_crq *sub_crq);
97
static int send_subcrq_indirect(struct ibmvnic_adapter *, u64, u64, u64);
98 99 100 101 102 103 104 105 106 107 108 109 110
static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance);
static int enable_scrq_irq(struct ibmvnic_adapter *,
			   struct ibmvnic_sub_crq_queue *);
static int disable_scrq_irq(struct ibmvnic_adapter *,
			    struct ibmvnic_sub_crq_queue *);
static int pending_scrq(struct ibmvnic_adapter *,
			struct ibmvnic_sub_crq_queue *);
static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
					struct ibmvnic_sub_crq_queue *);
static int ibmvnic_poll(struct napi_struct *napi, int data);
static void send_map_query(struct ibmvnic_adapter *adapter);
static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
static void send_request_unmap(struct ibmvnic_adapter *, u8);
111 112 113
static void send_login(struct ibmvnic_adapter *adapter);
static void send_cap_queries(struct ibmvnic_adapter *adapter);
static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
114
static int ibmvnic_init(struct ibmvnic_adapter *);
115
static void release_crq_queue(struct ibmvnic_adapter *);
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179

struct ibmvnic_stat {
	char name[ETH_GSTRING_LEN];
	int offset;
};

#define IBMVNIC_STAT_OFF(stat) (offsetof(struct ibmvnic_adapter, stats) + \
			     offsetof(struct ibmvnic_statistics, stat))
#define IBMVNIC_GET_STAT(a, off) (*((u64 *)(((unsigned long)(a)) + off)))

static const struct ibmvnic_stat ibmvnic_stats[] = {
	{"rx_packets", IBMVNIC_STAT_OFF(rx_packets)},
	{"rx_bytes", IBMVNIC_STAT_OFF(rx_bytes)},
	{"tx_packets", IBMVNIC_STAT_OFF(tx_packets)},
	{"tx_bytes", IBMVNIC_STAT_OFF(tx_bytes)},
	{"ucast_tx_packets", IBMVNIC_STAT_OFF(ucast_tx_packets)},
	{"ucast_rx_packets", IBMVNIC_STAT_OFF(ucast_rx_packets)},
	{"mcast_tx_packets", IBMVNIC_STAT_OFF(mcast_tx_packets)},
	{"mcast_rx_packets", IBMVNIC_STAT_OFF(mcast_rx_packets)},
	{"bcast_tx_packets", IBMVNIC_STAT_OFF(bcast_tx_packets)},
	{"bcast_rx_packets", IBMVNIC_STAT_OFF(bcast_rx_packets)},
	{"align_errors", IBMVNIC_STAT_OFF(align_errors)},
	{"fcs_errors", IBMVNIC_STAT_OFF(fcs_errors)},
	{"single_collision_frames", IBMVNIC_STAT_OFF(single_collision_frames)},
	{"multi_collision_frames", IBMVNIC_STAT_OFF(multi_collision_frames)},
	{"sqe_test_errors", IBMVNIC_STAT_OFF(sqe_test_errors)},
	{"deferred_tx", IBMVNIC_STAT_OFF(deferred_tx)},
	{"late_collisions", IBMVNIC_STAT_OFF(late_collisions)},
	{"excess_collisions", IBMVNIC_STAT_OFF(excess_collisions)},
	{"internal_mac_tx_errors", IBMVNIC_STAT_OFF(internal_mac_tx_errors)},
	{"carrier_sense", IBMVNIC_STAT_OFF(carrier_sense)},
	{"too_long_frames", IBMVNIC_STAT_OFF(too_long_frames)},
	{"internal_mac_rx_errors", IBMVNIC_STAT_OFF(internal_mac_rx_errors)},
};

static long h_reg_sub_crq(unsigned long unit_address, unsigned long token,
			  unsigned long length, unsigned long *number,
			  unsigned long *irq)
{
	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
	long rc;

	rc = plpar_hcall(H_REG_SUB_CRQ, retbuf, unit_address, token, length);
	*number = retbuf[0];
	*irq = retbuf[1];

	return rc;
}

static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
				struct ibmvnic_long_term_buff *ltb, int size)
{
	struct device *dev = &adapter->vdev->dev;

	ltb->size = size;
	ltb->buff = dma_alloc_coherent(dev, ltb->size, &ltb->addr,
				       GFP_KERNEL);

	if (!ltb->buff) {
		dev_err(dev, "Couldn't alloc long term buffer\n");
		return -ENOMEM;
	}
	ltb->map_id = adapter->map_id;
	adapter->map_id++;
180 181

	init_completion(&adapter->fw_done);
182 183 184 185 186 187 188 189 190 191 192
	send_request_map(adapter, ltb->addr,
			 ltb->size, ltb->map_id);
	wait_for_completion(&adapter->fw_done);
	return 0;
}

static void free_long_term_buff(struct ibmvnic_adapter *adapter,
				struct ibmvnic_long_term_buff *ltb)
{
	struct device *dev = &adapter->vdev->dev;

193 194 195
	if (!ltb->buff)
		return;

196 197
	if (!adapter->failover)
		send_request_unmap(adapter, ltb->map_id);
198
	dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr);
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
}

static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
			      struct ibmvnic_rx_pool *pool)
{
	int count = pool->size - atomic_read(&pool->available);
	struct device *dev = &adapter->vdev->dev;
	int buffers_added = 0;
	unsigned long lpar_rc;
	union sub_crq sub_crq;
	struct sk_buff *skb;
	unsigned int offset;
	dma_addr_t dma_addr;
	unsigned char *dst;
	u64 *handle_array;
	int shift = 0;
	int index;
	int i;

	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
				      be32_to_cpu(adapter->login_rsp_buf->
				      off_rxadd_subcrqs));

	for (i = 0; i < count; ++i) {
		skb = alloc_skb(pool->buff_size, GFP_ATOMIC);
		if (!skb) {
			dev_err(dev, "Couldn't replenish rx buff\n");
			adapter->replenish_no_mem++;
			break;
		}

		index = pool->free_map[pool->next_free];

		if (pool->rx_buff[index].skb)
			dev_err(dev, "Inconsistent free_map!\n");

		/* Copy the skb to the long term mapped DMA buffer */
		offset = index * pool->buff_size;
		dst = pool->long_term_buff.buff + offset;
		memset(dst, 0, pool->buff_size);
		dma_addr = pool->long_term_buff.addr + offset;
		pool->rx_buff[index].data = dst;

		pool->free_map[pool->next_free] = IBMVNIC_INVALID_MAP;
		pool->rx_buff[index].dma = dma_addr;
		pool->rx_buff[index].skb = skb;
		pool->rx_buff[index].pool_index = pool->index;
		pool->rx_buff[index].size = pool->buff_size;

		memset(&sub_crq, 0, sizeof(sub_crq));
		sub_crq.rx_add.first = IBMVNIC_CRQ_CMD;
		sub_crq.rx_add.correlator =
		    cpu_to_be64((u64)&pool->rx_buff[index]);
		sub_crq.rx_add.ioba = cpu_to_be32(dma_addr);
		sub_crq.rx_add.map_id = pool->long_term_buff.map_id;

		/* The length field of the sCRQ is defined to be 24 bits so the
		 * buffer size needs to be left shifted by a byte before it is
		 * converted to big endian to prevent the last byte from being
		 * truncated.
		 */
#ifdef __LITTLE_ENDIAN__
		shift = 8;
#endif
		sub_crq.rx_add.len = cpu_to_be32(pool->buff_size << shift);

		lpar_rc = send_subcrq(adapter, handle_array[pool->index],
				      &sub_crq);
		if (lpar_rc != H_SUCCESS)
			goto failure;

		buffers_added++;
		adapter->replenish_add_buff_success++;
		pool->next_free = (pool->next_free + 1) % pool->size;
	}
	atomic_add(buffers_added, &pool->available);
	return;

failure:
	dev_info(dev, "replenish pools failure\n");
	pool->free_map[pool->next_free] = index;
	pool->rx_buff[index].skb = NULL;
	if (!dma_mapping_error(dev, dma_addr))
		dma_unmap_single(dev, dma_addr, pool->buff_size,
				 DMA_FROM_DEVICE);

	dev_kfree_skb_any(skb);
	adapter->replenish_add_buff_failure++;
	atomic_add(buffers_added, &pool->available);
}

static void replenish_pools(struct ibmvnic_adapter *adapter)
{
	int i;

	if (adapter->migrated)
		return;

	adapter->replenish_task_cycles++;
	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
	     i++) {
		if (adapter->rx_pool[i].active)
			replenish_rx_pool(adapter, &adapter->rx_pool[i]);
	}
}

305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
static void release_stats_token(struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;

	if (!adapter->stats_token)
		return;

	dma_unmap_single(dev, adapter->stats_token,
			 sizeof(struct ibmvnic_statistics),
			 DMA_FROM_DEVICE);
	adapter->stats_token = 0;
}

static int init_stats_token(struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	dma_addr_t stok;

	stok = dma_map_single(dev, &adapter->stats,
			      sizeof(struct ibmvnic_statistics),
			      DMA_FROM_DEVICE);
	if (dma_mapping_error(dev, stok)) {
		dev_err(dev, "Couldn't map stats buffer\n");
		return -1;
	}

	adapter->stats_token = stok;
	return 0;
}

335
static void release_rx_pools(struct ibmvnic_adapter *adapter)
336
{
337 338 339
	struct ibmvnic_rx_pool *rx_pool;
	int rx_scrqs;
	int i, j;
340

341
	if (!adapter->rx_pool)
342 343
		return;

344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
	rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
	for (i = 0; i < rx_scrqs; i++) {
		rx_pool = &adapter->rx_pool[i];

		kfree(rx_pool->free_map);
		free_long_term_buff(adapter, &rx_pool->long_term_buff);

		if (!rx_pool->rx_buff)
		continue;

		for (j = 0; j < rx_pool->size; j++) {
			if (rx_pool->rx_buff[j].skb) {
				dev_kfree_skb_any(rx_pool->rx_buff[i].skb);
				rx_pool->rx_buff[i].skb = NULL;
			}
		}

		kfree(rx_pool->rx_buff);
	}

	kfree(adapter->rx_pool);
	adapter->rx_pool = NULL;
}

static int init_rx_pools(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_rx_pool *rx_pool;
	int rxadd_subcrqs;
	u64 *size_array;
	int i, j;

	rxadd_subcrqs =
		be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
		be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));

	adapter->rx_pool = kcalloc(rxadd_subcrqs,
				   sizeof(struct ibmvnic_rx_pool),
				   GFP_KERNEL);
	if (!adapter->rx_pool) {
		dev_err(dev, "Failed to allocate rx pools\n");
		return -1;
	}

	for (i = 0; i < rxadd_subcrqs; i++) {
		rx_pool = &adapter->rx_pool[i];

		netdev_dbg(adapter->netdev,
			   "Initializing rx_pool %d, %lld buffs, %lld bytes each\n",
			   i, adapter->req_rx_add_entries_per_subcrq,
			   be64_to_cpu(size_array[i]));

		rx_pool->size = adapter->req_rx_add_entries_per_subcrq;
		rx_pool->index = i;
		rx_pool->buff_size = be64_to_cpu(size_array[i]);
		rx_pool->active = 1;

		rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int),
					    GFP_KERNEL);
		if (!rx_pool->free_map) {
			release_rx_pools(adapter);
			return -1;
408
		}
409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430

		rx_pool->rx_buff = kcalloc(rx_pool->size,
					   sizeof(struct ibmvnic_rx_buff),
					   GFP_KERNEL);
		if (!rx_pool->rx_buff) {
			dev_err(dev, "Couldn't alloc rx buffers\n");
			release_rx_pools(adapter);
			return -1;
		}

		if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
					 rx_pool->size * rx_pool->buff_size)) {
			release_rx_pools(adapter);
			return -1;
		}

		for (j = 0; j < rx_pool->size; ++j)
			rx_pool->free_map[j] = j;

		atomic_set(&rx_pool->available, 0);
		rx_pool->next_alloc = 0;
		rx_pool->next_free = 0;
431
	}
432 433

	return 0;
434 435
}

436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504
static void release_tx_pools(struct ibmvnic_adapter *adapter)
{
	struct ibmvnic_tx_pool *tx_pool;
	int i, tx_scrqs;

	if (!adapter->tx_pool)
		return;

	tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
	for (i = 0; i < tx_scrqs; i++) {
		tx_pool = &adapter->tx_pool[i];
		kfree(tx_pool->tx_buff);
		free_long_term_buff(adapter, &tx_pool->long_term_buff);
		kfree(tx_pool->free_map);
	}

	kfree(adapter->tx_pool);
	adapter->tx_pool = NULL;
}

static int init_tx_pools(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_tx_pool *tx_pool;
	int tx_subcrqs;
	int i, j;

	tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
	adapter->tx_pool = kcalloc(tx_subcrqs,
				   sizeof(struct ibmvnic_tx_pool), GFP_KERNEL);
	if (!adapter->tx_pool)
		return -1;

	for (i = 0; i < tx_subcrqs; i++) {
		tx_pool = &adapter->tx_pool[i];
		tx_pool->tx_buff = kcalloc(adapter->req_tx_entries_per_subcrq,
					   sizeof(struct ibmvnic_tx_buff),
					   GFP_KERNEL);
		if (!tx_pool->tx_buff) {
			dev_err(dev, "tx pool buffer allocation failed\n");
			release_tx_pools(adapter);
			return -1;
		}

		if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff,
					 adapter->req_tx_entries_per_subcrq *
					 adapter->req_mtu)) {
			release_tx_pools(adapter);
			return -1;
		}

		tx_pool->free_map = kcalloc(adapter->req_tx_entries_per_subcrq,
					    sizeof(int), GFP_KERNEL);
		if (!tx_pool->free_map) {
			release_tx_pools(adapter);
			return -1;
		}

		for (j = 0; j < adapter->req_tx_entries_per_subcrq; j++)
			tx_pool->free_map[j] = j;

		tx_pool->consumer_index = 0;
		tx_pool->producer_index = 0;
	}

	return 0;
}

505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
static void release_bounce_buffer(struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;

	if (!adapter->bounce_buffer)
		return;

	if (!dma_mapping_error(dev, adapter->bounce_buffer_dma)) {
		dma_unmap_single(dev, adapter->bounce_buffer_dma,
				 adapter->bounce_buffer_size,
				 DMA_BIDIRECTIONAL);
		adapter->bounce_buffer_dma = DMA_ERROR_CODE;
	}

	kfree(adapter->bounce_buffer);
	adapter->bounce_buffer = NULL;
}

static int init_bounce_buffer(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct device *dev = &adapter->vdev->dev;
	char *buf;
	int buf_sz;
	dma_addr_t map_addr;

	buf_sz = (netdev->mtu + ETH_HLEN - 1) / PAGE_SIZE + 1;
	buf = kmalloc(adapter->bounce_buffer_size, GFP_KERNEL);
	if (!buf)
		return -1;

	map_addr = dma_map_single(dev, buf, buf_sz, DMA_TO_DEVICE);
	if (dma_mapping_error(dev, map_addr)) {
		dev_err(dev, "Couldn't map bounce buffer\n");
		kfree(buf);
		return -1;
	}

	adapter->bounce_buffer = buf;
	adapter->bounce_buffer_size = buf_sz;
	adapter->bounce_buffer_dma = map_addr;
	return 0;
}

549
static int ibmvnic_login(struct net_device *netdev)
550 551
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
552
	unsigned long timeout = msecs_to_jiffies(30000);
553 554
	struct device *dev = &adapter->vdev->dev;

555 556 557
	do {
		if (adapter->renegotiate) {
			adapter->renegotiate = false;
558
			release_sub_crqs(adapter);
559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577

			reinit_completion(&adapter->init_done);
			send_cap_queries(adapter);
			if (!wait_for_completion_timeout(&adapter->init_done,
							 timeout)) {
				dev_err(dev, "Capabilities query timeout\n");
				return -1;
			}
		}

		reinit_completion(&adapter->init_done);
		send_login(adapter);
		if (!wait_for_completion_timeout(&adapter->init_done,
						 timeout)) {
			dev_err(dev, "Login timeout\n");
			return -1;
		}
	} while (adapter->renegotiate);

578 579 580
	return 0;
}

581 582 583 584 585 586 587 588 589 590 591 592
static void release_resources(struct ibmvnic_adapter *adapter)
{
	release_bounce_buffer(adapter);
	release_tx_pools(adapter);
	release_rx_pools(adapter);

	release_sub_crqs(adapter);
	release_crq_queue(adapter);

	release_stats_token(adapter);
}

593 594 595 596 597 598
static int ibmvnic_open(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct device *dev = &adapter->vdev->dev;
	union ibmvnic_crq crq;
	int rc = 0;
599
	int i;
600

601 602 603 604 605 606
	if (adapter->is_closed) {
		rc = ibmvnic_init(adapter);
		if (rc)
			return rc;
	}

607 608 609 610
	rc = ibmvnic_login(netdev);
	if (rc)
		return rc;

611 612 613 614 615 616 617 618 619 620 621 622
	rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues);
	if (rc) {
		dev_err(dev, "failed to set the number of tx queues\n");
		return -1;
	}

	rc = init_sub_crq_irqs(adapter);
	if (rc) {
		dev_err(dev, "failed to initialize sub crq irqs\n");
		return -1;
	}

623 624 625 626
	adapter->map_id = 1;
	adapter->napi = kcalloc(adapter->req_rx_queues,
				sizeof(struct napi_struct), GFP_KERNEL);
	if (!adapter->napi)
627
		goto ibmvnic_open_fail;
628 629 630 631 632 633 634
	for (i = 0; i < adapter->req_rx_queues; i++) {
		netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll,
			       NAPI_POLL_WEIGHT);
		napi_enable(&adapter->napi[i]);
	}

	send_map_query(adapter);
635 636 637

	rc = init_rx_pools(netdev);
	if (rc)
638
		goto ibmvnic_open_fail;
639

640 641
	rc = init_tx_pools(netdev);
	if (rc)
642
		goto ibmvnic_open_fail;
643 644 645

	rc = init_bounce_buffer(netdev);
	if (rc)
646
		goto ibmvnic_open_fail;
647

648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664
	replenish_pools(adapter);

	/* We're ready to receive frames, enable the sub-crq interrupts and
	 * set the logical link state to up
	 */
	for (i = 0; i < adapter->req_rx_queues; i++)
		enable_scrq_irq(adapter, adapter->rx_scrq[i]);

	for (i = 0; i < adapter->req_tx_queues; i++)
		enable_scrq_irq(adapter, adapter->tx_scrq[i]);

	memset(&crq, 0, sizeof(crq));
	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_UP;
	ibmvnic_send_crq(adapter, &crq);

665
	netif_tx_start_all_queues(netdev);
666
	adapter->is_closed = false;
667

668 669
	return 0;

670
ibmvnic_open_fail:
671
	for (i = 0; i < adapter->req_rx_queues; i++)
672
		napi_disable(&adapter->napi[i]);
673
	release_resources(adapter);
674 675 676
	return -ENOMEM;
}

677 678 679 680 681 682 683 684 685 686 687 688 689
static int ibmvnic_close(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	union ibmvnic_crq crq;
	int i;

	adapter->closing = true;

	for (i = 0; i < adapter->req_rx_queues; i++)
		napi_disable(&adapter->napi[i]);

	if (!adapter->failover)
		netif_tx_stop_all_queues(netdev);
690

691 692 693 694 695 696
	memset(&crq, 0, sizeof(crq));
	crq.logical_link_state.first = IBMVNIC_CRQ_CMD;
	crq.logical_link_state.cmd = LOGICAL_LINK_STATE;
	crq.logical_link_state.link_state = IBMVNIC_LOGICAL_LNK_DN;
	ibmvnic_send_crq(adapter, &crq);

697
	release_resources(adapter);
698 699 700

	adapter->is_closed = true;
	adapter->closing = false;
701 702 703
	return 0;
}

704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833
/**
 * build_hdr_data - creates L2/L3/L4 header data buffer
 * @hdr_field - bitfield determining needed headers
 * @skb - socket buffer
 * @hdr_len - array of header lengths
 * @tot_len - total length of data
 *
 * Reads hdr_field to determine which headers are needed by firmware.
 * Builds a buffer containing these headers.  Saves individual header
 * lengths and total buffer length to be used to build descriptors.
 */
static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
			  int *hdr_len, u8 *hdr_data)
{
	int len = 0;
	u8 *hdr;

	hdr_len[0] = sizeof(struct ethhdr);

	if (skb->protocol == htons(ETH_P_IP)) {
		hdr_len[1] = ip_hdr(skb)->ihl * 4;
		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
			hdr_len[2] = tcp_hdrlen(skb);
		else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
			hdr_len[2] = sizeof(struct udphdr);
	} else if (skb->protocol == htons(ETH_P_IPV6)) {
		hdr_len[1] = sizeof(struct ipv6hdr);
		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
			hdr_len[2] = tcp_hdrlen(skb);
		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
			hdr_len[2] = sizeof(struct udphdr);
	}

	memset(hdr_data, 0, 120);
	if ((hdr_field >> 6) & 1) {
		hdr = skb_mac_header(skb);
		memcpy(hdr_data, hdr, hdr_len[0]);
		len += hdr_len[0];
	}

	if ((hdr_field >> 5) & 1) {
		hdr = skb_network_header(skb);
		memcpy(hdr_data + len, hdr, hdr_len[1]);
		len += hdr_len[1];
	}

	if ((hdr_field >> 4) & 1) {
		hdr = skb_transport_header(skb);
		memcpy(hdr_data + len, hdr, hdr_len[2]);
		len += hdr_len[2];
	}
	return len;
}

/**
 * create_hdr_descs - create header and header extension descriptors
 * @hdr_field - bitfield determining needed headers
 * @data - buffer containing header data
 * @len - length of data buffer
 * @hdr_len - array of individual header lengths
 * @scrq_arr - descriptor array
 *
 * Creates header and, if needed, header extension descriptors and
 * places them in a descriptor array, scrq_arr
 */

static void create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
			     union sub_crq *scrq_arr)
{
	union sub_crq hdr_desc;
	int tmp_len = len;
	u8 *data, *cur;
	int tmp;

	while (tmp_len > 0) {
		cur = hdr_data + len - tmp_len;

		memset(&hdr_desc, 0, sizeof(hdr_desc));
		if (cur != hdr_data) {
			data = hdr_desc.hdr_ext.data;
			tmp = tmp_len > 29 ? 29 : tmp_len;
			hdr_desc.hdr_ext.first = IBMVNIC_CRQ_CMD;
			hdr_desc.hdr_ext.type = IBMVNIC_HDR_EXT_DESC;
			hdr_desc.hdr_ext.len = tmp;
		} else {
			data = hdr_desc.hdr.data;
			tmp = tmp_len > 24 ? 24 : tmp_len;
			hdr_desc.hdr.first = IBMVNIC_CRQ_CMD;
			hdr_desc.hdr.type = IBMVNIC_HDR_DESC;
			hdr_desc.hdr.len = tmp;
			hdr_desc.hdr.l2_len = (u8)hdr_len[0];
			hdr_desc.hdr.l3_len = cpu_to_be16((u16)hdr_len[1]);
			hdr_desc.hdr.l4_len = (u8)hdr_len[2];
			hdr_desc.hdr.flag = hdr_field << 1;
		}
		memcpy(data, cur, tmp);
		tmp_len -= tmp;
		*scrq_arr = hdr_desc;
		scrq_arr++;
	}
}

/**
 * build_hdr_descs_arr - build a header descriptor array
 * @skb - socket buffer
 * @num_entries - number of descriptors to be sent
 * @subcrq - first TX descriptor
 * @hdr_field - bit field determining which headers will be sent
 *
 * This function will build a TX descriptor array with applicable
 * L2/L3/L4 packet header descriptors to be sent by send_subcrq_indirect.
 */

static void build_hdr_descs_arr(struct ibmvnic_tx_buff *txbuff,
				int *num_entries, u8 hdr_field)
{
	int hdr_len[3] = {0, 0, 0};
	int tot_len, len;
	u8 *hdr_data = txbuff->hdr_data;

	tot_len = build_hdr_data(hdr_field, txbuff->skb, hdr_len,
				 txbuff->hdr_data);
	len = tot_len;
	len -= 24;
	if (len > 0)
		num_entries += len % 29 ? len / 29 + 1 : len / 29;
	create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
			 txbuff->indir_arr + 1);
}

834 835 836 837
static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	int queue_num = skb_get_queue_mapping(skb);
838
	u8 *hdrs = (u8 *)&adapter->tx_rx_desc_req;
839 840
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_tx_buff *tx_buff = NULL;
841
	struct ibmvnic_sub_crq_queue *tx_scrq;
842 843 844 845 846 847 848 849 850 851 852 853
	struct ibmvnic_tx_pool *tx_pool;
	unsigned int tx_send_failed = 0;
	unsigned int tx_map_failed = 0;
	unsigned int tx_dropped = 0;
	unsigned int tx_packets = 0;
	unsigned int tx_bytes = 0;
	dma_addr_t data_dma_addr;
	struct netdev_queue *txq;
	bool used_bounce = false;
	unsigned long lpar_rc;
	union sub_crq tx_crq;
	unsigned int offset;
854
	int num_entries = 1;
855 856 857 858 859 860
	unsigned char *dst;
	u64 *handle_array;
	int index = 0;
	int ret = 0;

	tx_pool = &adapter->tx_pool[queue_num];
861
	tx_scrq = adapter->tx_scrq[queue_num];
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881
	txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
	handle_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
				   be32_to_cpu(adapter->login_rsp_buf->
					       off_txsubm_subcrqs));
	if (adapter->migrated) {
		tx_send_failed++;
		tx_dropped++;
		ret = NETDEV_TX_BUSY;
		goto out;
	}

	index = tx_pool->free_map[tx_pool->consumer_index];
	offset = index * adapter->req_mtu;
	dst = tx_pool->long_term_buff.buff + offset;
	memset(dst, 0, adapter->req_mtu);
	skb_copy_from_linear_data(skb, dst, skb->len);
	data_dma_addr = tx_pool->long_term_buff.addr + offset;

	tx_pool->consumer_index =
	    (tx_pool->consumer_index + 1) %
882
		adapter->req_tx_entries_per_subcrq;
883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920

	tx_buff = &tx_pool->tx_buff[index];
	tx_buff->skb = skb;
	tx_buff->data_dma[0] = data_dma_addr;
	tx_buff->data_len[0] = skb->len;
	tx_buff->index = index;
	tx_buff->pool_index = queue_num;
	tx_buff->last_frag = true;
	tx_buff->used_bounce = used_bounce;

	memset(&tx_crq, 0, sizeof(tx_crq));
	tx_crq.v1.first = IBMVNIC_CRQ_CMD;
	tx_crq.v1.type = IBMVNIC_TX_DESC;
	tx_crq.v1.n_crq_elem = 1;
	tx_crq.v1.n_sge = 1;
	tx_crq.v1.flags1 = IBMVNIC_TX_COMP_NEEDED;
	tx_crq.v1.correlator = cpu_to_be32(index);
	tx_crq.v1.dma_reg = cpu_to_be16(tx_pool->long_term_buff.map_id);
	tx_crq.v1.sge_len = cpu_to_be32(skb->len);
	tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);

	if (adapter->vlan_header_insertion) {
		tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
		tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
	}

	if (skb->protocol == htons(ETH_P_IP)) {
		if (ip_hdr(skb)->version == 4)
			tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV4;
		else if (ip_hdr(skb)->version == 6)
			tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_IPV6;

		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
			tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_TCP;
		else if (ip_hdr(skb)->protocol != IPPROTO_TCP)
			tx_crq.v1.flags1 |= IBMVNIC_TX_PROT_UDP;
	}

921
	if (skb->ip_summed == CHECKSUM_PARTIAL) {
922
		tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD;
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942
		hdrs += 2;
	}
	/* determine if l2/3/4 headers are sent to firmware */
	if ((*hdrs >> 7) & 1 &&
	    (skb->protocol == htons(ETH_P_IP) ||
	     skb->protocol == htons(ETH_P_IPV6))) {
		build_hdr_descs_arr(tx_buff, &num_entries, *hdrs);
		tx_crq.v1.n_crq_elem = num_entries;
		tx_buff->indir_arr[0] = tx_crq;
		tx_buff->indir_dma = dma_map_single(dev, tx_buff->indir_arr,
						    sizeof(tx_buff->indir_arr),
						    DMA_TO_DEVICE);
		if (dma_mapping_error(dev, tx_buff->indir_dma)) {
			if (!firmware_has_feature(FW_FEATURE_CMO))
				dev_err(dev, "tx: unable to map descriptor array\n");
			tx_map_failed++;
			tx_dropped++;
			ret = NETDEV_TX_BUSY;
			goto out;
		}
943
		lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
944 945 946
					       (u64)tx_buff->indir_dma,
					       (u64)num_entries);
	} else {
947 948
		lpar_rc = send_subcrq(adapter, handle_array[queue_num],
				      &tx_crq);
949
	}
950 951 952 953 954
	if (lpar_rc != H_SUCCESS) {
		dev_err(dev, "tx failed with code %ld\n", lpar_rc);

		if (tx_pool->consumer_index == 0)
			tx_pool->consumer_index =
955
				adapter->req_tx_entries_per_subcrq - 1;
956 957 958 959 960 961 962 963
		else
			tx_pool->consumer_index--;

		tx_send_failed++;
		tx_dropped++;
		ret = NETDEV_TX_BUSY;
		goto out;
	}
964

B
Brian King 已提交
965 966
	if (atomic_inc_return(&tx_scrq->used)
					>= adapter->req_tx_entries_per_subcrq) {
967 968 969 970
		netdev_info(netdev, "Stopping queue %d\n", queue_num);
		netif_stop_subqueue(netdev, queue_num);
	}

971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 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 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 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 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128
	tx_packets++;
	tx_bytes += skb->len;
	txq->trans_start = jiffies;
	ret = NETDEV_TX_OK;

out:
	netdev->stats.tx_dropped += tx_dropped;
	netdev->stats.tx_bytes += tx_bytes;
	netdev->stats.tx_packets += tx_packets;
	adapter->tx_send_failed += tx_send_failed;
	adapter->tx_map_failed += tx_map_failed;

	return ret;
}

static void ibmvnic_set_multi(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct netdev_hw_addr *ha;
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.request_capability.first = IBMVNIC_CRQ_CMD;
	crq.request_capability.cmd = REQUEST_CAPABILITY;

	if (netdev->flags & IFF_PROMISC) {
		if (!adapter->promisc_supported)
			return;
	} else {
		if (netdev->flags & IFF_ALLMULTI) {
			/* Accept all multicast */
			memset(&crq, 0, sizeof(crq));
			crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
			crq.multicast_ctrl.cmd = MULTICAST_CTRL;
			crq.multicast_ctrl.flags = IBMVNIC_ENABLE_ALL;
			ibmvnic_send_crq(adapter, &crq);
		} else if (netdev_mc_empty(netdev)) {
			/* Reject all multicast */
			memset(&crq, 0, sizeof(crq));
			crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
			crq.multicast_ctrl.cmd = MULTICAST_CTRL;
			crq.multicast_ctrl.flags = IBMVNIC_DISABLE_ALL;
			ibmvnic_send_crq(adapter, &crq);
		} else {
			/* Accept one or more multicast(s) */
			netdev_for_each_mc_addr(ha, netdev) {
				memset(&crq, 0, sizeof(crq));
				crq.multicast_ctrl.first = IBMVNIC_CRQ_CMD;
				crq.multicast_ctrl.cmd = MULTICAST_CTRL;
				crq.multicast_ctrl.flags = IBMVNIC_ENABLE_MC;
				ether_addr_copy(&crq.multicast_ctrl.mac_addr[0],
						ha->addr);
				ibmvnic_send_crq(adapter, &crq);
			}
		}
	}
}

static int ibmvnic_set_mac(struct net_device *netdev, void *p)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	struct sockaddr *addr = p;
	union ibmvnic_crq crq;

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

	memset(&crq, 0, sizeof(crq));
	crq.change_mac_addr.first = IBMVNIC_CRQ_CMD;
	crq.change_mac_addr.cmd = CHANGE_MAC_ADDR;
	ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data);
	ibmvnic_send_crq(adapter, &crq);
	/* netdev->dev_addr is changed in handle_change_mac_rsp function */
	return 0;
}

static void ibmvnic_tx_timeout(struct net_device *dev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(dev);
	int rc;

	/* Adapter timed out, resetting it */
	release_sub_crqs(adapter);
	rc = ibmvnic_reset_crq(adapter);
	if (rc)
		dev_err(&adapter->vdev->dev, "Adapter timeout, reset failed\n");
	else
		ibmvnic_send_crq_init(adapter);
}

static void remove_buff_from_pool(struct ibmvnic_adapter *adapter,
				  struct ibmvnic_rx_buff *rx_buff)
{
	struct ibmvnic_rx_pool *pool = &adapter->rx_pool[rx_buff->pool_index];

	rx_buff->skb = NULL;

	pool->free_map[pool->next_alloc] = (int)(rx_buff - pool->rx_buff);
	pool->next_alloc = (pool->next_alloc + 1) % pool->size;

	atomic_dec(&pool->available);
}

static int ibmvnic_poll(struct napi_struct *napi, int budget)
{
	struct net_device *netdev = napi->dev;
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	int scrq_num = (int)(napi - adapter->napi);
	int frames_processed = 0;
restart_poll:
	while (frames_processed < budget) {
		struct sk_buff *skb;
		struct ibmvnic_rx_buff *rx_buff;
		union sub_crq *next;
		u32 length;
		u16 offset;
		u8 flags = 0;

		if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
			break;
		next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
		rx_buff =
		    (struct ibmvnic_rx_buff *)be64_to_cpu(next->
							  rx_comp.correlator);
		/* do error checking */
		if (next->rx_comp.rc) {
			netdev_err(netdev, "rx error %x\n", next->rx_comp.rc);
			/* free the entry */
			next->rx_comp.first = 0;
			remove_buff_from_pool(adapter, rx_buff);
			break;
		}

		length = be32_to_cpu(next->rx_comp.len);
		offset = be16_to_cpu(next->rx_comp.off_frame_data);
		flags = next->rx_comp.flags;
		skb = rx_buff->skb;
		skb_copy_to_linear_data(skb, rx_buff->data + offset,
					length);
		skb->vlan_tci = be16_to_cpu(next->rx_comp.vlan_tci);
		/* free the entry */
		next->rx_comp.first = 0;
		remove_buff_from_pool(adapter, rx_buff);

		skb_put(skb, length);
		skb->protocol = eth_type_trans(skb, netdev);

		if (flags & IBMVNIC_IP_CHKSUM_GOOD &&
		    flags & IBMVNIC_TCP_UDP_CHKSUM_GOOD) {
			skb->ip_summed = CHECKSUM_UNNECESSARY;
		}

		length = skb->len;
		napi_gro_receive(napi, skb); /* send it up */
		netdev->stats.rx_packets++;
		netdev->stats.rx_bytes += length;
		frames_processed++;
	}
1129
	replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
1130 1131 1132

	if (frames_processed < budget) {
		enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
1133
		napi_complete_done(napi, frames_processed);
1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170
		if (pending_scrq(adapter, adapter->rx_scrq[scrq_num]) &&
		    napi_reschedule(napi)) {
			disable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
			goto restart_poll;
		}
	}
	return frames_processed;
}

#ifdef CONFIG_NET_POLL_CONTROLLER
static void ibmvnic_netpoll_controller(struct net_device *dev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(dev);
	int i;

	replenish_pools(netdev_priv(dev));
	for (i = 0; i < adapter->req_rx_queues; i++)
		ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq,
				     adapter->rx_scrq[i]);
}
#endif

static const struct net_device_ops ibmvnic_netdev_ops = {
	.ndo_open		= ibmvnic_open,
	.ndo_stop		= ibmvnic_close,
	.ndo_start_xmit		= ibmvnic_xmit,
	.ndo_set_rx_mode	= ibmvnic_set_multi,
	.ndo_set_mac_address	= ibmvnic_set_mac,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_tx_timeout		= ibmvnic_tx_timeout,
#ifdef CONFIG_NET_POLL_CONTROLLER
	.ndo_poll_controller	= ibmvnic_netpoll_controller,
#endif
};

/* ethtool functions */

1171 1172
static int ibmvnic_get_link_ksettings(struct net_device *netdev,
				      struct ethtool_link_ksettings *cmd)
1173
{
1174 1175 1176
	u32 supported, advertising;

	supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg |
1177
			  SUPPORTED_FIBRE);
1178
	advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg |
1179
			    ADVERTISED_FIBRE);
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
	cmd->base.speed = SPEED_1000;
	cmd->base.duplex = DUPLEX_FULL;
	cmd->base.port = PORT_FIBRE;
	cmd->base.phy_address = 0;
	cmd->base.autoneg = AUTONEG_ENABLE;

	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
						supported);
	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
						advertising);

1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
	return 0;
}

static void ibmvnic_get_drvinfo(struct net_device *dev,
				struct ethtool_drvinfo *info)
{
	strlcpy(info->driver, ibmvnic_driver_name, sizeof(info->driver));
	strlcpy(info->version, IBMVNIC_DRIVER_VERSION, sizeof(info->version));
}

static u32 ibmvnic_get_msglevel(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);

	return adapter->msg_enable;
}

static void ibmvnic_set_msglevel(struct net_device *netdev, u32 data)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);

	adapter->msg_enable = data;
}

static u32 ibmvnic_get_link(struct net_device *netdev)
{
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);

	/* Don't need to send a query because we request a logical link up at
	 * init and then we wait for link state indications
	 */
	return adapter->logical_link_state;
}

static void ibmvnic_get_ringparam(struct net_device *netdev,
				  struct ethtool_ringparam *ring)
{
	ring->rx_max_pending = 0;
	ring->tx_max_pending = 0;
	ring->rx_mini_max_pending = 0;
	ring->rx_jumbo_max_pending = 0;
	ring->rx_pending = 0;
	ring->tx_pending = 0;
	ring->rx_mini_pending = 0;
	ring->rx_jumbo_pending = 0;
}

static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
	int i;

	if (stringset != ETH_SS_STATS)
		return;

	for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN)
		memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN);
}

static int ibmvnic_get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(ibmvnic_stats);
	default:
		return -EOPNOTSUPP;
	}
}

static void ibmvnic_get_ethtool_stats(struct net_device *dev,
				      struct ethtool_stats *stats, u64 *data)
{
	struct ibmvnic_adapter *adapter = netdev_priv(dev);
	union ibmvnic_crq crq;
	int i;

	memset(&crq, 0, sizeof(crq));
	crq.request_statistics.first = IBMVNIC_CRQ_CMD;
	crq.request_statistics.cmd = REQUEST_STATISTICS;
	crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token);
	crq.request_statistics.len =
	    cpu_to_be32(sizeof(struct ibmvnic_statistics));

	/* Wait for data to be written */
	init_completion(&adapter->stats_done);
1275
	ibmvnic_send_crq(adapter, &crq);
1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290
	wait_for_completion(&adapter->stats_done);

	for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
		data[i] = IBMVNIC_GET_STAT(adapter, ibmvnic_stats[i].offset);
}

static const struct ethtool_ops ibmvnic_ethtool_ops = {
	.get_drvinfo		= ibmvnic_get_drvinfo,
	.get_msglevel		= ibmvnic_get_msglevel,
	.set_msglevel		= ibmvnic_set_msglevel,
	.get_link		= ibmvnic_get_link,
	.get_ringparam		= ibmvnic_get_ringparam,
	.get_strings            = ibmvnic_get_strings,
	.get_sset_count         = ibmvnic_get_sset_count,
	.get_ethtool_stats	= ibmvnic_get_ethtool_stats,
1291
	.get_link_ksettings	= ibmvnic_get_link_ksettings,
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
};

/* Routines for managing CRQs/sCRQs  */

static void release_sub_crq_queue(struct ibmvnic_adapter *adapter,
				  struct ibmvnic_sub_crq_queue *scrq)
{
	struct device *dev = &adapter->vdev->dev;
	long rc;

	netdev_dbg(adapter->netdev, "Releasing sub-CRQ\n");

	/* Close the sub-crqs */
	do {
		rc = plpar_hcall_norets(H_FREE_SUB_CRQ,
					adapter->vdev->unit_address,
					scrq->crq_num);
	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));

1311 1312 1313 1314 1315 1316
	if (rc) {
		netdev_err(adapter->netdev,
			   "Failed to release sub-CRQ %16lx, rc = %ld\n",
			   scrq->crq_num, rc);
	}

1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333
	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
			 DMA_BIDIRECTIONAL);
	free_pages((unsigned long)scrq->msgs, 2);
	kfree(scrq);
}

static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
							*adapter)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_sub_crq_queue *scrq;
	int rc;

	scrq = kmalloc(sizeof(*scrq), GFP_ATOMIC);
	if (!scrq)
		return NULL;

1334
	scrq->msgs = (union sub_crq *)__get_free_pages(GFP_ATOMIC, 2);
1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363
	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
	if (!scrq->msgs) {
		dev_warn(dev, "Couldn't allocate crq queue messages page\n");
		goto zero_page_failed;
	}

	scrq->msg_token = dma_map_single(dev, scrq->msgs, 4 * PAGE_SIZE,
					 DMA_BIDIRECTIONAL);
	if (dma_mapping_error(dev, scrq->msg_token)) {
		dev_warn(dev, "Couldn't map crq queue messages page\n");
		goto map_failed;
	}

	rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token,
			   4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq);

	if (rc == H_RESOURCE)
		rc = ibmvnic_reset_crq(adapter);

	if (rc == H_CLOSED) {
		dev_warn(dev, "Partner adapter not ready, waiting.\n");
	} else if (rc) {
		dev_warn(dev, "Error %d registering sub-crq\n", rc);
		goto reg_failed;
	}

	scrq->adapter = adapter;
	scrq->size = 4 * PAGE_SIZE / sizeof(*scrq->msgs);
	scrq->cur = 0;
1364
	atomic_set(&scrq->used, 0);
1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389
	scrq->rx_skb_top = NULL;
	spin_lock_init(&scrq->lock);

	netdev_dbg(adapter->netdev,
		   "sub-crq initialized, num %lx, hw_irq=%lx, irq=%x\n",
		   scrq->crq_num, scrq->hw_irq, scrq->irq);

	return scrq;

reg_failed:
	dma_unmap_single(dev, scrq->msg_token, 4 * PAGE_SIZE,
			 DMA_BIDIRECTIONAL);
map_failed:
	free_pages((unsigned long)scrq->msgs, 2);
zero_page_failed:
	kfree(scrq);

	return NULL;
}

static void release_sub_crqs(struct ibmvnic_adapter *adapter)
{
	int i;

	if (adapter->tx_scrq) {
1390 1391 1392 1393 1394
		for (i = 0; i < adapter->req_tx_queues; i++) {
			if (!adapter->tx_scrq[i])
				continue;

			if (adapter->tx_scrq[i]->irq) {
1395 1396
				free_irq(adapter->tx_scrq[i]->irq,
					 adapter->tx_scrq[i]);
T
Thomas Falcon 已提交
1397
				irq_dispose_mapping(adapter->tx_scrq[i]->irq);
1398
				adapter->tx_scrq[i]->irq = 0;
1399
			}
1400 1401 1402 1403

			release_sub_crq_queue(adapter, adapter->tx_scrq[i]);
		}

1404
		kfree(adapter->tx_scrq);
1405 1406 1407 1408
		adapter->tx_scrq = NULL;
	}

	if (adapter->rx_scrq) {
1409 1410 1411 1412 1413
		for (i = 0; i < adapter->req_rx_queues; i++) {
			if (!adapter->rx_scrq[i])
				continue;

			if (adapter->rx_scrq[i]->irq) {
1414 1415
				free_irq(adapter->rx_scrq[i]->irq,
					 adapter->rx_scrq[i]);
T
Thomas Falcon 已提交
1416
				irq_dispose_mapping(adapter->rx_scrq[i]->irq);
1417
				adapter->rx_scrq[i]->irq = 0;
1418 1419
			}

1420 1421
			release_sub_crq_queue(adapter, adapter->rx_scrq[i]);
		}
1422

1423
		kfree(adapter->rx_scrq);
1424 1425 1426 1427
		adapter->rx_scrq = NULL;
	}
}

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
static int disable_scrq_irq(struct ibmvnic_adapter *adapter,
			    struct ibmvnic_sub_crq_queue *scrq)
{
	struct device *dev = &adapter->vdev->dev;
	unsigned long rc;

	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
				H_DISABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
	if (rc)
		dev_err(dev, "Couldn't disable scrq irq 0x%lx. rc=%ld\n",
			scrq->hw_irq, rc);
	return rc;
}

static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
			   struct ibmvnic_sub_crq_queue *scrq)
{
	struct device *dev = &adapter->vdev->dev;
	unsigned long rc;

	if (scrq->hw_irq > 0x100000000ULL) {
		dev_err(dev, "bad hw_irq = %lx\n", scrq->hw_irq);
		return 1;
	}

	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
				H_ENABLE_VIO_INTERRUPT, scrq->hw_irq, 0, 0);
	if (rc)
		dev_err(dev, "Couldn't enable scrq irq 0x%lx. rc=%ld\n",
			scrq->hw_irq, rc);
	return rc;
}

static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
			       struct ibmvnic_sub_crq_queue *scrq)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_tx_buff *txbuff;
	union sub_crq *next;
	int index;
	int i, j;
1469
	u8 first;
1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491

restart_loop:
	while (pending_scrq(adapter, scrq)) {
		unsigned int pool = scrq->pool_index;

		next = ibmvnic_next_scrq(adapter, scrq);
		for (i = 0; i < next->tx_comp.num_comps; i++) {
			if (next->tx_comp.rcs[i]) {
				dev_err(dev, "tx error %x\n",
					next->tx_comp.rcs[i]);
				continue;
			}
			index = be32_to_cpu(next->tx_comp.correlators[i]);
			txbuff = &adapter->tx_pool[pool].tx_buff[index];

			for (j = 0; j < IBMVNIC_MAX_FRAGS_PER_CRQ; j++) {
				if (!txbuff->data_dma[j])
					continue;

				txbuff->data_dma[j] = 0;
				txbuff->used_bounce = false;
			}
1492 1493 1494 1495 1496 1497 1498
			/* if sub_crq was sent indirectly */
			first = txbuff->indir_arr[0].generic.first;
			if (first == IBMVNIC_CRQ_CMD) {
				dma_unmap_single(dev, txbuff->indir_dma,
						 sizeof(txbuff->indir_arr),
						 DMA_TO_DEVICE);
			}
1499

1500
			if (txbuff->last_frag) {
B
Brian King 已提交
1501 1502
				if (atomic_sub_return(next->tx_comp.num_comps,
						      &scrq->used) <=
1503 1504 1505 1506 1507 1508 1509 1510 1511 1512
				    (adapter->req_tx_entries_per_subcrq / 2) &&
				    netif_subqueue_stopped(adapter->netdev,
							   txbuff->skb)) {
					netif_wake_subqueue(adapter->netdev,
							    scrq->pool_index);
					netdev_dbg(adapter->netdev,
						   "Started queue %d\n",
						   scrq->pool_index);
				}

1513
				dev_kfree_skb_any(txbuff->skb);
1514
			}
1515 1516 1517 1518 1519

			adapter->tx_pool[pool].free_map[adapter->tx_pool[pool].
						     producer_index] = index;
			adapter->tx_pool[pool].producer_index =
			    (adapter->tx_pool[pool].producer_index + 1) %
1520
			    adapter->req_tx_entries_per_subcrq;
1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559
		}
		/* remove tx_comp scrq*/
		next->tx_comp.first = 0;
	}

	enable_scrq_irq(adapter, scrq);

	if (pending_scrq(adapter, scrq)) {
		disable_scrq_irq(adapter, scrq);
		goto restart_loop;
	}

	return 0;
}

static irqreturn_t ibmvnic_interrupt_tx(int irq, void *instance)
{
	struct ibmvnic_sub_crq_queue *scrq = instance;
	struct ibmvnic_adapter *adapter = scrq->adapter;

	disable_scrq_irq(adapter, scrq);
	ibmvnic_complete_tx(adapter, scrq);

	return IRQ_HANDLED;
}

static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance)
{
	struct ibmvnic_sub_crq_queue *scrq = instance;
	struct ibmvnic_adapter *adapter = scrq->adapter;

	if (napi_schedule_prep(&adapter->napi[scrq->scrq_num])) {
		disable_scrq_irq(adapter, scrq);
		__napi_schedule(&adapter->napi[scrq->scrq_num]);
	}

	return IRQ_HANDLED;
}

1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570
static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_sub_crq_queue *scrq;
	int i = 0, j = 0;
	int rc = 0;

	for (i = 0; i < adapter->req_tx_queues; i++) {
		scrq = adapter->tx_scrq[i];
		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);

1571
		if (!scrq->irq) {
1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590
			rc = -EINVAL;
			dev_err(dev, "Error mapping irq\n");
			goto req_tx_irq_failed;
		}

		rc = request_irq(scrq->irq, ibmvnic_interrupt_tx,
				 0, "ibmvnic_tx", scrq);

		if (rc) {
			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
				scrq->irq, rc);
			irq_dispose_mapping(scrq->irq);
			goto req_rx_irq_failed;
		}
	}

	for (i = 0; i < adapter->req_rx_queues; i++) {
		scrq = adapter->rx_scrq[i];
		scrq->irq = irq_create_mapping(NULL, scrq->hw_irq);
1591
		if (!scrq->irq) {
1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607
			rc = -EINVAL;
			dev_err(dev, "Error mapping irq\n");
			goto req_rx_irq_failed;
		}
		rc = request_irq(scrq->irq, ibmvnic_interrupt_rx,
				 0, "ibmvnic_rx", scrq);
		if (rc) {
			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
				scrq->irq, rc);
			irq_dispose_mapping(scrq->irq);
			goto req_rx_irq_failed;
		}
	}
	return rc;

req_rx_irq_failed:
1608
	for (j = 0; j < i; j++) {
1609 1610
		free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
1611
	}
1612 1613
	i = adapter->req_tx_queues;
req_tx_irq_failed:
1614
	for (j = 0; j < i; j++) {
1615 1616
		free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
		irq_dispose_mapping(adapter->rx_scrq[j]->irq);
1617
	}
1618
	release_sub_crqs(adapter);
1619 1620 1621
	return rc;
}

1622 1623 1624 1625 1626 1627 1628 1629
static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_sub_crq_queue **allqueues;
	int registered_queues = 0;
	union ibmvnic_crq crq;
	int total_queues;
	int more = 0;
1630
	int i;
1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651

	if (!retry) {
		/* Sub-CRQ entries are 32 byte long */
		int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4);

		if (adapter->min_tx_entries_per_subcrq > entries_page ||
		    adapter->min_rx_add_entries_per_subcrq > entries_page) {
			dev_err(dev, "Fatal, invalid entries per sub-crq\n");
			goto allqueues_failed;
		}

		/* Get the minimum between the queried max and the entries
		 * that fit in our PAGE_SIZE
		 */
		adapter->req_tx_entries_per_subcrq =
		    adapter->max_tx_entries_per_subcrq > entries_page ?
		    entries_page : adapter->max_tx_entries_per_subcrq;
		adapter->req_rx_add_entries_per_subcrq =
		    adapter->max_rx_add_entries_per_subcrq > entries_page ?
		    entries_page : adapter->max_rx_add_entries_per_subcrq;

1652 1653
		adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
1654
		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
1655

1656
		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724
	}

	total_queues = adapter->req_tx_queues + adapter->req_rx_queues;

	allqueues = kcalloc(total_queues, sizeof(*allqueues), GFP_ATOMIC);
	if (!allqueues)
		goto allqueues_failed;

	for (i = 0; i < total_queues; i++) {
		allqueues[i] = init_sub_crq_queue(adapter);
		if (!allqueues[i]) {
			dev_warn(dev, "Couldn't allocate all sub-crqs\n");
			break;
		}
		registered_queues++;
	}

	/* Make sure we were able to register the minimum number of queues */
	if (registered_queues <
	    adapter->min_tx_queues + adapter->min_rx_queues) {
		dev_err(dev, "Fatal: Couldn't init  min number of sub-crqs\n");
		goto tx_failed;
	}

	/* Distribute the failed allocated queues*/
	for (i = 0; i < total_queues - registered_queues + more ; i++) {
		netdev_dbg(adapter->netdev, "Reducing number of queues\n");
		switch (i % 3) {
		case 0:
			if (adapter->req_rx_queues > adapter->min_rx_queues)
				adapter->req_rx_queues--;
			else
				more++;
			break;
		case 1:
			if (adapter->req_tx_queues > adapter->min_tx_queues)
				adapter->req_tx_queues--;
			else
				more++;
			break;
		}
	}

	adapter->tx_scrq = kcalloc(adapter->req_tx_queues,
				   sizeof(*adapter->tx_scrq), GFP_ATOMIC);
	if (!adapter->tx_scrq)
		goto tx_failed;

	for (i = 0; i < adapter->req_tx_queues; i++) {
		adapter->tx_scrq[i] = allqueues[i];
		adapter->tx_scrq[i]->pool_index = i;
	}

	adapter->rx_scrq = kcalloc(adapter->req_rx_queues,
				   sizeof(*adapter->rx_scrq), GFP_ATOMIC);
	if (!adapter->rx_scrq)
		goto rx_failed;

	for (i = 0; i < adapter->req_rx_queues; i++) {
		adapter->rx_scrq[i] = allqueues[i + adapter->req_tx_queues];
		adapter->rx_scrq[i]->scrq_num = i;
	}

	memset(&crq, 0, sizeof(crq));
	crq.request_capability.first = IBMVNIC_CRQ_CMD;
	crq.request_capability.cmd = REQUEST_CAPABILITY;

	crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES);
1725
	crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues);
1726
	atomic_inc(&adapter->running_cap_crqs);
1727 1728 1729
	ibmvnic_send_crq(adapter, &crq);

	crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES);
1730
	crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues);
1731
	atomic_inc(&adapter->running_cap_crqs);
1732 1733 1734
	ibmvnic_send_crq(adapter, &crq);

	crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES);
1735
	crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues);
1736
	atomic_inc(&adapter->running_cap_crqs);
1737 1738 1739 1740 1741
	ibmvnic_send_crq(adapter, &crq);

	crq.request_capability.capability =
	    cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ);
	crq.request_capability.number =
1742
	    cpu_to_be64(adapter->req_tx_entries_per_subcrq);
1743
	atomic_inc(&adapter->running_cap_crqs);
1744 1745 1746 1747 1748
	ibmvnic_send_crq(adapter, &crq);

	crq.request_capability.capability =
	    cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ);
	crq.request_capability.number =
1749
	    cpu_to_be64(adapter->req_rx_add_entries_per_subcrq);
1750
	atomic_inc(&adapter->running_cap_crqs);
1751 1752 1753
	ibmvnic_send_crq(adapter, &crq);

	crq.request_capability.capability = cpu_to_be16(REQ_MTU);
1754
	crq.request_capability.number = cpu_to_be64(adapter->req_mtu);
1755
	atomic_inc(&adapter->running_cap_crqs);
1756 1757 1758 1759 1760 1761
	ibmvnic_send_crq(adapter, &crq);

	if (adapter->netdev->flags & IFF_PROMISC) {
		if (adapter->promisc_supported) {
			crq.request_capability.capability =
			    cpu_to_be16(PROMISC_REQUESTED);
1762
			crq.request_capability.number = cpu_to_be64(1);
1763
			atomic_inc(&adapter->running_cap_crqs);
1764 1765 1766 1767 1768
			ibmvnic_send_crq(adapter, &crq);
		}
	} else {
		crq.request_capability.capability =
		    cpu_to_be16(PROMISC_REQUESTED);
1769
		crq.request_capability.number = cpu_to_be64(0);
1770
		atomic_inc(&adapter->running_cap_crqs);
1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869
		ibmvnic_send_crq(adapter, &crq);
	}

	kfree(allqueues);

	return;

rx_failed:
	kfree(adapter->tx_scrq);
	adapter->tx_scrq = NULL;
tx_failed:
	for (i = 0; i < registered_queues; i++)
		release_sub_crq_queue(adapter, allqueues[i]);
	kfree(allqueues);
allqueues_failed:
	ibmvnic_remove(adapter->vdev);
}

static int pending_scrq(struct ibmvnic_adapter *adapter,
			struct ibmvnic_sub_crq_queue *scrq)
{
	union sub_crq *entry = &scrq->msgs[scrq->cur];

	if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP || adapter->closing)
		return 1;
	else
		return 0;
}

static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter,
					struct ibmvnic_sub_crq_queue *scrq)
{
	union sub_crq *entry;
	unsigned long flags;

	spin_lock_irqsave(&scrq->lock, flags);
	entry = &scrq->msgs[scrq->cur];
	if (entry->generic.first & IBMVNIC_CRQ_CMD_RSP) {
		if (++scrq->cur == scrq->size)
			scrq->cur = 0;
	} else {
		entry = NULL;
	}
	spin_unlock_irqrestore(&scrq->lock, flags);

	return entry;
}

static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter)
{
	struct ibmvnic_crq_queue *queue = &adapter->crq;
	union ibmvnic_crq *crq;

	crq = &queue->msgs[queue->cur];
	if (crq->generic.first & IBMVNIC_CRQ_CMD_RSP) {
		if (++queue->cur == queue->size)
			queue->cur = 0;
	} else {
		crq = NULL;
	}

	return crq;
}

static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
		       union sub_crq *sub_crq)
{
	unsigned int ua = adapter->vdev->unit_address;
	struct device *dev = &adapter->vdev->dev;
	u64 *u64_crq = (u64 *)sub_crq;
	int rc;

	netdev_dbg(adapter->netdev,
		   "Sending sCRQ %016lx: %016lx %016lx %016lx %016lx\n",
		   (unsigned long int)cpu_to_be64(remote_handle),
		   (unsigned long int)cpu_to_be64(u64_crq[0]),
		   (unsigned long int)cpu_to_be64(u64_crq[1]),
		   (unsigned long int)cpu_to_be64(u64_crq[2]),
		   (unsigned long int)cpu_to_be64(u64_crq[3]));

	/* Make sure the hypervisor sees the complete request */
	mb();

	rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua,
				cpu_to_be64(remote_handle),
				cpu_to_be64(u64_crq[0]),
				cpu_to_be64(u64_crq[1]),
				cpu_to_be64(u64_crq[2]),
				cpu_to_be64(u64_crq[3]));

	if (rc) {
		if (rc == H_CLOSED)
			dev_warn(dev, "CRQ Queue closed\n");
		dev_err(dev, "Send error (rc=%d)\n", rc);
	}

	return rc;
}

1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891
static int send_subcrq_indirect(struct ibmvnic_adapter *adapter,
				u64 remote_handle, u64 ioba, u64 num_entries)
{
	unsigned int ua = adapter->vdev->unit_address;
	struct device *dev = &adapter->vdev->dev;
	int rc;

	/* Make sure the hypervisor sees the complete request */
	mb();
	rc = plpar_hcall_norets(H_SEND_SUB_CRQ_INDIRECT, ua,
				cpu_to_be64(remote_handle),
				ioba, num_entries);

	if (rc) {
		if (rc == H_CLOSED)
			dev_warn(dev, "CRQ Queue closed\n");
		dev_err(dev, "Send (indirect) error (rc=%d)\n", rc);
	}

	return rc;
}

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 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986
static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter,
			    union ibmvnic_crq *crq)
{
	unsigned int ua = adapter->vdev->unit_address;
	struct device *dev = &adapter->vdev->dev;
	u64 *u64_crq = (u64 *)crq;
	int rc;

	netdev_dbg(adapter->netdev, "Sending CRQ: %016lx %016lx\n",
		   (unsigned long int)cpu_to_be64(u64_crq[0]),
		   (unsigned long int)cpu_to_be64(u64_crq[1]));

	/* Make sure the hypervisor sees the complete request */
	mb();

	rc = plpar_hcall_norets(H_SEND_CRQ, ua,
				cpu_to_be64(u64_crq[0]),
				cpu_to_be64(u64_crq[1]));

	if (rc) {
		if (rc == H_CLOSED)
			dev_warn(dev, "CRQ Queue closed\n");
		dev_warn(dev, "Send error (rc=%d)\n", rc);
	}

	return rc;
}

static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.generic.first = IBMVNIC_CRQ_INIT_CMD;
	crq.generic.cmd = IBMVNIC_CRQ_INIT;
	netdev_dbg(adapter->netdev, "Sending CRQ init\n");

	return ibmvnic_send_crq(adapter, &crq);
}

static int ibmvnic_send_crq_init_complete(struct ibmvnic_adapter *adapter)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.generic.first = IBMVNIC_CRQ_INIT_CMD;
	crq.generic.cmd = IBMVNIC_CRQ_INIT_COMPLETE;
	netdev_dbg(adapter->netdev, "Sending CRQ init complete\n");

	return ibmvnic_send_crq(adapter, &crq);
}

static int send_version_xchg(struct ibmvnic_adapter *adapter)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.version_exchange.first = IBMVNIC_CRQ_CMD;
	crq.version_exchange.cmd = VERSION_EXCHANGE;
	crq.version_exchange.version = cpu_to_be16(ibmvnic_version);

	return ibmvnic_send_crq(adapter, &crq);
}

static void send_login(struct ibmvnic_adapter *adapter)
{
	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
	struct ibmvnic_login_buffer *login_buffer;
	struct ibmvnic_inflight_cmd *inflight_cmd;
	struct device *dev = &adapter->vdev->dev;
	dma_addr_t rsp_buffer_token;
	dma_addr_t buffer_token;
	size_t rsp_buffer_size;
	union ibmvnic_crq crq;
	unsigned long flags;
	size_t buffer_size;
	__be64 *tx_list_p;
	__be64 *rx_list_p;
	int i;

	buffer_size =
	    sizeof(struct ibmvnic_login_buffer) +
	    sizeof(u64) * (adapter->req_tx_queues + adapter->req_rx_queues);

	login_buffer = kmalloc(buffer_size, GFP_ATOMIC);
	if (!login_buffer)
		goto buf_alloc_failed;

	buffer_token = dma_map_single(dev, login_buffer, buffer_size,
				      DMA_TO_DEVICE);
	if (dma_mapping_error(dev, buffer_token)) {
		dev_err(dev, "Couldn't map login buffer\n");
		goto buf_map_failed;
	}

1987 1988 1989 1990 1991
	rsp_buffer_size = sizeof(struct ibmvnic_login_rsp_buffer) +
			  sizeof(u64) * adapter->req_tx_queues +
			  sizeof(u64) * adapter->req_rx_queues +
			  sizeof(u64) * adapter->req_rx_queues +
			  sizeof(u8) * IBMVNIC_TX_DESC_VERSIONS;
1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121

	login_rsp_buffer = kmalloc(rsp_buffer_size, GFP_ATOMIC);
	if (!login_rsp_buffer)
		goto buf_rsp_alloc_failed;

	rsp_buffer_token = dma_map_single(dev, login_rsp_buffer,
					  rsp_buffer_size, DMA_FROM_DEVICE);
	if (dma_mapping_error(dev, rsp_buffer_token)) {
		dev_err(dev, "Couldn't map login rsp buffer\n");
		goto buf_rsp_map_failed;
	}
	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
	if (!inflight_cmd) {
		dev_err(dev, "Couldn't allocate inflight_cmd\n");
		goto inflight_alloc_failed;
	}
	adapter->login_buf = login_buffer;
	adapter->login_buf_token = buffer_token;
	adapter->login_buf_sz = buffer_size;
	adapter->login_rsp_buf = login_rsp_buffer;
	adapter->login_rsp_buf_token = rsp_buffer_token;
	adapter->login_rsp_buf_sz = rsp_buffer_size;

	login_buffer->len = cpu_to_be32(buffer_size);
	login_buffer->version = cpu_to_be32(INITIAL_VERSION_LB);
	login_buffer->num_txcomp_subcrqs = cpu_to_be32(adapter->req_tx_queues);
	login_buffer->off_txcomp_subcrqs =
	    cpu_to_be32(sizeof(struct ibmvnic_login_buffer));
	login_buffer->num_rxcomp_subcrqs = cpu_to_be32(adapter->req_rx_queues);
	login_buffer->off_rxcomp_subcrqs =
	    cpu_to_be32(sizeof(struct ibmvnic_login_buffer) +
			sizeof(u64) * adapter->req_tx_queues);
	login_buffer->login_rsp_ioba = cpu_to_be32(rsp_buffer_token);
	login_buffer->login_rsp_len = cpu_to_be32(rsp_buffer_size);

	tx_list_p = (__be64 *)((char *)login_buffer +
				      sizeof(struct ibmvnic_login_buffer));
	rx_list_p = (__be64 *)((char *)login_buffer +
				      sizeof(struct ibmvnic_login_buffer) +
				      sizeof(u64) * adapter->req_tx_queues);

	for (i = 0; i < adapter->req_tx_queues; i++) {
		if (adapter->tx_scrq[i]) {
			tx_list_p[i] = cpu_to_be64(adapter->tx_scrq[i]->
						   crq_num);
		}
	}

	for (i = 0; i < adapter->req_rx_queues; i++) {
		if (adapter->rx_scrq[i]) {
			rx_list_p[i] = cpu_to_be64(adapter->rx_scrq[i]->
						   crq_num);
		}
	}

	netdev_dbg(adapter->netdev, "Login Buffer:\n");
	for (i = 0; i < (adapter->login_buf_sz - 1) / 8 + 1; i++) {
		netdev_dbg(adapter->netdev, "%016lx\n",
			   ((unsigned long int *)(adapter->login_buf))[i]);
	}

	memset(&crq, 0, sizeof(crq));
	crq.login.first = IBMVNIC_CRQ_CMD;
	crq.login.cmd = LOGIN;
	crq.login.ioba = cpu_to_be32(buffer_token);
	crq.login.len = cpu_to_be32(buffer_size);

	memcpy(&inflight_cmd->crq, &crq, sizeof(crq));

	spin_lock_irqsave(&adapter->inflight_lock, flags);
	list_add_tail(&inflight_cmd->list, &adapter->inflight);
	spin_unlock_irqrestore(&adapter->inflight_lock, flags);

	ibmvnic_send_crq(adapter, &crq);

	return;

inflight_alloc_failed:
	dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size,
			 DMA_FROM_DEVICE);
buf_rsp_map_failed:
	kfree(login_rsp_buffer);
buf_rsp_alloc_failed:
	dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE);
buf_map_failed:
	kfree(login_buffer);
buf_alloc_failed:
	return;
}

static void send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr,
			     u32 len, u8 map_id)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.request_map.first = IBMVNIC_CRQ_CMD;
	crq.request_map.cmd = REQUEST_MAP;
	crq.request_map.map_id = map_id;
	crq.request_map.ioba = cpu_to_be32(addr);
	crq.request_map.len = cpu_to_be32(len);
	ibmvnic_send_crq(adapter, &crq);
}

static void send_request_unmap(struct ibmvnic_adapter *adapter, u8 map_id)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.request_unmap.first = IBMVNIC_CRQ_CMD;
	crq.request_unmap.cmd = REQUEST_UNMAP;
	crq.request_unmap.map_id = map_id;
	ibmvnic_send_crq(adapter, &crq);
}

static void send_map_query(struct ibmvnic_adapter *adapter)
{
	union ibmvnic_crq crq;

	memset(&crq, 0, sizeof(crq));
	crq.query_map.first = IBMVNIC_CRQ_CMD;
	crq.query_map.cmd = QUERY_MAP;
	ibmvnic_send_crq(adapter, &crq);
}

/* Send a series of CRQs requesting various capabilities of the VNIC server */
static void send_cap_queries(struct ibmvnic_adapter *adapter)
{
	union ibmvnic_crq crq;

2122
	atomic_set(&adapter->running_cap_crqs, 0);
2123 2124 2125 2126 2127
	memset(&crq, 0, sizeof(crq));
	crq.query_capability.first = IBMVNIC_CRQ_CMD;
	crq.query_capability.cmd = QUERY_CAPABILITY;

	crq.query_capability.capability = cpu_to_be16(MIN_TX_QUEUES);
2128
	atomic_inc(&adapter->running_cap_crqs);
2129 2130 2131
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MIN_RX_QUEUES);
2132
	atomic_inc(&adapter->running_cap_crqs);
2133 2134 2135
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_QUEUES);
2136
	atomic_inc(&adapter->running_cap_crqs);
2137 2138 2139
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_TX_QUEUES);
2140
	atomic_inc(&adapter->running_cap_crqs);
2141 2142 2143
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_RX_QUEUES);
2144
	atomic_inc(&adapter->running_cap_crqs);
2145 2146 2147
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_QUEUES);
2148
	atomic_inc(&adapter->running_cap_crqs);
2149 2150 2151 2152
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
	    cpu_to_be16(MIN_TX_ENTRIES_PER_SUBCRQ);
2153
	atomic_inc(&adapter->running_cap_crqs);
2154 2155 2156 2157
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
	    cpu_to_be16(MIN_RX_ADD_ENTRIES_PER_SUBCRQ);
2158
	atomic_inc(&adapter->running_cap_crqs);
2159 2160 2161 2162
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
	    cpu_to_be16(MAX_TX_ENTRIES_PER_SUBCRQ);
2163
	atomic_inc(&adapter->running_cap_crqs);
2164 2165 2166 2167
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
	    cpu_to_be16(MAX_RX_ADD_ENTRIES_PER_SUBCRQ);
2168
	atomic_inc(&adapter->running_cap_crqs);
2169 2170 2171
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(TCP_IP_OFFLOAD);
2172
	atomic_inc(&adapter->running_cap_crqs);
2173 2174 2175
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(PROMISC_SUPPORTED);
2176
	atomic_inc(&adapter->running_cap_crqs);
2177 2178 2179
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MIN_MTU);
2180
	atomic_inc(&adapter->running_cap_crqs);
2181 2182 2183
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_MTU);
2184
	atomic_inc(&adapter->running_cap_crqs);
2185 2186 2187
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_MULTICAST_FILTERS);
2188
	atomic_inc(&adapter->running_cap_crqs);
2189 2190 2191
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(VLAN_HEADER_INSERTION);
2192
	atomic_inc(&adapter->running_cap_crqs);
2193 2194 2195
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES);
2196
	atomic_inc(&adapter->running_cap_crqs);
2197 2198 2199
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(RX_SG_SUPPORTED);
2200
	atomic_inc(&adapter->running_cap_crqs);
2201 2202 2203
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(OPT_TX_COMP_SUB_QUEUES);
2204
	atomic_inc(&adapter->running_cap_crqs);
2205 2206 2207
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(OPT_RX_COMP_QUEUES);
2208
	atomic_inc(&adapter->running_cap_crqs);
2209 2210 2211 2212
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
			cpu_to_be16(OPT_RX_BUFADD_Q_PER_RX_COMP_Q);
2213
	atomic_inc(&adapter->running_cap_crqs);
2214 2215 2216 2217
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
			cpu_to_be16(OPT_TX_ENTRIES_PER_SUBCRQ);
2218
	atomic_inc(&adapter->running_cap_crqs);
2219 2220 2221 2222
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability =
			cpu_to_be16(OPT_RXBA_ENTRIES_PER_SUBCRQ);
2223
	atomic_inc(&adapter->running_cap_crqs);
2224 2225 2226
	ibmvnic_send_crq(adapter, &crq);

	crq.query_capability.capability = cpu_to_be16(TX_RX_DESC_REQ);
2227
	atomic_inc(&adapter->running_cap_crqs);
2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313
	ibmvnic_send_crq(adapter, &crq);
}

static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
	union ibmvnic_crq crq;
	int i;

	dma_unmap_single(dev, adapter->ip_offload_tok,
			 sizeof(adapter->ip_offload_buf), DMA_FROM_DEVICE);

	netdev_dbg(adapter->netdev, "Query IP Offload Buffer:\n");
	for (i = 0; i < (sizeof(adapter->ip_offload_buf) - 1) / 8 + 1; i++)
		netdev_dbg(adapter->netdev, "%016lx\n",
			   ((unsigned long int *)(buf))[i]);

	netdev_dbg(adapter->netdev, "ipv4_chksum = %d\n", buf->ipv4_chksum);
	netdev_dbg(adapter->netdev, "ipv6_chksum = %d\n", buf->ipv6_chksum);
	netdev_dbg(adapter->netdev, "tcp_ipv4_chksum = %d\n",
		   buf->tcp_ipv4_chksum);
	netdev_dbg(adapter->netdev, "tcp_ipv6_chksum = %d\n",
		   buf->tcp_ipv6_chksum);
	netdev_dbg(adapter->netdev, "udp_ipv4_chksum = %d\n",
		   buf->udp_ipv4_chksum);
	netdev_dbg(adapter->netdev, "udp_ipv6_chksum = %d\n",
		   buf->udp_ipv6_chksum);
	netdev_dbg(adapter->netdev, "large_tx_ipv4 = %d\n",
		   buf->large_tx_ipv4);
	netdev_dbg(adapter->netdev, "large_tx_ipv6 = %d\n",
		   buf->large_tx_ipv6);
	netdev_dbg(adapter->netdev, "large_rx_ipv4 = %d\n",
		   buf->large_rx_ipv4);
	netdev_dbg(adapter->netdev, "large_rx_ipv6 = %d\n",
		   buf->large_rx_ipv6);
	netdev_dbg(adapter->netdev, "max_ipv4_hdr_sz = %d\n",
		   buf->max_ipv4_header_size);
	netdev_dbg(adapter->netdev, "max_ipv6_hdr_sz = %d\n",
		   buf->max_ipv6_header_size);
	netdev_dbg(adapter->netdev, "max_tcp_hdr_size = %d\n",
		   buf->max_tcp_header_size);
	netdev_dbg(adapter->netdev, "max_udp_hdr_size = %d\n",
		   buf->max_udp_header_size);
	netdev_dbg(adapter->netdev, "max_large_tx_size = %d\n",
		   buf->max_large_tx_size);
	netdev_dbg(adapter->netdev, "max_large_rx_size = %d\n",
		   buf->max_large_rx_size);
	netdev_dbg(adapter->netdev, "ipv6_ext_hdr = %d\n",
		   buf->ipv6_extension_header);
	netdev_dbg(adapter->netdev, "tcp_pseudosum_req = %d\n",
		   buf->tcp_pseudosum_req);
	netdev_dbg(adapter->netdev, "num_ipv6_ext_hd = %d\n",
		   buf->num_ipv6_ext_headers);
	netdev_dbg(adapter->netdev, "off_ipv6_ext_hd = %d\n",
		   buf->off_ipv6_ext_headers);

	adapter->ip_offload_ctrl_tok =
	    dma_map_single(dev, &adapter->ip_offload_ctrl,
			   sizeof(adapter->ip_offload_ctrl), DMA_TO_DEVICE);

	if (dma_mapping_error(dev, adapter->ip_offload_ctrl_tok)) {
		dev_err(dev, "Couldn't map ip offload control buffer\n");
		return;
	}

	adapter->ip_offload_ctrl.version = cpu_to_be32(INITIAL_VERSION_IOB);
	adapter->ip_offload_ctrl.tcp_ipv4_chksum = buf->tcp_ipv4_chksum;
	adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum;
	adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
	adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum;

	/* large_tx/rx disabled for now, additional features needed */
	adapter->ip_offload_ctrl.large_tx_ipv4 = 0;
	adapter->ip_offload_ctrl.large_tx_ipv6 = 0;
	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;

	adapter->netdev->features = NETIF_F_GSO;

	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
		adapter->netdev->features |= NETIF_F_IP_CSUM;

	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
		adapter->netdev->features |= NETIF_F_IPV6_CSUM;

2314 2315 2316 2317
	if ((adapter->netdev->features &
	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
		adapter->netdev->features |= NETIF_F_RXCSUM;

2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330
	memset(&crq, 0, sizeof(crq));
	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
	crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;
	crq.control_ip_offload.len =
	    cpu_to_be32(sizeof(adapter->ip_offload_ctrl));
	crq.control_ip_offload.ioba = cpu_to_be32(adapter->ip_offload_ctrl_tok);
	ibmvnic_send_crq(adapter, &crq);
}

static void handle_error_info_rsp(union ibmvnic_crq *crq,
				  struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
2331
	struct ibmvnic_error_buff *error_buff, *tmp;
2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342
	unsigned long flags;
	bool found = false;
	int i;

	if (!crq->request_error_rsp.rc.code) {
		dev_info(dev, "Request Error Rsp returned with rc=%x\n",
			 crq->request_error_rsp.rc.code);
		return;
	}

	spin_lock_irqsave(&adapter->error_list_lock, flags);
2343
	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
2344 2345 2346 2347 2348 2349 2350 2351 2352
		if (error_buff->error_id == crq->request_error_rsp.error_id) {
			found = true;
			list_del(&error_buff->list);
			break;
		}
	spin_unlock_irqrestore(&adapter->error_list_lock, flags);

	if (!found) {
		dev_err(dev, "Couldn't find error id %x\n",
2353
			be32_to_cpu(crq->request_error_rsp.error_id));
2354 2355 2356 2357
		return;
	}

	dev_err(dev, "Detailed info for error id %x:",
2358
		be32_to_cpu(crq->request_error_rsp.error_id));
2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385

	for (i = 0; i < error_buff->len; i++) {
		pr_cont("%02x", (int)error_buff->buff[i]);
		if (i % 8 == 7)
			pr_cont(" ");
	}
	pr_cont("\n");

	dma_unmap_single(dev, error_buff->dma, error_buff->len,
			 DMA_FROM_DEVICE);
	kfree(error_buff->buff);
	kfree(error_buff);
}

static void handle_error_indication(union ibmvnic_crq *crq,
				    struct ibmvnic_adapter *adapter)
{
	int detail_len = be32_to_cpu(crq->error_indication.detail_error_sz);
	struct ibmvnic_inflight_cmd *inflight_cmd;
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_error_buff *error_buff;
	union ibmvnic_crq new_crq;
	unsigned long flags;

	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
		crq->error_indication.
		    flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
2386 2387
		be32_to_cpu(crq->error_indication.error_id),
		be16_to_cpu(crq->error_indication.error_cause));
2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463

	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
	if (!error_buff)
		return;

	error_buff->buff = kmalloc(detail_len, GFP_ATOMIC);
	if (!error_buff->buff) {
		kfree(error_buff);
		return;
	}

	error_buff->dma = dma_map_single(dev, error_buff->buff, detail_len,
					 DMA_FROM_DEVICE);
	if (dma_mapping_error(dev, error_buff->dma)) {
		if (!firmware_has_feature(FW_FEATURE_CMO))
			dev_err(dev, "Couldn't map error buffer\n");
		kfree(error_buff->buff);
		kfree(error_buff);
		return;
	}

	inflight_cmd = kmalloc(sizeof(*inflight_cmd), GFP_ATOMIC);
	if (!inflight_cmd) {
		dma_unmap_single(dev, error_buff->dma, detail_len,
				 DMA_FROM_DEVICE);
		kfree(error_buff->buff);
		kfree(error_buff);
		return;
	}

	error_buff->len = detail_len;
	error_buff->error_id = crq->error_indication.error_id;

	spin_lock_irqsave(&adapter->error_list_lock, flags);
	list_add_tail(&error_buff->list, &adapter->errors);
	spin_unlock_irqrestore(&adapter->error_list_lock, flags);

	memset(&new_crq, 0, sizeof(new_crq));
	new_crq.request_error_info.first = IBMVNIC_CRQ_CMD;
	new_crq.request_error_info.cmd = REQUEST_ERROR_INFO;
	new_crq.request_error_info.ioba = cpu_to_be32(error_buff->dma);
	new_crq.request_error_info.len = cpu_to_be32(detail_len);
	new_crq.request_error_info.error_id = crq->error_indication.error_id;

	memcpy(&inflight_cmd->crq, &crq, sizeof(crq));

	spin_lock_irqsave(&adapter->inflight_lock, flags);
	list_add_tail(&inflight_cmd->list, &adapter->inflight);
	spin_unlock_irqrestore(&adapter->inflight_lock, flags);

	ibmvnic_send_crq(adapter, &new_crq);
}

static void handle_change_mac_rsp(union ibmvnic_crq *crq,
				  struct ibmvnic_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct device *dev = &adapter->vdev->dev;
	long rc;

	rc = crq->change_mac_addr_rsp.rc.code;
	if (rc) {
		dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc);
		return;
	}
	memcpy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0],
	       ETH_ALEN);
}

static void handle_request_cap_rsp(union ibmvnic_crq *crq,
				   struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	u64 *req_value;
	char *name;

2464
	atomic_dec(&adapter->running_cap_crqs);
2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505
	switch (be16_to_cpu(crq->request_capability_rsp.capability)) {
	case REQ_TX_QUEUES:
		req_value = &adapter->req_tx_queues;
		name = "tx";
		break;
	case REQ_RX_QUEUES:
		req_value = &adapter->req_rx_queues;
		name = "rx";
		break;
	case REQ_RX_ADD_QUEUES:
		req_value = &adapter->req_rx_add_queues;
		name = "rx_add";
		break;
	case REQ_TX_ENTRIES_PER_SUBCRQ:
		req_value = &adapter->req_tx_entries_per_subcrq;
		name = "tx_entries_per_subcrq";
		break;
	case REQ_RX_ADD_ENTRIES_PER_SUBCRQ:
		req_value = &adapter->req_rx_add_entries_per_subcrq;
		name = "rx_add_entries_per_subcrq";
		break;
	case REQ_MTU:
		req_value = &adapter->req_mtu;
		name = "mtu";
		break;
	case PROMISC_REQUESTED:
		req_value = &adapter->promisc;
		name = "promisc";
		break;
	default:
		dev_err(dev, "Got invalid cap request rsp %d\n",
			crq->request_capability.capability);
		return;
	}

	switch (crq->request_capability_rsp.rc.code) {
	case SUCCESS:
		break;
	case PARTIALSUCCESS:
		dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n",
			 *req_value,
2506
			 (long int)be64_to_cpu(crq->request_capability_rsp.
2507
					       number), name);
2508
		release_sub_crqs(adapter);
2509
		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
2510
		init_sub_crqs(adapter, 1);
2511 2512 2513 2514 2515 2516 2517 2518
		return;
	default:
		dev_err(dev, "Error %d in request cap rsp\n",
			crq->request_capability_rsp.rc.code);
		return;
	}

	/* Done receiving requested capabilities, query IP offload support */
2519
	if (atomic_read(&adapter->running_cap_crqs) == 0) {
2520 2521 2522 2523 2524
		union ibmvnic_crq newcrq;
		int buf_sz = sizeof(struct ibmvnic_query_ip_offload_buffer);
		struct ibmvnic_query_ip_offload_buffer *ip_offload_buf =
		    &adapter->ip_offload_buf;

2525
		adapter->wait_capability = false;
2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559
		adapter->ip_offload_tok = dma_map_single(dev, ip_offload_buf,
							 buf_sz,
							 DMA_FROM_DEVICE);

		if (dma_mapping_error(dev, adapter->ip_offload_tok)) {
			if (!firmware_has_feature(FW_FEATURE_CMO))
				dev_err(dev, "Couldn't map offload buffer\n");
			return;
		}

		memset(&newcrq, 0, sizeof(newcrq));
		newcrq.query_ip_offload.first = IBMVNIC_CRQ_CMD;
		newcrq.query_ip_offload.cmd = QUERY_IP_OFFLOAD;
		newcrq.query_ip_offload.len = cpu_to_be32(buf_sz);
		newcrq.query_ip_offload.ioba =
		    cpu_to_be32(adapter->ip_offload_tok);

		ibmvnic_send_crq(adapter, &newcrq);
	}
}

static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
			    struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
	struct ibmvnic_login_buffer *login = adapter->login_buf;
	int i;

	dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
			 DMA_BIDIRECTIONAL);
	dma_unmap_single(dev, adapter->login_rsp_buf_token,
			 adapter->login_rsp_buf_sz, DMA_BIDIRECTIONAL);

2560 2561 2562 2563 2564 2565 2566 2567 2568 2569
	/* If the number of queues requested can't be allocated by the
	 * server, the login response will return with code 1. We will need
	 * to resend the login buffer with fewer queues requested.
	 */
	if (login_rsp_crq->generic.rc.code) {
		adapter->renegotiate = true;
		complete(&adapter->init_done);
		return 0;
	}

2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 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 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654
	netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
	for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
		netdev_dbg(adapter->netdev, "%016lx\n",
			   ((unsigned long int *)(adapter->login_rsp_buf))[i]);
	}

	/* Sanity checks */
	if (login->num_txcomp_subcrqs != login_rsp->num_txsubm_subcrqs ||
	    (be32_to_cpu(login->num_rxcomp_subcrqs) *
	     adapter->req_rx_add_queues !=
	     be32_to_cpu(login_rsp->num_rxadd_subcrqs))) {
		dev_err(dev, "FATAL: Inconsistent login and login rsp\n");
		ibmvnic_remove(adapter->vdev);
		return -EIO;
	}
	complete(&adapter->init_done);

	return 0;
}

static void handle_request_map_rsp(union ibmvnic_crq *crq,
				   struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	u8 map_id = crq->request_map_rsp.map_id;
	int tx_subcrqs;
	int rx_subcrqs;
	long rc;
	int i;

	tx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
	rx_subcrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);

	rc = crq->request_map_rsp.rc.code;
	if (rc) {
		dev_err(dev, "Error %ld in REQUEST_MAP_RSP\n", rc);
		adapter->map_id--;
		/* need to find and zero tx/rx_pool map_id */
		for (i = 0; i < tx_subcrqs; i++) {
			if (adapter->tx_pool[i].long_term_buff.map_id == map_id)
				adapter->tx_pool[i].long_term_buff.map_id = 0;
		}
		for (i = 0; i < rx_subcrqs; i++) {
			if (adapter->rx_pool[i].long_term_buff.map_id == map_id)
				adapter->rx_pool[i].long_term_buff.map_id = 0;
		}
	}
	complete(&adapter->fw_done);
}

static void handle_request_unmap_rsp(union ibmvnic_crq *crq,
				     struct ibmvnic_adapter *adapter)
{
	struct device *dev = &adapter->vdev->dev;
	long rc;

	rc = crq->request_unmap_rsp.rc.code;
	if (rc)
		dev_err(dev, "Error %ld in REQUEST_UNMAP_RSP\n", rc);
}

static void handle_query_map_rsp(union ibmvnic_crq *crq,
				 struct ibmvnic_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct device *dev = &adapter->vdev->dev;
	long rc;

	rc = crq->query_map_rsp.rc.code;
	if (rc) {
		dev_err(dev, "Error %ld in QUERY_MAP_RSP\n", rc);
		return;
	}
	netdev_dbg(netdev, "page_size = %d\ntot_pages = %d\nfree_pages = %d\n",
		   crq->query_map_rsp.page_size, crq->query_map_rsp.tot_pages,
		   crq->query_map_rsp.free_pages);
}

static void handle_query_cap_rsp(union ibmvnic_crq *crq,
				 struct ibmvnic_adapter *adapter)
{
	struct net_device *netdev = adapter->netdev;
	struct device *dev = &adapter->vdev->dev;
	long rc;

2655
	atomic_dec(&adapter->running_cap_crqs);
2656
	netdev_dbg(netdev, "Outstanding queries: %d\n",
2657
		   atomic_read(&adapter->running_cap_crqs));
2658 2659 2660 2661 2662 2663 2664 2665 2666
	rc = crq->query_capability.rc.code;
	if (rc) {
		dev_err(dev, "Error %ld in QUERY_CAP_RSP\n", rc);
		goto out;
	}

	switch (be16_to_cpu(crq->query_capability.capability)) {
	case MIN_TX_QUEUES:
		adapter->min_tx_queues =
2667
		    be64_to_cpu(crq->query_capability.number);
2668 2669 2670 2671 2672
		netdev_dbg(netdev, "min_tx_queues = %lld\n",
			   adapter->min_tx_queues);
		break;
	case MIN_RX_QUEUES:
		adapter->min_rx_queues =
2673
		    be64_to_cpu(crq->query_capability.number);
2674 2675 2676 2677 2678
		netdev_dbg(netdev, "min_rx_queues = %lld\n",
			   adapter->min_rx_queues);
		break;
	case MIN_RX_ADD_QUEUES:
		adapter->min_rx_add_queues =
2679
		    be64_to_cpu(crq->query_capability.number);
2680 2681 2682 2683 2684
		netdev_dbg(netdev, "min_rx_add_queues = %lld\n",
			   adapter->min_rx_add_queues);
		break;
	case MAX_TX_QUEUES:
		adapter->max_tx_queues =
2685
		    be64_to_cpu(crq->query_capability.number);
2686 2687 2688 2689 2690
		netdev_dbg(netdev, "max_tx_queues = %lld\n",
			   adapter->max_tx_queues);
		break;
	case MAX_RX_QUEUES:
		adapter->max_rx_queues =
2691
		    be64_to_cpu(crq->query_capability.number);
2692 2693 2694 2695 2696
		netdev_dbg(netdev, "max_rx_queues = %lld\n",
			   adapter->max_rx_queues);
		break;
	case MAX_RX_ADD_QUEUES:
		adapter->max_rx_add_queues =
2697
		    be64_to_cpu(crq->query_capability.number);
2698 2699 2700 2701 2702
		netdev_dbg(netdev, "max_rx_add_queues = %lld\n",
			   adapter->max_rx_add_queues);
		break;
	case MIN_TX_ENTRIES_PER_SUBCRQ:
		adapter->min_tx_entries_per_subcrq =
2703
		    be64_to_cpu(crq->query_capability.number);
2704 2705 2706 2707 2708
		netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n",
			   adapter->min_tx_entries_per_subcrq);
		break;
	case MIN_RX_ADD_ENTRIES_PER_SUBCRQ:
		adapter->min_rx_add_entries_per_subcrq =
2709
		    be64_to_cpu(crq->query_capability.number);
2710 2711 2712 2713 2714
		netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n",
			   adapter->min_rx_add_entries_per_subcrq);
		break;
	case MAX_TX_ENTRIES_PER_SUBCRQ:
		adapter->max_tx_entries_per_subcrq =
2715
		    be64_to_cpu(crq->query_capability.number);
2716 2717 2718 2719 2720
		netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n",
			   adapter->max_tx_entries_per_subcrq);
		break;
	case MAX_RX_ADD_ENTRIES_PER_SUBCRQ:
		adapter->max_rx_add_entries_per_subcrq =
2721
		    be64_to_cpu(crq->query_capability.number);
2722 2723 2724 2725 2726
		netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n",
			   adapter->max_rx_add_entries_per_subcrq);
		break;
	case TCP_IP_OFFLOAD:
		adapter->tcp_ip_offload =
2727
		    be64_to_cpu(crq->query_capability.number);
2728 2729 2730 2731 2732
		netdev_dbg(netdev, "tcp_ip_offload = %lld\n",
			   adapter->tcp_ip_offload);
		break;
	case PROMISC_SUPPORTED:
		adapter->promisc_supported =
2733
		    be64_to_cpu(crq->query_capability.number);
2734 2735 2736 2737
		netdev_dbg(netdev, "promisc_supported = %lld\n",
			   adapter->promisc_supported);
		break;
	case MIN_MTU:
2738
		adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
2739
		netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
2740 2741 2742
		netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
		break;
	case MAX_MTU:
2743
		adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
2744
		netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
2745 2746 2747 2748
		netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
		break;
	case MAX_MULTICAST_FILTERS:
		adapter->max_multicast_filters =
2749
		    be64_to_cpu(crq->query_capability.number);
2750 2751 2752 2753 2754
		netdev_dbg(netdev, "max_multicast_filters = %lld\n",
			   adapter->max_multicast_filters);
		break;
	case VLAN_HEADER_INSERTION:
		adapter->vlan_header_insertion =
2755
		    be64_to_cpu(crq->query_capability.number);
2756 2757 2758 2759 2760 2761 2762
		if (adapter->vlan_header_insertion)
			netdev->features |= NETIF_F_HW_VLAN_STAG_TX;
		netdev_dbg(netdev, "vlan_header_insertion = %lld\n",
			   adapter->vlan_header_insertion);
		break;
	case MAX_TX_SG_ENTRIES:
		adapter->max_tx_sg_entries =
2763
		    be64_to_cpu(crq->query_capability.number);
2764 2765 2766 2767 2768
		netdev_dbg(netdev, "max_tx_sg_entries = %lld\n",
			   adapter->max_tx_sg_entries);
		break;
	case RX_SG_SUPPORTED:
		adapter->rx_sg_supported =
2769
		    be64_to_cpu(crq->query_capability.number);
2770 2771 2772 2773 2774
		netdev_dbg(netdev, "rx_sg_supported = %lld\n",
			   adapter->rx_sg_supported);
		break;
	case OPT_TX_COMP_SUB_QUEUES:
		adapter->opt_tx_comp_sub_queues =
2775
		    be64_to_cpu(crq->query_capability.number);
2776 2777 2778 2779 2780
		netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n",
			   adapter->opt_tx_comp_sub_queues);
		break;
	case OPT_RX_COMP_QUEUES:
		adapter->opt_rx_comp_queues =
2781
		    be64_to_cpu(crq->query_capability.number);
2782 2783 2784 2785 2786
		netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n",
			   adapter->opt_rx_comp_queues);
		break;
	case OPT_RX_BUFADD_Q_PER_RX_COMP_Q:
		adapter->opt_rx_bufadd_q_per_rx_comp_q =
2787
		    be64_to_cpu(crq->query_capability.number);
2788 2789 2790 2791 2792
		netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n",
			   adapter->opt_rx_bufadd_q_per_rx_comp_q);
		break;
	case OPT_TX_ENTRIES_PER_SUBCRQ:
		adapter->opt_tx_entries_per_subcrq =
2793
		    be64_to_cpu(crq->query_capability.number);
2794 2795 2796 2797 2798
		netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n",
			   adapter->opt_tx_entries_per_subcrq);
		break;
	case OPT_RXBA_ENTRIES_PER_SUBCRQ:
		adapter->opt_rxba_entries_per_subcrq =
2799
		    be64_to_cpu(crq->query_capability.number);
2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814
		netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n",
			   adapter->opt_rxba_entries_per_subcrq);
		break;
	case TX_RX_DESC_REQ:
		adapter->tx_rx_desc_req = crq->query_capability.number;
		netdev_dbg(netdev, "tx_rx_desc_req = %llx\n",
			   adapter->tx_rx_desc_req);
		break;

	default:
		netdev_err(netdev, "Got invalid cap rsp %d\n",
			   crq->query_capability.capability);
	}

out:
2815 2816
	if (atomic_read(&adapter->running_cap_crqs) == 0) {
		adapter->wait_capability = false;
2817
		init_sub_crqs(adapter, 0);
2818
		/* We're done querying the capabilities, initialize sub-crqs */
2819
	}
2820 2821 2822 2823
}

static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
{
2824
	struct ibmvnic_inflight_cmd *inflight_cmd, *tmp1;
2825
	struct device *dev = &adapter->vdev->dev;
2826
	struct ibmvnic_error_buff *error_buff, *tmp2;
2827 2828 2829 2830
	unsigned long flags;
	unsigned long flags2;

	spin_lock_irqsave(&adapter->inflight_lock, flags);
2831
	list_for_each_entry_safe(inflight_cmd, tmp1, &adapter->inflight, list) {
2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844
		switch (inflight_cmd->crq.generic.cmd) {
		case LOGIN:
			dma_unmap_single(dev, adapter->login_buf_token,
					 adapter->login_buf_sz,
					 DMA_BIDIRECTIONAL);
			dma_unmap_single(dev, adapter->login_rsp_buf_token,
					 adapter->login_rsp_buf_sz,
					 DMA_BIDIRECTIONAL);
			kfree(adapter->login_rsp_buf);
			kfree(adapter->login_buf);
			break;
		case REQUEST_ERROR_INFO:
			spin_lock_irqsave(&adapter->error_list_lock, flags2);
2845 2846
			list_for_each_entry_safe(error_buff, tmp2,
						 &adapter->errors, list) {
2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863
				dma_unmap_single(dev, error_buff->dma,
						 error_buff->len,
						 DMA_FROM_DEVICE);
				kfree(error_buff->buff);
				list_del(&error_buff->list);
				kfree(error_buff);
			}
			spin_unlock_irqrestore(&adapter->error_list_lock,
					       flags2);
			break;
		}
		list_del(&inflight_cmd->list);
		kfree(inflight_cmd);
	}
	spin_unlock_irqrestore(&adapter->inflight_lock, flags);
}

2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884
static void ibmvnic_xport_event(struct work_struct *work)
{
	struct ibmvnic_adapter *adapter = container_of(work,
						       struct ibmvnic_adapter,
						       ibmvnic_xport);
	struct device *dev = &adapter->vdev->dev;
	long rc;

	ibmvnic_free_inflight(adapter);
	release_sub_crqs(adapter);
	if (adapter->migrated) {
		rc = ibmvnic_reenable_crq_queue(adapter);
		if (rc)
			dev_err(dev, "Error after enable rc=%ld\n", rc);
		adapter->migrated = false;
		rc = ibmvnic_send_crq_init(adapter);
		if (rc)
			dev_err(dev, "Error sending init rc=%ld\n", rc);
	}
}

2885 2886 2887 2888 2889 2890
static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
			       struct ibmvnic_adapter *adapter)
{
	struct ibmvnic_generic_crq *gen_crq = &crq->generic;
	struct net_device *netdev = adapter->netdev;
	struct device *dev = &adapter->vdev->dev;
2891
	u64 *u64_crq = (u64 *)crq;
2892 2893 2894
	long rc;

	netdev_dbg(netdev, "Handling CRQ: %016lx %016lx\n",
2895 2896
		   (unsigned long int)cpu_to_be64(u64_crq[0]),
		   (unsigned long int)cpu_to_be64(u64_crq[1]));
2897 2898 2899 2900 2901 2902 2903
	switch (gen_crq->first) {
	case IBMVNIC_CRQ_INIT_RSP:
		switch (gen_crq->cmd) {
		case IBMVNIC_CRQ_INIT:
			dev_info(dev, "Partner initialized\n");
			/* Send back a response */
			rc = ibmvnic_send_crq_init_complete(adapter);
2904 2905
			if (!rc)
				schedule_work(&adapter->vnic_crq_init);
2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920
			else
				dev_err(dev, "Can't send initrsp rc=%ld\n", rc);
			break;
		case IBMVNIC_CRQ_INIT_COMPLETE:
			dev_info(dev, "Partner initialization complete\n");
			send_version_xchg(adapter);
			break;
		default:
			dev_err(dev, "Unknown crq cmd: %d\n", gen_crq->cmd);
		}
		return;
	case IBMVNIC_CRQ_XPORT_EVENT:
		if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
			dev_info(dev, "Re-enabling adapter\n");
			adapter->migrated = true;
2921
			schedule_work(&adapter->ibmvnic_xport);
2922 2923 2924 2925
		} else if (gen_crq->cmd == IBMVNIC_DEVICE_FAILOVER) {
			dev_info(dev, "Backing device failover detected\n");
			netif_carrier_off(netdev);
			adapter->failover = true;
2926 2927 2928 2929
		} else {
			/* The adapter lost the connection */
			dev_err(dev, "Virtual Adapter failed (rc=%d)\n",
				gen_crq->cmd);
2930
			schedule_work(&adapter->ibmvnic_xport);
2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 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 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014
		}
		return;
	case IBMVNIC_CRQ_CMD_RSP:
		break;
	default:
		dev_err(dev, "Got an invalid msg type 0x%02x\n",
			gen_crq->first);
		return;
	}

	switch (gen_crq->cmd) {
	case VERSION_EXCHANGE_RSP:
		rc = crq->version_exchange_rsp.rc.code;
		if (rc) {
			dev_err(dev, "Error %ld in VERSION_EXCHG_RSP\n", rc);
			break;
		}
		dev_info(dev, "Partner protocol version is %d\n",
			 crq->version_exchange_rsp.version);
		if (be16_to_cpu(crq->version_exchange_rsp.version) <
		    ibmvnic_version)
			ibmvnic_version =
			    be16_to_cpu(crq->version_exchange_rsp.version);
		send_cap_queries(adapter);
		break;
	case QUERY_CAPABILITY_RSP:
		handle_query_cap_rsp(crq, adapter);
		break;
	case QUERY_MAP_RSP:
		handle_query_map_rsp(crq, adapter);
		break;
	case REQUEST_MAP_RSP:
		handle_request_map_rsp(crq, adapter);
		break;
	case REQUEST_UNMAP_RSP:
		handle_request_unmap_rsp(crq, adapter);
		break;
	case REQUEST_CAPABILITY_RSP:
		handle_request_cap_rsp(crq, adapter);
		break;
	case LOGIN_RSP:
		netdev_dbg(netdev, "Got Login Response\n");
		handle_login_rsp(crq, adapter);
		break;
	case LOGICAL_LINK_STATE_RSP:
		netdev_dbg(netdev, "Got Logical Link State Response\n");
		adapter->logical_link_state =
		    crq->logical_link_state_rsp.link_state;
		break;
	case LINK_STATE_INDICATION:
		netdev_dbg(netdev, "Got Logical Link State Indication\n");
		adapter->phys_link_state =
		    crq->link_state_indication.phys_link_state;
		adapter->logical_link_state =
		    crq->link_state_indication.logical_link_state;
		break;
	case CHANGE_MAC_ADDR_RSP:
		netdev_dbg(netdev, "Got MAC address change Response\n");
		handle_change_mac_rsp(crq, adapter);
		break;
	case ERROR_INDICATION:
		netdev_dbg(netdev, "Got Error Indication\n");
		handle_error_indication(crq, adapter);
		break;
	case REQUEST_ERROR_RSP:
		netdev_dbg(netdev, "Got Error Detail Response\n");
		handle_error_info_rsp(crq, adapter);
		break;
	case REQUEST_STATISTICS_RSP:
		netdev_dbg(netdev, "Got Statistics Response\n");
		complete(&adapter->stats_done);
		break;
	case QUERY_IP_OFFLOAD_RSP:
		netdev_dbg(netdev, "Got Query IP offload Response\n");
		handle_query_ip_offload_rsp(adapter);
		break;
	case MULTICAST_CTRL_RSP:
		netdev_dbg(netdev, "Got multicast control Response\n");
		break;
	case CONTROL_IP_OFFLOAD_RSP:
		netdev_dbg(netdev, "Got Control IP offload Response\n");
		dma_unmap_single(dev, adapter->ip_offload_ctrl_tok,
				 sizeof(adapter->ip_offload_ctrl),
				 DMA_TO_DEVICE);
3015
		complete(&adapter->init_done);
3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029
		break;
	case COLLECT_FW_TRACE_RSP:
		netdev_dbg(netdev, "Got Collect firmware trace Response\n");
		complete(&adapter->fw_done);
		break;
	default:
		netdev_err(netdev, "Got an invalid cmd type 0x%02x\n",
			   gen_crq->cmd);
	}
}

static irqreturn_t ibmvnic_interrupt(int irq, void *instance)
{
	struct ibmvnic_adapter *adapter = instance;
3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041
	unsigned long flags;

	spin_lock_irqsave(&adapter->crq.lock, flags);
	vio_disable_interrupts(adapter->vdev);
	tasklet_schedule(&adapter->tasklet);
	spin_unlock_irqrestore(&adapter->crq.lock, flags);
	return IRQ_HANDLED;
}

static void ibmvnic_tasklet(void *data)
{
	struct ibmvnic_adapter *adapter = data;
3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062
	struct ibmvnic_crq_queue *queue = &adapter->crq;
	struct vio_dev *vdev = adapter->vdev;
	union ibmvnic_crq *crq;
	unsigned long flags;
	bool done = false;

	spin_lock_irqsave(&queue->lock, flags);
	vio_disable_interrupts(vdev);
	while (!done) {
		/* Pull all the valid messages off the CRQ */
		while ((crq = ibmvnic_next_crq(adapter)) != NULL) {
			ibmvnic_handle_crq(crq, adapter);
			crq->generic.first = 0;
		}
		vio_enable_interrupts(vdev);
		crq = ibmvnic_next_crq(adapter);
		if (crq) {
			vio_disable_interrupts(vdev);
			ibmvnic_handle_crq(crq, adapter);
			crq->generic.first = 0;
		} else {
3063 3064 3065 3066 3067
			/* remain in tasklet until all
			 * capabilities responses are received
			 */
			if (!adapter->wait_capability)
				done = true;
3068 3069
		}
	}
3070 3071 3072 3073 3074
	/* if capabilities CRQ's were sent in this tasklet, the following
	 * tasklet must wait until all responses are received
	 */
	if (atomic_read(&adapter->running_cap_crqs) != 0)
		adapter->wait_capability = true;
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 3114 3115 3116 3117 3118 3119 3120 3121
	spin_unlock_irqrestore(&queue->lock, flags);
}

static int ibmvnic_reenable_crq_queue(struct ibmvnic_adapter *adapter)
{
	struct vio_dev *vdev = adapter->vdev;
	int rc;

	do {
		rc = plpar_hcall_norets(H_ENABLE_CRQ, vdev->unit_address);
	} while (rc == H_IN_PROGRESS || rc == H_BUSY || H_IS_LONG_BUSY(rc));

	if (rc)
		dev_err(&vdev->dev, "Error enabling adapter (rc=%d)\n", rc);

	return rc;
}

static int ibmvnic_reset_crq(struct ibmvnic_adapter *adapter)
{
	struct ibmvnic_crq_queue *crq = &adapter->crq;
	struct device *dev = &adapter->vdev->dev;
	struct vio_dev *vdev = adapter->vdev;
	int rc;

	/* Close the CRQ */
	do {
		rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));

	/* Clean out the queue */
	memset(crq->msgs, 0, PAGE_SIZE);
	crq->cur = 0;

	/* And re-open it again */
	rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
				crq->msg_token, PAGE_SIZE);

	if (rc == H_CLOSED)
		/* Adapter is good, but other end is not ready */
		dev_warn(dev, "Partner adapter not ready\n");
	else if (rc != 0)
		dev_warn(dev, "Couldn't register crq (rc=%d)\n", rc);

	return rc;
}

3122
static void release_crq_queue(struct ibmvnic_adapter *adapter)
3123 3124 3125 3126 3127
{
	struct ibmvnic_crq_queue *crq = &adapter->crq;
	struct vio_dev *vdev = adapter->vdev;
	long rc;

3128 3129 3130
	if (!crq->msgs)
		return;

3131 3132
	netdev_dbg(adapter->netdev, "Releasing CRQ\n");
	free_irq(vdev->irq, adapter);
3133
	tasklet_kill(&adapter->tasklet);
3134 3135 3136 3137 3138 3139 3140
	do {
		rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));

	dma_unmap_single(&vdev->dev, crq->msg_token, PAGE_SIZE,
			 DMA_BIDIRECTIONAL);
	free_page((unsigned long)crq->msgs);
3141
	crq->msgs = NULL;
3142 3143
}

3144
static int init_crq_queue(struct ibmvnic_adapter *adapter)
3145 3146 3147 3148 3149 3150
{
	struct ibmvnic_crq_queue *crq = &adapter->crq;
	struct device *dev = &adapter->vdev->dev;
	struct vio_dev *vdev = adapter->vdev;
	int rc, retrc = -ENOMEM;

3151 3152 3153
	if (crq->msgs)
		return 0;

3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182
	crq->msgs = (union ibmvnic_crq *)get_zeroed_page(GFP_KERNEL);
	/* Should we allocate more than one page? */

	if (!crq->msgs)
		return -ENOMEM;

	crq->size = PAGE_SIZE / sizeof(*crq->msgs);
	crq->msg_token = dma_map_single(dev, crq->msgs, PAGE_SIZE,
					DMA_BIDIRECTIONAL);
	if (dma_mapping_error(dev, crq->msg_token))
		goto map_failed;

	rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
				crq->msg_token, PAGE_SIZE);

	if (rc == H_RESOURCE)
		/* maybe kexecing and resource is busy. try a reset */
		rc = ibmvnic_reset_crq(adapter);
	retrc = rc;

	if (rc == H_CLOSED) {
		dev_warn(dev, "Partner adapter not ready\n");
	} else if (rc) {
		dev_warn(dev, "Error %d opening adapter\n", rc);
		goto reg_crq_failed;
	}

	retrc = 0;

3183 3184 3185
	tasklet_init(&adapter->tasklet, (void *)ibmvnic_tasklet,
		     (unsigned long)adapter);

3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206
	netdev_dbg(adapter->netdev, "registering irq 0x%x\n", vdev->irq);
	rc = request_irq(vdev->irq, ibmvnic_interrupt, 0, IBMVNIC_NAME,
			 adapter);
	if (rc) {
		dev_err(dev, "Couldn't register irq 0x%x. rc=%d\n",
			vdev->irq, rc);
		goto req_irq_failed;
	}

	rc = vio_enable_interrupts(vdev);
	if (rc) {
		dev_err(dev, "Error %d enabling interrupts\n", rc);
		goto req_irq_failed;
	}

	crq->cur = 0;
	spin_lock_init(&crq->lock);

	return retrc;

req_irq_failed:
3207
	tasklet_kill(&adapter->tasklet);
3208 3209 3210 3211 3212 3213 3214
	do {
		rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
	} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
reg_crq_failed:
	dma_unmap_single(dev, crq->msg_token, PAGE_SIZE, DMA_BIDIRECTIONAL);
map_failed:
	free_page((unsigned long)crq->msgs);
3215
	crq->msgs = NULL;
3216 3217 3218
	return retrc;
}

3219 3220 3221 3222 3223 3224 3225 3226
static void handle_crq_init_rsp(struct work_struct *work)
{
	struct ibmvnic_adapter *adapter = container_of(work,
						       struct ibmvnic_adapter,
						       vnic_crq_init);
	struct device *dev = &adapter->vdev->dev;
	struct net_device *netdev = adapter->netdev;
	unsigned long timeout = msecs_to_jiffies(30000);
3227
	bool restart = false;
3228 3229
	int rc;

3230 3231 3232 3233 3234 3235 3236 3237 3238
	if (adapter->failover) {
		release_sub_crqs(adapter);
		if (netif_running(netdev)) {
			netif_tx_disable(netdev);
			ibmvnic_close(netdev);
			restart = true;
		}
	}

3239
	reinit_completion(&adapter->init_done);
3240
	send_version_xchg(adapter);
3241 3242 3243 3244 3245
	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
		dev_err(dev, "Passive init timeout\n");
		goto task_failed;
	}

3246
	netdev->mtu = adapter->req_mtu - ETH_HLEN;
3247

3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258
	if (adapter->failover) {
		adapter->failover = false;
		if (restart) {
			rc = ibmvnic_open(netdev);
			if (rc)
				goto restart_failed;
		}
		netif_carrier_on(netdev);
		return;
	}

3259 3260 3261 3262 3263 3264 3265 3266 3267 3268
	rc = register_netdev(netdev);
	if (rc) {
		dev_err(dev,
			"failed to register netdev rc=%d\n", rc);
		goto register_failed;
	}
	dev_info(dev, "ibmvnic registered\n");

	return;

3269 3270
restart_failed:
	dev_err(dev, "Failed to restart ibmvnic, rc=%d\n", rc);
3271 3272 3273 3274 3275 3276
register_failed:
	release_sub_crqs(adapter);
task_failed:
	dev_err(dev, "Passive initialization was not successful\n");
}

3277
static int ibmvnic_init(struct ibmvnic_adapter *adapter)
3278
{
3279
	struct device *dev = &adapter->vdev->dev;
3280
	unsigned long timeout = msecs_to_jiffies(30000);
3281 3282
	int rc;

3283
	rc = init_crq_queue(adapter);
3284 3285 3286 3287 3288
	if (rc) {
		dev_err(dev, "Couldn't initialize crq. rc=%d\n", rc);
		return rc;
	}

3289 3290
	rc = init_stats_token(adapter);
	if (rc) {
3291
		release_crq_queue(adapter);
3292
		return rc;
3293 3294 3295 3296 3297 3298
	}

	init_completion(&adapter->init_done);
	ibmvnic_send_crq_init(adapter);
	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
		dev_err(dev, "Initialization sequence timed out\n");
3299
		release_crq_queue(adapter);
3300 3301 3302 3303 3304 3305 3306 3307
		return -1;
	}

	return 0;
}

static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
{
3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333
	struct ibmvnic_adapter *adapter;
	struct net_device *netdev;
	unsigned char *mac_addr_p;
	int rc;

	dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
		dev->unit_address);

	mac_addr_p = (unsigned char *)vio_get_attribute(dev,
							VETH_MAC_ADDR, NULL);
	if (!mac_addr_p) {
		dev_err(&dev->dev,
			"(%s:%3.3d) ERROR: Can't find MAC_ADDR attribute\n",
			__FILE__, __LINE__);
		return 0;
	}

	netdev = alloc_etherdev_mq(sizeof(struct ibmvnic_adapter),
				   IBMVNIC_MAX_TX_QUEUES);
	if (!netdev)
		return -ENOMEM;

	adapter = netdev_priv(netdev);
	dev_set_drvdata(&dev->dev, netdev);
	adapter->vdev = dev;
	adapter->netdev = netdev;
3334
	adapter->failover = false;
3335 3336 3337 3338 3339 3340 3341 3342

	ether_addr_copy(adapter->mac_addr, mac_addr_p);
	ether_addr_copy(netdev->dev_addr, adapter->mac_addr);
	netdev->irq = dev->irq;
	netdev->netdev_ops = &ibmvnic_netdev_ops;
	netdev->ethtool_ops = &ibmvnic_ethtool_ops;
	SET_NETDEV_DEV(netdev, &dev->dev);

3343
	INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
3344
	INIT_WORK(&adapter->ibmvnic_xport, ibmvnic_xport_event);
3345

3346 3347 3348 3349 3350 3351 3352
	spin_lock_init(&adapter->stats_lock);

	INIT_LIST_HEAD(&adapter->errors);
	INIT_LIST_HEAD(&adapter->inflight);
	spin_lock_init(&adapter->error_list_lock);
	spin_lock_init(&adapter->inflight_lock);

3353 3354 3355 3356
	rc = ibmvnic_init(adapter);
	if (rc) {
		free_netdev(netdev);
		return rc;
3357 3358
	}

3359
	netdev->mtu = adapter->req_mtu - ETH_HLEN;
3360
	adapter->is_closed = false;
3361 3362 3363 3364

	rc = register_netdev(netdev);
	if (rc) {
		dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
3365 3366
		free_netdev(netdev);
		return rc;
3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463
	}
	dev_info(&dev->dev, "ibmvnic registered\n");

	return 0;
}

static int ibmvnic_remove(struct vio_dev *dev)
{
	struct net_device *netdev = dev_get_drvdata(&dev->dev);

	unregister_netdev(netdev);
	free_netdev(netdev);
	dev_set_drvdata(&dev->dev, NULL);

	return 0;
}

static unsigned long ibmvnic_get_desired_dma(struct vio_dev *vdev)
{
	struct net_device *netdev = dev_get_drvdata(&vdev->dev);
	struct ibmvnic_adapter *adapter;
	struct iommu_table *tbl;
	unsigned long ret = 0;
	int i;

	tbl = get_iommu_table_base(&vdev->dev);

	/* netdev inits at probe time along with the structures we need below*/
	if (!netdev)
		return IOMMU_PAGE_ALIGN(IBMVNIC_IO_ENTITLEMENT_DEFAULT, tbl);

	adapter = netdev_priv(netdev);

	ret += PAGE_SIZE; /* the crq message queue */
	ret += adapter->bounce_buffer_size;
	ret += IOMMU_PAGE_ALIGN(sizeof(struct ibmvnic_statistics), tbl);

	for (i = 0; i < adapter->req_tx_queues + adapter->req_rx_queues; i++)
		ret += 4 * PAGE_SIZE; /* the scrq message queue */

	for (i = 0; i < be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs);
	     i++)
		ret += adapter->rx_pool[i].size *
		    IOMMU_PAGE_ALIGN(adapter->rx_pool[i].buff_size, tbl);

	return ret;
}

static int ibmvnic_resume(struct device *dev)
{
	struct net_device *netdev = dev_get_drvdata(dev);
	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
	int i;

	/* kick the interrupt handlers just in case we lost an interrupt */
	for (i = 0; i < adapter->req_rx_queues; i++)
		ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq,
				     adapter->rx_scrq[i]);

	return 0;
}

static struct vio_device_id ibmvnic_device_table[] = {
	{"network", "IBM,vnic"},
	{"", "" }
};
MODULE_DEVICE_TABLE(vio, ibmvnic_device_table);

static const struct dev_pm_ops ibmvnic_pm_ops = {
	.resume = ibmvnic_resume
};

static struct vio_driver ibmvnic_driver = {
	.id_table       = ibmvnic_device_table,
	.probe          = ibmvnic_probe,
	.remove         = ibmvnic_remove,
	.get_desired_dma = ibmvnic_get_desired_dma,
	.name		= ibmvnic_driver_name,
	.pm		= &ibmvnic_pm_ops,
};

/* module functions */
static int __init ibmvnic_module_init(void)
{
	pr_info("%s: %s %s\n", ibmvnic_driver_name, ibmvnic_driver_string,
		IBMVNIC_DRIVER_VERSION);

	return vio_register_driver(&ibmvnic_driver);
}

static void __exit ibmvnic_module_exit(void)
{
	vio_unregister_driver(&ibmvnic_driver);
}

module_init(ibmvnic_module_init);
module_exit(ibmvnic_module_exit);