ixgbe_sriov.c 29.2 KB
Newer Older
G
Greg Rose 已提交
1 2 3
/*******************************************************************************

  Intel 10 Gigabit PCI Express Linux driver
D
Don Skidmore 已提交
4
  Copyright(c) 1999 - 2012 Intel Corporation.
G
Greg Rose 已提交
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

  This program is free software; you can redistribute it and/or modify it
  under the terms and conditions of the GNU General Public License,
  version 2, as published by the Free Software Foundation.

  This program is distributed in the hope 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; if not, write to the Free Software Foundation, Inc.,
  51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.

  The full GNU General Public License is included in this distribution in
  the file called "COPYING".

  Contact Information:
  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497

*******************************************************************************/

#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/ipv6.h>
#ifdef NETIF_F_HW_VLAN_TX
#include <linux/if_vlan.h>
#endif

#include "ixgbe.h"
G
Greg Rose 已提交
43
#include "ixgbe_type.h"
G
Greg Rose 已提交
44 45
#include "ixgbe_sriov.h"

G
Greg Rose 已提交
46 47 48 49 50 51 52 53 54
#ifdef CONFIG_PCI_IOV
void ixgbe_enable_sriov(struct ixgbe_adapter *adapter,
			 const struct ixgbe_info *ii)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int num_vf_macvlans, i;
	struct vf_macvlans *mv_list;
	int pre_existing_vfs = 0;

55
	pre_existing_vfs = pci_num_vf(adapter->pdev);
G
Greg Rose 已提交
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73
	if (!pre_existing_vfs && !adapter->num_vfs)
		return;

	/* If there are pre-existing VFs then we have to force
	 * use of that many because they were not deleted the last
	 * time someone removed the PF driver.  That would have
	 * been because they were allocated to guest VMs and can't
	 * be removed.  Go ahead and just re-enable the old amount.
	 * If the user wants to change the number of VFs they can
	 * use ethtool while making sure no VFs are allocated to
	 * guest VMs... i.e. the right way.
	 */
	if (pre_existing_vfs) {
		adapter->num_vfs = pre_existing_vfs;
		dev_warn(&adapter->pdev->dev, "Virtual Functions already "
			 "enabled for this device - Please reload all "
			 "VF drivers to avoid spoofed packet errors\n");
	} else {
74 75 76 77 78 79 80 81 82 83
		int err;
		/*
		 * The 82599 supports up to 64 VFs per physical function
		 * but this implementation limits allocation to 63 so that
		 * basic networking resources are still available to the
		 * physical function.  If the user requests greater thn
		 * 63 VFs then it is an error - reset to default of zero.
		 */
		adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, 63);

G
Greg Rose 已提交
84
		err = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
85 86
		if (err) {
			e_err(probe, "Failed to enable PCI sriov: %d\n", err);
87 88
			adapter->num_vfs = 0;
			return;
89
		}
G
Greg Rose 已提交
90 91
	}

92
	adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED;
G
Greg Rose 已提交
93 94
	e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs);

95 96 97 98 99 100
	/* Enable VMDq flag so device will be set in VM mode */
	adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED;
	if (!adapter->ring_feature[RING_F_VMDQ].limit)
		adapter->ring_feature[RING_F_VMDQ].limit = 1;
	adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs;

G
Greg Rose 已提交
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
	num_vf_macvlans = hw->mac.num_rar_entries -
	(IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs);

	adapter->mv_list = mv_list = kcalloc(num_vf_macvlans,
					     sizeof(struct vf_macvlans),
					     GFP_KERNEL);
	if (mv_list) {
		/* Initialize list of VF macvlans */
		INIT_LIST_HEAD(&adapter->vf_mvs.l);
		for (i = 0; i < num_vf_macvlans; i++) {
			mv_list->vf = -1;
			mv_list->free = true;
			mv_list->rar_entry = hw->mac.num_rar_entries -
				(i + adapter->num_vfs + 1);
			list_add(&mv_list->l, &adapter->vf_mvs.l);
			mv_list++;
		}
	}

	/* If call to enable VFs succeeded then allocate memory
	 * for per VF control structures.
	 */
	adapter->vfinfo =
		kcalloc(adapter->num_vfs,
			sizeof(struct vf_data_storage), GFP_KERNEL);
	if (adapter->vfinfo) {
		/* Now that we're sure SR-IOV is enabled
		 * and memory allocated set up the mailbox parameters
		 */
		ixgbe_init_mbx_params_pf(hw);
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
		memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops));

		/* limit trafffic classes based on VFs enabled */
		if ((adapter->hw.mac.type == ixgbe_mac_82599EB) &&
		    (adapter->num_vfs < 16)) {
			adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS;
			adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS;
		} else if (adapter->num_vfs < 32) {
			adapter->dcb_cfg.num_tcs.pg_tcs = 4;
			adapter->dcb_cfg.num_tcs.pfc_tcs = 4;
		} else {
			adapter->dcb_cfg.num_tcs.pg_tcs = 1;
			adapter->dcb_cfg.num_tcs.pfc_tcs = 1;
		}

		/* We do not support RSS w/ SR-IOV */
		adapter->ring_feature[RING_F_RSS].limit = 1;
G
Greg Rose 已提交
148 149 150 151

		/* Disable RSC when in SR-IOV mode */
		adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE |
				     IXGBE_FLAG2_RSC_ENABLED);
152 153

		/* enable spoof checking for all VFs */
154 155
		for (i = 0; i < adapter->num_vfs; i++)
			adapter->vfinfo[i].spoofchk_enabled = true;
G
Greg Rose 已提交
156 157 158 159 160 161
		return;
	}

	/* Oh oh */
	e_err(probe, "Unable to allocate memory for VF Data Storage - "
	      "SRIOV disabled\n");
162
	ixgbe_disable_sriov(adapter);
G
Greg Rose 已提交
163 164
}

165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
static bool ixgbe_vfs_are_assigned(struct ixgbe_adapter *adapter)
{
	struct pci_dev *pdev = adapter->pdev;
	struct pci_dev *vfdev;
	int dev_id;

	switch (adapter->hw.mac.type) {
	case ixgbe_mac_82599EB:
		dev_id = IXGBE_DEV_ID_82599_VF;
		break;
	case ixgbe_mac_X540:
		dev_id = IXGBE_DEV_ID_X540_VF;
		break;
	default:
		return false;
	}

	/* loop through all the VFs to see if we own any that are assigned */
	vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL);
	while (vfdev) {
		/* if we don't own it we don't care */
		if (vfdev->is_virtfn && vfdev->physfn == pdev) {
			/* if it is assigned we cannot release it */
			if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED)
				return true;
		}

		vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev);
	}

	return false;
}

#endif /* #ifdef CONFIG_PCI_IOV */
G
Greg Rose 已提交
199 200 201 202 203 204
void ixgbe_disable_sriov(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 gpie;
	u32 vmdctl;

205 206 207 208 209 210 211 212 213 214 215
	/* set num VFs to 0 to prevent access to vfinfo */
	adapter->num_vfs = 0;

	/* free VF control structures */
	kfree(adapter->vfinfo);
	adapter->vfinfo = NULL;

	/* free macvlan list */
	kfree(adapter->mv_list);
	adapter->mv_list = NULL;

216 217 218 219
	/* if SR-IOV is already disabled then there is nothing to do */
	if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED))
		return;

G
Greg Rose 已提交
220
#ifdef CONFIG_PCI_IOV
221 222 223 224 225 226 227 228
	/*
	 * If our VFs are assigned we cannot shut down SR-IOV
	 * without causing issues, so just leave the hardware
	 * available but disabled
	 */
	if (ixgbe_vfs_are_assigned(adapter)) {
		e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n");
		return;
229
	}
G
Greg Rose 已提交
230 231 232 233 234
	/* disable iov and allow time for transactions to clear */
	pci_disable_sriov(adapter->pdev);
#endif

	/* turn off device IOV mode */
235
	IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, 0);
G
Greg Rose 已提交
236 237 238 239 240 241 242 243 244 245
	gpie = IXGBE_READ_REG(hw, IXGBE_GPIE);
	gpie &= ~IXGBE_GPIE_VTMODE_MASK;
	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);

	/* set default pool back to 0 */
	vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL);
	vmdctl &= ~IXGBE_VT_CTL_POOL_MASK;
	IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl);
	IXGBE_WRITE_FLUSH(hw);

246 247 248 249 250
	/* Disable VMDq flag so device will be set in VM mode */
	if (adapter->ring_feature[RING_F_VMDQ].limit == 1)
		adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED;
	adapter->ring_feature[RING_F_VMDQ].offset = 0;

G
Greg Rose 已提交
251 252 253 254 255 256
	/* take a breather then clean up driver data */
	msleep(100);

	adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED;
}

E
Emil Tantilov 已提交
257
static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
258
				   u32 *msgbuf, u32 vf)
G
Greg Rose 已提交
259
{
260 261 262
	int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK)
		       >> IXGBE_VT_MSGINFO_SHIFT;
	u16 *hash_list = (u16 *)&msgbuf[1];
G
Greg Rose 已提交
263
	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
264
	struct ixgbe_hw *hw = &adapter->hw;
G
Greg Rose 已提交
265
	int i;
266 267 268
	u32 vector_bit;
	u32 vector_reg;
	u32 mta_reg;
G
Greg Rose 已提交
269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284

	/* only so many hash values supported */
	entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES);

	/*
	 * salt away the number of multi cast addresses assigned
	 * to this VF for later use to restore when the PF multi cast
	 * list changes
	 */
	vfinfo->num_vf_mc_hashes = entries;

	/*
	 * VFs are limited to using the MTA hash table for their multicast
	 * addresses
	 */
	for (i = 0; i < entries; i++) {
285
		vfinfo->vf_mc_hashes[i] = hash_list[i];
G
Greg Rose 已提交
286 287
	}

288 289 290 291 292 293 294
	for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
		vector_reg = (vfinfo->vf_mc_hashes[i] >> 5) & 0x7F;
		vector_bit = vfinfo->vf_mc_hashes[i] & 0x1F;
		mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
		mta_reg |= (1 << vector_bit);
		IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
	}
G
Greg Rose 已提交
295 296 297 298

	return 0;
}

G
Greg Rose 已提交
299 300 301 302 303 304 305 306
static void ixgbe_restore_vf_macvlans(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct list_head *pos;
	struct vf_macvlans *entry;

	list_for_each(pos, &adapter->vf_mvs.l) {
		entry = list_entry(pos, struct vf_macvlans, l);
307
		if (!entry->free)
G
Greg Rose 已提交
308 309 310 311 312 313
			hw->mac.ops.set_rar(hw, entry->rar_entry,
					    entry->vf_macvlan,
					    entry->vf, IXGBE_RAH_AV);
	}
}

G
Greg Rose 已提交
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct vf_data_storage *vfinfo;
	int i, j;
	u32 vector_bit;
	u32 vector_reg;
	u32 mta_reg;

	for (i = 0; i < adapter->num_vfs; i++) {
		vfinfo = &adapter->vfinfo[i];
		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
			hw->addr_ctrl.mta_in_use++;
			vector_reg = (vfinfo->vf_mc_hashes[j] >> 5) & 0x7F;
			vector_bit = vfinfo->vf_mc_hashes[j] & 0x1F;
			mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg));
			mta_reg |= (1 << vector_bit);
			IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
		}
	}
G
Greg Rose 已提交
334 335 336

	/* Restore any VF macvlans */
	ixgbe_restore_vf_macvlans(adapter);
G
Greg Rose 已提交
337 338
}

E
Emil Tantilov 已提交
339 340
static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
			     u32 vf)
G
Greg Rose 已提交
341
{
342 343 344 345
	/* VLAN 0 is a special case, don't allow it to be removed */
	if (!vid && !add)
		return 0;

G
Greg Rose 已提交
346 347 348
	return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add);
}

349
static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
350 351
{
	struct ixgbe_hw *hw = &adapter->hw;
352
	int max_frame = msgbuf[1];
353 354
	u32 max_frs;

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
	/*
	 * For 82599EB we have to keep all PFs and VFs operating with
	 * the same max_frame value in order to avoid sending an oversize
	 * frame to a VF.  In order to guarantee this is handled correctly
	 * for all cases we have several special exceptions to take into
	 * account before we can enable the VF for receive
	 */
	if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
		struct net_device *dev = adapter->netdev;
		int pf_max_frame = dev->mtu + ETH_HLEN;
		u32 reg_offset, vf_shift, vfre;
		s32 err = 0;

#ifdef CONFIG_FCOE
		if (dev->features & NETIF_F_FCOE_MTU)
			pf_max_frame = max_t(int, pf_max_frame,
					     IXGBE_FCOE_JUMBO_FRAME_SIZE);

#endif /* CONFIG_FCOE */
		/*
		 * If the PF or VF are running w/ jumbo frames enabled we
		 * need to shut down the VF Rx path as we cannot support
		 * jumbo frames on legacy VFs
		 */
		if ((pf_max_frame > ETH_FRAME_LEN) ||
		    (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)))
			err = -EINVAL;

		/* determine VF receive enable location */
		vf_shift = vf % 32;
		reg_offset = vf / 32;

		/* enable or disable receive depending on error */
		vfre = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset));
		if (err)
			vfre &= ~(1 << vf_shift);
		else
			vfre |= 1 << vf_shift;
		IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), vfre);

		if (err) {
			e_err(drv, "VF max_frame %d out of range\n", max_frame);
			return err;
		}
	}
400 401

	/* MTU < 68 is an error and causes problems on some kernels */
402 403 404
	if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) {
		e_err(drv, "VF max_frame %d out of range\n", max_frame);
		return -EINVAL;
405 406
	}

407 408 409 410 411 412 413
	/* pull current max frame size from hardware */
	max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS);
	max_frs &= IXGBE_MHADD_MFS_MASK;
	max_frs >>= IXGBE_MHADD_MFS_SHIFT;

	if (max_frs < max_frame) {
		max_frs = max_frame << IXGBE_MHADD_MFS_SHIFT;
414 415 416
		IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs);
	}

417 418 419
	e_info(hw, "VF requests change max MTU to %d\n", max_frame);

	return 0;
420 421
}

E
Emil Tantilov 已提交
422
static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
G
Greg Rose 已提交
423 424
{
	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
425
	vmolr |= (IXGBE_VMOLR_ROMPE |
G
Greg Rose 已提交
426
		  IXGBE_VMOLR_BAM);
427 428 429 430
	if (aupe)
		vmolr |= IXGBE_VMOLR_AUPE;
	else
		vmolr &= ~IXGBE_VMOLR_AUPE;
G
Greg Rose 已提交
431 432 433
	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
}

434 435 436 437 438 439 440 441 442 443 444
static void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, u32 vid, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;

	if (vid)
		IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf),
				(vid | IXGBE_VMVIR_VLANA_DEFAULT));
	else
		IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0);
}

E
Emil Tantilov 已提交
445
static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
G
Greg Rose 已提交
446 447
{
	struct ixgbe_hw *hw = &adapter->hw;
448
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
G
Greg Rose 已提交
449 450

	/* reset offloads to defaults */
451 452 453 454 455 456 457 458 459
	if (adapter->vfinfo[vf].pf_vlan) {
		ixgbe_set_vf_vlan(adapter, true,
				  adapter->vfinfo[vf].pf_vlan, vf);
		ixgbe_set_vmvir(adapter,
				(adapter->vfinfo[vf].pf_vlan |
				 (adapter->vfinfo[vf].pf_qos <<
				  VLAN_PRIO_SHIFT)), vf);
		ixgbe_set_vmolr(hw, vf, false);
	} else {
460
		ixgbe_set_vf_vlan(adapter, true, 0, vf);
461 462 463
		ixgbe_set_vmvir(adapter, 0, vf);
		ixgbe_set_vmolr(hw, vf, true);
	}
G
Greg Rose 已提交
464 465 466 467 468 469 470

	/* reset multicast table array for vf */
	adapter->vfinfo[vf].num_vf_mc_hashes = 0;

	/* Flush and reset the mta with the new values */
	ixgbe_set_rx_mode(adapter->netdev);

471
	hw->mac.ops.clear_rar(hw, rar_entry);
G
Greg Rose 已提交
472 473
}

E
Emil Tantilov 已提交
474 475
static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
			    int vf, unsigned char *mac_addr)
G
Greg Rose 已提交
476 477
{
	struct ixgbe_hw *hw = &adapter->hw;
478
	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
G
Greg Rose 已提交
479 480

	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6);
481
	hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV);
G
Greg Rose 已提交
482 483 484 485

	return 0;
}

G
Greg Rose 已提交
486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540
static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
				int vf, int index, unsigned char *mac_addr)
{
	struct ixgbe_hw *hw = &adapter->hw;
	struct list_head *pos;
	struct vf_macvlans *entry;

	if (index <= 1) {
		list_for_each(pos, &adapter->vf_mvs.l) {
			entry = list_entry(pos, struct vf_macvlans, l);
			if (entry->vf == vf) {
				entry->vf = -1;
				entry->free = true;
				entry->is_macvlan = false;
				hw->mac.ops.clear_rar(hw, entry->rar_entry);
			}
		}
	}

	/*
	 * If index was zero then we were asked to clear the uc list
	 * for the VF.  We're done.
	 */
	if (!index)
		return 0;

	entry = NULL;

	list_for_each(pos, &adapter->vf_mvs.l) {
		entry = list_entry(pos, struct vf_macvlans, l);
		if (entry->free)
			break;
	}

	/*
	 * If we traversed the entire list and didn't find a free entry
	 * then we're out of space on the RAR table.  Also entry may
	 * be NULL because the original memory allocation for the list
	 * failed, which is not fatal but does mean we can't support
	 * VF requests for MACVLAN because we couldn't allocate
	 * memory for the list management required.
	 */
	if (!entry || !entry->free)
		return -ENOSPC;

	entry->free = false;
	entry->is_macvlan = true;
	entry->vf = vf;
	memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN);

	hw->mac.ops.set_rar(hw, entry->rar_entry, mac_addr, vf, IXGBE_RAH_AV);

	return 0;
}

G
Greg Rose 已提交
541 542 543
int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
{
	unsigned char vf_mac_addr[6];
544
	struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
G
Greg Rose 已提交
545 546 547 548 549
	unsigned int vfn = (event_mask & 0x3f);

	bool enable = ((event_mask & 0x10000000U) != 0);

	if (enable) {
J
Joe Perches 已提交
550
		eth_random_addr(vf_mac_addr);
551 552
		e_info(probe, "IOV: VF %d is enabled MAC %pM\n",
		       vfn, vf_mac_addr);
G
Greg Rose 已提交
553 554 555 556 557 558 559 560 561 562
		/*
		 * Store away the VF "permananet" MAC address, it will ask
		 * for it later.
		 */
		memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6);
	}

	return 0;
}

563
static int ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf)
G
Greg Rose 已提交
564 565
{
	struct ixgbe_hw *hw = &adapter->hw;
566 567
	unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses;
	u32 reg, msgbuf[4];
G
Greg Rose 已提交
568
	u32 reg_offset, vf_shift;
569 570 571 572 573 574 575 576 577
	u8 *addr = (u8 *)(&msgbuf[1]);

	e_info(probe, "VF Reset msg received from vf %d\n", vf);

	/* reset the filters for the device */
	ixgbe_vf_reset_event(adapter, vf);

	/* set vf mac address */
	ixgbe_set_vf_mac(adapter, vf, vf_mac);
G
Greg Rose 已提交
578 579 580 581

	vf_shift = vf % 32;
	reg_offset = vf / 32;

582
	/* enable transmit for vf */
G
Greg Rose 已提交
583
	reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset));
584
	reg |= 1 << vf_shift;
G
Greg Rose 已提交
585 586
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg);

587
	/* enable receive for vf */
G
Greg Rose 已提交
588
	reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset));
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
	reg |= 1 << vf_shift;
	/*
	 * The 82599 cannot support a mix of jumbo and non-jumbo PF/VFs.
	 * For more info take a look at ixgbe_set_vf_lpe
	 */
	if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
		struct net_device *dev = adapter->netdev;
		int pf_max_frame = dev->mtu + ETH_HLEN;

#ifdef CONFIG_FCOE
		if (dev->features & NETIF_F_FCOE_MTU)
			pf_max_frame = max_t(int, pf_max_frame,
					     IXGBE_FCOE_JUMBO_FRAME_SIZE);

#endif /* CONFIG_FCOE */
		if (pf_max_frame > ETH_FRAME_LEN)
			reg &= ~(1 << vf_shift);
	}
G
Greg Rose 已提交
607 608
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg);

609 610 611
	/* enable VF mailbox for further messages */
	adapter->vfinfo[vf].clear_to_send = true;

612 613 614 615 616
	/* Enable counting of spoofed packets in the SSVPC register */
	reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset));
	reg |= (1 << vf_shift);
	IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg);

617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717
	/* reply to reset with ack and vf mac address */
	msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
	memcpy(addr, vf_mac, ETH_ALEN);

	/*
	 * Piggyback the multicast filter type so VF can compute the
	 * correct vectors
	 */
	msgbuf[3] = hw->mac.mc_filter_type;
	ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf);

	return 0;
}

static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter,
				 u32 *msgbuf, u32 vf)
{
	u8 *new_mac = ((u8 *)(&msgbuf[1]));

	if (!is_valid_ether_addr(new_mac)) {
		e_warn(drv, "VF %d attempted to set invalid mac\n", vf);
		return -1;
	}

	if (adapter->vfinfo[vf].pf_set_mac &&
	    memcmp(adapter->vfinfo[vf].vf_mac_addresses, new_mac,
		   ETH_ALEN)) {
		e_warn(drv,
		       "VF %d attempted to override administratively set MAC address\n"
		       "Reload the VF driver to resume operations\n",
		       vf);
		return -1;
	}

	return ixgbe_set_vf_mac(adapter, vf, new_mac);
}

static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter,
				 u32 *msgbuf, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	int add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT;
	int vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK);
	int err;

	if (adapter->vfinfo[vf].pf_vlan) {
		e_warn(drv,
		       "VF %d attempted to override administratively set VLAN configuration\n"
		       "Reload the VF driver to resume operations\n",
		       vf);
		return -1;
	}

	if (add)
		adapter->vfinfo[vf].vlan_count++;
	else if (adapter->vfinfo[vf].vlan_count)
		adapter->vfinfo[vf].vlan_count--;

	err = ixgbe_set_vf_vlan(adapter, add, vid, vf);
	if (!err && adapter->vfinfo[vf].spoofchk_enabled)
		hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);

	return err;
}

static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter,
				    u32 *msgbuf, u32 vf)
{
	u8 *new_mac = ((u8 *)(&msgbuf[1]));
	int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >>
		    IXGBE_VT_MSGINFO_SHIFT;
	int err;

	if (adapter->vfinfo[vf].pf_set_mac && index > 0) {
		e_warn(drv,
		       "VF %d requested MACVLAN filter but is administratively denied\n",
		       vf);
		return -1;
	}

	/* An non-zero index indicates the VF is setting a filter */
	if (index) {
		if (!is_valid_ether_addr(new_mac)) {
			e_warn(drv, "VF %d attempted to set invalid mac\n", vf);
			return -1;
		}

		/*
		 * If the VF is allowed to set MAC filters then turn off
		 * anti-spoofing to avoid false positives.
		 */
		if (adapter->vfinfo[vf].spoofchk_enabled)
			ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false);
	}

	err = ixgbe_set_vf_macvlan(adapter, vf, index, new_mac);
	if (err == -ENOSPC)
		e_warn(drv,
		       "VF %d has requested a MACVLAN filter but there is no space for it\n",
		       vf);
	return err;
G
Greg Rose 已提交
718 719 720 721 722
}

static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
	u32 mbx_size = IXGBE_VFMAILBOX_SIZE;
E
Emil Tantilov 已提交
723
	u32 msgbuf[IXGBE_VFMAILBOX_SIZE];
G
Greg Rose 已提交
724 725 726 727 728
	struct ixgbe_hw *hw = &adapter->hw;
	s32 retval;

	retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf);

729
	if (retval) {
730
		pr_err("Error receiving message from VF\n");
731 732
		return retval;
	}
G
Greg Rose 已提交
733 734 735 736 737

	/* this is a message we already processed, do nothing */
	if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK))
		return retval;

738 739 740
	/* flush the ack before we write any messages back */
	IXGBE_WRITE_FLUSH(hw);

G
Greg Rose 已提交
741 742 743 744 745
	/*
	 * until the vf completes a virtual function reset it should not be
	 * allowed to start any configuration.
	 */

746 747
	if (msgbuf[0] == IXGBE_VF_RESET)
		return ixgbe_vf_reset_msg(adapter, vf);
G
Greg Rose 已提交
748 749 750 751 752 753 754 755 756

	if (!adapter->vfinfo[vf].clear_to_send) {
		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
		ixgbe_write_mbx(hw, msgbuf, 1, vf);
		return retval;
	}

	switch ((msgbuf[0] & 0xFFFF)) {
	case IXGBE_VF_SET_MAC_ADDR:
757
		retval = ixgbe_set_vf_mac_addr(adapter, msgbuf, vf);
G
Greg Rose 已提交
758 759
		break;
	case IXGBE_VF_SET_MULTICAST:
760 761 762 763
		retval = ixgbe_set_vf_multicasts(adapter, msgbuf, vf);
		break;
	case IXGBE_VF_SET_VLAN:
		retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf);
G
Greg Rose 已提交
764 765
		break;
	case IXGBE_VF_SET_LPE:
766
		retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf);
G
Greg Rose 已提交
767
		break;
G
Greg Rose 已提交
768
	case IXGBE_VF_SET_MACVLAN:
769
		retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf);
G
Greg Rose 已提交
770
		break;
G
Greg Rose 已提交
771
	default:
772
		e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]);
G
Greg Rose 已提交
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
		retval = IXGBE_ERR_MBX;
		break;
	}

	/* notify the VF of the results of what it sent us */
	if (retval)
		msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK;
	else
		msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK;

	msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS;

	ixgbe_write_mbx(hw, msgbuf, 1, vf);

	return retval;
}

static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 msg = IXGBE_VT_MSGTYPE_NACK;

	/* if device isn't clear to send it shouldn't be reading either */
	if (!adapter->vfinfo[vf].clear_to_send)
		ixgbe_write_mbx(hw, &msg, 1, vf);
}

void ixgbe_msg_task(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 vf;

	for (vf = 0; vf < adapter->num_vfs; vf++) {
		/* process any reset requests */
		if (!ixgbe_check_for_rst(hw, vf))
			ixgbe_vf_reset_event(adapter, vf);

		/* process any messages pending */
		if (!ixgbe_check_for_msg(hw, vf))
			ixgbe_rcv_msg_from_vf(adapter, vf);

		/* process any acks */
		if (!ixgbe_check_for_ack(hw, vf))
			ixgbe_rcv_ack_from_vf(adapter, vf);
	}
}

820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845
void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;

	/* disable transmit and receive for all vfs */
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0);
	IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0);

	IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0);
	IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0);
}

void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter)
{
	struct ixgbe_hw *hw = &adapter->hw;
	u32 ping;
	int i;

	for (i = 0 ; i < adapter->num_vfs; i++) {
		ping = IXGBE_PF_CONTROL_MSG;
		if (adapter->vfinfo[i].clear_to_send)
			ping |= IXGBE_VT_MSGTYPE_CTS;
		ixgbe_write_mbx(hw, &ping, 1, i);
	}
}

846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	if (!is_valid_ether_addr(mac) || (vf >= adapter->num_vfs))
		return -EINVAL;
	adapter->vfinfo[vf].pf_set_mac = true;
	dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf);
	dev_info(&adapter->pdev->dev, "Reload the VF driver to make this"
				      " change effective.");
	if (test_bit(__IXGBE_DOWN, &adapter->state)) {
		dev_warn(&adapter->pdev->dev, "The VF MAC address has been set,"
			 " but the PF device is not up.\n");
		dev_warn(&adapter->pdev->dev, "Bring the PF device up before"
			 " attempting to use the VF device.\n");
	}
	return ixgbe_set_vf_mac(adapter, vf, mac);
}

int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
{
	int err = 0;
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
868
	struct ixgbe_hw *hw = &adapter->hw;
869 870 871 872 873 874 875 876

	if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7))
		return -EINVAL;
	if (vlan || qos) {
		err = ixgbe_set_vf_vlan(adapter, true, vlan, vf);
		if (err)
			goto out;
		ixgbe_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf);
877
		ixgbe_set_vmolr(hw, vf, false);
878
		if (adapter->vfinfo[vf].spoofchk_enabled)
G
Greg Rose 已提交
879
			hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf);
880
		adapter->vfinfo[vf].vlan_count++;
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896
		adapter->vfinfo[vf].pf_vlan = vlan;
		adapter->vfinfo[vf].pf_qos = qos;
		dev_info(&adapter->pdev->dev,
			 "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf);
		if (test_bit(__IXGBE_DOWN, &adapter->state)) {
			dev_warn(&adapter->pdev->dev,
				 "The VF VLAN has been set,"
				 " but the PF device is not up.\n");
			dev_warn(&adapter->pdev->dev,
				 "Bring the PF device up before"
				 " attempting to use the VF device.\n");
		}
	} else {
		err = ixgbe_set_vf_vlan(adapter, false,
					adapter->vfinfo[vf].pf_vlan, vf);
		ixgbe_set_vmvir(adapter, vlan, vf);
897 898
		ixgbe_set_vmolr(hw, vf, true);
		hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf);
899 900
		if (adapter->vfinfo[vf].vlan_count)
			adapter->vfinfo[vf].vlan_count--;
901 902 903 904 905 906 907
		adapter->vfinfo[vf].pf_vlan = 0;
		adapter->vfinfo[vf].pf_qos = 0;
       }
out:
       return err;
}

908
static int ixgbe_link_mbps(struct ixgbe_adapter *adapter)
909
{
910
	switch (adapter->link_speed) {
911 912 913 914 915 916 917 918 919 920 921
	case IXGBE_LINK_SPEED_100_FULL:
		return 100;
	case IXGBE_LINK_SPEED_1GB_FULL:
		return 1000;
	case IXGBE_LINK_SPEED_10GB_FULL:
		return 10000;
	default:
		return 0;
	}
}

922
static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf)
923
{
924 925 926 927 928 929 930 931 932
	struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ];
	struct ixgbe_hw *hw = &adapter->hw;
	u32 bcnrc_val = 0;
	u16 queue, queues_per_pool;
	u16 tx_rate = adapter->vfinfo[vf].tx_rate;

	if (tx_rate) {
		/* start with base link speed value */
		bcnrc_val = adapter->vf_rate_link_speed;
933 934

		/* Calculate the rate factor values to set */
935 936 937 938 939 940 941 942 943
		bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT;
		bcnrc_val /= tx_rate;

		/* clear everything but the rate factor */
		bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK |
			     IXGBE_RTTBCNRC_RF_DEC_MASK;

		/* enable the rate scheduler */
		bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA;
944 945
	}

L
Lior Levy 已提交
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
	/*
	 * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
	 * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported
	 * and 0x004 otherwise.
	 */
	switch (hw->mac.type) {
	case ixgbe_mac_82599EB:
		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x4);
		break;
	case ixgbe_mac_X540:
		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x14);
		break;
	default:
		break;
	}

962 963 964 965 966 967 968 969 970 971
	/* determine how many queues per pool based on VMDq mask */
	queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask);

	/* write value for all Tx queues belonging to VF */
	for (queue = 0; queue < queues_per_pool; queue++) {
		unsigned int reg_idx = (vf * queues_per_pool) + queue;

		IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx);
		IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val);
	}
972 973 974 975
}

void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
{
976
	int i;
977 978

	/* VF Tx rate limit was not set */
979
	if (!adapter->vf_rate_link_speed)
980 981
		return;

982
	if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) {
983 984
		adapter->vf_rate_link_speed = 0;
		dev_info(&adapter->pdev->dev,
985
			 "Link speed has been changed. VF Transmit rate is disabled\n");
986 987 988
	}

	for (i = 0; i < adapter->num_vfs; i++) {
989
		if (!adapter->vf_rate_link_speed)
990 991
			adapter->vfinfo[i].tx_rate = 0;

992
		ixgbe_set_vf_rate_limit(adapter, i);
993 994 995
	}
}

996 997
int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
{
998
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
	int link_speed;

	/* verify VF is active */
	if (vf >= adapter->num_vfs)
		return -EINVAL;

	/* verify link is up */
	if (!adapter->link_up)
		return -EINVAL;

	/* verify we are linked at 10Gbps */
	link_speed = ixgbe_link_mbps(adapter);
	if (link_speed != 10000)
		return -EINVAL;
1013

1014 1015
	/* rate limit cannot be less than 10Mbs or greater than link speed */
	if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed)))
1016 1017
		return -EINVAL;

1018 1019 1020 1021 1022 1023
	/* store values */
	adapter->vf_rate_link_speed = link_speed;
	adapter->vfinfo[vf].tx_rate = tx_rate;

	/* update hardware configuration */
	ixgbe_set_vf_rate_limit(adapter, vf);
1024 1025

	return 0;
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
int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	int vf_target_reg = vf >> 3;
	int vf_target_shift = vf % 8;
	struct ixgbe_hw *hw = &adapter->hw;
	u32 regval;

	adapter->vfinfo[vf].spoofchk_enabled = setting;

	regval = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg));
	regval &= ~(1 << vf_target_shift);
	regval |= (setting << vf_target_shift);
	IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), regval);

	if (adapter->vfinfo[vf].vlan_count) {
		vf_target_shift += IXGBE_SPOOF_VLANAS_SHIFT;
		regval = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg));
		regval &= ~(1 << vf_target_shift);
		regval |= (setting << vf_target_shift);
		IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), regval);
	}

	return 0;
}

1054 1055 1056 1057 1058 1059 1060 1061
int ixgbe_ndo_get_vf_config(struct net_device *netdev,
			    int vf, struct ifla_vf_info *ivi)
{
	struct ixgbe_adapter *adapter = netdev_priv(netdev);
	if (vf >= adapter->num_vfs)
		return -EINVAL;
	ivi->vf = vf;
	memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN);
1062
	ivi->tx_rate = adapter->vfinfo[vf].tx_rate;
1063 1064
	ivi->vlan = adapter->vfinfo[vf].pf_vlan;
	ivi->qos = adapter->vfinfo[vf].pf_qos;
1065
	ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled;
1066 1067
	return 0;
}